A method and system for industrial equipment control optimization based on monitoring data

Abstract

The invention discloses an industrial equipment control optimization method based on monitoring data, which aligns different time stamps between historical operating state data and historical process data, and generates historical operating state data sets and historical process data sets with consistent time series; Carry out model training on the formed feature vector sample set to build a health diagnosis model; input the current operating status data and current process control data into the health diagnosis model to obtain the predicted probability of the current equipment health state; if the predicted probability is less than or equal to the probability threshold, Divide the process control parameter set into multiple sets of process control parameter sets, input each set of process control parameter sets and the current operating state data combination into the health diagnosis model, obtain the maximum prediction probability of the current equipment health state, and correspond the maximum prediction probability to The process control parameter set of is set as the process control parameters of the current equipment. The invention can more comprehensively analyze the operating state of the equipment.

Description

technical field [0001] The invention relates to the technical field of industrial equipment fault diagnosis, in particular to an industrial equipment control optimization method and system based on monitoring data. Background technique [0002] With the development of big data technology and machine learning, the use of machine learning and big data analysis technology has become an important research direction for industrial equipment process improvement. The data comes from various sensors of industrial equipment. Multi-sensor information fusion technology is a research hotspot in recent years. It is a comprehensive technology that combines various disciplines such as control theory, signal processing, artificial intelligence, probability and statistics. Utilize the redundancy of multiple sensor information in time and space, improve the accuracy and reliability of measurement information, and obtain more accurate identification, judgment and decision-making. The measurem...

AI Technical Summary

Problems solved by technology

However, in the existing technical solutions, only the sensor information from a single source is analyzed, and the sensor information from multiple sources is not analyzed, nor is the process data information of the equipment combined for analysis. Therefore, the analysis of the operating status of the equipment Not comprehensive, unable to accurately grasp the working status of the equipment

[0003] The patent publication No. CN110119339A needs to select a sensor as the target sensor, and the algorithm is developed based on the data of this sensor. On the one hand, the accuracy of the system depends on the accuracy of the sensor, and the fluctuation is large. On the other hand, the robustness of the system is poor.

The patent of patent publication number CN111913443A only considers the feature extraction of each data itself, but does not consider the correlation and synergistic features between data and data, and also does not perform time alignment between data, and the accuracy will be affected

The patent with the patent publication number CN110377001A can perform pattern recognition through data fusion, and give the fault severity level of each component of industrial equipment, but cannot actively give suggestions for equipment process improvement

The patent publication number CN108803552A collects and analyzes the state quantities of equipment operation, and does not integrate the process quantities in the equipment DCS (Distributed Control System, distributed control system) data for collaborative analysis

Images