The invention discloses a strain balance temperature gradient error compensation method and system based on deep learning. The method comprises the following steps: arranging a temperature sensor on abalance to obtain temperature data and temperature gradient error data of the balance; selecting a key temperature measuring point according to the balance temperature gradient error data; finally, establishing a deep belief network DBN, setting initial parameters, and carrying out deep belief network DBN training and temperature gradient error prediction by taking the temperature data of the keytemperature measurement points as an input value of the deep belief network DBN and taking the temperature gradient error data as an output value of the network. According to the method provided by the invention, the problems of low precision and poor robustness and generalization ability of a balance temperature gradient error compensation method are solved. By selecting the key temperature measuring points on the balance, the number of the temperature sensors is reduced, and the complexity of the model is reduced; secondly, the temperature gradient error compensation method is high in prediction precision and good in robustness and generalization ability.

    本发明公开了一种基于深度学习的应变天平温度梯度误差补偿方法及系统,该方法通过在天平上布置温度传感器获取天平的温度数据以及温度梯度误差数据;然后根据天平温度梯度误差数据选取关键温度测点;最后建立深度置信网络DBN,设置初始参数,以关键温度测点的温度数据作为深度置信网络DBN的输入值,以温度梯度误差数据作为网络的输出值,进行深度置信网络DBN训练和温度梯度误差预测。本发明提出的方法,解决了天平温度梯度误差补偿方法精度不够高、鲁棒性及泛化能力不好的问题。通过选取出了天平上的关键温度测点,减少了温度传感器个数,降低了模型复杂程度;二是该温度梯度误差补偿方法预测精度高、鲁棒性和泛化能力较好。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Strain balance temperature gradient error compensation method and system based on deep learning


    Weitere Titelangaben:

    基于深度学习的应变天平温度梯度误差补偿方法及系统


    Beteiligte:
    PI YANGJUN (Autor:in) / ZOU XINGWANG (Autor:in) / WANG CHAO (Autor:in) / ZHU JIANGLING (Autor:in) / XIE ZHIJIANG (Autor:in) / XIE BIN (Autor:in) / LIU FEI (Autor:in) / XIANG GUANGWEI (Autor:in) / SONG DAIPING (Autor:in) / ZHU JIAHAO (Autor:in)

    Erscheinungsdatum :

    2020-09-08


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G01M TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES , Prüfen der statischen oder dynamischen Massenverteilung rotierender Teile von Maschinen oder Konstruktionen / B64F GROUND OR AIRCRAFT-CARRIER-DECK INSTALLATIONS SPECIALLY ADAPTED FOR USE IN CONNECTION WITH AIRCRAFT , Boden- oder Flugzeugträgerdeckeinrichtungen besonders ausgebildet für die Verwendung in Verbindung mit Luftfahrzeugen / G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Model Free Error Compensation for Cable-Driven Robot Based on Deep Learning with Sim2real Transfer Learning

    Akhmetzyanov, Aydar / Rassabin, Maksim / Maloletov, Alexander et al. | TIBKAT | 2022


    Elevator car balance compensation chain system

    WEI WEI / MAO LIANG / HAN YANG et al. | Europäisches Patentamt | 2015

    Freier Zugriff

    Electromechanical actuator strain gauge temperature compensation device

    DRENNEN DAVID / KELLER STEVEN | Europäisches Patentamt | 2015

    Freier Zugriff


    Fiber Optic Gyro Temperature Error Compensation Based on Multi-parameter Model*

    Dai, Shaowu / Zheng, Baidong / Dai, Hongde | IEEE | 2018