CN116719293B - Production monitoring method and system for cold-rolled steel strip - Google Patents
Production monitoring method and system for cold-rolled steel strip Download PDFInfo
- Publication number
- CN116719293B CN116719293B CN202310973500.2A CN202310973500A CN116719293B CN 116719293 B CN116719293 B CN 116719293B CN 202310973500 A CN202310973500 A CN 202310973500A CN 116719293 B CN116719293 B CN 116719293B
- Authority
- CN
- China
- Prior art keywords
- production
- node
- nodes
- monitoring
- analysis
- 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.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 263
- 238000000034 method Methods 0.000 title claims abstract description 188
- 238000012544 monitoring process Methods 0.000 title claims abstract description 150
- 239000010960 cold rolled steel Substances 0.000 title claims abstract description 50
- 230000008569 process Effects 0.000 claims abstract description 148
- 230000002159 abnormal effect Effects 0.000 claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims description 61
- 230000003993 interaction Effects 0.000 claims description 48
- 238000012216 screening Methods 0.000 claims description 33
- 238000012423 maintenance Methods 0.000 claims description 25
- 238000013507 mapping Methods 0.000 claims description 16
- 238000012806 monitoring device Methods 0.000 claims description 15
- 238000012482 interaction analysis Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 5
- 238000002910 structure generation Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 description 5
- 238000005498 polishing Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000010008 shearing Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000005554 pickling Methods 0.000 description 1
- 238000011958 production data acquisition Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a production monitoring method and system of a cold-rolled steel strip, which relate to the technical field of intelligent monitoring control, and are used for generating a process topology structure based on a target production process of the cold-rolled steel strip, and if real-time monitoring data of a process node does not meet an initial deviation interval, a target association system is called based on the process topology structure, a node to be executed is locked, and a cooperative control parameter is generated to carry out production control and monitoring early warning, so that the technical problems that in the prior art, the production monitoring method of the cold-rolled steel strip only aims at production monitoring, substantial production adjustment cannot be carried out on abnormal monitoring data, the monitoring early warning range is limited, and the current production requirement cannot be met are solved. And applying the flow node real-time monitoring data to an actual production process, and performing control adjustment on the follow-up related flow nodes so as to weaken global influence caused by the current abnormal production node, maximally improve the production quality, and continuously performing production monitoring and abnormal early warning on the adjusted related flow nodes.
Description
Technical Field
The application relates to the technical field of intelligent monitoring control, in particular to a production monitoring method and system of a cold-rolled steel strip.
Background
The cold-rolled steel strip is widely applied to the fields of automobiles, buildings and the like due to the performance preference of high dimensional accuracy, excellent mechanical property, good surface quality and the like, and production monitoring is required to be strictly carried out to ensure that the quality reaches the standard in order to ensure the application energy efficiency of the cold-rolled steel strip. At present, the production monitoring of the cold-rolled steel strip is mainly carried out based on a traditional monitoring mode, real-time production data acquisition is carried out based on a multidimensional monitoring device, data analysis is carried out to determine the actual production condition, the execution range is too one-sided, and further optimization innovation is to be carried out.
In the prior art, the production monitoring method of the cold-rolled steel strip is only aimed at the aspect of production monitoring, and cannot carry out substantial production adjustment on abnormal monitoring data, so that the monitoring and early warning range is limited, and the current production requirements cannot be met.
Disclosure of Invention
The application provides a production monitoring method and a production monitoring system for a cold-rolled steel strip, which are used for solving the technical problems that in the prior art, the production monitoring method for the cold-rolled steel strip is only aimed at production monitoring, and cannot carry out substantial production adjustment on abnormal monitoring data, so that the monitoring and early warning range is limited, and the current production requirements cannot be met.
In view of the above problems, the application provides a method and a system for monitoring production of a cold-rolled steel strip.
In a first aspect, the present application provides a method for monitoring production of a cold-rolled steel strip, the method comprising:
obtaining a target production process of the cold-rolled steel strip, and carrying out interaction analysis on each flow node based on the target production process to generate a process topology structure, wherein the process topology structure is marked with a plurality of association systems;
connecting a production monitoring system, and acquiring real-time monitoring data of a flow node based on the sensing monitoring device;
setting an initial deviation interval, and judging whether the real-time monitoring data meets the initial deviation interval or not;
if the process topology structure is not satisfied, traversing the plurality of association systems, and calling a target association system, wherein the target association system comprises a plurality of interaction nodes;
based on the plurality of interaction nodes, locking the node to be executed, and generating cooperative control parameters by combining a cooperative adjustment model, wherein the cooperative control parameters are adjusted production control parameters of the node to be executed;
traversing the target production process to perform positioning coverage based on the cooperative control parameters to obtain an updated process flow, wherein the updated process flow is a single production process;
and carrying out production monitoring analysis based on the updated process flow, and executing abnormal production early warning.
In a second aspect, the present application provides a production monitoring system for a cold rolled steel strip, the system comprising:
the topological structure generation module is used for acquiring a target production process of the cold-rolled steel strip, and carrying out interaction analysis on each flow node based on the target production process to generate a process topological structure, wherein the process topological structure is marked with a plurality of association systems;
the data acquisition module is used for connecting a production monitoring system and acquiring real-time monitoring data of the process node based on the sensing monitoring device;
the interval judging module is used for setting an initial deviation interval and judging whether the real-time monitoring data meet the initial deviation interval or not;
the system calling module is used for traversing the plurality of association systems based on the process topology structure and calling a target association system if the process topology structure is not satisfied, wherein the target association system comprises a plurality of interaction nodes;
the parameter adjustment module is used for locking the node to be executed based on the plurality of interaction nodes and generating cooperative control parameters in combination with a cooperative adjustment model, wherein the cooperative control parameters are adjusted production control parameters of the node to be executed;
the process updating module is used for traversing the target production process to carry out positioning coverage based on the cooperative control parameters to obtain an updated process flow, wherein the updated process flow is a single production process;
and the monitoring and early warning module is used for carrying out production monitoring analysis based on the updated technological process and executing abnormal production early warning.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
according to the production monitoring method for the cold-rolled steel strip, a target production process of the cold-rolled steel strip is obtained, each process node is subjected to interaction analysis to generate a process topology structure, a plurality of associated systems are identified in the process topology structure, real-time monitoring data of the process node are obtained, an initial deviation interval is set, whether the real-time monitoring data meet the initial deviation interval is judged, if not, the plurality of associated systems are traversed, the target associated systems are called, the plurality of interaction nodes are included, the nodes to be executed are locked, a cooperative control parameter is generated by combining a cooperative adjustment model, the target production process is subjected to positioning coverage based on the cooperative control parameter, the process flow is updated, production monitoring analysis is carried out, abnormal production early warning is carried out, and the technical problems that in the prior art, the production monitoring method for the cold-rolled steel strip is limited in monitoring range and cannot meet the current production requirements due to the fact that the abnormal monitoring data cannot be subjected to substantial production adjustment only in terms of production monitoring are solved. And applying the flow node real-time monitoring data to an actual production process, and performing control adjustment on the follow-up related flow nodes so as to weaken global influence caused by the current abnormal production node, maximally improve the production quality, and continuously performing production monitoring and abnormal early warning on the adjusted related flow nodes.
Drawings
FIG. 1 is a schematic flow chart of a production monitoring method of a cold-rolled steel strip;
FIG. 2 is a schematic diagram showing a process topology acquisition flow in a method for monitoring production of a cold-rolled steel strip;
FIG. 3 is a schematic diagram showing a process for obtaining nodes to be executed in a method for monitoring production of a cold-rolled steel strip;
fig. 4 is a schematic structural view of a production monitoring system for a cold-rolled steel strip.
Reference numerals illustrate: the system comprises a topology structure generation module 11, a data acquisition module 12, an interval judgment module 13, a system calling module 14, a parameter adjustment module 15, a process update module 16 and a monitoring and early warning module 17.
Detailed Description
The application provides a production monitoring method and system for a cold-rolled steel strip, which are used for generating a process topology structure based on a target production process of the cold-rolled steel strip, acquiring real-time monitoring data of process nodes and judging whether an initial deviation interval is met, if not, calling a target association system based on the process topology structure, locking nodes to be executed, generating cooperative control parameters by combining a cooperative adjustment model, positioning and covering the target production process, acquiring an updated process flow, carrying out production monitoring analysis and carrying out abnormal production early warning, and is used for solving the technical problems that the production monitoring method for the cold-rolled steel strip in the prior art only aims at the aspect of production monitoring, cannot carry out substantial production adjustment on the abnormal monitoring data, and therefore the monitoring early warning range is limited and cannot meet the current production requirements.
Example 1
As shown in fig. 1, the present application provides a method for monitoring production of a cold-rolled steel strip, the method being applied to a production monitoring system of a cold-rolled steel strip, the system being communicatively connected to a sensing and monitoring device, the method comprising:
step S100: obtaining a target production process of the cold-rolled steel strip, and carrying out interaction analysis on each flow node based on the target production process to generate a process topology structure, wherein the process topology structure is marked with a plurality of association systems;
specifically, the cold-rolled steel strip is widely applied to the fields of automobiles, buildings and the like due to the performance preference of high dimensional accuracy, excellent mechanical performance, good surface quality and the like, and strict production monitoring is required to ensure that the quality reaches the standard in order to ensure the application energy efficiency of the cold-rolled steel strip. The production monitoring method of the cold-rolled steel strip is applied to a production monitoring system of the cold-rolled steel strip, the system is a master control system for carrying out production full-period monitoring management, the system is in communication connection with the sensing monitoring device, and the sensing monitoring device is a functional auxiliary acquisition device for carrying out real-time production monitoring and comprises multi-dimensional monitoring equipment, and can be subjected to self-defining configuration according to monitoring requirements.
Specifically, the current production process of the cold-rolled steel strip is collected and used as the target production process, and the production sequence among the process nodes is associated and connected aiming at each process node of the target production process to generate the process topological structure. And respectively carrying out production influence analysis on each flow node, determining two flow nodes with direct influence relation, summarizing and integrating the two flow nodes, namely determining at least one flow node with direct influence management of each flow node, and carrying out mapping identification in the process topological structure as a correlation system corresponding to the flow node for quickly carrying out correlation identification when carrying out production influence analysis later. The process topology structure is an integral framework of the cold-rolled steel strip production, and a foundation is tamped for the subsequent association analysis of flow nodes.
Further, as shown in fig. 2, the step S100 of the present application further includes:
step S110: determining a main body process node based on the target production process, and generating a main body process sequence;
step S120: determining sub-process nodes of the main process nodes, and performing positioning association with the main process sequence to generate a process topology structure;
step S130: based on the process topology structure, performing inter-node interaction analysis to generate a plurality of interaction combinations, wherein the interaction combinations are interaction analysis results between every two flow nodes;
step S140: traversing the interaction combinations, taking each flow node as a response target, identifying and extracting the mapping flow nodes, and generating the association systems;
step S150: in the process topology, the plurality of association systems are identified, wherein identification information of the plurality of association systems is different.
Specifically, the target production process is a process flow executed in the current production, and based on the target production process, key flow nodes, such as material preparation, annealing and pickling, rolling and the like, are extracted as the main flow nodes. And carrying out serialization adjustment based on the sequence of the process flows to generate the main process sequence. Each main body process node may have at least one sub-process node, for example, the raw material preparation includes raw material inspection, heat treatment, stretching, and other sub-process nodes, and the sub-process nodes included in the main body process nodes are determined, and are inserted into the main body process sequence to perform process node connection, so as to form a node network as the process topology structure.
Further, based on the process topology structure, mutual influence analysis is performed on any two process nodes respectively, that is, whether the production of the current process node directly affects the production of each subsequent process node, for example, the polishing effect directly affects the production effect of the subsequent polishing shearing, but the polishing and the polishing shearing can be used as a group of mutual influence combinations regardless of the influence of the subsequent process node of the polishing shearing, wherein at least one group of mutual influence combinations exists on any one process node, and the plurality of mutual influence combinations are generated. And respectively extracting at least one interaction combination corresponding to each flow node based on the interaction combinations, determining a plurality of interaction nodes corresponding to the same flow node as a correlation system, and generating the correlation systems.
And respectively configuring different identification information for the plurality of association systems, for example, mapping and identifying in the process topological structure by taking different colors or different degrees of colors as the identification information so as to perfect the process topological structure and facilitate the subsequent rapid association identification of the flow nodes.
Step S200: connecting a production monitoring system, and acquiring real-time monitoring data of a flow node based on the sensing monitoring device;
further, the step S200 of the present application further includes:
step S210: the real-time monitoring data comprise production environment information, equipment control information and production energy efficiency information of each flow node;
step S220: the production energy efficiency information comprises appearance characteristics, color characteristics and surface state characteristics.
Specifically, the production monitoring system is a control system for monitoring the production of the cold-rolled steel strip, the sensing monitoring device is auxiliary monitoring equipment for monitoring the real-time production, such as image monitoring equipment, temperature sensing equipment, power sensing equipment and the like, and the custom layout of the sensing monitoring setting and the assembly position can be performed based on the monitoring requirements of the process nodes.
Further, the production monitoring system is connected, monitoring data of the sensing monitoring device are called, and the called monitoring data are provided with flow node identifiers. Specifically, because the layout types of the sensing and monitoring devices are different, corresponding monitoring data modes are different, such as an array, an image and the like, monitoring data are identified and extracted, for example, characteristic enhancement, identification and extraction and the like are performed on an acquired image, required monitoring information is determined, and production temperature, environmental noise, dust content and the like are extracted as the production environment information by way of example; extracting equipment control parameters, control precision and the like as the equipment control information; and carrying out visual production feature extraction of corresponding flow nodes, for example, taking the size and the surface flaw as appearance features, recognizing the color, the glossiness and the like as the color features, recognizing the surface residues, the surface flatness and the like as the surface state features, and taking the appearance features, the color features and the surface state features as the production energy efficiency information. And taking the production environment information, the equipment control information and the production energy efficiency information as the real-time monitoring data. The real-time monitoring data has a unified data mode and is used for carrying out real-time production state analysis.
Step S300: setting an initial deviation interval, and judging whether the real-time monitoring data meets the initial deviation interval or not;
step S400: if the process topology structure is not satisfied, traversing the plurality of association systems, and calling a target association system, wherein the target association system comprises a plurality of interaction nodes;
specifically, in the production process of the cold-rolled steel strip, certain production deviation is allowed, and the deviation in a production controllable range is negligible. And aiming at each flow node, directly carrying out production deviation acquisition and determination based on the production standard of the cold-rolled steel strip, and setting the initial deviation interval based on an acquisition result, wherein the initial deviation interval corresponds to a plurality of flow node mappings. Identifying and extracting monitoring data of the current process node based on the real-time monitoring data, traversing the initial deviation interval for mapping and checking, judging whether the initial deviation interval is met, and when the initial deviation interval is met, indicating that the current process node is in a normal production state and advancing based on a set production process; when the current process node is not satisfied, the current process node is in an abnormal production state, meanwhile, the production effect of the final process node can cause the production limitation of the subsequent direct influence related node, and the global influence caused by the abnormal production of the current process node is weakened by carrying out production adjustment on the current process node.
Specifically, the process nodes corresponding to the node real-time monitoring data are used as index targets, the plurality of association systems are traversed in the process topology structure, identification information corresponding to the index targets is identified and extracted, the association system covered by the identification information, namely, the process nodes with direct interaction relation with the index targets are included as the target association system, and the acquisition of the target association system provides a basic basis for subsequent production control adjustment.
Step S500: based on the plurality of interaction nodes, locking the node to be executed, and generating cooperative control parameters by combining a cooperative adjustment model, wherein the cooperative control parameters are adjusted production control parameters of the node to be executed;
further, as shown in fig. 3, based on the plurality of interacting nodes, locking the node to be executed, step S500 of the present application further includes:
step S510: building a global influence degree analysis model, wherein the global influence degree analysis model comprises a global analysis layer, a sequence adjustment layer and a node screening layer, and a preset screening proportion is embedded in the node screening layer;
step S520: and inputting the plurality of interaction nodes into the global influence degree analysis model, and outputting the node to be executed, wherein the node to be executed is a serialization interception result of the plurality of interaction nodes meeting the preset screening proportion.
Specifically, the parameter adjustment coverage of the plurality of interaction nodes is required to be completed before the real-time production process reaches the subsequent production node, so that the analysis efficiency requirement is high, the plurality of interaction nodes are screened, the associated node with weaker global influence is eliminated, the execution efficiency is improved, and the follow-up timeliness of the subsequent production process is ensured. And extracting a flow node to be subjected to production control adjustment from the plurality of interaction nodes by performing global influence analysis, and taking the flow node as the node to be executed and locking.
Specifically, the global influence analysis model is built, and is an auxiliary analysis tool for screening the multiple interaction nodes, and the auxiliary analysis tool comprises a multi-level network layer and different corresponding execution functions. The global analysis layer is trained and learned based on a global analysis algorithm, the target production process is embedded into the global analysis layer as a global analysis basis, the preset screening proportion, namely the proportion for screening the plurality of interaction nodes is set, and the target production process can be set in a self-defined mode based on the node magnitude contained in each association system in the plurality of association systems and based on expert production experience. And embedding the preset screening proportion into the node screening and the like for assisting in executing the node screening. And embedding a hierarchical execution mechanism, namely each network layer processing flow, into the multi-level network layer, collecting and determining sample data to perform model verification, and ensuring the analysis precision of the model. Further inputting the plurality of interaction nodes into the global influence degree analysis model, carrying out global influence assessment on the plurality of interaction nodes based on the global analysis layer, generating an influence degree assessment result and carrying out mapping identification with the plurality of interaction nodes; further transmitting the result to the sequence adjustment layer, and sequencing the plurality of interaction nodes based on the influence degree evaluation result from large to small to generate a node sequence; transmitting the node sequence header to the node screening layer, taking the preset screening proportion as a screening standard, intercepting a plurality of nodes meeting the preset screening proportion based on the node sequence header, and outputting the nodes serving as the nodes to be executed for model output. The node screening evaluation is carried out by constructing the global influence degree analysis model, so that the accuracy of screening results can be effectively improved, and the matching degree with the target production process is ensured.
Further constructing the collaborative adjustment model, exemplarily, collecting a plurality of groups of historical production records, analyzing by combining the process topological structure, determining abnormal production nodes and determining nodes to be executed, performing node control adjustment based on actual production data, determining a plurality of sample collaborative adjustment data, performing mapping association on the plurality of groups of historical production records and the plurality of sample collaborative adjustment data, determining a hierarchy identification node and a hierarchy decision node, taking the hierarchy identification node and the hierarchy decision node as training samples, and generating the collaborative adjustment model by performing neural network training. Further, determining a node production deviation value based on the real-time monitoring data and the initial deviation interval, inputting the node production deviation value and the plurality of interaction nodes into the cooperative control model, and directly outputting the cooperative control parameters through hierarchical matching and decision analysis, wherein the cooperative control parameters are adjusted production control parameters of the nodes to be executed, and carrying out production control of the follow-up corresponding process nodes based on the cooperative control parameters.
Step S600: traversing the target production process to perform positioning coverage based on the cooperative control parameters to obtain an updated process flow, wherein the updated process flow is a single production process;
step S700: and carrying out production monitoring analysis based on the updated process flow, and executing abnormal production early warning.
Further, the present application also includes step S800, including:
step S810: product production is carried out based on the updated process flow, and a reset execution instruction is generated after the production of each flow node is finished;
step S820: and carrying out reset control on the production control parameters of the nodes to be executed based on the reset execution instruction, wherein the reset control effect is that each node to be executed gradually restores the target production process.
Specifically, the cooperative control parameters are in one-to-one correspondence with the nodes to be executed, the target production process is traversed, the process nodes corresponding to the nodes to be executed are determined, the node control parameters are matched and positioned with the cooperative control parameters, the node control parameters are covered based on the matching result, the cooperative control parameters are used as production control parameters for iterative updating, and the updated process flow is generated. Further, production control is performed based on the updated process flow, production monitoring of subsequent process nodes is continued, production monitoring data are collected, abnormality analysis is performed, if production abnormality exists in the process nodes, abnormal production early warning information is generated, and the abnormal production early warning information comprises product codes of production early warning products.
Further, the updating process flow is a single production process, the product production is carried out based on the updating process flow, after the production of each process node is finished, namely after the production of each process node is gradually finished by the nodes to be executed, the reset execution instruction is sequentially generated along with the end of the production of each node, and the reset execution instruction is a start instruction for recovering the coverage parameters of the process node. And along with the receiving of the reset execution instruction, the production control parameters of the nodes to be executed are gradually and sequentially restored, each node to be executed gradually restores the target production process, and the production of the subsequent cold-rolled steel strip is continuously controlled based on the target production process.
Further, based on the updated process flow, the production monitoring analysis is performed, and the abnormal production early warning is executed, and the step S700 of the present application further includes:
step S710-1: performing production monitoring based on the updated process flow, and determining node monitoring data;
step S720-1: based on the updated process flow, the initial deviation interval is adjusted, and an overlapped deviation interval is generated;
step S730-1: and carrying out mapping judgment on the overlapped deviation interval and the node monitoring data, and carrying out early warning and warning based on a judgment result, wherein the attribution information of the product to be detected is additional output information.
Specifically, after the to-be-executed node performs process coverage based on the cooperative control parameter, performing subsequent production control based on the updated process flow. And continuing to monitor subsequent production and collecting node monitoring data to perform abnormality analysis. Specifically, for the updated process flow, the node to be executed performs matching extraction of the initial deviation interval, the cooperative control parameter and the initial production control parameter are mapped and correspond, a parameter difference value is calculated based on a mapping result to determine an adjustment direction and an adjustment scale, the initial deviation interval is subjected to same-frequency adjustment, and the overlapped deviation interval is generated, wherein the overlapped deviation interval is an adaptation check analysis interval of monitoring data of the updated process flow. Mapping and corresponding the overlapped deviation interval and the node monitoring data, judging whether the production deviation of the node monitoring data meets the overlapped deviation interval or not, and if so, indicating that the node monitoring data is in a normal production state; if the information is not satisfied, the production monitoring abnormality exists after the production adjustment, abnormal production early warning information is generated to carry out early warning, the attribution information of the product to be detected is synchronously generated, namely the product to be detected is primarily judged to be a defective product, and quality inspection qualification judgment is needed again after the production is completed so as to improve the production efficiency.
Further, step S700 of the present application further includes:
step S710-2: configuring a device operation and maintenance period, wherein the device operation and maintenance period is a periodic operation and maintenance time zone;
step S720-2: setting a dynamic monitoring period, and counting cooperative adjustment frequency based on the dynamic monitoring period;
step S730-2: if the collaborative adjustment frequency meets the preset frequency, generating an instant operation node;
step S740-2: and inserting the instant operation and maintenance node into the operation and maintenance period of the equipment to monitor and early warn the abnormal operation of the equipment.
Specifically, in the production process of the cold-rolled steel strip, along with the advancement of production time sequence, certain production equipment damage is inevitably generated so as to influence the production performance. And setting a periodic operation and maintenance time zone of the production equipment as an operation and maintenance period of the equipment, namely, a time interval for carrying out periodic operation and maintenance inspection of the production equipment, carrying out fault monitoring of the production equipment based on the operation and maintenance period of the equipment, wherein the operation and maintenance period of the equipment can be custom set based on actual production conditions and equipment loss trend.
Furthermore, dynamic fault tracing is required to be performed aiming at the abnormal conditions in the production process. Specifically, the dynamic monitoring period, that is, an analysis interval for performing equipment fault detection and judgment, is set, an initial time node and a termination time node are determined based on the dynamic monitoring period, and the cooperative adjustment frequency in the initial time node and the termination time node is counted. Setting the preset frequency, namely judging whether the critical frequency of the detection necessity of the equipment exists or not, and carrying out custom configuration based on production experience according to the production live. Judging whether the cooperative adjustment frequency meets the preset frequency, and continuously detecting equipment operation faults based on the equipment operation period when the cooperative adjustment frequency is smaller than the preset frequency; when the current time node is more than or equal to the preset frequency, the abnormal production frequency is excessively high, the abnormal influence of equipment possibly exists, the current time node is used as the instant operation and maintenance node, and the instant operation and maintenance node is a temporarily determined equipment detection time node. And the instant operation and maintenance node is inserted into the equipment operation period, the operation fault detection and tracing of the production equipment are carried out, and the abnormal operation monitoring and early warning of the equipment are carried out on the fault equipment so as to ensure the timeliness of equipment overhaul.
Example two
Based on the same inventive concept as the production monitoring method of a cold rolled steel strip in the foregoing embodiments, as shown in fig. 4, the present application provides a production monitoring system of a cold rolled steel strip, the system comprising:
the topology structure generation module 11 is used for acquiring a target production process of the cold-rolled steel strip, and performing interaction analysis on each flow node based on the target production process to generate a process topology structure, wherein the process topology structure is marked with a plurality of association systems;
the data acquisition module 12 is used for connecting a production monitoring system, and acquiring real-time monitoring data of the process node based on the sensing monitoring device;
the interval judging module 13 is used for setting an initial deviation interval and judging whether the real-time monitoring data meets the initial deviation interval or not;
the system calling module 14 is configured to, if not, traverse the plurality of association systems based on the process topology structure, and call a target association system, where the target association system includes a plurality of interaction nodes;
the parameter adjustment module 15 is configured to lock a node to be executed based on the plurality of interaction nodes, and generate a cooperative control parameter in combination with a cooperative adjustment model, where the cooperative control parameter is an adjusted production control parameter of the node to be executed;
the process updating module 16 is configured to traverse the target production process to perform positioning coverage based on the cooperative control parameter, and obtain an updated process flow, where the updated process flow is a single production process;
and the monitoring and early warning module 17 is used for carrying out production monitoring analysis based on the updated technological process and executing abnormal production early warning.
Further, the system further comprises:
the process sequence generation module is used for determining a main body flow node based on the target production process to generate a main body process sequence;
the process topology structure generation module is used for determining sub-process nodes of the main process nodes, and performing positioning association with the main process sequence to generate a process topology structure;
the combination acquisition module is used for carrying out inter-node interaction analysis based on the process topological structure to generate a plurality of interaction combinations, wherein the interaction combinations are interaction analysis results between every two flow nodes;
the association system generation module is used for traversing the plurality of interaction combinations, taking each flow node as a response target, identifying and extracting the mapping flow node and generating the plurality of association systems;
and the association system identification module is used for identifying the plurality of association systems in the process topological structure, wherein the identification information of the plurality of association systems is different.
Further, the system further comprises:
the real-time monitoring data analysis module is used for enabling the real-time monitoring data to comprise production environment information, equipment control information and production energy efficiency information of each flow node;
and the production energy efficiency information analysis module is used for analyzing the production energy efficiency information, wherein the production energy efficiency information comprises appearance characteristics, color characteristics and surface state characteristics.
Further, the system further comprises:
the monitoring data determining module is used for carrying out production monitoring based on the updated process flow and determining node monitoring data;
the interval adjusting module is used for adjusting the initial deviation interval based on the updated technological process to generate an overlapped deviation interval;
and the result early warning module is used for carrying out mapping judgment on the overlapping deviation interval and the node monitoring data and carrying out early warning and warning based on a judgment result, wherein the attribution information of the product to be detected is additional output information.
Further, the system further comprises:
the instruction generation module is used for carrying out product production based on the updated process flow, and generating a reset execution instruction after the production of each flow node is finished;
and the reset control module is used for carrying out reset control on the production control parameters of the nodes to be executed based on the reset execution instruction, wherein the reset control effect is that each node to be executed gradually restores the target production process.
Further, the system further comprises:
the system comprises a model building module, a global influence analysis module and a node screening module, wherein the model building module is used for building a global influence analysis model, the global influence analysis model comprises a global analysis layer, a sequence adjustment layer and a node screening layer, and a preset screening proportion is embedded in the node screening layer;
the node to be executed output module is used for inputting the interaction nodes into the global influence degree analysis model and outputting the node to be executed, wherein the node to be executed is a serialization interception result of the interaction nodes meeting the preset screening proportion.
Further, the system further comprises:
the period configuration module is used for configuring the equipment operation and maintenance period, wherein the equipment operation and maintenance period is a periodic operation and maintenance time zone;
the frequency statistics module is used for setting a dynamic monitoring period and counting the cooperative adjustment frequency based on the dynamic monitoring period;
the instant operation and maintenance node generation module is used for generating an instant operation and maintenance node if the collaborative adjustment frequency meets the preset frequency;
and the abnormality monitoring module is used for penetrating the instant operation and maintenance node into the equipment operation and maintenance period to monitor and early warn the abnormal operation of the equipment.
The foregoing detailed description of a method for monitoring the production of a cold-rolled steel strip will be apparent to those skilled in the art, and the device disclosed in the embodiments is relatively simple in description and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A method for monitoring production of a cold-rolled steel strip, the method being applied to a production monitoring system of a cold-rolled steel strip, the system being in communication with a sensor monitoring device, the method comprising:
obtaining a target production process of the cold-rolled steel strip, and carrying out interaction analysis on each flow node based on the target production process to generate a process topology structure, wherein the process topology structure is marked with a plurality of association systems;
connecting a production monitoring system, and acquiring real-time monitoring data of a flow node based on the sensing monitoring device;
setting an initial deviation interval, and judging whether the real-time monitoring data meets the initial deviation interval or not;
if the process topology structure is not satisfied, traversing the plurality of association systems, and calling a target association system, wherein the target association system comprises a plurality of interaction nodes;
locking a node to be executed based on the plurality of interaction nodes, and generating a cooperative control parameter in combination with a cooperative adjustment model, wherein a node production deviation value is determined based on the real-time monitoring data and the initial deviation interval, the node production deviation value and the plurality of interaction nodes are input into the cooperative adjustment model, the cooperative control parameter is output through hierarchical matching and decision analysis, the cooperative control parameter is the adjusted production control parameter of the node to be executed, and constructing the cooperative adjustment model comprises: collecting a plurality of groups of historical production records, analyzing by combining the process topological structure, determining abnormal production nodes, determining nodes to be executed, performing node control adjustment based on actual production data, determining a plurality of sample cooperative adjustment data, performing mapping association on the plurality of groups of historical production records and the plurality of sample cooperative adjustment data, determining hierarchy identification nodes and hierarchy decision nodes, taking the hierarchy identification nodes and the hierarchy decision nodes as training samples, and generating the cooperative adjustment model by performing neural network training;
traversing the target production process to perform positioning coverage based on the cooperative control parameters to obtain an updated process flow, wherein the method comprises the following steps: traversing the target production process, determining a process node corresponding to the node to be executed, determining a node control parameter, performing matching positioning with the cooperative control parameter, covering the node control parameter based on a matching result, and generating the updating process flow by taking the cooperative control parameter as an iteratively updated production control parameter, wherein the updating process flow is a single production process;
performing production monitoring analysis based on the updated process flow, and executing abnormal production early warning;
wherein locking the node to be executed based on the plurality of interacting nodes comprises:
building a global influence degree analysis model, wherein the global influence degree analysis model is an auxiliary analysis tool for screening a plurality of interaction nodes and comprises a multi-level network layer, the multi-level network layer comprises a global analysis layer, a sequence adjustment layer and a node screening layer, training and learning are carried out on the global analysis layer based on a global analysis algorithm, the target production process is embedded into the global analysis layer, a preset screening proportion is embedded into the node screening layer and used for assisting in executing node screening, the processing flow of each network layer is embedded into the multi-level network layer, and model verification is carried out by collecting and determining sample data;
and inputting the plurality of interaction nodes into the global influence degree analysis model, and outputting the node to be executed, wherein the node to be executed is a serialization interception result of the plurality of interaction nodes meeting the preset screening proportion.
2. The method of claim 1, wherein performing a cross-influence analysis on each process node based on the target production process to generate a process topology comprises:
determining a main body process node based on the target production process, and generating a main body process sequence;
determining sub-process nodes of a plurality of main process nodes, and performing positioning association with the main process sequence to generate a process topology structure;
based on the process topology structure, performing inter-node interaction analysis to generate a plurality of interaction combinations, wherein the interaction combinations are interaction analysis results between every two flow nodes;
traversing the interaction combinations, taking each flow node as a response target, identifying and extracting the mapping flow nodes, and generating the association systems;
in the process topology, the plurality of association systems are identified, wherein identification information of the plurality of association systems is different.
3. The method as claimed in claim 1, comprising:
the real-time monitoring data comprise production environment information, equipment control information and production energy efficiency information of each flow node;
the production energy efficiency information comprises appearance characteristics, color characteristics and surface state characteristics.
4. The method of claim 1, wherein performing abnormal production pre-warning based on the updated process flow for production monitoring analysis comprises:
performing production monitoring based on the updated process flow, and determining node monitoring data;
based on the updated process flow, the initial deviation interval is adjusted, and an overlapped deviation interval is generated;
and carrying out mapping judgment on the overlapped deviation interval and the node monitoring data, and carrying out early warning and warning based on a judgment result, wherein the attribution information of the product to be detected is additional output information.
5. The method as claimed in claim 1, comprising:
product production is carried out based on the updated process flow, and a reset execution instruction is generated after the production of each flow node is finished;
and carrying out reset control on the production control parameters of the nodes to be executed based on the reset execution instruction, wherein the reset control effect is that each node to be executed gradually restores the target production process.
6. The method as claimed in claim 1, comprising:
configuring a device operation and maintenance period, wherein the device operation and maintenance period is a periodic operation and maintenance time zone;
setting a dynamic monitoring period, and counting cooperative adjustment frequency based on the dynamic monitoring period;
if the collaborative adjustment frequency meets the preset frequency, generating an instant operation node;
and inserting the instant operation and maintenance node into the operation and maintenance period of the equipment to monitor and early warn the abnormal operation of the equipment.
7. A production monitoring system for cold rolled steel strip, the system being in communication with a sensing and monitoring device, the system comprising:
the topological structure generation module is used for acquiring a target production process of the cold-rolled steel strip, and carrying out interaction analysis on each flow node based on the target production process to generate a process topological structure, wherein the process topological structure is marked with a plurality of association systems;
the data acquisition module is used for connecting a production monitoring system and acquiring real-time monitoring data of the process node based on the sensing monitoring device;
the interval judging module is used for setting an initial deviation interval and judging whether the real-time monitoring data meet the initial deviation interval or not;
the system calling module is used for traversing the plurality of association systems based on the process topology structure and calling a target association system if the process topology structure is not satisfied, wherein the target association system comprises a plurality of interaction nodes;
the parameter adjustment module is configured to lock a node to be executed based on the multiple interaction nodes, and combine with a collaborative adjustment model to generate a collaborative control parameter, where determining a node production deviation value based on the real-time monitoring data and the initial deviation interval, inputting the node production deviation value and the multiple interaction nodes into the collaborative adjustment model, and outputting the collaborative control parameter through hierarchical matching and decision analysis, where the collaborative control parameter is an adjusted production control parameter of the node to be executed, and constructing the collaborative adjustment model includes: collecting a plurality of groups of historical production records, analyzing by combining the process topological structure, determining abnormal production nodes, determining nodes to be executed, performing node control adjustment based on actual production data, determining a plurality of sample cooperative adjustment data, performing mapping association on the plurality of groups of historical production records and the plurality of sample cooperative adjustment data, determining hierarchy identification nodes and hierarchy decision nodes, taking the hierarchy identification nodes and the hierarchy decision nodes as training samples, and generating the cooperative adjustment model by performing neural network training;
the process updating module is used for traversing the target production process to carry out positioning coverage based on the cooperative control parameters, and acquiring an updated process flow, and comprises the following steps: traversing the target production process, determining a process node corresponding to the node to be executed, determining a node control parameter, performing matching positioning with the cooperative control parameter, covering the node control parameter based on a matching result, and generating the updating process flow by taking the cooperative control parameter as an iteratively updated production control parameter, wherein the updating process flow is a single production process;
the monitoring and early warning module is used for carrying out production monitoring analysis based on the updated process flow and executing abnormal production early warning;
the model building module is used for building a global influence degree analysis model, wherein the global influence degree analysis model is an auxiliary analysis tool for screening a plurality of interaction nodes and comprises a multi-level network layer, the multi-level network layer comprises a global analysis layer, a sequence adjustment layer and a node screening layer, training and learning are carried out on the global analysis layer based on a global analysis algorithm, the target production process is embedded into the global analysis layer, a preset screening proportion is embedded into the node screening layer and used for assisting in executing node screening, each network layer processing flow is embedded into the multi-level network layer, and sample data are acquired and determined for model verification;
the node to be executed output module is used for inputting the interaction nodes into the global influence degree analysis model and outputting the node to be executed, wherein the node to be executed is a serialization interception result of the interaction nodes meeting the preset screening proportion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310973500.2A CN116719293B (en) | 2023-08-04 | 2023-08-04 | Production monitoring method and system for cold-rolled steel strip |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310973500.2A CN116719293B (en) | 2023-08-04 | 2023-08-04 | Production monitoring method and system for cold-rolled steel strip |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116719293A CN116719293A (en) | 2023-09-08 |
| CN116719293B true CN116719293B (en) | 2023-11-17 |
Family
ID=87868227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310973500.2A Active CN116719293B (en) | 2023-08-04 | 2023-08-04 | Production monitoring method and system for cold-rolled steel strip |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116719293B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094605B (en) * | 2023-10-18 | 2023-12-22 | 南通钢安机械制造有限公司 | Casting quality control method and system |
| CN117094608B (en) * | 2023-10-19 | 2023-12-26 | 江苏甬金金属科技有限公司 | Titanium belt production control method and system combining application requirements |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112116198A (en) * | 2020-08-04 | 2020-12-22 | 西安交通大学 | Data-driven process industrial state perception network key node screening method |
| CN112162528A (en) * | 2020-09-29 | 2021-01-01 | 广东工业大学 | Fault diagnosis method, device, equipment and storage medium of numerical control machine tool |
| WO2021051618A1 (en) * | 2019-09-20 | 2021-03-25 | 平安科技（深圳）有限公司 | Abnormality early warning method, device, server and storage medium |
| CN113807715A (en) * | 2021-09-23 | 2021-12-17 | 厦门标安科技有限公司 | Chemical device risk dynamic early warning method |
| CN113835411A (en) * | 2021-09-07 | 2021-12-24 | 北京科技大学顺德研究生院 | Comprehensive diagnosis method for abnormal quality of steel rolling process flow |
| CN114841396A (en) * | 2022-03-16 | 2022-08-02 | 广东石油化工学院 | Method for predicting metamorphic trend and warning catastrophe risk in petrochemical production process |
| CN116307405A (en) * | 2023-05-25 | 2023-06-23 | 日照鲁光电子科技有限公司 | Diode performance prediction method and system based on production data |
| CN116382219A (en) * | 2023-05-16 | 2023-07-04 | 苏州海卓伺服驱动技术有限公司 | Motor production process optimization method and system based on online measurement technology |
| CN116423005A (en) * | 2023-06-14 | 2023-07-14 | 苏州松德激光科技有限公司 | Tin soldering process optimization method and system for improving welding precision |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210243069A1 (en) * | 2020-01-31 | 2021-08-05 | Opsramp, Inc. | Alert correlating using sequence model with topology reinforcement systems and methods |
| TWI746038B (en) * | 2020-07-02 | 2021-11-11 | 阿證科技股份有限公司 | Neural network-like artificial intelligence decision-making core system |
-
2023
- 2023-08-04 CN CN202310973500.2A patent/CN116719293B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021051618A1 (en) * | 2019-09-20 | 2021-03-25 | 平安科技（深圳）有限公司 | Abnormality early warning method, device, server and storage medium |
| CN112116198A (en) * | 2020-08-04 | 2020-12-22 | 西安交通大学 | Data-driven process industrial state perception network key node screening method |
| CN112162528A (en) * | 2020-09-29 | 2021-01-01 | 广东工业大学 | Fault diagnosis method, device, equipment and storage medium of numerical control machine tool |
| CN113835411A (en) * | 2021-09-07 | 2021-12-24 | 北京科技大学顺德研究生院 | Comprehensive diagnosis method for abnormal quality of steel rolling process flow |
| CN113807715A (en) * | 2021-09-23 | 2021-12-17 | 厦门标安科技有限公司 | Chemical device risk dynamic early warning method |
| CN114841396A (en) * | 2022-03-16 | 2022-08-02 | 广东石油化工学院 | Method for predicting metamorphic trend and warning catastrophe risk in petrochemical production process |
| CN116382219A (en) * | 2023-05-16 | 2023-07-04 | 苏州海卓伺服驱动技术有限公司 | Motor production process optimization method and system based on online measurement technology |
| CN116307405A (en) * | 2023-05-25 | 2023-06-23 | 日照鲁光电子科技有限公司 | Diode performance prediction method and system based on production data |
| CN116423005A (en) * | 2023-06-14 | 2023-07-14 | 苏州松德激光科技有限公司 | Tin soldering process optimization method and system for improving welding precision |
Non-Patent Citations (1)
| Title |
|---|
| 钢铁企业全流程质量管控研究;栾绍峻;;冶金经济与管理(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116719293A (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116719293B (en) | Production monitoring method and system for cold-rolled steel strip | |
| CN115833400B (en) | Monitoring and early warning method and system for power equipment of transformer substation | |
| CN111737909B (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
| CN106404441B (en) | A kind of failure modes diagnostic method based on non-linear similarity index | |
| CN109086470A (en) | A kind of method for diagnosing faults based on fuzzy preference relation and D-S evidence theory | |
| CN116204842B (en) | Abnormality monitoring method and system for electrical equipment | |
| CN110083860A (en) | A kind of industrial method for diagnosing faults based on correlated variables selection | |
| CN115643159A (en) | Equipment abnormity early warning method and system based on edge calculation | |
| CN113657221A (en) | Power plant equipment state monitoring method based on intelligent sensing technology | |
| CN106907927A (en) | The flexible manifold insertion electric melting magnesium furnace fault monitoring method of one seed nucleus | |
| CN110677437A (en) | User disguised attack detection method and system based on potential space countermeasure clustering | |
| CN116224930A (en) | Processing control method and system for numerically controlled grinder product | |
| CN117057644A (en) | Equipment production quality detection method and system based on characteristic matching | |
| CN116092014A (en) | Intelligent inspection control method and system based on Internet of things equipment | |
| CN117115169A (en) | Intelligent recognition method for abnormal deformation of surface of die-casting die of automobile part | |
| CN117014817B (en) | Intelligent tour inspection method and system for park equipment based on Internet of things | |
| CN117252809A (en) | Identification system and method based on AI industrial vision | |
| CN110320802B (en) | Complex system signal time sequence identification method based on data visualization | |
| CN115983684B (en) | Copper pipe production defect management method and system for refrigeration | |
| CN116704729A (en) | Industrial kiln early warning system and method based on big data analysis | |
| CN116449761B (en) | Intelligent pump station intelligent control system and method | |
| CN114077933B (en) | Real-time transmission system and method for steam on-line monitoring data | |
| CN117686757B (en) | Intelligent early warning method and system for outdoor power metering box | |
| CN113077002B (en) | Machine olfaction visual sensing data analysis method based on space heterodyne Raman spectrum | |
| CN117399435B (en) | Self-adaptive compensation adjustment method and system for copper pipe rolling 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |