Fleet Of Machines Research Articles

Maintenance plan adaptation based on health ratings of servitised machines through a fleet-wide machine clustering method

The increased requests for value-added services to integrate product performance push manufacturing companies to extend their service offerings to meet customers’ needs. In this context, maintenance planning can leverage new possibilities offered by digital technologies for data analytics services. The present research then proposes an approach for maintenance plan adaptation based on a data-driven method applied over a fleet of machines installed in different production sites. The method relies on collaborative prognostics to develop a clustering of machines’ behaviour aimed at providing the health ratings of the machines and the subsequent maintenance plan adaptation due to the deviation from the expected behaviour. The method is adopted from the perspective of an Original Equipment Manufacturer, as part of a transformation path towards an advanced provision of digitalization for maintenance service offerings. The method is validated in the context of two lines at selected customer’s premises. This demonstrates the viability and effectiveness of adapting the maintenance plans thanks to the data analytics in light of the current behaviour of the machines within the lines.

МАТЕМАТИЧЕСКАЯ МОДЕЛЬ ОРГАНИЗАЦИИ ТЕХНИЧЕСКОГО СЕРВИСА

A wide range of agricultural machinery in need of high-quality maintenance throughout the entire operational period to ensure uninterrupted and efficient operation is one of the most important links in the agro-industrial complex. (Research purpose) The research purpose is developing a mathematical model showing the relationship between the conduct of maintenance activities and the unit of equipment of the agricultural fleet; within the framework of the obtained mathematical model, deriving a criterion assessment of the quantitative conduct of maintenance. (Materials and methods) Indicated that such estimates can be obtained by applying mathematical modeling. A mathematical model was constructed using a visual diagram reflecting the relationship between the machines of the agricultural park, types of maintenance, elements of set theory and mathematical analysis. We used the theory of sets, which allowed us to move from the units of equipment of the fleet of agricultural machines to an analytical representation of realities and derive a constant that gives an assessment of maintenance depending on the number of activities carried out during the time interval under consideration. (Results and discussion) It was noted that it is necessary to improve the quality of maintenance by improving the control of its implementation in real conditions. The novelty of this work consists in the originality of the obtained scheme linking the types of maintenance and the machines of the agricultural fleet, without being tied to the number of units of equipment; in the development of a mathematical model that allows, using theoretical calculations, contributing to improving the control of maintenance activities by obtaining a universal constant that quantifies for any type of equipment and maintenance. The theoretical results were tested using the Kirovets-739 tractor as an example. (Conclusions) We obtained a schematic representation of the relationship between the components of the machine and tractor fleet and a numerical estimate reflecting the number of completed scheduled maintenance steps during the time period under study when using mathematical methods in the organization and conduct of maintenance.

ПРОБЛЕМА ПОВЫШЕНИЯ НАДЕЖНОСТИ МАШИН И ОБОРУДОВАНИЯ

The basis for a satisfactory level of operability of modern machines and equipment of domestic production was and remains the engineering and technical service of equipment and the "Planned preventive maintenance and repair system of machines in agriculture." Timely implementation of mechanized processes and work with low reliability of agricultural machinery requires an increase in the level of reliability and serviceability of the fleet of machines and equipment. (Research purpose) The research purpose is increasing the operational reliability of modern agricultural machinery based on the development and implementation of proprietary technical service. (Materials and methods) Materials obtained as a result of the author's own research and data on the reliability of domestic machinery and equipment from open sources were used in the research. The following methods were applied: comparative assessments, analysis and synthesis of the results of a survey of the operational reliability of agricultural machinery and equipment in real-world operation, the effectiveness of using various forms and methods of organizing their production and technical service. (Results and discussion) It was determined that an increase in the level of operability and reliability of modern domestic equipment can be ensured only with a significant improvement in the quality of manufacturing machinery and equipment and with the direct participation of the equipment manufacturer in technical service based on the proprietary method of technical service. It was noted that the organization of corporate technical service is possible only when creating a corporate production and technological system of mechanical engineering. The solution of this problem by the forces and means of existing separate equipment manufacturing plants is not possible. (Conclusions) To improve the reliability of modern domestic technology, it is necessary to reorganize the existing system of separate manufacturing plants, create large machine-building firms and branded technical service centers.

Effect of war on radiotherapy in Ukraine and how to help.

1513 Background: The full-scale Russian invasion of Ukraine on February 24th, 2022 brought the largest humanitarian disaster to the heart of Europe since the World War II. In this work, we describe the impact of the full-scale Russian invasion on the radiation therapy (RT) services in Ukraine and suggest how to help. Methods: We collected the information on operation of RT centers in Ukraine during the war. In addition, in 2023 an annual survey was conducted by Grigoriev Institute for Medical Radiology in Kharkiv for the IAEA DIRAC database. The survey was sent to 41 RT centers in Ukraine requesting information on equipment, staffing, and patient volume. Due to the war conditions the data provided in the survey is limited to the un-occupied territories. Results: After the initial Russian invasion of Ukraine in 2014 and occupation of Crimea and parts of Donbas, Ukraine lost access to 7 RT centers with 18 external beam radiotherapy (EBRT) machines (17% of total). Just before the full-scale invasion in 2022, there were a total of 44 Co-60 machines (57%) and 33 linear accelerators (43%) in the unoccupied territories. As a result of the full-scale invasion of Ukraine in 2022, almost all RT centers suspended operation in the first weeks of war. The most challenging period for RT in Ukraine was in March when Kyiv (where 20 EBRT machines are located) was partially surrounded by the occupiers. Based on the DIRAC survey, compared to 2021 data, in 2022 the number of radiation oncologists decreased on average by 2.9%, medical physicists by 6.7%, and therapists by 6.5% but there was a large variation in staffing levels depending on the region and its proximity to war. The workload in the RT centers close to the combat zone almost halved, while increasing by 10 - 60% in the western and central Ukraine. The total number of patients treated with EBRT decreased by 11% and brachytherapy by 21%. Brachytherapy services sustained the most interruption (47% decrease in LDR and 18% decrease in HDR patient volume) due to inability to perform source exchanges. Overall, approximately 5,500 less patients were treated in 2022 compared to 2021. Despite the ongoing war, Ukrainian cancer centers installed 8 new linear accelerators, with 5 linear accelerators pending installation. In addition, the Ministry of Heath of Ukraine has recently purchased 15 linear accelerators to replace the aging Co-60 machine fleet as the future source exchanges might not be possible. There is an acute need in helping Ukraine transition from Co-60 to modern IMRT/VMAT linear accelerators. Conclusions: Radiotherapy in Ukraine sustained significant damages since the 2014 Russian invasion, which was exacerbated further by the full-scale invasion in 2022. To support the vitality and absorptive capacity of RT services in Ukraine, the democratic world can help by donating equipment, hardware, software, and participating in training of Ukrainian RT professionals as they transition to modern and high-quality RT care for Ukrainian cancer patients.

A sensor-driven operations and maintenance planning approach for large-scale leased manufacturing systems

The rise of mass customisation drives manufacturers to adopt leasing agreements for their machinery rather than outright their ownership. This industrial trend results in large-scale leased manufacturing systems, where the asset conditions and maintenance requirements for a fleet of machines and/or production lines from several manufacturers are continuously monitored and managed by a lessor. In this paper, we propose an operations and maintenance planning model that explicitly models (i) dynamic real-time failure rate predictions for machines based on sensor-driven degradation data, (ii) optimal routes for maintenance teams across a number of geographically-distributed manufacturing sites, and (iii) operational outcomes. The model can handle complex maintenance and operational outcome interdependencies between multiple machines, and incorporate demand for different products, heterogeneous machine capacities and capabilities, factory topology, and the resulting production flow capacities of products. To demonstrate the model’s practicality, it is applied to three experimental case studies with various numbers of machines, operating schedules, product types, and flow capacities. The results show that the proposed model significantly outperforms the traditional reliability-based maintenance model in key metrics such as the number of unexpected failures, the cost of preventive maintenance actions, machine downtime, the percentage of unsatisfied demand, and total cost.

Determination of reliability for a complex technical system on the example of a mobile medical module

The article presents a proposal for a method to determine a total and partial reliability for a mobile medical module as a complex technical system. The dedicated functions of such a module are to evacuate the wounded from the battlefield (in the basic version) and to ensure the maintenance of his vital functions and the performance of necessary medical procedures (in the extended version). Work on developing the concept or advanced construction of such modules using unmanned aerial vehicles as transport drones has been carried out for several years by many countries and aviation companies, including: DARPA agency (USA) and AFIT (Poland). Even though there is no fleet of such machines in Poland yet, this comes from experience in managing aircraft in the Armed Forces RP results from the need to simultaneously secure the operation of such modules in an IT support system using algorithms and mathematical relationships in determining a total and partial reliability . Due to the structural complexity of the mobile medical module (carrier platform, drive, basic and additional avionics equipment and basic and extended medical equipment), a total and partial reliability can be determined for a simple object (in a simplified reliability version as full) or a complex system (as a total and partial reliability).

ANALYTICITY OF MARKOV PROCESSES FOR DESCRIPTION OF COEFFICIENT OF TECHNICAL READINESS OF GRAIN HARVESTERS COMBINES

The article presents the results of a study of the influence of operating conditions and modes on the technical condition of grain harvesters. The grain harvester gradually loses its performance during operation. To ensure stable operation of the fleet of agricultural machines, maintain its technical condition and increase operational reliability, technical control of grain harvesters is carried out. The analysis of the technical condition of combine harvesters showed that there remains a high percentage of defective combine harvesters, downtime for all types of repairs and the number of unplanned repairs. One of the main reasons for this condition is the low level of organization and quality of technical control, insufficient mechanization of technological processes. The basic element of the technological preparation of repair production is the development of a technological process that ensures the availability of a complete set of technological documentation at the enterprise for organizing and carrying out technical maintenance and repairs of traction rolling stock. During the development of technological processes of repair, the selection of technological operations and means of their technological equipment, normative documents of requirements for tolerances, clearances, forces of landings, pressings, threaded connections, processing quality, assembly accuracy, etc. is carried out. Technical conditions for the development of non-standard technological equipment are determined from the developed technological operations. As a target function, the rational periodicity of maintenance of grain harvesters was taken, namely, the rational time between services. The analysis of the results of known works on mathematical modeling and periodicity of repair and maintenance of complex technical systems based on Markov and semi-Markov processes allowed us to propose complex criteria as criteria for modeling the objective function: the functional of readiness, which is used to estimate the allowable time, and the functional of technical use, which allows determining the value of the optimal time between services of the combine harvester according to the technical parameter at the maximum point.

Elimination of damage to parts and disruption of mating seats

Annually up to 22% of tractors, 23% of cars, 21% of others do not participate due to technical malfunction. This state of equipment has aggravated the extremely difficult situation with the provision of the main types of machines: tractors, and machinery. With the supply of tractors at 55% of the need, the actual level due to their technical malfunction on average in Russia did not exceed 43%. Under the current conditions, one of the ways to preserve the existing fleet of machines and increase the number of workable equipment may be the purchase of equipment on the secondary market after a high-quality rehabilitation repair programme has been carried out

ОРГАНИЗАЦИЯ РЕМОНТА И ТЕХНОЛОГИИ ВОССТАНОВЛЕНИЯ ДЕТАЛЕЙ МАШИН В АПК

The volume of agricultural products depends on the technical readiness of equipment, repair and maintenance facilities. The emergence of new technologies can change the very process of organizing repairs. (Research purpose) The research purpose is analyzing in historical perspective the mutual relationship of the fleet of machines, the organization and technology of repair and restoration of parts of agricultural machinery. (Materials and methods) Used statistical data, scientific papers of researchers, authors' own observations. We applied the general scientific method, analysis, generalization, synthesis, etc. (Results and discussion) The paper notes the presence during the planned economy of a large fleet of the same type of machines in agriculture, which required constant repair impacts, contributed to the creation of an appropriate repair and maintenance base. It was pointed out that in 1986 184 repair plants were built, 2106 district repair and technical enterprises, including 818 specialized and 1288 general purpose workshops, technical exchange offices, repair shops for worn parts, etc.). The possibility of directive instructions was provided by the mass collection of the same type of parts, which made it possible to apply appropriate technologies on production-mechanized lines, reduce the cost of restoring parts: the organization of repair determined the technology. It has been shown that in a market economy, the equipment nomenclature has decreased, the number of brands has increased, repairs have moved from specialized to agricultural organizations and are mainly reduced to replacing worn-out parts with new ones. At the same time, additive technologies have appeared that do not require reconfiguration of equipment when changing the nomenclature of recoverable parts. (Conclusions) Additive technologies can transform sectoral repairs into intersectoral repairs, which will increase equipment utilization and improve economic performance.

Влияние энергозатрат на формирование рационального машинно-тракторного парка

In the modern period, the structure of enterprises engaged in the production of agricultural products differs significantly from each other. The main differences include the presence, contour and condition of sown areas, as well as the composition and quality condition of the machine and tractor fleet. This can be explained by the fact that, along with enterprises that have large acreage and an energy-saturated machine and tractor fleet, small peasant farms (KFH) also participate in the production of agricultural products and the formation of the gross regional product in terms of the size of the acreage and the composition of the machine and tractor fleet. At the same time, they make a significant contribution to the production of gross domestic product. Thus, in the Amur region, the share of agricultural enterprises from all agricultural products produced in the region in the total volume accounts for up to 25 ... 28 percent. Thus, in the current production conditions, the issue of rational selection and formation of a machine and tractor fleet that would be optimal for both large agricultural holdings and small farms becomes particularly relevant. At the same time, when forming a machine and tractor fleet, the most responsible is the financial component, since the cost part, of course, is not comparable between large agricultural enterprises with high production volumes and small farms. If we analyze the market of agricultural machinery offered by manufacturers, it is very diverse both in price value and technological efficiency, and in energy saturation. Therefore, for the rational selection of the composition of the machine-tractor fleet and the train of machines, it is necessary to apply various methods based on the financial capabilities of a particular agricultural enterprise and other components of the production process. In this paper, we propose a method for selecting and forming a machine and tractor fleet, which is based on the use of energy consumption through the profitability coefficient, as an indicator that is most independent of market conditions. Keywords: MACHINE AND TRACTOR FLEET, ENERGY RESOURCES, AGRICULTURAL MACHINERY, ENERGY CONSUMPTION, PROFITABILITY, PROFITABILITY COEFFICIENT, PRODUCTIVITY, EFFICIENCY

Primary, Secondary, and Tertiary Interactions for Fleet HumanRobot Interaction: Insights from Field Testing

A growing number of domains for Human-Robot and Human-Machine Interactions (HRI/HMI) will involve fleets of autonomous machines. In these fleet environments, robots will encounter not just primary interactors in one-on-one encounters, but also secondary, and even tertiary ones who are bystanders to direct human-to-robot interactions. Thus, the interaction paradigms used by such robots may need to be reconsidered to meet a growing diversity of interactions as fleet HRI/HMI applications continue to grow. Relying on use cases from field testing in mock urban environments, the purpose of this paper is to discuss our lessons learned when supporting multiple “layers” of interactors and how they relate to needs that Human Factors and Ergonomic (HF/E) science can help to address.

Optimization of Selection and Use of a Machine and Tractor Fleet in Agricultural Enterprises: A Case Study

This article presents a realized application of a model and algorithm to optimize the formation and use of a machine and tractor fleet of an agricultural enterprise in crop farming. The concepts and indicators characterizing the processes of agricultural operations of the machine fleet in the agrarian business are considered. A classification of approaches for optimizing the implementation of a complex of mechanized agro-technical operations is given. We systemize different views on the problems under study and possible solutions. The advantages of the proposed model and algorithm, as well as the problematic aspects of their information and instrumental support are discussed. The problem of choosing the optimality criterion when setting the formal problem of optimizing agricultural operations by a fleet of machines in the agricultural field is considered. A modification of the economic and mathematical model for optimizing the structure and production schedules of the machine and tractor fleet is developed. The model is applied in a numerical experiment using real data of a specific agricultural enterprise, and the economic interpretation of the results is discussed. We apply an approach for determining the economic effect of the use of the developed model and algorithm. The possibilities for practical application of the obtained results of the study are substantiated.

Intelliot: a smart IoT environment

This paper examines classic cloud-based IoT systems, typically centered on a centralized IoT platform where data is uploaded for further processing. Next-generation IoT applications are shown, incorporating technologies such as artificial intelligence, augmented reality and distributed registry to implement semi-autonomous vehicle behavior, user management and machine-to-machine interaction in a trusted manner. It is emphasized that such applications require more dynamic IoT environments that can run locally without the need to connect to the cloud. The article describes three use cases for next-generation IoT applications — in agriculture (autonomous management of fleets of agricultural machines), healthcare (IoT for remote patient monitoring) and industry (autonomous interaction between production machines). The authors identified five key component groups of a high-level representation of the IntellIoT logic architecture, which includes the five necessary components to address the identified challenges and enable the development of next-generation IoT applications. Three key concepts (Collaborative IoT, Human-in-the-loop, and Trustworthiness) that occupy an important place in the IntellIoT architecture were taken as benchmarks. The authors present current research on key factors for implementing the next generation IoT concept (the IntellIoT approach) and highlight relevant research challenges for future research on distributed, self-managed, semi-autonomous IoT applications in HITL. The paper outlines prospects for future work to improve the efficiency and reliability of computing and communication infrastructure.

Обоснование выбора режимов функционирования организационных человеко-машинных систем

The article discusses the main modes and work schedules of machine operators as part of on-farm and machine-technical stations (MTS) of organizational human-machine systems (OHMS). The graphs are presented to describe the operation mode of the main farm machinery operators. However, in the compositions of the OHMS, service units may have other operation modes. Thus, the option is given when, with the 18-hour operation mode of the main machinery operators, operators of the maintenance facility (MF) work around the clock. From the point of view of the production organization, the presence of dual-mode schedules in relatively small and concentrated OHMSs causes certain organizational difficulties. Nevertheless, the above schedules allow organizing such a double (mixed) operation mode. Keywords: MAN-MACHINE SYSTEMS, SERVICE, PERSONNEL, OPERATION MODE, OPERABILITY, MACHINE AND TRACTOR FLEET, MACHINE-TECHNICAL STATION

INCREASING THE DURABILITY OF EXTERIOR PARTS OF AGRICULTURAL MACHINERY USING COMPOSITE MATERIALS

The problem of ensuring the durability of machines is currently extremely relevant, since the aging of the fleet of machines is outpacing the pace of the necessary technical re-equipment. The use of traditional metal materials and outdated technologies in the designs of agricultural machines leads to an increase in the cost of their production, a decrease in resource and durability. The use of corrosion-resistant materials, such as polymer composites, for exterior elements allows to increase the durability of agricultural machinery and reduce corrosion-related damage. (Research purpose) To perform an analytical review of production methods by which it is possible to manufacture exterior parts of agricultural machinery from composite materials. (Materials and methods) It was determined that the material of this study is open information sources; the research method consists in the collection, study and comparative analysis of information. (Results and discussion) It was noted that the following technologies are used for the production of exterior parts of agricultural machinery: vacuum molding, contact molding, pressure impregnation, injection molding. Vacuum forming consists in the production of materials in hot form by the method of exposure to vacuum or low air pressure. Contact molding is a manual layering of reinforcing material and impregnation of each layer with resin. When impregnated under pressure, the fibrous billet is placed in the inner mold, leaving a gap that allows the resin to be injected and the fibers to be impregnated. The essence of injection molding is the forced filling of the working cavity of the metal mold with melt and the formation of the casting, which occurs under the action of the press piston. (Conclusions) Distinctive features of the exterior elements of agricultural machinery are their large overall dimensions and low requirements for the accuracy of shapes and sizes, which determines the scope of technologies possible for their manufacture. The least labor-intensive and simply implemented in a single production method is contact molding. In mass production, the most suitable method is injection molding.

SYNTHESIS OF THE MODERN AGRICULTURAL MACHINES TECHNICAL MAINTENANCE ORGANIZATION FORM, TAKING INTO ACCOUNT THE PECULIARITIES OF THE OPERATION OF THEIR HYDRAULIC DRIVES IN THE AGRICULTURAL SECTOR OF UKRAINE

The domestic scientific and methodical principles of the organization of the system of technical maintenance and repair of agricultural machines today do not fully comply with the established material and technical capabilities and market relations that have developed in the agro-industrial sector of Ukraine, directly in the context of hydraulic machines, which are equipped with modern agricultural machinery. Decomposition of the theoretical structure of the organization of technical maintenance and repair of components of agricultural machines, further analysis of its elements made it possible to identify a number of factors: subjective distribution of service personnel, improperly organized exchange of experience between equipment operators within the enterprise, no reward for independent elimination of equipment failures by own efforts, an unhealthy level of competition between equipment operators during seasonal agricultural works in accordance with the terms of their implementation, which affects the quality of repair and maintenance work of hydraulic equipment. As a result of solving the identified issues of the maintenance and repair system, a system of restrictions has been proposed, which reflects the control of the efficiency indicators of the operators of the equipment due to their compliance with the values of the performance factor of the norms of agricultural technical works, changes in the time of performing agricultural technical works and restoring the efficiency of hydraulic drives. Based on the proposals, an algorithm has also been built to eliminate the failure of machines in the organization of maintenance and repair due to the depersonalization of the items of the machine and tractor fleet. The presented form, to a greater extent, is based on the minimization of the negative effects of the human factor, which prevent the objective organization of the work of equipment operators in the agro-industrial sector of Ukraine, which allows to reduce the average downtime of equipment and the deadlines for performing agricultural technical works due to the reassessment of the role of the qualification of equipment operators in service maintenance aggregates of hydraulic systems. The theoretical efficiency of the developed form of organization of maintenance and repair of agricultural machinery will boost with an increase in the number of machines in the machine fleet of the agricultural sector, and proposals involving a change in the system of exchange of experience between machinery operators require a sufficient number of workers and machinery to ensure the possibility of solving tasks in pairs to avoid working equipment downtime.

Physics Informed Deep Learning for Tracker Fault Detection in Photovoltaic Power Plants

One of the main challenges for fault detection in commercial fleets of machines is the lack of annotated data from the faulty condition. The use of supervised algorithms for anomaly detection or fault diagnosis is often unrealistic in this case. One approach to overcome this challenge is to augment the available normal data by generating synthetic anomalous data that represents faulty conditions. In this paper we apply this approach to the detection of faults in the tracking system of solar panels in utility-scale photovoltaic (PV) power plants. We develop a physical model in order to augment the training data for a deep convolutional neural network. We show that the physics informed learning algorithm is capable of detecting faults in an accurate and robust manner under diverse weather conditions, outperforming a purely data-driven approach. Developing and testing the algorithm with real operational data ensures its efficient deployment for PV power plants that are monitored at string level. This in turn enables the early detection of root causes for power losses, thereby contributing to the accelerated adoption of solar energy at utility scale.

The Effectiveness of No­Till Sowing and Minimal Tillage in the Cultivation of Corn for Grain

It was noted that technologies of direct sowing No-till and sowing with minimal soil tillage Mini-till play an increasing role in transferring crop production to a new technological level. The comparison of the efficiency of cultivating corn for grain when using different tillage and sowing technologies revealed the inconsistency of the scientific research results.Research purpose To compare the cost-effectiveness of two technologies for cultivating corn for grain: Mini-till and the traditional one. (Materials and methods) The advantages and disadvantages of the traditional cultivation of corn for grain were considered in comparison with No-till and Mini-till sowing.Results and discussion The authors carried out field studies of the technology based on minimal tillage and minimum organic fertilizers and used for seven years in Derevyanko V.I. peasant farm (Krasnodar Krai). As a result, the operational and technological performance indicators were determined for Optima TFmaxi direct seeder aggregated with John Deere 8310RT tractor and other machines used for the main technological operations. The volumes of technological materials used were determined. A systematic analysis of the economic efficiency sources was carried out at two levels: machine and tractor fleet, technology in general.Conclusions It was determined that compared to the traditional technology, Mini-till ensures a 49-percent decrease in the labor intensity of mechanized operations, though results in a 1-percent increase in fuel consumption and a 69-percent rise in unit operating costs, which is, though, offset by a 3-ton-per-hectare, or a 43-percent, increase in the productivity of corn for grain.

Transferring the Contamination Factor between Anomaly Detection Domains by Shape Similarity

Anomaly detection attempts to find examples in a dataset that do not conform to the expected behavior. Algorithms for this task assign an anomaly score to each example representing its degree of anomalousness. Setting a threshold on the anomaly scores enables converting these scores into a discrete prediction for each example. Setting an appropriate threshold is challenging in practice since anomaly detection is often treated as an unsupervised problem. A common approach is to set the threshold based on the dataset's contamination factor, i.e., the proportion of anomalous examples in the data. While the contamination factor may be known based on domain knowledge, it is often necessary to estimate it by labeling data. However, many anomaly detection problems involve monitoring multiple related, yet slightly different entities (e.g., a fleet of machines). Then, estimating the contamination factor for each dataset separately by labeling data would be extremely time-consuming. Therefore, this paper introduces a method for transferring the known contamination factor from one dataset (the source domain) to a related dataset where it is unknown (the target domain). Our approach does not require labeled target data and is based on modeling the shape of the distribution of the anomaly scores in both domains. We theoretically analyze how our method behaves when the (biased) target domain anomaly score distribution converges to its true one. Empirically, our method outperforms several baselines on real-world datasets.

Модернизация валочно-сучкорезно-раскряжевочного механизма лесного харвестера

There is an annual increase in the number of modern forestry machines at logging enterprises both in Russia and in foreign countries. At the same time, the fleet of forestry machines is becoming more diverse and multifunctional, and their manufacturers, competing for market outlets, find themselves interested in constant upgrading of existing and development of new design and technological solutions. The research is aimed at finding a new engineering solution that will allow along with harvesting high-quality logs to perform their partial debarking without a significant reduction in the processing speed. The effective result is achieved by the fact that the proposed new method of processing tree trunks provides the possibility of timber barking in strips, i.e. removing the bark from a fallen tree along its entire length, as well as bast removal (partially or completely). The method involves, as in the traditional model of harvesting (processing) head functioning, crosscutting of the trunk by the sawing mechanism and delimbing by delimbing knives. This leads to accelerated natural drying of wood during its storage in the warehouses and significantly increases the floatability of thin coniferous logs during their further timber floating. The implementation of the proposed option of harvesting debarked timber at the logging site and the working body of harvesters (processors) to carry out such harvesting will increase the share of logging waste at the logging site. The design of the new harvesting (processing) head does not require significant financial expenses for its upgrading. The design of the new harvester head allows the logs to be barked in strips along the entire length. Additional drive of working mechanisms is not required. This will enable the implementation of rough debarking with minimal financial costs already at the stage of logging operations and increase the efficiency of logging and timber processing enterprises.