Multi-device cooperative linkage control method applied to industrial scene and related device

Abstract

The invention discloses a multi-equipment cooperative linkage control method applied to an industrial scene and related equipment, which can improve the cooperative efficiency of factory equipment in the industrial scene and reduce resource waste, thereby being beneficial to improving the production continuity. The method comprises the following steps: receiving operation state data and production task progress data of each factory device; on the basis of the operation state data and the production task progress data, predicting the operation of each factory device and the change trend of the production task in the future preset time; acquiring a communication protocol of each factory device; identifying a communication protocol through a built-in protocol feature library, and uniformly translating equipment information of each factory equipment into industrial universal intermediate protocol information; acquiring data indexes based on the intermediate protocol information, wherein the data indexes comprise production task emergency degree, equipment load rate and energy consumption cost parameters; and calculating and updating the priority score of each factory device in real time according to the data index and the dynamic collaborative algorithm.

Description

A method and related equipment for multi-device collaborative control in industrial scenarios Technical Field

[0001] This application relates to the field of industrial data processing technology, and in particular to a multi-device collaborative control method and related equipment applied in industrial scenarios. Background Technology

[0002] Against the backdrop of rapid development in industry and intelligent manufacturing, the demand for multi-device collaboration in factory production scenarios is becoming increasingly prominent. Currently, with the improvement of industrial automation, many factories deploy a large number of heterogeneous devices, such as CNC machine tools, robots, conveyor belts, and testing equipment. These devices come from different manufacturers, use different communication protocols, and have significant differences in operating status, task load, and energy consumption characteristics.

[0003] Currently, in the collaborative control of industrial equipment, due to the use of proprietary or non-standard communication protocols by different manufacturers, the data formats and interaction rules vary greatly, making it difficult for devices to communicate directly and share data. Although existing technologies can achieve partial protocol adaptation through gateways or protocol conversion modules, they are mostly static configurations, lacking the ability to dynamically identify and uniformly translate protocol characteristics, making it difficult to support the data consistency requirements for real-time collaboration of multiple devices. Moreover, current control methods are mostly based on static task allocation or passive response to the current state, and cannot dynamically predict the operating trends and task progress of equipment, thus causing problems such as low efficiency of equipment collaboration, large resource waste, and poor production continuity in current industrial scenarios. Summary of the Invention

[0004] To address the aforementioned technical issues, this application provides a multi-device collaborative control method and related equipment applicable to industrial scenarios.

[0005] The technical solution provided in this application is described below: The first aspect of this application provides a multi-device collaborative control method applied in industrial scenarios. The method includes: receiving operating status data and production task progress data of various factory equipment; predicting the changing trends of the operation and production tasks of the various factory equipment within a preset future timeframe based on the operating status data and the production task progress data; acquiring the communication protocols of the various factory equipment; identifying the communication protocols through a built-in protocol feature library and uniformly translating the equipment information of the various factory equipment into industrially common intermediate protocol information; acquiring data indicators based on the intermediate protocol information, the data indicators including production task urgency, equipment load rate, and energy consumption cost parameters; calculating and updating the priority scores of each factory equipment in real time according to the data indicators and a dynamic collaborative algorithm; predicting the failure risk of factory equipment based on the changing trends and calculating the failure probability; when the failure probability exceeds a preset threshold, allocating the tasks of the equipment at risk of failure to backup factory equipment according to the priority scores; acquiring feedback adjustment information from the backup factory equipment, and adjusting other factory equipment and production tasks according to the feedback adjustment information to form a closed-loop control.

[0006] Optionally, predicting the changing trends of the operation and production tasks of each factory equipment within a future preset time period based on the operation status data and the production task progress data includes: extracting target features from the operation status data and the production task progress data, wherein the target features include trend features of equipment operation and time features of production tasks; acquiring historical operation status data and historical production task data of the factory equipment; training a time series prediction model based on the historical operation status data and the historical production task data to obtain an industrial time series prediction model; and inputting the target features into the industrial time series prediction model to predict the changing trends of equipment operation status and production task progress within a future preset time period.

[0007] Optionally, the communication protocol is identified through a built-in protocol feature library, and the equipment information of each factory device is uniformly translated into industrially common intermediate protocol information. This includes: calling the built-in protocol feature library; comparing and matching the communication protocol of the factory device with various industrial protocol features in the built-in protocol feature library to determine the communication protocol type of each industrial device; based on the communication protocol type of each industrial device, parsing the original information data output by each industrial device and the logical relationships between the data, wherein the original information includes device ID, operating parameters, and status identifier; converting unstructured or protocol-specific information in the original information data into identifiable structured data; and translating the structured data into standardized information conforming to the industrially common intermediate protocol based on the standard specifications of the industrially common intermediate protocol.

[0008] Optionally, the priority scores of each factory equipment are calculated and updated in real time according to the data instructions and dynamic collaborative algorithm, including: dynamically assigning preset weights to data indicators based on production targets, the data indicators including production task urgency, equipment load rate, and energy consumption cost parameters; standardizing the data indicators of each factory equipment into indicator values ​​with unified dimensions; substituting the indicator values ​​into the dynamic collaborative algorithm and performing weighted calculations in combination with preset weights to obtain the initial priority scores of each industrial equipment, and synchronously updating the priority scores according to the real-time changes in equipment operating status and production task progress.

[0009] Optionally, based on the changing trend, the risk of factory equipment failure is predicted and the failure probability is calculated. When the failure probability exceeds a preset threshold, the tasks of the equipment at risk of failure are allocated to backup factory equipment according to the priority score. This includes: identifying potential failure risk points based on the changing trend of the factory equipment; locking the failure equipment based on the potential failure risk points; quantifying and calculating the failure probability of the failure equipment within a preset time period based on the historical failure data and current abnormal parameters of the failure equipment; when the failure probability exceeds the preset threshold, selecting backup equipment with high priority, load adaptability, and no failure risk based on the real-time updated priority scores of each factory equipment; and allocating the current production tasks undertaken by the failure equipment to the selected backup equipment according to the priority matching rules.

[0010] Optionally, obtaining feedback adjustment information from the backup factory equipment and adjusting other factory equipment and production tasks based on the feedback adjustment information to form closed-loop control includes: obtaining deviation data and manual adjustment instructions during the production execution process of the backup factory equipment; analyzing the causes of deviations based on the deviation data and manual adjustment instructions; generating adjustment strategies based on the causes of deviations; and adjusting other factory equipment and production tasks based on the adjustment strategies to form closed-loop control.

[0011] Optionally, after receiving the operating status data and production task progress data of each factory equipment, the method further includes: classifying the operating status data and the production task progress data according to each factory equipment to obtain classification results; sorting the classification results to obtain sorting results; and preprocessing the data in the sorting results to obtain preprocessed data.

[0012] The second aspect of this application provides a multi-device collaborative control device for industrial scenarios. The device includes: a receiving unit for receiving operating status data and production task progress data of various factory equipment; a prediction unit for predicting the changing trends of the operation and production tasks of each factory equipment within a preset future timeframe based on the operating status data and the production task progress data; a first acquisition unit for acquiring the communication protocols of each factory equipment; a translation unit for identifying the communication protocols through a built-in protocol feature library and uniformly translating the equipment information of each factory equipment into industrially common intermediate protocol information; a second acquisition unit for acquiring data indicators based on the intermediate protocol information, the data indicators including production task urgency, equipment load rate, and energy consumption cost parameters; an update unit for calculating and updating the priority scores of each factory equipment in real time according to the data indicators and a dynamic collaborative algorithm; an allocation unit for predicting the failure risk of factory equipment based on the changing trends and calculating the failure probability, and when the failure probability exceeds a preset threshold, allocating the tasks of the equipment at risk of failure to backup factory equipment according to the priority scores; and a third acquisition unit for acquiring feedback adjustment information from the backup factory equipment and adjusting other factory equipment and production tasks according to the feedback adjustment information to form a closed-loop control.

[0013] A third aspect of this application provides a multi-device collaborative control device for industrial scenarios. The device includes a processor, a memory, an input / output unit, and a bus. The processor is connected to the memory, the input / output unit, and the bus. The memory stores a program, and the processor calls the program to execute the method described in the first aspect and any one of the first aspects.

[0014] A fourth aspect of this application provides a computer-readable storage medium on which a program is stored, which, when executed on a computer, performs the method as described in the first aspect and any one of the first aspects.

[0015] As can be seen from the above technical solutions, this application has the following beneficial effects: 1. This application uses the built-in protocol feature library to identify the communication protocols of each device and translates the device information into a unified industrial common intermediate protocol, which can effectively solve the problem of data isolation caused by protocol differences between different devices and realize efficient data communication between devices in various factories.

[0016] 2. This application obtains production task urgency, equipment load rate, and energy consumption cost parameters based on intermediate protocols, and updates equipment priority scores in real time by combining dynamic collaborative algorithms. It can dynamically adjust scheduling strategies according to actual production needs, ensure that high-urgency tasks are prioritized, and balance equipment load and energy consumption costs to optimize resource allocation.

[0017] 3. This application predicts the trend of equipment operation and task changes, anticipates failure risks and calculates probabilities. When the probability exceeds the threshold, the failure risk equipment tasks are allocated to backup equipment according to priority scores to reduce downtime. Then, combined with feedback from backup equipment, other equipment and tasks are adjusted to form a closed-loop control, further ensuring the stability and continuity of the production process and improving production reliability.

[0018] 4. This application can improve the collaborative efficiency of factory equipment in industrial settings and reduce resource waste, thereby helping to improve production continuity. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 is a schematic diagram of one embodiment of the multi-device collaborative linkage control method of this application applied to an industrial scenario; Figure 2 is a schematic diagram of another embodiment of the multi-device collaborative linkage control method of this application applied to an industrial scenario; Figure 3 is a schematic diagram of another embodiment of the multi-device collaborative linkage control method of this application applied to an industrial scenario; Figure 4 is a schematic diagram of another embodiment of the multi-device collaborative linkage control method of this application applied to an industrial scenario; Figure 5 is a schematic diagram of another embodiment of the multi-device collaborative linkage control method of this application applied to an industrial scenario; Figure 6 is a schematic diagram of another embodiment of the multi-device collaborative linkage control method of this application applied to an industrial scenario; Figure 7 is a schematic diagram of one embodiment of the multi-device collaborative linkage control device of this application applied to an industrial scenario; Figure 8 is a schematic diagram of another embodiment of the multi-device collaborative linkage control device of this application applied to an industrial scenario. Detailed Implementation

[0021] In this embodiment, the execution entity of the method is not limited to a specific type of computing device, server, or control system. The method can be executed by any hardware, software, or hardware / software combination system capable of providing the necessary computing and data processing capabilities, such as a general-purpose computer, a distributed server cluster, a networked control unit, a virtualization processing platform, or a cloud computing environment.

[0022] The job event flow path construction method described in this embodiment can also be implemented through embedded programs, application software modules, or by controlling remote execution units through network communication interfaces. Regardless of whether the specific execution entity is a single device, multiple parallel collaborative processing units, or a scalable distributed processing system, this method can be operated according to the step sequence and logic described in the following embodiments.

[0023] The method of this application is applicable to any system capable of performing necessary computation and data processing operations, and the system is not limited to a specific type of computing device, server cluster, virtualization platform, network control unit, or cloud computing environment. Regardless of whether the executing entity is a single device, multiple collaborative processing units, or a distributed computing platform, the method of this application can be operated according to the step sequence and logic described in the embodiments.

[0024] Currently, in the collaborative control of industrial equipment, due to the use of proprietary or non-standard communication protocols by different manufacturers, the data formats and interaction rules vary greatly, making it difficult for devices to communicate directly and share data. Although existing technologies can achieve partial protocol adaptation through gateways or protocol conversion modules, they are mostly static configurations, lacking the ability to dynamically identify and uniformly translate protocol characteristics, making it difficult to support the data consistency requirements for real-time collaboration of multiple devices. Moreover, current control methods are mostly based on static task allocation or passive response to the current state, and cannot dynamically predict the operating trends and task progress of equipment, thus causing problems such as low efficiency of equipment collaboration, large resource waste, and poor production continuity in current industrial scenarios.

[0025] Based on this, this application provides a multi-device collaborative linkage control method and related equipment for industrial scenarios, which can improve the collaborative efficiency of factory equipment in industrial scenarios, reduce resource waste, and thus help improve production continuity.

[0026] Please refer to Figure 1. This application discloses a multi-device collaborative control method applied in an industrial scenario. The method includes: 101. Receiving operating status data and production task progress data of each factory device; 102. Predicting the changing trends of the operation and production tasks of each factory device within a preset time period based on the operating status data and the production task progress data; 103. Obtaining the communication protocols of each factory device; 104. Identifying the communication protocols through a built-in protocol feature library and uniformly translating the device information of each factory device into industrially common intermediate protocol information; 105. Obtaining data indicators based on the intermediate protocol information, including production task urgency, equipment load rate, and energy consumption cost parameters; 106. Calculating and updating the priority scores of each factory device in real time according to the data indicators and a dynamic collaborative algorithm; 107. Predicting the failure risk of factory devices based on the changing trends and calculating the failure probability. When the failure probability exceeds a preset threshold, allocating the tasks of the failure-risk devices to backup factory devices according to the priority scores; 108. Obtaining feedback adjustment information from the backup factory devices and adjusting other factory devices and production tasks according to the feedback adjustment information to form a closed-loop control.

[0027] In this embodiment, the system first receives operating status data and production task progress data of each factory device. Then, based on the operating status data and production task progress data, it predicts the changing trends of the operation of each factory device and production tasks within a preset time period. Next, it acquires the communication protocols of each factory device and identifies the communication protocols through a built-in protocol feature library. It then translates the device information of each factory device into industrially common intermediate protocol information. Based on the intermediate protocol information, it acquires data indicators, including production task urgency, equipment load rate, and energy consumption cost parameters. Based on the data indicators and dynamic collaborative algorithm, it calculates and updates the priority scores of each factory device in real time. Then, it predicts the failure risk of factory devices based on the changing trends and calculates the failure probability. When the failure probability exceeds a preset threshold, it allocates the tasks of the failure-risk devices to backup factory devices according to the priority scores. Finally, it acquires feedback adjustment information from the backup factory devices and adjusts other factory devices and production tasks according to the feedback adjustment information to form a closed-loop control.

[0028] In step 101, the operational status data and production task progress data of each factory device are first received. In an industrial setting, factories contain various types of equipment with different functions, such as processing equipment, conveying equipment, and testing equipment. These devices generate a large amount of real-time data reflecting their own status during operation, such as the spindle speed, temperature, and vibration frequency of processing equipment; the operating speed and load of conveying equipment; and the detection accuracy and operating time of testing equipment. Simultaneously, each device undertakes a specific production task, generating corresponding production task progress data, such as the number of completed parts, the remaining workload to the task target, and the current task completion percentage. To obtain the real-time status of each industrial device and production, it is necessary to centrally collect these dispersed operational status data and production task progress data from the devices themselves, using their built-in sensors, data acquisition modules, and the factory's industrial communication network, providing data support for subsequent analysis and control.

[0029] In step 102, based on the received operating status data and production task progress data, the changing trends of the operation of each factory equipment and production tasks within a preset time period are predicted. The preset time period can be flexibly set according to the factory's production plan, equipment operating cycle and the urgency of the production task, such as 1 hour, 4 hours or 1 production shift. During the forecasting process, the collected historical and real-time data are first preprocessed to remove outliers and noise. Then, data analysis models, such as time series analysis models or machine learning prediction models, are used in conjunction with the equipment's historical operating patterns. For example, after a certain type of processing equipment runs continuously for 3 hours, the temperature will show a slow upward trend, the load rate will increase by about 15% when the workload increases by 20%, and the pace of production tasks are considered. For example, based on the current task progress, if 50 products are completed per hour, the remaining 300 products will require another 6 hours to complete. This allows for the prediction of the direction of changes in the equipment's operating status within a preset timeframe. For instance, whether the equipment temperature will exceed the safety threshold, whether the operating speed will fluctuate, and the progress of production tasks are also predicted, such as whether they can be completed on time, and how the progress will change when the workload increases or decreases. This allows for the advance understanding of potential changes in equipment operation and production tasks.

[0030] After obtaining the trend prediction, step 103 involves acquiring the communication protocols of each factory's equipment. Since the equipment within a factory often comes from different manufacturers, each manufacturer uses its own communication protocols for data transmission and control. For example, some equipment uses Modbus, some Profinet, and others EtherNet / IP. These different communication protocols differ in data format, transmission rate, and command encoding. Therefore, it is necessary to obtain protocol information by consulting the equipment's technical specifications, communicating with the equipment manufacturers, or using industrial network scanning tools to detect the protocol type followed by the equipment during communication. This accurate acquisition of the communication protocol corresponding to each factory piece of equipment prepares for the subsequent unified translation of equipment data.

[0031] After obtaining the communication protocols of each device, in step 104, these communication protocols are identified through a built-in protocol feature library, and the device information of each factory device is uniformly translated into industrially common intermediate protocol information. It should be noted that the built-in protocol feature library is pre-built and stores feature parameters of mainstream industrial communication protocols on the market, such as data frame formats, start characters, verification methods, and function code definitions of different protocols. During the identification process, the features of each device's communication protocol obtained in step 103 are compared with the feature parameters in the built-in protocol feature library to accurately determine the type of communication protocol used by each device. Because the data formats of device information under different protocols are not uniform, they cannot be directly used for cross-device collaborative analysis and control. Therefore, after completing the protocol identification, it is necessary to convert the information originally presented by each device in its own protocol format, such as the encoding method of device operating parameters and the representation of task progress data, into a unified data format and encoding rules specified by the intermediate protocol, according to the specifications of the industrially common intermediate protocol. This allows the originally inconsistent device information to be transmitted, parsed, and used under the same standard, achieving interconnection and interoperability of device information.

[0032] After completing the unified translation from equipment information to intermediate protocol information, step 105 proceeds to obtain data indicators based on the intermediate protocol information. These data indicators include production task urgency, equipment load rate, and energy consumption cost parameters. After the translation operation in step 104, all equipment information has been converted into standard intermediate protocol information. At this point, key data indicators for collaborative control can be extracted from this standardized information. The urgency of production tasks is determined by considering the delivery deadline, the task's importance in the overall production plan, and the current progress. For example, if a batch of products needs to be delivered within 24 hours and only 30% has been completed, the urgency level of that task will be set to a higher level. Equipment load rate is calculated as the ratio of the equipment's current actual load to its rated load. For instance, if the rated load is 100 units / hour and the current actual processing is 80 units / hour, the load rate is 80%. This is further adjusted based on the equipment's operating time and historical load changes. Obtaining energy cost parameters requires statistical analysis of the equipment's electricity and gas consumption per unit time, combined with the factory's energy price, to calculate the unit energy cost of equipment operation and the total energy cost required to complete the current production task. After obtaining the above data, step 105 is executed.

[0033] After acquiring the data metrics in step 105, step 106 is executed. Based on these data metrics and the dynamic collaboration algorithm, the priority score of each factory's equipment is calculated and updated in real time. The dynamic collaboration algorithm pre-sets different weights for production task urgency, equipment load rate, and energy consumption cost parameters. The weights can be adjusted according to the factory's production goals at different times. For example, when the factory prioritizes ensuring the delivery of urgent orders, the weight of production task urgency will increase; when the factory focuses on equipment operation and maintenance and energy conservation, the weights of equipment load rate and energy consumption cost parameters will increase accordingly. When calculating the priority score, each data metric is first standardized to eliminate the influence of different dimensions. Then, the standardized metric values ​​are weighted and summed according to the set weights to obtain the initial priority score for each piece of equipment. Meanwhile, since the operating status of equipment and the progress of production tasks change in real time, such as a sudden increase in the load rate of a certain piece of equipment or an increase in the urgency of a certain production task due to changes in customer demand, it is necessary to continuously update the priority score of the equipment based on these real-time changing data through dynamic collaborative algorithms. This ensures that the priority score of each piece of equipment can accurately reflect the current production needs and equipment status, providing a dynamic priority basis for subsequent task allocation and fault response.

[0034] After updating the equipment priority score in real time in step 106, step 107 is executed. Based on the predicted trend, the risk of equipment failure in the factory is predicted and the failure probability is calculated. When the failure probability exceeds the preset threshold, the task of the equipment at risk of failure is assigned to the backup factory equipment according to the priority score.

[0035] When predicting failure risks, the system combines the predicted trends in equipment operation, such as predicting that the temperature of a certain piece of equipment will continue to rise within the next two hours and tend to exceed the safety threshold. It also combines the equipment's historical failure data, such as the fact that in the past year, the number of times the equipment failed when the temperature exceeded the safety threshold by 10% reached 80%, as well as information such as the equipment's aging level and maintenance records. Through failure probability calculation models, such as fault tree analysis models and Bayesian probability models, the system calculates the specific probability value of the equipment failing within a preset time in the future.

[0036] It should be noted that the preset threshold is set based on the degree of impact of equipment failure on production. For example, for critical production equipment, since its failure would cause the entire production chain to be interrupted, the preset threshold would be set lower, such as 15%. For auxiliary equipment, the preset threshold can be set higher, such as 30%. When the calculated failure probability exceeds the preset threshold, it indicates that the equipment has a high failure risk. At this time, the task transfer mechanism needs to be activated: that is, based on the real-time updated equipment priority score, the backup factory equipment with higher priority and lower current load rate, and capable of undertaking the tasks of the equipment with failure risk, is selected first. The unfinished production tasks on the equipment with failure risk, including the specific parameters and schedule requirements of the tasks, are fully allocated to the backup equipment to avoid production interruption due to equipment failure.

[0037] In step 108, feedback adjustment information from standby factory equipment is acquired, and adjustments are made to other factory equipment and production tasks based on this feedback adjustment information to form a closed-loop control. After the standby factory equipment takes over a task, it generates new operating status data and task execution data during operation. This data constitutes the feedback adjustment information. For example, after taking over a task, the load rate of the standby equipment increases, exceeding its optimal operating load range, or the task execution speed is slower than expected, failing to complete the task as originally planned. After acquiring this feedback adjustment information in real time through the industrial communication network, it is necessary to combine the entire factory's production process and equipment coordination requirements to make targeted adjustments to other related factory equipment and production tasks. For example, if the standby equipment is overloaded, some of its non-core tasks can be transferred to other equipment with lower current loads; if the standby equipment's task execution speed is slow, the operating rhythm of subsequent connecting equipment can be appropriately adjusted, such as slowing down the speed at which conveyor equipment delivers raw materials to it to avoid raw material accumulation. At the same time, the time nodes of the overall production task can be adjusted to ensure smooth connection of tasks in each stage. Through such feedback and adjustments, the equipment collaborative control forms a complete closed loop, which not only addresses the risk of failure but also ensures the stable and efficient operation of the entire factory production process. Furthermore, it can continuously optimize the control strategy based on the actual operating conditions to adapt to various changes in the production process.

[0038] Referring to Figure 2, according to some embodiments of the present invention, step 102, which predicts the changing trends of the operation and production tasks of each factory equipment within a future preset time period based on the operating status data and the production task progress data, may specifically include, but is not limited to, the following: 201. Extracting target features from the operating status data and the production task progress data, wherein the target features include trend features of equipment operation and time features of production tasks; 202. Obtaining historical operating status data and historical production task data of the factory equipment; 203. Training a time-series prediction model based on the historical operating status data and the historical production task data to obtain an industrial time-series prediction model; 204. Inputting the target features into the industrial time-series prediction model to predict the changing trends of equipment operating status and production task progress within a future preset time period.

[0039] In this embodiment, target features are first extracted from operational status data and production task progress data. These target features explicitly include trend characteristics of equipment operation and time characteristics of production tasks. After receiving the operational status data and production task progress data from each factory, it is necessary to filter and extract key features with practical value for prediction from the massive amount of raw data. The trend characteristics of equipment operation should focus on data dimensions that reflect the patterns of equipment status changes, such as the temperature fluctuation range of a processing machine within one hour, the stability of the spindle speed, and the frequency of peak load rates. The time characteristics of production tasks are extracted based on the correlation between task progress and time, such as the ratio of remaining time to remaining workload, task completion efficiency per unit time, and the time difference between the task deadline and the current time. Through this feature extraction, the raw data is transformed into more representative "data labels."

[0040] Next, historical operating status data and historical production task data of the factory equipment are acquired. Since trend prediction needs to be based on the long-term operating patterns of the equipment and the historical progress patterns of production tasks, relying solely on the currently received real-time data cannot fully capture potential change patterns. For example, a certain piece of equipment may exhibit a periodic pattern of "a slight decrease in load rate every 72 hours of operation." If only 12 hours of real-time data are used, this pattern cannot be discovered at all, leading to deviations in the prediction results. Therefore, it is necessary to retrieve historical data from the factory's historical database that matches the current equipment type and production task type. For historical operating status data, it is necessary to cover the equipment's operating records under different production scenarios, such as temperature, speed, and fault records under different scenarios such as full-load production, half-load production, and restart after maintenance. At the same time, it is necessary to ensure that the time span of the data is long enough, usually covering at least 3-6 months of complete operating cycle to include various states such as normal operation, minor faults, and maintenance.

[0041] For historical production task data, it is necessary to collect production task records for the same or similar products, including the initial workload, completion cycle, intermediate schedule adjustments, and final results of different batches of tasks. Particular attention should be paid to special cases in historical tasks involving schedule delays or task adjustments, as this data can help subsequent models learn predictive logic to handle complex scenarios. Furthermore, after acquiring historical data, it is necessary to preprocess it to ensure its accuracy and completeness, avoiding data quality issues that could negatively impact subsequent model training performance.

[0042] After acquiring and preprocessing historical data, a time-series prediction model is trained based on historical operational status data and historical production task data to obtain an industrial time-series prediction model. The core advantage of the time-series prediction model lies in its ability to handle data sequences that change over time, capturing the dependencies and patterns of change in data over time, which highly aligns with the characteristics of factory equipment operating status and production task progress. During training, the preprocessed historical data is first divided into training and validation sets. Typically, 70%-80% of the historical data is used as the training set for learning model parameters; the remaining 20%-30% is used as the validation set to test the model's predictive performance and adjust the parameters. Next, a time-series prediction model architecture suitable for the industrial scenario is selected. Common models include ARIMA, LSTM, and Prophet, among others, without specific limitations here. During training, trend features from historical operational data, such as historical temperature change trends and rotational speed stability, and time features from historical production task data, such as historical task completion rates and time difference features, are used as input variables for the model. Actual equipment status changes and production task progress results from historical data are used as output labels for the model. The model iterates to learn the mapping relationship between input features and output results. During training, the model's prediction error is continuously monitored using a validation set. If the error is too large, the model's hyperparameters are adjusted until the model's prediction accuracy on the validation set meets industrial production requirements. The trained model at this point is a viable industrial time-series prediction model for real-world scenarios.

[0043] After training the industrial time-series prediction model, the extracted target features are input into the model to predict the changing trends of equipment operating status and production task progress within a preset time period. The "preset time" here needs to be determined based on the actual production needs of the factory and is not specifically limited here. For example, for a fast-paced production line, the preset time can be set to 1 hour; for heavy machinery processing tasks with longer production cycles, the preset time can be set to 8 hours.

[0044] During prediction, the extracted real-time target features are first standardized according to the input format used during the training of the industrial time series prediction model. Then, the standardized target features are input into the model. The model analyzes and calculates the real-time features based on the historical patterns learned during the training phase. For example, if the model learns during training that "when the equipment temperature rises by 5°C every 30 minutes and the load rate frequently exceeds 80%, the temperature will continue to rise by 3-4°C in the next hour, and the load rate may reach 90%", then when the corresponding real-time features are input, the model will output a prediction of the operating status change trend of "the equipment temperature will rise by 3.5°C and the load rate will rise to 89% in the next hour".

[0045] For production tasks, if the model learns the pattern that "when there are 3 hours left in the task and the completion rate per unit time is 40 pieces, if the remaining workload is 150 pieces, 120 pieces can be completed in the next 3 hours, with a risk of 30 pieces being delayed," it will output a task progress trend prediction: "The production task will complete 120 pieces in the next 3 hours, with a 10% delay." Through such predictions, the factory can anticipate potential equipment operation problems and production task risks, providing accurate decision-making basis for subsequent fault prediction and task allocation, further improving the effectiveness of multi-equipment collaborative control.

[0046] Referring to Figure 3, according to some embodiments of the present invention, step 104 identifies the communication protocol through a built-in protocol feature library and uniformly translates the equipment information of each factory device into industrially common intermediate protocol information. Specifically, this may include, but is not limited to, the following: 301. Calling the built-in protocol feature library; 302. Comparing and matching the communication protocol of the factory device with various industrial protocol features in the built-in protocol feature library to determine the communication protocol type of each industrial device; 303. Based on the communication protocol type of each industrial device, parsing the original information data output by each industrial device and the logical relationships between the data, wherein the original information includes device ID, operating parameters, and status identifier; 304. Converting unstructured or protocol-specific information in the original information data into identifiable structured data; 305. Based on the standard specifications of the industrially common intermediate protocol, translating the structured data into standardized information conforming to the industrially common intermediate protocol.

[0047] In this embodiment, the built-in protocol feature library is first invoked. In industrial production environments, different brands and types of factory equipment often employ differentiated communication protocols. These protocols differ significantly in their underlying logic, data formats, and instruction rules. To achieve unified management and control of various types of equipment, it is necessary to first identify the protocol type followed by each device. The built-in protocol feature library is the core basis for achieving this goal. This feature library is a pre-built database by technicians based on mainstream industrial communication protocols such as Modbus, Profinet, EtherNet / IP, and DeviceNet. It stores the core feature parameters of various protocols, including but not limited to the protocol's data frame structure, instruction encoding rules, data transmission rate range, and default communication port configuration. When it is necessary to identify the device protocol, the system retrieves this feature data from the database through a preset program interface.

[0048] After calling the built-in protocol feature library, the communication protocols of the factory equipment are compared and matched with various industrial protocol features in the built-in protocol feature library to determine the communication protocol type of each industrial device. In this step, the system first collects protocol data fragments generated by the target device during communication through the industrial communication network, such as status feedback data packets sent by the device to the network and response data frames when receiving control commands. Then, the collected protocol data fragments are broken down into specific feature items, such as whether the starting character of the data frame is a specific byte, whether the value range of the function code conforms to a certain protocol specification, and whether the verification method is CRC check or LRC check. Next, these decomposed device protocol feature items are compared item by item with the standard features of various protocols in the built-in protocol feature library. For example, if the starting character of a device's protocol data frame is 0x01, the function code range is between 0x01 and 0x06, the verification method is CRC16, and the data field length is fixed at 8 bytes, these features completely match the standard features of the Modbus RTU protocol in the feature library, then it can be preliminarily determined that the device uses the Modbus RTU protocol. If there are partial feature matches but not complete consistency, the system will further analyze the differences, combine auxiliary information such as the device's brand, model, and production batch, eliminate interference factors, and determine the final protocol type to ensure that the communication protocol of each device can be identified.

[0049] After determining the communication protocol type of each industrial device, the system parses the raw information data output by each device and the logical relationships between the data based on the defined protocol type. The raw information includes device ID, operating parameters, and status identifiers. Since different protocols encapsulate data differently, the corresponding parsing rules can only be used to extract valid information after the protocol type is clearly defined. This application takes a processing device using the Profinet protocol as an example. Its output raw information data is transmitted in the form of "messages." The system extracts the device ID from the messages according to the Profinet protocol's message parsing rules. This device ID is a unique identifier that distinguishes different devices and is usually composed of a fixed code set at the factory, used to accurately locate the target device in a multi-device environment. Then, the system extracts the operating parameters, which are core data reflecting the real-time operating status of the equipment, such as the spindle speed, cutting temperature, and feed rate of the processing equipment, and the conveyor belt speed and load capacity of the conveyor equipment. The system decodes these parameters from the raw data according to the data format specified by the protocol. Simultaneously, the system also parses status identifiers, such as the device's "run / stop" status and "fault / normal" status.

[0050] During the parsing process, the system also sorts out the logical relationships between the data. For example, when the equipment status is marked as "fault", the corresponding operating parameter "cutting temperature" will be significantly higher than the value range during normal operation. This logical association can provide a basis for subsequent judgment on whether the equipment status is abnormal, ensuring that the parsed original information is not only complete, but also reflects the inherent laws of equipment operation.

[0051] After parsing the raw information data, unstructured or protocol-specific information is transformed into recognizable structured data. A large amount of unstructured or protocol-specific data exists in the raw information output by industrial equipment, making it difficult to directly use for cross-device collaborative analysis and unified control. For example, a certain testing equipment uses a proprietary protocol, and its output "test results" information is presented in free text format, such as "There are two scratches with a diameter of 0.5mm on the product surface, which meets the secondary standard." This type of text data has no fixed field divisions and is considered unstructured data. Another example is that a device's "runtime" data is stored in BCD code format, which is only applicable to the parsing of the protocol to which the device belongs and is protocol-specific data.

[0052] At this point, the system will employ corresponding conversion strategies for different types of unstructured or proprietary format data: For unstructured text data, key information will be extracted using natural language processing technology, transforming "There are two scratches with a diameter of 0.5mm on the product surface, which meets the Level 2 standard" into structured data containing fixed fields such as "Number of defects: 2", "Defect type: scratch", "Defect size: 0.5mm", and "Acceptance level: Level 2".

[0053] For protocol-specific format data, such as "runtime" in BCD code format, a format conversion algorithm is used to convert it into a universal decimal number format, and fields such as "unit: hours" are added to form structured data such as "runtime: 1200 hours". After conversion, the raw information of all devices will be presented in a unified structured form, with each data item having clear field definitions, data types, and units.

[0054] Finally, based on the standard specifications of the industrial common intermediate protocol, the structured data is translated into standardized information conforming to the industrial common intermediate protocol. The industrial common intermediate protocol is a unified data interaction standard developed to solve the differences in protocols of different devices. It has clear provisions on the field names, data types, value ranges, and transmission formats of data. For example, in the intermediate protocol, the "Device ID" field is uniformly named "Device_ID", the data type is a string, and the length is fixed at 10 characters; the "Spindle Speed" field is uniformly named "Spindle_Speed", the data type is an integer, and the unit is uniformly "r / min"; the "Device Status" field is uniformly named "Device_Status", with "Running" indicating running, "Stopped" indicating stopping, and "Faulty" indicating fault, and must be associated with the fault code field "Fault_Code".

[0055] During the translation process, the system first maps the obtained structured data to the standard fields of the intermediate protocol. For example, it maps the "machine tool number" in the structured data of a device to the "Device_ID" in the intermediate protocol, and the "spindle speed per minute" to "Spindle_Speed". Then, it adjusts the data type and unit requirements according to the intermediate protocol. For example, it converts the unit "degrees Celsius" in "temperature: 30.5 degrees Celsius" in the structured data of a device to "℃" as specified in the intermediate protocol, and retains the data type as a floating-point number. At the same time, it ensures that the value range of the data conforms to the intermediate protocol specification. If the "load rate: 120%" in the structured data of a device exceeds the "0%-100%" range specified in the intermediate protocol, the system will mark the data as an "outlier" and add an exception description as required by the protocol.

[0056] After mapping and adjustment, the system encapsulates the data according to the transmission format specified by the intermediate protocol, such as JSON or XML, ultimately forming standardized information that conforms to the common industrial intermediate protocol. Through this processing, equipment data that originally varied in format due to protocol differences is uniformly converted into a standard format, enabling free transmission and parsing between different devices and systems. This provides data support for subsequent collaborative control operations based on unified data, such as production trend prediction, equipment priority calculation, and fault risk prediction.

[0057] Referring to Figure 4, according to some embodiments of the present invention, step 106, which calculates and updates the priority scores of each factory equipment in real time according to the data instructions and dynamic collaborative algorithm, may specifically include, but is not limited to, the following: 401. Dynamically assigning preset weights to data indicators based on production targets, wherein the data indicators include production task urgency, equipment load rate, and energy consumption cost parameters; 402. Standardizing the data indicators of each factory equipment into indicator values ​​with uniform dimensions; 403. Substituting the indicator values ​​into the dynamic collaborative algorithm and performing weighted calculations in combination with preset weights to obtain the initial priority scores of each industrial equipment, and synchronously updating the priority scores according to the real-time changes in equipment operating status and production task progress.

[0058] In this embodiment, preset weights are first dynamically assigned to data indicators based on production goals. These data indicators include production task urgency, equipment load rate, and energy consumption cost parameters. Production goals in industrial scenarios are not fixed and are flexibly adjusted based on order demand, factory operation strategies, and changes in the external environment. Under different production goals, the impact of each data indicator on equipment priority varies significantly. Therefore, dynamic weight allocation is necessary to match current core needs. For example, when a factory receives an urgent order and the core production goal is "delivering the urgent task on time," the importance of the production task urgency increases significantly. In this case, a higher preset weight is assigned, such as 50%. Simultaneously, to prevent equipment failure due to overload and impact on delivery, the equipment load rate still retains a certain weight, such as 30%, while the weight of the energy consumption cost parameter is temporarily reduced, such as 20%.

[0059] Conversely, if the factory is in a normal production phase, and the core objective is to "balance equipment load and energy costs to achieve stable and efficient production," then the weighting will be adjusted. The weight of equipment load rate will be increased to 40%, the weight of energy cost parameters will be increased to 35%, and the weight of production task urgency will be appropriately reduced to 25% based on the urgency of the orders. In special circumstances where energy supply is tight and energy consumption needs to be strictly controlled, the weight of energy cost parameters may even become the highest, thus ensuring that the weighting is always highly aligned with the current production goals and laying a reasonable weighting foundation for subsequent priority calculations.

[0060] After weighting, the data indicators of each factory's equipment are standardized into numerical values ​​with uniform dimensions. Since the original data dimensions for production task urgency, equipment load rate, and energy cost parameters are completely different, directly using them for calculations will lead to biased results and fail to accurately reflect the actual impact of each indicator. For example, the original data for production task urgency may be presented as "remaining delivery time (hours)," with one piece of equipment showing "5 hours" and another "10 hours"; the original data for equipment load rate may be presented as "percentage (%)," with one piece of equipment showing "60%" and another "80%"; and the original data for energy cost parameters may be presented as "yuan / hour," with one piece of equipment showing "120 yuan / hour" and another "180 yuan / hour."

[0061] These data with different dimensions cannot be directly compared or weighted, so standardization is needed to eliminate the differences in dimensions. Standardization methods include Min-Max standardization. Taking Min-Max standardization as an example, the range of values ​​for each indicator is first determined. For example, the remaining delivery time range for the urgency of the production task is "2-12 hours", the equipment load rate range is "30%-90%", and the energy consumption cost parameter range is "80-200 yuan / hour". Then, the original indicator data of each device is converted into a uniform dimension value between 0 and 1 by the calculation formula: (Original data - Minimum indicator value) / (Maximum indicator value - Minimum indicator value). For example, the standardized urgency value of equipment with a remaining delivery time of 5 hours is (5-2) / (12-2)=0.3; the standardized value of equipment with a load rate of 60% is (60-30) / (90-30)=0.5; and the standardized value of equipment with an energy cost of 120 yuan / hour is (120-80) / (200-80)≈0.33. Through such processing, the data of different indicators have a basis for comparison and calculation.

[0062] After standardization is completed, the standardized index values ​​are substituted into the dynamic collaborative algorithm, and weighted calculation is performed in combination with the determined preset weights to obtain the initial priority score of each industrial device. The priority score is then updated synchronously according to the real-time changes in the device's operating status and production task progress.

[0063] First, the initial priority score is calculated. The dynamic collaborative algorithm calculates the score for each of the three indicators separately according to the formula "standardized value of each indicator × corresponding weight", and then sums the results to obtain the initial score. Taking a certain device as an example, if its standardized value for production task urgency is 0.8 (corresponding to a weight of 50%), its standardized value for equipment load rate is 0.4 (corresponding to a weight of 30%), and its standardized value for energy cost parameter is 0.6 (corresponding to a weight of 20%), then the initial priority score is 0.8×0.5 + 0.4×0.3 + 0.6×0.2 = 0.4 + 0.12 + 0.12 = 0.64. The initial score for all devices can be obtained through the same calculation method. The higher the score, the higher the priority of the device under the current production target.

[0064] However, in industrial production, equipment operating status and production task progress change in real time. For example, a piece of equipment may initially have a load rate of 60% (standardized 0.5), but after one hour of operation, the load rate may rise to 80% (standardized 0.8) due to increased workload. Similarly, an urgent task may initially have a remaining delivery time of 5 hours (standardized 0.3), but due to delays in preceding steps, the remaining time may be shortened to 3 hours (standardized 0.1). These changes directly affect the indicator values. The dynamic collaborative algorithm captures these data changes in real time, re-standardizes them, and combines them with currently applicable preset weights. That is, if the production target remains unchanged, the weights remain the same; if the production target is adjusted, the weights are updated synchronously, and a weighted calculation is performed again to obtain the updated priority score.

[0065] For example, for the equipment with increased load rate mentioned above, if other indicators remain unchanged, the updated score will become 0.8×0.5 +0.8×0.3 + 0.6×0.2 = 0.4 + 0.24 + 0.12 = 0.76, and the priority will be increased accordingly. This ensures that the priority score is always synchronized with the actual production situation, providing real-time and accurate decision support for subsequent collaborative control links such as task allocation and fault response.

[0066] Referring to Figure 5, according to some embodiments of the present invention, step 107, which involves predicting the risk of factory equipment failure and calculating the failure probability based on the changing trend, and when the failure probability exceeds a preset threshold, allocating the tasks of the equipment at risk of failure to backup factory equipment according to the priority score, may specifically include, but is not limited to, the following: 501. Identifying potential failure risk points based on the changing trend of the factory equipment; 502. Locking the failure equipment based on the potential failure risk points; 503. Quantitatively calculating the failure probability of the failure equipment within a preset time period based on the historical failure data and current abnormal parameters of the failure equipment; 504. When the failure probability exceeds the preset threshold, selecting backup equipment with high priority, load adaptability, and no failure risk based on the real-time updated priority scores of each factory equipment; 505. Allocating the current production tasks undertaken by the failure equipment to the selected backup equipment according to the priority matching rules.

[0067] In this embodiment, potential failure risk points are first identified based on the changing trends of factory equipment. Previously, the changing trends of equipment operation and production tasks within a preset future timeframe were predicted; these trend data contain potential factors that could lead to equipment failure.

[0068] For example, the predicted trend of a certain processing equipment shows that its spindle temperature will rise from the normal 45℃ to 65℃ (exceeding the equipment's safety threshold of 60℃) within the next 2 hours, while the vibration frequency will climb from the normal 0.2mm / s to 0.5mm / s. According to the equipment operation manual, abnormal increases in temperature and vibration frequency are often precursors to spindle wear and bearing aging. Another example is the predicted trend of a certain conveyor equipment, where the fluctuation range of the operating speed increases from ±2% to ±8%, and the load rate suddenly rises by 15% without an increase in workload. This may mean that there is a risk of jamming in the equipment's transmission system.

[0069] By analyzing such abnormal trend data, combined with the structural principles and common failure modes of the equipment, we can accurately pinpoint the potential risk points for each piece of equipment that may fail, such as the "risk point of abnormal increase in spindle temperature" and the "risk point of excessive bearing vibration" for processing equipment, and the "risk point of transmission system jamming" for conveying equipment.

[0070] After identifying potential fault risks, the faulty equipment is located based on these identified risks. Since different equipment has unique correlations regarding potential fault risks—that is, a specific risk point corresponds only to a specific piece of equipment—for example, a "spindle temperature abnormal rise risk point" only applies to machining equipment with a spindle structure, and a "battery voltage sudden drop risk point" only applies to mobile detection equipment that relies on battery power, the equipment with potential faults can be directly located through the correspondence between risk points and equipment.

[0071] After identifying the faulty equipment, its probability of failure within a preset timeframe is calculated based on historical fault data and current abnormal parameters. First, the historical fault database of the faulty equipment is retrieved. This database records information such as the time of past failures, fault type, abnormal parameter values ​​before the failure, and fault repair status. Next, the specific values ​​of the current abnormal parameters of the faulty equipment are collected. Then, using a fault probability quantification model, historical fault patterns are combined with the intensity of current abnormal parameters to calculate the probability of the faulty equipment failing within the next 4 hours.

[0072] When the calculated failure probability exceeds a preset threshold, backup equipment with high priority, load adaptability, and no failure risk is selected based on the real-time updated priority scores of equipment in each factory. First, the preset threshold setting needs to be combined with the importance of the equipment in the production process. For example, hydraulic forming equipment is a core piece of equipment in a critical production link, and its failure may cause the entire production line to stop. Therefore, the preset threshold is set at 50%. However, the current failure probability has far exceeded this threshold, and backup equipment needs to be deployed immediately.

[0073] At this point, the real-time updated priority scores of each device are retrieved, and devices with the highest priority rankings are prioritized for selection. Priority scores are related to the urgency of the production task and equipment energy efficiency; higher priority devices mean they can better guarantee production targets. Next, the load adaptability of high-priority devices is assessed. For example, if a hydraulic forming machine is currently at 75% load and is tasked with processing 100 parts per hour, then devices with a current load rate below 50% and a rated processing capacity of at least 100 parts per hour should be selected to prevent backup equipment from malfunctioning due to excessive load. Finally, based on the analysis results, devices with potential failure risks are excluded, and devices with no failure risk are ultimately selected as backup equipment.

[0074] Once the backup equipment is identified, the production tasks currently undertaken by the faulty equipment are assigned to the selected backup equipment according to the priority matching rules. Subsequently, based on the priority matching rules, the backup equipment takes priority in accepting high-priority tasks. At the same time, the allocation is carried out in combination with the backup equipment's capacity and time window. The processing parameters, quality standards, delivery deadlines and other information of the tasks are synchronized to the backup equipment to ensure that the backup equipment can accurately accept and efficiently complete the tasks, and avoid production delays or quality problems caused by improper task allocation.

[0075] Referring to Figure 6, according to some embodiments of the present invention, in step 108, feedback adjustment information of the standby factory equipment is obtained, and other factory equipment and production tasks are adjusted according to the feedback adjustment information to form closed-loop control. Specifically, this may include, but is not limited to, the following: 601. Obtaining deviation data and manual adjustment instructions during the production execution process of the standby factory equipment; 602. Analyzing the causes of deviations based on the deviation data and manual adjustment instructions; 603. Generating an adjustment strategy according to the causes of deviations; 604. Adjusting other factory equipment and production tasks according to the adjustment strategy to form closed-loop control.

[0076] After the task of the equipment at risk of failure is assigned to the standby plant equipment, deviation data and manual adjustment instructions during the production execution process of the standby plant equipment are obtained. After the standby equipment takes on a new task, the actual production execution will often differ from the preset production target or standard parameters, and these differences will be presented in the form of deviation data.

[0077] After acquiring the data and instructions, the causes of the deviations are analyzed based on the deviation data and manual adjustment instructions. During the analysis, the collected deviation data is first categorized and organized, and combined with the problem direction indicated by the manual adjustment instructions, the causes are investigated from multiple angles to ensure that the root cause of the deviation is found comprehensively and accurately.

[0078] After identifying the causes of the deviation, adjustment strategies are generated based on these causes. The generation of these adjustment strategies must closely align with the causes of the deviation, ensuring they are targeted and feasible. If the intervention measures proposed in the manual adjustment instructions are verified to be effective, they will also be integrated into the adjustment strategy, forming a systematic and comprehensive adjustment plan to ensure that the deviation problem can be fundamentally resolved.

[0079] Finally, adjustments are made to other factory equipment and production tasks based on the generated adjustment strategy to form a closed-loop control. Because the equipment and production tasks within the factory are interconnected and mutually influential, deviations in standby equipment production and adjustment strategies not only affect the equipment itself but may also have a chain reaction on upstream and downstream related equipment and the overall production task. Through this systematic adjustment of other equipment and production tasks, not only is the deviation problem of standby equipment resolved, but the operation of the entire production system is also coordinated, forming a complete closed-loop control from deviation detection, cause analysis, strategy generation to system adjustment, ensuring the continuous, stable, and efficient operation of factory production.

[0080] Please refer to Figure 7. A second aspect of this application provides a multi-device collaborative control device applied in industrial scenarios. The device includes: a receiving unit 701 for receiving operating status data and production task progress data of various factory equipment; a prediction unit 702 for predicting the changing trends of the operation and production tasks of the various factory equipment within a preset future timeframe based on the operating status data and the production task progress data; a first acquisition unit 703 for acquiring the communication protocols of the various factory equipment; a translation unit 704 for identifying the communication protocols through a built-in protocol feature library and uniformly translating the equipment information of the various factory equipment into industrially common intermediate protocol information; and a second acquisition unit 705. The system acquires data indicators based on the intermediate protocol information, including production task urgency, equipment load rate, and energy consumption cost parameters; an update unit 706 is used to calculate and update the priority score of each factory equipment in real time based on the data indicators and dynamic collaborative algorithm; an allocation unit 707 is used to predict the failure risk of factory equipment based on the changing trend and calculate the failure probability. When the failure probability exceeds a preset threshold, the task of the equipment at failure risk is allocated to the backup factory equipment according to the priority score; and a third acquisition unit 708 is used to acquire the feedback adjustment information of the backup factory equipment and adjust other factory equipment and production tasks according to the feedback adjustment information to form a closed-loop control.

[0081] Referring to Figure 8, this application also provides a ship offline network security response device based on edge computing. The device includes: a processor 801, a storage unit 802, an input / output unit 803, and a bus 804. The processor 801 is connected to the storage unit 802, the input / output unit 803, and the bus 804. The storage unit 802 stores a program, and the processor 801 calls the program to execute any of the methods described above.

[0082] This application also relates to a computer-readable storage medium on which a program is stored, which, when run on a computer, causes the computer to perform any of the methods described above.

[0083] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0085] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0086] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0087] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A multi-device collaborative control method applied in industrial scenarios, characterized in that, The method includes: receiving operational status data and production task progress data of various factory equipment; predicting the changing trends of the operation and production tasks of the various factory equipment within a preset time period based on the operational status data and the production task progress data; acquiring the communication protocols of the various factory equipment; identifying the communication protocols through a built-in protocol feature library, and uniformly translating the equipment information of the various factory equipment into industrially common intermediate protocol information; acquiring data indicators based on the intermediate protocol information, the data indicators including production task urgency, equipment load rate, and energy consumption cost parameters; calculating and updating the priority score of each factory equipment in real time according to the data indicators and a dynamic collaborative algorithm; predicting the failure risk of factory equipment and calculating the failure probability according to the changing trends, and when the failure probability exceeds a preset threshold, allocating the tasks of the equipment with failure risk to backup factory equipment according to the priority score; acquiring feedback adjustment information from the backup factory equipment, and adjusting other factory equipment and production tasks according to the feedback adjustment information to form a closed-loop control.

2. The multi-device collaborative control method for industrial scenarios according to claim 1, characterized in that, Predicting the changing trends of the operation and production tasks of each factory equipment within a future preset time period based on the operational status data and the production task progress data includes: extracting target features from the operational status data and the production task progress data, the target features including trend features of equipment operation and time features of production tasks; acquiring historical operational status data and historical production task data of the factory equipment; training a time series prediction model based on the historical operational status data and historical production task data to obtain an industrial time series prediction model; and inputting the target features into the industrial time series prediction model to predict the changing trends of equipment operational status and production task progress within a future preset time period.

3. The multi-device collaborative control method for industrial scenarios according to claim 1, characterized in that, The communication protocol is identified through a built-in protocol feature library, and the equipment information of each factory device is uniformly translated into industrially common intermediate protocol information. This includes: calling the built-in protocol feature library; comparing and matching the communication protocol of the factory devices with various industrial protocol features in the built-in protocol feature library to determine the communication protocol type of each industrial device; based on the communication protocol type of each industrial device, parsing the original information data output by each industrial device and the logical relationships between the data, wherein the original information includes device ID, operating parameters, and status identifier; converting unstructured or protocol-specific information in the original information data into recognizable structured data; and translating the structured data into standardized information conforming to the industrially common intermediate protocol based on the standard specifications of the industrially common intermediate protocol.

4. The multi-device collaborative control method for industrial scenarios according to claim 1, characterized in that, The priority scores of each factory equipment are calculated and updated in real time according to the data instructions and dynamic collaborative algorithm, including: dynamically assigning preset weights to data indicators based on production targets, the data indicators including production task urgency, equipment load rate and energy consumption cost parameters; standardizing the data indicators of each factory equipment into indicator values ​​with unified dimensions; substituting the indicator values ​​into the dynamic collaborative algorithm and performing weighted calculations in combination with preset weights to obtain the initial priority scores of each industrial equipment, and synchronously updating the priority scores according to the real-time changes in equipment operating status and production task progress.

5. The multi-device collaborative control method for industrial scenarios according to claim 1, characterized in that, Based on the changing trends, the risk of factory equipment failure is predicted and the failure probability is calculated. When the failure probability exceeds a preset threshold, the tasks of the equipment at risk of failure are allocated to backup factory equipment according to the priority score. This includes: identifying potential failure risk points based on the changing trends of the factory equipment; locking the failure equipment based on the potential failure risk points; quantifying and calculating the failure probability of the failure equipment within a preset time period based on the historical failure data and current abnormal parameters of the failure equipment; when the failure probability exceeds the preset threshold, selecting backup equipment with high priority, load adaptability, and no failure risk based on the real-time updated priority scores of each factory equipment; and allocating the current production tasks undertaken by the failure equipment to the selected backup equipment according to the priority matching rules.

6. The multi-device collaborative control method for industrial scenarios according to claim 1, characterized in that, The process of obtaining feedback adjustment information from the backup factory equipment and adjusting other factory equipment and production tasks based on the feedback adjustment information to form a closed-loop control includes: obtaining deviation data and manual adjustment instructions during the production execution process of the backup factory equipment; analyzing the causes of deviations based on the deviation data and manual adjustment instructions; generating adjustment strategies based on the causes of deviations; and adjusting other factory equipment and production tasks based on the adjustment strategies to form a closed-loop control.

7. The multi-device collaborative control method for industrial scenarios according to claim 1, characterized in that, After receiving the operating status data and production task progress data of each factory equipment, the method further includes: classifying the operating status data and the production task progress data according to each factory equipment to obtain classification results; sorting the classification results to obtain sorting results; and preprocessing the data in the sorting results to obtain preprocessed data.

8. A multi-device collaborative control device for industrial applications, characterized in that, The device includes: a receiving unit for receiving operating status data and production task progress data of various factory equipment; a prediction unit for predicting the changing trends of the operation and production tasks of various factory equipment within a preset time period based on the operating status data and the production task progress data; a first acquisition unit for acquiring the communication protocols of various factory equipment; a translation unit for identifying the communication protocols through a built-in protocol feature library and uniformly translating the equipment information of various factory equipment into industrially common intermediate protocol information; a second acquisition unit for acquiring data indicators based on the intermediate protocol information, the data indicators including production task urgency, equipment load rate, and energy consumption cost parameters; an update unit for calculating and updating the priority scores of various factory equipment in real time according to the data indicators and a dynamic collaborative algorithm; an allocation unit for predicting the failure risk of factory equipment based on the changing trends and calculating the failure probability, and when the failure probability exceeds a preset threshold, allocating the tasks of the equipment at failure risk to backup factory equipment according to the priority scores; and a third acquisition unit for acquiring feedback adjustment information from the backup factory equipment and adjusting other factory equipment and production tasks according to the feedback adjustment information to form closed-loop control.

9. A multi-device collaborative control device for industrial applications, characterized in that, The device includes: a processor, a memory, an input / output unit, and a bus; the processor is connected to the memory, the input / output unit, and the bus; the memory stores a program, and the processor calls the program to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains a program that, when executed on a computer, performs the method as described in any one of claims 1 to 7.

Images