Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00063
Huabo Shen, Xiaodong Sun, Shenghang Xu, Hao Hu
In order to solve the low debugging efficiency of real-time axle temperature detection system in the debugging process of EMU, an automatic test device is designed for the real-time axle temperature system of EMU. Based on the real-time shaft temperature test logic, the device can exchange data with the digital debugging platform and achieve the automatic function verification of the real-time shaft temperature detection system. In this paper, the overall function of the device is introduced, while the realization of hardware structure and software function is described in detail. The field test results show that the device can meet the requirements on automatic debugging by the real-time axle temperature testing system of EMU, and can effectively optimize the debugging process, while reducing the input of debugging workers. It can significantly shorten the production cycle of EMU, reduce operating costs, and improve production efficiency and quality.
{"title":"Design of Automatic Test Device for Real-time Axle Temperature Detection System of EMU","authors":"Huabo Shen, Xiaodong Sun, Shenghang Xu, Hao Hu","doi":"10.1109/PHM2022-London52454.2022.00063","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00063","url":null,"abstract":"In order to solve the low debugging efficiency of real-time axle temperature detection system in the debugging process of EMU, an automatic test device is designed for the real-time axle temperature system of EMU. Based on the real-time shaft temperature test logic, the device can exchange data with the digital debugging platform and achieve the automatic function verification of the real-time shaft temperature detection system. In this paper, the overall function of the device is introduced, while the realization of hardware structure and software function is described in detail. The field test results show that the device can meet the requirements on automatic debugging by the real-time axle temperature testing system of EMU, and can effectively optimize the debugging process, while reducing the input of debugging workers. It can significantly shorten the production cycle of EMU, reduce operating costs, and improve production efficiency and quality.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"18 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":"114995697","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-London52454.2022.00027
Y. Tao
With the development of social economy, the scale and quantity of engineering projects are growing rapidly. The difficulty of engineering project management is also growing. Traditional management methods have become increasingly unable to meet the needs of modern engineering project management. New theoretical methods are needed to optimize the engineering project process. This paper considers the overall engineering project as a complex system. This complex system is composed of a series of sub-engineering projects and refines the engineering project management process. The time of sub-engineering project is calculated on the assumption that the independent engineering project time distribution obeys the exponential distribution. Then the engineering project management process uses the Coxian distribution to build a calculation model. Firstly, the engineering project process is divided into several phases. Then the k-order Erlang distribution is divided for each stage, and the phase time distribution is solved. Based on the given sub-engineering projects, the Erlang distributions of each stage are mixed to obtain the Coxian distribution model. Finally, the feasibility of the model is verified by data analysis. By combining the Coxian distribution, this paper considers multiple engineering projects as a whole and studies the impact of the sub-engineering projects on the whole engineering project. The completion degree of the entire multi-engineering project process performs mathematical modeling. There are theoretical and practical significance in actual engineering projects. In addition, the results show that the model is more consistent with the reality.
{"title":"Model analysis of engineering project process based on Coxian distribution","authors":"Y. Tao","doi":"10.1109/PHM2022-London52454.2022.00027","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00027","url":null,"abstract":"With the development of social economy, the scale and quantity of engineering projects are growing rapidly. The difficulty of engineering project management is also growing. Traditional management methods have become increasingly unable to meet the needs of modern engineering project management. New theoretical methods are needed to optimize the engineering project process. This paper considers the overall engineering project as a complex system. This complex system is composed of a series of sub-engineering projects and refines the engineering project management process. The time of sub-engineering project is calculated on the assumption that the independent engineering project time distribution obeys the exponential distribution. Then the engineering project management process uses the Coxian distribution to build a calculation model. Firstly, the engineering project process is divided into several phases. Then the k-order Erlang distribution is divided for each stage, and the phase time distribution is solved. Based on the given sub-engineering projects, the Erlang distributions of each stage are mixed to obtain the Coxian distribution model. Finally, the feasibility of the model is verified by data analysis. By combining the Coxian distribution, this paper considers multiple engineering projects as a whole and studies the impact of the sub-engineering projects on the whole engineering project. The completion degree of the entire multi-engineering project process performs mathematical modeling. There are theoretical and practical significance in actual engineering projects. In addition, the results show that the model is more consistent with the reality.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"70 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":"115399379","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-London52454.2022.00011
Yingshun Li, Xiuyu Hu, Zhao Yao, Yang Zhang
In view of the complex structure of the fire control system, difficulty in obtaining fault information, and multiple fault characteristics. This paper proposes a fire control system fault diagnosis method based on genetic algorithm optimized BP neural network. For the problem of poor prediction accuracy of BP neural network in the operation process, and easy to fall into local extreme value. In order to obtain a better diagnosis effect, the principle of complementary advantages is used to combine genetic algorithm with BP neural network algorithm. The genetic algorithm is used to calculate the initial values of network parameters, optimize the initial weights and thresholds, and find the optimal number of hidden layer nodes. Combined with case analysis, the accuracy of this method is improved compared with traditional BP neural network in solving the problem of fire control system fault diagnosis. At the same time, it proves the effectiveness of the proposed method in fire control system fault diagnosis.
{"title":"Fault diagnosis of fire control system based on genetic algorithm optimized BP neural network","authors":"Yingshun Li, Xiuyu Hu, Zhao Yao, Yang Zhang","doi":"10.1109/PHM2022-London52454.2022.00011","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00011","url":null,"abstract":"In view of the complex structure of the fire control system, difficulty in obtaining fault information, and multiple fault characteristics. This paper proposes a fire control system fault diagnosis method based on genetic algorithm optimized BP neural network. For the problem of poor prediction accuracy of BP neural network in the operation process, and easy to fall into local extreme value. In order to obtain a better diagnosis effect, the principle of complementary advantages is used to combine genetic algorithm with BP neural network algorithm. The genetic algorithm is used to calculate the initial values of network parameters, optimize the initial weights and thresholds, and find the optimal number of hidden layer nodes. Combined with case analysis, the accuracy of this method is improved compared with traditional BP neural network in solving the problem of fire control system fault diagnosis. At the same time, it proves the effectiveness of the proposed method in fire control system fault diagnosis.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"3 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":"114325773","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-London52454.2022.00065
Keyu Li, Dongsheng Wu, Lanlan Ping
To meet the antenna requirements of metal-framed mobile terminals in 5G era, an eight-unit MIMO array antenna composed of four "ring-slots" is proposed. In each "ring-slot" structure, the ring antenna and the slot antenna share a rectangular slot. Without adding an external decoupling structure, the current distribution around the rectangular gap is reverse and orthogonal, which realizes the high isolation of the structure. Through simulation and actual measurement, the center frequency of the MIMO antenna array is 3.5 GHz, which can work well in the LTE band 42(3.4-3.6GHz) of 5G communication. The isolation of the antenna unit is better than 16 dB, the radiation efficiency is between 65.8% ~ 73.7%, the envelope correlation coefficient is less than 0.02, and the radiation effect is good. The simulation and measurement results show that the proposed eight-unit MIMO array antenna has high compactness and isolation, and will be well applied to 5G metal frame mobile terminals to promote the progress and development of the 5G communication system.
{"title":"Research on 8-unit MIMO antenna of 5G metal frame mobile terminal","authors":"Keyu Li, Dongsheng Wu, Lanlan Ping","doi":"10.1109/PHM2022-London52454.2022.00065","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00065","url":null,"abstract":"To meet the antenna requirements of metal-framed mobile terminals in 5G era, an eight-unit MIMO array antenna composed of four \"ring-slots\" is proposed. In each \"ring-slot\" structure, the ring antenna and the slot antenna share a rectangular slot. Without adding an external decoupling structure, the current distribution around the rectangular gap is reverse and orthogonal, which realizes the high isolation of the structure. Through simulation and actual measurement, the center frequency of the MIMO antenna array is 3.5 GHz, which can work well in the LTE band 42(3.4-3.6GHz) of 5G communication. The isolation of the antenna unit is better than 16 dB, the radiation efficiency is between 65.8% ~ 73.7%, the envelope correlation coefficient is less than 0.02, and the radiation effect is good. The simulation and measurement results show that the proposed eight-unit MIMO array antenna has high compactness and isolation, and will be well applied to 5G metal frame mobile terminals to promote the progress and development of the 5G communication system.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"18 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":"121456285","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-london52454.2022.00068
Min Wang, Xingzhong Wang, Wei Luo, Yixue Huang, Yuanqiang Yu
While Deep Reinforcement Learning (DRL) has emerged as a prospective method to many tough tasks, it remains laborious to train DRL agents with a handful of data collection and high sample efficiency. In this paper, we present an Adaptive Fuzzy Reinforcement Learning framework (AFuRL) for accelerating the learning process by incorporating adaptive fuzzy logic rules, enabling DRL agents to improve the efficiency of exploring the state space. In AFuRL, the DRL agent first leverages prior fuzzy logic rules designed especially for the actor-critic framework to learn some near-optimal policies, then further improves these policies by automatically generating adaptive fuzzy rules from state-action pairs. Ultimately, the RL algorithm is applied to refine the rough policy obtained by a fuzzy controller. We demonstrate the validity of AFuRL in both discrete and continuous control tasks, where our method surpasses DRL algorithms by a substantial margin. The experiment results show that AFuRL can find superior policies in comparison with imitation-based and some prior knowledge-based approaches.
{"title":"Accelerating Deep Reinforcement Learning Under the Guidance of Adaptive Fuzzy Logic Rules","authors":"Min Wang, Xingzhong Wang, Wei Luo, Yixue Huang, Yuanqiang Yu","doi":"10.1109/phm2022-london52454.2022.00068","DOIUrl":"https://doi.org/10.1109/phm2022-london52454.2022.00068","url":null,"abstract":"While Deep Reinforcement Learning (DRL) has emerged as a prospective method to many tough tasks, it remains laborious to train DRL agents with a handful of data collection and high sample efficiency. In this paper, we present an Adaptive Fuzzy Reinforcement Learning framework (AFuRL) for accelerating the learning process by incorporating adaptive fuzzy logic rules, enabling DRL agents to improve the efficiency of exploring the state space. In AFuRL, the DRL agent first leverages prior fuzzy logic rules designed especially for the actor-critic framework to learn some near-optimal policies, then further improves these policies by automatically generating adaptive fuzzy rules from state-action pairs. Ultimately, the RL algorithm is applied to refine the rough policy obtained by a fuzzy controller. We demonstrate the validity of AFuRL in both discrete and continuous control tasks, where our method surpasses DRL algorithms by a substantial margin. The experiment results show that AFuRL can find superior policies in comparison with imitation-based and some prior knowledge-based approaches.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"31 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":"132684323","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}
At present, there is no effective evaluation method for the integrated diagnosis for aviation equipment, and the existing testability and maintainability evaluation methods do not fully evaluate the integrated diagnosis capability. In order to solve these problems, an evaluation model of integrated diagnosis capability is defined, and the evaluation method is given, adapting to the trend of the rapid development of aviation equipment integrated diagnostic design. The integrated diagnostic design can be checked and evaluated by defining diagnostic evaluation elements, carrying out FMECA work, analysing diagnostic design capability and carrying out the fault injection test. Application of this method in an active vibration control system of aviation seat effectively verified the testability level and the integrated diagnostic efficiency, also point out the shortcomings of the integrated diagnostic design, and provide a reference for the design improvement of the system.
{"title":"A comprehensive evaluation method for aerospace equipment fault diagnosis capability","authors":"Jing Zhao, Dong Wu, Rui-Jia Zhang, Zhong Shi, Chunhui Wang, Tong Li","doi":"10.1109/PHM2022-London52454.2022.00094","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00094","url":null,"abstract":"At present, there is no effective evaluation method for the integrated diagnosis for aviation equipment, and the existing testability and maintainability evaluation methods do not fully evaluate the integrated diagnosis capability. In order to solve these problems, an evaluation model of integrated diagnosis capability is defined, and the evaluation method is given, adapting to the trend of the rapid development of aviation equipment integrated diagnostic design. The integrated diagnostic design can be checked and evaluated by defining diagnostic evaluation elements, carrying out FMECA work, analysing diagnostic design capability and carrying out the fault injection test. Application of this method in an active vibration control system of aviation seat effectively verified the testability level and the integrated diagnostic efficiency, also point out the shortcomings of the integrated diagnostic design, and provide a reference for the design improvement of the system.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"7 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":"132896800","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 recent years, the use of UAV oblique photography for power transmission line three-dimensional real-life modeling is more and more, from single lens, double lens, three-lens, development to five lenses, but the more lenses, resulting in more redundant data, making the power transmission line real-time three-dimensional modeling time longer and longer, reducing the efficiency of modeling, is not conducive to the large-scale application of power transmission line real-life three-dimensional model. Therefore, redundant data deletion for oblique photography of power transmission lines is necessary. In this paper, oblique photography redundant data rejection is carried out for power transmission lines, which can effectively shorten the modeling time and optimize the modeling efficiency while ensuring the modeling effect.
{"title":"A method for refining oblique photography data of power transmission lines","authors":"Hongbing Wen, Qi Xiao, Xiao-Bin Li, Zi-ping Li, Zuhong Liang","doi":"10.1109/PHM2022-London52454.2022.00058","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00058","url":null,"abstract":"In recent years, the use of UAV oblique photography for power transmission line three-dimensional real-life modeling is more and more, from single lens, double lens, three-lens, development to five lenses, but the more lenses, resulting in more redundant data, making the power transmission line real-time three-dimensional modeling time longer and longer, reducing the efficiency of modeling, is not conducive to the large-scale application of power transmission line real-life three-dimensional model. Therefore, redundant data deletion for oblique photography of power transmission lines is necessary. In this paper, oblique photography redundant data rejection is carried out for power transmission lines, which can effectively shorten the modeling time and optimize the modeling efficiency while ensuring the modeling effect.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"16 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":"114463314","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}
This paper takes the side strut of an aircraft's main landing gear as the research object, the finite element analysis of its maximum compression conditions is carried out by ANSYS Workbench2020, mainly analyses its equivalent stress, fatigue life, safety factor and fatigue damage under constant amplitude load and random load, and provides data support for the placement of landing gear health monitoring sensors and failure prediction.
{"title":"Fatigue Life Analysis of Landing Gear Side Strut Based on Finite Element","authors":"Zihang Ge, Sensen Zhu, Ting Ma, Fangyi Wan, Chunlin Zhang, Guanghui Liu, Hao Wei","doi":"10.1109/PHM2022-London52454.2022.00048","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00048","url":null,"abstract":"This paper takes the side strut of an aircraft's main landing gear as the research object, the finite element analysis of its maximum compression conditions is carried out by ANSYS Workbench2020, mainly analyses its equivalent stress, fatigue life, safety factor and fatigue damage under constant amplitude load and random load, and provides data support for the placement of landing gear health monitoring sensors and failure prediction.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"26 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":"115098438","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}
The lock mechanism on the aircraft hatch door is a complex model that integrates mechanical and hydraulic system. To work out the motion rules of lock mechanism, a complete virtual experimental platform is built up. The lock mechanism is researched to model and simulate with AMESim and LMS Virtual.Lab based on their own characteristics and the differences in application. The simulation results show that the established virtual experiment model could simulate the working condition and obtain the inner system parameters efficiently. Meanwhile work in this paper provides an available approach to get fault data for fault diagnosis and analysis, by injecting fault information into the model, which lays a good foundation for the fault detection and health management of the whole system.
{"title":"Modeling and Fault Simulation of Aircraft Lock Mechanism","authors":"Sensen Zhu, Zihang Ge, Ting Ma, Fangyi Wan, Chunlin Zhang, Guanghui Liu, Hao Wei","doi":"10.1109/PHM2022-London52454.2022.00047","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00047","url":null,"abstract":"The lock mechanism on the aircraft hatch door is a complex model that integrates mechanical and hydraulic system. To work out the motion rules of lock mechanism, a complete virtual experimental platform is built up. The lock mechanism is researched to model and simulate with AMESim and LMS Virtual.Lab based on their own characteristics and the differences in application. The simulation results show that the established virtual experiment model could simulate the working condition and obtain the inner system parameters efficiently. Meanwhile work in this paper provides an available approach to get fault data for fault diagnosis and analysis, by injecting fault information into the model, which lays a good foundation for the fault detection and health management of the whole system.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"59 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":"116005780","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-London52454.2022.00093
Jinlong Kang, C. Varnier, A. Mosallam, N. Zerhouni, Fares Ben Youssef, Na-Na Shen
The electronic boards in drilling and measurement (D&M) tools provide multiple functions, such as data acquisition, signal processing, operation control, and data storage. However, due to the harsh downhole operating conditions; i.e., high temperature, dynamic vibration, and extensive shocks, the boards are likely to suffer from complex failure modes and result in failed jobs. Estimating the risk level of the boards can tolerate and provide support for maintenance decision making and job planning, this paper presents a statistical method for risk assessment of the electronic boards. The method first selects relevant channels from D&M tool measurement data and extracts histogram features based on those selected channels. The histogram features are then enhanced based on a linear interpolation method and aggregated using weighted sum. Finally, hidden Markov models (HMMs) with different parameter settings are trained using the processed features. The best HMM is chosen according to the Akaike information criterion and Bayesian information criterion. The proposed HMM-based method is tested on a real-world data set of failed control processing unit boards that were assembled for a specific D&M tool. The experimental results show that this method is effective in estimating the risks as a sequence of events, which in turn, helps to achieve consistent risk estimation. The work presented in this paper is also part of a long-term project with the aim to construct a risk-based decision advisor for D&M tools used in the oil and gas industry.
{"title":"Risk Level Estimation for Electronics Boards in Drilling and Measurement Tools Based on the Hidden Markov Model","authors":"Jinlong Kang, C. Varnier, A. Mosallam, N. Zerhouni, Fares Ben Youssef, Na-Na Shen","doi":"10.1109/PHM2022-London52454.2022.00093","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00093","url":null,"abstract":"The electronic boards in drilling and measurement (D&M) tools provide multiple functions, such as data acquisition, signal processing, operation control, and data storage. However, due to the harsh downhole operating conditions; i.e., high temperature, dynamic vibration, and extensive shocks, the boards are likely to suffer from complex failure modes and result in failed jobs. Estimating the risk level of the boards can tolerate and provide support for maintenance decision making and job planning, this paper presents a statistical method for risk assessment of the electronic boards. The method first selects relevant channels from D&M tool measurement data and extracts histogram features based on those selected channels. The histogram features are then enhanced based on a linear interpolation method and aggregated using weighted sum. Finally, hidden Markov models (HMMs) with different parameter settings are trained using the processed features. The best HMM is chosen according to the Akaike information criterion and Bayesian information criterion. The proposed HMM-based method is tested on a real-world data set of failed control processing unit boards that were assembled for a specific D&M tool. The experimental results show that this method is effective in estimating the risks as a sequence of events, which in turn, helps to achieve consistent risk estimation. The work presented in this paper is also part of a long-term project with the aim to construct a risk-based decision advisor for D&M tools used in the oil and gas industry.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"52 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":"116007292","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：