CN-117010504-B - Multi-target maintenance strategy optimization method for yarn-making infrared moisture meter and storage medium

CN117010504BCN 117010504 BCN117010504 BCN 117010504BCN-117010504-B

Abstract

The invention discloses a multi-target maintenance strategy optimization method and a storage medium for a wire-making infrared moisture meter, wherein the method comprises the steps of S1, obtaining a state x i of the infrared moisture meter, S2, determining a priority according to the state x i , determining maintenance task completion time and maintenance task completion cost according to the proportion of the infrared moisture meter to be maintained in the whole infrared moisture meter and the non-maintenance result state, S3, determining a comprehensive analysis index of the infrared moisture meter according to the priority, the maintenance task completion time and the maintenance task completion cost, S4, constructing a Markov decision model according to the state x i of the infrared moisture meter and the comprehensive analysis index, and S5, generating an optimal maintenance strategy based on the Markov decision model. The method aims at specific requirements and characteristics of the moisture meter, can improve the operation efficiency of equipment, reduce the failure rate and prolong the service life of the equipment, and meanwhile, adds maintenance time factors to determine the optimal maintenance time window so as to minimize the interference to the production process.

Inventors

WU YUE
JI YIFAN
XU XIAOYUAN
LI WENLIANG

Assignees

红云红河烟草(集团)有限责任公司

Dates

Publication Date: 20260512
Application Date: 20230809

Claims (10)

1. The method for optimizing the multi-target maintenance strategy of the infrared moisture meter of the wire making line is characterized by comprising the following steps of: S1, acquiring states of an infrared moisture meter, wherein the states comprise a design characteristic state, an operation condition state, a degradation characteristic state and an unaware result state; step S2, determining priority according to the design characteristic state, the operation condition state and the degradation characteristic state; Determining maintenance task completion time and maintenance task completion cost according to the proportion of the infrared moisture meter to be maintained in the total infrared moisture meter and the non-maintenance result state; step S3, determining the comprehensive analysis index of the infrared moisture meter according to the priority, the maintenance task completion time and the maintenance task completion cost; S4, constructing a Markov decision model according to the design characteristic state, the operation condition state, the degradation characteristic state, the non-maintenance result state and the comprehensive analysis index of the infrared moisture meter, wherein the Markov decision model comprises a state space, an action space and a reward function; S5, generating an optimal maintenance strategy based on a Markov decision model; The state of the infrared moisture meter is represented by x i ; the design characteristic states comprise a moisture meter optical filter motor rotating speed design characteristic x 1 and a zero point offset x 2 ; The operating condition states comprise correction value offset rate x 3 of each license plate of the month and oven offset amount x 4 of the same month; the degradation characteristic state comprises an offset x 5 between a motor rotation speed central value of the moisture meter and a standard value and an offset x 6 between a light source illumination central value of the moisture meter and the standard value; The non-maintenance result states comprise quality risk x 7 caused by non-maintenance, economic risk x 8 caused by non-maintenance and human resource x 9 required by maintenance.
2. The method of claim 1, wherein, ; ; ; ; ; 。
3. The method according to claim 2, wherein in step S2, for the design feature state, the operation condition state, and the degradation feature state, the priority P is output according to the following rule: If x i _ min is less than or equal to 0.85, outputting a first priority P1; If 0.85 < x i _ min is less than or equal to 0.9, outputting a second priority P2; If 0.9 < x i _ min is less than or equal to 0.95, outputting a third priority P3; If 0.95 < x i _ min , outputting the fourth priority P4; x i _ min is the minimum value in the state x i of the infrared moisture meter.
4. The method according to claim 2, wherein in the step S2, the maintenance task completion time is determined according to the following rule: If R is less than or equal to 0.2, then output t=2/x 9 ; If 0.2 < R < 0.4, then output T=3/x 9 ; if 0.4 < R < 0.6, then output T=4/x 9 ; If 0.6 < R, then output t=5/x 9 ; wherein R is the proportion of the infrared moisture meter to be maintained to the total infrared moisture meter, and T is the maintenance task completion time.
5. The method according to claim 4, wherein in the step S2, the maintenance task completion cost c=c T +C R ; Wherein, C T is time cost, C R is labor cost; If R is less than or equal to 0.2, C T =2*A,C R =B 1 *X 9 ; if 0.2 < R < 0.4, then C T =3*A,C R =B 2 *X 9 ; if 0.4 < R < 0.6, then C T =4*A,C R =B 3 *X 9 ; If 0.6 < R, C T =5*A,C R =B 4 *X 9 ; Wherein A is the cost of each time unit, and B 1 to B 4 are the cost of human resource units corresponding to different proportions R.
6. The method according to claim 1, wherein in the step S3, the integrated analysis index F of the infrared moisture meter is: ; wherein P is the priority of the task, T is the time for completing the maintenance task, C is the cost for completing the maintenance task, and N is the total number of the infrared moisture meters to be maintained.
7. The method of claim 1, wherein the action space is represented as actions: actions = [action_1, action_2, action_3, action_4, action_5]; Wherein, action_1 is the rotation speed of the filter motor of the overhauling moisture meter; action_2 is to adjust zero offset of the moisture meter; action_3 is a parameter for correcting different brands; action_4 is to perform light source maintenance operation; action_5 is to do nothing.
8. The method of claim 5, wherein the bonus function is represented as R total : ; Wherein, the Rewarding for performance stability; Rewarding maintenance cost; Rewards for risk assessment; the action selects a reward.
9. The method of claim 8, wherein, ; ; ; ; Wherein, the Is a state space; Is a target value; As the weight of the material to be weighed, Is the action space, namely , Is a decay function; a value of quality risk caused by the fact that maintenance is not performed; The maintenance cost is the maintenance task completion cost C; refers to quality risk.
10. A computer readable storage medium having stored thereon a computer program, wherein the computer program is executable by a processor to perform the steps of the method according to any of claims 1-9.

Description

Multi-target maintenance strategy optimization method for yarn-making infrared moisture meter and storage medium Technical Field The invention relates to the technical field of cigarette cut-tobacco production, in particular to a method for optimizing a multi-target maintenance strategy of an infrared moisture meter of a cut-tobacco production line and a storage medium. Background In the production of cut tobacco of cigarettes, an infrared moisture meter is a very important device for measuring the moisture content in cut tobacco so as to ensure the taste, filling value and the like of the cigarette products. Therefore, the maintenance strategy needs to ensure the normal operation of the infrared moisture meter, including accuracy, reliability, stability and the like, so as to ensure the accurate control of the moisture content of tobacco shreds in the cigarette production process. The method adopted at present is mainly based on statistics or empirical formulas to optimize maintenance strategies, but lacks comprehensive consideration of reliability analysis of the infrared moisture meter. And is based on the optimization of maintenance requirements of the equipment, with less consideration for integration with the production plan. In the cigarette cut-making production, the infrared moisture meter is one of key equipment in the production process, and a maintenance strategy of the infrared moisture meter needs to be coordinated with a production plan to ensure that maintenance is performed within an optimal time window so as to minimize interference to the production process. Based on this, a maintenance strategy solution is needed for the specific needs and characteristics of the infrared moisture meter. Disclosure of Invention Aiming at the problems, the invention provides a multi-target maintenance strategy optimization method and a storage medium for the wire-making infrared moisture meter aiming at the specific requirements and characteristics of the infrared moisture meter. According to a first aspect, the invention provides a method for optimizing a multi-objective maintenance strategy of a wire-making infrared moisture meter, which comprises the following steps: Step S1, acquiring a state x i of an infrared moisture meter, wherein the state comprises a design characteristic state, an operation condition state, a degradation characteristic state and an unwarranted consequence state; step S2, determining priority according to the design characteristic state, the operation condition state or the degradation characteristic state; Determining maintenance task completion time and maintenance task completion cost according to the proportion of the infrared moisture meter to be maintained in the total infrared moisture meter and the non-maintenance result state; step S3, determining the comprehensive analysis index of the infrared moisture meter according to the priority, the maintenance task completion time and the maintenance task completion cost; S4, constructing a Markov decision model according to the design characteristic state, the operation condition state, the degradation characteristic state, the non-maintenance result state and the comprehensive analysis index of the infrared moisture meter, wherein the Markov decision model comprises a state space, an action space and a reward function; and S5, generating an optimal maintenance strategy based on the Markov decision model. Further, in step S2, for the design feature state, the operation condition state, and the degradation feature state, the priority P is output according to the following rule: If x i_min is less than or equal to 0.85, outputting a first priority P1; If 0.85< x i_min is less than or equal to 0.9, outputting a second priority P2; If 0.9< x i_min is less than or equal to 0.95, outputting a third priority P3; outputting a fourth priority P4 if 0.95< x i_min; x i_min is the minimum value in the state x i of the infrared moisture meter. Further, the design feature state includes: Moisture meter filter motor rotational speed design feature x 1 and zero offset x 2; wherein x 1 is a design feature for describing the filter capability of the moisture meter, and the stability of the motor rotation speed and the stability of the filter performance can be evaluated by checking whether the rotation speed reaches a unified standard. Discrete (1000) defines a Discrete space ranging from 7000 to 8000. Zero offset x 2 is a parameter describing the magnitude of the zero offset of the moisture meter. Zero point offset is a form of damage caused by repeated loading and light source attenuation, electronic component aging, random factors, etc., which can be used to evaluate the stability of moisture meter measurements. X 2 ranges from 0 to 1, and is a floating point number. The operating condition states include: Correction value offset rate x 3 and same month oven offset x 4 of each license plate of the month; wherein x 3 is the variation parameter