This paper focuses on the new approach of on line monitoring of grinding burn and wheel wear based on the rough set theory. This method adopts the grinding chip flow thermal signal, and acquires identification rules ...This paper focuses on the new approach of on line monitoring of grinding burn and wheel wear based on the rough set theory. This method adopts the grinding chip flow thermal signal, and acquires identification rules by establishing sensitive characteristic parameters and constructing the knowledge system through continuum attribute discretization, attribute reduction and knowledge acquisition, and then monitors grinding burn and wheel wear in accordance with the acquired rules. The experiment results show that the new method is effective.展开更多
On the basis of analyzing the influencing factors and harmfulness of stray current, and discussing the existing problems of monitoring and prevention system for stray current, the integrated monitoring and prevention ...On the basis of analyzing the influencing factors and harmfulness of stray current, and discussing the existing problems of monitoring and prevention system for stray current, the integrated monitoring and prevention system for stray current in metro was developed. A net system of distributed computers for monitoring was set up. It can monitor the distribution of stray current in metro and the corrosion of the metal structure in the whole line. According to the situation of monitoring it can also control the drainage of its tank to reach the best effect and eliminate the negative effect of polarity drainage. By using the new type unilateral electric device, the problem of burning the rail by electric arc can be avoided. The unilateral electric device can be connected with the monitoring net system directly to realize the monitor in line and improve the reliability of the device.展开更多
In recent years,several efforts have been made to develop power transmission line abnormal target detection models based on edge devices.Typically,updates to these models rely on participation of the cloud,which means...In recent years,several efforts have been made to develop power transmission line abnormal target detection models based on edge devices.Typically,updates to these models rely on participation of the cloud,which means that network resource shortages can lead to update failures,followed by unsatisfactory recognition and detection performance in practical use.To address this problem,this article proposes an edge visual incremental perception framework,based on deep semisupervised learning,for monitoring power transmission lines.After generation of the initial model using a small amount of labeled data,models trained using this framework can update themselves based on unlabeled data.A teacher-student joint training strategy,a data augmentation strategy,and a model updating strategy are also designed and adopted to improve the performance of the models trained with this framework.The proposed framework is then examined with various transmission line datasets with 1%,2%,5%,and 10%labeled data.General performance enhancement is thus confirmed against traditional supervised learning strategies.With the 10%labeled data training set,the recognition accuracy of the model is improved to exceed 80%,meeting the practical needs of power system operation,and thus clearly validating the effectiveness of the framework.展开更多
文摘This paper focuses on the new approach of on line monitoring of grinding burn and wheel wear based on the rough set theory. This method adopts the grinding chip flow thermal signal, and acquires identification rules by establishing sensitive characteristic parameters and constructing the knowledge system through continuum attribute discretization, attribute reduction and knowledge acquisition, and then monitors grinding burn and wheel wear in accordance with the acquired rules. The experiment results show that the new method is effective.
文摘On the basis of analyzing the influencing factors and harmfulness of stray current, and discussing the existing problems of monitoring and prevention system for stray current, the integrated monitoring and prevention system for stray current in metro was developed. A net system of distributed computers for monitoring was set up. It can monitor the distribution of stray current in metro and the corrosion of the metal structure in the whole line. According to the situation of monitoring it can also control the drainage of its tank to reach the best effect and eliminate the negative effect of polarity drainage. By using the new type unilateral electric device, the problem of burning the rail by electric arc can be avoided. The unilateral electric device can be connected with the monitoring net system directly to realize the monitor in line and improve the reliability of the device.
基金supported by the National Key R&D Program of China (2020YFB0905900).
文摘In recent years,several efforts have been made to develop power transmission line abnormal target detection models based on edge devices.Typically,updates to these models rely on participation of the cloud,which means that network resource shortages can lead to update failures,followed by unsatisfactory recognition and detection performance in practical use.To address this problem,this article proposes an edge visual incremental perception framework,based on deep semisupervised learning,for monitoring power transmission lines.After generation of the initial model using a small amount of labeled data,models trained using this framework can update themselves based on unlabeled data.A teacher-student joint training strategy,a data augmentation strategy,and a model updating strategy are also designed and adopted to improve the performance of the models trained with this framework.The proposed framework is then examined with various transmission line datasets with 1%,2%,5%,and 10%labeled data.General performance enhancement is thus confirmed against traditional supervised learning strategies.With the 10%labeled data training set,the recognition accuracy of the model is improved to exceed 80%,meeting the practical needs of power system operation,and thus clearly validating the effectiveness of the framework.
