| In recent years,the Internet of Things intelligent control technology,intelligent production and fault diagnosis technology have gradually become popular,and online fault diagnosis has become a trend.At present,there are some problems in the maintenance of most rolling mill equipment,such as the need for maintenance personnel to operate on site or difficult to find in time.Due to the disadvantages of low efficiency and high cost due to various factors such as distance,it is imperative to design a remote fault diagnosis system for rolling mills based on the internet of things.First,take the AGC system as the research object,and analyze its working principle.The structural framework of remote fault diagnosis is designed according to the system requirements,and the hardware selection and design of the fault diagnosis system are studied and expounded: data is collected by displacement sensors,pressure sensors and other equipment;in terms of data transmission,the MQTT intelligent gateway is configured,and PHP is selected.Apache server,My SQL database,etc.are used as system tools to realize remote fault diagnosis based on the Internet of Things platform.Secondly,taking the fault of the AGC system as an example,a dynamic model is established to collect normal and fault data.Aiming at the high-dimensional features of the data,a fault classification and diagnosis model based on a deep belief network is proposed,which solves the problem of large diagnostic errors of the traditional model,and the optimal diagnostic rate of the model is verified by experiments.The diagnosis results are exchanged with the Internet of Things System to realize remote fault diagnosis.Finally,the requirements of the system are introduced and analyzed,and then the comparison and selection,interface design,and system construction are carried out to realize the functions of remote data monitoring,fault diagnosis,and data alarm.The Io T-based remote fault diagnosis system for rolling mills can improve the efficiency of staff and users and ensure the production efficiency of equipment.Figure 36;Table 7;Reference 51... |