Cloud service-based industrial intelligent operating system and method

Abstract

The application discloses an industrial intelligent operation system and method based on cloud services, and relates to the technical field of data processing.The application comprises the following steps: establishing the production equipment topology of a target production line, and determining a master node and a plurality of collaborative nodes; connecting the master node, the plurality of collaborative nodes and a cloud computing platform to construct a cloud operation configuration network; receiving product information to be produced by the cloud computing platform, generating master node operation parameters of the master node, and generating a plurality of groups of initial collaborative node operation parameters of the plurality of collaborative nodes based on the parameters; jointly verifying the plurality of groups of initial collaborative node operation parameters, determining a plurality of groups of optimized collaborative node operation parameters according to the joint verification result; and configuring the master node operation parameters to the master node and the plurality of groups of optimized collaborative node operation parameters to the plurality of collaborative nodes through the cloud operation configuration network.The application effectively improves the overall efficiency of the industrial production line and the intelligent level of collaborative control.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to an industrial intelligent operating system and method based on cloud services. Background Technology

[0002] With the rapid development of industrial intelligence and cloud computing technology, industrial production lines are gradually transforming into multi-equipment collaborative and flexible production. Traditional technologies can now achieve remote monitoring and basic parameter configuration of single production equipment, providing basic support for the large-scale advancement of industrial production.

[0003] However, existing technologies rely heavily on human experience for parameter matching and collaborative configuration of production nodes, lacking in-depth mining of historical data and effective application of intelligent algorithms. This makes it difficult to further improve the overall operating efficiency of the production line and meet the higher demands of industrial production for overall efficiency upgrades and intelligent collaborative control. Summary of the Invention

[0004] This application provides an industrial intelligent operating system and method based on cloud services, aiming to solve the technical problems in the prior art that are difficult to meet the needs of industrial production for overall efficiency upgrade and intelligent collaborative control.

[0005] In view of the above problems, this application provides an industrial intelligent operating system and method based on cloud services.

[0006] Firstly, this application provides a cloud-based industrial intelligent operating system, including:

[0007] The topology node initialization module is used to determine the target production line, establish the production equipment topology of the target production line, and determine the master control node and multiple cooperating nodes based on the production equipment topology.

[0008] The cloud network construction module is used to connect the master control node, the multiple collaborative nodes and the cloud computing platform to build a cloud operation configuration network;

[0009] The operation parameter generation module is used by the cloud computing platform to receive information about products to be produced, generate the main control node operation parameters of the main control node based on the information about products to be produced, and generate multiple sets of initial collaborative node operation parameters for multiple collaborative nodes based on the main control node operation parameters.

[0010] The parameter joint verification module is used to jointly verify multiple sets of initial collaborative node operating parameters and determine multiple sets of optimized collaborative node operating parameters based on the joint verification results.

[0011] The parameter configuration deployment module is used to configure the master control node's operating parameters on the master control node through the cloud operation configuration network, and to configure multiple sets of optimized collaborative node operating parameters on multiple collaborative nodes respectively.

[0012] Secondly, this application provides a cloud-based industrial intelligent operation method, including:

[0013] Identify the target production line, establish the production equipment topology of the target production line, and determine the master control node and multiple cooperating nodes based on the production equipment topology;

[0014] The master control node, the multiple collaborating nodes, and the cloud computing platform are connected to construct a cloud-based operation and configuration network;

[0015] The cloud computing platform receives information about products to be manufactured, generates master control node operating parameters for the master control node based on the information about products to be manufactured, and generates multiple sets of initial collaborative node operating parameters for multiple collaborative nodes based on the master control node operating parameters.

[0016] Multiple sets of initial collaborative node operating parameters are jointly verified, and multiple sets of optimized collaborative node operating parameters are determined based on the joint verification results.

[0017] The cloud-based operation configuration network configures the master control node's operating parameters on the master control node, and configures multiple sets of optimized collaborative node operating parameters on multiple collaborative nodes respectively.

[0018] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0019] This application provides an industrial intelligent operating system and method based on cloud services. By establishing a device topology, the master-slave collaborative relationship is clarified, laying the foundation for centralized control. Efficient data and command interaction is achieved through cloud networks. Master control and initial collaborative parameters are automatically generated based on product information, abandoning the traditional manual experience configuration mode and shifting to automated decision-making based on historical data and intelligent algorithms. Through joint verification of multiple sets of parameters, the coordination of equipment operation and overall process feasibility are ensured, avoiding the problem of local optima but global conflicts. Through the precise deployment of optimized parameters via cloud networks, the entire production line is driven to operate in an efficient, collaborative, and stable state, thereby significantly improving resource allocation efficiency, production flexibility, and overall system efficiency. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A schematic diagram of the structure of a cloud-based industrial intelligent operating system provided in this application embodiment;

[0022] Figure 2 A flowchart illustrating the cloud-based intelligent industrial operation method provided in this application embodiment;

[0023] The components represented by each mark in the attached diagram are explained below:

[0024] Topology node initialization module 11, cloud network construction module 12, running parameter generation module 13, parameter joint verification module 14, parameter configuration and deployment module 15. Detailed Implementation

[0025] This application provides a cloud-based industrial intelligent operating system and method to address the technical problems that existing technologies struggle to meet the demands of industrial production for overall efficiency upgrades and intelligent collaborative control.

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0027] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0028] Example 1, as Figure 1 As shown, this application provides a cloud-based industrial intelligent operating system, the system comprising:

[0029] The topology node initialization module 11 is used to determine the target production line, establish the production equipment topology of the target production line, and determine the master control node and multiple cooperative nodes based on the production equipment topology.

[0030] In this embodiment, a target production line is determined, a production equipment topology for the target production line is established, and a master control node and multiple collaborative nodes are determined based on the production equipment topology. The production line consists of multiple devices with different functions, and each device needs to cooperate according to specific logic to complete the production task. To ensure that subsequent cloud connections, parameter configurations, and device collaboration can be accurately implemented, it is necessary to first clarify the relationships and functional divisions of the devices in the production line, laying the foundation for the orderly advancement of the overall production process.

[0031] In one embodiment, the topology node initialization module 11 is further configured to:

[0032] In the production equipment topology, the core production equipment is identified as the master control node;

[0033] Based on the core production equipment, multiple auxiliary production equipment that are functionally associated with the master control node are identified in the production equipment topology and serve as multiple collaborative nodes.

[0034] First, identify the target production line and establish its production equipment topology. This involves identifying the target production line, identifying all equipment involved in the production process, recording the functional attributes, physical connections, and operational dependencies of each piece of equipment, and constructing the production equipment topology. The production equipment topology refers to the structured system formed by the actual connection logic and functional relationships of all equipment in the production line, which can intuitively present the interactions and relationships between equipment. For example, a certain automotive parts processing production line includes raw material cutting equipment, grinding equipment, drilling equipment, surface treatment equipment, etc. After analysis, it is determined that the cutting equipment provides raw materials to the grinding equipment, and the drilling equipment connects to the grinding equipment for precise processing. Based on this, the equipment topology of the production line is constructed.

[0035] Secondly, core production equipment is identified in the production equipment topology as master control nodes. In the completed production equipment topology, production equipment that undertakes key production processes and drives the production flow is selected and designated as master control nodes. For example, in the aforementioned automotive parts processing production line, the grinding equipment undertakes the precision machining process for the parts' shape, directly affecting the product's key dimensional parameters; therefore, the grinding equipment is designated as a master control node.

[0036] Furthermore, based on the core production equipment, multiple auxiliary production devices functionally associated with the main control node are identified in the production equipment topology and designated as multiple collaborative nodes. Using the determined main control node as a benchmark, auxiliary production devices in the production equipment topology that have functional cooperation requirements with that node and need to synchronously respond to its operating status are identified as collaborative nodes. For example, in the aforementioned production line, the cutting equipment that supplies blanks to the grinding equipment, the drilling equipment that drills holes in the ground parts, and the surface treatment equipment that performs rust prevention all need to work in coordination with the main control node's operating rhythm, thus resulting in three collaborative nodes: the cutting equipment, the drilling equipment, and the surface treatment equipment.

[0037] In this embodiment, by clearly identifying the core production equipment as the main control node and selecting auxiliary equipment as collaborative nodes based on functional association, the role positioning of each piece of equipment in the production line is clearly defined, ensuring the matching of collaborative nodes and main control nodes in terms of production functions. This provides a clear node architecture foundation for subsequent modules such as parameter generation, verification, and deployment, and ensures the logical rationality of the collaborative operation of production line equipment.

[0038] The cloud network construction module 12 is used to connect the master control node, the multiple collaborative nodes and the cloud computing platform to build a cloud operation configuration network.

[0039] In this embodiment, the master control node, the multiple collaborating nodes, and the cloud computing platform are connected to construct a cloud-based operation configuration network. To achieve efficient information exchange between the master control node, collaborating nodes, and the cloud computing platform, and to ensure accurate transmission of operating parameters and real-time feedback of device status, a dedicated connection network needs to be built to provide a communication foundation for the collaborative operation of each node. The cloud computing platform is a remote service platform integrating computing resources, storage resources, and data processing capabilities, capable of centrally receiving information, generating parameters, and enabling remote interaction. The cloud-based operation configuration network is a dedicated network connecting each node to the cloud computing platform for transmitting operating parameters and device status information.

[0040] For example, in this automotive parts processing production line, the grinding equipment has been identified as the main control node, while the cutting equipment, drilling equipment, and surface treatment equipment are the collaborating nodes. First, it was confirmed that the communication interfaces of each device are all industrial Ethernet interfaces and support a unified data transmission protocol, ensuring basic communication compatibility. Then, the network address, dedicated access port, and device access permissions of the cloud computing platform were configured, clarifying the data interaction path and security rules. Subsequently, the grinding equipment, cutting equipment, drilling equipment, and surface treatment equipment were sequentially connected to the cloud computing platform via a wired network. Tests showed that the data transmission latency between each node and the platform was controlled within 40 milliseconds, and the connection stability reached 100% for 24 consecutive hours, thus constructing a cloud-based operation and configuration network.

[0041] In this embodiment, by constructing a cloud-based operation configuration network, a stable interconnection between the main control node, collaborative nodes, and cloud computing platform in the automotive parts processing production line is achieved, establishing an efficient and secure information transmission channel. This ensures that the operating parameters generated by the cloud computing platform can be quickly and accurately distributed to each device, and also guarantees that the real-time operating status of each device can be synchronously fed back to the platform, providing reliable network support for subsequent parameter configuration and collaborative control.

[0042] The operation parameter generation module 13 is used by the cloud computing platform to receive the product information to be produced, generate the master control node operation parameters of the master control node based on the product information to be produced, and generate multiple sets of initial collaborative node operation parameters of multiple collaborative nodes based on the master control node operation parameters.

[0043] In this embodiment, the cloud computing platform receives information about products to be produced, generates master control node operating parameters based on the product information, and generates multiple sets of initial collaborative node operating parameters for multiple collaborative nodes based on the master control node operating parameters. To ensure that each node on the production line operates precisely according to the requirements of the products to be produced, it is necessary to generate suitable operating parameters based on the product information to ensure parameter matching between the master control node and collaborative nodes, providing data support for efficient collaboration in the production process.

[0044] In one embodiment, the runtime parameter generation module 13 is further configured to:

[0045] The cloud computing platform receives information about products to be manufactured and generates master control node operating parameters based on this information, including:

[0046] The model of the product to be produced is extracted based on the product information to be produced. Based on the model of the product to be produced, historical production records are retrieved to obtain a set of production records for the same model of product. Each production record for the same model of product includes historical main control node operating parameters and historical batch product qualification rate.

[0047] Extract the preset pass rate from the information of products to be produced, and filter the record set of products of the same model based on the preset pass rate and the historical batch product pass rate to obtain the operating parameters of multiple qualified master control nodes;

[0048] Based on the historical batch product pass rates of the operating parameters of multiple qualified master control nodes, multiple fusion weights of the operating parameters of multiple qualified master control nodes are obtained;

[0049] Based on the multiple fusion weights, the operating parameters of multiple qualified master control nodes are fused to obtain the master control node operating parameters.

[0050] First, the product model is extracted from the product information to be manufactured. Based on this model, historical production records are retrieved to obtain a set of production records for the same product model. Each production record for the same product model includes historical master control node operating parameters and historical batch product pass rates. The product model is extracted from the product information to be manufactured, and historical production records are retrieved based on this model to form a set of production records for the same product model. Each record in the product production record set contains historical operating parameters of the master control node in the corresponding production batch, as well as the pass rate of that batch of products. For example, if the product to be manufactured is a certain model of automotive driveshaft, after extracting the model, a historical record set is retrieved, where one product production record contains: historical master control node operating parameters: grinding pressure 50N, feed speed 10mm / s; historical batch product pass rate: 99.3%.

[0051] Secondly, a preset pass rate is extracted from the product information to be manufactured. Based on the preset pass rate and the historical batch product pass rate, a record set of products of the same model is generated and filtered to obtain multiple qualified master control node operating parameters. A preset pass rate standard is extracted from the product information to be manufactured, and compared with the historical batch product pass rate of each record in the historical record set. Records with a pass rate not lower than the preset standard are retained, and their corresponding historical master control node operating parameters are the qualified master control node operating parameters. For example, if the preset pass rate of the drive shaft to be manufactured is 99%, then records with a historical batch product pass rate ≥ 99% are filtered out to obtain multiple qualified master control node operating parameters, for example: operating parameters of qualified master control node 1: grinding pressure 48N, feed speed 11mm / s, pass rate 99.5%; operating parameters of qualified master control node 2: grinding pressure 52N, feed speed 9mm / s, pass rate 99.2%.

[0052] Furthermore, based on the historical batch product pass rates of the operating parameters of multiple qualified master control nodes, multiple fusion weights of the operating parameters of multiple qualified master control nodes are obtained.

[0053] Among them, based on the historical batch product pass rates of the operating parameters of multiple qualified master control nodes, multiple fusion weights of the operating parameters of multiple qualified master control nodes are obtained, including:

[0054] The historical batch product pass rates of multiple qualified master control nodes are summed to obtain the total pass rate.

[0055] Calculate the historical batch product pass rate and the total pass rate of multiple qualified master control nodes respectively to obtain multiple pass rate percentages;

[0056] Multiple fusion weights are set for the operating parameters of multiple qualified master control nodes based on the multiple qualification rate ratios.

[0057] First, the historical batch product pass rates of the operating parameters of multiple qualified master control nodes are summed to obtain a total pass rate. This sum of pass rates quantifies the overall pass level of all qualified parameters, providing a unified calculation benchmark for subsequent weight allocation and ensuring that the weight percentage of each parameter reflects its relative contribution to the overall pass performance. For example, the total pass rate of qualified master control node 1 and qualified master control node 2 is 0.995 + 0.992 = 198.7.

[0058] Secondly, the historical batch product pass rates and the total pass rate of multiple qualified master control nodes are calculated separately to obtain multiple pass rate percentages. The pass rates of each parameter are converted into relative proportions, so that parameters with high pass rates receive a higher weight in the fusion process. The higher the pass rate, the greater its impact on the final parameters, ensuring that the fusion result is more inclined towards parameters with better historical performance. For example, the pass rate percentage of qualified master control node 1 is 0.995 / 0.1987≈0.501, and the pass rate percentage of qualified master control node 2 is 0.992 / 0.1987≈0.499.

[0059] Then, based on the multiple pass rate percentages, multiple fusion weights are set for the operating parameters of multiple qualified master control nodes. The fusion weights must meet the basic requirement that their sum is 1, and they must be directly correlated with the historical pass performance of each parameter. This ensures that the weighted fusion of the master control node operating parameters not only integrates the advantages of multiple qualified parameters but also favors parameters with higher pass rates, thereby improving the reliability and adaptability of the final parameters. For example, based on the pass rate percentages obtained above, the fusion weight for the operating parameters of qualified master control node 1 is 0.501, and the fusion weight for the operating parameters of qualified master control node 2 is 0.499.

[0060] Finally, based on the multiple fusion weights, the operating parameters of multiple qualified master control nodes are fused to obtain the master control node operating parameters. According to the calculated fusion weights, the operating parameters of multiple qualified master control nodes are weighted and fused to obtain the final master control node operating parameters. For example, based on the above weighted fusion of the parameters of master control node 1 and master control node 2, the master control node operating parameters are: grinding pressure: 48N×50.1%+52N×49.9%≈50N; feed rate: 11mm / s×50.1%+9mm / s×49.9%≈10mm / s.

[0061] Based on the operating parameters of the master control node, multiple sets of initial operating parameters for multiple collaborative nodes are generated, including:

[0062] Determine a first collaborative node among the plurality of collaborative nodes, and obtain a first collaborative parameter generator bound to the first collaborative node;

[0063] The first collaborative parameter generator is constructed based on the sample master control node operation parameter set and the sample first collaborative node operation parameter set. The sample master control node operation parameter set and the sample first collaborative node operation parameter set are obtained according to the historical collaborative operation data between the first collaborative node and the master control node.

[0064] The master control node's operating parameters are input into the first collaborative parameter generator to obtain the initial collaborative node operating parameters of the first collaborative node;

[0065] Following the method of obtaining the initial collaborative node operating parameters of the first collaborative node, the initial collaborative node operating parameters of the remaining collaborative nodes are obtained, resulting in multiple sets of initial collaborative node operating parameters.

[0066] First, a first collaborative node is determined among the multiple collaborative nodes, and a first collaborative parameter generator bound to the first collaborative node is obtained. The collaborative parameter generator is a dedicated tool configured for a specific collaborative node. It learns the parameter association patterns between the master node and collaborative nodes based on historical data to achieve automated parameter matching. Continuing the previous example, the collaborative nodes of the automotive driveshaft production line include cutting equipment, drilling equipment, and surface treatment equipment. The cutting equipment is selected as the first collaborative node, and the corresponding first collaborative parameter generator is a parameter generation tool specifically configured for the cutting equipment.

[0067] Secondly, a first collaborative parameter generator is constructed. This generator is based on the sample master control node operating parameter set and the sample first collaborative node operating parameter set, which are obtained from historical collaborative operation data between the first collaborative node and the master control node. The sample master control node operating parameter set is a collection of operating parameters extracted from historical production data that the master control node used in past collaborative production. For example, in an automotive driveshaft production line, one historical operating parameter of the master control node's grinding equipment is: grinding pressure 48N, feed speed 11mm / s; grinding pressure 52N, feed speed 9mm / s. All historical operating parameters are organized to form the sample master control node operating parameter set. The sample first collaborative node operating parameter set corresponds to the sample master control node operating parameter set and is the collection of operating parameters used by the first collaborative node in past collaborative production with the master control node. For example, when the first collaborative node cutting device corresponds to the above grinding parameters, one of its historical operating parameters is: cutting speed 7.8m / min, cutting depth 2.9mm; cutting speed 8.2m / min, cutting depth 3.1mm. After organizing all the historical operating parameters, a sample first collaborative node operating parameter set is formed.

[0068] For example, taking an automotive driveshaft production line, the obtained sample master control node operating parameter set is used as input features, including two dimensions: grinding pressure and feed speed. The sample first collaborative node operating parameter set is used as output labels, including two dimensions: cutting speed and cutting depth. A neural network model is used to learn the correlation between the master control node operating parameters and the first collaborative node operating parameters. The input layer has 2 neurons, corresponding to 2 master control parameters; the hidden layer has 3 layers, each with 16 neurons, processed by the ReLU activation function; the output layer has 2 neurons, corresponding to 2 cutting parameters. During training, the sample master control node operating parameters are input into the model, and the predicted first collaborative node operating parameters are output. The error is calculated by comparing the predicted first collaborative node operating parameters with the sample first collaborative node operating parameters. The mean squared error loss function is used, and the weights of each layer are adjusted by backpropagation using the gradient descent algorithm. Each iteration uses 100 sets of sample data, and a total of 500 iterations are performed until the error stabilizes within 0.01, thus completing the construction of the first collaborative parameter generator. Once trained, the first collaborative parameter generator can automatically output adapted initial parameters for the first collaborative node based on the new master node's operating parameters, thus achieving intelligent parameter matching.

[0069] Furthermore, the operating parameters of the master control node are input into the first collaborative parameter generator to obtain the initial collaborative node operating parameters of the first collaborative node. For example, if the current operating parameters of the master control node are: grinding pressure 50N and feed speed 10mm / s, and these are input into the first collaborative parameter generator, the first collaborative parameter generator outputs the initial collaborative node operating parameters of the first collaborative node based on the learned correlation rules: cutting speed 8m / min and cutting depth 3mm.

[0070] Finally, following the same method used to obtain the initial operating parameters of the first collaborative node, the initial operating parameters of the remaining collaborative nodes are obtained, resulting in multiple sets of initial operating parameters. When generating the initial parameters for the remaining collaborative nodes, the same method used to generate the initial parameters for the first collaborative node is applied to each of them. Taking an automotive driveshaft production line as an example, for other collaborative nodes such as drilling equipment and surface treatment equipment, the specific nodes are first identified, and then the corresponding collaborative parameter generators for each node are trained. For example, the second collaborative parameter generator corresponds to the drilling equipment, and the third collaborative parameter generator corresponds to the surface treatment equipment. The determined operating parameters of the master control node are input into the second and third collaborative parameter generators, respectively. Based on the parameter correlation rules learned by each generator with the master control node, the generators output the initial operating parameters of the corresponding collaborative nodes. For example, the initial operating parameters of the second collaborative node are: drilling speed of 2000 r / min and drilling depth of 5 mm for the drilling equipment; and the initial operating parameters of the third collaborative node are: processing temperature of 80℃ and processing time of 10 s for the surface treatment equipment. This yields the initial operating parameters of all collaborative nodes, ultimately forming multiple sets of initial operating parameters.

[0071] In this embodiment, by receiving information about products to be manufactured, historical production records are retrieved based on the product model. Qualified main control node operating parameters are then selected based on a preset pass rate. Adapted main control node operating parameters are generated based on historical batch data fusion, ensuring that the parameters accurately match product needs and production requirements. Simultaneously, relying on the main control node operating parameters, an initial operating parameter generator built based on historical collaborative data is used to generate initial operating parameters for each collaborative node, establishing a correlation and adaptation between the collaborative node parameters and the main control node parameters. This automates the process of generating operating parameters from historical data-driven to intelligent generation, ensuring both the reliability of the main control node parameters and the synergy between the collaborative node parameters and the main control node. This provides data support for the precise coordination and efficient operation of various equipment on the production line, helping to improve the stability of the production process and the product pass rate, while reducing errors and costs associated with manual parameter configuration.

[0072] The parameter joint verification module 14 is used to jointly verify multiple sets of initial collaborative node operating parameters and determine multiple sets of optimized collaborative node operating parameters based on the joint verification results.

[0073] In this embodiment, multiple sets of initial collaborative node operating parameters are jointly verified, and multiple sets of optimized collaborative node operating parameters are determined based on the joint verification results. Although the generated master node operating parameters and collaborative node initial parameters are constructed based on historical data, in actual production, parameter combinations may become mismatched due to equipment status fluctuations, changes in environmental factors, etc., which may affect the product qualification rate. Simulation verification can identify potential problems with parameter combinations in advance before actual production, avoiding resource waste and efficiency losses caused by direct application, improving the success rate of parameter configuration, and ensuring that the final parameter combination can stably meet production requirements.

[0074] In one embodiment, the parameter joint verification module 14 is further configured to:

[0075] Activate the production line simulation model of the target production line;

[0076] Configure the production line simulation model based on the operating parameters of the master control node and the operating parameters of the multiple sets of initial collaborative nodes;

[0077] Run the configured production line simulation model to obtain the predicted product qualification rate;

[0078] Extract a preset pass rate from the information on products to be manufactured, compare the predicted product pass rate with the preset pass rate, and obtain a joint verification result.

[0079] When the joint verification result indicates that the predicted product qualification rate is greater than or equal to the preset qualification rate, the multiple sets of initial collaborative node operating parameters are used as multiple sets of optimized collaborative node operating parameters.

[0080] First, activate the production line simulation model of the target production line. Start the pre-built virtual simulation model of the target production line, which can simulate the operating status of each piece of equipment and the product processing in a real production environment. For example, the virtual simulation model of an automotive driveshaft production line can reproduce the physical principles of processes such as grinding, cutting, drilling, and surface treatment, as well as the material transfer logic between equipment.

[0081] Secondly, the production line simulation model is configured based on the operating parameters of the master control node and the operating parameters of the multiple sets of initial collaborative nodes. The operating parameters of the master control node and the initial parameters of the collaborative nodes are input into the simulation model to set corresponding operating parameters for the virtual equipment, enabling the production line simulation model to operate according to actual production logic. For example, a grinding pressure of 50N and a feed speed of 10mm / s are set for the virtual grinding equipment, and a cutting speed of 8m / min is set for the virtual cutting equipment.

[0082] Furthermore, the configured production line simulation model is run to obtain the predicted product pass rate. For example, the configured production line simulation model simulates the production of 1000 automotive drive shafts. The simulation model automatically detects the dimensional accuracy, surface quality, and other indicators of the virtual products, counts the number of qualified products, and calculates the predicted product pass rate. It is assumed that the predicted pass rate is 99.3% after the first run.

[0083] Furthermore, a preset pass rate is extracted from the information on products to be manufactured, and the predicted pass rate is compared with the preset pass rate to obtain a joint verification result. For example, in the information on automotive drive shafts to be manufactured, the preset pass rate for the automotive drive shafts to be manufactured is 99%, and the predicted pass rate is 99.3%, which is higher than the preset pass rate of 99%. Therefore, the joint verification result is determined to be compliant.

[0084] When the joint verification results indicate that the predicted product qualification rate is greater than or equal to the preset qualification rate, the multiple sets of initial collaborative node operating parameters are used as multiple sets of optimized collaborative node operating parameters. For example, if the predicted qualification rate of 99.3% is greater than or equal to the preset qualification rate of 99%, it indicates that the parameter sets of the main control node and the collaborative nodes are well matched and can cover common fluctuation scenarios in production. At this time, the current initial collaborative node operating parameters are directly determined as the optimized collaborative node operating parameters. For example, the parameters are configured as [cutting speed 7.9m / min, cutting depth 3.0mm; drilling speed 2050r / min, drilling depth 5.0mm; processing temperature 82℃, processing time 10s], which can be directly used for parameter configuration and production preparation in the actual production line.

[0085] In one embodiment, the parameter joint verification module 14 is further configured to:

[0086] When the joint verification result indicates that the predicted product pass rate is less than the preset pass rate, multiple sets of initial collaborative node operating parameters will be added as forbidden combination parameters to the forbidden parameter list.

[0087] The collaborative parameter generators of each collaborative node are called again to generate multiple new sets of collaborative node operating parameters while avoiding the taboo parameter list, thus obtaining multiple sets of updated collaborative node operating parameters.

[0088] The production line simulation model is reconfigured and run according to multiple sets of updated collaborative node operating parameters to obtain the updated predicted product qualification rate.

[0089] Compare the updated predicted product pass rate with the preset pass rate. When the updated predicted product pass rate is greater than or equal to the preset pass rate, use the multiple sets of updated collaborative node operating parameters as multiple sets of optimized collaborative node operating parameters.

[0090] When the updated predicted product pass rate is less than the preset pass rate, the multiple sets of update collaborative node operating parameters are added to the taboo parameter list and iterated until multiple sets of optimized collaborative node operating parameters that meet the preset pass rate are obtained.

[0091] In this embodiment, when the predicted pass rate of the first simulation verification is lower than the preset standard, it indicates that the current parameter combination has an adaptability defect. If invalid parameter combinations are directly and repeatedly generated, the verification efficiency will be low. Therefore, a tabu search mechanism needs to be introduced to record and avoid failed combinations, guide parameter generation to iterate in a better direction, and quickly converge to a parameter configuration that meets the pass rate requirements.

[0092] First, when the joint verification result indicates that the predicted product pass rate is less than the preset pass rate, multiple sets of initial collaborative node operating parameters are added as forbidden combination parameters to the forbidden parameter list. Multiple sets of initial collaborative node operating parameters that failed the initial verification are added as forbidden combination parameters to the forbidden parameter list. The forbidden parameter list stores verified invalid parameter combinations to prevent the subsequent parameter generator from repeatedly outputting the same configuration, reducing the number of invalid simulations. For example, if the initial collaborative operating parameters are [cutting speed 8.2m / min, cutting depth 3.2mm; drilling speed 1950r / min, drilling depth 5.1mm; processing temperature 78℃, processing time 9s], and the production line simulation model is configured and run, the predicted product pass rate is 93%, which is less than the preset pass rate of 99%. In this case, the initial collaborative operating parameters are added as forbidden combination parameters.

[0093] Secondly, the collaborative parameter generators of each collaborative node are re-invoked to generate multiple new sets of collaborative node operating parameters while avoiding the taboo parameter list, resulting in multiple sets of updated collaborative node operating parameters. Based on learning historical collaborative patterns, the collaborative parameter generators of each collaborative node introduce additional constraints from the taboo list to ensure that the new parameter combinations do not overlap with the taboo parameters. For example, the cutting equipment generates new parameters: 8.0 m / min, 3.0 mm, avoiding the original taboo combination of 8.2 m / min and 3.2 mm; the drilling equipment generates new parameters: 2020 r / min, 4.9 mm, adjusting the rotation speed and depth to distinguish it from the taboo item 1950 r / min, 5.1 mm; the surface treatment equipment generates new parameters: 81℃, 11 s, with both temperature and time deviating from the taboo values ​​of 78℃ and 9 s. Finally, multiple sets of updated collaborative node operating parameters are obtained.

[0094] Furthermore, the production line simulation model is reconfigured and run according to multiple sets of updated collaborative node operating parameters to obtain the updated predicted product pass rate. The updated collaborative node parameters are then combined with the original master control node parameters to configure the production line simulation model, and 1000 drive shafts are simulated for production again. The dimensional accuracy, surface quality, and other indicators of the products are tested, and the updated predicted pass rate is calculated, which is 98.8% in this case.

[0095] Finally, the updated predicted product pass rate is compared with the preset pass rate. When the updated predicted product pass rate is greater than or equal to the preset pass rate, the multiple sets of updated collaborative node operating parameters are used as multiple sets of optimized collaborative node operating parameters. When the updated predicted product pass rate is greater than or equal to the preset pass rate, it indicates that the current parameter combination meets the production quality requirements. The multiple sets of updated collaborative node operating parameters are then determined as multiple sets of optimized collaborative node operating parameters, which can be directly applied to the actual production line configuration. For example, if the updated predicted pass rate is 99.2%, which is greater than 99%, then the optimized collaborative node operating parameters are: [Cutting equipment: 7.9 m / min, 3.1 mm; Drilling equipment: 2050 r / min, 5.0 mm].

[0096] Conversely, when the updated predicted product pass rate is less than the preset pass rate, the multiple sets of updated collaborative node operating parameters are added to the taboo parameter list, and the process is iteratively executed until multiple sets of optimized collaborative node operating parameters that meet the preset pass rate are obtained. When the updated predicted product pass rate is less than the preset pass rate, it indicates that the parameter combination still has an adaptability problem, and it needs to be added to the taboo parameter list to avoid subsequent duplicate generation. Based on the expanded taboo list, the collaborative parameter generator is called again to generate a new parameter combination and verify it again. This iterative execution continues until multiple sets of optimized collaborative node operating parameters that meet the preset standard for the predicted pass rate are obtained.

[0097] In this embodiment, a tabu search mechanism is used to record and avoid parameter combinations that have failed verification, thereby avoiding the repeated generation of invalid configurations, reducing redundant simulation verification steps, and making the parameter optimization process more efficient. After multiple rounds of iterative verification, the final optimized collaborative node operating parameters can stably meet the preset pass rate requirements, ensuring the adaptability and quality stability of the parameter combination in actual production. During the iteration process, the tabu list continuously accumulates invalid parameter patterns, guiding parameter generation to converge towards a better direction, so that the final parameter combination can not only meet basic production requirements, but also better adapt to various fluctuations in actual production.

[0098] The parameter configuration deployment module 15 is used to configure the main control node's operating parameters on the main control node through the cloud operation configuration network, and to configure multiple sets of optimized collaborative node operating parameters on multiple collaborative nodes respectively.

[0099] In this embodiment, the master control node's operating parameters are configured on the master control node through the cloud-based operation configuration network, and multiple sets of optimized collaborative node operating parameters are configured on multiple collaborative nodes respectively. The generated master control node and optimized collaborative node operating parameters need to be accurately applied to the actual equipment. Automated deployment through the cloud-based operation configuration network ensures that parameters are distributed in real time and consistently across multiple nodes, adapting to the collaborative operation requirements of production line equipment.

[0100] For example, the final optimized collaborative node operating parameters are as follows: [Cutting equipment: cutting speed 7.9 m / min, cutting depth 3.1 mm; Drilling equipment: drilling speed 2050 r / min, drilling depth 5.0 mm; Surface treatment equipment: processing temperature 82℃, processing time 10 s]. Through cloud-based configuration, the main control node operating parameters [grinding pressure 50 N, feed speed 10 mm / s] are transmitted to the main control node's control system for writing. Simultaneously, the optimized collaborative parameters are sent to the control terminals of the cutting, drilling, and surface treatment equipment according to their respective equipment identifiers. This achieves automatic configuration of parameters for each collaborative node, ensuring synchronized parameter effects across the entire production line, improving configuration efficiency and accuracy, facilitating parameter change traceability, and providing a guarantee for stable production.

[0101] The embodiments of this application, through the specific implementation methods described above, achieve the following technical effects:

[0102] This application provides an industrial intelligent operating system and method based on cloud services. It generates master control and initial collaborative parameters through historical data, selects the optimal parameter combination through simulation iteration and tabu search, and then realizes the automated synchronous deployment of parameters of each node by relying on the cloud network. It completely replaces traditional manual operation, avoids the error of manual intervention, ensures the high adaptability and production stability of master control and collaborative node parameters, eliminates redundant links such as physical trial and error and improves the efficiency of the whole process, strengthens management standardization by data traceability, and ultimately enhances the anti-interference capability of the production line, helps to stably achieve the preset production quality requirements, and effectively improves the overall efficiency of industrial production lines and the level of intelligent collaborative control.

[0103] Example 2, as Figure 2 As shown, this application provides an industrial intelligent operation method based on cloud services, the method comprising:

[0104] S100: Determine the target production line, establish the production equipment topology of the target production line, and determine the master control node and multiple collaborative nodes based on the production equipment topology.

[0105] Step S100 in the method provided in this application embodiment includes:

[0106] In the production equipment topology, the core production equipment is identified as the master control node;

[0107] Based on the core production equipment, multiple auxiliary production equipment that are functionally associated with the master control node are identified in the production equipment topology and serve as multiple collaborative nodes.

[0108] S200: Connect the master control node, the multiple collaborative nodes, and the cloud computing platform to build a cloud operation configuration network.

[0109] S300: The cloud computing platform receives information about products to be manufactured, generates master control node operating parameters for the master control node based on the information about products to be manufactured, and generates multiple sets of initial collaborative node operating parameters for multiple collaborative nodes based on the master control node operating parameters.

[0110] Step S300 in the method provided in this application embodiment includes:

[0111] The cloud computing platform receives information about products to be manufactured and generates master control node operating parameters based on this information, including:

[0112] The model of the product to be produced is extracted based on the product information to be produced. Based on the model of the product to be produced, historical production records are retrieved to obtain a set of production records for the same model of product. Each production record for the same model of product includes historical main control node operating parameters and historical batch product qualification rate.

[0113] Extract the preset pass rate from the information of products to be produced, and filter the record set of products of the same model based on the preset pass rate and the historical batch product pass rate to obtain the operating parameters of multiple qualified master control nodes;

[0114] Based on the historical batch product pass rates of the operating parameters of multiple qualified master control nodes, multiple fusion weights of the operating parameters of multiple qualified master control nodes are obtained;

[0115] Based on the multiple fusion weights, the operating parameters of multiple qualified master control nodes are fused to obtain the master control node operating parameters.

[0116] Among them, based on the historical batch product pass rates of the operating parameters of multiple qualified master control nodes, multiple fusion weights of the operating parameters of multiple qualified master control nodes are obtained, including:

[0117] The historical batch product pass rates of multiple qualified master control nodes are summed to obtain the total pass rate.

[0118] Calculate the historical batch product pass rate and the total pass rate of multiple qualified master control nodes respectively to obtain multiple pass rate percentages;

[0119] Multiple fusion weights are set for the operating parameters of multiple qualified master control nodes based on the multiple qualification rate ratios.

[0120] Based on the operating parameters of the master control node, multiple sets of initial operating parameters for multiple collaborative nodes are generated, including:

[0121] Determine a first collaborative node among the plurality of collaborative nodes, and obtain a first collaborative parameter generator bound to the first collaborative node;

[0122] The first collaborative parameter generator is constructed based on the sample master control node operation parameter set and the sample first collaborative node operation parameter set. The sample master control node operation parameter set and the sample first collaborative node operation parameter set are obtained according to the historical collaborative operation data between the first collaborative node and the master control node.

[0123] The master control node's operating parameters are input into the first collaborative parameter generator to obtain the initial collaborative node operating parameters of the first collaborative node;

[0124] Following the method of obtaining the initial collaborative node operating parameters of the first collaborative node, the initial collaborative node operating parameters of the remaining collaborative nodes are obtained, resulting in multiple sets of initial collaborative node operating parameters.

[0125] S400: Jointly verify multiple sets of initial collaborative node operating parameters, and determine multiple sets of optimized collaborative node operating parameters based on the joint verification results.

[0126] Step S400 in the method provided in this application embodiment includes:

[0127] Activate the production line simulation model of the target production line;

[0128] Configure the production line simulation model based on the operating parameters of the master control node and the operating parameters of the multiple sets of initial collaborative nodes;

[0129] Run the configured production line simulation model to obtain the predicted product qualification rate;

[0130] Extract a preset pass rate from the information on products to be manufactured, compare the predicted product pass rate with the preset pass rate, and obtain a joint verification result.

[0131] When the joint verification result indicates that the predicted product qualification rate is greater than or equal to the preset qualification rate, the multiple sets of initial collaborative node operating parameters are used as multiple sets of optimized collaborative node operating parameters.

[0132] Step S400 in the method provided in this application embodiment further includes:

[0133] When the joint verification result indicates that the predicted product pass rate is less than the preset pass rate, multiple sets of initial collaborative node operating parameters will be added as forbidden combination parameters to the forbidden parameter list.

[0134] The collaborative parameter generators of each collaborative node are called again to generate multiple new sets of collaborative node operating parameters while avoiding the taboo parameter list, thus obtaining multiple sets of updated collaborative node operating parameters.

[0135] The production line simulation model is reconfigured and run according to multiple sets of updated collaborative node operating parameters to obtain the updated predicted product qualification rate.

[0136] Compare the updated predicted product pass rate with the preset pass rate. When the updated predicted product pass rate is greater than or equal to the preset pass rate, use the multiple sets of updated collaborative node operating parameters as multiple sets of optimized collaborative node operating parameters.

[0137] When the updated predicted product pass rate is less than the preset pass rate, the multiple sets of update collaborative node operating parameters are added to the taboo parameter list and iterated until multiple sets of optimized collaborative node operating parameters that meet the preset pass rate are obtained.

[0138] S500: Configure the master control node's operating parameters on the master control node through the cloud operation configuration network, and configure multiple sets of optimized collaborative node operating parameters on multiple collaborative nodes respectively.

[0139] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0140] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0141] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A cloud-based industrial intelligent operating system, characterized in that, The system includes: The topology node initialization module is used to determine the target production line, establish the production equipment topology of the target production line, and determine the master control node and multiple cooperating nodes based on the production equipment topology. The cloud network construction module is used to connect the master control node, the multiple collaborative nodes and the cloud computing platform to build a cloud operation configuration network; The operation parameter generation module is used by the cloud computing platform to receive information about products to be produced, generate the main control node operation parameters of the main control node based on the information about products to be produced, and generate multiple sets of initial collaborative node operation parameters for multiple collaborative nodes based on the main control node operation parameters. The process of generating master control node operating parameters based on the product information to be produced includes: The model of the product to be produced is extracted based on the product information to be produced. Based on the model of the product to be produced, historical production records are retrieved to obtain a set of production records for the same model of product. Each production record for the same model of product includes historical main control node operating parameters and historical batch product qualification rate. Extract the preset pass rate from the information of products to be produced, and filter the record set of products of the same model based on the preset pass rate and the historical batch product pass rate to obtain the operating parameters of multiple qualified master control nodes; Based on the historical batch product pass rates of the operating parameters of multiple qualified master control nodes, multiple fusion weights of the operating parameters of multiple qualified master control nodes are obtained; Based on the multiple fusion weights, the operating parameters of multiple qualified master control nodes are fused to obtain the master control node operating parameters of the master control node. The parameter joint verification module is used to jointly verify multiple sets of initial collaborative node operating parameters and determine multiple sets of optimized collaborative node operating parameters based on the joint verification results. The parameter configuration deployment module is used to configure the master control node's operating parameters on the master control node through the cloud operation configuration network, and to configure multiple sets of optimized collaborative node operating parameters on multiple collaborative nodes respectively.

2. The system according to claim 1, characterized in that, The topology node initialization module is also used for: In the production equipment topology, the core production equipment is identified as the master control node; Based on the core production equipment, multiple auxiliary production equipment that are functionally associated with the master control node are identified in the production equipment topology and serve as multiple collaborative nodes.

3. The system according to claim 1, characterized in that, The operating parameter generation module is also used for: The historical batch product pass rates of multiple qualified master control nodes are summed to obtain the total pass rate. Calculate the historical batch product pass rate and the total pass rate of multiple qualified master control nodes respectively to obtain multiple pass rate percentages; Multiple fusion weights are set for the operating parameters of multiple qualified master control nodes based on the multiple qualification rate ratios.

4. The system according to claim 1, characterized in that, The operating parameter generation module is also used for: Determine a first collaborative node among the plurality of collaborative nodes, and obtain a first collaborative parameter generator bound to the first collaborative node; The first collaborative parameter generator is constructed based on the sample master control node operation parameter set and the sample first collaborative node operation parameter set. The sample master control node operation parameter set and the sample first collaborative node operation parameter set are obtained according to the historical collaborative operation data between the first collaborative node and the master control node. The master control node's operating parameters are input into the first collaborative parameter generator to obtain the initial collaborative node operating parameters of the first collaborative node; Following the method of obtaining the initial collaborative node operating parameters of the first collaborative node, the initial collaborative node operating parameters of the remaining collaborative nodes are obtained, resulting in multiple sets of initial collaborative node operating parameters.

5. The system according to claim 1, characterized in that, The parameter joint verification module is also used for: Activate the production line simulation model of the target production line; Configure the production line simulation model based on the operating parameters of the master control node and the operating parameters of the multiple sets of initial collaborative nodes; Run the configured production line simulation model to obtain the predicted product qualification rate; Extract a preset pass rate from the information on products to be manufactured, compare the predicted product pass rate with the preset pass rate, and obtain a joint verification result. When the joint verification result indicates that the predicted product qualification rate is greater than or equal to the preset qualification rate, the multiple sets of initial collaborative node operating parameters are used as multiple sets of optimized collaborative node operating parameters.

6. The system according to claim 5, characterized in that, The parameter joint verification module is also used for: When the joint verification result indicates that the predicted product pass rate is less than the preset pass rate, multiple sets of initial collaborative node operating parameters will be added as forbidden combination parameters to the forbidden parameter list. The collaborative parameter generators of each collaborative node are called again to generate multiple new sets of collaborative node operating parameters while avoiding the taboo parameter list, thus obtaining multiple sets of updated collaborative node operating parameters. The production line simulation model is reconfigured and run according to multiple sets of updated collaborative node operating parameters to obtain the updated predicted product qualification rate. Compare the updated predicted product pass rate with the preset pass rate. When the updated predicted product pass rate is greater than or equal to the preset pass rate, use the multiple sets of updated collaborative node operating parameters as multiple sets of optimized collaborative node operating parameters. When the updated predicted product pass rate is less than the preset pass rate, the multiple sets of update collaborative node operating parameters are added to the taboo parameter list and iterated until multiple sets of optimized collaborative node operating parameters that meet the preset pass rate are obtained.

7. An industrial intelligent operation method based on cloud services, characterized in that, The method includes: Identify the target production line, establish the production equipment topology of the target production line, and determine the master control node and multiple cooperating nodes based on the production equipment topology; The master control node, the multiple collaborating nodes, and the cloud computing platform are connected to construct a cloud-based operation and configuration network; The cloud computing platform receives information about products to be manufactured, generates master control node operating parameters for the master control node based on the information about products to be manufactured, and generates multiple sets of initial collaborative node operating parameters for multiple collaborative nodes based on the master control node operating parameters. The process of generating master control node operating parameters based on the product information to be produced includes: The model of the product to be produced is extracted based on the product information to be produced. Based on the model of the product to be produced, historical production records are retrieved to obtain a set of production records for the same model of product. Each production record for the same model of product includes historical main control node operating parameters and historical batch product qualification rate. Extract the preset pass rate from the information of products to be produced, and filter the record set of products of the same model based on the preset pass rate and the historical batch product pass rate to obtain the operating parameters of multiple qualified master control nodes; Based on the historical batch product pass rates of the operating parameters of multiple qualified master control nodes, multiple fusion weights of the operating parameters of multiple qualified master control nodes are obtained; Based on the multiple fusion weights, the operating parameters of multiple qualified master control nodes are fused to obtain the master control node operating parameters of the master control node. Multiple sets of initial collaborative node operating parameters are jointly verified, and multiple sets of optimized collaborative node operating parameters are determined based on the joint verification results. The cloud-based operation configuration network configures the master control node's operating parameters on the master control node, and configures multiple sets of optimized collaborative node operating parameters on multiple collaborative nodes respectively.

Images