Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00067
Syed Meesam Raza Naqvi, Mohammad Ghufran, Safa Meraghni, C. Varnier, J. Nicod, N. Zerhouni
Recently, Prognostics and Health Management (PHM) has emerged to promote predictive maintenance as a methodological key to overcome the limitations of traditional reliability analysis. The Natural Language Processing (NLP) methods allow the maintenance log usage for maintenance diagnostics and decision making. The Maintenance Work Orders (MWOs) contain vital health indicators and decades of experience related to various maintenance actions. However, due to the unstructured nature of maintenance text, it is not common to develop a tool using these textual maintenance entries. This paper proposes a textual Case-Based Reasoning (CBR) approach combined with Technical Language Processing (TLP) to find solutions for new problems based on previous experiences. The Bidirectional Encoder Representations from Transformers (BERT) model is adopted for maintenance data using unsupervised finetuning technique Transformer-based Sequential Denoising AutoEncoder (TSDAE) for aviation case study. Results show that the pre-trained BERT model can adopt domain-specific data and produce semantic matches with only a small amount (1000 samples) of domain specific data.
{"title":"CBR-Based Decision Support System for Maintenance Text Using NLP for an Aviation Case Study","authors":"Syed Meesam Raza Naqvi, Mohammad Ghufran, Safa Meraghni, C. Varnier, J. Nicod, N. Zerhouni","doi":"10.1109/PHM2022-London52454.2022.00067","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00067","url":null,"abstract":"Recently, Prognostics and Health Management (PHM) has emerged to promote predictive maintenance as a methodological key to overcome the limitations of traditional reliability analysis. The Natural Language Processing (NLP) methods allow the maintenance log usage for maintenance diagnostics and decision making. The Maintenance Work Orders (MWOs) contain vital health indicators and decades of experience related to various maintenance actions. However, due to the unstructured nature of maintenance text, it is not common to develop a tool using these textual maintenance entries. This paper proposes a textual Case-Based Reasoning (CBR) approach combined with Technical Language Processing (TLP) to find solutions for new problems based on previous experiences. The Bidirectional Encoder Representations from Transformers (BERT) model is adopted for maintenance data using unsupervised finetuning technique Transformer-based Sequential Denoising AutoEncoder (TSDAE) for aviation case study. Results show that the pre-trained BERT model can adopt domain-specific data and produce semantic matches with only a small amount (1000 samples) of domain specific data.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134166809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A data-driven lifetime prediction is proposed and implemented on the power module in this paper. Insulated gate bipolar transistors (IGBTs) are widely used in various power electronic converter systems. The IGBT modules suffering failure may influence the reliability of the power systems enormously. Thus, it is significate to accurately predict the remaining useful life (RUL) of this critical component. Based on the wide-used particle filter (PF) prediction algorithm, the particle swarm optimization (PSO) is combined to optimize the step of sequential important resampling in PF and solve the particle impoverishment problem. In addition, a power cycling test is designed, which is conducted to obtain the degradation data under specified operating stress. The method in this paper can effectively process the experimental results under power cycling tests.
{"title":"Remaining Useful Life Prediction of IGBT Module Based on Particle Filter Combining with Particle Swarm Optimization","authors":"Maogong Jiang, Qianqian Lv, Peilei Li, Hantian Gu, Chongyang Gu, Wei Zhang, Guicui Fu","doi":"10.1109/PHM2022-London52454.2022.00031","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00031","url":null,"abstract":"A data-driven lifetime prediction is proposed and implemented on the power module in this paper. Insulated gate bipolar transistors (IGBTs) are widely used in various power electronic converter systems. The IGBT modules suffering failure may influence the reliability of the power systems enormously. Thus, it is significate to accurately predict the remaining useful life (RUL) of this critical component. Based on the wide-used particle filter (PF) prediction algorithm, the particle swarm optimization (PSO) is combined to optimize the step of sequential important resampling in PF and solve the particle impoverishment problem. In addition, a power cycling test is designed, which is conducted to obtain the degradation data under specified operating stress. The method in this paper can effectively process the experimental results under power cycling tests.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134195661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00056
Chao Lou, Wang Luo, Dequan Gao, Z. Zhao, Fenggang Lai, Shengya Han, Chao Ma
Cloud Data Center (CDC) has the characteristics of multi-level and multi-domain complex system relations. It is difficult to analyze the alarm information manually to obtain the fault devices and fault cause. In this paper, a knowledge graph is used to track the dynamic changes of CDC topology, and Bayesian Network (BN) diagnosis model with probability attribute is dynamically generated through graph search. Firstly, based on the dynamic topology of CDC tracked in the KG, and the collected fault symptoms from the server log, the graph search is carried out to construct the BN topology, which contains possible fault devices, fault modes and causes. Then with the proposed Causality Strength and Leakage Probability, which could be stored in the KG database, the Condition Probability Table is calculated. Combined with the a priori probability, the Bayesian Network model is established. Finally, the fault cause with the largest a posteriori probability is obtained through the calculation of BN. If the fault cannot be solved by eliminating this cause, reason again with the rest causes. During the maintenance process, constantly update the fault symptoms and causes to make the BN model more accurate. Two fault diagnosis cases show that this method is of great significance to the operation and maintenance of CDC.
{"title":"Research on Diagnostic Reasoning of Cloud Data Center Based on Bayesian Network and Knowledge Graph","authors":"Chao Lou, Wang Luo, Dequan Gao, Z. Zhao, Fenggang Lai, Shengya Han, Chao Ma","doi":"10.1109/PHM2022-London52454.2022.00056","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00056","url":null,"abstract":"Cloud Data Center (CDC) has the characteristics of multi-level and multi-domain complex system relations. It is difficult to analyze the alarm information manually to obtain the fault devices and fault cause. In this paper, a knowledge graph is used to track the dynamic changes of CDC topology, and Bayesian Network (BN) diagnosis model with probability attribute is dynamically generated through graph search. Firstly, based on the dynamic topology of CDC tracked in the KG, and the collected fault symptoms from the server log, the graph search is carried out to construct the BN topology, which contains possible fault devices, fault modes and causes. Then with the proposed Causality Strength and Leakage Probability, which could be stored in the KG database, the Condition Probability Table is calculated. Combined with the a priori probability, the Bayesian Network model is established. Finally, the fault cause with the largest a posteriori probability is obtained through the calculation of BN. If the fault cannot be solved by eliminating this cause, reason again with the rest causes. During the maintenance process, constantly update the fault symptoms and causes to make the BN model more accurate. Two fault diagnosis cases show that this method is of great significance to the operation and maintenance of CDC.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133131127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00009
Baoqi Xie, Yingshun Li, Haiyang Liu, Xing-dang Kang, Yang Zhang
The tank fire control system plays a very important role in today's war. With the development of science and technology, the fire control system has become more modern. Taking the fire control computer as an example, this paper proposes a fault prediction method using rough set and neural network. First, according to the grey relational analysis technology and rough set theory, the original fault decision table is reduced by attributes. Then delete the redundant and invalid attribute data in the original data, and finally use the reduced rough set data as the input of the BP neural network to complete the failure prediction of the fire control computer. This method not only improves the efficiency and accuracy of failure prediction, but also reduces the maintenance cost of the fire control system.
{"title":"Fault prediction of fire control system based on Grey rough set and BP neural network","authors":"Baoqi Xie, Yingshun Li, Haiyang Liu, Xing-dang Kang, Yang Zhang","doi":"10.1109/PHM2022-London52454.2022.00009","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00009","url":null,"abstract":"The tank fire control system plays a very important role in today's war. With the development of science and technology, the fire control system has become more modern. Taking the fire control computer as an example, this paper proposes a fault prediction method using rough set and neural network. First, according to the grey relational analysis technology and rough set theory, the original fault decision table is reduced by attributes. Then delete the redundant and invalid attribute data in the original data, and finally use the reduced rough set data as the input of the BP neural network to complete the failure prediction of the fire control computer. This method not only improves the efficiency and accuracy of failure prediction, but also reduces the maintenance cost of the fire control system.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"233 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115091538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00055
Adaiton Moreira De Oliveira-Filho, Philippe Cambron, Antoine Tahan
This work improves a condition monitoring approach for wind turbine main bearings based on data from the supervisory control and data acquisition system, and on the principle of energy conservation. Previous works have proposed a main bearing temperature parametric model which residue in respect to measured data was used to detect main bearing degradation. Such an approach allowed detections with anticipation of the failure of around one month for the analyzed case studies, showing therefore a good potential for industrial applications. The present work investigates a relaxed formulation of the parametric model and introduces a novel detection criterion based on the model coefficients. This new formulation is evaluated within an operating wind farm, showing improved detection capabilities, and longer anticipation of failures.
{"title":"Condition Monitoring of Wind Turbine Main Bearing Using SCADA Data and Informed by the Principle of Energy Conservation","authors":"Adaiton Moreira De Oliveira-Filho, Philippe Cambron, Antoine Tahan","doi":"10.1109/PHM2022-London52454.2022.00055","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00055","url":null,"abstract":"This work improves a condition monitoring approach for wind turbine main bearings based on data from the supervisory control and data acquisition system, and on the principle of energy conservation. Previous works have proposed a main bearing temperature parametric model which residue in respect to measured data was used to detect main bearing degradation. Such an approach allowed detections with anticipation of the failure of around one month for the analyzed case studies, showing therefore a good potential for industrial applications. The present work investigates a relaxed formulation of the parametric model and introduces a novel detection criterion based on the model coefficients. This new formulation is evaluated within an operating wind farm, showing improved detection capabilities, and longer anticipation of failures.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"297 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114442066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00102
Chen Feng, Xiaochen Liu, Shulei Bi, Jian Kang
In order to solve the problem of equipment degradation state assessment, one idea was to use data-driven method to build equipment health state model and evaluate equipment degradation based on residual. However, most current data-driven models revealed the correlation between condition monitoring variables and equipment state rather than the causal relationship, so the rationality of the model construction lacked explanation. Therefore, causality discovery algorithm was introduced in this work to find variables that were causally related to degradation state to build a state model and improve the interpretability of the model. In this paper, the COmbined Diesel eLectric And Gas (CODLAG) Propulsion system degradation dataset was used for experiments. The Fast Causal Inference (FCI) algorithm was used to discover the causal relationships among the variables, as shown in the causal graph. Based on the causal graph, 4 groups of variables were selected to train the Long Short Term Memory (LSTM) neural networks as models to assess the degradation state. The experimental results showed that those variables that had strong causal relationships with the equipment state were sufficient for the training of the model. And the trained LSTM neural network had good performance for the degradation state assessment. More importantly, the model trained by this way had better interpretability.
为了解决设备退化状态评估问题，一种思路是采用数据驱动的方法建立设备健康状态模型，基于残差对设备退化进行评估。然而，目前大多数数据驱动模型揭示了状态监测变量与设备状态之间的相关关系，而不是因果关系，因此模型构建的合理性缺乏解释。因此，本文引入因果关系发现算法，寻找与退化状态有因果关系的变量，建立状态模型，提高模型的可解释性。本文利用CODLAG (COmbined Diesel - eLectric And Gas)推进系统退化数据集进行实验。使用快速因果推理(Fast Causal Inference, FCI)算法发现变量之间的因果关系，如图所示。基于因果图，选择4组变量训练长短期记忆(LSTM)神经网络作为模型来评估退化状态。实验结果表明，那些与设备状态有较强因果关系的变量足以用于模型的训练。训练后的LSTM神经网络具有良好的退化状态评估性能。更重要的是，通过这种方式训练的模型具有更好的可解释性。
{"title":"Degradation State Assessment Modeling Using Causality Discovery","authors":"Chen Feng, Xiaochen Liu, Shulei Bi, Jian Kang","doi":"10.1109/PHM2022-London52454.2022.00102","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00102","url":null,"abstract":"In order to solve the problem of equipment degradation state assessment, one idea was to use data-driven method to build equipment health state model and evaluate equipment degradation based on residual. However, most current data-driven models revealed the correlation between condition monitoring variables and equipment state rather than the causal relationship, so the rationality of the model construction lacked explanation. Therefore, causality discovery algorithm was introduced in this work to find variables that were causally related to degradation state to build a state model and improve the interpretability of the model. In this paper, the COmbined Diesel eLectric And Gas (CODLAG) Propulsion system degradation dataset was used for experiments. The Fast Causal Inference (FCI) algorithm was used to discover the causal relationships among the variables, as shown in the causal graph. Based on the causal graph, 4 groups of variables were selected to train the Long Short Term Memory (LSTM) neural networks as models to assess the degradation state. The experimental results showed that those variables that had strong causal relationships with the equipment state were sufficient for the training of the model. And the trained LSTM neural network had good performance for the degradation state assessment. More importantly, the model trained by this way had better interpretability.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134565596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the aviation field, people have always paid great attention to flight safety. Various sensors are often placed on the aircraft to detect the structural health of the aircraft, so as to ensure the safe life of the aircraft and reduce the occurrence of safety accidents. Along with the rapid development of sensor technology, sensor networks with sensing ability, computing ability and wireless communication ability are developing rapidly, and the advantages of wireless sensor networks in aviation monitoring are becoming more and more obvious. However, there may be malicious attack nodes in actual wireless sensor networks. It tampers with its own observation data to interfere with or attack the whole network. When wireless sensor networks are in an insecure environment, it will affect information transmission and parameter estimation. On this basis, this paper proposes a distributed diffusion least mean square algorithm based on single channel communication to detect and eliminate Byzantine attacks on special nodes. Through MATLAB simulation, the proposed algorithm has high feasibility, reduces the traffic and can get good parameter estimation.
{"title":"Aircraft sensor fault detection based on SLD-LMS algorithm","authors":"Ting Ma, Sensen Zhu, Zihang Ge, Fangyi Wan, Chunlin Zhang, Guanghui Liu","doi":"10.1109/PHM2022-London52454.2022.00051","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00051","url":null,"abstract":"In the aviation field, people have always paid great attention to flight safety. Various sensors are often placed on the aircraft to detect the structural health of the aircraft, so as to ensure the safe life of the aircraft and reduce the occurrence of safety accidents. Along with the rapid development of sensor technology, sensor networks with sensing ability, computing ability and wireless communication ability are developing rapidly, and the advantages of wireless sensor networks in aviation monitoring are becoming more and more obvious. However, there may be malicious attack nodes in actual wireless sensor networks. It tampers with its own observation data to interfere with or attack the whole network. When wireless sensor networks are in an insecure environment, it will affect information transmission and parameter estimation. On this basis, this paper proposes a distributed diffusion least mean square algorithm based on single channel communication to detect and eliminate Byzantine attacks on special nodes. Through MATLAB simulation, the proposed algorithm has high feasibility, reduces the traffic and can get good parameter estimation.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125584771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00076
Yuwei Fan, Chao Liu, Tengbo Guo, D. Jiang
Non-instructive load monitoring (NILM) is a data processing method that decomposes the total energy consumption and estimates the power of individual electrical appliances. The application of NILM can provide additional information for optimal control strategy of smart grid, to achieve the purpose of saving energy by fine management. However, the accuracy of traditional NILM methods doesn’t have high accuracy of decomposed power value. In this work, we apply long short-term memory (LSTM) and achieve good accuracy by enhancing the LSTM model with bidirectional and attention mechanisms, as well as kernel density estimation. The model first normalizes the total energy consumption and converts the normalized data to time series of fixed length. LSTM extracts features from the time series, with the bidirectional mechanism to operate from both normal and reverse order and the attention mechanism to calculate the attention weights of different time steps. Besides, kernel density estimation is used to fit the training data and modify the output of the deep learning model, which upgrades the disaggregation accuracy. The proposed model is tested on UK-dale dataset.
{"title":"Bidirectional Attention LSTM Networks for Non-instructive Load Monitoring","authors":"Yuwei Fan, Chao Liu, Tengbo Guo, D. Jiang","doi":"10.1109/PHM2022-London52454.2022.00076","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00076","url":null,"abstract":"Non-instructive load monitoring (NILM) is a data processing method that decomposes the total energy consumption and estimates the power of individual electrical appliances. The application of NILM can provide additional information for optimal control strategy of smart grid, to achieve the purpose of saving energy by fine management. However, the accuracy of traditional NILM methods doesn’t have high accuracy of decomposed power value. In this work, we apply long short-term memory (LSTM) and achieve good accuracy by enhancing the LSTM model with bidirectional and attention mechanisms, as well as kernel density estimation. The model first normalizes the total energy consumption and converts the normalized data to time series of fixed length. LSTM extracts features from the time series, with the bidirectional mechanism to operate from both normal and reverse order and the attention mechanism to calculate the attention weights of different time steps. Besides, kernel density estimation is used to fit the training data and modify the output of the deep learning model, which upgrades the disaggregation accuracy. The proposed model is tested on UK-dale dataset.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124369889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00018
Xinwei Wang, Hongxia Pan, Heng Zhang, Xu An
For the problem that the early fault information of diesel engine system is weak and difficult to identify and diagnose, an early fault diagnosis method based on cross-point frequency response and static and dynamic information fusion was proposed for the assembly quality of diesel engine system. The dynamic vibration response signal and static cross-point frequency response signal of the diesel engine system were collected by reasonable layout of measuring points. After CEEMD reconstruction and de-noising, the sample entropy and approximate entropy were extracted as characteristic parameters of the dynamic signal, and the frequency response features were extracted from the static signal. The static and dynamic information of the two kinds of information was integrated by PCA. The optimized support vector machine is used to identify the dynamic information and the static and dynamic fusion information respectively. The results show that this method can effectively detect the assembly quality of key components of diesel engine system, and the accuracy of diagnosis is up to 95%, and the recognition rate after static and dynamic information fusion is better than that of dynamic information. The method presented in this paper has a good application prospect in the assembly quality inspection and early fault diagnosis of diesel engine system.
{"title":"A Diesel Engine Assembly Quality Detection Method Based on Cross-point Frequency Response and Static and Dynamic Information Fusion","authors":"Xinwei Wang, Hongxia Pan, Heng Zhang, Xu An","doi":"10.1109/PHM2022-London52454.2022.00018","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00018","url":null,"abstract":"For the problem that the early fault information of diesel engine system is weak and difficult to identify and diagnose, an early fault diagnosis method based on cross-point frequency response and static and dynamic information fusion was proposed for the assembly quality of diesel engine system. The dynamic vibration response signal and static cross-point frequency response signal of the diesel engine system were collected by reasonable layout of measuring points. After CEEMD reconstruction and de-noising, the sample entropy and approximate entropy were extracted as characteristic parameters of the dynamic signal, and the frequency response features were extracted from the static signal. The static and dynamic information of the two kinds of information was integrated by PCA. The optimized support vector machine is used to identify the dynamic information and the static and dynamic fusion information respectively. The results show that this method can effectively detect the assembly quality of key components of diesel engine system, and the accuracy of diagnosis is up to 95%, and the recognition rate after static and dynamic information fusion is better than that of dynamic information. The method presented in this paper has a good application prospect in the assembly quality inspection and early fault diagnosis of diesel engine system.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124619620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00016
Yancheng Lv, Lin Lin, Jie Liu, Hao Guo, Chang-sheng Tong, Zhiquan Cui
As a key part of the boom structure of drilling jumbo, the structural stability of the telescopic boom plays a decisive role in the operational reliability of the drilling jumbo. However, the extreme condition of the telescopic boom in the existing optimization cases is determined according to the experience of designers, and there is a lack of research on the extreme condition of the telescopic boom. Given the above problem, the calculation model of the load at the top of the telescopic boom is constructed, and the Biogeography-Based Optimization (BBO) algorithm is used to optimize the pose parameters of the boom structure with the maximum optimization objective of the calculation results of the model. To solve the problem of insufficient adaptability of the linear migration model, 12 nonlinear migration models are proposed and combined with the original BBO algorithm. The performance tests of various migration models are carried out by calculating the limit value of the load at the top of the telescopic boom, the results show that the overall performance and stability of the BBO algorithm based on the exponential migration model is better than other classic optimization algorithms and BBO algorithms based on other migration models. The exponential migration model can better adapt to the nonlinear migration problem, and the corresponding BBO algorithm has better optimization ability.
{"title":"The Calculation of Extreme Condition of Telescopic Boom of Drilling Jumbo Based on New Biogeography-Based Optimization Algorithm","authors":"Yancheng Lv, Lin Lin, Jie Liu, Hao Guo, Chang-sheng Tong, Zhiquan Cui","doi":"10.1109/PHM2022-London52454.2022.00016","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00016","url":null,"abstract":"As a key part of the boom structure of drilling jumbo, the structural stability of the telescopic boom plays a decisive role in the operational reliability of the drilling jumbo. However, the extreme condition of the telescopic boom in the existing optimization cases is determined according to the experience of designers, and there is a lack of research on the extreme condition of the telescopic boom. Given the above problem, the calculation model of the load at the top of the telescopic boom is constructed, and the Biogeography-Based Optimization (BBO) algorithm is used to optimize the pose parameters of the boom structure with the maximum optimization objective of the calculation results of the model. To solve the problem of insufficient adaptability of the linear migration model, 12 nonlinear migration models are proposed and combined with the original BBO algorithm. The performance tests of various migration models are carried out by calculating the limit value of the load at the top of the telescopic boom, the results show that the overall performance and stability of the BBO algorithm based on the exponential migration model is better than other classic optimization algorithms and BBO algorithms based on other migration models. The exponential migration model can better adapt to the nonlinear migration problem, and the corresponding BBO algorithm has better optimization ability.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122882042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：