CN114002948A - Method and device for accessing third-party numerical control machine tool to service platform - Google Patents
Method and device for accessing third-party numerical control machine tool to service platform Download PDFInfo
- Publication number
- CN114002948A CN114002948A CN202111187395.7A CN202111187395A CN114002948A CN 114002948 A CN114002948 A CN 114002948A CN 202111187395 A CN202111187395 A CN 202111187395A CN 114002948 A CN114002948 A CN 114002948A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- machine tool
- current
- output
- trust domain
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000006870 function Effects 0.000 claims abstract description 30
- 238000005457 optimization Methods 0.000 claims abstract description 29
- 230000002787 reinforcement Effects 0.000 claims abstract description 19
- 238000010367 cloning Methods 0.000 claims abstract description 7
- 238000004519 manufacturing process Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 9
- 238000009795 derivation Methods 0.000 claims description 3
- 238000003754 machining Methods 0.000 claims 1
- 238000004891 communication Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
Images
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
- G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
- G05B13/024—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a method and a device for accessing a third-party numerical control machine tool to a service platform, wherein the method comprises the steps of acquiring historical data, and determining input, output and reward functions of an algorithm based on the historical data; bringing the input, output and reward functions of the algorithm into the trust domain strategy optimization algorithm for reinforcement learning, and updating strategy parameters of the trust domain strategy optimization algorithm; adopting self-behavior cloning to accelerate convergence of reinforcement learning, obtaining updated strategy parameters, and updating a trust domain strategy optimization algorithm based on the updated strategy parameters; obtaining current data of operation of the numerical control machine tool, determining current input of an algorithm based on the current data, and substituting the current input of the algorithm into an updated trust domain strategy optimization algorithm to obtain current output of the algorithm; acquiring data operated in the current time period according to the current output of the algorithm, and uploading the data to a service platform; the invention can effectively solve the technical problem of high data communication cost of the third-party numerical control machine tool and the service platform.
Description
Technical Field
The invention relates to a method and a device for accessing a third-party numerical control machine tool to a service platform, and belongs to the technical field of intelligent manufacturing.
Background
The intelligent production line is an automatic production line integrating the technologies of automatic control, computer, big data and the like, and is the core of an intelligent factory. A key sharing service platform of an intelligent production line for medium and small enterprises is established, and a key technology sharing system with centralized resources, high utilization rate and smooth collaborative sharing can be formed. However, the intelligent production lines required by enterprises in different fields are different, and the cost for establishing a key shared service platform of a full-functional intelligent production line across industries from scratch is immeasurable. Therefore, how to dynamically access the existing intelligent production line to the key sharing service platform of the intelligent production line is a key technology in the research and development of the key technology sharing service platform for the intelligent production line of medium and small enterprises. The shared service platform needs to communicate with tens of thousands or even hundreds of thousands of third-party numerical control machines, read the running state of the third-party numerical control machines and issue running instructions. Enterprises in different fields have different sensor types, technical standards and process data. The platform reads the data of all the sensors on the production line in real time and indiscriminately, and carries out remote control according to the data, which brings great pressure to communication and needs to call a large amount of computing resources of the platform. The method not only influences the use experience of users, increases the daily operation and maintenance cost of the service platform, but also does not meet the national requirement of reducing carbon emission.
In order to solve the above problems, the present application provides a method and an apparatus for accessing a third party numerical control machine to a service platform.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a method and a device for accessing a third-party numerical control machine tool to a service platform, and solves the technical problem of high data communication cost of the third-party numerical control machine tool and the service platform.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the present invention provides a method for accessing a third-party numerical control machine to a service platform, including:
acquiring historical data of the operation of a sensor of the numerical control machine tool, and determining input, output and reward functions of an algorithm based on the historical data;
bringing the input, output and reward functions of the algorithm into the trust domain strategy optimization algorithm for reinforcement learning, and updating strategy parameters of the trust domain strategy optimization algorithm;
accelerating convergence of the trust domain strategy optimization algorithm by adopting self-behavior cloning, acquiring updated strategy parameters, and updating the trust domain strategy optimization algorithm based on the updated strategy parameters;
obtaining current data of operation of the numerical control machine tool, determining current input of an algorithm based on the current data, and substituting the current input of the algorithm into an updated trust domain strategy optimization algorithm to obtain current output of the algorithm;
and acquiring the data of the numerical control machine tool sensor in the current time period according to the current output of the algorithm, and uploading the data to the service platform.
Optionally, the input is sensor information acquired in a previous time period, and the output is a sensor number and an acquisition frequency corresponding to the sensor information acquired in the current time period.
Optionally, the reward function is:
R＝α1EE+α2JD
wherein R is a reward function, EE is an energy efficiency ratio of a processing state, and JDFor order production progress, α1，α2Is a hyper-parameter.
Optionally, the obtaining of the energy efficiency ratio EE of the processing state includes:
acquiring the time period T and the sum of the processing, standby, shutdown and fault states of the machine tool, and respectively recording the time periods T as T1、T2、T3、T4；
Computing energy efficiency E of each staten：
Calculating the energy efficiency ratio EE of the processing state:
wherein ,tB-tARepresenting the t time periodThe length of time.
Optionally, the order production schedule JDComprises the following steps:
wherein D represents an order, PnThe process for order D is denoted as D ═ P1、P2、…Pn…、PNN is the total number of the working procedures,
is a process PnThe production schedule.
Optionally, the policy parameters for updating the trust domain policy optimization algorithm are as follows:
wherein ,
theta is the current strategy parameter, alpha is the learning rate,
partial derivation of theta for J (theta), ES,AFor the expectation in case the input is S output A,. pi.is the current strategy, S and A are the input and output, respectively, of the algorithm for reinforcement learning, Qπ(S, A) is an action value function, and the expression is as follows:
Qπ(S,A)＝ES,A[R1+γR2+γ2R3+...+γt-1Rt|S,A]
where γ is a discount factor, RtA reward function for a period of t.
Optionally, the accelerating convergence of the trust domain policy optimization algorithm by using self-behavior cloning includes:
determining a loss function:
where n is the number of inputs and outputs of the algorithm for reinforcement learning,
representing the actual output of the algorithm, atT is the time period for the output of the algorithm for reinforcement learning;
and adding supervised learning in reinforcement learning based on a loss function so as to accelerate convergence of the trust domain strategy optimization algorithm.
In a second aspect, the invention provides a device for accessing a third-party numerical control machine tool to a service platform, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate according to the instructions to perform the steps of any of the above methods.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a method and a device for accessing a third-party numerical control machine tool to a service platform, wherein an algorithm is obtained by updating a trust domain strategy optimization algorithm in a reinforcement learning mode; the data acquisition frequency and the information acquisition quantity of the sensor are adaptively adjusted through the updated trust domain strategy optimization algorithm, so that the requirements on the communication speed and the platform computing resources are reduced, and the platform operation efficiency is improved. In addition, the invention provides self-behavior cloning, and supervised training strategies are provided by using some input-output pairs which are rewarded more than others in the exploration process as training data, so that the convergence of the strategies is accelerated, and the reinforcement learning training cost is reduced.
Drawings
Fig. 1 is a flowchart of a method for accessing a third-party numerical control machine to a service platform according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
as shown in fig. 1, an embodiment of the present invention provides a method for accessing a third-party numerical control machine to a service platform, including the following steps:
step 1, obtaining historical data of operation of a sensor of the numerical control machine tool, and determining input, output and reward functions of an algorithm based on the historical data;
inputting sensor information acquired in the previous time period;
outputting a sensor number and a collection frequency corresponding to the information of the collected sensor in the current time period;
the reward function is:
R＝α1EE+α2JD
wherein R is a reward function, EE is an energy efficiency ratio of a processing state, and JDFor order production progress, α1，α2Is a hyper-parameter.
Specifically, the method comprises the following steps:
the obtaining of the energy efficiency ratio EE of the processing state includes:
acquiring the time period T and the sum of the processing, standby, shutdown and fault states of the machine tool, and respectively recording the time periods T as T1、T2、T3、T4；
Computing energy efficiency E of each staten：
Calculating the energy efficiency ratio EE of the processing state:
wherein ,tB-tAIndicating the duration of the t period.
Order production schedule JDComprises the following steps:
wherein D represents an order, PnThe process for order D is denoted as D ═ P1、P2、…Pn…、PNN is the total number of the working procedures,
is a process PnThe production schedule.
Step 2, bringing the input and output of the algorithm and the reward function into a trust domain strategy optimization algorithm for reinforcement learning, and updating strategy parameters of the trust domain strategy optimization algorithm;
the strategy parameters for updating the trust domain strategy optimization algorithm are as follows:
wherein ,
theta is the current strategy parameter, alpha is the learning rate,
partial derivation of theta for J (theta), ES,AFor the expectation in case the input is S output A,. pi.is the current strategy, S and A are the input and output, respectively, of the algorithm for reinforcement learning, Qπ(S, A) is an action valueThe function, its expression is as follows:
Qπ(S,A)＝ES,A[R1+γR2+γ2R3+...+γt-1Rt|S,A]
where γ is a discount factor (typically set to 0.99), RtA reward function for a period of t.
Step 3, adopting self-behavior cloning to accelerate convergence of the trust domain strategy optimization algorithm, obtaining updated strategy parameters, and updating the trust domain strategy optimization algorithm based on the updated strategy parameters;
determining a loss function:
where n is the number of inputs and outputs of the algorithm for reinforcement learning,
representing the actual output of the algorithm, atT is the time period for the output of the algorithm for reinforcement learning;
and adding supervised learning in reinforcement learning based on a loss function so as to accelerate convergence of the trust domain strategy optimization algorithm.
Step 4, obtaining current data of the operation of the numerical control machine tool, determining the current input of the algorithm based on the current data, and substituting the current input of the algorithm into the updated trust domain strategy optimization algorithm to obtain the current output of the algorithm;
and 5, acquiring data of the numerical control machine tool sensor in the current time period according to the current output of the algorithm, and uploading the data to a service platform.
Example two:
the embodiment of the invention provides a device for accessing a third-party numerical control machine tool to a service platform, which comprises a processor and a storage medium, wherein the processor is used for processing a plurality of data files;
a storage medium to store instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of any of the methods described above.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (8)
1. A method for accessing a third-party numerical control machine tool to a service platform is characterized by comprising the following steps:
acquiring historical data of the operation of a sensor of the numerical control machine tool, and determining input, output and reward functions of an algorithm based on the historical data;
bringing the input, output and reward functions of the algorithm into the trust domain strategy optimization algorithm for reinforcement learning, and updating strategy parameters of the trust domain strategy optimization algorithm;
accelerating convergence of the trust domain strategy optimization algorithm by adopting self-behavior cloning, acquiring updated strategy parameters, and updating the trust domain strategy optimization algorithm based on the updated strategy parameters;
obtaining current data of operation of the numerical control machine tool, determining current input of an algorithm based on the current data, and substituting the current input of the algorithm into an updated trust domain strategy optimization algorithm to obtain current output of the algorithm;
and acquiring the data of the numerical control machine tool sensor in the current time period according to the current output of the algorithm, and uploading the data to the service platform.
2. The method according to claim 1, wherein the input is sensor information acquired in a previous time period, and the output is a sensor number and an acquisition frequency corresponding to the sensor information acquired in a current time period.
3. The method of claim 1, wherein the reward function is:
R＝α1EE+α2JD
wherein R is a reward function, EE is an energy efficiency ratio of a processing state, and JDFor order production progress, α1，α2Is a hyper-parameter.
4. The method for accessing the third party numerically controlled machine tool to the service platform according to claim 3, wherein the obtaining of the energy efficiency ratio EE of the machining state comprises:
acquiring the time period T and the sum of the processing, standby, shutdown and fault states of the machine tool, and respectively recording the time periods T as T1、T2、T3、T4；
Computing energy efficiency E of each staten：
Calculating the energy efficiency ratio EE of the processing state:
wherein ,tB-tAIndicating the duration of the t period.
5. The method for accessing the third party NC machine tool to the service platform according to claim 3, wherein the order production progress JDComprises the following steps:
wherein D represents an order, PnThe process for order D is denoted as D ═ P1、P2、...Pn...、PNN is the total number of the working procedures,
is a process PnThe production schedule.
6. The method according to claim 1, wherein the policy parameters for updating the trust domain policy optimization algorithm are:
wherein ,
theta is the current strategy parameter, alpha is the learning rate,
partial derivation of theta for J (theta), ES，AFor the expectation in case the input is S output A,. pi.is the current strategy, S and A are the input and output, respectively, of the algorithm for reinforcement learning, Qπ(S, A) is an action value function, and the expression is as follows:
Qπ(S，A)＝ES，A[R1+γR2+γ2R3+...+γt-1Rt|S，A]
where γ is a discount factor, RtA reward function for a period of t.
7. The method of claim 1, wherein the accelerating convergence of the trust domain policy optimization algorithm by self-behavioral cloning comprises:
determining a loss function:
where n is the number of inputs and outputs of the algorithm for reinforcement learning,
representing the actual output of the algorithm, atT is the time period for the output of the algorithm for reinforcement learning;
and adding supervised learning in reinforcement learning based on a loss function so as to accelerate convergence of the trust domain strategy optimization algorithm.
8. A device for accessing a third-party numerical control machine tool to a service platform comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111187395.7A CN114002948B (en) | 2021-10-12 | 2021-10-12 | Method and device for accessing third-party numerical control machine tool to service platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111187395.7A CN114002948B (en) | 2021-10-12 | 2021-10-12 | Method and device for accessing third-party numerical control machine tool to service platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114002948A true CN114002948A (en) | 2022-02-01 |
| CN114002948B CN114002948B (en) | 2023-09-26 |
Family
ID=79922688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111187395.7A Active CN114002948B (en) | 2021-10-12 | 2021-10-12 | Method and device for accessing third-party numerical control machine tool to service platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114002948B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4405660A1 (en) * | 1994-02-22 | 1995-08-24 | Wagner Maschf Gustav | Computer-controlled operation of machine tool with adaptive regulation |
| KR20120002033A (en) * | 2010-06-30 | 2012-01-05 | 전자부품연구원 | Auto tuning system and method of operating parameter for robot |
| CN102566503A (en) * | 2012-01-17 | 2012-07-11 | 江苏高精机电装备有限公司 | Remote monitoring and fault diagnosis system for numerical control machine tool |
| CN102736561A (en) * | 2012-07-10 | 2012-10-17 | 北京信息科技大学 | Electromechanical equipment-oriented remote dynamic adaptive rule acquisition method |
| CN105588251A (en) * | 2014-10-20 | 2016-05-18 | 株式会社理光 | Method and device for controlling air-conditioning system |
| CN108196514A (en) * | 2018-03-29 | 2018-06-22 | 武汉理工大学 | A kind of numerically-controlled machine tool operating status long-distance monitoring method |
| WO2018182745A1 (en) * | 2017-03-31 | 2018-10-04 | Intel IP Corporation | Techniques for channel state determination |
| CN108646694A (en) * | 2018-07-12 | 2018-10-12 | 大族激光科技产业集团股份有限公司 | Intelligent management, device, system and the computer equipment of numerically-controlled machine tool |
| US20190025794A1 (en) * | 2017-07-21 | 2019-01-24 | Fanuc Corporation | Machine learning device, numerical control device, numerical control system, and machine learning method |
| CN111241952A (en) * | 2020-01-03 | 2020-06-05 | 广东工业大学 | Reinforced learning reward self-learning method in discrete manufacturing scene |
| US20210132580A1 (en) * | 2019-11-06 | 2021-05-06 | D.P. Technology Corp. | Systems and methods for virtual environment for reinforcement learning in manufacturing |
-
2021
- 2021-10-12 CN CN202111187395.7A patent/CN114002948B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4405660A1 (en) * | 1994-02-22 | 1995-08-24 | Wagner Maschf Gustav | Computer-controlled operation of machine tool with adaptive regulation |
| KR20120002033A (en) * | 2010-06-30 | 2012-01-05 | 전자부품연구원 | Auto tuning system and method of operating parameter for robot |
| CN102566503A (en) * | 2012-01-17 | 2012-07-11 | 江苏高精机电装备有限公司 | Remote monitoring and fault diagnosis system for numerical control machine tool |
| CN102736561A (en) * | 2012-07-10 | 2012-10-17 | 北京信息科技大学 | Electromechanical equipment-oriented remote dynamic adaptive rule acquisition method |
| CN105588251A (en) * | 2014-10-20 | 2016-05-18 | 株式会社理光 | Method and device for controlling air-conditioning system |
| WO2018182745A1 (en) * | 2017-03-31 | 2018-10-04 | Intel IP Corporation | Techniques for channel state determination |
| US20190025794A1 (en) * | 2017-07-21 | 2019-01-24 | Fanuc Corporation | Machine learning device, numerical control device, numerical control system, and machine learning method |
| CN108196514A (en) * | 2018-03-29 | 2018-06-22 | 武汉理工大学 | A kind of numerically-controlled machine tool operating status long-distance monitoring method |
| CN108646694A (en) * | 2018-07-12 | 2018-10-12 | 大族激光科技产业集团股份有限公司 | Intelligent management, device, system and the computer equipment of numerically-controlled machine tool |
| US20210132580A1 (en) * | 2019-11-06 | 2021-05-06 | D.P. Technology Corp. | Systems and methods for virtual environment for reinforcement learning in manufacturing |
| CN111241952A (en) * | 2020-01-03 | 2020-06-05 | 广东工业大学 | Reinforced learning reward self-learning method in discrete manufacturing scene |
Non-Patent Citations (5)
| Title |
|---|
| 冯金金;邓昌义;张健;: "基于工业互联网的数控机床数据采集平台应用研究", 制造技术与机床, no. 03 * |
| 杨能俊;郭宇;方伟光;黄少华;吴鹏兴;: "实时数据驱动的离散制造车间自适应调度方法", 组合机床与自动化加工技术, no. 09 * |
| 沈江;徐曼;王粟;: "多传感器自适应控制网络平台构建及其硬件设计", 制造技术与机床, no. 03 * |
| 王象磊;: "数控机床负载自适应加工控制系统设计分析", 内燃机与配件, no. 18 * |
| 韦文姬;何岭松;吴玉叶;: "智能数控机床加工状态监测EtherCAT从站设计", 装备制造技术, no. 06 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114002948B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105302096B (en) | Intelligent factory scheduling method | |
| US8078294B2 (en) | Conditional download of data from embedded historians | |
| CN111260181B (en) | Workshop self-adaptive production scheduling device based on distributed intelligent manufacturing unit | |
| CN114048857B (en) | Calculation force distribution method and device and calculation force server | |
| KR102229859B1 (en) | Operation management method, apparatus and system using machine learning and transfer learning | |
| CN101859135A (en) | Method and device for controlling distributed automation system | |
| Brodsky et al. | Analysis and optimization in smart manufacturing based on a reusable knowledge base for process performance models | |
| CN115098278B (en) | Digital twin workshop multi-scene interaction method based on microservice | |
| Hu et al. | Short-term hydropower generation scheduling using an improved cloud adaptive quantum-inspired binary social spider optimization algorithm | |
| CN110556823B (en) | Model dimension reduction based safety constraint unit combination rapid calculation method and system | |
| Parto et al. | Cyber-physical system implementation for manufacturing with analytics in the cloud layer | |
| CN114218866A (en) | Power distribution network real-time dynamic reconstruction method and device based on deep learning algorithm | |
| CN114002948A (en) | Method and device for accessing third-party numerical control machine tool to service platform | |
| CN107330608A (en) | A kind of production scheduling method based on Techniques of Neural Network | |
| CN114047729B (en) | Natural plant processing control method, system, computer device and storage medium | |
| CN114895623A (en) | Granular sludge process intelligent control system, method, computer equipment and storage medium | |
| CN110298538B (en) | Intelligent workshop combined scheduling control method | |
| CN110532597B (en) | Air compressor set adjusting and assembling system and method based on pressure track prediction and time nodes | |
| CN113610484A (en) | Intelligent manufacturing production execution system L-MES and manufacturing method thereof | |
| CN110647085A (en) | Parameter adjusting method and device | |
| CN113741815B (en) | Storage system management and control method, device and equipment and readable storage medium | |
| CN202230377U (en) | Control system for copper pipe production line | |
| CN116307593A (en) | Multi-task automatic distribution method and system based on artificial intelligence | |
| KR102530794B1 (en) | Data Pre-Processing System | |
| Fan et al. | An improved genetic algorithm for solving the RGV shop scheduling problem |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |