ABSTRACT
The health of DC-DC power supply is the key factor to determine the normal operation of electronic equipment. In this paper, according to the actual test data of the maximum temperature of the DC-DC power module, the variation characteristics of the actual collected data and reasonable reasoning assumptions, we constructed the variation of the maximum temperature of the power module during the degradation process in a period of time by means of stochastic simulation. On this basis, the LSTM network model of the maximum temperature time series of the power module is established to predict the change rule of the temperature time series of the power module. Since the constructed temperature samples cover a large time range, we use the fusion processing method of data samples to further reduce the sample set. The modeling and data analysis show that the LSTM prediction model of the maximum temperature of power module constructed in this paper has high accuracy, and has certain theoretical and engineering value for the practice of health management of DC-DC power supply.
- Dalal M , Ma J , He D . Lithium-ion battery life prognostic health management system using particle filtering framework[J]. Journal of Risk & Reliability, 2011, 225(1):81-90.Google ScholarCross Ref
- Agarwal V , Lybeck N , Pham B T , Prognostic and health management of active assets in nuclear power plants[J]. International Journal of Prognostics and Health Management, 2015, 6:1-17.Google Scholar
- Li R , Verhagen W , Curran R . A systematic methodology for Prognostic and Health Management system architecture definition[J]. Reliability Engineering & System Safety, 2020,(Jan. 193) : 106598.1 to 106598.19.Google ScholarCross Ref
- Jia X , Gao H , Huang J . Uncertainty Analysis of Fault Prediction for DC-DC Power Module Based on Bayesian Network[J]. Electronics & Packaging, 2019.Google Scholar
- YU S, XU Z W, DONG J Q. Analysis of Capacitor Life Prediction in Switching Power Supply [J]. Journal of Power Supply, 2016,14 (6) : 87-92.Google Scholar
- Wang F R , Ping Y U. Approach of state determination for secondary electrical power source based on Mahalanobis distance[J]. Transducer and Microsystem Technologies, 2016.Google Scholar
- Wu Y , Wang Y , Jiang Y , Fault prediction method of DC/DC converter based on characteristic parameter degradation[J]. Chinese Journal of entific Instrument, 2013, 34(6):1380-1387.Google Scholar
- Sundermeyer M, R Schluter, Ney H. LSTM Neural Networks for Language Modeling[C]// Interspeech. 2012.Google Scholar
- Wen T H , Gasic M , Mrksic N , Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems[J]. Computer Science, 2015.Google Scholar
- Rubwurm M ,Korner M . Temporal Vegetation Modelling using Long Short-Term Memory Networks for Crop Identification from Medium-Resolution Multi-Spectral Satellite Images[C]// IEEE Conference on Computer Vision &Pattern Recognition. IEEE, 2017:1496-1504.Google Scholar
Recommendations
Degradation Characteristics Analysis and Fault Prediction of Switching Power Supply Based on Data Mining
MLMI '21: Proceedings of the 2021 4th International Conference on Machine Learning and Machine IntelligenceFault prediction and health monitoring of DC-DC switching power supply plays an important role in the safe and reliable operation of power electronic equipment. In this paper, a long-term high temperature degradation test was carried out for DC-DC power ...
LSTM-based indoor air temperature prediction framework for HVAC systems in smart buildings
AbstractAccurate indoor air temperature (IAT) predictions for heating, ventilation, and air conditioning (HVAC) systems are challenging, especially for multi-zone building and for different HVAC system types. Moreover, the nonlinearity of the buildings ...
Comments