Intelligent factory safety monitoring method and system based on digital twinning

Abstract

The invention relates to the technical field of factory safety monitoring, in particular to an intelligent factory safety monitoring method and system based on digital twinning, and the method comprises the steps: accurately analyzing the real-time operation state of a factory based on the collected real-time operation feature data of the factory and the safety interval of the factory operation feature data, generating the real-time operation state analysis data of the factory, and if the data is normal, carrying out the real-time operation of the factory; if so, finishing the safety monitoring operation of the factory; otherwise, generating factory abnormal operation characteristic data, performing factory real-time abnormal operation type matching with the collected factory abnormal operation type characteristic data, generating factory real-time abnormal operation type data, and constructing a factory real-time monitoring digital twin model according to the factory three-dimensional model and the factory real-time operation characteristic data; according to the method, factory real-time abnormal operation type data are marked, factory real-time abnormal state display data are generated and pushed to a factory safety monitoring platform, and safety monitoring of an intelligent factory operation process and visual display of a monitoring result are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of factory safety monitoring, and specifically to a smart factory safety monitoring method and system based on digital twins. Background Art

[0002] With the continuous development of industrial automation and intelligence, smart factories have gradually become the development trend of the manufacturing industry. At the same time, they are also accompanied by the increase in factory scale and the complexity of factory operation. Traditional security monitoring requires a lot of human resources, and the accuracy and comprehensiveness of the monitoring results are poor, which cannot meet the needs of smart factories.

[0003] The Chinese patent invention application with publication number CN113359639A introduces a factory equipment monitoring method and system based on a safety detection robot. During the operation of the factory, the safety detection robot automatically obtains the working data of each device in the factory, and detects the changes in the working data of each device in real time. If multiple working data of the equipment are lower or higher than the preset working data range, the safety detection robot will check the equipment to reduce the damage to the equipment. However, during the factory safety monitoring process, it is impossible to intelligently identify the type of data anomalies, nor can it intuitively reflect the location and situation of the anomalies during the real-time operation of the factory, resulting in poor accuracy of factory safety monitoring operations. Summary of the invention

[0004] 1. Technical issues to be resolved In order to solve the deficiencies in the background technology, the present invention provides a smart factory safety monitoring method and system based on digital twins, which can realize the safety monitoring of the operation process of the smart factory and the visual display of the monitoring results.

[0005] (II) Technical solution A smart factory safety monitoring method based on digital twins includes the following steps: S1. Collect real-time operation characteristic data of the factory; S2, performing factory real-time operation status analysis and processing on the factory real-time operation characteristic data and the factory operation characteristic data safety interval, generating factory real-time operation status analysis data, if it is normal, then ending this factory safety monitoring operation; otherwise, generating factory abnormal operation characteristic data; S3, collecting characteristic data of abnormal operation types of the factory; S4, performing a matching process of the real-time abnormal operation type of the factory according to the abnormal operation characteristic data of the factory and the abnormal operation type characteristic data of the factory, and generating the real-time abnormal operation type data of the factory; S5. Build a three-dimensional model of the factory, and build a real-time monitoring digital twin model of the factory based on the three-dimensional model of the factory and the real-time operation characteristic data of the factory; S6. Perform abnormal operation data annotation processing according to the real-time abnormal operation type data of the factory and the real-time monitoring digital twin model of the factory to generate real-time abnormal state display data of the factory; S7. Push the real-time abnormal status display data of the factory to the factory safety monitoring platform, and end the factory safety monitoring operation.

[0006] The present invention accurately analyzes the real-time operation status of the factory based on the collected real-time operation characteristic data of the factory and the safety interval of the factory operation characteristic data, and generates the real-time operation status analysis data of the factory. If it is normal, the current factory safety monitoring operation is terminated; otherwise, the abnormal operation characteristic data of the factory is generated, and the real-time abnormal operation type of the factory is matched with the collected abnormal operation type characteristic data of the factory to generate the real-time abnormal operation type data of the factory. According to the three-dimensional model of the factory and the real-time operation characteristic data of the factory, a real-time monitoring digital twin model of the factory is constructed, and the real-time abnormal operation type data of the factory is marked therein, and the real-time abnormal status display data of the factory is generated, and the data is pushed to the factory safety monitoring platform to realize the safety monitoring of the operation process of the smart factory and the visual display of the monitoring results.

[0007] Preferably, the specific steps for collecting the real-time operation characteristic data of the factory are as follows: S11. Install various sensors at various security monitoring locations in the smart factory. Use the installed sensors to regularly collect various operation characteristic data during the real-time operation of the smart factory to obtain the factory real-time operation characteristic data set. ,in, It indicates the first time data collected by the installed sensors during the operation of the smart factory. Real-time operation characteristic data of each factory, Represents the total number of real-time operating characteristic data of the factory. The safety monitoring location includes each operating equipment and important monitoring areas in the smart factory. The various sensors include but are not limited to any one or more of temperature sensors, humidity sensors, speed sensors, pressure sensors and current sensors.

[0008] Preferably, the plant real-time operation characteristic data and the plant operation characteristic data safety interval are subjected to plant real-time operation status analysis processing to generate plant real-time operation status analysis data. If the data is normal, the plant safety monitoring operation is terminated; otherwise, the specific steps of generating plant abnormal operation characteristic data are as follows: S21. Establish a safe interval set of plant operation characteristic data ,in, It indicates the first time data collected by the installed sensors during the operation of the smart factory. The safety interval of plant operation characteristic data corresponding to the real-time operation characteristic data; S22, the The real-time operation characteristic data of each factory and the safety interval set of the factory operation characteristic data The corresponding safety interval of the plant operation characteristic data is numerically matched; If all the plant real-time operation characteristic data in the plant real-time operation characteristic data set are within the corresponding plant operation characteristic data safety interval, it means that the value match is successful, then the plant real-time operation status analysis data is output. The real-time operation status analysis data of the plant is transmitted through the wireless communication network. Push to the factory safety monitoring platform and end the factory safety monitoring operation; If any of the plant real-time operation feature data in the plant real-time operation feature data set is not within the corresponding plant operation feature data safety interval, it means that the match is unsuccessful, then the plant real-time operation status analysis data is output. If the plant real-time operation characteristic data set is abnormal, the plant real-time operation characteristic data that fails to match the corresponding plant operation characteristic data safety interval is selected and the data is marked to generate a plant abnormal operation characteristic data set. ,in, Indicates that the first Real-time operation characteristic data of each factory, Indicates the total number of abnormal operation characteristic data of the plant.

[0009] By scientifically presetting the safety interval of the factory operation characteristic data and combining the real-time collected factory operation characteristic data, the real-time operation status of the factory can be accurately analyzed. If the real-time operation status of the factory is normal, the factory safety monitoring operation is terminated; otherwise, the abnormal real-time operation characteristic data of the factory is accurately screened out to generate abnormal factory operation characteristic data; by conducting a preliminary analysis of the acquired data, it is possible to quickly and accurately identify whether the real-time operation status of the factory is abnormal.

[0010] Preferably, the specific steps of collecting the characteristic data of abnormal operation type of the factory are as follows: S31, collecting feature data of various types of factory abnormal operation corresponding to each factory abnormal operation feature data in the factory abnormal operation feature data set online through the factory safety monitoring platform, and generating a factory abnormal operation type feature data set ,in, Indicates that the first A subset of the abnormal operation type feature data of a factory corresponding to the real-time operation feature data of the factory, ,in, Indicates that the first The real-time operation characteristic data of each factory corresponds to the Class factory abnormal operation type characteristic data, Indicates that the first The total number of abnormal operation type characteristic data of the factory corresponding to the real-time operation characteristic data of the factory.

[0011] Preferably, the specific steps of performing plant real-time abnormal operation type matching processing based on the plant abnormal operation characteristic data and the plant abnormal operation type characteristic data to generate the plant real-time abnormal operation type data are as follows: S41, using the Sky Eagle optimization algorithm, sequentially match each plant abnormal operation feature data in the plant abnormal operation feature data set with the corresponding plant abnormal operation type feature data subset in the plant abnormal operation type feature data set to perform plant real-time abnormal operation type matching processing, and generate a plant real-time abnormal operation type data set according to the matching results. ,in, Indicates that the first Real-time abnormal operation type data of each factory; S411, build an abnormal operation type to search for the Eagle population, set the population size to , the current number of iterations is The maximum number of iterations is And the search space dimension of the plant abnormal operation type feature data is ; The subset of the plant abnormal operation type feature data corresponding to the plant abnormal operation feature data being matched is used as the plant abnormal operation type feature data search space, and a random abnormal operation type characteristic data of each factory, each abnormal operation type characteristic data of each factory corresponds to an abnormal operation type search eagle individual in the abnormal operation type search eagle population; S412, calculating the fitness values ​​of each abnormal operation type search eagle individual in the abnormal operation type search eagle population and the abnormal operation characteristic data of the factory being matched, arranging each abnormal operation type search eagle individual in the abnormal operation type search eagle population from large to small according to the fitness value, and selecting the abnormal operation type search eagle individual with the highest fitness value as the current optimal individual; S413, according to the current number of iterations and the behavioral control coefficient The search behavior of each abnormal operation type search eagle individual in the abnormal operation type search eagle population in the abnormal operation type feature data search space of the factory is controlled, and the behavior control coefficient Represents a random number that obeys a uniform distribution between (0,1); when and When the abnormal operation type search eagle individual in the abnormal operation type search eagle population is in the expansion search stage, it approaches the prey by flying high and descending vertically in the abnormal operation type feature data search space of the factory to update the position; the position update formula is as follows: , in, Indicates that the abnormal operation type searches for the first The abnormal operation type searches for the location of the Sky Eagle individual after the location update, represents the position of the current optimal individual, Indicates During the iteration, the average position of each abnormal operation type search eagle individual in the abnormal operation type search eagle population, Represents a random number that obeys a uniform distribution between (0,1); when and When the abnormal operation type search eagle individual in the abnormal operation type search eagle population is in the narrowing search stage, the prey is attacked by equal altitude flight and short gliding in the abnormal operation type feature data search space of the factory to update the position; the position update formula is as follows: , in, represents the Levy flight distribution function, represents a randomly selected position from the search space of the feature data of the abnormal operation type of the plant, represents a random number that is uniformly distributed between (0,1). and Represents two parameters that control the shape of the spiral search;

[0012] when and When each individual in the abnormal operation type search eagle population is in the expansion and development stage, it attacks the prey by vertically and slowly descending in the abnormal operation type feature data search space of the factory to update its position; the position update formula is as follows: , in, and represent the upper and lower limits of the search space of the abnormal operation type feature data of the plant, respectively, and Both represent random numbers that are uniformly distributed between (0,1);

[0013] when and When the abnormal operation type search eagle individual in the abnormal operation type search eagle population is in the shrinking development stage, it attacks the prey by walking on land and following the prey's movement trajectory in the abnormal operation type feature data search space of the factory to update the position; the position update formula is as follows: , in, Indicates that the abnormal operation type searches for the first The current location of the Skyhawk instance is searched for by the abnormal operation type. represents the quality function value of the balanced search strategy, represents a random number that is uniformly distributed between [-1,1]. represents the slope of the abnormal operation type search eagle individual when following prey, and , and Both represent random numbers that are uniformly distributed between (0,1); S414, calculating the fitness value of each abnormal operation type search eagle individual in the abnormal operation type search eagle population after the position is updated and the abnormal operation characteristic data of the factory being matched, if the fitness value of the abnormal operation type search eagle individual after the position is updated is greater than the original fitness value, then the original position is replaced by the position of the abnormal operation type search eagle individual after the position is updated; otherwise, the original position is retained; Rearranging the abnormal operation type search eagle individuals in the abnormal operation type search eagle population from large to small according to fitness values, and selecting the abnormal operation type search eagle individual with the highest fitness value as the new current optimal individual; S415, determine the current number of iterations Is it less than the maximum number of iterations? , if the current number of iterations Less than the maximum number of iterations , then the current number of iterations Add 1 and return to S3; otherwise, take the current optimal individual as the global optimal solution, and retain the abnormal operation type characteristic data of the plant corresponding to the global optimal solution; S416, repeating the operations in S411 to S415 until all the plant abnormal operation characteristic data in the plant abnormal operation characteristic data set are traversed, and then the plant abnormal operation type data corresponding to all the retained plant abnormal operation type characteristic data are combined to generate a plant real-time abnormal operation type data set.

[0014] The Tianying optimization algorithm is used to match the plant's abnormal operation characteristic data and the plant's abnormal operation type characteristic data to the plant's real-time abnormal operation type, so as to quickly and accurately match the type of abnormal data occurring during the plant's operation, thereby providing a data basis for processing abnormalities occurring during the plant's real-time operation. At the same time, the Tianying optimization algorithm has good robustness, ensuring the stability of the matching process.

[0015] Preferably, the specific steps of constructing a three-dimensional model of a factory and constructing a real-time monitoring digital twin model of the factory based on the three-dimensional model of the factory and the real-time operation characteristic data of the factory are as follows: S51, constructing a three-dimensional model of the factory according to the actual terrain of the smart factory through three-dimensional modeling software; S52: perform data association processing on the real-time operation feature data of the factory in the real-time operation feature data set and the three-dimensional model of the factory through a data interface and a communication protocol, dynamically map the real-time operation feature data of the factory in the real-time operation feature data set to the three-dimensional model of the factory, and generate a real-time monitoring digital twin model of the factory .

[0016] Preferably, the specific steps of performing abnormal operation data annotation processing according to the real-time abnormal operation type data of the factory and the real-time monitoring digital twin model of the factory to generate the real-time abnormal state display data of the factory are as follows: S61. The position where each plant abnormal operation characteristic data in the plant abnormal operation characteristic data set appears in the plant real-time monitoring digital twin model is marked with flashing red, and a window is added at the position where each plant abnormal operation characteristic data in the plant abnormal operation characteristic data set appears, and the corresponding plant real-time abnormal operation type data in the plant real-time abnormal operation type data set is entered into the window to generate plant real-time abnormal status display data. .

[0017] A factory real-time monitoring digital twin model is scientifically constructed through the factory three-dimensional model and the factory real-time operation feature data, and the location where the abnormality occurs is marked with flashing red in the factory real-time monitoring digital twin model. At the same time, the corresponding factory real-time abnormal operation type data is filled in to generate factory real-time abnormal status display data, so as to realize the visualization of the smart factory safety monitoring results, and help managers intuitively understand the location and situation of safety abnormalities.

[0018] Preferably, the specific steps of pushing the real-time abnormal status display data of the factory to the factory safety monitoring platform and ending the factory safety monitoring operation are as follows: S71, displaying the real-time abnormal status data of the factory through a wireless communication network The data is pushed to the factory safety monitoring platform for display, and the factory safety monitoring operation is ended.

[0019] The present invention also includes a smart factory safety monitoring system based on digital twins, including a factory real-time operation feature data acquisition module, a factory real-time operation status analysis module, a factory abnormal operation type feature data acquisition module, a factory real-time abnormal operation type matching module, a digital twin model construction module, an abnormal operation data annotation module, and a factory real-time abnormal status display module; The factory real-time operation characteristic data acquisition module collects the real-time operation characteristic data of the intelligent factory during operation by means of the installed sensors at regular intervals to obtain the real-time operation characteristic data of the factory; The factory real-time operation status analysis module numerically matches each factory real-time operation characteristic data with the corresponding factory operation characteristic data safety interval, and generates factory real-time operation status analysis data according to the matching result. If it is normal, the factory safety monitoring operation is terminated; otherwise, the abnormal operation characteristic data of the factory is generated; The plant abnormal operation type characteristic data collection module collects characteristic data of various types of plant abnormal operation corresponding to each plant abnormal operation characteristic data in the plant abnormal operation characteristic data set online through the plant safety monitoring platform to generate plant abnormal operation type characteristic data; The factory real-time abnormal operation type matching module performs factory real-time abnormal operation type matching processing on the factory abnormal operation characteristic data and the factory abnormal operation type characteristic data in sequence through the Sky Eagle optimization algorithm, and generates factory real-time abnormal operation type data according to the matching result; The digital twin model construction module constructs a three-dimensional model of the factory according to the actual terrain of the smart factory through the three-dimensional modeling software, and associates the factory real-time operation feature data in the factory real-time operation feature data set with the factory three-dimensional model through the data interface and communication protocol to generate a factory real-time monitoring digital twin model; The abnormal operation data annotation module generates real-time abnormal state display data of the factory by marking the location where the abnormal operation characteristic data of the factory appears in the real-time monitoring digital twin model of the factory with red flashing and adding a window, and entering the corresponding real-time abnormal operation type data of the factory in the window; The factory real-time abnormal status display module pushes the factory real-time abnormal status display data to the factory safety monitoring platform for display through the wireless communication network, and ends the factory safety monitoring operation.

[0020] (III) Beneficial effects 1. The present invention accurately analyzes the real-time operation status of the factory based on the collected real-time operation characteristic data of the factory and the safety interval of the factory operation characteristic data, generates the real-time operation status analysis data of the factory, and if it is normal, ends the current factory safety monitoring operation; otherwise, generates the abnormal operation characteristic data of the factory, and matches the real-time abnormal operation type of the factory with the collected abnormal operation type characteristic data of the factory, generates the real-time abnormal operation type data of the factory, constructs the real-time monitoring digital twin model of the factory according to the three-dimensional model of the factory and the real-time operation characteristic data of the factory, marks the real-time abnormal operation type data of the factory in it, generates the real-time abnormal state display data of the factory, and pushes it to the factory safety monitoring platform, so as to realize the safety monitoring of the operation process of the smart factory and the visual display of the monitoring results; 2. Through scientifically presetting the safety interval of factory operation characteristic data, and combining the real-time collected factory real-time operation characteristic data, the real-time operation status of the factory is accurately analyzed. If the real-time operation status of the factory is normal, the factory safety monitoring operation is terminated; otherwise, the real-time operation characteristic data of the factory with abnormalities is accurately screened out to generate abnormal factory operation characteristic data; through preliminary analysis of the acquired data, whether the real-time operation status of the factory is abnormal can be quickly and accurately identified; 3. The abnormal operation characteristic data of the factory and the abnormal operation type characteristic data of the factory are matched with the real-time abnormal operation type of the factory through the Tianying optimization algorithm, so as to quickly and accurately match the type of abnormal data appearing in the factory operation process, and provide a data basis for processing the abnormalities appearing in the real-time operation process of the factory. At the same time, the Tianying optimization algorithm has good robustness, which ensures the stability of the matching process; 4. A real-time monitoring digital twin model of the factory is scientifically constructed through the factory three-dimensional model and the real-time operation characteristic data of the factory, and the location where the abnormality occurs is marked with flashing red in the real-time monitoring digital twin model of the factory. At the same time, the corresponding real-time abnormal operation type data of the factory is filled in to generate real-time abnormal status display data of the factory, so as to realize the visualization display of the safety monitoring results of the smart factory, and help managers intuitively understand the location and situation of the safety abnormality. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0022] Figure 1 A flowchart of a smart factory safety monitoring method based on digital twins provided by the present invention; Figure 2 A module schematic diagram of a smart factory safety monitoring system based on digital twins provided by the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0025] Embodiment 1 is as follows: See also Figure 1 , a smart factory safety monitoring method based on digital twins, comprising the following steps: S1. Collect real-time operation characteristic data of the factory; S11. Install various sensors at various security monitoring locations in the smart factory. Use the installed sensors to regularly collect real-time operation characteristic data during the operation of the smart factory to obtain the factory real-time operation characteristic data set. ,in, It indicates the first time data collected by the installed sensors during the operation of the smart factory. Real-time operation characteristic data, Represents the total number of real-time operating characteristic data of the factory. The safety monitoring location includes each operating equipment and important monitoring areas in the smart factory. The various sensors include but are not limited to any one or more of temperature sensors, humidity sensors, speed sensors, pressure sensors and current sensors.

[0026] S2, performing factory real-time operation status analysis and processing on the factory real-time operation characteristic data and the factory operation characteristic data safety interval, generating factory real-time operation status analysis data, if it is normal, then ending this factory safety monitoring operation; otherwise, generating factory abnormal operation characteristic data; S21. Establish a safe interval set of plant operation characteristic data ,in, It indicates the first time data collected by the installed sensors during the operation of the smart factory. The safety interval of plant operation characteristic data corresponding to the real-time operation characteristic data; S22, the The real-time operation characteristic data of each factory and the safety interval set of the factory operation characteristic data The corresponding safety interval of the plant operation characteristic data is numerically matched; If all the plant real-time operation characteristic data in the plant real-time operation characteristic data set are within the corresponding plant operation characteristic data safety interval, it means that the value match is successful, then the plant real-time operation status analysis data is output. The real-time operation status analysis data of the plant is transmitted through the wireless communication network. Push to the factory safety monitoring platform and end the factory safety monitoring operation; If any of the plant real-time operation feature data in the plant real-time operation feature data set is not within the corresponding plant operation feature data safety interval, it means that the match is unsuccessful, then the plant real-time operation status analysis data is output. If the plant real-time operation characteristic data set is abnormal, the plant real-time operation characteristic data that fails to match the corresponding plant operation characteristic data safety interval is selected and the data is marked to generate a plant abnormal operation characteristic data set. ,in, Indicates that the first Real-time operation characteristic data of each factory, Indicates the total number of abnormal operation characteristic data of the plant.

[0027] S3, collecting characteristic data of abnormal operation types of the factory; S31, collecting feature data of various types of factory abnormal operation corresponding to each factory abnormal operation feature data in the factory abnormal operation feature data set online through the factory safety monitoring platform, and generating a factory abnormal operation type feature data set ,in, Indicates that the first The subset of abnormal operation type feature data of the factory corresponding to the real-time operation feature data of the factory ,in, Indicates that the first The real-time operation characteristic data of each factory corresponds to the Class factory abnormal operation type characteristic data, Indicates that the first The total number of abnormal operation type characteristic data of the factory corresponding to the real-time operation characteristic data of the factory.

[0028] S4, performing a matching process of the real-time abnormal operation type of the factory according to the abnormal operation characteristic data of the factory and the abnormal operation type characteristic data of the factory, and generating the real-time abnormal operation type data of the factory; S41, using the Sky Eagle optimization algorithm, sequentially match each plant abnormal operation feature data in the plant abnormal operation feature data set with the corresponding plant abnormal operation type feature data subset in the plant abnormal operation type feature data set to perform plant real-time abnormal operation type matching processing, and generate a plant real-time abnormal operation type data set according to the matching results. ,in, Indicates that the first Real-time abnormal operation type data of each factory; S411, build an abnormal operation type to search for the Eagle population, set the population size to , the current number of iterations is The maximum number of iterations is And the search space dimension of the plant abnormal operation type feature data is ; The subset of the plant abnormal operation type feature data corresponding to the plant abnormal operation feature data being matched is used as the plant abnormal operation type feature data search space, and a random abnormal operation type characteristic data of each factory, each abnormal operation type characteristic data of each factory corresponds to an abnormal operation type search eagle individual in the abnormal operation type search eagle population; S412, calculating the fitness values ​​of each abnormal operation type search eagle individual in the abnormal operation type search eagle population and the abnormal operation characteristic data of the factory being matched, arranging each abnormal operation type search eagle individual in the abnormal operation type search eagle population from large to small according to the fitness value, and selecting the abnormal operation type search eagle individual with the highest fitness value as the current optimal individual; S413, according to the current number of iterations and the behavioral control coefficient The search behavior of each abnormal operation type search eagle individual in the abnormal operation type search eagle population in the abnormal operation type feature data search space of the factory is controlled, and the behavior control coefficient Represents a random number that obeys a uniform distribution between (0,1); when and When the abnormal operation type search eagle individual in the abnormal operation type search eagle population is in the expansion search stage, it approaches the prey by flying high and descending vertically in the abnormal operation type feature data search space of the factory to update the position; the position update formula is as follows: , in, Indicates that the abnormal operation type searches for the first The abnormal operation type searches for the location of the Sky Eagle individual after the location update, represents the position of the current optimal individual, Indicates During the iteration, the average position of each abnormal operation type search eagle individual in the abnormal operation type search eagle population, Represents a random number that obeys a uniform distribution between (0,1); when and When the abnormal operation type search eagle individual in the abnormal operation type search eagle population is in the narrowing search stage, the prey is attacked by equal altitude flight and short gliding in the abnormal operation type feature data search space of the factory to update the position; the position update formula is as follows: , in, represents the Levy flight distribution function, represents a randomly selected position from the search space of the feature data of the abnormal operation type of the plant, represents a random number that is uniformly distributed between (0,1). and Represents two parameters that control the shape of the spiral search;

[0029] when and When each individual in the abnormal operation type search eagle population is in the expansion and development stage, it attacks the prey by vertically and slowly descending in the abnormal operation type feature data search space of the factory to update its position; the position update formula is as follows: , in, and represent the upper and lower limits of the search space of the abnormal operation type feature data of the plant, respectively, and Both represent random numbers that are uniformly distributed between (0,1);

[0030] when and When the abnormal operation type search eagle individual in the abnormal operation type search eagle population is in the shrinking development stage, it attacks the prey by walking on land and following the prey's movement trajectory in the abnormal operation type feature data search space of the factory to update the position; the position update formula is as follows: , in, Indicates that the abnormal operation type searches for the first The current location of the Skyhawk instance is searched for by the abnormal operation type. represents the quality function value of the balanced search strategy, represents a random number that is uniformly distributed between [-1,1]. represents the slope of the abnormal operation type search eagle individual when following prey, and , and Both represent random numbers that are uniformly distributed between (0,1); S414, calculating the fitness value of each abnormal operation type search eagle individual in the abnormal operation type search eagle population after the position is updated and the abnormal operation characteristic data of the factory being matched, if the fitness value of the abnormal operation type search eagle individual after the position is updated is greater than the original fitness value, then the original position is replaced by the position of the abnormal operation type search eagle individual after the position is updated; otherwise, the original position is retained; Rearranging the abnormal operation type search eagle individuals in the abnormal operation type search eagle population from large to small according to fitness values, and selecting the abnormal operation type search eagle individual with the highest fitness value as the new current optimal individual; S415, determine the current number of iterations Is it less than the maximum number of iterations? , if the current number of iterations Less than the maximum number of iterations , then the current number of iterations Add 1 and return to S3; otherwise, take the current optimal individual as the global optimal solution, and retain the abnormal operation type characteristic data of the plant corresponding to the global optimal solution; S416, repeating the operations in S411 to S415 until all the plant abnormal operation characteristic data in the plant abnormal operation characteristic data set are traversed, and then the plant abnormal operation type data corresponding to all the retained plant abnormal operation type characteristic data are combined to generate a plant real-time abnormal operation type data set.

[0031] S5. Build a three-dimensional model of the factory, and build a real-time monitoring digital twin model of the factory based on the three-dimensional model of the factory and the real-time operation characteristic data of the factory; S51, constructing a three-dimensional model of the factory according to the actual terrain of the smart factory through three-dimensional modeling software; S52: perform data association processing on the real-time operation feature data of the factory in the real-time operation feature data set and the three-dimensional model of the factory through a data interface and a communication protocol, dynamically map the real-time operation feature data of the factory in the real-time operation feature data set to the three-dimensional model of the factory, and generate a real-time monitoring digital twin model of the factory .

[0032] S6. Perform abnormal operation data annotation processing according to the real-time abnormal operation type data of the factory and the real-time monitoring digital twin model of the factory to generate real-time abnormal state display data of the factory; S61. The position where each plant abnormal operation characteristic data in the plant abnormal operation characteristic data set appears in the plant real-time monitoring digital twin model is marked with flashing red, and a window is added at the position where each plant abnormal operation characteristic data in the plant abnormal operation characteristic data set appears, and the corresponding plant real-time abnormal operation type data in the plant real-time abnormal operation type data set is entered into the window to generate plant real-time abnormal status display data. .

[0033] S7, pushing the real-time abnormal status display data of the factory to the factory safety monitoring platform, and ending the factory safety monitoring operation; S71, displaying the real-time abnormal status data of the factory through a wireless communication network The data is pushed to the factory safety monitoring platform for display, and the factory safety monitoring operation is ended.

[0034] Embodiment 2 is as follows: See also Figure 2, a smart factory safety monitoring system based on digital twins, including a factory real-time operation feature data acquisition module, a factory real-time operation status analysis module, a factory abnormal operation type feature data acquisition module, a factory real-time abnormal operation type matching module, a digital twin model construction module, an abnormal operation data annotation module, and a factory real-time abnormal status display module; The factory real-time operation characteristic data acquisition module collects the real-time operation characteristic data of the intelligent factory during operation by means of the installed sensors at regular intervals to obtain the real-time operation characteristic data of the factory; The factory real-time operation status analysis module numerically matches each factory real-time operation characteristic data with the corresponding factory operation characteristic data safety interval, and generates factory real-time operation status analysis data according to the matching result. If it is normal, the factory safety monitoring operation is terminated; otherwise, the abnormal operation characteristic data of the factory is generated; The plant abnormal operation type characteristic data collection module collects characteristic data of various types of plant abnormal operation corresponding to each plant abnormal operation characteristic data in the plant abnormal operation characteristic data set online through the plant safety monitoring platform to generate plant abnormal operation type characteristic data; The factory real-time abnormal operation type matching module performs factory real-time abnormal operation type matching processing on the factory abnormal operation characteristic data and the factory abnormal operation type characteristic data in sequence through the Sky Eagle optimization algorithm, and generates factory real-time abnormal operation type data according to the matching result; The digital twin model construction module constructs a three-dimensional model of the factory according to the actual terrain of the smart factory through the three-dimensional modeling software, and associates the factory real-time operation feature data in the factory real-time operation feature data set with the factory three-dimensional model through the data interface and communication protocol to generate a factory real-time monitoring digital twin model; The abnormal operation data annotation module generates real-time abnormal state display data of the factory by marking the location where the abnormal operation characteristic data of the factory appears in the real-time monitoring digital twin model of the factory with red flashing and adding a window, and entering the corresponding real-time abnormal operation type data of the factory in the window; The factory real-time abnormal status display module pushes the factory real-time abnormal status display data to the factory safety monitoring platform for display through the wireless communication network, and ends the factory safety monitoring operation.

[0035] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0036] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A smart factory safety monitoring method based on digital twins, characterized in that: The steps include: S1. Collect real-time operation characteristic data of the factory; S2, performing factory real-time operation status analysis and processing on the factory real-time operation characteristic data and the factory operation characteristic data safety interval, generating factory real-time operation status analysis data, and if it is normal, ending this factory safety monitoring operation; Otherwise, abnormal operation characteristic data of the plant is generated; S3, collecting characteristic data of abnormal operation types of the factory; S4, performing a matching process of the real-time abnormal operation type of the factory according to the abnormal operation characteristic data of the factory and the abnormal operation type characteristic data of the factory, and generating the real-time abnormal operation type data of the factory; S5. Build a three-dimensional model of the factory, and build a real-time monitoring digital twin model of the factory based on the three-dimensional model of the factory and the real-time operation characteristic data of the factory; S6. Perform abnormal operation data annotation processing according to the real-time abnormal operation type data of the factory and the real-time monitoring digital twin model of the factory to generate real-time abnormal state display data of the factory; S7. Push the real-time abnormal status display data of the factory to the factory safety monitoring platform, and end the factory safety monitoring operation.

2. According to claim 1, a smart factory safety monitoring method based on digital twins is characterized in that: The S1 comprises the following steps: S11. Install various sensors at various security monitoring locations in the smart factory. Use the installed sensors to regularly collect various operation characteristic data during the real-time operation of the smart factory to obtain the factory real-time operation characteristic data set. ,in, It indicates the first time data collected by the installed sensors during the operation of the smart factory. Real-time operation characteristic data of each factory, Indicates the total number of real-time operation characteristic data of the factory.

3. The method for intelligent factory safety monitoring based on digital twin according to claim 2 is characterized in that: The S2 comprises the following steps: S21. Establish a safe interval set of plant operation characteristic data ,in, It indicates the first time data collected by the installed sensors during the operation of the smart factory. The safety interval of plant operation characteristic data corresponding to the real-time operation characteristic data of each plant; S22, the The real-time operation characteristic data of each factory and the safety interval set of the factory operation characteristic data The corresponding safety interval of the plant operation characteristic data is numerically matched; If the If the real-time operation characteristic data of each factory are within the corresponding factory operation characteristic data safety range, it means that the value matches successfully, then the real-time operation status analysis data of the factory is output. is normal, the wireless communication network Push to the factory safety monitoring platform and end the factory safety monitoring operation; Otherwise, output the real-time operation status analysis data of the factory For abnormality, filter out The real-time operation characteristic data of the plant that failed to match the safety interval of the corresponding plant operation characteristic data is marked and the abnormal operation characteristic data set of the plant is generated. ,in, Indicates the The first one that fails to match the corresponding plant operation characteristic data safety interval Real-time operation characteristic data of each factory, Indicates the total number of abnormal operation characteristic data of the plant.

4. The method for intelligent factory safety monitoring based on digital twin according to claim 3 is characterized in that: The S3 comprises the following steps: S31, collect the following information online through the factory safety monitoring platform The characteristic data of various types of abnormal operation of each factory corresponding to the abnormal operation characteristic data of each factory in the , generating a characteristic data set of abnormal operation type of the factory ,in, Indicates the The first one that fails to match the corresponding plant operation characteristic data safety interval A subset of the abnormal operation type feature data of a factory corresponding to the real-time operation feature data of the factory, ,in, express The first one that fails to match the corresponding plant operation characteristic data safety interval The real-time operation characteristic data of each factory corresponds to the Class factory abnormal operation type characteristic data, express The first one that fails to match the corresponding plant operation characteristic data safety interval The total number of abnormal operation type characteristic data of the factory corresponding to the real-time operation characteristic data of the factory.

5. The method for intelligent factory safety monitoring based on digital twin according to claim 4 is characterized in that: The S4 comprises the following steps: S41, using the Eagle optimization algorithm to The abnormal operation characteristic data of each factory are respectively The corresponding plant abnormal operation type feature data subset is used to match the plant real-time abnormal operation type, and the plant real-time abnormal operation type data set is generated according to the matching results. ,in, Indicates that the first The real-time abnormal operation type data of each factory is the real-time operation characteristic data of each factory.

6. The method for intelligent factory safety monitoring based on digital twin according to claim 5 is characterized in that: The S41 comprises the following steps: S411, build an abnormal operation type to search for the Eagle population, set the population size to , the current number of iterations is The maximum number of iterations is And the search space dimension of the plant abnormal operation type feature data is ; The subset of the plant abnormal operation type feature data corresponding to the plant abnormal operation feature data being matched is used as the plant abnormal operation type feature data search space, and a random Abnormal operation type characteristic data of each factory, each abnormal operation type characteristic data of each factory corresponds to an abnormal operation type search eagle individual; S412, calculating the fitness value of each abnormal operation type search eagle individual and the abnormal operation characteristic data of the factory being matched; S413, according to the current number of iterations and the behavioral control coefficient The search behavior of each abnormal operation type search eagle individual in the abnormal operation type feature data search space of the plant is controlled. Represents a random number that obeys a uniform distribution between (0,1); when and When each abnormal operation type search eagle individual is in the expansion search stage, it approaches the prey by flying high and descending vertically in the search space of the abnormal operation type characteristic data of the factory to update the position; when and When each abnormal operation type search eagle individual is in the narrowing search stage, it attacks the prey by means of equal altitude flight and short gliding in the search space of the abnormal operation type characteristic data of the factory to update the position; when and When each abnormal operation type search eagle individual is in the expansion development stage, it attacks the prey by vertically and slowly descending in the abnormal operation type characteristic data search space of the factory to update the position; when and When each abnormal operation type search eagle individual is in the narrowing development stage, it attacks the prey by walking on land and following the prey's movement trajectory in the search space of the abnormal operation type characteristic data of the factory to update the position; S414, calculating the fitness value of each abnormal operation type search eagle individual after the position is updated and the abnormal operation characteristic data of the factory being matched, if the fitness value of the abnormal operation type search eagle individual after the position is updated is greater than the original fitness value, then the original position is replaced by the position of the abnormal operation type search eagle individual after the position is updated; otherwise, the original position is retained; Arrange the abnormal operation type search eagle individuals from large to small according to the fitness value, and select the abnormal operation type search eagle individual with the highest fitness value as the current optimal individual; S415, Judgment Is it less than ,like Less than ,but Add 1 and return to S3; otherwise, take the current optimal individual as the global optimal solution, and retain the abnormal operation type characteristic data of the plant corresponding to the global optimal solution; S416, repeat the operations from S411 to S415 until the After all the abnormal operation characteristic data of the plants are obtained, the abnormal operation type data of the plants corresponding to all the retained abnormal operation type characteristic data of the plants are combined to generate a real-time abnormal operation type data set of the plants.

7. The method for safety monitoring of a smart factory based on digital twins according to claim 6 is characterized in that: The S5 comprises the following steps: S51, constructing a three-dimensional model of the factory according to the actual terrain of the smart factory through three-dimensional modeling software; S52, through the data interface and communication protocol The real-time operation characteristic data of the factory in the system is processed by data association with the three-dimensional model of the factory. The real-time operation characteristic data of the factory is dynamically mapped in the three-dimensional model of the factory to generate a real-time monitoring digital twin model of the factory .

8. The method for intelligent factory safety monitoring based on digital twin according to claim 7 is characterized in that: The S6 comprises the following steps: S61, in the The above mentioned The position of abnormal operation characteristic data of each plant in the Add a window at the location of the abnormal operation characteristic data of each factory in the The corresponding factory real-time abnormal operation type data generates the factory real-time abnormal status display data .

9. The method for intelligent factory safety monitoring based on digital twin according to claim 8 is characterized in that: The S7 comprises the following steps: S71, transmitting the The data is pushed to the factory safety monitoring platform for display, and the factory safety monitoring operation is ended.

10. A system for implementing the smart factory safety monitoring method based on digital twins as described in any one of claims 1 to 9, characterized in that: It includes a factory real-time operation feature data collection module, a factory real-time operation status analysis module, a factory abnormal operation type feature data collection module, a factory real-time abnormal operation type matching module, a digital twin model construction module, an abnormal operation data annotation module and a factory real-time abnormal status display module.

Images