Deep learning is an appropriate methodology for modeling complex industrial data in the field of soft sensors, owing to its powerful feature representation capability. Given the nonlinear and dynamic nature of the process industry, the key challenge for soft sensor technology is to effectively mine dynamic information from long sequences and accurately extract features of relevance to quality. A dual temporal attention mechanism-based convolutional long short-term memory network (DTA-ConvLSTM) under an encoder-decoder framework is proposed as a soft sensor model to acquire quality-relevant dynamic features from serial data. Considering different influences of process variables for prediction at multiple time steps and various locations, ConvLSTM and temporal self-attention mechanism are utilized as the encoder to adaptively fuse spatiotemporal features and capture long-term dynamic properties of process in order to capture the trends of industrial variables. Furthermore, a quality-driven temporal attention mechanism is employed throughout the decoding process to dynamically select relevant features to more accurately track quality changes. The encoder-decoder model meticulously analyses the interactions between process and quality variables by incorporating dual-sequence dynamic information to improve the prediction performance. The validity and superiority of the DTA-ConvLSTM model was validated on two industrial case studies of the debutanizer column and sulfur recovery unit. Compared to the traditional LSTM model, the proposed model demonstrated a substantial improvement with the accuracy R2 up to 97.3% and 94.9% and the root mean square error reducing to 0.122 and 0.022.
{"title":"Dual Temporal Attention Mechanism-based Convolutional LSTM Model for Industrial Dynamic Soft Sensor","authors":"Jiarui Cui, Yuyu Shi, Jian Huang, Xu Yang, Jingjing Gao, Qing Li","doi":"10.1088/1361-6501/ad66f7","DOIUrl":"https://doi.org/10.1088/1361-6501/ad66f7","url":null,"abstract":"\u0000 Deep learning is an appropriate methodology for modeling complex industrial data in the field of soft sensors, owing to its powerful feature representation capability. Given the nonlinear and dynamic nature of the process industry, the key challenge for soft sensor technology is to effectively mine dynamic information from long sequences and accurately extract features of relevance to quality. A dual temporal attention mechanism-based convolutional long short-term memory network (DTA-ConvLSTM) under an encoder-decoder framework is proposed as a soft sensor model to acquire quality-relevant dynamic features from serial data. Considering different influences of process variables for prediction at multiple time steps and various locations, ConvLSTM and temporal self-attention mechanism are utilized as the encoder to adaptively fuse spatiotemporal features and capture long-term dynamic properties of process in order to capture the trends of industrial variables. Furthermore, a quality-driven temporal attention mechanism is employed throughout the decoding process to dynamically select relevant features to more accurately track quality changes. The encoder-decoder model meticulously analyses the interactions between process and quality variables by incorporating dual-sequence dynamic information to improve the prediction performance. The validity and superiority of the DTA-ConvLSTM model was validated on two industrial case studies of the debutanizer column and sulfur recovery unit. Compared to the traditional LSTM model, the proposed model demonstrated a substantial improvement with the accuracy R2 up to 97.3% and 94.9% and the root mean square error reducing to 0.122 and 0.022.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"44 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141809510","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 : 2024-07-24DOI: 10.1088/1361-6501/ad6176
Xuanyu Liu, Wenshuai Zhang, Mengting Jiang, Yudong Wang, Lili Ma
Realizing automatic control of shield machine tunneling attitude is a challenging problem. Realizing multi-step intelligent prediction for attitude and position is an important prerequisite for solving this problem in the tunneling process with complex and varied geological environments. In this paper, a multi-step intelligent predictive scheme based on beluga whale optimization-convolutional neural network-Long Short-term memory-gated recurrent unit (BWO-CNN-LSTM-GRU) is proposed for shield machine position attitude. First, Pearson correlation analysis is utilized to determine the input feature variables from the construction data and temporalize the input features. Subsequently, CNN-LSTM-GRU predictive models are established for the six positional parameters, separately. Among them, CNN performs feature extraction on the input variables, and LSTM-GRU realizes the predictions for the target positional parameters. In the end, the optimization of the convolutional layer dimension, the number of convolutional layers, iterations, the learning rate, the number of neurons in the LSTM layer and GRU layer of each position predictive model is performed on the basis of BWO, separately, and the best hyperparameters found are built into a BWO-CNN-LSTM-GRU position predictive model, which realizes the multi-step intelligent predictions for the shield machine’s position. The proposed approach is examined by utilizing the Beijing Metro Line 10. The results show that the predictive deviation of the position predictive model is within 3 mm, and the positional trajectory points obtained on the basis of the predicted values and the 3D coordinate system are highly coincident with the actual trajectory points. Therefore, the approach provides a more accurate predictive result for shield attitude and position and can provide a decision-making scheme for further realizing the coordinated autonomous control of shield machine.
{"title":"Multi-step intelligent prediction of shield machine position attitude on the basis of BWO-CNN-LSTM-GRU","authors":"Xuanyu Liu, Wenshuai Zhang, Mengting Jiang, Yudong Wang, Lili Ma","doi":"10.1088/1361-6501/ad6176","DOIUrl":"https://doi.org/10.1088/1361-6501/ad6176","url":null,"abstract":"\u0000 Realizing automatic control of shield machine tunneling attitude is a challenging problem. Realizing multi-step intelligent prediction for attitude and position is an important prerequisite for solving this problem in the tunneling process with complex and varied geological environments. In this paper, a multi-step intelligent predictive scheme based on beluga whale optimization-convolutional neural network-Long Short-term memory-gated recurrent unit (BWO-CNN-LSTM-GRU) is proposed for shield machine position attitude. First, Pearson correlation analysis is utilized to determine the input feature variables from the construction data and temporalize the input features. Subsequently, CNN-LSTM-GRU predictive models are established for the six positional parameters, separately. Among them, CNN performs feature extraction on the input variables, and LSTM-GRU realizes the predictions for the target positional parameters. In the end, the optimization of the convolutional layer dimension, the number of convolutional layers, iterations, the learning rate, the number of neurons in the LSTM layer and GRU layer of each position predictive model is performed on the basis of BWO, separately, and the best hyperparameters found are built into a BWO-CNN-LSTM-GRU position predictive model, which realizes the multi-step intelligent predictions for the shield machine’s position. The proposed approach is examined by utilizing the Beijing Metro Line 10. The results show that the predictive deviation of the position predictive model is within 3 mm, and the positional trajectory points obtained on the basis of the predicted values and the 3D coordinate system are highly coincident with the actual trajectory points. Therefore, the approach provides a more accurate predictive result for shield attitude and position and can provide a decision-making scheme for further realizing the coordinated autonomous control of shield machine.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"59 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141808715","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}
With the advancement of deep learning technologies, industrial intelligent detection algorithms are gradually being applied in practical steel surface defect detection. Addressing the issues of high computational resource consumption and poor detection performance faced by existing models in large-scale industrial production lines, this paper proposes an EFS-YOLO model based on improved YOLOv8s architecture. Firstly, the EfficientViT is employed as the feature extraction network, effectively reducing the model's parameters and calculations while enhancing its capability to represent defect features. Secondly, the designed lightweight C2f-Faster-EffectiveSE Block (CFE-Block) was integrated into the model neck, accelerating feature fusion and better preserving detailed defect features at lower levels. Finally, the model detection head was reconstructed using the concept of shared parameters to address the high computational cost of the original detection head. Experimental results on the NEU-DET and GC10-DET datasets demonstrate that compared to the baseline model, the proposed model achieves a reduction in parameters, calculations and size by 49.5%, 62.7% and 46.9% respectively. It also exhibits an improvement in accuracy by 2.4% and 2.3% on the two datasets. The EFS-YOLO model effectively enhances precision in steel surface defect detection while maintaining lightweight characteristics, offering superior performance.
{"title":"EFS-YOLO: A Lightweight Network Based on Steel Strip Surface Defect Detection","authors":"Beilong Chen, Mingjun Wei, Jianuo Liu, Hui Li, Chenxu Dai, Jinyun Liu, Zhanlin Ji","doi":"10.1088/1361-6501/ad66fe","DOIUrl":"https://doi.org/10.1088/1361-6501/ad66fe","url":null,"abstract":"\u0000 With the advancement of deep learning technologies, industrial intelligent detection algorithms are gradually being applied in practical steel surface defect detection. Addressing the issues of high computational resource consumption and poor detection performance faced by existing models in large-scale industrial production lines, this paper proposes an EFS-YOLO model based on improved YOLOv8s architecture. Firstly, the EfficientViT is employed as the feature extraction network, effectively reducing the model's parameters and calculations while enhancing its capability to represent defect features. Secondly, the designed lightweight C2f-Faster-EffectiveSE Block (CFE-Block) was integrated into the model neck, accelerating feature fusion and better preserving detailed defect features at lower levels. Finally, the model detection head was reconstructed using the concept of shared parameters to address the high computational cost of the original detection head. Experimental results on the NEU-DET and GC10-DET datasets demonstrate that compared to the baseline model, the proposed model achieves a reduction in parameters, calculations and size by 49.5%, 62.7% and 46.9% respectively. It also exhibits an improvement in accuracy by 2.4% and 2.3% on the two datasets. The EFS-YOLO model effectively enhances precision in steel surface defect detection while maintaining lightweight characteristics, offering superior performance.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"52 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141808235","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 : 2024-07-24DOI: 10.1088/1361-6501/ad66f4
Matthieu Denoual, Nicolas Lobato-Dauzier, Luis Saluden, L. Jalabert, Takaaki Sato, Hiroyuki Fujita
Understanding the microscopic mechanisms behind mechanical fractures is essential for enhancing material properties and increasing reliability through fatigue suppression. Conventional mechanical testing methods, such as indentation tests that press a sharp needle into a specimen or tensile tests using hydraulic pumps, are unable to capture nanoscale deformations under applied forces. As a result, the microscopic mechanisms that influence mechanical properties are often inferred indirectly, and material design largely depends on the engineer’s intuition and occasional serendipity To overcome these challenges, in-situ observation techniques utilizing transmission electron microscopes (TEMs) have been developed to enable the observation of sample deformations at the nanoscale. However, despite their high resolution, conventional TEMs are limited by a small available space -often just a few millimeters- that restricts the application of sufficient force to fracture specimens. Traditional actuation methods, such as thermal expansion, electrostatic force, and piezoelectric actuators, fail to generate significant forces within such confined spaces. In response to these limitations, our research involved the development of a micromachine with multiple parallel beams. This device leverages the Laplace force generated by an electric current passing through the beams and the magnetic field of the TEM. We demonstrated the capability to produce significant force using the magnetic field from the microscope’s magnetic lens. The actuator developed in our study successfully generated forces exceeding 50 µN, marking a significant advancement in the in-situ observation capabilities for mechanical testing.
了解机械断裂背后的微观机理对于通过抑制疲劳来增强材料性能和提高可靠性至关重要。传统的机械测试方法，如将尖针压入试样的压痕测试或使用液压泵的拉伸测试，无法捕捉到外力作用下的纳米级变形。因此，影响机械性能的微观机制往往是间接推断出来的，材料设计在很大程度上依赖于工程师的直觉和偶尔的偶然性。 为了克服这些挑战，人们开发了利用透射电子显微镜（TEM）的原位观测技术，以实现对纳米级样品变形的观测。然而，尽管分辨率很高，但传统的 TEM 受限于狭小的可用空间（通常只有几毫米），无法对断裂试样施加足够的力。传统的致动方法，如热膨胀、静电力和压电致动器，无法在如此狭小的空间内产生巨大的力。针对这些限制，我们的研究涉及开发一种带有多个平行梁的微型机械。该装置利用电流通过横梁和 TEM 磁场产生的拉普拉斯力。我们展示了利用显微镜磁透镜产生的磁场产生巨大力的能力。我们在研究中开发的致动器成功产生了超过 50 µN 的力，标志着机械测试原位观测能力的重大进步。
{"title":"Parallel-beams magnetic actuator for in-situ transmission electron microscope observation of mechanical testing","authors":"Matthieu Denoual, Nicolas Lobato-Dauzier, Luis Saluden, L. Jalabert, Takaaki Sato, Hiroyuki Fujita","doi":"10.1088/1361-6501/ad66f4","DOIUrl":"https://doi.org/10.1088/1361-6501/ad66f4","url":null,"abstract":"\u0000 Understanding the microscopic mechanisms behind mechanical fractures is essential for enhancing material properties and increasing reliability through fatigue suppression. Conventional mechanical testing methods, such as indentation tests that press a sharp needle into a specimen or tensile tests using hydraulic pumps, are unable to capture nanoscale deformations under applied forces. As a result, the microscopic mechanisms that influence mechanical properties are often inferred indirectly, and material design largely depends on the engineer’s intuition and occasional serendipity To overcome these challenges, in-situ observation techniques utilizing transmission electron microscopes (TEMs) have been developed to enable the observation of sample deformations at the nanoscale. However, despite their high resolution, conventional TEMs are limited by a small available space -often just a few millimeters- that restricts the application of sufficient force to fracture specimens. Traditional actuation methods, such as thermal expansion, electrostatic force, and piezoelectric actuators, fail to generate significant forces within such confined spaces. In response to these limitations, our research involved the development of a micromachine with multiple parallel beams. This device leverages the Laplace force generated by an electric current passing through the beams and the magnetic field of the TEM. We demonstrated the capability to produce significant force using the magnetic field from the microscope’s magnetic lens. The actuator developed in our study successfully generated forces exceeding 50 µN, marking a significant advancement in the in-situ observation capabilities for mechanical testing.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"4 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141809284","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 : 2024-07-24DOI: 10.1088/1361-6501/ad66f3
Yun Yang, Baohu Han, Jinzhao Zuo, Long Li, Kenan Li
With the intelligent development of magnetic particle inspection, the quality of magnetic indications formed at cracks is closely related to the accuracy of magnetic particle inspection image analysis results. The concentration of magnetic suspension is a key process parameter affecting the quality of magnetic indication formation. Hence, this study presents an online detection method based on machine vision for measuring magnetic suspension concentration. The method initially enhances the contrast of images of the pear-shaped measuring tube containing magnetic suspension and then extracts scale lines through feature analysis and morphological processing. A method for extracting the magnetic particle sedimentation area of magnetic suspension based on a dual-threshold segmentation algorithm is proposed. The contour filtering algorithm and pixel calibration method are used to obtain the magnetic particle concentration of the non-estimation and estimation areas based on scale line extraction, ultimately forming an online accurate detection method for magnetic suspension concentration values. Experiments were conducted to validate the method against different concentrations, turbidity levels, tilting angles of the pear-shaped measuring tube, and ambient brightness. The results show that the error in magnetic suspension concentration detection based on this method is within 5%. This has certain reference value for the stable control of magnetic suspension concentration and for enhancing the reliability of intelligent decision-making results in magnetic particle inspection.
{"title":"Online Detection Method for Magnetic Suspension Concentration Based on Machine Vision","authors":"Yun Yang, Baohu Han, Jinzhao Zuo, Long Li, Kenan Li","doi":"10.1088/1361-6501/ad66f3","DOIUrl":"https://doi.org/10.1088/1361-6501/ad66f3","url":null,"abstract":"\u0000 With the intelligent development of magnetic particle inspection, the quality of magnetic\u0000indications formed at cracks is closely related to the accuracy of magnetic particle inspection\u0000image analysis results. The concentration of magnetic suspension is a key process parameter\u0000affecting the quality of magnetic indication formation. Hence, this study presents an online\u0000detection method based on machine vision for measuring magnetic suspension concentration.\u0000The method initially enhances the contrast of images of the pear-shaped measuring tube\u0000containing magnetic suspension and then extracts scale lines through feature analysis and\u0000morphological processing. A method for extracting the magnetic particle sedimentation area of\u0000magnetic suspension based on a dual-threshold segmentation algorithm is proposed. The\u0000contour filtering algorithm and pixel calibration method are used to obtain the magnetic particle\u0000concentration of the non-estimation and estimation areas based on scale line extraction,\u0000ultimately forming an online accurate detection method for magnetic suspension concentration\u0000values. Experiments were conducted to validate the method against different concentrations,\u0000turbidity levels, tilting angles of the pear-shaped measuring tube, and ambient brightness. The\u0000results show that the error in magnetic suspension concentration detection based on this method\u0000is within 5%. This has certain reference value for the stable control of magnetic suspension\u0000concentration and for enhancing the reliability of intelligent decision-making results in\u0000magnetic particle inspection.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"23 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141810297","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 : 2024-07-24DOI: 10.1088/1361-6501/ad66f8
Gang Wang, Ying Su, Mingfeng Lu, Rongsheng Chen, Xusheng Sun
Magnetic flux leakage (MFL) testing is widely used for acquiring MFL signals to detect pipeline defects, and data-driven approaches have been effectively investigated for MFL defect identification. However, with the increasing complexity of pipeline defects, current methods are constrained by the incomplete information from single modal data, which fails to meet detection requirements. Moreover, the incorporation of multimodal MFL data results in feature redundancy. Therefore, the Multi-Modality Hierarchical Attention Networks (MMHAN) are proposed for defect identification. Firstly, stacked residual blocks with Cross-Level Attention Module (CLAM) and multiscale 1D-CNNs with Multiscale Attention Module (MAM) are utilized to extract multiscale defect features. Secondly, the Multi-Modality Feature Enhancement Attention Module (MMFEAM) is developed to enhance critical defect features by leveraging correlations among multimodal features. Lastly, the Multi-Modality Feature Fusion Attention Module (MMFFAM) is designed to dynamically integrate multimodal features deeply, utilizing the consistency and complementarity of multimodal information. Extensive experiments were conducted on multimodal pipeline datasets to assess the proposed MMHAN. The experimental results demonstrate that MMHAN achieves a higher identification accuracy, validating its exceptional performance.
{"title":"Multi-modality Hierarchical Attention Networks for Defect Identification in Pipeline MFL Detection","authors":"Gang Wang, Ying Su, Mingfeng Lu, Rongsheng Chen, Xusheng Sun","doi":"10.1088/1361-6501/ad66f8","DOIUrl":"https://doi.org/10.1088/1361-6501/ad66f8","url":null,"abstract":"\u0000 Magnetic flux leakage (MFL) testing is widely used for acquiring MFL signals to detect pipeline defects, and data-driven approaches have been effectively investigated for MFL defect identification. However, with the increasing complexity of pipeline defects, current methods are constrained by the incomplete information from single modal data, which fails to meet detection requirements. Moreover, the incorporation of multimodal MFL data results in feature redundancy. Therefore, the Multi-Modality Hierarchical Attention Networks (MMHAN) are proposed for defect identification. Firstly, stacked residual blocks with Cross-Level Attention Module (CLAM) and multiscale 1D-CNNs with Multiscale Attention Module (MAM) are utilized to extract multiscale defect features. Secondly, the Multi-Modality Feature Enhancement Attention Module (MMFEAM) is developed to enhance critical defect features by leveraging correlations among multimodal features. Lastly, the Multi-Modality Feature Fusion Attention Module (MMFFAM) is designed to dynamically integrate multimodal features deeply, utilizing the consistency and complementarity of multimodal information. Extensive experiments were conducted on multimodal pipeline datasets to assess the proposed MMHAN. The experimental results demonstrate that MMHAN achieves a higher identification accuracy, validating its exceptional performance.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"63 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141806793","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 : 2024-07-24DOI: 10.1088/1361-6501/ad66f5
Minh Tuyet Dang, Dung Ba Nguyen
Path planning for Unmanned Aerial Vehicle (UAV) is the process of determining the path that travels through each location of interest within a particular area. There are numerous algorithms proposed and described in the publications to address UAV path planning problems. However, in order to handle the complex and dynamic environment with different obstacles, it is critical to utilize the proper fusion algorithms in planning the UAV path. This paper reviews some hybrid algorithms used in finding the optimal route of UAVs that developed in the last ten years as well as their advantages and disadvantages. The UAV path planning methods were classified into categories of hybrid algorithms based on traditional, heuristic, machine learning approaches. Criteria used to evaluate algorithms include execution time, total cost, energy consumption, robustness, data, computation, obstacle avoidance, and environment. The results of this study provide reference resources for researchers in finding the path for UAVs.
{"title":"Hybrid algorithms in path planning for autonomous navigation of Unmanned Aerial Vehicle: A comprehensive review","authors":"Minh Tuyet Dang, Dung Ba Nguyen","doi":"10.1088/1361-6501/ad66f5","DOIUrl":"https://doi.org/10.1088/1361-6501/ad66f5","url":null,"abstract":"\u0000 Path planning for Unmanned Aerial Vehicle (UAV) is the process of determining the path that travels through each location of interest within a particular area. There are numerous algorithms proposed and described in the publications to address UAV path planning problems. However, in order to handle the complex and dynamic environment with different obstacles, it is critical to utilize the proper fusion algorithms in planning the UAV path. This paper reviews some hybrid algorithms used in finding the optimal route of UAVs that developed in the last ten years as well as their advantages and disadvantages. The UAV path planning methods were classified into categories of hybrid algorithms based on traditional, heuristic, machine learning approaches. Criteria used to evaluate algorithms include execution time, total cost, energy consumption, robustness, data, computation, obstacle avoidance, and environment. The results of this study provide reference resources for researchers in finding the path for UAVs.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"60 32","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141806967","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 : 2024-07-24DOI: 10.1088/1361-6501/ad6700
Suna Guo, Jiawen Han, Baonan Li, L. Fang, Tao Zhang, Fan Wang
The error introduced by the integration method is an important factor affecting the measurement accuracy of the multipath ultrasonic flowmeter. An adaptive weighted integration method(AWICS-VP, Adaptive Weighted Integration Method for Velocity Profile of Circular Section) is proposed to reduce the integration error, taking a DN400 double-side eight-path ultrasonic flowmeter as an example. This method is based on the velocity distribution information in the full flow range and the integration weights are determined by the principle of minimum error. The applicability of this method is verified by numerical simulation and actual fluid flow experiments. The results show that the integration error of the proposed method is superior to the Gauss-Jacobi and OWICS integration methods, and the maximum integration error is reduced from 0.0877% and -0.0355% to 0.0220% in the flow range of 125 to 2500 t/h.
{"title":"An Adaptive Weighted Integration Method for Multipath Ultrasonic Flowmeter","authors":"Suna Guo, Jiawen Han, Baonan Li, L. Fang, Tao Zhang, Fan Wang","doi":"10.1088/1361-6501/ad6700","DOIUrl":"https://doi.org/10.1088/1361-6501/ad6700","url":null,"abstract":"\u0000 The error introduced by the integration method is an important factor affecting the measurement accuracy of the multipath ultrasonic flowmeter. An adaptive weighted integration method(AWICS-VP, Adaptive Weighted Integration Method for Velocity Profile of Circular Section) is proposed to reduce the integration error, taking a DN400 double-side eight-path ultrasonic flowmeter as an example. This method is based on the velocity distribution information in the full flow range and the integration weights are determined by the principle of minimum error. The applicability of this method is verified by numerical simulation and actual fluid flow experiments. The results show that the integration error of the proposed method is superior to the Gauss-Jacobi and OWICS integration methods, and the maximum integration error is reduced from 0.0877% and -0.0355% to 0.0220% in the flow range of 125 to 2500 t/h.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"56 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807608","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 : 2024-07-24DOI: 10.1088/1361-6501/ad66f1
Jiashuai Huang, Guang-qiang Chen, Hong Wei, Zhuang Chen, Yingxin Lv
With the continuous development of the aerospace, defense, and military industry, along with other high-end fields, the complexity of machined parts has gradually increased. Consequently, the demand for tool intelligence has also strengthened. However, traditional tools are prone to wear during cutting due to high cutting forces, high temperatures, and vibrations. Intelligent tools, in contrast to traditional ones, integrate sensors into their design, allowing for real-time monitoring of the cutting status and timely prediction of tool wear. The application of intelligent tools in machining significantly enhances machining quality, increases productivity, and reduces production costs. In this review, first, the tool wear monitoring methods were classified and discussed. Second, the intelligence and innovation of sensors in monitoring cutting force, temperature, and vibration were introduced, and the commonly used types of sensors for online monitoring of cutting force were detailed. Furthermore, different types of sensors in tool wear were discussed, and the advantages of multi-sensor monitoring were summarized. Some urgent issues and perspectives that need to be addressed were proposed, providing new ideas for the design and development of intelligent tools.
{"title":"Sensor-based intelligent tool online monitoring technology: Applications and progress","authors":"Jiashuai Huang, Guang-qiang Chen, Hong Wei, Zhuang Chen, Yingxin Lv","doi":"10.1088/1361-6501/ad66f1","DOIUrl":"https://doi.org/10.1088/1361-6501/ad66f1","url":null,"abstract":"\u0000 With the continuous development of the aerospace, defense, and military industry, along with other high-end fields, the complexity of machined parts has gradually increased. Consequently, the demand for tool intelligence has also strengthened. However, traditional tools are prone to wear during cutting due to high cutting forces, high temperatures, and vibrations. Intelligent tools, in contrast to traditional ones, integrate sensors into their design, allowing for real-time monitoring of the cutting status and timely prediction of tool wear. The application of intelligent tools in machining significantly enhances machining quality, increases productivity, and reduces production costs. In this review, first, the tool wear monitoring methods were classified and discussed. Second, the intelligence and innovation of sensors in monitoring cutting force, temperature, and vibration were introduced, and the commonly used types of sensors for online monitoring of cutting force were detailed. Furthermore, different types of sensors in tool wear were discussed, and the advantages of multi-sensor monitoring were summarized. Some urgent issues and perspectives that need to be addressed were proposed, providing new ideas for the design and development of intelligent tools.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"51 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807665","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 : 2024-07-24DOI: 10.1088/1361-6501/ad66ff
Xiangdong Zhou, Xiao Deng, Zhengwu Liu, Haidong Shao, Bin Liu
Existing domain generalization-based intelligent fault diagnosis methods mainly focus on learning domain-invariant features. However, in practical scenarios, these features are difficult to extract and effectively distinguish from class-related features. Moreover, these methods often assume identical label distributions between the source and target domain, making it challenging to handle scenarios where unknown classes exist in the target domain. To address these issues, this paper proposes a domain generalized open-set intelligent fault diagnosis method based on feature disentanglement meta-learning. A binary mask feature disentanglement module is constructed to overcome the information loss caused by feature reconstruction, enabling the separation of domain-specific and class-related features. Additionally, a meta-purification loss function is defined, incorporating a correlation loss term to remove impurity features from the class-related features, and further purifying class information through feature combination pairing. The method is trained on multiple source domains using a meta-learning strategy and generalized to target domains with unknown classes. The method is utilized for bearing fault diagnosis, designing multi-task experimental scenarios under different rotational speeds, and compared with existing domain generalization methods. Experimental results show that the proposed method exhibits excellent generalization ability and effectively addresses the issue of domain generalized open-set fault diagnosis.
{"title":"Domain Generalized Open-Set Intelligent Fault Diagnosis Based on Feature Disentanglement Meta-Learning","authors":"Xiangdong Zhou, Xiao Deng, Zhengwu Liu, Haidong Shao, Bin Liu","doi":"10.1088/1361-6501/ad66ff","DOIUrl":"https://doi.org/10.1088/1361-6501/ad66ff","url":null,"abstract":"\u0000 Existing domain generalization-based intelligent fault diagnosis methods mainly focus on learning domain-invariant features. However, in practical scenarios, these features are difficult to extract and effectively distinguish from class-related features. Moreover, these methods often assume identical label distributions between the source and target domain, making it challenging to handle scenarios where unknown classes exist in the target domain. To address these issues, this paper proposes a domain generalized open-set intelligent fault diagnosis method based on feature disentanglement meta-learning. A binary mask feature disentanglement module is constructed to overcome the information loss caused by feature reconstruction, enabling the separation of domain-specific and class-related features. Additionally, a meta-purification loss function is defined, incorporating a correlation loss term to remove impurity features from the class-related features, and further purifying class information through feature combination pairing. The method is trained on multiple source domains using a meta-learning strategy and generalized to target domains with unknown classes. The method is utilized for bearing fault diagnosis, designing multi-task experimental scenarios under different rotational speeds, and compared with existing domain generalization methods. Experimental results show that the proposed method exhibits excellent generalization ability and effectively addresses the issue of domain generalized open-set fault diagnosis.","PeriodicalId":510602,"journal":{"name":"Measurement Science and Technology","volume":"5 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141808818","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：