Academic literature on the topic 'Clogging detection'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Clogging detection.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Clogging detection":
1
Liu, Huaqing, Zhen Hu, Shiying Song, Jian Zhang, Lichao Nie, Hongying Hu, Fengmin Li, and Zhengyu Liu. "Quantitative Detection of Clogging in Horizontal Subsurface Flow Constructed Wetland Using the Resistivity Method." Water 10, no. 10 (September 26, 2018): 1334. http://dx.doi.org/10.3390/w10101334.
Abstract:
Substrate clogging seriously affects the lifetime and treatment performance of subsurface flow constructed wetlands (SSF CWs), and the quantitative detection of clogging is the key challenge in the management of substrate clogging. This paper explores the feasibility of the resistivity method to detect the clogging degree of an SSF CW. The clogged substrate was found to have a high water-holding capacity, which led to low apparent resistivity in the draining phase. On the basis of the resistivity characteristics, clogging quantification was performed with a standard laboratory procedure, i.e., the Wenner method used in a Miller Soil Box. The apparent resistivity to sediment fraction (v/v) (ARSF) model was established to evaluate the degree of clogging from the apparent resistivity. The results showed that the ARSF model fit well with the actual values (linear slope = 0.986; R-squared = 0.98). The methods for in situ resistivity detection were applied in a lab-scale horizontal subsurface flow constructed wetland (HSSF CW). Combined with the ARSF model, the two-probe method demonstrated high accuracy for clogging quantification (relative error less than 9%). These results suggest that the resistivity method is a reliable and feasible technique for in situ detection of clogging in SSF CWs.
2
Zhu, Sha, Ying Xu, Chunyang Zu, Yuexiang Li, and Zifeng Yu. "Study on the method of detecting oil pipeline clogging by fluid oscillation theory." Journal of Physics: Conference Series 2418, no. 1 (February 1, 2023): 012039. http://dx.doi.org/10.1088/1742-6596/2418/1/012039.
Abstract:
Abstract In order to solve the problem of pipeline clogging detection, a mathematical model of pipeline clogging detection is established by applying fluid oscillation theory. The amplitude of each component harmonic in different periods is expressed by Fourier series, and then the clogging attenuation parameters of each harmonic are obtained. According to the ratio of harmonic of two separate components and the plugging attenuation parameter, the plugging position and magnitude are determined respectively. Through the analysis of numerical simulation and experimental results, it can be concluded that the method of using fluid oscillation theory to detect pipeline blockage is correct.
3
Vong, Chin Nee, and Peter Ako Larbi. "Development and Prototype Testing of an Agricultural Nozzle Clog Detection Device." Transactions of the ASABE 64, no. 1 (2021): 49–61. http://dx.doi.org/10.13031/trans.13519.
Abstract:
HighlightsPrototypes of an agricultural nozzle clog detection system (for 18 nozzles) have been successfully developed.Spray quality characteristics (droplet size, pattern, and coverage) were not significantly affected when testing the device with extended-range nozzles (TeeJet XR8004).Most of the spray quality characteristics were significantly affected when testing the device with ultra low-drift nozzles (John Deere PSULDQ2004).Abstract. Agricultural nozzles are the main components that perform the spraying of agrochemicals, and their proper functionality is a key element for uniform spray application on crops. Because nozzles have small orifices, they can become clogged when there is debris from the agrochemical in the tank. Nozzle clogging during spray application results in poor pest and weed management and increased cost for re-spraying the affected crop row. Measures used to prevent nozzles from clogging include using screens or strainers to filter out debris before it reaches the nozzle tip, as well as performing regular checks on the nozzles. However, nozzle clogging still occurs during spraying despite the precautions taken. Thus, a device that can detect nozzle clogging during spraying is necessary to enable a quicker response that will ensure uniform application across each row of the crop. A novel, patented device for detecting clogged nozzles that is externally attachable to each nozzle on a sprayer boom was developed in the Precision Application Technology Lab at Arkansas State University. The main objective of this article is to present a general description of this prototype nozzle clog detection device and the nozzle clog detection system. Spray droplet size and pattern tests under controlled conditions and spray coverage tests under field conditions were conducted with and without the device to determine if there were significant differences in droplet size, spray pattern, or spray coverage between using and not using the device. The tests demonstrated that this new technology has potential for detecting clogged nozzles without significantly influencing spray quality for extended-range nozzles but not for ultra low-drift nozzles. To increase the reliability of the performance of this new technology, further improvements in the design need to be considered. Keywords: Clogged nozzle, Detection, Droplet size, Prototype device, Spray coverage, Spray pattern.
4
Diniz, Ana P. M., Patrick M. Ciarelli, Evandro O. T. Salles, and Klaus F. Coco. "Long short-term memory neural networks for clogging detection in the submerged entry nozzle." Decision Making: Applications in Management and Engineering 5, no. 1 (March 20, 2022): 154–68. http://dx.doi.org/10.31181/dmame0313052022d.
Abstract:
The clogging in the Submerged Entry Nozzle (SEN), responsible for controlling the steel flow in continuous casting, is one of the main problems faced by steelmaking process, since it can increase the frequency of interruptions in the operation for the maintenance and/or exchange of its equipment. Although it is a problem inherent to the process, not identifying the clogging can result in losses associated with the process yield, as well as compromising the product quality. In order to detect the occurrences of clogging in a real steel industry from historical data of process variables, in this paper, different models of Long Short-Term Memory (LSTM) neural networks were tested and discussed. The overall performance of the classifiers developed here showed very promising results in real data with class imbalance.
5
Johansson, A., and A. Medvedev. "Detection of incipient clogging in pulverized coal injection lines." IEEE Transactions on Industry Applications 36, no. 3 (2000): 877–83. http://dx.doi.org/10.1109/28.845065.
6
Abouelazayem, Shereen, Ivan Glavinić, Thomas Wondrak, and Jaroslav Hlava. "Switched MPC Based on Clogging Detection in Continuous Casting Process." IFAC-PapersOnLine 53, no. 2 (2020): 11491–96. http://dx.doi.org/10.1016/j.ifacol.2020.12.589.
7
Becker, Vincent, Thilo Schwamm, Sven Urschel, and Jose Alfonso Antonino-Daviu. "Fault Investigation of Circulation Pumps to Detect Impeller Clogging." Applied Sciences 10, no. 21 (October 27, 2020): 7550. http://dx.doi.org/10.3390/app10217550.
Abstract:
Pumps have a wide range of applications. Methods for fault detection of motors are increasingly being used for pumps. In the context of this paper, a test bench is built to investigate circulation pumps for faults. As a use case, the fault of impeller clogging was first measured and then examined with the help of motor current signature analysis. It can be seen that there are four frequencies at which there is an increase in amplitude in case of a fault. The sidebands around the supply frequency are in particular focus. The clogging of three and four of a total of seven channels leads to the highest amplitudes at the fault frequencies. The efficiency is reduced by 9 to 15% in case of faulty operation. These results indicate that the implementation of fault detection algorithms on the pump electronics represents added value for the pump operator. Furthermore, the results can be transferred to other applications.
8
Bai, Xue-Dong, Wen-Chieh Cheng, Brian B. Sheil, and Ge Li. "Pipejacking clogging detection in soft alluvial deposits using machine learning algorithms." Tunnelling and Underground Space Technology 113 (July 2021): 103908. http://dx.doi.org/10.1016/j.tust.2021.103908.
9
Qiu, Xuefeng, Jiandong Wang, Haitao Wang, Chuanjuan Wang, Yuechao Sun, and Guangyong Li. "Elimination of Clogging of a Biogas Slurry Drip Irrigation System Using the Optimal Acid and Chlorine Addition Mode." Agriculture 12, no. 6 (May 28, 2022): 777. http://dx.doi.org/10.3390/agriculture12060777.
Abstract:
As an emerging contaminant, the clogging substances of emitters in biogas slurry drip irrigation systems affect the efficient return and utilization of biogas slurry to the field to a great extent. This can be prevented using acid and chlorination as engineering measures. Through a hydraulic performance test and sampling detection and analysis, under the same acid addition conditions (pH = 5.5–6.0), three chlorine addition concentrations (0, 1–3, and 4–9 mg/L) and four chlorine addition cycles (6, 10, 14, and 20 days) were tested, aimed to clarify the influence of acid and chlorine addition parameters (chlorine adding cycle, chlorine adding concentration, etc.) on the anti-clogging performance of emitters in biogas slurry drip irrigation system. The results showed that compared with no acid and chlorination treatment (CK), only acid and a reasonable combination of acid and chlorination can significantly reduce the probability of serious and complete clogging of biogas slurry drip irrigation emitters, and they can stabilize the relative average flow of emitters by more than 75%. The measures of adding acid and chlorine change the distribution characteristics of clogging substances at the front and rear of the drip irrigation belt. Furthermore, they promote the migration of clogging substances to the rear of the drip irrigation belt, facilitating the clogging of emitters located thereat. The measures of acid addition and sequential addition of acid and chlorine significantly inhibit the growth of an extracellular polymer in the emitter, and the effect of inhibiting the increase in extracellular polymer concentrations is relatively poor when the acid addition period is excessively long or short. There exists a negative correlation between the extracellular polymer content in the emitter and the change in the emitter flow. Based on the obtained results, to ensure excellent anti-clogging performance of biogas slurry drip irrigation systems, for acid-only treatment measures, the acid dosing cycle is recommended to be 10 days. When acid and chlorination measures are implemented sequentially, the acid chlorination cycle is recommended to be 14 and 10 days when the chlorine concentration is 1–3 and 4–9 mg/L, respectively. This study has important scientific significance and practical value for the establishment of long-term operation management and protection technologies of large-scale biogas slurry drip irrigation systems.
10
Ibrahim, Najihah, Fadratul Hafinaz Hassan, Nor Muzlifah Mahyuddin, and Noorhazlinda Abd Ra. "Cellular Automaton based Fire Spreading Simulation in Closed Area: Clogging Region Detection." International Journal of Engineering & Technology 7, no. 4.44 (December 1, 2018): 37. http://dx.doi.org/10.14419/ijet.v7i4.44.26859.
Abstract:
Fire spreading is one of the visualization techniques used for re-enacting or envisions the fire incidents for conducting the post-incidents’ responses and analysing the incidents for post-mortem purposes. There are several current researches on the fire spreading incidents that involve the construction of fire spreading simulation which has focusing on the fire development, smoke control, the prediction of temperature distribution during the fire spreading, emergency response’s plans and post-fire damage assessment. However, there are more features need to be explored in the fire spreading simulation and also the pedestrians movement of the affected incident’s area for the future space design development, arrangement and structural improvement that are impactful towards human safety and also useful for the justification and prediction on the pedestrian survival rate during any panic situations. Hence, this research has focusing on the features of realistic scaling of the spatial layout and implementing the Cellular Automata (CA) approach for imitating the near-realistic pedestrian self-organizing movement and fire spreading characteristics at the microstructure level for designing the heat map of the affected area to show the clogging region in the spatial layout while constructing a reliable prediction on the pedestrian survival rate. This clogging region mapping will be useful for finding the existing issues that lead towards high casualties. Based on the experiments and observations, the heat map of the affected area showed the heavy congestions happened specifically near to the ingress/ egress points and narrow pathways that had affected the pedestrian flow rate and caused the 75% of the 352 pedestrians in the spatial layout to burn and die during the fire simulation by unintentionally taking an extra of 43.85 seconds more than the total fire spreading time (13.42 seconds) to evacuate from the closed area building.
Dissertations / Theses on the topic "Clogging detection":
1
Zhang, Yueqian. "Resource Clogging Attacks in Mobile Crowd-Sensing: AI-based Modeling, Detection and Mitigation." Thesis, Université d'Ottawa / University of Ottawa, 2020. http://hdl.handle.net/10393/40082.
Abstract:
Mobile Crowdsensing (MCS) has emerged as a ubiquitous solution for data collection from embedded sensors of the smart devices to improve the sensing capacity and reduce the sensing costs in large regions. Due to the ubiquitous nature of MCS, smart devices require cyber protection against adversaries that are becoming smarter with the objective of clogging the resources and spreading misinformation in such a non-dedicated sensing environment. In an MCS setting, one of the various adversary types has the primary goal of keeping participant devices occupied by submitting fake/illegitimate sensing tasks so as to clog the participant resources such as the battery, sensing, storage, and computing. With this in mind, this thesis proposes a systematical study of fake task injection in MCS, including modeling, detection, and mitigation of such resource clogging attacks.
We introduce modeling of fake task attacks in MCS intending to clog the server and drain battery energy from mobile devices. We creatively grant mobility to the tasks for more extensive coverage of potential participants and propose two take movement patterns, namely Zone-free Movement (ZFM) model and Zone-limited Movement (ZLM) model. Based on the attack model and task movement patterns, we design task features and create structured simulation settings that can be modified to adapt different research scenarios and research purposes.
Since the development of a secure sensing campaign highly depends on the existence of a realistic adversarial model. With this in mind, we apply the self-organizing feature map (SOFM) to maximize the number of impacted participants and recruits according to the user movement pattern of these cities. Our simulation results verify the magnified effect of SOFM-based fake task injection comparing with randomly selected attack regions in terms of more affected recruits and participants, and increased energy consumption in the recruited devices due to the illegitimate task submission.
For the sake of a secure MCS platform, we introduce Machine Learning (ML) methods into the MCS server to detect and eliminate the fake tasks, making sure the tasks arrived at the user side are legitimate tasks. In our work, two machine learning algorithms, Random Forest and Gradient Boosting are adopted to train the system to predict the legitimacy of a task, and Gradient Boosting is proven to be a more promising algorithm. We have validated the feasibility of ML in differentiating the legitimacy of tasks in terms of precision, recall, and F1 score. By comparing the energy-consuming, effected recruits, and impacted candidates with and without ML, we convince the efficiency of applying ML to mitigate the effect of fake task injection.
2
Mohamadi, Parian Sadat. "Système innovant de détection du colmatage des filtres à air basé sur les e-textiles." Electronic Thesis or Diss., Centrale Lille Institut, 2023. http://www.theses.fr/2023CLIL0012.
Abstract:
Dans cette étude, des nanofibres en polyuréthane thermoplastique (TPU) ont été fabriquées en optimisant les paramètres d'électrofilage. Afin de rendre les membranes conductrices, l'encre de carbone a été imprimée sur la surface des membranes de nanofibres de TPU en utilisant différents motifs. Des tests mécaniques, des mesures électromécaniques et des tests cycliques ont démontré des propriétés mécaniques adaptées, des variations de résistance lors de l'étirement et une répétabilité des performances du capteur.Afin d'optimiser les capacités du capteur, des membranes avec des trous structurés ont été fabriquées pour réduire la perte de charge. Ensuite, la perte de charge et la variation de résistance des capteurs avec différents motifs d'impression ont été mesurées dans un tunnel de ventilation. La comparaison avec des filtres M5 a montré que la perte de charge de ces membranes structurées imprimées était similaire à celle des filtres à air et n'entraînait pas d'augmentation de la perte de charge du système. De plus, la variation de résistance du capteur sous différentes vitesses d'air a indiqué une haute sensibilité. En conclusion, cette étude a développé avec succès une technique facile et évolutive pour fabriquer des capteurs textiles permettant de détecter la vitesse de l'air dans les filtres à airIn this study, thermoplastic polyurethane (TPU) nanofibers were fabricated by optimizing electrospinning parameters. In order to make the membranes conductive, the carbon ink was printed on the surface of TPU nanofibers membranes using different patterns. Mechanical tests, electromechanical measurements, and cycle testing demonstrated suitable mechanical properties, resistance changes during stretching, andrepeatability of the sensor performance. To optimize the sensor ability, membranes with structured holeswere fabricated to minimize the pressure drop. Then, the pressure drop and resistance change of the sensorswith various printing patterns were measured in a ventilation tunnel. Comparison with M5 filters showedthat the pressure drop of these printed structured membranes was similar to air filters, and did not cause anincrease in the pressure drop of the system. Moreover, the resistance change of the sensor under differentair velocities indicated high sensitivity. In conclusion, this study successfully developed a facile andscalable technique to fabricate textile sensors for detecting air velocity in air filters
Book chapters on the topic "Clogging detection":
1
Kaur, Kuljit, and Harpreet Kaur. "Removal of Microplastic Contaminants from Aquatic Environment." In Microplastic Pollution: Causes, Effects and Control, 69–92. BENTHAM SCIENCE PUBLISHERS, 2023. http://dx.doi.org/10.2174/9789815165104123010007.
Abstract:
Microplastics (MPs) contamination has recently been recognized as a serious global concern for global food security and modern society's well-being due to its widespread presence in the aquatic and terrestrial environment. According to a growing number of reports, micro- and nanosized plastic components have been discovered in nearly every part of the world, from the bottom of the ocean to the mountain top. Microplastics have become prevalent in the environment due to the gradual disposal of plastic waste, a lack of conventional detection processes with particular removal techniques, and a slow disposal rate. By adsorbing various heavy metals, pathogens, and other chemical additives frequently utilised in the production of raw plastic, microplastics have been shown to work as potential vectors. At the tertiary level of the food chain, microplastics are consumed by marine organisms such as fish and crustaceans, and then by humans. This phenomenon is responsible for clogging digestive systems, disrupting digestion, and ultimately reducing the reproductive growth of entire living species. As a result of these repercussions, microplastics have become a growing concern as a new possible risk, demanding the management of microplastics in aquatic media. This review chapter gives a comprehensive overview of existing and newly developed technologies for detecting and removing microplastics from aquatic environments in order to minimise the ultimate possible impact on aquatic habitats.
2
Hahn Schlam, Federico, and Fermín Martínez Solís. "WSN System Warns Producer When Micro-Sprinklers Do Not Work in Fruit Trees." In Nut Crops - New Insights [Working Title]. IntechOpen, 2022. http://dx.doi.org/10.5772/intechopen.106023.
Abstract:
Salts in the irrigation water cause micro-sprinklers to clog. Farmers find it difficult to detect sprinkler clog due to the great number of trees grown in commercial orchards, causing a reduction in yield and timing problems. In this article, IoT can support farmers with daily soil moisture detection. A wireless sensor network, WSN was developed to warn the farmer from micro-sprinkling clogging. Trees were gathered into groups of 9 trees, where the central tree holds the master microcontroller and the other eight trees presented slave microcontrollers (nodes). The system uses BLE (Bluetooth Low Energy) to communicate between the master microcontroller by BLE. A second WSN using lasers was also tested but resulted to be a little more expensive. Soil moisture sensor performance against corrosion and current consumption was analyzed being the best sensors the V1.2 capacitance probe and the sprinkler-encoder one. When micro-sprinklers did not apply water to a tree, its number was transmitted via LoRa from the master to the producer\'s smartphone to warn him/her. A hexacopter was used to detect canopy stress from a height of 30 m, but only after 7 days of water removal did the NDVI indexes detect it.
Conference papers on the topic "Clogging detection":
1
Beck, David, Florian Brokhausen, and Paul Uwe Thamsen. "Time-Resolved Measurements for the Detection of Clogging Mechanisms." In ASME 2022 Fluids Engineering Division Summer Meeting. American Society of Mechanical Engineers, 2022. http://dx.doi.org/10.1115/fedsm2022-86961.
Abstract:
Abstract The effects of clogging in pumps are manifold and change over time. This is demonstrated with time-resolved observations of the operating data on a test rig at the chair of fluid system dynamics of the Technische Universität Berlin. On the test rig, the head, flow, power consumption and efficiency of different pumps operating with artificial wastewater are recorded. In the data, different clogging behavior reflect in the operating parameters. There are three major clogging-induced characteristics to be differentiated in the time-resolved measurements. For some aggregates there is a rapid drop in the hydraulic parameters right from the start due to initial clogging, with following stagnating performance. This is showcased on a semi-open two-channel impeller, where efficiency drops by 40 % at the very beginning of the measurement and subsequently stagnates. In other cases, like demonstrated here on a closed two-channel impeller, the operating parameters decline continuously over the entire measurement period due to increasing clogging. In the showcased example, the efficiency drops by over 40% in the first six minutes of the measurement due to initial clogging and keeps declining till the end for another 6%. Lastly, there are cases where self-cleansing mechanisms are identified. It is further shown that this phenomenon also highly varies in its timing and hydraulic effects. Finally, it is concluded that all operating parameters must be monitored to generate sufficient knowledge about the clogging behavior of a given aggregate. Additionally, longer observation times are necessary to sufficiently identify effects like the self-cleansing of an impeller.
2
Cowart, Jim, Patrick Moore, Harrison Yosten, Leonard Hamilton, and Dianne Luning Prak. "Diesel Engine Acoustic Emission Airflow Clogging Diagnostics With Machine Learning." In ASME 2018 Internal Combustion Engine Division Fall Technical Conference. American Society of Mechanical Engineers, 2018. http://dx.doi.org/10.1115/icef2018-9601.
Abstract:
A diesel engine electrical generator set (’gen-set’) was instrumented with in-cylinder indicating sensors as well as acoustic emission microphones near the engine. Air filter clogging was emulated by progressive restriction of the engine’s inlet air flow path during which comprehensive engine and acoustic data were collected. Fast Fourier Transforms (FFTs) were analyzed on the acoustic data. Dominant FFT peaks were then applied to supervised machine learning neural network analysis with MATLAB based tools. The progressive detection of the air path clogging was audibly determined with correlation coefficients greater than 95% on test data sets for various FFT minimum intensity thresholds. Further, unsupervised machine learning Self Organizing Maps (SOMs) were produced during normal-baseline operation of the engine. Application of the degrading air flow engine sound data was then applied to the normal-baseline operation SOM. The quantization error of the degraded engine data showed clear statistical differentiation from the normal operation data map. This unsupervised SOM based approach does not know the engine degradation behavior in advance, yet shows clear promise as a method to monitor and detect changing engine operation. Companion in-cylinder combustion data additionally shows the degrading nature of the engine’s combustion with progressive airflow restriction (richer and lower density combustion).
3
Kim, Tae Yoon, and Young-Ho Cho. "An Electrical Particle Velocity Profiler for In-Channel Clogging Detection and Flow Pattern Characterization." In TRANSDUCERS 2007 - 2007 International Solid-State Sensors, Actuators and Microsystems Conference. IEEE, 2007. http://dx.doi.org/10.1109/sensor.2007.4300245.
4
Choudhari, Sahil J., Sujay B. J., Swarit Anand Singh, and K. A. Desai. "Utilizing Vision-Based Object Detection Algorithms in Recognizing Uncommon Operating Conditions for CNC Milling Machine." In ASME 2023 18th International Manufacturing Science and Engineering Conference. American Society of Mechanical Engineers, 2023. http://dx.doi.org/10.1115/msec2023-105311.
Abstract:
Abstract Although Computer Numerical Control (CNC) machines were designed to perform tasks with the least human intervention, operator involvement is mandatory to ensure fault-free operations. Numerous technological solutions utilizing Artificial Intelligence, sensor fusion, Internet of Things (IoT), machine vision, etc., have been developed for process, component, and machine monitoring to impart smartness and autonomous operating abilities. The primary focus of these solutions is to monitor process faults such as tool wear, chatter, static deflections, and cutting forces to assist the operator in minimizing the consequences. The present work develops a vision-based solution for identifying uncommon process abnormalities like improper coolant flow, chip clogging, and tool breakage during CNC milling. The proposed solution replicates the task of a machine operator in identifying these faults and assists in fault-free operations. The study explores the feasibility of utilizing classical and deep learning-based object detection algorithms while developing these solutions. The classical image processing algorithm is ineffective during dynamic process conditions. The deep learning-based algorithm, with an average precision of about 0.75, showed proficiency in abnormalities detection. A Graphical User Interface (GUI) has been developed and integrated with the CNC milling machine to provide an interactive in-process monitoring tool. It is demonstrated that the proposed solution can reduce dependence on a machine operator while monitoring these faults.
5
Choudhari, Sahil J., Swarit Anand Singh, Aitha Sudheer Kumar, and K. A. Desai. "Machine Setup Abnormality Detection Using Machine Vision and Deep Learning." In ASME 2022 17th International Manufacturing Science and Engineering Conference. American Society of Mechanical Engineers, 2022. http://dx.doi.org/10.1115/msec2022-85519.
Abstract:
Abstract Machine tools can perform manufacturing operations autonomously with minimal involvement of machine operators. However, significant human expertise is required while machine setup to minimize machine faults, downtime, and scrap parts for achieving better productivity. The machine setup involves activities such as the presence/absence of a correct cutting tool in the spindle, adequate placement of workpiece on the fixture, ensuring proper coolant flow, clogging of chips, etc. The present machine shops employ skilled human operators to perform these tasks with a checklist for ensuring completeness. The outcomes of the process are dependent on the judgment, consistency, and skills of the operator. Machine vision is considered a low-cost, low-error, and higher consistency substitute for skilled humans in industrial processes involving repetition or fatiguing tasks. The existing machine vision systems developed for dimension measurement or surface defect detection application cannot detect machine setting abnormalities due to the distinct requirements. The present work explores the development of a robust algorithm by augmenting machine vision with the deep learning algorithm You Only Look Once (YOLO) to directly extract features from the captured images. The object detection algorithm based on YOLO-v2 and ResNet-50 is implemented to detect and segregate the elements of interest from different shop-floor images. The algorithm is trained using labeled image datasets generated for several machine setup abnormalities. An interactive Graphical User Interface (GUI) is developed and integrated with the model to implement the proposed framework on the manufacturing shop floor. The developed system was implemented to detect machine setup abnormalities by considering different case studies. The study demonstrated robust detection abilities of the algorithm, offering a potential solution to minimize dependence on human operators for machine setup abnormalities.
6
Moore, Patrick, Dianne Luning Prak, Len Hamilton, and Jim Cowart. "Diesel Engine Acoustic Diagnostics With Machine Learning During Various Degradation Modes." In ASME 2019 Internal Combustion Engine Division Fall Technical Conference. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/icef2019-7120.
Abstract:
Abstract A diesel engine electrical generator set (‘gen-set’) was instrumented with an in-cylinder pressure indicating system as well as an acoustic emission sensor near the engine. Air filter clogging, rocker arm gap and fuel cetane changes were applied during which engine combustion and acoustic data were collected. Fast Fourier Transforms (FFTs) were analyzed on the acoustic data. FFT data were then applied to categorical supervised machine learning neural network analysis with MATLAB based tools. The detection of the various degradation modes was audibly determined with correlation coefficients greater than 99% on test data. Next, an unsupervised machine learning Self Organizing Map (SOM) was produced during normal-baseline operation of the engine. Application of the degraded mode engine sound data from operation with the various faults were then applied to the normal-baseline SOM. The quantization error of the various degraded engine data showed clear statistical differentiation from the normal operation data map. This unsupervised SOM based approach does not know the engine degradation behavior in advance, yet shows promise as a method to monitor and detect changing engine operation. Companion in-cylinder combustion data shows how changing combustion characteristics result in emitted sound differences.
7
Kumar, Ankit, Amit Priyadarshan, and Pragadeesh K. Sekar. "Monitoring Mechanical Equipment on an Offshore Rig with Contrastive Learning on Acoustic Features." In ADIPEC. SPE, 2022. http://dx.doi.org/10.2118/211145-ms.
Abstract:
Abstract Mechanical equipment, operating in the oil and gas industry produces a wide range of sounds, often culminating in noise. A functional equipment creates a standard sound, while malfunctioning equipment creates an anomalous sound. In this paper, we propose an application of a contrastive learning algorithm to detect anomalous sound amidst industrial noise, which in turn helps in the identification of the malfunctioning equipment on an offshore rig. The recent success of contrastive learning algorithms to detect novelty in visual representation has inspired our work. We hypothesise that for most of its lifetime, equipment operates normally. Instances of malfunction that produce anomalous sound and hazardous consequences are rare in their defined lifetime. To this end, we implement a contrastive learning algorithm to identify similarities between audio clips using 10-second length normal-audio clips collected from 6 different equipment for training purposes. It extracts local and global features from the augmented audio clips and presents them in latent space, where the loss function differentiates between normal and anomalous sound. Finally, we input normal audio and anomalous audio into the algorithm. The performance of the proposed algorithm is measured using Receiver-Operating-Curve - Area-Under-Curve (ROC-AUC) (Koizumi et al., 2020; Nunes, 2021)[5]. It successfully differentiates normal and anomalous audio to achieve an average ROC-AUC of 0.77 on the scale (0-1). 26092 audio clips of normal equipment sound and 6065 audio clips of anomalous sound from Valve, pump, fan, slide-rail etc., are used to perform the proposed experiment. Diverse industrial anomalies produced by unbalanced-voltage change, clogging, leaking, contamination, loose belt, no grease etc., are present in the dataset. The proposed methodology of contrastive learning consists of a data-augmentation module followed by an encoder and a Neural Network (NN). Data augmentation transforms the input audio clip to ensure robust performance. The encoder extracts the features from audio clips and projects them in the space of contrastive loss function with the help of NN. Automatic failure detection using Artificial Intelligence is essential for Industry 4.0. Prompt decision by monitoring sound produced by mechanical equipment holds immense potential for asset maintenance in the petroleum industry. This paper is one of the first instances wherein the application of contrastive learning for the maintenance of mechanical equipment has been demonstrated. The proposed method is a unique approach towards anomaly detection using acoustic-features and it significantly reduces human intervention in hazardous and hard-to-reach environments.
8
Nnanna, A. G. Agwu, Chenguang Sheng, Kimberly Conrad, and Greg Crowley. "Performance Assessment of Pre-Filtration Strainer of an Ultrafiltration Membrane System by Particle Size Analysis." In ASME 2015 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2015. http://dx.doi.org/10.1115/imece2015-53447.
Abstract:
One of the industrial applications of ultrafiltration membrane system is water purification and wastewater treatment. Membranes act as physical barriers by eliminating particles such as pollen, yeast, bacteria, colloids, viruses, and macromolecules from feed water. The effectiveness of the membrane to separate particles is determined by its molecular weight cut-off and feed water characteristics. Typically, pre-filtration strainers are installed upstream of an ultrafiltration membrane system to separate large particles from the flow stream. The criteria for selection of the strainer pore size is unclear and is often determined by the feed water average particle size distribution. This paper is motivated by the hydraulic loading failure of a 125 μm strainer by average feed water particle size of 1.6 μm when the volumetric flow is at or greater than 40% of the rated design flow capacity. The objective of this paper are to: a) determine if the feed particle size distribution is a sufficient parameter for selection of pre-filtration strainer, b) evaluate the effect of feed flow velocity on strainer performance, and c) enhance strainer performance using vortex generator. In this experimental study, a Single Particle Optical Sensing, Accusizer, was used to analyze particle size distribution of five water samples collected at strainer feed, strainer filtrate, and strainer backwash. All samples were analyzed using a lower detection limit of 0.5 μm. In order to capture more counts of the larger particles present in the sample, a second analysis was done for each sample at a higher detection limit, 5.09 μm for feed sample, and 2.15 μm for the rest of the samples. Particle size data based on individual detection limits were statistically combined to generate comprehensive blended results of total number and total volume. The volume was determined based on assumption that each particle is spherically shaped. The Particle Size Distribution Measurement Accuracy is ±0.035 μm. Results showed that the feed particle size diameter and volume was insufficient to determine strainer size. Particle size distribution is needed at the feed, filtrate, and backwash to evaluate the strainer particle separation efficiency. It was observed that the total particle count in the filtrate (4.4 × 106) was an order of magnitude higher than the feed (3.2 × 105). Specifically, the total count for particles with diameter less than 7.22 μm were higher in the filtrate while larger particle size ≥ 7.22 μm were more in the feed stream. It appears that the large particles in the feed breaks down into smaller particles at the strainer interface and the small particles (≤ 7.22μm) passed through the pore into the filtrate. The particle breakdown, detachment of particles in the strainer pore into the filtrate, and particle to particle interactions are enhanced by increase in flow velocity hence increasing the hydrodynamic shear that acts on attached particles. A vortex generator inserted in to the strainer reduced pore clogging and pressure drop.
9
Tan, Yongwen, Yang Chen, Andrew W. Peterson, and Mehdi Ahmadian. "Monitoring and Detecting Fouled Ballast Using Forward-Looking Infrared Radiometer (FLIR) Aerial Technology: Possibilities and Limitations." In 2019 Joint Rail Conference. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/jrc2019-1327.
Abstract:
This paper examines the feasibility and limitations of Forward Looking Infrared Radiometer (FLIR) Aerial Technology for detecting fouled ballast. The method is intended to provide an efficient and ready-to-use approach that can help the railroads detect fouled ballast in their early stages. Ballast fouling commonly occurs as a result of fine particles clogging off water passage through them. Subsequently, this results in trapped water that often results in poor foundation strength, rotting of the ties, and other ill effects. This study includes a novel approach to evaluate the railway ballast fouling by using thermal imaging techniques. In particular, the thermal characteristics of clean and fouled ballast are studied using FLIR cameras that can be used onboard rolling stock, Hyrail trucks, or drones. Laboratory tests are primarily performed to measure the surface temperature changing rate of clean and fouled ballast in response to ambient temperature changes. For the purpose of laboratory testing, the camera is set up in stationary and moving configurations. The test results indicate that clean and fouled ballast have different thermal characteristics. In particular, different thermal patterns are obtained during naturally-occurring daily temperature change. The test results also indicate that the FLIR cameras can be used on a moving platform for quick scanning of thermal images of the ballast that could be used for assessing the early stage of fouling.
10
Hosseini, SayedMohammad, Yongwen Tan, and Mehdi Ahmadian. "Forward-Looking Infrared Radiometry (FLIR) Application for Detecting Ballast Fouling." In 2020 Joint Rail Conference. American Society of Mechanical Engineers, 2020. http://dx.doi.org/10.1115/jrc2020-8032.
Abstract:
Abstract This paper is intended to assess the practical aspects of the previously proposed approach for detecting railroad ballast fouling using an off-the-shelf Forward-Looking Infrared Radiometry (FLIR) Technology. FLIR is among the technologies that are becoming more prevalent in railroad applications [1,2]. The method discussed in this paper takes advantage of the temperature differences measured by the FLIR camera between the top surface of clean and partially fouled ballast samples as an indicator of fouling. The method is intended to potentially serve as an efficient and time-effective manner for detecting early stages of ballast fouling prior to it requiring a costly intervention. Ballast fouling is a common maintenance-of-way issue for the railroad industry, which occurs as a result of contaminants clogging up the ballast and preventing water drainage. The water retained at the sublayers diminishes the strength of the foundation and could result in other undesirable conditions such as clay pumping and reduced track strength. In this study, experiments are performed to study the thermal behavior and characteristics of clean, and partially- and fully-fouled ballast using a FLIR camera. The FLIR camera is set up in a stationary configuration for ease of testing and also providing a more direct approach to analyzing the data, to keep the test conditions highly repeatable and reduce any environmental variations. The results indicate that the cooling and heating rate at the top surface for clean, partially fouled, and fouled ballast are different during the daily heat-up cycle. It is determined that although the FLIR camera is able to measure some changes in the ballast temperature for the fouling conditions that are evaluated in the study, the differences may be within the range of variations that could occur in field conditions. The paper includes the range of measured temperature by the FLIR camera and discusses the pros and cons of using this approach in practice. Additional field testing is needed to validate or dispute the initial findings of the study.
Reports on the topic "Clogging detection":
1
Seginer, Ido, Louis D. Albright, and Robert W. Langhans. On-line Fault Detection and Diagnosis for Greenhouse Environmental Control. United States Department of Agriculture, February 2001. http://dx.doi.org/10.32747/2001.7575271.bard.
Abstract:
Background Early detection and identification of faulty greenhouse operation is essential, if losses are to be minimized by taking immediate corrective actions. Automatic detection and identification would also free the greenhouse manager to tend to his other business. Original objectives The general objective was to develop a method, or methods, for the detection, identification and accommodation of faults in the greenhouse. More specific objectives were as follows: 1. Develop accurate systems models, which will enable the detection of small deviations from normal behavior (of sensors, control, structure and crop). 2. Using these models, develop algorithms for an early detection of deviations from the normal. 3. Develop identifying procedures for the most important faults. 4. Develop accommodation procedures while awaiting a repair. The Technion team focused on the shoot environment and the Cornell University team focused on the root environment. Achievements Models: Accurate models were developed for both shoot and root environment in the greenhouse, utilizing neural networks, sometimes combined with robust physical models (hybrid models). Suitable adaptation methods were also successfully developed. The accuracy was sufficient to allow detection of frequently occurring sensor and equipment faults from common measurements. A large data base, covering a wide range of weather conditions, is required for best results. This data base can be created from in-situ routine measurements. Detection and isolation: A robust detection and isolation (formerly referred to as 'identification') method has been developed, which is capable of separating the effect of faults from model inaccuracies and disturbance effects. Sensor and equipment faults: Good detection capabilities have been demonstrated for sensor and equipment failures in both the shoot and root environment. Water stress detection: An excitation method of the shoot environment has been developed, which successfully detected water stress, as soon as the transpiration rate dropped from its normal level. Due to unavailability of suitable monitoring equipment for the root environment, crop faults could not be detected from measurements in the root zone. Dust: The effect of screen clogging by dust has been quantified. Implications Sensor and equipment fault detection and isolation is at a stage where it could be introduced into well equipped and maintained commercial greenhouses on a trial basis. Detection of crop problems requires further work. Dr. Peleg was primarily responsible for developing and implementing the innovative data analysis tools. The cooperation was particularly enhanced by Dr. Peleg's three summer sabbaticals at the ARS, Northem Plains Agricultural Research Laboratory, in Sidney, Montana. Switching from multi-band to hyperspectral remote sensing technology during the last 2 years of the project was advantageous by expanding the scope of detected plant growth attributes e.g. Yield, Leaf Nitrate, Biomass and Sugar Content of sugar beets. However, it disrupted the continuity of the project which was originally planned on a 2 year crop rotation cycle of sugar beets and multiple crops (com and wheat), as commonly planted in eastern Montana. Consequently, at the end of the second year we submitted a continuation BARD proposal which was turned down for funding. This severely hampered our ability to validate our findings as originally planned in a 4-year crop rotation cycle. Thankfully, BARD consented to our request for a one year extension of the project without additional funding. This enabled us to develop most of the methodology for implementing and running the hyperspectral remote sensing system and develop the new analytical tools for solving the non-repeatability problem and analyzing the huge hyperspectral image cube datasets. However, without validation of these tools over a ful14-year crop rotation cycle this project shall remain essentially unfinished. Should the findings of this report prompt the BARD management to encourage us to resubmit our continuation research proposal, we shall be happy to do so.