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

Abstract

The method uses self-learning mode to construct equipment state probability model with probability nervous network based on dynamic data of equipment operation. The model adjusts its probability distribution by following to the equipment operation to describe variation rule of the equipment state dynamically. Relying on the model, the dynamic evaluation rule of the equipment state is studied and simultaneously the threshold for different state is set up to form adaptive alarming limit for the equipment operation. The equipment state can be graded in three classes of normal, fault and quick deterioration by utilizing this adaptive alarming method.

Description

1. The technical field [0001] The invention belongs to the field of equipment state monitoring and diagnosis, relates to equipment operating state level division and alarm threshold setting technology, and further relates to a probability model-based dynamic adaptive alarm method for equipment state. 2. Background technology [0002] The classification and threshold setting of equipment operating status has always been a difficult problem in equipment status monitoring technology. From the perspective of expression, there are absolute standards and relative standards for equipment status alarms. The absolute standard refers to the use of the absolute value of the monitoring quantity to judge the status 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 main problems i...

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