Application of neural networks to forecast changes in the technical condition of critical production facilities

2021 ◽  
Vol 93 ◽  
pp. 107225
Author(s):  
Vitaliy Yemelyanov ◽  
Sergei Chernyi ◽  
Nataliya Yemelyanova ◽  
Vijayakumar Varadarajan
Keyword(s):  
Neural Networks ◽  
Technical Condition ◽  
Critical Production ◽  
Production Facilities

scholarly journals The Mathematical Models of the Operation Process for Critical Production Facilities Using Advanced Technologies

Inventions ◽  
2021 ◽  
Vol 7 (1) ◽  
pp. 8
Author(s):  
Vitaliy A. Yemelyanov ◽  
Anton A. Zhilenkov ◽  
Sergei G. Chernyi ◽  
Anton Zinchenko ◽  
Elena Zinchenko
Keyword(s):  
Metallurgical Industry ◽  
Mathematical Study ◽  
Advanced Technologies ◽  
Utilization Coefficient ◽  
Operation Process ◽  
Optimal Period ◽  
Different Types ◽  
Preventive Diagnostics ◽  
Critical Production ◽  
Production Facilities

The paper presents data on the problems of monitoring and diagnosing the technical conditions of critical production facilities, such as torpedo ladle cars, steel ladles. The accidents with critical production facilities, such as torpedo ladle cars, lead to losses and different types of damages in the metallurgical industry. The paper substantiates the need for a mathematical study of the operation process of the noted critical production facilities. A Markovian graph has been built that describes the states of torpedo ladle cars during their operation. A mathematical model is presented that allows determining the optimal frequency of diagnostics of torpedo ladle cars, which, in contrast to the existing approaches, take into account the procedures for preventive diagnostics of torpedo ladle cars, without taking them out of service. Dependence of the utilization coefficient on the period of diagnostics of PM350t torpedo ladle cars was developed. The results (of determining the optimal period of diagnostics for PM350t torpedo ladle cars) are demonstrated. The system for automated monitoring and diagnosing the technical conditions of torpedo ladle cars, without taking them out of service, has been developed and described.

Risk Regulation and Management Related to the Operation of Hazardous Production Facilities

2020 ◽  
pp. 85-91
Author(s):  
N.A. Makhutov ◽  
◽  
D.O. Reznikov ◽  
M.V. Lisanov ◽  
◽  
...  
Keyword(s):  
Safety Management ◽  
Technical Condition ◽  
Industrial Safety ◽  
Quantitative Risk Assessment ◽  
Necessary Condition ◽  
Individual Risk ◽  
Average Risk ◽  
Monitoring And Control ◽  
Hazardous Production ◽  
Production Facilities

The paper examines the types of uncertainties associated with operation of hazardous production facilities caused by the natural variability of the facility parameters and the limited knowledge about complex processes in the system under consideration, as well as the uncertainty of the results of quantitative risk assessment. Qualitative and quantitative criteria of tolerable (acceptable) risk adopted in various countries of the world are presented. The article considers the operation of the ALARP principle in making managerial decisions on the need to implement protective measures aimed at reducing individual risk, which allows to provide a compromise between competing requirements for ensuring safety and economic efficiency in the operation of hazardous production facilities. In the future of socio-economic development, due to the improvement of existing and the emergence of new safety technologies, the maximum allowable and acceptable levels of risk should be revised in order to meet more stringent safety requirements. Therefore, the value of tolerable individual risk in case of accidents at hazardous production facilities may not be a strictly specified value (as is generally accepted), but may decrease as the reliability of technological systems increases, the efficiency of industrial safety management increases, and the background (average) risk of mortality decreases. A necessary condition for implementing a risk management system is to improve the efficiency of the system for collecting and analyzing data on reliability, accident rate, monitoring and control of technical condition at hazardous production facilities, and further develop the methodological support for risk analysis within the framework of the currently implemented risk-oriented approach in the field of industrial safety.

Monitoring of Technical Condition of Technical Devices at Hazardous Production Facilities

2020 ◽  
pp. 52-56
Author(s):  
O.A. Bardyshev ◽  
◽  
V.A. Popov ◽  
S.K. Korovin ◽  
A.N. Filin ◽  
...  
Keyword(s):  
Technical Condition ◽  
Hazardous Production ◽  
Production Facilities

scholarly journals Automatic diagnostic of transmission lines based on ultraviolet inspection

2019 ◽  
Vol 140 ◽  
pp. 07008
Author(s):  
Phuong Nguyen ◽  
Sergey Dudkin ◽  
Chenzai Kong
Keyword(s):  
Neural Networks ◽  
Unmanned Aerial Vehicle ◽  
Transmission Lines ◽  
Power Plants ◽  
Electrical Equipment ◽  
Scientific Basis ◽  
Technical Condition ◽  
Power Lines ◽  
Actual Problem ◽  
Aerial Vehicle

Evaluation of the technical condition, reliability of the insulation of electrical equipment is an actual problem. It is confirmed by experience and statistics of operation at power plants and railway facilities. The combination of an unmanned aerial vehicle with UV-camera and software based on neural networks allows us to effectively diagnose long power lines. To increase the effectiveness of non-contact inspection of power lines, especially in hard-to-reach areas, more compact mobile solutions should be used which include an UV-camera and an unmanned aerial vehicle (UAV). The aircraft market currently has significant growth, that allows to bring the diagnostic experience to a new level by attaching an UV-camera to an aerial device, which will have a tremendous effect on examining long power lines. But we faced one problem related to the absence of any scientific basis for this method of examination, so it was decided to conduct experiments in a laboratory of St. Petersburg Polytechnic University. The results of experiments are presented in the work.

scholarly journals Using of Artificial Neural Networks in Support System of Forensic Building-Technical Expertise

2020 ◽  
Vol 9 (4) ◽  
pp. 3162-3168 ◽  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Technical Condition ◽  
Fuzzy Neural Networks ◽  
Impact Factors ◽  
Technical Expertise ◽  
Structural Elements ◽  
Resonance Theory ◽  
Artificial Neural ◽  
The Impact

The article contains an analysis of the order of forensic building-technical expertise and expert research to determine the reasons for the deterioration of the technical condition of the structural elements of buildings. The conditions for forming expert conclusions about the possible correlation between the appearance of negative changes in the technical condition of the structural elements that have become the subject of forensic building-technical expertise and the various factors of influence of the environment are investigated. In doing so, the focus is on the impact factors associated with carrying out renovation work in adjacent premises. In addition, issues related to the fuzzy uncertainty of the different nature of the expert researches are highlighted. Some of these problems are proposed to be solved by the using of artificial neural networks in the fuzzy subsystem of the system of support of forensic building-technical expertise. It is shown that a considerable part of the materials of forensic building-technical expertise and expert research is represented by photographs of injuries. Fixation of damaged structures is reflected in the plans of premises and schemes of placement of structures in the buildings. The graphic information of the research materials is accompanied by textual information, the processing of which requires the use of models and methods of fuzzy mathematics. The fragment of the knowledge base is provided, which contains information on the geometric parameters of damage to building structures and an example of a fuzzy rule that reflects an expert conclusion. The expediency of using fuzzy neural networks of adaptive resonance theory of the Cascade ARTMAP category is substantiated. Cascade ARTMAP memory card schematic is shown.

scholarly journals Neural network technique when distribution of vehicle component parts on the technological repair routes, taking into account their technical condition

2018 ◽  
Vol 170 ◽  
pp. 05011
Author(s):  
Valentin Krasovsky ◽  
Nina Krasovskaya ◽  
Victor Poptsov ◽  
Irina Nordman
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Oil And Gas ◽  
Technical Condition ◽  
Probabilistic Methods ◽  
Practical Application ◽  
Repair Work ◽  
Vehicle Component ◽  
Repair Enterprise ◽  
Artificial Neural

Increase of repair efficiency is achieved due to the formation of centralized specialized production facilities which implement the vehicle component parts repair technique with the use of industrial technological processes to restore the technical state of the units and their components. In this case, the establishment of the expediency of sending the unit to repair, as well as the defining of volumes and nomenclature for necessary repair actions, should be performed at the stage of pre-repair diagnosis for each individual unit taking into account its actual technical condition. However, the effectiveness of pre-repair diagnosis using both deterministic and probabilistic methods of processing and analyzing the information obtained is significantly reduced by the presence of errors in the recognition of defects and the distribution of aggregates in accordance with the repair work variety preformed at the repair enterprise. Using promising cognitive technology based on neural networks it is possible to completely avoid the losses associated with the repetition of repair work. Therefore, the formation of scientific and methodological bases for the development, training and practical application of artificial neural networks in the subsystems of the pre-repair diagnosis of the repair fund of automobile vehicle omponent parts is an important and urgent task. The paper presents the results of analytical studies and a number of original techniques for the formation of scientific and methodological foundations for the development, training and practical application of artificial neural networks in the process of diagnosis the car vehicle component parts and special oil and gas equipment entering the centralized repair according to their technical condition

scholarly journals Locomotive asynchronous traction motor rolling bearing fault detection based on current intelligent methods

2021 ◽  
Vol 2131 (4) ◽  
pp. 042084
Author(s):  
O R Khamidov ◽  
A V Grishchenko
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Detection ◽  
Network Model ◽  
Neural Network Model ◽  
Technical Condition ◽  
Traction Motors ◽  
Squirrel Cage ◽  
Asynchronous Traction Motor ◽  
Intelligent Methods

Abstract The paper is devoted to current issues of locomotive asynchronous traction motor (ATEM) fault detection using neural networks. Developed sophisticated intelligent methods for monitoring and inspecting the technical condition of ATE bearings. Current absorption spectra are analysed to assess the technical condition of the induction bearing units. The mechanical vibration frequencies of a squirrel cage induction motor are presented. The method of artificial neural networks which are universal approximators and can effectively and efficiently solve problems of monitoring and diagnostics of technical condition of locomotive induction traction motors is applied. A neural network model and framework for monitoring the technical condition of ATED bearings has been developed. They are based on rules and user-provided facts to recognise the situation, make a diagnosis, formulate a solution or make a recommendation. The main failures of the bearing units of squirrel cage ATED are analysed. A methodology has been developed to build a neural network model of the ATED. The structure and architecture of the artificial neural network is defined. An experimental research has been conducted. The results enable the determination of bearing faults in asynchronous traction motors with squirrel cage rotor.

scholarly journals Information technology of monitoring technical condition of torpedo ladle cars based on neural networks

2018 ◽  
Vol 1118 ◽  
pp. 012051
Author(s):  
V A Yemelyanov ◽  
T E Tochilkina ◽  
E V Vasilieva ◽  
E A Deeva ◽  
A A Nedelkin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Information Technology ◽  
Technical Condition

scholarly journals The Use of Deep Learning Methods in Diagnosing Rotating Machines Operating in Variable Conditions

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4231
Author(s):  
Paweł Pawlik ◽  
Konrad Kania ◽  
Bartosz Przysucha
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Technical Condition ◽  
Variable Load ◽  
Efficient System ◽  
New Approach ◽  
Load Variations ◽  
Current Consumption ◽  
Damage States ◽  
Drive Systems

This paper presents the use of artificial neural networks in diagnosing the technical condition of drive systems operating under variable conditions. The effects of temperature and load variations on the values of diagnostic parameters were considered. An experiment was conducted on a testing rig where a variable load was introduced corresponding to the load of the main gearbox of the bucket wheel excavator. The signals of vibration acceleration on the gearbox body, rotational speed, and current consumption of the drive motor for different values of oil temperature were measured. Synchronous analysis was performed, and the values of order amplitudes and the corresponding values of current, speed, and temperature were determined. Such datasets were the learning vectors for a set of artificial deep learning neural networks. A new approach proposed in this paper is to train the network using a learning set consisting only of data from the efficient system. The responses of the trained neural networks to new data from the undamaged system were performed against the response to data recorded for three damage states: misalignment, unbalance, and simultaneous misalignment and unbalance. As a result, a diagnostic parameter as a normalized measure of the deviation of the network results was developed for the faulted system from the result for the undamaged condition.

Sign in / Sign up

Export Citation Format

Share Document