Littérature scientifique sur le sujet « Forestry machinery chain »

At the present time cutting of trees, delimbing, and crosscutting with gasoline-powered saws and logging machines are carried out in the forestry cutting area operations with the help of chain saws. Therefore, the efficiency of forestry work depends on the reliability and performance of the chain saw machine. The problem of increasing the reliability of sawing machines, increasing their service life becomes particularly relevant due to a sharp decrease in the volume of logging with the use of multi-operator logging machines. In this regard, the wide use of efficient motor tools, improvement of their design, especially the chain saw machine, with regard to reducing the harmful effect on the operator is of great importance. Poor quality and performance of domestic machinery has led to the fact that mainly imported tools are used in Russia, while their price and maintenance costs are constantly increasing and, consequently, the cost of harvested wood increases too. In this regard, it is important to develop and introduce new, more perfect tool designs that are not only as good as the reliability and performance of the imported equipment, but even much better. Taking it into account, we can consider that the issue of chain saw research with regard to the specifics of its design, as well as its science-based improvement will increase the operational performance and reliability of machines, which is important for the logging industry. One of the main causes of saw unit failures is the increased wear of its components accompanied by the improper saw chain tensioning. Currently, the proposed devices for regulating the tension of the saw chain require periodic stopping of the saw, as none of the devices provides its automatic tensioning. Thus, the purpose of the research is to improve the reliability and service life of chain saws of forestry machinery on the basis of improving the design that provides automatic tensioning of the saw chain. The paper describes the design solutions to improve the saw machine, that is the design of the device that provides automatic tensioning of the saw chain when the saw bar is fixed, allowing to increase the reliability and service life of chain saws, to reduce the chain slipping during the work, which will increase the safety of work and reduce the risk of injury to the operator.

The feasibility of reliably generating bioenergy from forest biomass waste is intimately linked to supply chain and production processing costs. These costs are, at least in part, directly related to assumptions about the reliability and cost-efficiency of the machinery used along the forestry bioenergy supply chain. Although mechanization in forestry operations has advanced in the last 20 years, it is evident that challenges remain in relation to production capability, standardization of wood quality, and supply guarantee from forestry resources because of the age and reliability of the machinery. An important component in sustainable bioenergy from biomass supply chains will be confidence in consistent production costs linked to guarantees about harvest and haulage machinery reliability. In this context, this paper examines the issue of machinery maintenance and advances in machine learning and big data analysis that are contributing to improved intelligent prediction that is aiding supply chain reliability in bioenergy from woody biomass. The concept of “Industry 4.0” refers to the integration of numerous technologies and business processes that are transforming many aspects of conventional industries. In the realm of machinery maintenance, the dramatic increase in the capacity to dynamically collect, collate, and analyze data inputs including maintenance archive data, sensor-based monitoring, and external environmental and contextual variables. Big data analytics offers the potential to enhance the identification and prediction of maintenance (PdM) requirements. Given that estimates of costs associated with machinery maintenance vary between 20% and 60% of the overall costs, the need to find ways to better mitigate these costs is important. While PdM has been shown to help, it is noticeable that to-date there has been limited assessment of the impacts of external factors such as weather condition, operator experiences and/or operator fatigue on maintenance costs, and in turn the accuracy of maintenance predictions. While some researchers argue these data are captured by sensors on machinery components, this remains to be proven and efforts to enhance weighted calibrations for these external factors may further contribute to improving the prediction accuracy of remaining useful life (RUL) of machinery. This paper reviews and analyzes underlying assumptions embedded in different types of data used in maintenance regimes and assesses their quality and their current utility for predictive maintenance in forestry. The paper also describes an approach to building ‘intelligent’ predictive maintenance for forestry by incorporating external variables data into the computational maintenance model. Based on these insights, the paper presents a model for an intelligent predictive maintenance system (IPdM) for forestry and a method for its implementation and evaluation in the field.

In recent decades, the forest industry has been growingly expanded due to economic conditions, climate changes, environmental and energy policies, and intense demand changes. Thus, appropriate planning is required to improve this industry. To achieve economic, social and environmental goals, a supply chain network is designed based on a multi-period and multi-product Mixed-Integer Non-Linear Programming (MINLP) model in which the objective is to maximize the profit, minimize detrimental environmental effects, improve social effects, and minimize the number of lost demands. In addition, to improve forest industry planning, strategic and tactical decisions have been implemented throughout the supply chain for all facilities, suppliers and machinery. These decisions significantly help to improve processes and product flows and to meet customers’ needs. In addition, because of the presence of uncertainty in some parameters, the proposed model was formulated and optimized under uncertainty using the hybrid robust possibilistic programming (HRPP-II) approach. The ε-constraint technique was used to solve the multi-objective model, and the Lagrangian relaxation (LR) method was utilized to solve the model of more complex dimensions. A case study in Northern Iran was conducted to assess the efficiency of the suggested approach. Finally, a sensitivity analysis was performed to determine the impact of important parameters on objective functions. The results of this study show that increasing the working hours of machines instead of increasing their number, increasing the capacity of some facilities instead of establishing new facilities and expanding the transport fleet has a significant impact on achieving predetermined goals.

This paper investigates the environmental impacts and energy benefits of the cultivation of Miscanthus (Miscanthus × giganteus Greef et Deu.), in order to initiate its use in sustainable household heating in the Republic of Serbia. Based on the analysis of available data regarding the use of agricultural machinery in Serbia, a Miscanthus supply chain is constructed and examined in detail, scrutinizing all relevant operations—from planting of rhizomes to thermal energy production. Results of the life cycle assessment identify the briquetting process as the most environmentally burdensome operation due to high electricity consumption and low productivity. It is concluded that an average yield of 23.5 t dry matter (d.m.) year−1 obtained from 1 ha of chernozem soil would have energy output:energy input (EO:EI) ratio of 51:1, and would release 365.5 gigajoules (GJ) of heat during combustion in a boiler. With this amount of energy, around 383 m2 of a free-standing family house in Serbia can be heated annually. The same amount of energy is obtained by the combustion of 22 t of lignite or 23 t of wood logs. The substitution of lignite and wood with Miscanthus briquettes would lead to significant reduction of CO2 equivalents (eq), SO2 eq, P eq, N eq, 1,4 dichlorobenzene (1,4-DB) eq, Non-methane volatile organic compound (NMVOC), PM10 eq and U235 eq emissions. This designates Miscanthus as a more sustainable energy solution for household heating. In instances where more modern agricultural machinery is used, emission reduction is higher, except for CO2 eq due to higher emission factors predicted for more powerful engines. Depending on Miscanthus’ annual yield, the replacement of set-aside land with Miscanthus plantations result in carbon (C) sequestration from 0.08 t C ha−1 year−1 to 0.91 t C ha−1 year−1. In a modern machinery scenario, C sequestration is only attainable when maximal Miscanthus yield is obtained. The combined use of machinery with different engine power is the best option for Miscanthus cultivation in Serbia.

Public participation has become an important driver in increasing public acceptance of policy decisions, especially in the forestry sector, where conflicting interests among the actors are frequent. Stakeholder Analysis, complemented by Social Network Analysis techniques, was used to support the participatory process and to understand the complex relationships and the strong interactions among actors. This study identifies the forestry training sector stakeholders in the Western Italian Alps and describes their characteristics and priorities, in relation to training activities on entrepreneurial topics for forestry loggers. The hierarchy among actors has been identified, highlighting their respective roles and influence in decision-making processes. A lack of mutual communication among different and well-separated categories of actors has been identified, while good connections between stakeholders, operating in different territories, despite the presence of administrative and logistical barriers, have been observed. Training is a topic involving actors with different roles and interests. Nevertheless, all actors consider training about how to improve yields of forest operations and how to assess investments, particularly in innovative machinery, to be crucially important and conducive to a better comprehension of the wood supply chain and the enhancement of the raw material.

Logistics of roundwood and biomass comprise a high number of operations, machinery, storage sites and transportable roundwood and biomass assortments. Moreover, complex and highly varying operational environment through the year poses logistics challenges incurring additional costs. An extensive review of studies was conducted in Sweden and Finland concerning roundwood and biomass logistics, starting from roadside landings and ending with delivery to a mill or a conversion facility. The main aim of the review was to describe trends in roundwood and biomass logistics since the start of the century. Papers were classified to categories of truck transports and roads, terminals, multimodal transports, storage and supply chain logistics. Slightly over 50% of reviewed articles were constrained to biomass only, 31% to roundwood only and 14% to both. Rapid technology development, amendments concerning road transports, increasing environmental concerns and forestry sector’s push to decrease the logistics costs can be seen as the biggest drivers for the reviewed studies and their study objectives. These aspects will also drive and increase the demand for research and development in roundwood and biomass logistics in the future.

Post-wildfire regenerated Mediterranean pine stands have a high risk of wildfire recurrence. Preventive clearings are frequently applied in a mix of systematic and selective ways, being a potential biomass source using technologies such as the collector-bundler BioBaler WB55. Our research aimed to compare the BioBaler with a chain mulcher performing systematic mulching of 50% vs. 67% of stand surface over 11.4 ha dominated by Pinus pinaster Ait. regenerated after a severe wildfire. Time studies included the machinery GPS follow-up and the weighing of each produced bale. Environmental aspects were also assessed. A regression curve related BioBaler weight productivity (odt·Workh−1) to pine biovolume (cover (%) average tree height, m). Surface productivity (stand ha·Workh−1) was greater for both technologies when a lower percentage of the total surface was cleared, but less than theoretically predicted. The BioBaler’s economic balance, including the cost of further selective clearing and the income from biomass selling, was costlier than that of the mulcher—in the most representative strata, 475 EUR·ha−1 vs. 350 EUR·ha−1. Under the studied conditions, BioBaler was not economically competitive with the conventional treatment, its main constraint being low collection efficiency (31% of the standing biomass in the cleared surface, 5.33 out of 17.1 fresh tonnes·ha−1).

Annually in the North-West of Russia, the percentage of cutting using assorted harvesting technology is increased. As a result, the issue of increasing productivity of forestry machines is becoming increasingly important. One of the key points is the proper maintenance and operation of equipment, in particular a saw of a harvester head. However, the experiments show that the operators of logging machines do not know the rules or, often, neglect the need for proper and timely maintenance of the saw apparatus. The condition of the saw chains and the saw apparatus as a whole is directly reflected in the performance of forestry machines. One way to solve this problem may be to use the method of rotational replacement of saw chains. During the study, a series of field experiments were conducted at a logging enterprise located in the Arkhangelsk region. The aim of the experiment was to determine the most optimal method of using saw chains. It will increase the productivity of multioperational forestry machines. As a result of the study, it was found that the saw chain replacement system currently used in enterprises does not have sufficient efficiency and requires changes. In this paper, we use the method of rotational replacement of saw chains, which, based on practical and theoretical observations, increases the time of clean sawing, the volume of harvested wood on one chain and, accordingly, increases the productivity of the forestry machine. This work, in general, helps increase the efficiency of harvesters, as well as reduce the cost of consumables.

Making managerial decisions when choosing a variant of the technological chain for logging is complicated by the variety of natural and climatic conditions. The climatic features of the periods affect the productivity of technological machines and the cost of implementation. This research suggests using network planning to determine the technological chain of timber land development. The purpose of the research is construction of multi-purpose network models for planning the technological chain of logging operations in various production conditions of forestry enterprises operation. These models are aimed at making it possible to conduct calculations to increase the efficiency of labour, materials, funds, equipment distribution with the maximum reduction in the cost of logged products. As a result of the analysis of possible options for technological chains, several network models for the implementation of logging technological processes have been built.

Currently, in the Russian Federation, a large number of areas require reforestation. Introduction of new technologies in artificial reforestation (planting seedlings with a closed root system) requires the use of new means of mechanization when planting seedlings. The assessment of the degree of similarity and difference of the selected structures was carried out on the basis of statistical analysis (hierarchical classification). The country's industry practically does not produce tree planting machines for planting seedlings with a closed root system. Imported specimens of forest planting machines are expensive, require aggregation with heavy equipment, which is practically absent in forestry. In addition, climatic conditions may also be a limitation in the use of imported equipment. In connection with the above, Voronezh State University of Forestry and Technologies has developed designs of universal planting machines with rotary and chain planting mechanisms. They enable planting of both standard seedling and seedlings with closed root system. The use of universal tree planting machines in forestry enables to keep one tree planting machine instead of two specialized ones. This will significantly save on maintenance and storage of mechanisms

The PhD Thesis focuses on two topics: (i) assessment of forest wood and carbon (C) stock and (ii) forestry mechanization applicable at the forest stand level for any given conditions among those found in the Italian Alpine and pre-Alpine mountainous areas. Both these topics aim to improve the use of forestry resources for climate change mitigation, starting from a bottom-up approach scaled on the information made available by Forest Management Plans (FMP). After an introduction on the topics given in chapter 1, the first topic (assessment of forest wood and C stock) is investigated in chapters 2, 3, 4 and 5, by taking the Valle Camonica District (Lombardy Region, Italy) as Case Study Area. The aim is to develop a stand-level model to estimate the mass of wood (t·yr-1 dry matter, DM) and C (t·yr-1 C) in aboveground wood biomass, belowground wood biomass and dead organic matter (i.e., deadwood and litter), quantifying, at the same time, the mass of potentially available logging residues (i.e., branches and tops; t·yr-1 DM) for energy generation and the corresponding potentially generated energy (GJ·yr-1), under the assumption that wood replaces non-renewable energy sources. Chapter 2 presents the first version of the model, called “WOody biomass and Carbon ASsessment” (WOCAS v1), aimed at the quantification of the mass of wood and C in the forest pools in a predefined reference year, by using a methodology already applied at the regional and national level. The model was tested on a dataset of 2019 public forest stands extracted from 45 FMPs (area: 37000 ha) covering the period from 1984 (year in which the oldest FMP came into force) to 2016 (most recent available data from the local FMPs). Preliminary results showed that, in 2016, the total C stock (given by the sum of C stock in aboveground wood biomass, belowground wood biomass, and dead organic matter) achieved 76.02 t·ha-1 C. The model also gives the possibility to analyze future scenarios based on the continuation of the current management practices rather than improved practices, to define a possible mitigation strategy for the activation of a local Voluntary Carbon Market. WOCAS v1 was implemented into a second version (WOCAS v2), by introducing, first of all, an improved methodology to calculate the mass of wood (t·yr-1 DM) and C (t·yr-1 C) within the forest pools from the year in which the FMPs entry into force until a predefined reference year (chapter 3). The main innovative aspect of the improved methodology is that the gross annual increment of each stand is calculated through an age-independent theoretical non-linear growth function based on the merchantable stem mass, solving the limitation of WOCAS v1 in which the gross annual increment of the stand is assumed as constant, as reported by the FMPs. This improved methodology was applied to the same dataset used for WOCAS 1 (i.e., 2019 forest stands, 45 FMPs; forest area: 37000 ha; period: 1984-2016). The total weighted average wood yield, calculated as the sum of wood yield in all the above-mentioned forest pools, ranged from 53.36±53.13 t∙ha-1∙yr-1 DM (1984) to 156.38±79.76 t∙ha-1∙yr-1 DM (2016). The total weighted average C yield ranged from 26.63±26.80 t∙ha-1∙yr-1 C (1984) to 77.45±40.19 t∙ha-1∙yr-1 C (2016). The average C yield related to the whole analyzed period (1984-2016) was 66.04 t∙ha-1 C. Of this, C yield in the aboveground wood biomass, belowground wood biomass and dead organic matter was equal to 72.0%, 15.8% and 12.2%, respectively. Validation of the results at the stand level was performed by comparing the value of the gross annual increment provided by the FMPs with the one predicted by WOCAS v2. The model caused, in some cases, an overestimation and, in other cases, an underestimation. For example, for Larix decidua Mill. and for Picea abies L., the Pearson coefficient of correlation (r2) between predicted and provided increments was r2 = 0.69 and r2 = 0.46, respectively. This was due to the fact that the methodology currently implemented into WOCAS v2 is based on average values of growth parameters valid for the whole Lombardy Region, and does not consider the productivity class of the stands since specific information was not always made available by the FMPs. WOCAS v2 also includes an innovative methodology (chapter 4 and chapter 5) to quantify – as an additional climate change mitigation strategy – the mass of potentially available residues (t·yr-1 DM) for energy generation, the potentially generated heat and electricity (GJ·yr-1) and the potentially avoided CO2 emissions into the atmosphere related to the final combustion process (t·yr-1 CO2), under the assumption that wood substituted non-renewable energy sources. In chapter 4, since not all the required data were initially made available for the Case Study Area, the mass of residues was computed by considering only the stand’s function and the stand’s management system, covering the period from 1994 (year in which the first wood cut was performed) to 2016. The calculation was then improved (chapter 5) by taking into account also the stand’s accessibility, the forest roads’ transitability and the energy market demand. Information on topographic features, landscape morphology and characteristics of the forest roads were collected by combining the FMPs data coming from WOCAS v2 and a Digital Elevation Model (DEM) in a Geographic Information System (GIS) software. The georeferenced stands were characterized by both single contiguous areas (single stands), as well as different non-contiguous areas (sub-stands). Overall, 2157 polygons – consisting of both single and sub-stands – were analyzed, covering the period from 2009 (most recent available data on forest roads’ transitability) and 2016. The mass of potentially available residues calculated for the analyzed period was used to estimate the current sustainable supply (i.e., 1.82∙103±6.61∙102 t·yr-1 DM). Under the hypothesis that these residues were prepared into woodchips to feed the Organic Rankine Cycle (ORC) unit of the local centralized heating plant of Ponte di Legno, the potentially generated heat and electricity (GJ·yr-1) and the potentially avoided CO2 emissions into the atmosphere (t∙yr-1 CO2) for the final combustion process were estimated by assuming that: (i) heat generated by the ORC unit replaced the one produced by natural gas-based heating plants; (ii) electricity generated by the ORC unit replaced the one generated by the Italian natural gas-based plants-mix for combined heat and electricity production and distributed through the National grid. Results showed that if only the current sustainable mass of residues was used to feed the ORC unit of the plant, the potentially generated heat and electricity would represent at most 28.7% of that generated by the unit in the year 2019. The thermal and electric power would be equal to 0.70 MW and 0.17 MW, with an average power load of the ORC unit of 23.6%. Experimental tests are needed to collect information on the harvesting method, used machines and technologies – which considerably affect the mass of available resides – as well as the currently harvested mass of residues for the validation of the results, that up to now is not possible since no measured data are available yet at the stand level. The second topic (forestry mechanization) is investigated in chapter 6. The aim is to develop an innovative approach in order to: (i) select the most suitable Forestry Machinery Chain (FMC) to adopt at the stand level for wood collection (harvesting and transport) and (ii) compute the economic costs (€·h-1; €·t-1 DM; €) of the selected FMC. To make the selection feasible, a user-friendly stand-level model called “FOREstry MAchinery chain selection” (FOREMA v1) was developed. FOREMA v1 supports the user in selecting the FMC according to seven technical parameters that characterize the stand. For each FMC, the model defines the sequence of the operations and the types of machines that can be used. The economic costs of the selected FMC are then quantified by taking into account the fixed and the variable costs. The approach was applied for a Case Study concerning the collection of woodchips from a coppice stand in the Italian Alps for energy generation. The analyzed FMC was made up of the following operations: (i) felling, (ii) bunching and extraction, (iii) chipping and (iv) loading and transport. For the whole FMC, the cost per unit of time was 669.3 €·h-1; the cost per unit of product was 113.0 €·t DM, whereas the cost of production amounted to 6893.2 €. Results provided by FOREMA v1 still need to be validated; experimental tests are required to collect information on the operating conditions in which the machines are actually used and, consequently, on the corresponding economic costs. Obtained results on the costs of the operations were compared with that reported in literature and related to studies performed under similar forestry and operating conditions.

Thesis (MEng)--Stellenbosch University, 2014.
ENGLISH ABSTRACT: For wood manufacturers around the world, the single biggest cost factor is known to be its raw material. Thus maximum utilisation, specifically volume recovery of this raw material, is of key importance for the industry. The wood products industry consists of several interrelated manufacturing steps for converting trees into logs and logs into finished lumber. At most primary and secondary wood processors the different manufacturing steps are optimised in isolation or based on operator experience. This can lead to suboptimal decisions and a substantial waste of raw material. The objective of this study was to determine the optimal machine settings for two interrelated operations, namely the sawing and ripping operations which have traditionally been optimised individually. A model, having two decision variables, was developed which aims to satisfy market demand at a minimal cost. The first decision was how to saw the log supply into different thicknesses by choosing specific sawing patterns. The second was to decide on a rip saw’s settings, namely part priority values, which determines how the products from the primary sawing operation are ripped into products of a certain thickness and width. The techniques used to determine the machine settings included static simulation with the SIMSAW software to represent the sawing operation and mixed integer programming to model the ripping operation. A metaheuristic, namely the Population Based Incremental Learning algorithm, was the link between the two operations and determined the optimal settings for the combined process. The model’s objective function was formulated to minimise the cost of production. This cost included the raw material waste cost and the over or under production cost. The over production cost was estimated to include the stock keeping costs. The under production cost was estimated as the buy-in cost of purchasing the under supplied products from another wood supplier. The model performed well against current decision software available in South Africa, namely the Sawmill Production Planning System package, which combines simulation (SIMSAW) and mixed integer programming techniques to maximise profit. The model added further value in modelling and determining the ripping priority settings in addition to the primary sawing patterns.
AFRIKAANSE OPSOMMING: Die grootste enkele koste vir houtprodukvervaardigers wêreldwyd is dié van hulle roumateriaal. Die maksimale gebruik van rou materiaal, of volume herwinning, is dus van primêre belang vir hierdie industrie. Die vervaardigingsproses in die houtprodukte-industrie bestaan uit ‘n verskeidenheid interafhanklike stappe om bome na stompe te verwerk en stompe na eindprodukte. By meeste primêre -en sekondêre houtvervaardigers word die verskillende vervaardigingsstappe in isolasie ge-optimeer. Hierdie praktyk lei tot sub-optimale besluite en ‘n vermorsing van roumateriale. Die doelwit van hierdie studie was om die optimale masjienverstellings vir twee interafhanklike prosesse, die primêre -en kloofsaag prosesse, te bepaal. Tradisioneel word hierdie twee prosesse individueel optimeer. ‘n Model met twee besluitnemingsveranderlikes is ontwikkel wat poog om die markaanvraag te bevredig teen ‘n minimum koste. Die eerste besluit was watter saagpatroon gekies moet word om die stompe in die regte dikte produkte te saag. Die tweede besluit was wat die kloofsaagstellings, ook bekend as prioriteitswaardes, moet wees sodat die regte wydte produkte gesaag word. Die tegnieke wat gebruik is sluit statiese simulasie met SIMSAW sagteware in om die primêre saagproses te modelleer en gemengde heelgetalprogammering (“mixed integer programming”) om die kloofsaagproses te modelleer. ‘n Metaheuristiek genaamd die “Population Based Incremental Learning” algoritme,was die skakel tussen die twee operasies om die optimale masjienstellings vir die proses te bepaal. Die model se doelfunksie was geformuleer om die koste van produksie te minimeer. Hierdie koste sluit die roumateriaal afvalkoste en die kostes van oor -en onderproduksie in. Die oorproduksiekoste was ‘n skatting van die voorraadkostes. Die onderproduksiekoste was ‘n skatting van die koste om voorraad van ‘n ander verskaffer aan te koop. Die model het goed opgeweeg teen die beskikbare besluitnemingssagteware in Suid Afrika, die “Sawmill Production Planning System”, wat ‘n kombinasie van SIMSAW en ‘n gemengde heelgetalprogrammeringstegniek is. Die model het verder waarde toegevoeg deur die kloofsaag se prioriteitswaardes te modelleer saam met die primêre saagpatrone.

The objectives of this thesis were to develop a machine learning tool-chain and to investigate the relationship between heart rate and trigger squeeze and shooting accuracy when firing a handgun in a simulated environment. There are several aspects that affects the accuracy of a shooter. To accelerate the learning process and to complement the instructors, different sensors can be used by the shooter. By extracting sensor data and presenting this to the shooter in real-time the rate of improvement can potentially be accelerated. An experiment which replicated precision shooting was conducted at SAAB AB using their GC-IDT simulator. 14 participants with experience ranging from zero to over 30 years participated. The participants were randomly divided into two groups where one group started the experiment with a heart rate of at least 150 beats per minute. The iTouchGlove2.3 was used to measure trigger squeeze and Polar H10 heart rate belt was used to measure heart rate. Random forest regression was then used to predict accuracy on the data collected from the experiment. A machine learning tool-chain was successfully developed to process raw sensor data which was then used by a random forest regression algorithm to form a prediction. This thesis provides insights and guidance for further experimental explorations of handgun exercises and shooting performance.

Tremor is an involuntary quivering movement or shake. Characteristically occurring at rest, the classic slow, rhythmic tremor of Parkinson's disease (PD) typically starts in one hand, foot, or leg and can eventually affect both sides of the body. The resting tremor of PD can also occur in the jaw, chin, mouth, or tongue. Loss of dopamine leads to the symptoms of Parkinson's disease and may include a tremor. For some people, a tremor might be the first symptom of PD. Various studies have proposed measurable technologies and the analysis of the characteristics of Parkinsonian tremors using different techniques. Various machine-learning algorithms such as a support vector machine (SVM) with three kernels, a discriminant analysis, a random forest, and a kNN algorithm are also used to classify and identify various kinds of tremors. This chapter focuses on an in-depth review on identification and classification of various Parkinsonian tremors using machine learning algorithms.

Tremor is an involuntary quivering movement or shake. Characteristically occurring at rest, the classic slow, rhythmic tremor of Parkinson's disease (PD) typically starts in one hand, foot, or leg and can eventually affect both sides of the body. The resting tremor of PD can also occur in the jaw, chin, mouth, or tongue. Loss of dopamine leads to the symptoms of Parkinson's disease and may include a tremor. For some people, a tremor might be the first symptom of PD. Various studies have proposed measurable technologies and the analysis of the characteristics of Parkinsonian tremors using different techniques. Various machine-learning algorithms such as a support vector machine (SVM) with three kernels, a discriminant analysis, a random forest, and a kNN algorithm are also used to classify and identify various kinds of tremors. This chapter focuses on an in-depth review on identification and classification of various Parkinsonian tremors using machine learning algorithms.

This chapter addresses the concerns of Harold Hochschild after he learned that Governor Nelson Rockefeller was planning to give responsibility for campgrounds and other public facilities in the forest preserve to the new Office of Parks and Recreation, which was governed by a commission whose chair was Laurance Rockefeller. The chapter argues that the change was a mortal threat, according to Hochschild and Harold Jerry. Hochschild feared that if Laurance's people were allowed to operate public facilities in the forest preserve, he would use his influence to increase the number and size of those facilities. The chapter also discusses the commissioners' vision to protect the natural integrity of wild areas, promote quieter forms of recreation, shift the park's economy toward nature-oriented tourism, and tighten regulations on motorboats, snowmobiles, logging equipment, and other gasoline-powered machines. It highlights how a singular combination of political power and good timing persuaded the legislature to set up a new agency — Adirondack Park Agency (APA). The creation of the Adirondack Park Agency was one of three measures that Jerry considered essential to “saving” the Adirondacks. The other two were specifically focused on the large tracts of private land that defined the park's character.

In current supply chain operations, the transactions among suppliers and original equipment manufacturers (OEMs) are sometimes inefficient and unreliable due to limited information exchange and lack of knowledge about the supplier capabilities. For the OEMs, majority of downstream operations are sequential, requiring the availabilities of all the parts on time to ensure successful executions of production schedules. Therefore, accurate prediction of the delivery times of purchase orders (POs) is critical to satisfying these requirements. However, such prediction is challenging due to the suppliers’ distributed locations, time-varying capabilities and capacities, and unexpected changes in raw materials procurements. We address some of these challenges by developing supervised machine learning models in the form of Random Forests and Quantile Regression Forests that are trained on historical PO transactional data. Further, given the fact that many predictors are categorical variables, we apply a dimension reduction method to identify the most influential category levels. Results on real-world OEM data show effective performance with substantially lower prediction errors than supplier-provided delivery time estimates.

Purchasing air tickets by the lowest price is a challenging task for consumers since the prices might fluctuate over time influenced by several factors. In order to support users’ decision, some price prediction techniques have been developed. Considering that this problem could be solved by multi-target approaches from Machine Learning, this work proposes a novel method looking forward to obtaining an improvement in air ticket prices prediction. The method, called Deep Regressor Stacking (DRS), applies a naive deep learning methodology to reach more accurate predictions. To evaluate the contribution of the DRS, it was compared with the competence of the single-target regression and two state-of-the-art multi-target regressions (Stacked Single Target and Ensemble of Regressor Chains). All four approaches were performed based on Random Forest and Support Vector Machine algorithms over two real-life airfares datasets. After results, it was concluded DRS outperformed the other three methods, being the most indicated (most predictive) to assist air passengers in the prediction of flight ticket price.

Abstract Well integrity in the oilfield is one of the challenges that petroleum engineers face, as they seek to monitor well corrosion in the field to optimize well performance. Most of these fields can be categorized as brownfields, with some of the wells considered aged and have expected integrity issues. To achieve sustainable production targets with cost-effective and safe operations from these fields requires a close monitoring of the integrity of all elements involved in the production chain. Addressing these challenges requires the engineers to coordinate and analyze several data elements, including casedhole, openhole, reservoir, well, and production data from multiple sources. Another challenge is to create and automate a corrosion workflow that saves the engineers’ time and improves efficiency. In this paper, we introduce an innovative workflow that uses the historical corrosion data while integrating the multiple production and reservoir variables. The innovative approach uses machine learning (ML) algorithms to provide a powerful tool for workover (W/O) candidate selection and for optimizing the corrosion evaluation frequency, which are required in different areas of the fields. Different ML methods (random forest classification and neural net) were applied on training data. Different models were created, and the best model will be used. This offered key insights on the rate of corrosion and corrosion patterns. Further, the developed workflow was designed to be self-sustaining and acting as a surveillance tool for monitoring the integrity of the wells. The first step of the workflow was to start with organizing and auditing the available corrosion data, followed by a review and analysis of existing openhole, casedhole, production, and reservoir engineering data. This approach led us to understand the extent and severity of corrosion in terms of the corrosion rate and the corrosion index. The corrosion logs were digitally interpreted depth-wise in order to explore the maximum metal loss for each interval. New animated conformance corrosion maps were created. The successful diagnosis through data analytics in a modern integrated software platform will assist in corrosion monitoring and decision-making. The multiple corrosion maps can be animated to visualize the current corrosion profile and predict the corrosion over time, in addition to ranking the wells for W/O candidate selection.

One of the main challenges we are facing whenever teaching Mathematics to first year Politehnica University students is how to enable them to establish a connection between abstract notions and their recognition and concrete use in specialized engineering courses or even in post graduate job problems. Such a connection is needed because the multipurpose mathematical models encountered during the first university year are more often than not general notions. Nevertheless, problems with which students are usually confronted later in their work life relate to a well delimited approach in a specific engineering field. In order to serve this purpose, our present paper relies on two key elements. The first one is the visual association between abstract elements (in our case solutions of systems of differential equations) and certain representations in a real world problem (specifically, predefined trajectories of motion). The second, equally important element, is the form in which the above mentioned link is presented. Since the use of mobile technology in higher education offers a very attractive, interactive method, we have chosen to merge the mathematical e-learning dimension with a platform game developed for Android systems (phones and tablets). Consequently, the recognition of abstract notions is encompassed in the levels of the game. The mathematics behind the game deals with systems of first order linear differential equations, their associated matrix and the corresponding eigenvalues. Nevertheless, there is also a captivating story to support the game and engage the player. The main character, RC (RealComplex) has been teleported, by a mad dentist, from his cabinet, straight into the habitat of the Bengali tiger. In fact, the mad dentist had secretly transformed his dental chair into a space traveling machine. RC must travel across grasslands, subtropical rain forests, mangroves and eventually escape to an island where the space traveling machine can be transformed into an escape plane. While the game comprises four levels, two of which are mathematical levels, evolution from one level to the next is only allowed if the previous level has been completed. Thus, no one can avoid going through a mathematical revision before reaching the island and the end of the game. Moreover, a deeper understanding of the geometric representation of complex numbers is also part of the game. In fact, trajectories corresponding to complex eigenvalues are solutions to be avoided by the player since this type of directions, if chosen, disable the character's freedom to move in the game world.