作者:北京和利時智能技術(shù)有限公司,寧波和利時智能科技有限公司 范瑩,李天輝,劉宗福,姜百寧
摘要:為解決機器人故障預(yù)測問題,提出一種使用機器人軸溫預(yù)測的方法,實現(xiàn)機器人異常發(fā)熱的提前預(yù)警,避免故障的發(fā)生。本文使用生產(chǎn)中機器人的歷史數(shù)據(jù)作為數(shù)據(jù)源,分析對機器人軸溫產(chǎn)生影響的測點,結(jié)合機器人機理,對數(shù)據(jù)進行衍生轉(zhuǎn)換等操作,生成可以用于機器人軸溫預(yù)測的特征數(shù)據(jù)。鑒于沒有免費午餐(NFL,No Free Lunch)定理,對所有數(shù)據(jù)可用回歸算法進行自動化選擇,然后使用hyperopt進行優(yōu)化調(diào)參,最終生成可用的機器人軸溫預(yù)測模型。本文中所述數(shù)據(jù)獲取、分析建模、上線部署及在線預(yù)測全部過程在HolliCube工業(yè)互聯(lián)網(wǎng)平臺上進行。
關(guān)鍵詞:溫度預(yù)測;故障診斷;機器人;工業(yè)互聯(lián)網(wǎng)平臺;運行周期
Abstract: Aiming at fault diagnosis for robots, a method which predicts robot's axes temperature is proposed to realize abnormal robot heating in advance and avoid the occurrence of faults. In this paper, the historical data of the robot in production are used as data source to analyze the measuring points which affect the axle temperature of the robot. Combined with the mechanism of the robot, the data are derived and converted to generate the characteristic data which can be used to predict the axle temperature of the robot. Then select regression algorithms automatically caused by the NFL theory, and then optimize the hyper-parameters by hyperopt and finally we got the model. The whole process of data acquisition, analysis and modeling, online deployment and online prediction described in this paper are carried out on HolliCube industrial Internet platform.
Key words: Temperature prediction; Fault diagnosis; Robot;Industrial internet platform; Running cycle
在線預(yù)覽:基于數(shù)據(jù)驅(qū)動的機器人軸溫預(yù)測建模與應(yīng)用
摘自《自動化博覽》2019年10月刊