Self-adapt dynamic apparatus status alarming method based on probability model

Abstract

The invention discloses a probabilistic model-based equipment state dynamic self-adaptive alarm method. Based on the dynamic data of equipment operation, the probability model of the equipment state is constructed by using the probability neural network self-learning. The model adjusts its distribution profile with the operation of the equipment, and dynamically describes the change rule of the equipment state. Relying on the model, study the dynamic judgment rules of equipment status; at the same time, construct thresholds between different states to form an adaptive alarm line for equipment operation. The present invention ignores the traditional basis for dividing the operating status of on-site equipment according to various general standards, and finds the rules from the respective development history of the equipment, and can establish a status level for each equipment, each measuring point, and even each monitoring quantity Judgment basis, clearly divides the state of conventional equipment on site into three levels: normal state, fault state, and rapid deterioration state, and determines the measures that should be taken in the field for each state, laying a foundation for comprehensive evaluation of equipment state Base.

Description

technical field [0001] The invention belongs to the field of equipment state monitoring and diagnosis, and relates to equipment operation state classification and alarm threshold setting technology, and further relates to a probability model-based equipment state dynamic self-adaptive alarm method. Background technique [0002] Equipment operating status classification and threshold setting have always been difficult problems in equipment status monitoring technology. From the perspective of manifestation, there are absolute standards and relative standards for equipment status alarms. The absolute standard refers to the absolute value of the monitored quantity to judge the state of the equipment; the relative standard refers to the allowable value of the change rate of the vibration value of the equipment itself. Standard research on equipment status alarms is generally led by standardization organizations. However, there are several major problems in the use of these sta...

AI Technical Summary

Problems solved by technology

However, there are several major problems in the use of these standards in industrial sites at present. The first is the clarity of the classification. Due to the continuity of the state changes of mechanical equipment, it is difficult to explain that the different monitoring quantities above and below the threshold of a certain level have essential differences. It cannot clearly explain the state of the current equipment in a physical sense; the second is the applicability of the threshold setting. Since the actual operation of the field equipment and the working conditions of the field are not taken into account, these standards only put forward reference significance from the commonality The above judgment standard, its actual guiding significance is not obvious

[0003] On the other hand, with the continuous development of sensor technology and monitoring and diagnosis technology, in addition to vibration, enterprises have gradually begun to strengthen the monitoring of various process quantities such as equipment temperature, pressure, flow, etc., and use these process quantity data to monitor equipment. In terms of status division, there is still no effective basis for judging

Images