Continuous monitoring method when diagnosing the technical condition of tractors using digital systems

2021 ◽  
pp. 25-28
Author(s):  
I. A. Tishaninov
Keyword(s):  
Neural Network ◽  
Continuous Monitoring ◽  
Technical Condition ◽  
Diagnostic Process ◽  
Industrial Complex ◽  
Special Program ◽  
Monitoring Method ◽  
Engine Operation ◽  
Network Interaction ◽  
Engine Failure

The proposed method is aimed at the development and implementation of new intelligent technologies that make it possible to increase the effectiveness of the diagnostic process and the reliability of the functional technical characteristics of the engine operation of automotive equipment in the agro-industrial complex. The article presents the results on substantiation and development of a digital system based on neural network interaction. The advantage of the method is the evaluation of tractor health under the condition of automation of diagnostic processes. The ability to determine not only the cause of engine failure, but also to assess the efficiency of the agricultural machine as a whole. Proposed neural network is able to perform analysis and transfer of obtained data during diagnostics to database of special program or server.

Analysis of Hemodynamics During Blood Purification Therapy Using a Newly Developed Noninvasive Continuous Monitoring Method

2006 ◽  
Vol 10 (4) ◽  
pp. 380-386 ◽  
Author(s):  
Jun Niwayama ◽  
Takashi Sato ◽  
Mizuki Komatsu ◽  
Tsutomu Sanaka ◽  
Takeshi Kurosawa
Keyword(s):  
Continuous Monitoring ◽  
Blood Purification ◽  
Monitoring Method ◽  
Blood Purification Therapy

Application of neural network expert systems for monitoring, diagnostics and forecasting of technical condition of aircraft engines

2020 ◽  
pp. 51-59
Author(s):  
Д.О. Пушкарёв
Keyword(s):  
Neural Network ◽  
Expert Systems ◽  
Gas Turbine ◽  
Technical Condition ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Fuzzy Interference System ◽  
Interference System ◽  
Monitoring And Diagnostics ◽  
Technical Operation

Рассматривается применение нейросетевых экспертных систем в области контроля, диагностики и прогнозирования технического состояния авиационных ГТД на основе нечеткой логики. Показана методика для решения таких задач в области технической эксплуатации авиационной техники совместно с использованием фаззи-интерференсной системы программы MATLAB. Используя статистические данные о работе двигателя формируется экспертная система на основе нейронной сети позволяющая осуществлять контроль и диагностику ГТД, а также прогнозировать дальнейшее техническое состояния анализируемого двигателя. The application of neural network expert systems in the field of monitoring, diagnostics and forecasting of the technical condition of aviation gas turbine engines based on fuzzy logic is considered. The technique for solving such problems in the field of technical operation of aircraft and using the fuzzy-interference system of the MATLAB program is shown. Using statistical data on the operation of the engine, an expert system is based on the fundamental of a neural network that provide monitoring and diagnostics of gas turbine engines, as well as predicting the further technical condition of the analyzed engine.

scholarly journals Condition Monitoring of Wind Turbine Based on Copula Function and Autoregressive Neural Network

2018 ◽  
Vol 198 ◽  
pp. 04008
Author(s):  
Zhongshan Huang ◽  
Ling Tian ◽  
Dong Xiang ◽  
Sichao Liu ◽  
Yaozhong Wei
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Wind Turbine ◽  
Condition Monitoring ◽  
Copula Function ◽  
Single Step ◽  
Fusion Model ◽  
Monitoring Method ◽  
Monitoring Model ◽  
Autoregressive Neural Network

The traditional wind turbine fault monitoring is often based on a single monitoring signal without considering the overall correlation between signals. A global condition monitoring method based on Copula function and autoregressive neural network is proposed for this problem. Firstly, the Copula function was used to construct the binary joint probability density function of the power and wind speed in the fault-free state of the wind turbine. The function was used as the data fusion model to output the fusion data, and a fault-free condition monitoring model based on the auto-regressive neural network in the faultless state was established. The monitoring model makes a single-step prediction of wind speed and power, and statistical analysis of the residual values of the prediction determines whether the value is abnormal, and then establishes a fault warning mechanism. The experimental results show that this method can provide early warning and effectively realize the monitoring of wind turbine condition.

OPERATIONAL ASSESSMENT OF THE LIMIT STATE OF TRACTOR UNITS WITH THE USE OF INDICATOR COUNTERS

2021 ◽  
Vol 3 (144) ◽  
pp. 12-21
Author(s):  
Nikolay A. Petrishchev ◽  
◽  
Mikhail N. Kostomakhin ◽  
Aleksandr S. Sayapin ◽  
Igor’ M. Makarkin ◽  
...  
Keyword(s):  
Limit State ◽  
Technical Condition ◽  
Point Of View ◽  
Research Purpose ◽  
Diagnostic Tools ◽  
Diagnostic Process ◽  
Technical Documentation ◽  
Limit States ◽  
Limit Condition ◽  
Reliability Indicators

In accordance with GOST 20793-2009, the tractor and its components are subjected to resource diagnostics before maintenance. The technical condition of the components of the tractor or machine should be checked with the use of control and diagnostic equipment. Currently, the criteria for the limit state are significantly outdated and require revision from the point of view of tightening modern requirements for operational and economic characteristics and reliability indicators. (Research purpose) The research purpose is in analyzing the state of the issue and the current regulatory documentation and making proposals for remote monitoring of the criteria for the limit states of individual components and aggregates. (Materials and methods) The article presents an analysis of scientific and technical documentation, State standards of the Russian Federation and scientific papers on the problems of minimizing technological risks, diagnostics and control suitability for determining the maximum technical condition, and staged studies on the possibility of monitoring the operation of individual components and units online. The article notes the need to adjust the criteria for the maximum technical condition in accordance with the new designs of resource-determining units, aggregates and existing technical regulations. (Results and discussion). The article presents the justification of the diagnostic process and identified contradictions in the design of tractors and existing scientific and technical documentation and standards, and proposed option of using meters-identifiers when upgrading tractors as a system of built-in online diagnostic tools. (Conclusions) Timely, automated monitoring of the technical condition of tractors, which is based on comparing data with the criteria of the limit condition, serves as a justification for the effective operation of equipment with built-in devices for diagnostics, which allows minimizing agrotechnological risks.

Real-time fault monitoring method of charging pile based on improved RNN neural network

2021 ◽  
Author(s):  
Jian Zhang ◽  
Dan Li ◽  
Qin Xie ◽  
Weidong Liu ◽  
Bin Liang
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Monitoring Method ◽  
Fault Monitoring

Monitoring the technical condition of the railway track using the method of continuous recording of dynamic processes occurring due to the interaction between rolling stock and railway track

2021 ◽  
pp. 66-82
Author(s):  
Yuriy P. BORONENKO ◽  
◽  
Aleksandr V. TRET’YAKOV ◽  
Rustam V. RAKHIMOV ◽  
Mariya V. ZIMAKOVA ◽  
...  
Keyword(s):  
Practical Importance ◽  
Stability Margin ◽  
Technical Condition ◽  
Continuous Recording ◽  
Railway Track ◽  
Lateral Interaction ◽  
Rolling Stock ◽  
Monitoring Method ◽  
Wheel Pair ◽  
Interaction Forces

Objective: To develop the method to monitor the technical condition of the railway track. Me-thods: A strain-gauge wheel pair is used for continuous recording of vertical and lateral interaction forces in a dynamic wheel–rail system. Results: Stability margin factors of a wagon relative to de-railment have been determined and the defective (prone to derailment) sections of a railway track have been identified with the exact identification of their location (GPS coordinates) on the map using navigation devices. Practical importance: The developed monitoring method makes it possi-ble to promptly re¬gister and eliminate railway track defects

Predictive analytics of the technical condition of diesel locomotive systems using neural network predictive models

2021 ◽  
pp. 102-114
Author(s):  
Mikhail V. FEDOTOV ◽  
◽  
Vladimir V. GRACHEV ◽  
Keyword(s):  
Neural Network ◽  
Predictive Model ◽  
Predictive Models ◽  
Short Term Memory ◽  
Predictive Analytics ◽  
Practical Importance ◽  
Technical Condition ◽  
Feedforward Neural Network ◽  
Diesel Locomotive ◽  
Short Term

Objective: Study of the possibility of carrying out predictive analysis of the technical condition of locomotive equipment using neural network predictive models enabling to plan the scope of equipment maintenance for routine types of maintenance and repair. Methods: A comparative assessment of the accuracy of forecasts made using a feedforward neural network and a recurrent network with an LSTM layer (Long Short-Term Memory) has been carried out. For training and test-ing of predictive models, we used the results of monitoring the parameters of the lubrication sys-tem of the 2TE116 (2ТЭ116) diesel locomotive by means of on-board diagnostics. Results: The aver-age interval for preventive inspections (TO-3) of locomotives in the existing locomotive mainte-nance system is 25–30 days, and therefore it is this interval that determines the minimum duration of the lead-in period, which the predictive model should provide. We have established that a mod-el based on a feedforward neural network provides sufficient accuracy only for short-term fore-casts with a lead period of no more than 1–3 days. With a further increase in the lead-in period, the error of the model res¬ponse increases to 10–15 %, which prevents it from being effectively used for solving practical problems associated with planning the operation of service locomotive depots. At the same time, the ave¬rage response error of the predictive model based on a recurrent net-work with an LSTM layer does not exceed 3,5–5 % over a 30-day lead-in period, so it can be used to plan the scope and timing of locomotive maintenance procedures. Practical importance: The possi-bility of using time-series analysis methods for predictive analytics of the technical condition of units and systems of a locomotive is shown. Predictive models based on recurrent neural networks with LSTM layers provide prediction accuracy and lead-in period sufficient for solving practical prob-lems that are associated with planning the scope and timing of locomotive maintenance.

scholarly journals Non-Intrusive Monitoring Algorithm for Resident Loads with Similar Electrical Characteristic

Processes ◽  
2020 ◽  
Vol 8 (11) ◽  
pp. 1385
Author(s):  
Sheng Wu ◽  
Kwok L. Lo
Keyword(s):  
Neural Network ◽  
Probability Distribution ◽  
Bp Neural Network ◽  
Distribution Curve ◽  
Electrical Characteristics ◽  
Monitoring Methods ◽  
Monitoring Method ◽  
Current Frequency ◽  
Operation Pattern ◽  
Load Monitoring

Non-intrusive load monitoring is a vital part of an overall load management scheme. One major disadvantage of existing non-intrusive load monitoring methods is the difficulty to accurately identify loads with similar electrical characteristics. To overcome the various switching probability of loads with similar characteristics in a specific time period, a new non-intrusive load monitoring method is proposed in this paper which will modify monitoring results based on load switching probability distribution curve. Firstly, according to the addition theorem of load working currents, the complex current is decomposed into the independently working current of each load. Secondly, based on the load working current, the initial identification of load is achieved with current frequency domain components, and then the load switching times in each hour is counted due to the initial identified results. Thirdly, a back propagation (BP) neural network is trained by the counted results, the switching probability distribution curve of an identified load is fitted with the BP neural network. Finally, the load operation pattern is profiled according to the switching probability distribution curve, the load operation pattern is used to modify identification result. The effectiveness of the method is verified by the measured data. This approach combines the operation pattern of load to modify the identification results, which improves the ability to identify loads with similar electrical characteristics.

Preliminary Study of Fuel Injector Monitoring System by I-KazTM Multilevel Analysis

2013 ◽  
Vol 471 ◽  
pp. 229-234
Author(s):  
Zailan Karim ◽  
M.A. Jusoh ◽  
A.R. Bahari ◽  
Mohd Zaki Nuawi ◽  
Jaharah Abd. Ghani ◽  
...  
Keyword(s):  
Monitoring System ◽  
Single Channel ◽  
Injection System ◽  
Fuel Injector ◽  
Monitoring Method ◽  
Engine Operation ◽  
Automotive Engine ◽  
Actual Operation ◽  
Pressure Bar ◽  
The Relationship

Fuel injector in automotive engine is a very important component in injecting the correct amount of fuel into the combustion chamber. The injection system need to be in a very safe and optimum condition during the engine operation. The mulfunction of the injection system can be avoided if the current working condition is known and a proper maintenence procedure is implemented. This paper proposes the development of a fuel injector monitoring method using strain signals captured by a single-channel strain gage attached on the fuel injector body. The fuel injector was operated under three main sets of parameters; pulse width (ms), frequency (Hz) and pressure (bar) which were varried from 5 ms to 15 ms, 17 Hz to 25 Hz and 10 bar to 70 bar respectively. The settings produce 27 different engine operations and the strain signal will be captured at each operation. The captured strain signals will be analyzed using I-kazTM Multilevel technique and will be correlated with the main parameters. The relationship between the I-kazTM Multilevel coefficient and the main parameters indicate good correlations which can be used as the guidance for fuel injector monitoring during actual operation. The I-kaz Multilevel technique was found to be very suitable in this study since it is capable of showing consistence pattern change at every parameter change during the engine operation. This monitoring system has a big potential to be developed and improved for the optimization of fuel injector system performance in the automotive industry.

Sign in / Sign up

Export Citation Format

Share Document