The Experts below are selected from a list of 102 Experts worldwide ranked by ideXlab platform
Hanna Lukashevich - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Sounding Industry: Challenges and Datasets for Industrial Sound Analysis
2019 27th European Signal Processing Conference (EUSIPCO), 2019Co-Authors: Sascha Grollmisch, Judith Liebetrau, Jakob Abeber, Hanna LukashevichAbstract:The ongoing process of automation in production lines increases the requirements for robust and reliable quality control. Acoustic quality control can play a major part in advanced quality control systems since several types of faults such as changes in machine conditions can be heard by experienced machine operators but can hardly be detected otherwise. To this day, acoustic detection systems using airborne sounds struggle due to the highly complex noise scenarios inside factories. Machine learning systems are theoretically able to cope with these conditions. However, recent advancements in the field of Industrial Sound Analysis (ISA) are sparse compared to related research fields like Music Information Retrieval (MIR) or Acoustic Event Detection (AED). One main reason is the lack of freely available datasets since most of the data is very sensitive for companies. Therefore, three novel datasets for ISA with different application fields were recorded and published along with this paper: detection of the operational state of an electric engine, detection of the surface of Rolling Metal balls, and detection of different bulk materials. For each dataset, neural network based baseline systems were evaluated. The results show that such systems obtain high classification accuracies over all datasets in many of the subtasks which demonstrates the feasibility of audio-based analysis of industrial analysis scenarios. However, the baseline systems remain highly sensitive to changes in the recording setup, which leaves a lot of room for improvement. The main goal of this paper is to stimulate further research in the field of ISA.
-
Sounding Industry: Challenges and Datasets for Industrial Sound Analysis
2019 27th European Signal Processing Conference (EUSIPCO), 2019Co-Authors: Sascha Grollmisch, Jakob Abeβer, Judith Liebetrau, Hanna LukashevichAbstract:The ongoing process of automation in production lines increases the requirements for robust and reliable quality control. Acoustic quality control can play a major part in advanced quality control systems since several types of faults such as changes in machine conditions can be heard by experienced machine operators but can hardly be detected otherwise. To this day, acoustic detection systems using airborne sounds struggle due to the highly complex noise scenarios inside factories. Machine learning systems are theoretically able to cope with these conditions. However, recent advancements in the field of Industrial Sound Analysis (ISA) are sparse compared to related research fields like Music Information Retrieval (MIR) or Acoustic Event Detection (AED). One main reason is the lack of freely available datasets since most of the data is very sensitive for companies. Therefore, three novel datasets for ISA with different application fields were recorded and published along with this paper: detection of the operational state of an electric engine, detection of the surface of Rolling Metal balls, and detection of different bulk materials. For each dataset, neural network based baseline systems were evaluated. The results show that such systems obtain high classification accuracies over all datasets in many of the subtasks which demonstrates the feasibility of audio-based analysis of industrial analysis scenarios. However, the baseline systems remain highly sensitive to changes in the recording setup, which leaves a lot of room for improvement. The main goal of this paper is to stimulate further research in the field of ISA.
Sascha Grollmisch - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Sounding Industry: Challenges and Datasets for Industrial Sound Analysis
2019 27th European Signal Processing Conference (EUSIPCO), 2019Co-Authors: Sascha Grollmisch, Judith Liebetrau, Jakob Abeber, Hanna LukashevichAbstract:The ongoing process of automation in production lines increases the requirements for robust and reliable quality control. Acoustic quality control can play a major part in advanced quality control systems since several types of faults such as changes in machine conditions can be heard by experienced machine operators but can hardly be detected otherwise. To this day, acoustic detection systems using airborne sounds struggle due to the highly complex noise scenarios inside factories. Machine learning systems are theoretically able to cope with these conditions. However, recent advancements in the field of Industrial Sound Analysis (ISA) are sparse compared to related research fields like Music Information Retrieval (MIR) or Acoustic Event Detection (AED). One main reason is the lack of freely available datasets since most of the data is very sensitive for companies. Therefore, three novel datasets for ISA with different application fields were recorded and published along with this paper: detection of the operational state of an electric engine, detection of the surface of Rolling Metal balls, and detection of different bulk materials. For each dataset, neural network based baseline systems were evaluated. The results show that such systems obtain high classification accuracies over all datasets in many of the subtasks which demonstrates the feasibility of audio-based analysis of industrial analysis scenarios. However, the baseline systems remain highly sensitive to changes in the recording setup, which leaves a lot of room for improvement. The main goal of this paper is to stimulate further research in the field of ISA.
-
Sounding Industry: Challenges and Datasets for Industrial Sound Analysis
2019 27th European Signal Processing Conference (EUSIPCO), 2019Co-Authors: Sascha Grollmisch, Jakob Abeβer, Judith Liebetrau, Hanna LukashevichAbstract:The ongoing process of automation in production lines increases the requirements for robust and reliable quality control. Acoustic quality control can play a major part in advanced quality control systems since several types of faults such as changes in machine conditions can be heard by experienced machine operators but can hardly be detected otherwise. To this day, acoustic detection systems using airborne sounds struggle due to the highly complex noise scenarios inside factories. Machine learning systems are theoretically able to cope with these conditions. However, recent advancements in the field of Industrial Sound Analysis (ISA) are sparse compared to related research fields like Music Information Retrieval (MIR) or Acoustic Event Detection (AED). One main reason is the lack of freely available datasets since most of the data is very sensitive for companies. Therefore, three novel datasets for ISA with different application fields were recorded and published along with this paper: detection of the operational state of an electric engine, detection of the surface of Rolling Metal balls, and detection of different bulk materials. For each dataset, neural network based baseline systems were evaluated. The results show that such systems obtain high classification accuracies over all datasets in many of the subtasks which demonstrates the feasibility of audio-based analysis of industrial analysis scenarios. However, the baseline systems remain highly sensitive to changes in the recording setup, which leaves a lot of room for improvement. The main goal of this paper is to stimulate further research in the field of ISA.
Judith Liebetrau - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Sounding Industry: Challenges and Datasets for Industrial Sound Analysis
2019 27th European Signal Processing Conference (EUSIPCO), 2019Co-Authors: Sascha Grollmisch, Judith Liebetrau, Jakob Abeber, Hanna LukashevichAbstract:The ongoing process of automation in production lines increases the requirements for robust and reliable quality control. Acoustic quality control can play a major part in advanced quality control systems since several types of faults such as changes in machine conditions can be heard by experienced machine operators but can hardly be detected otherwise. To this day, acoustic detection systems using airborne sounds struggle due to the highly complex noise scenarios inside factories. Machine learning systems are theoretically able to cope with these conditions. However, recent advancements in the field of Industrial Sound Analysis (ISA) are sparse compared to related research fields like Music Information Retrieval (MIR) or Acoustic Event Detection (AED). One main reason is the lack of freely available datasets since most of the data is very sensitive for companies. Therefore, three novel datasets for ISA with different application fields were recorded and published along with this paper: detection of the operational state of an electric engine, detection of the surface of Rolling Metal balls, and detection of different bulk materials. For each dataset, neural network based baseline systems were evaluated. The results show that such systems obtain high classification accuracies over all datasets in many of the subtasks which demonstrates the feasibility of audio-based analysis of industrial analysis scenarios. However, the baseline systems remain highly sensitive to changes in the recording setup, which leaves a lot of room for improvement. The main goal of this paper is to stimulate further research in the field of ISA.
-
Sounding Industry: Challenges and Datasets for Industrial Sound Analysis
2019 27th European Signal Processing Conference (EUSIPCO), 2019Co-Authors: Sascha Grollmisch, Jakob Abeβer, Judith Liebetrau, Hanna LukashevichAbstract:The ongoing process of automation in production lines increases the requirements for robust and reliable quality control. Acoustic quality control can play a major part in advanced quality control systems since several types of faults such as changes in machine conditions can be heard by experienced machine operators but can hardly be detected otherwise. To this day, acoustic detection systems using airborne sounds struggle due to the highly complex noise scenarios inside factories. Machine learning systems are theoretically able to cope with these conditions. However, recent advancements in the field of Industrial Sound Analysis (ISA) are sparse compared to related research fields like Music Information Retrieval (MIR) or Acoustic Event Detection (AED). One main reason is the lack of freely available datasets since most of the data is very sensitive for companies. Therefore, three novel datasets for ISA with different application fields were recorded and published along with this paper: detection of the operational state of an electric engine, detection of the surface of Rolling Metal balls, and detection of different bulk materials. For each dataset, neural network based baseline systems were evaluated. The results show that such systems obtain high classification accuracies over all datasets in many of the subtasks which demonstrates the feasibility of audio-based analysis of industrial analysis scenarios. However, the baseline systems remain highly sensitive to changes in the recording setup, which leaves a lot of room for improvement. The main goal of this paper is to stimulate further research in the field of ISA.
Jakob Abeβer - One of the best experts on this subject based on the ideXlab platform.
-
Sounding Industry: Challenges and Datasets for Industrial Sound Analysis
2019 27th European Signal Processing Conference (EUSIPCO), 2019Co-Authors: Sascha Grollmisch, Jakob Abeβer, Judith Liebetrau, Hanna LukashevichAbstract:The ongoing process of automation in production lines increases the requirements for robust and reliable quality control. Acoustic quality control can play a major part in advanced quality control systems since several types of faults such as changes in machine conditions can be heard by experienced machine operators but can hardly be detected otherwise. To this day, acoustic detection systems using airborne sounds struggle due to the highly complex noise scenarios inside factories. Machine learning systems are theoretically able to cope with these conditions. However, recent advancements in the field of Industrial Sound Analysis (ISA) are sparse compared to related research fields like Music Information Retrieval (MIR) or Acoustic Event Detection (AED). One main reason is the lack of freely available datasets since most of the data is very sensitive for companies. Therefore, three novel datasets for ISA with different application fields were recorded and published along with this paper: detection of the operational state of an electric engine, detection of the surface of Rolling Metal balls, and detection of different bulk materials. For each dataset, neural network based baseline systems were evaluated. The results show that such systems obtain high classification accuracies over all datasets in many of the subtasks which demonstrates the feasibility of audio-based analysis of industrial analysis scenarios. However, the baseline systems remain highly sensitive to changes in the recording setup, which leaves a lot of room for improvement. The main goal of this paper is to stimulate further research in the field of ISA.
Xianzhang Feng - One of the best experts on this subject based on the ideXlab platform.
-
Stress analysis of bearings of main eccentric shaft for width mill
PIAGENG 2009: Intelligent Information Control and Communication Technology for Agricultural Engineering, 2009Co-Authors: Xianzhang Feng, Zhiqiang JiangAbstract:In order to analyze the dynamic load and lifespan of bearing of maim eccentric axis of mill in the course of working, the mechanical model of maim eccentric axis was established using the theory of free beam in material mechanics under the research load character of Metal Rolling, make the results of the finite element analysis as conditions for the model during Rolling Metal. The force and lifespan calculation were studied for the bearing systematically, the calculated results show that the bearings exist periodicity force of impact, the same rules as testing inline. The calculated results coincide better with practical measured results and completely achieve the prediction accuracy requirements required by the engineering, and the bearings can meet requirements in the field.
-
WKDD - Study on Head Regional of Hot Forming for Wide-Thick Plate
2009 Second International Workshop on Knowledge Discovery and Data Mining, 2009Co-Authors: Xianzhang Feng, Junwei Cheng, Junhui LiAbstract:To analyze the forming rules of the width dimensions reduction change of wide-thick plate head regional, the coupled heat Rolling model of was created by the theory of the nonlinear finite element. Under the base of constant wide-thick plate width and different side pressing regulations, the forming rules were obtained for wide-thick plate head width reduction amount and side press amount, rounded analysis of variation of wide-thick plate head width reduction and corresponding experimental research were performed, the calculated results were very inosculated with the measured values, it indicates that the model is reality and credibility. The studied results have provided the theoretical references for contRolling wide-thick plate head width reduction during Rolling Metal.
-
Study on Head Regional of Hot Forming for Wide-Thick Plate
2009 Second International Workshop on Knowledge Discovery and Data Mining, 2009Co-Authors: Xianzhang Feng, Junwei Cheng, Junhui LiAbstract:To analyze the forming rules of the width dimensions reduction change of wide-thick plate head regional, the coupled heat Rolling model of was created by the theory of the nonlinear finite element. Under the base of constant wide-thick plate width and different side pressing regulations, the forming rules were obtained for wide-thick plate head width reduction amount and side press amount, rounded analysis of variation of wide-thick plate head width reduction and corresponding experimental research were performed, the calculated results were very inosculated with the measured values, it indicates that the model is reality and credibility. The studied results have provided the theoretical references for contRolling wide-thick plate head width reduction during Rolling Metal.
