CN115933537A - Multi-level cognitive model of digit control machine tool - Google Patents
Multi-level cognitive model of digit control machine tool Download PDFInfo
- Publication number
- CN115933537A CN115933537A CN202211587839.0A CN202211587839A CN115933537A CN 115933537 A CN115933537 A CN 115933537A CN 202211587839 A CN202211587839 A CN 202211587839A CN 115933537 A CN115933537 A CN 115933537A
- Authority
- CN
- China
- Prior art keywords
- numerical control
- control machine
- machine tool
- cognitive
- layer
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention provides a multi-level cognitive model of a numerical control machine tool, which comprises an execution layer, a cognitive layer and a high-level cognitive layer; the cognitive layer comprises three functional layers, namely a perception layer, a storage layer and a processing layer, and the advanced cognitive layer comprises three functional layers, namely an analysis layer, a decision layer and a learning layer; and finally, the cognitive activities of the numerical control machine tool are divided into 7 layers, and the 7 layers form a cognitive analysis ring and a cognitive learning ring in the cognitive model. By means of the cognitive analysis ring, dynamic analysis in the manufacturing process of the manufacturing unit is supported, and dynamic sensing and dynamic response capabilities of the manufacturing unit are improved. Through the cognitive learning ring, the knowledge mining in the numerical control machine tool execution scheme is realized, the knowledge accumulation of the numerical control machine tool is realized, and the cognitive ability of the numerical control machine tool is supported to be continuously improved. The cognitive model of the numerical control machine tool can provide a more accurate and intelligent method for state monitoring, dynamic analysis, operation maintenance, optimization decision and knowledge accumulation of the numerical control machine tool.
Description
Technical Field
The invention relates to the technical field of equipment analysis and intellectualization, in particular to a multi-level cognitive model of a numerical control machine tool, which is a multi-level and multi-dimensional cognitive model of the numerical control machine tool.
Background
The numerical control machine tool is used as an industrial master machine and is the root of the manufacturing industry. The numerical control machine tool is used as basic equipment and a capability providing unit in the manufacturing industry, and the quality of the state of the numerical control machine tool not only affects the production efficiency of the numerical control machine tool, but also affects the processing quality and the production progress of the parts to be processed. With the falling to the ground and the implementation of the relevant policies such as intelligent manufacturing, industrial 4.0, chinese manufacturing 2025 and the like, the intelligence of production equipment, production processes and production systems is realized by combining with the new generation information communication technology, which is the current research trend. Therefore, how to combine with a new generation information communication technology to construct the cognitive ability of the numerical control machine tool and improve the intelligent level and the self-adaptive ability of the numerical control machine tool becomes a key problem of the current intelligent manufacturing.
At present, intelligent research aiming at numerical control machine tools becomes a research hotspot, for example, patent CN108107841a discloses a numerical control machine tool digital twin modeling method comprising a physical space, a digital twin digital space and a digital twin mapping model, mainly solving the problem of a multi-field object-oriented component-based machine tool digital model modeling method, and realizing data transmission, data analysis and intelligent service through the analysis capability of the digital twin model. For example, a document of "a method of NC machine tools organizing system in smart technologies" proposes a bidirectional integration framework of data and control flow, which realizes the state monitoring and data processing of the operation of the numerical control machine based on the acquired big data of the machining process and the extracted important information. However, the current research is mostly biased to modeling or single-aspect cognitive research, and a systematic cognitive model is lacked to guide the intelligent construction and the continuous improvement of the self-adaptive capacity of the numerical control machine tool.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a numerical control machine tool multi-level cognitive model, which comprises an execution layer, a cognitive layer and a high-level cognitive layer;
the execution layer comprises a numerical control machine tool, a workbench, a machine tool spindle, a cutter and various sensors, and realizes execution of manufacturing tasks and acquisition of manufacturing data;
the cognitive layer comprises a sensing layer, a storage layer and a processing layer, and the three functional layers are used for respectively realizing the functions of data sensing, data storage and data preprocessing in the manufacturing process of the numerical control machine;
the advanced cognitive layer comprises an analysis layer, a decision layer and a learning layer, and the functions of dynamic analysis, dynamic decision and knowledge learning in a decision scheme in the manufacturing process of the numerical control machine are respectively realized.
Furthermore, the sensing layer realizes data acquisition of the machining process through a numerical control system, various sensors and field executors, and realizes dynamic sensing of the numerical control machine; the data perceived by the perception layer includes, but is not limited to, the following types: bending moment, torque, current, power, vibration, acoustic emission, temperature and cutting.
Furthermore, the storage layer realizes caching and storage of big data in the manufacturing process and transmission butt joint with a cloud platform by using a computer at the edge end, and realizes data storage, data management and data security of the edge end in the manufacturing process of the numerical control machine tool; the storage layer comprises a state database and a knowledge base, the state data stores real-time and historical data acquired in the running process of the numerical control machine tool, and the knowledge base stores rules and knowledge data executed by the manufacturing unit.
Furthermore, the processing layer preprocesses data acquired in the manufacturing process of the numerical control machine tool so as to improve the data quality of large manufactured data and support high-level cognition of the numerical control machine tool; the processing layers include, but are not limited to, the following data processing functions: standardization, normalization, data noise reduction, data filtering and feature extraction.
Furthermore, the analysis layer simulates and analyzes the manufacturing process of the numerical control machine tool, so that the running states of the numerical control machine tool, the cutter and the clamp and the quality state of the machined part are obtained, and the high-efficiency production of quality and quantity guarantee is supported; the analysis method in the analysis layer comprises simulation analysis, mechanism analysis, data analysis and evolution analysis; the analysis layer realizes the cognitive functions of cutter abrasion, cutter residual life, part surface quality, clamping force and numerical control machine tool load.
Furthermore, the decision layer carries out dynamic decision aiming at problems existing in the manufacturing process so as to improve the self-adaptive capacity of the production system; the decision layer takes problems in the manufacturing process as trigger conditions and takes the cognitive result of the numerical control machine as a basis, so that the optimization of process parameters, the optimization of feed tracks, the optimization of loads and the optimization decision of cutters are realized, and the optimized production of the numerical control machine is realized.
Furthermore, the learning layer excavates knowledge in the decision scheme, and the intelligent level of the numerical control machine tool is continuously improved; the execution scheme and the optimization scheme of the numerical control machine tool comprise implicit knowledge, including expert experience and process knowledge, and mining of the implicit knowledge is realized through classification, induction, reasoning and deduction modes of a learning layer so as to support continuous improvement of execution efficiency and machining quality of the numerical control machine tool.
Furthermore, the multi-level cognitive model of the numerical control machine comprises a cognitive analysis ring and a cognitive learning ring, dynamic analysis in the manufacturing process of the numerical control machine and knowledge mining and accumulation in the manufacturing process of the numerical control machine are respectively realized, and the self-adaptive capacity and the intelligent level of the numerical control machine are improved.
Further, the cognitive analysis ring of the numerical control machine tool is as follows: performing-sensing-storing-processing-analyzing-deciding-performing; through the mutual cooperation among the six cognitive analysis processes, a cognitive analysis ring of the numerical control machine is constructed, the dynamic execution, the dynamic perception, the dynamic analysis and the dynamic decision in the manufacturing process of the numerical control machine are realized, and the self-adaptive capacity of the numerical control machine is improved.
Further, the cognitive learning ring of the numerical control machine tool is as follows: learning-analysis-decision-execution-learning; through the mutual cooperation of the four cognitive learning processes, the cognitive learning ring of the numerical control machine tool is constructed, knowledge mining in numerical control machine tool manufacturing tasks and schemes is realized, manufacturing knowledge such as optimized process parameters and tool optimization rules is obtained, and the intelligent level of the numerical control machine tool is continuously improved.
The multi-level cognitive model of the numerical control machine tool can be applied to intelligent lifting of the numerical control machine tool and intelligent lifting of a manufacturing system or a production system.
Advantageous effects
According to the cognitive model of the numerical control machine tool constructed by the invention, the cognitive activities of the numerical control machine tool are systematically divided into 7 layers, the cognitive activities of the numerical control machine tool are unified into one cognitive model, and the cognitive ability construction and continuous improvement of the numerical control machine tool can be effectively guided through introduction and description of the 7 layers. The dynamic analysis in the manufacturing process of the manufacturing unit is supported through the cognitive analysis ring in the cognitive model of the numerical control machine tool, and the dynamic sensing and dynamic response capability of the manufacturing unit is improved. Through the cognitive learning ring in the cognitive model of the numerical control machine tool, knowledge mining in the execution scheme of the numerical control machine tool is realized, and knowledge accumulation of the numerical control machine tool is realized, so that the cognitive ability of the numerical control machine tool is supported to be continuously improved. The cognitive model of the numerical control machine tool can provide a more accurate and intelligent method for state monitoring, dynamic analysis, operation maintenance, optimization decision and knowledge accumulation of the numerical control machine tool.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic diagram of a multi-level cognitive model of a NC machine tool;
FIG. 2 is a schematic diagram of a cognitive analysis loop of a multi-level cognitive model of a numerically controlled machine tool;
FIG. 3 is a schematic diagram of a cognitive learning loop of a multi-level cognitive model of a numerically controlled machine tool.
Detailed Description
The following detailed description of embodiments of the invention is intended to be illustrative, and not to be construed as limiting the invention.
As shown in fig. 1, the present embodiment provides a multi-level cognitive model of a numerical control machine tool, which supports the improvement of the adaptive capacity and the intelligence level of the numerical control machine tool.
The numerical control machine tool multi-level cognitive model comprises an execution layer, a cognitive layer and a high-grade cognitive layer.
The execution layer is mainly used for executing the numerical control machine tool and the auxiliary equipment of the normal production task.
The cognitive layer is mainly used for carrying out data primary processing on the cognitive process of the numerical control machine tool and comprises a perception layer, a storage layer and a processing layer. The sensing layer realizes the collection of state data, process data, sensing data and the like in the running process of the numerical control machine by using the numerical control machine and auxiliary equipment; the storage layer mainly realizes the storage and transmission of the acquired data by using a computing terminal of an edge end; the processing layer is mainly used for preprocessing the sensed data so as to reduce noise in the data and improve the quality of the data.
The advanced cognitive layer is mainly used for advanced cognitive activities in the running process of the numerical control machine tool and comprises an analysis layer, a decision layer and a learning layer, and dynamic analysis and optimization decision of the running process of the numerical control machine tool and knowledge mining in a processing scheme are respectively realized.
Through the three parts of 7 layers, intelligent services such as dynamic execution, dynamic perception, dynamic analysis, optimization decision, knowledge accumulation and the like of the numerical control machine tool are realized.
As shown in fig. 2, a cognitive analysis ring is formed in the multi-level cognitive model of the numerical control machine provided in this embodiment, and dynamic analysis and optimization decision of the numerical control machine during the manufacturing process are implemented through six layers, namely, an execution layer, a sensing layer, a storage layer, a processing layer, an analysis layer, and a decision layer, so that the adaptive level of the numerical control machine during the operation process is improved.
As shown in fig. 3, a cognitive learning loop is further formed in the multi-level cognitive model of the numerical control machine tool provided in this embodiment, and mining of implicit knowledge in the machining scheme of the numerical control machine tool is realized through four layers, namely a learning layer, an execution layer, an analysis layer and a decision layer, so that knowledge accumulation at an edge end is realized, and the intelligence level of the running process of the numerical control machine tool is improved.
As shown in fig. 1, the execution layer of the multi-level cognitive model of the numerical control machine in the embodiment is composed of a five-axis numerical control milling machine (siemens 840D numerical control system), a numerical control tool, a Spike cutting force acquisition terminal, a cutting fluid sensing terminal, a machine environment sensing terminal, and a numerical control machine information acquisition system, and supports normal processing production of the numerical control machine.
As shown in fig. 1, a sensing layer in a multi-level cognitive model of a numerical control machine tool realizes data acquisition in a manufacturing process through the numerical control machine tool and an auxiliary device. The numerical control machine tool acquisition system can acquire data such as spindle temperature, spindle current, spindle speed, feed rate multiplying power, X-axis current, Y-axis current, Z-axis current, B-axis current, C-axis current, X-axis machine tool coordinates, Y-axis machine tool coordinates, Z-axis machine tool coordinates, B-axis machine tool coordinates, C-axis machine tool coordinates and the like through an OPC UA protocol. Bending moment data of an X axis, a Y axis and a Z axis in the machining process of the numerical control machine tool, and torque, axial force and temperature data of a cutter in the machining process are acquired through a Spike cutting force acquisition terminal. And the temperature, the PH value, the conductivity and the dissolved oxygen rate data of the cutting fluid in the machining process of the numerical control machine tool are acquired through the cutting fluid sensing terminal. The dynamic perception of the numerical control machine tool is realized by acquiring data of vibration in the cabin, vibration outside the cabin, temperature in the cabin, lighting and humidity in the machining process of the machine tool through the machine tool environment perception terminal. The cutting fluid sensing terminal and the machine tool environment sensing terminal adopt a Modbus/RS485 transmission protocol for transmission.
As shown in FIG. 1, the storage layer in the multi-level cognitive model of the NC machine tool realizes the storage of perception data through a computer at the edge end. Respectively adopting a relational database MySQL to construct a knowledge base according to different types of data acquired by the numerical control machine tool, and storing data such as knowledge, rules and the like; and a non-relational database MongoDB is adopted to construct a state database for storing state data such as bending moment, torque, current and the like.
As shown in fig. 1, a processing layer in the multi-level cognitive model of the numerical control machine mainly performs data preprocessing on data acquired by the numerical control machine, reduces noise in the data, improves data quality, and provides data support for further data analysis. In this embodiment, the processing layer adopts a Z-Score normalization method to realize the normalization processing of data; the noise reduction processing of the data is carried out by adopting a wavelet transform method, so that the quality of the acquired state data is improved; the extraction of data features is carried out by adopting a method of a depth self-encoder (DAE).
As shown in fig. 1, the analysis layer in the multi-level cognitive model of the numerical control machine mainly uses the processed data to perform index decomposition of the processing process. In this embodiment, a long-term cyclic convolution network (LRCN) is used to analyze the bending moment and the torque collected by Spike, so as to analyze and predict the wear state of the tool. And analyzing the bending moment, the torque and the surface roughness acquired by the Spike by adopting a long-short-term circulating neural network (LSTM), so as to realize the analysis and prediction of the machining surface roughness of the numerical control machine tool. And analyzing the pH value, the conductivity and the dissolved oxygen rate of the cutting fluid collected in the numerical control machining process by a statistical analysis method, so as to realize the quality analysis of the cutting fluid in the running process of the numerical control machine. Through the analysis, support is provided for dynamic decision of the numerical control machine tool machining process.
As shown in fig. 1, a decision layer in a multi-level cognitive model of a numerical control machine tool mainly performs optimization decision on process parameters and a tool in a machining process according to an operation result of the numerical control machine tool, so as to improve the machining quality and the machining efficiency of the numerical control machine tool. In the embodiment, technological parameters in the machining process of the numerical control machine tool are optimized by adopting a particle swarm optimization, so that the running efficiency and the machining quality of the numerical control machine tool are improved.
As shown in fig. 1, a learning layer in a multi-level cognitive model of a numerical control machine mainly analyzes an execution scheme of the numerical control machine, obtains a processing rule and processing knowledge of a response, and accumulates operation knowledge of the numerical control machine. In this embodiment, apriori algorithm is adopted to perform mining and learning of process parameters of the numerical control machine under different working conditions, so as to accumulate process knowledge.
As shown in fig. 2, the machining task of the part is performed by the numerical control machine tool equipped with Spike, a cutting fluid, and an environment sensing terminal. And the dynamic perception of the machining process is realized by collecting relevant data of the cutter, the cutting fluid, the environment of the numerical control machine tool and parts through the perception layer. The storage of the collected data is realized by utilizing a computer at the edge end, and the normalization, the data noise reduction and the feature extraction of the collected data are realized through a corresponding data processing algorithm. And inputting the processed data into an analysis layer to analyze the wear state and the surface roughness of the cutter. The decision layer obtains the analysis results of the wear state and the surface roughness of the cutter, optimizes the process parameters by adopting a particle swarm algorithm, generates a corresponding optimization decision scheme, and adjusts the operation parameters of the numerical control machine tool. Through the process, the cognitive analysis loop of the numerical control machine tool is realized, and the self-adaptive capacity of the numerical control machine tool is improved.
As shown in fig. 3, based on the process scheme and the execution result executed by the numerical control machine, apriori algorithm is used to perform mining analysis on the process parameters under the current working condition, so as to obtain corresponding decision-making knowledge. And in the subsequent processing of the numerical control machine tool, the knowledge is utilized to guide the data analysis and the optimization decision of the numerical control machine tool, so that the intelligent degree of the numerical control machine tool is continuously improved.
By combining with a software tool of a corresponding algorithm and implementing the embodiment, the sensing capability, the analysis capability, the decision-making capability and the learning capability of the numerical control machine tool are effectively improved, the self-adaption capability and the intelligent level of the numerical control machine tool are effectively improved, and the intelligent construction of a production line and a production workshop is promoted.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that those skilled in the art may make variations, modifications, substitutions and alterations within the scope of the present invention without departing from the spirit and scope of the present invention.
Claims (10)
1. The utility model provides a multilayer cognitive model of digit control machine tool which characterized in that: the system comprises an execution layer, a cognitive layer and an advanced cognitive layer;
the execution layer comprises a numerical control machine tool, a workbench, a machine tool spindle, a cutter and various sensors, and realizes execution of a manufacturing task and acquisition of manufacturing data;
the cognitive layer comprises a sensing layer, a storage layer and a processing layer, and the three functional layers respectively realize the functions of data sensing, data storage and data preprocessing in the manufacturing process of the numerical control machine;
the advanced cognitive layer comprises an analysis layer, a decision layer and a learning layer, and the functions of dynamic analysis, dynamic decision and knowledge learning in a decision scheme in the manufacturing process of the numerical control machine are respectively realized.
2. The multi-level cognitive model of a numerical control machine tool according to claim 1, wherein: the sensing layer realizes data acquisition of a processing process through a numerical control system, various sensors and field executors, and realizes dynamic sensing of the numerical control machine; the data perceived by the perception layer includes, but is not limited to, the following types: bending moment, torque, current, power, vibration, acoustic emission, temperature and cutting.
3. The multi-level cognitive model of a numerical control machine tool according to claim 1, wherein: the storage layer realizes caching and storage of big data in the manufacturing process and transmission butt joint with the cloud platform by using a computer at the edge end, and realizes data storage, data management and data security of the edge end in the manufacturing process of the numerical control machine; the storage layer comprises a state database and a knowledge base, the state data stores real-time and historical data acquired in the running process of the numerical control machine tool, and the knowledge base stores rules and knowledge data executed by the manufacturing unit.
4. The multi-level cognitive model of a numerical control machine tool according to claim 1, wherein: the processing layer is used for preprocessing data acquired in the manufacturing process of the numerical control machine tool so as to improve the data quality of large manufacturing data and support high-level cognition of the numerical control machine tool; the processing layers include, but are not limited to, the following data processing functions: standardization, normalization, data noise reduction, data filtering and feature extraction.
5. The multi-level cognitive model of a numerical control machine tool according to claim 1, wherein: the analysis layer simulates and analyzes the manufacturing process of the numerical control machine tool, so that the running states of the numerical control machine tool, the cutter and the clamp and the quality state of the machined part are obtained, and the high-efficiency production of quality guarantee is supported; the analysis method in the analysis layer comprises simulation analysis, mechanism analysis, data analysis and evolution analysis; the analysis layer realizes the cognitive functions of tool abrasion, tool residual life, part surface quality, clamping force and numerical control machine tool load.
6. The multi-level cognitive model of a numerical control machine tool according to claim 1, wherein: the decision layer carries out dynamic decision aiming at problems existing in the manufacturing process so as to improve the self-adaptive capacity of the production system; the decision layer takes problems in the manufacturing process as trigger conditions and takes the cognitive result of the numerical control machine as a basis, so that the optimization of process parameters, the optimization of feed tracks, the optimization of loads and the optimization decision of cutters are realized, and the optimized production of the numerical control machine is realized.
7. The multi-level cognitive model of a numerical control machine tool according to claim 1, wherein: the learning layer excavates knowledge in the decision scheme, and the intelligent level of the numerical control machine tool is continuously improved; the execution scheme and the optimization scheme of the numerical control machine tool comprise implicit knowledge, including expert experience and process knowledge, and the mining of the implicit knowledge is realized through classification, induction, reasoning and deduction modes of a learning layer so as to support the continuous improvement of the execution efficiency and the processing quality of the numerical control machine tool.
8. The multi-level cognitive model of a numerical control machine tool according to claim 1, wherein: the numerical control machine tool multi-level cognitive model comprises a cognitive analysis ring and a cognitive learning ring, dynamic analysis in the numerical control machine tool manufacturing process and knowledge mining and accumulation in the numerical control machine tool manufacturing process are respectively realized, and the self-adaptive capacity and the intelligent level of the numerical control machine tool are improved.
9. The multi-level cognitive model of a numerical control machine tool according to claim 8, wherein: the cognitive analysis ring of the numerical control machine tool is as follows: performing-sensing-storing-processing-analyzing-deciding-performing; through the mutual cooperation of the six cognitive analysis processes, a cognitive analysis ring of the numerical control machine is constructed, the dynamic execution, the dynamic perception, the dynamic analysis and the dynamic decision in the manufacturing process of the numerical control machine are realized, and the self-adaptive capacity of the numerical control machine is improved.
10. The multi-level cognitive model of a numerical control machine tool according to claim 8, wherein: the cognitive learning ring of the numerical control machine tool is as follows: learning-analysis-decision-execution-learning; through the mutual cooperation of the four cognitive learning processes, the cognitive learning ring of the numerical control machine tool is constructed, knowledge mining in numerical control machine tool manufacturing tasks and schemes is realized, manufacturing knowledge such as optimized process parameters and tool optimization rules is obtained, and the intelligent level of the numerical control machine tool is continuously improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211587839.0A CN115933537A (en) | 2022-12-11 | 2022-12-11 | Multi-level cognitive model of digit control machine tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211587839.0A CN115933537A (en) | 2022-12-11 | 2022-12-11 | Multi-level cognitive model of digit control machine tool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115933537A true CN115933537A (en) | 2023-04-07 |
Family
ID=86655383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211587839.0A Pending CN115933537A (en) | 2022-12-11 | 2022-12-11 | Multi-level cognitive model of digit control machine tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115933537A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080091628A1 (en) * | 2006-08-16 | 2008-04-17 | Narayan Srinivasa | Cognitive architecture for learning, action, and perception |
| WO2012000649A1 (en) * | 2010-06-28 | 2012-01-05 | Precitec Kg | Method for controlling a laser processing operation by means of a reinforcement learning agent and laser material processing head using the same |
| CN104299351A (en) * | 2014-10-22 | 2015-01-21 | 常州大学 | Intelligent early warning and fire extinguishing robot |
| CN108241343A (en) * | 2016-12-24 | 2018-07-03 | 青岛海尔模具有限公司 | A kind of intelligent plant management platform system |
| CN108549353A (en) * | 2018-05-25 | 2018-09-18 | 南京邮电大学 | Wisdom factory monitoring method and system, readable storage medium storing program for executing, terminal |
| CN108733027A (en) * | 2017-04-20 | 2018-11-02 | 发那科株式会社 | Process poor prognostic cause estimating device |
| CN110362037A (en) * | 2019-07-05 | 2019-10-22 | 南京简睿捷软件开发有限公司 | A kind of integrated maintenance system platform for numerically-controlled machine tool |
| CN211906073U (en) * | 2020-04-10 | 2020-11-10 | 华南理工大学 | SNCR denitration control system of industrial boiler |
| CN112783132A (en) * | 2021-01-11 | 2021-05-11 | 中国船舶重工集团公司第七二三研究所 | Cognitive cooperation energizing intelligent body unit in unmanned cluster |
| US20220187847A1 (en) * | 2019-11-05 | 2022-06-16 | Strong Force Vcn Portfolio 2019, Llc | Robot Fleet Management for Value Chain Networks |
| CN115129004A (en) * | 2022-06-12 | 2022-09-30 | 西北工业大学 | Intelligent production system and method based on edge calculation and digital twinning |
-
2022
- 2022-12-11 CN CN202211587839.0A patent/CN115933537A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080091628A1 (en) * | 2006-08-16 | 2008-04-17 | Narayan Srinivasa | Cognitive architecture for learning, action, and perception |
| WO2012000649A1 (en) * | 2010-06-28 | 2012-01-05 | Precitec Kg | Method for controlling a laser processing operation by means of a reinforcement learning agent and laser material processing head using the same |
| CN104299351A (en) * | 2014-10-22 | 2015-01-21 | 常州大学 | Intelligent early warning and fire extinguishing robot |
| CN108241343A (en) * | 2016-12-24 | 2018-07-03 | 青岛海尔模具有限公司 | A kind of intelligent plant management platform system |
| CN108733027A (en) * | 2017-04-20 | 2018-11-02 | 发那科株式会社 | Process poor prognostic cause estimating device |
| CN108549353A (en) * | 2018-05-25 | 2018-09-18 | 南京邮电大学 | Wisdom factory monitoring method and system, readable storage medium storing program for executing, terminal |
| CN110362037A (en) * | 2019-07-05 | 2019-10-22 | 南京简睿捷软件开发有限公司 | A kind of integrated maintenance system platform for numerically-controlled machine tool |
| US20220187847A1 (en) * | 2019-11-05 | 2022-06-16 | Strong Force Vcn Portfolio 2019, Llc | Robot Fleet Management for Value Chain Networks |
| CN211906073U (en) * | 2020-04-10 | 2020-11-10 | 华南理工大学 | SNCR denitration control system of industrial boiler |
| CN112783132A (en) * | 2021-01-11 | 2021-05-11 | 中国船舶重工集团公司第七二三研究所 | Cognitive cooperation energizing intelligent body unit in unmanned cluster |
| CN115129004A (en) * | 2022-06-12 | 2022-09-30 | 西北工业大学 | Intelligent production system and method based on edge calculation and digital twinning |
Non-Patent Citations (1)
| Title |
|---|
| 孟博洋等: "机床智能控制***体系架构及关键技术研究进展", 机械工程学报, vol. 57, no. 9, pages 147 - 163 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110704974B (en) | Modeling and using method of process model based on digital twin driving | |
| CN109270899B (en) | Digital twin-based marine diesel engine heavy part manufacturing process control method | |
| US11481630B2 (en) | Machining condition adjustment device and machining condition adjustment system | |
| CN102929210B (en) | Control and optimization system for feature-based numerical control machining process and control and optimization method therefor | |
| CN112613646A (en) | Equipment state prediction method and system based on multi-dimensional data fusion | |
| CN111694320B (en) | Machine tool self-adaptive control method considering flutter suppression | |
| CN103760820A (en) | Evaluation device of state information of machining process of numerical control milling machine | |
| CN113569903B (en) | Method, system, equipment, medium and terminal for predicting cutter abrasion of numerical control machine tool | |
| CN111556032A (en) | Industrial big data processing system based on artificial intelligence algorithm | |
| CN113741377A (en) | Machining process intelligent monitoring system and method based on cutting characteristic selection | |
| CN107479521A (en) | A kind of pin wheel housing intelligence manufacture production line | |
| CN101334656A (en) | Numerical control machine processability monitoring system | |
| CN116187725B (en) | Forging equipment management system for forging automatic line | |
| CN109799787B (en) | Intelligent camshaft grinding process software database system based on numerical control system | |
| Ma et al. | Artificial intelligence enhanced interaction in digital twin shop-floor | |
| CN115351601A (en) | Tool wear monitoring method based on transfer learning | |
| CN111650891A (en) | Five-axis precise small gantry numerical control machining center with constant-force adaptive control method | |
| CN115933537A (en) | Multi-level cognitive model of digit control machine tool | |
| CN109034540B (en) | Machine tool sequence arrangement dynamic prediction method based on work-in-process flow | |
| CN113051685B (en) | Numerical control equipment health state evaluation method, system, equipment and storage medium | |
| CN104834787B (en) | Perception and analysis method for energy consumption of bearing grinding machine production workshop | |
| Xu et al. | A novel process planning schema based on process knowledge customization | |
| CN115716218A (en) | Online monitored control system of numerical control cutter state | |
| CN112862326A (en) | System scheduling optimization method based on big data mining | |
| Derevianchenko et al. | Improvement of the Quality for Cutting Tool Monitoring by Optimizing the Features of the State Space |
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 |