CN-121998503-A - Space division production line health degree evaluation method, system and equipment

CN121998503ACN 121998503 ACN121998503 ACN 121998503ACN-121998503-A

Abstract

The invention relates to the technical field of equipment health assessment, in particular to a method, a system and equipment for evaluating the health degree of an air separation production line, comprising the following steps of S1, dividing the air separation production line into a primary subsystem layer, an evaluation dimension layer and an evaluation index layer from top to bottom; the method comprises the steps of S2, collecting index real-time data, calculating real-time health degree scores of indexes according to the relation between the index real-time data and a preset state threshold value, S3, dynamically calculating real-time weights of the indexes based on the deviation degree of the index real-time data from the threshold value, S4, calculating dimension scores of evaluation dimensions according to the scores and weights of the indexes, S5, calculating health degree scores of first-level subsystems according to the dimension scores and the preset dimension weights, and S6, calculating and outputting overall health degree evaluation results of the space division production line according to the subsystem scores and the preset subsystem weights. The invention realizes comprehensive, dynamic and quantitative evaluation of the health state of the space production line and supports layer-by-layer accurate positioning of faults.

Inventors

JI JUNPING
ZHU YAJUN
JIN CHAO
ZHANG GUOPING
YANG LING
XING GANG
WANG ZHONGCHANG

Assignees

宝武清洁能源有限公司

Dates

Publication Date: 20260508
Application Date: 20260127

Claims (10)

1. The space division production line health degree evaluation method is characterized by comprising the following steps of: S1, dividing an air separation production line to be evaluated into a plurality of first-level subsystem layers, a plurality of evaluation dimension layers under each first-level subsystem and a plurality of evaluation index layers under each evaluation dimension from top to bottom according to a function level; S2, collecting monitoring data of all evaluation indexes in real time, and calculating real-time health degree scores of the evaluation indexes according to the relation between the real-time data of the evaluation indexes and a plurality of preset state thresholds; S3, dynamically calculating the real-time weight of each evaluation index based on the deviation degree between the real-time data of each evaluation index and the preset state thresholds; s4, calculating dimension scores of all evaluation dimensions according to the real-time health scores of all evaluation indexes and the real-time weights corresponding to the real-time health scores; s5, calculating the health degree score of each primary subsystem layer according to the dimension score and the preset dimension weight; and S6, calculating and outputting the overall health evaluation result of the space division production line according to the health score of each primary subsystem layer and the preset subsystem weight.
2. The method for evaluating the health degree of a space division line according to claim 1, wherein in step S1, the space division line to be evaluated is divided from top to bottom according to a function hierarchy, comprising: Dividing the air separation production line to be evaluated into a plurality of first-stage subsystem layers comprising an air compressor system, a precooling system, a purifying system, a supercharger system and a fractionating tower system according to an air separation process flow; dividing the corresponding evaluation dimension layer according to key equipment or functional modules in the primary subsystem layer; And dividing the physical parameters under the evaluation dimension layer into the evaluation index layers including vibration, temperature, pressure, displacement, power and flow.
3. The method according to claim 1, wherein in step S2, calculating a real-time health score of each evaluation index according to a relationship between real-time data of each evaluation index and a plurality of preset state thresholds, includes: The state thresholds divide the numerical range of the index into a plurality of continuous state intervals including a normal interval, an early warning interval and an alarm interval; comparing the real-time data with the state threshold value to determine a state interval to which the real-time data belongs; And calculating to obtain the real-time health score of the evaluation index according to a standard score calculation rule preset in the determined state interval.
4. The method for evaluating the health degree of a space division line according to claim 3, wherein the reference score calculation rule is a piecewise function, comprising: According to the real-time detection value x of the evaluation index, the preset eight state thresholds are as follows < < < < < < < The real-time health score y is calculated as follows: , Wherein, the , 。
5. The method according to claim 4, wherein in step S3, dynamically calculating the real-time weight of each evaluation index comprises: According to the real-time detection value x of the evaluation index, calculating real-time weight w as follows: Wherein, the Is the normal interval of the core, x < Is a shutdown/invalid interval in which, Is a preset weight upper limit value.
6. The method according to claim 1, wherein in step S4, the step of calculating the score of each evaluation dimension based on the score of each evaluation index and the corresponding real-time weight thereof comprises: wherein score is an evaluation dimension score, The real-time weight of the ith evaluation index under the dimension layer, And (3) a real-time health score of the evaluation index, wherein n is the total number of the evaluation indexes in the evaluation dimension.
7. The method for evaluating the health degree of a space division line according to claim 1, wherein in step S5, calculating the health degree score of each primary subsystem layer according to the score of each evaluation dimension and a preset dimension weight comprises: The health score SubsysScore of the primary subsystem layer is calculated by a weighted summation method, and the formula is as follows: Wherein, the The preset dimension weight of the ith evaluation dimension under the primary subsystem layer is the preset dimension weight, and the preset dimension weight meets the following requirements , And (3) scoring the ith evaluation dimension layer, wherein m is the total number of the evaluation dimension layers under the first-level subsystem layer.
8. The method according to claim 1, wherein in step S6, calculating and outputting the overall health evaluation result of the space division line includes: Calculating the overall health evaluation result of the space division production line by adopting a weighted summation method The formula is as follows: Wherein, the Preset subsystem weight for the jth primary subsystem layer and meets the following requirements , The health score for the jth level one subsystem layer, p is the total number of level one subsystem layers.
9. A computer device comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of a space division line health assessment method according to any one of claims 1 to 8.
10. A storage medium storing computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of a space division line health assessment method according to any one of claims 1 to 8.

Description

Space division production line health degree evaluation method, system and equipment Technical Field The invention relates to the technical field of equipment health assessment, in particular to a method, a system and equipment for evaluating the health degree of a space division production line. Background The air separation (air separation) production line is used as key industrial equipment, and the long-term stable operation of the air separation (air separation) production line is important to the guarantee of continuous production. The traditional equipment state monitoring and health management method mainly has the following limitations: Conventional approaches typically rely on a single sensor (e.g., vibration, temperature) to monitor a particular component and empirically set a fixed alarm threshold. The method can not reflect the whole operation state of the complex production line, the fixed threshold is difficult to adapt to the dynamic changes of the equipment in different working conditions and service life stages, false alarm or missing alarm is easy to occur, the existing method focuses on fault diagnosis or abnormal alarm, and quantitative evaluation on the whole health degree of the equipment is lacking. The evaluation by adopting a statistical model (such as a reliability model and survival analysis) is seriously dependent on a large amount of historical fault data, but the complete fault data of the industrial field is often difficult to obtain, so that the model is difficult to build, and real-time and visual health scoring is difficult to realize. When comprehensively evaluating a plurality of parameters, the prior method mostly adopts fixed weight. However, in actual operation, the same parameter varies in severity as represented by different numerical intervals, and its contribution (i.e., weight) to overall health should be dynamically changed. Therefore, a quantitative evaluation method for the health degree of the space division production line, which can overcome the defects, realize multi-level and multi-parameter fusion and weight dynamic self-adaption, is needed to reflect the whole health condition of the production line in real time and intuitively, accurately position potential risk points and provide scientific basis for predictive maintenance. Disclosure of Invention The invention aims to solve the defects in the prior art, and provides a space division production line health degree evaluation method, which comprises the following steps: S1, dividing an air separation production line to be evaluated into a plurality of first-level subsystem layers, a plurality of evaluation dimension layers under each first-level subsystem and a plurality of evaluation index layers under each evaluation dimension from top to bottom according to a function level; S2, collecting monitoring data of all evaluation indexes in real time, and calculating real-time health degree scores of the evaluation indexes according to the relation between the real-time data of the evaluation indexes and a plurality of preset state thresholds; S3, dynamically calculating the real-time weight of each evaluation index based on the deviation degree between the real-time data of each evaluation index and the preset state thresholds; s4, calculating dimension scores of all evaluation dimensions according to the real-time health scores of all evaluation indexes and the real-time weights corresponding to the real-time health scores; s5, calculating the health degree score of each primary subsystem layer according to the dimension score and the preset dimension weight; and S6, calculating and outputting the overall health evaluation result of the space division production line according to the health score of each primary subsystem layer and the preset subsystem weight. Preferably, in step S1, the dividing the space division line to be evaluated from top to bottom according to the function level includes: Dividing the air separation production line to be evaluated into a plurality of first-stage subsystem layers comprising an air compressor system, a precooling system, a purifying system, a supercharger system and a fractionating tower system according to an air separation process flow; dividing the corresponding evaluation dimension layer according to key equipment or functional modules in the primary subsystem layer; And dividing the physical parameters under the evaluation dimension layer into the evaluation index layers including vibration, temperature, pressure, displacement, power and flow. Preferably, in step S2, calculating a real-time health score of each evaluation index according to a relationship between real-time data of each evaluation index and a preset plurality of state thresholds, includes: The state thresholds divide the numerical range of the index into a plurality of continuous state intervals including a normal interval, an early warning interval and an alarm interval; comparing the real-time