CN109445282A - A kind of Optimization Scheduling towards basic device processing technology - Google Patents
A kind of Optimization Scheduling towards basic device processing technology Download PDFInfo
- Publication number
- CN109445282A CN109445282A CN201811317035.2A CN201811317035A CN109445282A CN 109445282 A CN109445282 A CN 109445282A CN 201811317035 A CN201811317035 A CN 201811317035A CN 109445282 A CN109445282 A CN 109445282A
- Authority
- CN
- China
- Prior art keywords
- processing
- state
- time
- energy consumption
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 159
- 238000005457 optimization Methods 0.000 title claims abstract description 30
- 238000005516 engineering process Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 133
- 230000008569 process Effects 0.000 claims abstract description 106
- 238000005265 energy consumption Methods 0.000 claims abstract description 44
- 238000004519 manufacturing process Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims description 44
- 230000009471 action Effects 0.000 claims description 30
- 238000011156 evaluation Methods 0.000 claims description 21
- 238000003754 machining Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000013178 mathematical model Methods 0.000 claims description 8
- 230000002787 reinforcement Effects 0.000 claims description 4
- 230000007547 defect Effects 0.000 abstract 1
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 238000004140 cleaning Methods 0.000 description 10
- 238000013461 design Methods 0.000 description 5
- 238000005422 blasting Methods 0.000 description 4
- 229920003023 plastic Polymers 0.000 description 4
- 239000004033 plastic Substances 0.000 description 4
- 238000005507 spraying Methods 0.000 description 4
- 238000003801 milling Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013386 optimize process Methods 0.000 description 2
- 238000010923 batch production Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001050 lubricating effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The present invention relates to a kind of Optimization Schedulings towards basic device processing technology, for the defects of process time present in basic device process is too long, basic device process equipment energy consumption is higher and apparatus of load is unbalanced, a kind of processing route Optimization Scheduling is designed.Firstly, establishing basic device process model；Secondly, establishing the constraint relationship according to technique and manufacturing resource limits in process；Finally, binding model problem, improves enhancing learning algorithm to solve to model, completes the Optimized Operation to basic device processing technology path.The present invention can significantly improve basic device processing efficiency, reduce basic device tooling cost, improve resource utilization, the processing route Optimized Operation suitable for basic device manufacturing field Single unit job lot production.
Description
Technical Field
The invention relates to an optimized scheduling method for a basic component processing technology, which is mainly applied to the process path optimization of a non-production line technology of a basic component manufacturing workshop.
Background
The complex product processing has the characteristics of long operation period, single piece processing and small batch production, but the complex product processing has large market demand, multiple application fields, wide technical popularization range, wide product popularization range and wide benefit range. The machining process comprises two stages of part machining and part assembly. As a complex product, the basic component is usually controlled by pressure oil of a pressure distribution valve, can be combined with an electromagnetic pressure distribution valve for use, and is used for remotely controlling the on-off of oil, gas and water pipeline systems of a hydropower station and oil ways for clamping, controlling, lubricating and the like. Meanwhile, basic components are necessary for high-end manufacturing and general product manufacturing of aerospace, automobile and rail transit, mechanical equipment and the like, are key for supporting development of engineering machinery hosts, and have the characteristics of complex design and high requirement on casting machining precision. The market space of the engineering machinery in China is wide in the future, and the demand on basic components is large.
At present, the development of domestic high-end basic components cannot meet the urgent need of a host, the domestic high-level basic components cannot reach the batch matching level of the host, the basic components are basically in the testing and trial stages, the specifications are few, the reliability cannot be fully verified in a short time, and the situation of dependence on import is not fundamentally changed. The process design is used as a connecting link for product design and manufacturing, and the processing efficiency and the quality level of product parts are greatly limited. Due to the selection of part features, manufacturing accuracy, processing methods and manufacturing resources, diversity is presented in process route design. Therefore, how to select the optimal processing scheme among various process routes for product manufacturing to save cost and improve manufacturing quality is important. The processing process of the basic components is researched, and the purposes of reasonably distributing manufacturing resources, shortening the processing period of products and reducing the processing cost of enterprises are achieved by optimizing a process route.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the problems of overlong processing time, higher energy consumption of basic component processing equipment, unbalanced equipment load and the like in the basic component processing process, the optimized scheduling method for the basic component processing technology is provided, the convergence speed of the method is high, the production efficiency can be obviously improved, and the processing cost is saved.
The technical solution of the invention is as follows: an optimized scheduling method for a basic component processing technology comprises the following implementation steps:
firstly, establishing a mathematical model of a basic component process path, wherein the model comprises the following steps:
① energy consumption model, basic components are the main components of products in mechanical and electronic industries, the process route of the basic components is composed of different procedures, and is subject to the component processing process, each procedure is processed on different equipment in a factory workshop, the energy consumption of equipment (including a shot blasting machine, an inter-sequence cleaning machine, a vertical processing center, a horizontal processing center, a milling machine, a cleaning assembly line and a plastic spraying line) in the processing process is calculated, the energy consumption of the basic component processing equipment is equal to the sum of the working energy consumption and the standby energy consumption, and the energy consumption model is as follows:
Ei＝Ei worker+EWait for
EI worker＝PI worker×tI worker
EWait for＝PWait for×tWait for
Wherein E isiDescribing the total energy consumption of the processing equipment, i is 1,2, …, n represents the number of equipment, EI workerDescription of the energy consumption of the processing apparatus i during processing, EWait forDescribing the energy consumption, P, generated by the processing apparatus i during standbyI workerDescription of the processing Power, t, of the apparatus iI workerDescription of the duration of processing of the apparatus i, PWait forStandby power, t, of the description deviceWait forThe standby time period of the device i is described.
The total energy consumption of the basic component processing workshop equipment is the sum of the energy consumptions of all the processing equipment in the basic component processing workshop:
wherein E isGeneral assemblyThe total energy consumption of all the processing equipment, i.e. optimization goal one, is described.
② time model, the standby time of the basic component processing equipment is calculated by subtracting the sum of the processing start time and the processing time of the basic component processing equipment in the processing process from the processing finish time of the basic component processing equipment, and the time model is as follows:
ti Standby＝ti completion-tI worker-ti start with
Wherein, ti start withIndicates the starting time, t, of the machining of the part on the machine ii completionIndicating the end time, t, of the machining of the part on the machine ii StandbyStandby duration of the apparatus i during the machining of the parts, tI workerWhich represents the time that the device i is operating normally, i.e., the length of time that the part is being machined. max { t }i completionAnd f, the total processing completion time is the optimization objective II.
③ load balance model the load balance of basic component processing equipment is measured by the variance of the processing time of each processing equipment in a workshop (the smaller the variance of the processing time, the higher the load balance is), and the load balance model is as follows:
wherein,and the average value of the processing time of all the processing equipment is represented, and L represents the variance of the processing time of each processing equipment, namely the optimization target III.
Secondly, after a process path mathematical model is established, determining the manufacturing resource constraints of the basic component process and the processing workshop in the model, wherein the specific constraint conditions are expressed as follows and need to be considered in all respects:
① only one process can be performed by the same equipment at the same time;
② different processes on the same part cannot be processed simultaneously;
③ only one device is selected for processing in the same process;
④ the process of the part actually processing is in the process set of the part;
and thirdly, improving the reinforcement learning algorithm to optimize the process path:
and (3) optimizing the process paths by adopting an improved Q learning algorithm and combining the processing technology of the basic components and the processing equipment of the manufacturing workshop, wherein each processing process path obtained in the optimization process needs to meet 4 constraint conditions in the second step, otherwise, the processing process path which is unqualified needs to be abandoned, and then the processing procedure sequence is rearranged and optimized. And obtaining the optimal processing process path of the part after the optimization, namely the processing procedure permutation and combination of the part, and processing equipment corresponding to each procedure. The optimization method comprises the following specific steps:
first, a set of process paths is divided into different state spaces: the method comprises the steps of randomly selecting an initial solution of a process path model meeting constraint conditions, wherein each model solution corresponds to a state, and executing an optimization action under the constraint conditions to obtain a next model solution corresponding to a next state. The optimization actions include changes in process content, adjustment of sequence between processes and implementation of the three types of the same process on different processing equipment. Introducing an evaluation function p, the evaluation function p being defined as: and under the current state, dividing the difference value between the objective function value and the minimum value of the objective function in each previous state and the difference value between the maximum value and the minimum value of the objective function corresponding to each previous state to obtain a quotient, and adding the corresponding quotients under the energy consumption, time and load balance of the three objective functions to obtain an evaluation function. Two explanations are made in the solving process:
(1) when the number of times of performing the action is 0 (i.e., the initial state), the evaluation function value is defined as 3;
(2) when the number of times of performing the action is 1, the quotient is defined as: in the second state, the difference between the objective function value and the objective function value in the initial state is obtained by dividing the objective function value in the initial state by the objective function value in the initial state.
And carrying out state division according to a state evaluation function: because the new process path obtained after each action is executed can obtain the value of the evaluation function, the process path set is divided into different states according to the difference of the evaluation function values. 0< p <1, divided into state zero; p is more than or equal to 1 and less than 2, and is divided into a state I; p is more than or equal to 2 and less than 3, and is divided into a state two; p is more than or equal to 3 and less than 4, and is divided into a state III; p is more than or equal to 4, and is divided into a fifth state;
secondly, obtaining the optimal solution of the process path, which comprises the following specific steps:
① initializing Q matrix and learning times;
②, selecting an initial state, namely an initial process path meeting the constraint condition, and acquiring an initial value of an optimization index, wherein the initial state is randomly established and is used as a starting point for searching and optimizing;
③ finding the next executable action under the constraint condition according to the initial state, and continuously circulating to reach the next state after executing the next executable action;
④ calculating the likelihood of each executable action for the next state;
⑤ selecting the most likely action to be performed, and reaching the next state;
⑥, the Q matrix is updated, and the next executable action is continuously searched until the Q matrix converges or the set learning times limit is reached, at this time, the corresponding process path in this state is the optimal process path.
Compared with the prior art, the invention has the advantages that: aiming at the problems of overlong processing time, higher energy consumption of basic component processing equipment, unbalanced equipment load and the like in the basic component processing process, the optimized scheduling method for the basic component processing process is provided. Furthermore, standby power consumption, which is easily negligible in power consumption calculation, is considered. Through the process sequence in the machining process and the optimized scheduling of the machining equipment corresponding to each part in the machining process, the utilization rate of the machining equipment is improved, the standby time of the equipment and the total machining time are reduced, the energy consumption of the equipment is reduced, the machining balance of each equipment is measured by the total time variance of the machining of the equipment in the optimization process, the resource idleness is reduced, the machining task is executed in a more balanced mode, and therefore the utilization rate of workshop manpower and material resources is improved.
Drawings
FIG. 1 is a design flow chart of an optimized scheduling method for basic component processing technology according to the present invention;
in fig. 2, the horizontal axis of the coordinate of the present invention represents the processing time period, and the vertical axis represents the processing equipment number.
Detailed Description
The invention is further described in detail by taking a basic component hydraulic valve body as an example in combination with the attached drawings.
As shown in fig. 1, the present invention is specifically implemented as follows:
firstly, establishing a mathematical model of a process path of a valve body of a hydraulic valve, wherein the model comprises the following steps:
① the hydraulic valve body is an important basic component, the processing technology route is that the blank oil duct shot blasting (shot blasting machine) — cleaning (inter-sequence cleaning machine) — milling the bottom surface of the blank (milling machine) — drilling the screw hole of the valve body and the screw pit (vertical processing center) — processing the two ends of the main hole of the valve body and the top surface (horizontal processing center) — cleaning (inter-sequence cleaning machine) — processing the sealing pit (vertical processing center) — cleaning (cleaning production line) — spraying plastics (spraying plastics line) ", the equipment applied in the process is the shot blasting machine, the inter-sequence cleaning machine, the vertical processing center, the horizontal processing center, the cleaning production line and the spraying plastics line, the energy consumption of the processing equipment is equal to the sum of the work energy consumption and the standby energy consumption, the energy consumption:
Ei＝Ei worker+EWait for
EI worker＝PI worker×tI worker
EWait for＝PWait for×tWait for
Wherein E isiDescribing the total energy consumption of the processing equipment, i is 1,2, …, n represents the number of equipment, EI workerDescription of the energy consumption of the processing apparatus i during processing, EWait forDescribing the energy consumption, P, generated by the processing apparatus i during standbyI workerDescription of the processing Power, t, of the apparatus iI workerDescription of the duration of processing of the apparatus i, PWait forStandby power, t, of the description deviceWait forThe standby time period of the device i is described.
The total energy consumption of the basic component processing workshop equipment is the sum of the energy consumptions of all the processing equipment in the basic component processing workshop:
wherein E isGeneral assemblyThe total energy consumption of all the processing equipment, i.e. optimization goal one, is described. The processing energy consumption of main processing equipment of the hydraulic valve is as follows:
② the standby time of the basic component processing equipment is calculated by subtracting the sum of the processing start time and the processing time of the hydraulic valve processing equipment in the processing process from the processing finish time of the basic component processing equipment, and the time model is as follows:
ti Standby＝ti completion-tI worker-ti start with
Wherein, ti start withIndicates the starting time, t, of the machining of the part on the machine ii completionIndicating the end time, t, of the machining of the part on the machine ii StandbyStandby duration of the apparatus i during the machining of the parts, tI workerWhich represents the time that the device i is operating normally, i.e., the length of time that the part is being machined. ma isx{ti completionAnd f, the total processing completion time is the optimization objective II. The processing time of main equipment in the processing of two main types of hydraulic valves 4WE6 is as follows:
wherein, OjJ is 1,2,3, …,9 denotes a process set.
③ the hydraulic valve processing equipment load balance is measured by the variance of the processing time of each processing equipment in the workshop (the smaller the variance of the processing time, the higher the load balance), the load balance model is:
wherein,and the average value of the processing time of all the processing equipment is represented, and L represents the variance of the processing time of each processing equipment, namely the optimization target III.
Secondly, after a process path mathematical model is established, determining the manufacturing resource constraints of the basic component process and the processing workshop in the model, wherein the specific constraint conditions are expressed as follows and need to be considered in all respects:
① only one process can be performed by the same equipment at the same time;
② different processes on the same part cannot be processed simultaneously;
③ only one device is selected for processing in the same process;
④ the process of the part actually processing is in the process set of the part;
thirdly, improving the reinforcement learning algorithm to optimize the process path and optimize the process path;
and (3) optimizing the process paths by adopting an improved Q learning algorithm and combining the processing technology of the basic components and the processing equipment of the manufacturing workshop, wherein each processing process path obtained in the optimization process needs to meet 4 constraint conditions in the second step, otherwise, the processing process path which is unqualified needs to be abandoned, and then the processing procedure sequence is rearranged and optimized. And obtaining the optimal processing process path of the part after the optimization, namely the processing procedure permutation and combination of the part, and processing equipment corresponding to each procedure. The optimization steps are as follows:
first, a set of process paths is divided into different state spaces: the method comprises the steps of randomly selecting an initial solution of a process path model meeting constraint conditions, wherein each model solution corresponds to a state, and executing an optimization action under the constraint conditions to obtain a next model solution corresponding to a next state. The optimization actions include changes in process content, adjustment of sequence between processes and implementation of the three types of the same process on different processing equipment. Introducing an evaluation function p, the evaluation function p being defined as: and under the current state, dividing the difference value between the objective function value and the minimum value of the objective function in each previous state and the difference value between the maximum value and the minimum value of the objective function corresponding to each previous state to obtain a quotient, and adding the corresponding quotients under the energy consumption, time and load balance of the three objective functions to obtain an evaluation function. The solving process has two explanations:
(1) when the number of times of performing the action is 0 (i.e., an initial state), the evaluation function is defined as 3;
(2) when the number of times of performing the action is 1, the quotient is defined as: in the second state, the difference between the objective function value and the objective function value in the initial state is obtained by dividing the objective function value in the initial state by the objective function value in the initial state.
And carrying out state division according to a state evaluation function: since a new process path is available after each action is performed, the new process path corresponds to a new evaluation function value. And carrying out different state space division on the process path set according to different values of the evaluation function. 0< p <1, divided into state zero; p is more than or equal to 1 and less than 2, and is divided into a state I; p is more than or equal to 2 and less than 3, and is divided into a state two; p is more than or equal to 3 and less than 4, and is divided into a state III; p is more than or equal to 4, and is divided into a fifth state;
secondly, obtaining an optimal solution:
① initializing Q matrix and learning times;
②, selecting an initial state, namely an initial process path of hydraulic valve processing meeting constraint conditions, and acquiring initial values of energy consumption, time and load balance of optimization indexes;
③ finding the next executable action under the constraint condition according to the initial state, and continuously circulating to reach the next state after executing the next executable action;
④ calculating the likelihood of each executable action for the next state;
⑤ selecting the most likely action to be performed, and reaching the next state;
⑥, the Q matrix is updated, and the next executable action is continuously searched until the Q matrix converges or the set learning times limit is reached, at this time, the corresponding process path in this state is the optimal process path.
Taking the workshop process hydraulic valves 4WE6 and 4WE10 as an example, the optimized process path corresponds to fig. 2, namely, the process path gantt chart is obtained. In fig. 2, the horizontal axis of the coordinate represents the processing time period, and the vertical axis represents the processing equipment number. Compared with the process path not optimized in a factory, the total production time of the optimized process path is reduced by 5min and 4.7%, the energy consumption of equipment is reduced by 709 w.h and 3.1%, and the load balance of the equipment is improved by 12.5min2The improvement is 6.2%.
Those skilled in the art will appreciate that the invention may be practiced without these specific details.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (2)
1. An optimized scheduling method for a basic component processing technology comprises the following implementation steps:
firstly, establishing a basic component process path mathematical model, wherein the mathematical model comprises an energy consumption model, a time model and a load balancing model;
①, the energy consumption model is calculated as that the energy consumption of the basic component processing equipment is equal to the sum of the working energy consumption and the standby energy consumption, and the energy consumption model is as follows:
Ei＝Ei worker+EWait for
EI worker＝PI worker×tI worker
EWait for＝PWait for×tWait for
Wherein E isiDescribing the total energy consumption of the processing equipment, i is 1,2, …, n represents the number of equipment, EI workerDescription of the energy consumption of the processing apparatus i during processing, EWait forDescribing the energy consumption, P, generated by the processing apparatus i during standbyI workerDescription of the processing Power, t, of the apparatus iI workerDescription of the duration of processing of the apparatus i, PWait forStandby power, t, of the description deviceWait forDescribing the standby duration of the device i;
the total energy consumption of the basic component processing workshop equipment is the sum of the energy consumptions of all the processing equipment in the basic component processing workshop:
wherein E isGeneral assemblyDescribing the total energy consumption of all processing equipment, namely optimizing an objective one;
②, the time model is calculated by subtracting the sum of the processing start time and the processing time of the basic component processing equipment in the processing process from the processing finish time of the basic component processing equipment, and the time model is:
ti Standby＝ti completion-tI worker-ti start with
Wherein, ti start withIndicates the starting time, t, of the machining of the part on the machine ii completionIndicating the end time, t, of the machining of the part on the machine ii StandbyStandby time of device i during processing of parts, tI workerIndicating the time during which the device i is operating normally, i.e. the length of time for which the part is machined, max ti completionThe total processing completion time is the optimization objective II;
③, the load balance model is calculated by the load balance of the basic component processing equipment calculated by the variance of the processing time of each processing equipment in the workshop, and the load balance model is:
wherein,the average value of the processing time of all the processing equipment is represented, and L represents the variance of the processing time of each processing equipment, namely the optimization target III;
secondly, after a process path mathematical model is established, determining manufacturing resource constraints of a basic component process and a processing workshop in the mathematical model, wherein the specific constraint conditions are expressed as follows, and the following 4 constraint conditions are all required to be met:
① only one process can be performed by the same equipment at the same time;
② different processes on the same part cannot be processed simultaneously;
③ only one device is selected for processing in the same process;
④ the process of the part actually processing is in the process set of the part;
thirdly, improving the reinforcement learning algorithm to optimize the process path and optimize the process path;
and (3) optimizing the process paths by adopting an improved Q learning algorithm and combining the processing technology of the basic components and the processing equipment of the manufacturing workshop, wherein each processing process path obtained in the optimization process needs to meet 4 constraint conditions in the second step, otherwise, the processing process path which is unqualified needs to be abandoned, and then the processing procedure sequence is rearranged and optimized. And obtaining the optimal processing process path of the part after the optimization, namely the processing procedure permutation and combination of the part, and processing equipment corresponding to each procedure.
2. The optimized scheduling method for the basic component processing technology according to claim 1, wherein the optimized scheduling method comprises the following steps: the method improves the reinforcement learning algorithm to optimize the process path, and comprises the following specific steps:
(1) first, a set of process paths is divided into different state spaces: the method comprises the steps of randomly selecting an initial solution of a process path model meeting constraint conditions, wherein each model solution corresponds to a state, and executing an optimization action under the constraint conditions to obtain a next model solution corresponding to a next state. The optimization actions include changes in process content, adjustment of sequence between processes and implementation of the three types of the same process on different processing equipment. Introducing an evaluation function p, the evaluation function p being defined as: and under the current state, dividing the difference value between the objective function value and the minimum value of the objective function in each previous state and the difference value between the maximum value and the minimum value of the objective function corresponding to each previous state to obtain a quotient, and adding the corresponding quotients under the energy consumption, time and load balance of the three objective functions to obtain an evaluation function. The solving process has two explanations:
(a) when the number of times of executing the action is 0, namely the initial state, the evaluation function value is defined as 3;
(b) when the number of times of performing the action is 1, the quotient is defined as: in the second state, the difference value between the target function value and the target function value in the initial state is obtained by dividing the difference value by the target function value in the initial state;
(2) and (3) dividing the state space according to an evaluation function: obtaining the value of an evaluation function after executing each action, dividing different states into the same according to different evaluation function values, wherein the state is 0< p <1, and the state is zero; p is more than or equal to 1 and less than 2, and is divided into a state I; p is more than or equal to 2 and less than 3, and is divided into a state two; p is more than or equal to 3 and less than 4, and is divided into a state III; p is more than or equal to 4, and is divided into a fifth state;
(3) obtaining an optimal solution of a process path, which comprises the following specific steps:
① initializing Q matrix and setting learning times;
② selecting an initial state, namely an initial process path meeting the constraint condition, obtaining the initial value of the optimization index, and randomly establishing the initial state as the starting point of searching and optimizing;
③ finding the next executable action under the constraint condition according to the initial state, and continuously circulating to reach the next state after executing the next executable action;
④ calculating the likelihood of each executable action for the next state;
⑤ selecting the most likely action to be performed, and reaching the next state;
⑥, the Q matrix is updated, and the next executable action is continuously searched until the Q matrix converges or the set learning times limit is reached, at this time, the corresponding process path in this state is the optimal process path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811317035.2A CN109445282A (en) | 2018-11-07 | 2018-11-07 | A kind of Optimization Scheduling towards basic device processing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811317035.2A CN109445282A (en) | 2018-11-07 | 2018-11-07 | A kind of Optimization Scheduling towards basic device processing technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109445282A true CN109445282A (en) | 2019-03-08 |
Family
ID=65551279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811317035.2A Pending CN109445282A (en) | 2018-11-07 | 2018-11-07 | A kind of Optimization Scheduling towards basic device processing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109445282A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989535A (en) * | 2019-12-20 | 2020-04-10 | 华南理工大学 | Dynamic production plan adjusting method for coping with change of processing sequence |
| CN111679637A (en) * | 2020-05-29 | 2020-09-18 | 浙江财经大学 | Flexible multi-task scheduling method in manufacturing system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226467A (en) * | 2013-05-23 | 2013-07-31 | 中国人民解放军国防科学技术大学 | Data parallel processing method and system as well as load balancing scheduler |
| CN103390195A (en) * | 2013-05-28 | 2013-11-13 | 重庆大学 | Machine workshop task scheduling energy-saving optimization system based on reinforcement learning |
| CN104009499A (en) * | 2014-06-13 | 2014-08-27 | 东南大学 | Dispatching method for overcoming current unbalance of wind power grid-connected system |
| CN104808636A (en) * | 2015-04-28 | 2015-07-29 | 广东工业大学 | Flexible flow shop energy consumption optimization scheduling method |
| CN104881325A (en) * | 2015-05-05 | 2015-09-02 | 中国联合网络通信集团有限公司 | Resource scheduling method and resource scheduling system |
| CN106020142A (en) * | 2016-05-16 | 2016-10-12 | 佛山市南海区广工大数控装备协同创新研究院 | Flexible job shop scheduling method considering energy consumption cost and weighted tardiness cost |
| CN106959675A (en) * | 2017-03-21 | 2017-07-18 | 山东大学 | A kind of multi-objective scheduling optimization method towards Flow Shop |
-
2018
- 2018-11-07 CN CN201811317035.2A patent/CN109445282A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226467A (en) * | 2013-05-23 | 2013-07-31 | 中国人民解放军国防科学技术大学 | Data parallel processing method and system as well as load balancing scheduler |
| CN103390195A (en) * | 2013-05-28 | 2013-11-13 | 重庆大学 | Machine workshop task scheduling energy-saving optimization system based on reinforcement learning |
| CN104009499A (en) * | 2014-06-13 | 2014-08-27 | 东南大学 | Dispatching method for overcoming current unbalance of wind power grid-connected system |
| CN104808636A (en) * | 2015-04-28 | 2015-07-29 | 广东工业大学 | Flexible flow shop energy consumption optimization scheduling method |
| CN104881325A (en) * | 2015-05-05 | 2015-09-02 | 中国联合网络通信集团有限公司 | Resource scheduling method and resource scheduling system |
| CN106020142A (en) * | 2016-05-16 | 2016-10-12 | 佛山市南海区广工大数控装备协同创新研究院 | Flexible job shop scheduling method considering energy consumption cost and weighted tardiness cost |
| CN106959675A (en) * | 2017-03-21 | 2017-07-18 | 山东大学 | A kind of multi-objective scheduling optimization method towards Flow Shop |
Non-Patent Citations (8)
| Title |
|---|
| MENG ZHANG 等: "Equipment Energy Consumption Management in Digital Twin Shop-floorA Framework and Potential Applications", 《IEEE》 * |
| YONGPING ZHANG 等: "Consensus aware manufacturing service collaboration optimization under blockchain based Industrial Internet platform", 《COMPUTERS & INDUSTRIAL ENGINEERING》 * |
| 何彦 等: "一种面向机械车间柔性工艺路线的加工任务节能调度方法", 《机械工程学报》 * |
| 刘波: "一种基于强化学习的机械车间任务调度节能优化支持系统研究", 《CNKI》 * |
| 向峰 等: "面向服务水平等级协议的制造服务能效评估", 《中国机械工程》 * |
| 李聪波 等: "面向能耗的多工艺路线柔性作业车间分批优化调度模型", 《机械工程学报》 * |
| 王国磊 等: "基于模糊聚类的Q学习在动态调度中的应用", 《计算机集成制造系统》 * |
| 王颖 等: "基于一种新的评价指标的可重入生产系统调度", 《系统工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989535A (en) * | 2019-12-20 | 2020-04-10 | 华南理工大学 | Dynamic production plan adjusting method for coping with change of processing sequence |
| CN111679637A (en) * | 2020-05-29 | 2020-09-18 | 浙江财经大学 | Flexible multi-task scheduling method in manufacturing system |
| CN111679637B (en) * | 2020-05-29 | 2021-10-08 | 浙江财经大学 | Flexible multi-task scheduling method in manufacturing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103809506B (en) | The method of part processing optimal scheduling scheme is obtained based on a dimension particle cluster algorithm | |
| Wu et al. | The flexible job-shop scheduling problem considering deterioration effect and energy consumption simultaneously | |
| CN103390195B (en) | A kind of machine shop task scheduling energy saving optimizing system based on intensified learning | |
| WO2020007016A1 (en) | Dynamic linkage control method for automatic production process of intelligent workshop based on digital twin | |
| Wang et al. | Production logistics simulation and optimization of industrial enterprise based on Flexsim | |
| WO2016101624A1 (en) | Machining workshop workpiece energy consumption quota formulation method | |
| CN109445282A (en) | A kind of Optimization Scheduling towards basic device processing technology | |
| CN102059635A (en) | Typical part optimized grinding process integrated numerically controlled grinding system | |
| CN106898572A (en) | Material dispatch method and system based on equipment real-time status | |
| CN107817771B (en) | Consider the modeling method of the hybrid flowshop energy-saving distribution of cycle power strategy | |
| CN105160442B (en) | A kind of physics Nesting Algorithms for circular piece | |
| CN104808629A (en) | Flexible robot manufacturing unit scheduling method | |
| CN112381273A (en) | Multi-target job shop energy-saving optimization method based on U-NSGA-III algorithm | |
| CN116466659A (en) | Distributed assembly flow shop scheduling method based on deep reinforcement learning | |
| Cuixia et al. | Optimization control method for carbon footprint of machining process | |
| CN110580019B (en) | Edge calculation-oriented equipment calling method and device | |
| CN104503381B (en) | A kind of Optimization Scheduling of the production assembling process of mobile phone | |
| CN103020763A (en) | Operation workshop scheduling key outside cooperation process identification method based on relation chains | |
| Feng et al. | Minimizing the energy consumption of hole machining integrating the optimization of tool path and cutting parameters on CNC machines | |
| CN104537425B (en) | A kind of Optimization Scheduling of the production assembling process of vehicle air conditioning outlet | |
| CN104392130A (en) | Method for determining multi-axis fatigue most damage load direction and application thereof | |
| CN116512250A (en) | Disassembling line balancing method based on man-machine cooperation | |
| Safarov et al. | Energy planning in production shops with numerically controlled machine tools | |
| CN112418478B (en) | Low-carbon scheduling model under flexible flow shop and energy-saving optimization method | |
| CN108873850A (en) | A kind of Optimization Scheduling of automation of machinery manufacture production process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190308 |