Factory data remote monitoring management system and method based on Internet of Things

Abstract

The invention discloses a factory data remote monitoring management system and method based on the Internet of Things, and relates to the related field of the Internet of Things technology, and the system comprises a production data recording, tracking and sensing module which is used for carrying out production data recording, tracking and sensing; the data processing module is used for performing data processing on the equipment operation data set; the operation optimization suggestion generation module is used for performing regression analysis based on the equipment operation prediction data set in combination with factory production environment information, determining an operation efficiency data set and generating operation optimization suggestions; the operation simulation module is used for performing operation simulation and sending a simulation operation result to the remote terminal; and the visual monitoring management module is used for executing the remote control instruction to carry out remote intelligent visual monitoring management. The technical problem that the management level is insufficient due to the lack of intelligent management means in existing factory remote monitoring data management is solved, and the technical effect of improving the remote monitoring management level through intelligent monitoring and analysis means is achieved.

Description

Technical Field

[0001] The present application relates to fields related to Internet of Things technology, and in particular to a factory data remote monitoring management system and method based on the Internet of Things. Background Art

[0002] Factory monitoring plays a vital role in modern manufacturing. In order to ensure the stable operation of the factory, improve production efficiency, reduce operating costs and ensure production safety, it is particularly important to monitor the factory in real time. Factory monitoring can obtain information such as the operating status of the equipment, production progress, and environmental parameters in real time to provide decision support for managers. Through monitoring, equipment failures can be discovered and handled in a timely manner to avoid production interruptions and delays; at the same time, the production process can be optimized to improve production efficiency. At present, factory monitoring mainly relies on manual inspections and local monitoring systems. These methods lack intelligent monitoring and management methods, resulting in inefficient production decision-making in the factory, which in turn affects production efficiency and management level.

[0003] Among the current related technologies, factory remote monitoring data management lacks intelligent management methods, leading to technical problems such as insufficient management level. Summary of the invention

[0004] The present application provides a factory data remote monitoring management system and method based on the Internet of Things, records and tracks production data on the equipment side through the Internet of Things platform, obtains multiple equipment operation data sets, transmits the equipment operation data sets to the data acquisition cloud gateway for data processing, obtains the equipment operation prediction data set, introduces the factory production environment information, performs regression analysis based on the equipment operation prediction data set, determines the equipment operation efficiency data set, generates operation optimization suggestions, simulates the equipment operation based on the operation optimization suggestions, generates simulation operation results, and sends the results to a remote terminal for analysis, obtains remote control instructions, executes remote control instructions to perform remote intelligent visual monitoring and management of factory equipment, and other technical means, thereby achieving the technical effect of improving the level of remote monitoring and management through intelligent monitoring and analysis means.

[0005] The present application provides a factory data remote monitoring and management system based on the Internet of Things, which is connected to the device end, the Internet of Things platform, the data acquisition cloud gateway, and the remote terminal in communication, including: A production data recording and tracking sensing module, the production data recording and tracking sensing module is used to perform production data recording and tracking sensing on the device side through the Internet of Things platform to obtain multiple device operation data sets; a data processing module, the data processing module is used to transmit the multiple device operation data sets to the data acquisition cloud gateway for data processing to obtain multiple device operation prediction data sets; an operation optimization suggestion generation module, the operation optimization suggestion generation module is used to introduce the factory production environment information, perform regression analysis based on the multiple device operation prediction data sets combined with the factory production environment information, determine the operation efficiency data sets of multiple devices, and generate operation optimization suggestions based on the operation efficiency data sets; an operation simulation module, the operation simulation module is used to perform operation simulation on multiple devices based on the operation optimization suggestions, generate simulation operation results, send the simulation operation results to the remote terminal for analysis, and obtain remote control instructions; a visual monitoring management module, the visual monitoring management module is used to execute the remote control instructions to perform remote intelligent visual monitoring and management of multiple devices in the factory.

[0006] In a possible implementation, the data processing module is used to: The multiple device operation data sets are transmitted to the data acquisition cloud gateway for data storage classification to generate multiple data indexes; the historical operation data sets of multiple devices are retrieved according to the multiple data indexes, and operation timing analysis is performed based on the historical operation data sets of multiple devices to generate operation trends of multiple devices; operation prediction is performed based on the operation trends of multiple devices combined with the multiple device operation data sets to generate the multiple device operation prediction data sets.

[0007] In a possible implementation, the operation optimization suggestion generating module is used to: Based on the Internet of Things platform, multiple sensor devices are activated to perform environmental sensing of the factory to obtain multiple real-time environmental data; the multiple real-time environmental data are synchronized according to the data collection sequence to obtain multiple real-time environmental synchronization data; based on the multiple real-time environmental synchronization data and the multiple equipment operation data sets, an impact analysis is performed to generate multiple environmental impact coefficients; based on the multiple environmental impact coefficients, the multiple real-time environmental synchronization data are data-associated with the multiple equipment operation data sets, and the factory production environment information is generated according to the correlation factors.

[0008] In a possible implementation, the operation optimization suggestion generating module is used to: Perform variable analysis based on the multiple equipment operation prediction data sets to determine independent parameters; perform variable analysis based on the factory production environment information to determine dependent parameters; perform data segmentation according to correlation factors based on the independent parameters and the dependent parameters to generate a data training set and a data test set; perform iterative training based on the data training set to generate training results, verify the training results in combination with the data test set, and build a multivariate regression model based on the verification results; synchronize the multiple equipment operation prediction data sets in combination with the factory production environment information to the multivariate regression model for calculation, and generate the operation efficiency data sets of multiple devices.

[0009] In a possible implementation, the operation optimization suggestion generating module is used to: Based on the data training set, first training data, second training data...Nth training data are randomly extracted; based on the first training data, the second training data...the Nth training data, gradient descent analysis is performed to generate a first training result, a second training result...the Nth training result, the first training result, the second training result...the Nth training result and the first training data, the second training data...the Nth training data have a corresponding relationship, and N is an integer greater than 1; a loss function is introduced to calculate the first training data, the second training data...the Nth training data in combination with the first training result, the second training result...the Nth training result to generate a first regression coefficient, a second regression coefficient...the Nth regression coefficient; according to the data test set, it is determined in turn whether the first regression coefficient, the second regression coefficient...the Nth regression coefficient meets the expected regression interval, and the regression coefficient that meets the expected regression interval is extracted to determine the first multiple regression coefficient of the multiple regression model; according to the first multiple regression coefficient of the multiple regression model, the regression coefficient that does not meet the expected regression interval is adjusted to generate a second multiple regression coefficient; according to the second multiple regression coefficient, the multiple regression model is constructed in combination with the first training result, the second training result...the Nth training result.

[0010] In a possible implementation, the operation simulation module is used to: Initialization is performed based on the cloud platform in combination with the factory production environment information to generate factory production simulation environment information, wherein the factory production simulation environment information includes a simulation operation starting point and a simulation operation ending point; the operation optimization suggestion is synchronized to the cloud platform for optimization identification to generate a plurality of operation parameters to be optimized; a plurality of devices are mapped according to the factory production simulation environment information in combination with the plurality of operation parameters to be optimized to generate a plurality of device simulation operation groups; according to the simulation operation starting point, the plurality of device simulation operation groups are activated for monitoring until the simulation operation ending point ends to generate the simulation operation result.

[0011] In a possible implementation, the operation simulation module is used to: The simulation operation result is packaged to generate a data packet, and the data packet is sent to the remote terminal for parsing to generate a plurality of deconstructed data; the plurality of deconstructed data are classified and managed to generate a plurality of data categories, and features of the simulation operation result are extracted according to the plurality of data categories to determine a plurality of operation features; a risk assessment is performed on the simulation operation result according to the simulation operation start point, the simulation operation end point and the plurality of operation features in combination with the plurality of operation features to generate a plurality of operation risk parameters; equipment operation analysis is performed according to the plurality of operation risk parameters in combination with the simulation operation result to generate a control instruction; the control instruction is verified through the remote terminal to generate a verification token, and the control instruction is updated according to the verification token to generate the remote control instruction.

[0012] This application also provides a remote monitoring and management method for factory data based on the Internet of Things, including: Through the Internet of Things platform, production data is recorded, tracked and sensed on the device side to obtain multiple equipment operation data sets; the multiple equipment operation data sets are transmitted to the data acquisition cloud gateway for data processing to obtain multiple equipment operation prediction data sets; the factory production environment information is introduced, and regression analysis is performed based on the multiple equipment operation prediction data sets combined with the factory production environment information to determine the operation efficiency data sets of multiple devices, and operation optimization suggestions are generated based on the operation efficiency data sets; based on the operation optimization suggestions, operation simulation is performed on multiple devices to generate simulation operation results, and the simulation operation results are sent to a remote terminal for analysis to obtain remote control instructions; the remote control instructions are executed to perform remote intelligent visual monitoring and management of multiple devices in the factory.

[0013] It is intended to adopt the factory data remote monitoring management system and method based on the Internet of Things proposed in this application, through the production data recording and tracking sensor module, to perform production data recording and tracking sensing on the device side based on the Internet of Things platform, to obtain multiple equipment operation data sets, and transmit the multiple equipment operation data sets to the data acquisition cloud gateway for data processing through the data processing module to obtain multiple equipment operation prediction data sets, and introduce the factory production environment information through the operation optimization suggestion generation module, and perform regression analysis based on the multiple equipment operation prediction data sets combined with the factory production environment information to determine the operation efficiency data sets of multiple equipment, generate operation optimization suggestions based on the operation efficiency data sets, and simulate the operation of multiple equipment through the operation simulation module to generate simulation operation results, send the simulation operation results to the remote terminal for analysis, obtain remote control instructions, and execute the remote control instructions through the visual monitoring management module to perform remote intelligent visual monitoring and management of multiple equipment in the factory, thereby achieving the technical effect of improving the level of remote monitoring and management through intelligent monitoring and analysis means. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of the structure of a factory data remote monitoring and management system based on the Internet of Things provided in an embodiment of the present application.

[0016] Figure 2 A flowchart of a remote monitoring and management method for factory data based on the Internet of Things provided in an embodiment of the present application.

[0017] Explanation of the reference numerals: production data recording and tracking sensor module 10, data processing module 20, operation optimization suggestion generation module 30, operation simulation module 40, visual monitoring management module 50. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The embodiment of the present application provides a factory data remote monitoring and management system based on the Internet of Things, wherein the factory data remote monitoring and management system based on the Internet of Things is connected to the device end, the Internet of Things platform, the data acquisition cloud gateway, and the remote terminal in communication, such as Figure 1 As shown, the system comprises: The production data recording and tracking sensor module 10 is used to record and track the production data of the device side through the Internet of Things platform to obtain multiple device operation data sets. Specifically, the Internet of Things platform is a platform that connects devices, sensors and applications, and is used for data collection, processing and analysis. The production data recording and tracking sensor module 10 first establishes a connection with the Internet of Things platform to ensure that the channel for data transmission is unobstructed. Through the Internet of Things platform, the production data recording and tracking sensor module 10 records and tracks the production data of the device side (actual production equipment in the factory, such as machine tools, production lines, etc.), that is, reads the data provided by the device sensors, such as temperature, pressure, speed, energy consumption, etc. The production data recording and tracking sensor module 10 collects data from multiple devices to form an equipment operation data set.

[0022] The data processing module 20 is used to transmit the multiple device operation data sets to the data acquisition cloud gateway for data processing to obtain multiple device operation prediction data sets. Specifically, the device operation data sets are transmitted to the data acquisition cloud gateway, which is a gateway located in the cloud for data collection, storage, processing and forwarding. In the data acquisition cloud gateway, a time series analysis is performed on the multiple device operation data sets, that is, the law of data change over time is analyzed, and the future operation trend of the device is predicted based on the time series analysis results to generate a device operation prediction data set.

[0023] In one possible implementation, the data processing module 20 is used to: transmit the multiple device operation data sets to the data acquisition cloud gateway for data storage classification, and generate multiple data indexes; retrieve the historical operation data sets of multiple devices according to the multiple data indexes, perform operation timing analysis based on the historical operation data sets of multiple devices, and generate operation trends of multiple devices; perform operation prediction based on the operation trends of multiple devices in combination with the multiple device operation data sets, and generate the multiple device operation prediction data sets.

[0024] Specifically, the data processing module 20 receives multiple equipment operation data sets transmitted from the production data record tracking sensor module 10. These data sets contain real-time data generated by each device in the factory during operation, such as temperature, pressure, speed, energy consumption, etc. The data processing module 20 transmits these data sets to the data acquisition cloud gateway for storage and classification. In the data acquisition cloud gateway, the data is stored in a database. In order to efficiently manage and retrieve data, the data processing module 20 generates multiple data indexes based on data type, timestamp, device ID and other attributes, so that the data can be quickly located and accessed. The data processing module 20 retrieves the historical operation data sets of multiple devices according to the data index. These data sets contain the operation records of the equipment in the past period of time. The data processing module 20 uses statistics and machine learning to perform time series analysis on historical data to reveal the laws of data changes over time, such as periodicity, trend, seasonality, etc. Based on the results of the time series analysis, the operation trends of multiple devices are generated. These trends describe the possible performance of the equipment in the future. Combine the operation trend with the current equipment operation data set, and use a prediction model (such as linear regression) for operation prediction. The model generates a prediction data set for the equipment in the future based on historical data and current data. These data sets contain various data that the equipment may generate in the future, such as temperature, pressure, speed, energy consumption, etc., as well as the change trend of these data over time. This implementation method improves the efficiency of managing and retrieving the massive data generated by factory equipment through data storage classification and data indexing, so that data can be quickly located and accessed, which facilitates data analysis and processing. Using historical data and current data for time series analysis and operation prediction improves the accuracy of generating equipment operation prediction data sets, providing strong support for factory intelligent decision-making.

[0025] An operation optimization suggestion generation module 30 is used to introduce factory production environment information, perform regression analysis based on the multiple equipment operation prediction data sets combined with the factory production environment information, determine the operation efficiency data sets of multiple equipment, and generate operation optimization suggestions based on the operation efficiency data sets. Specifically, the sensor equipment is activated through the Internet of Things platform to obtain factory production environment information, such as temperature, humidity, air quality, etc. Based on the equipment operation prediction data set and the factory production environment information, regression analysis (studying the relationship between independent variables and dependent variables) is performed to evaluate the operation efficiency of the equipment in different environments, and based on the operation efficiency data set (reflecting the operation efficiency of the equipment in different production environments, including production capacity, energy consumption, failure rate and other indicators), operation optimization suggestions are generated, such as adjusting equipment parameters, optimizing production processes, etc.

[0026] In one possible implementation, the operation optimization suggestion generation module 30 is used to: activate multiple sensor devices based on the Internet of Things platform to perform environmental sensing on the factory to obtain multiple real-time environmental data; synchronize the multiple real-time environmental data according to the data collection sequence to obtain multiple real-time environmental synchronization data; perform impact analysis based on the multiple real-time environmental synchronization data combined with the multiple equipment operation data sets to generate multiple environmental impact coefficients; based on the multiple environmental impact coefficients, associate the multiple real-time environmental synchronization data with the multiple equipment operation data sets, and generate the factory production environment information according to the association factors.

[0027] Specifically, the operation optimization suggestion generation module 30 activates multiple sensor devices in the factory through the Internet of Things platform, including temperature sensors, humidity sensors, light sensors, air quality sensors, etc., for monitoring various environmental parameters inside the factory. After the sensor devices are activated, they start to collect environmental data inside the factory in real time. These real-time environmental data reflect the current environmental status of the factory. In order to ensure the accuracy and consistency of the data, the timestamp of each sensor device collecting data, that is, the data collection sequence, is recorded. Based on the data collection sequence, the real-time environmental data from different sensor devices are synchronized, that is, the data at the same time point are integrated together to form multiple real-time environmental synchronization data. The synchronized environmental data is integrated with multiple equipment operation data sets, so that the data at each time point contains information about the equipment operation status and environmental parameters. Using statistics, machine learning or deep learning, the integrated data is subjected to impact analysis, that is, the correlation and mutual influence between the equipment operation status and the environmental parameters are analyzed. Based on the results of the impact analysis, multiple environmental impact coefficients are generated, which quantify the degree of influence of different environmental parameters on the equipment operation status. For example, high temperature may increase the energy consumption of the equipment, while high humidity may reduce the performance of the equipment. According to the environmental impact coefficient, the real-time environmental synchronization data is associated with the equipment operation data set. During the data association process, the association factor is calculated to quantify the degree of association between the equipment operation status and the environmental parameters. Finally, based on the results of data association and association factors, the factory production environment information is generated. This information includes the environmental status inside the factory, the equipment operation status, and the mutual influence relationship between them. This implementation method activates multiple sensing devices to perform environmental sensing on the factory, comprehensively monitors various environmental parameters inside the factory, and at the same time, combines the equipment operation data set for impact analysis, revealing the correlation between environmental parameters and equipment performance.

[0028] In one possible implementation, the operation optimization suggestion generation module 30 is used to: perform variable analysis based on the multiple equipment operation prediction data sets to determine independent parameters; perform variable analysis based on the factory production environment information to determine dependent parameters; perform data segmentation according to correlation factors based on the independent parameters and the dependent parameters to generate a data training set and a data test set; perform iterative training based on the data training set to generate training results, verify the training results in combination with the data test set, and construct a multivariate regression model based on the verification results; synchronize the multiple equipment operation prediction data sets in combination with the factory production environment information to the multivariate regression model for calculation to generate the operation efficiency data sets of multiple equipment.

[0029] Specifically, multiple equipment operation prediction data sets are deeply analyzed to determine independent variables, which are key parameters in the equipment operation prediction data set and can directly or indirectly affect the equipment's operating conditions, such as failure rate, energy consumption, production efficiency, etc. Variable analysis is performed on the factory production environment information to determine dependent variables, which are parameters in the factory production environment information, such as temperature, humidity, air quality, etc., which will have a significant impact on the equipment's operating efficiency. According to the correlation factors between independent variables (key parameters in the equipment operation prediction data set) and dependent variables (parameters in the factory production environment information), the data is divided into a data training set and a data test set to ensure that there is enough data for learning during the model training process, and there is also independent data for verifying the accuracy of the model. Iterative training is performed using the data training set to generate training results. After the training is completed, the training results are combined with the data test set for verification to ensure that the model can accurately predict the equipment's operating efficiency under different environmental conditions. Based on the verification results, a multivariate regression model is constructed. This model comprehensively considers multiple parameters in the equipment operation prediction data set and the factory production environment information to predict the equipment's operating efficiency under different environmental conditions. The multiple equipment operation prediction data sets and factory production environment information are synchronized to the multivariate regression model for calculation. The model comprehensively considers all relevant parameters and generates multiple equipment operation efficiency data sets. This data set reflects the operating performance of different equipment under various environmental conditions. Each data point represents the efficiency performance of the equipment under a specific environmental parameter. This implementation method comprehensively considers multiple parameters in the equipment operation prediction data set and factory production environment information. Through iterative training and model verification, a highly accurate multivariate regression model is constructed, which improves the accuracy of predicting equipment operation efficiency under different conditions.

[0030] In a possible implementation, the operation optimization suggestion generating module 30 is used to: randomly extract first training data, second training data...Nth training data based on the data training set, perform gradient descent analysis based on the first training data, the second training data...the Nth training data, and generate a first training result, a second training result...the Nth training result, the first training result, the second training result...the Nth training result and the first training data, the second training data...the Nth training data have a corresponding relationship, and N is an integer greater than 1; introduce a loss function to combine the first training result, the second training result...the Nth training result with the first training data The method comprises the following steps: calculating the first regression coefficient, the second regression coefficient, and the Nth regression coefficient according to the data test set, the second training data, and the Nth training data to generate a first regression coefficient, a second regression coefficient, and the Nth regression coefficient; determining in turn whether the first regression coefficient, the second regression coefficient, and the Nth regression coefficient meet the expected regression interval according to the data test set, extracting the regression coefficients meeting the expected regression interval to determine the first multiple regression coefficient of the multiple regression model; adjusting the regression coefficients that do not meet the expected regression interval according to the first multiple regression coefficient of the multiple regression model to generate a second multiple regression coefficient; constructing the multiple regression model according to the second multiple regression coefficient in combination with the first training result, the second training result, and the Nth training result.

[0031] Specifically, multiple groups of training data are randomly extracted from the data training set, namely the first training data, the second training data, ... until the Nth training data, where N is an integer greater than 1, indicating the number of extracted training data groups. Random extraction is to increase the generalization ability of the model and avoid overfitting of the model. Gradient descent analysis is performed on each group of training data. Gradient descent is an optimization algorithm used to minimize the value of the loss function. In this process, the parameters of the model are continuously adjusted so that the difference between the predicted value and the actual value (i.e., the loss) gradually decreases. For each group of training data, a corresponding training result is generated after gradient descent analysis, namely the first training result, the second training result, ... until the Nth training result, and these training results have a one-to-one correspondence with the corresponding training data. The loss function is used to quantify the difference between the model predicted value and the actual value. Based on the loss function and each group of training results, the corresponding regression coefficients are calculated, namely the first regression coefficient, the second regression coefficient, ... until the Nth regression coefficient. These regression coefficients reflect the degree of influence of each independent variable in the model on the dependent variable. According to the data test set, each group of regression coefficients is judged in turn whether it meets the expected regression interval. The expected regression interval is a preset range used to evaluate the rationality of the regression coefficient. From all the regression coefficients, the regression coefficients that meet the expected regression interval are extracted, and these coefficients are determined as the first multiple regression coefficients of the multiple regression model. For the regression coefficients that do not meet the expected regression interval, they are adjusted according to the first multiple regression coefficient of the multiple regression model to generate the second multiple regression coefficient. The multiple regression model is constructed according to the second multiple regression coefficient combined with all the training results (first training result, second training result...Nth training result). This implementation method increases the generalization ability of the model by randomly extracting training data and performing gradient descent analysis, so that it can show good prediction performance under different conditions, ensuring the prediction accuracy of the model.

[0032] The operation simulation module 40 is used to perform operation simulation on multiple devices based on the operation optimization suggestions, generate simulation operation results, send the simulation operation results to the remote terminal for analysis, and obtain remote control instructions. Specifically, through computer simulation technology, according to the operation optimization suggestions, multiple devices are simulated, the operation of the devices in the actual production environment is simulated, and simulation operation results are generated, including output, energy consumption, fault prediction, etc. The simulation operation results are sent to the remote terminal for analysis and decision-making, and the remote control instructions (instructions for controlling the operation of the equipment) sent by the remote terminal are received.

[0033] In one possible implementation, the operation simulation module 40 is used to: initialize based on the cloud platform in combination with the factory production environment information to generate factory production simulation environment information, wherein the factory production simulation environment information includes a simulation operation starting point and a simulation operation ending point; synchronize the operation optimization suggestions to the cloud platform for optimization identification to generate multiple operation parameters to be optimized; map multiple devices according to the factory production simulation environment information in combination with the multiple operation parameters to be optimized to generate multiple device simulation operation groups; according to the simulation operation starting point, activate the multiple device simulation operation groups for monitoring until the simulation operation ending point ends, and generate the simulation operation results.

[0034] Specifically, the cloud platform is located in the data acquisition cloud gateway, and uses the actual production environment information of the factory (such as temperature, humidity, light, equipment layout, etc.) to initialize a virtual factory production simulation environment, which simulates the production conditions, equipment layout and process flow of the actual factory, and is used to test and optimize the production process without affecting the actual production. After initializing the simulation environment, set the starting point and end point of the simulation operation. Among them, the starting point defines the conditions for the start of the simulation, such as the initial state of the equipment, temperature, operating speed, initial configuration of the production line, etc. The end point defines the conditions for the end of the simulation, such as reaching a certain production volume, running for a certain time, etc. The operation optimization suggestions are synchronized to the cloud platform, and on the cloud platform, an optimization mark is added to each device parameter to be optimized to distinguish which parameters need to be adjusted. Based on the optimization mark, multiple sets of operation parameters to be optimized are generated, and these parameter sets represent optimization schemes and will be tested in the simulation operation. The operation parameters to be optimized are mapped to the virtual devices in the simulation environment to generate multiple equipment simulation operation groups. Starting from the starting point of the simulation operation, the equipment simulation operation group is activated and its operation process is monitored. The equipment simulation operation group executes the production process in the virtual environment and collects operation data at the same time. When the simulation operation termination point is reached, the simulation operation is stopped and simulation operation results are generated. These results include key indicators such as production volume, energy consumption, and failure rate, which are used to evaluate the performance of the optimization plan. This implementation method tests and optimizes the production process through simulation operation without interfering with actual production, reducing the risks that may be caused by implementing new plans. Simulation operation can quickly test multiple optimization plans, helping managers quickly find the best production configuration, thereby improving production efficiency.

[0035] In one possible implementation, the operation simulation module 40 is used to: package the simulation operation results into data packets, generate data packets, send the data packets to the remote terminal for parsing, and generate multiple deconstructed data; classify and manage the multiple deconstructed data to generate multiple data categories, extract features of the simulation operation results according to the multiple data categories, and determine multiple operation features; conduct risk assessment on the simulation operation results according to the simulation operation starting point, the simulation operation ending point and the multiple operation features, and generate multiple operation risk parameters; conduct equipment operation analysis according to the multiple operation risk parameters and the simulation operation results, and generate control instructions; verify the control instructions through the remote terminal to generate a verification token, update the control instructions according to the verification token, and generate the remote control instructions.

[0036] Specifically, after completing the simulation operation, the simulation operation results (including various operation data, performance indicators, etc.) are packaged and processed to generate a data packet. The packaged data packet is sent to the remote terminal through the network. The remote terminal is a device or system dedicated to data parsing and processing, and has powerful data processing capabilities. After receiving the data packet, the remote terminal parses it and generates multiple deconstructed data (specific data items parsed from the data packet, such as energy consumption data, production efficiency data, fault analysis data, etc.). These deconstructed data are classified and managed according to categories, such as the energy consumption data, operation frequency, failure rate, and productivity of the equipment are classified separately. Based on the classified data, feature extraction is performed on the simulation operation results to determine multiple operation features (such as the optimal operation frequency of the equipment, the maximum load bearing capacity, the peak energy consumption, etc.), which reflect the operation law and performance characteristics of the equipment. Combined with the simulation operation start point, the simulation operation end point and multiple operation features, the simulation operation results are risk assessed to generate multiple operation risk parameters, which reflect the potential risks of the equipment under specific operating conditions. Based on the risk assessment results and simulation operation results, the equipment operation is analyzed and control instructions are generated. The control instructions are used to guide the actual operation of the equipment, including equipment start, stop, adjustment of operating parameters and other operations, in order to optimize production efficiency and reduce risks. The remote terminal verifies the generated control instructions to ensure the correctness and feasibility of the instructions. After the verification is passed, a verification token is generated, and the control instructions are updated according to the verification token to generate the final remote control instructions, which are sent to the equipment for execution. This implementation method uses the remote terminal to centrally process and analyze the simulation operation results, fully utilizes the computing and storage resources of the remote terminal, and improves data processing efficiency. Through risk assessment, the potential risks of the equipment under specific operating conditions are quantified. The control instructions generated based on risk assessment and simulation operation results are more accurate and effective, and can guide the equipment to operate in the best way, improve production efficiency and safety. Through the generation and verification of remote control instructions, the correctness and feasibility of the control instructions are ensured, and problems in actual operation are avoided.

[0037] Visual monitoring management module 50, the visual monitoring management module 50 is used to execute the remote control command to perform remote intelligent visual monitoring and management on multiple devices in the factory. Specifically, according to the remote control command, multiple devices in the factory are remotely intelligently visually monitored and managed, and the equipment operation status, output, energy consumption and other information are displayed in real time, and an intuitive monitoring interface and alarm function are provided. The embodiment of the present application records and tracks the production data of the equipment end through the Internet of Things platform, obtains multiple equipment operation data sets, transmits the equipment operation data sets to the data acquisition cloud gateway for data processing, obtains the equipment operation prediction data set, introduces the factory production environment information, performs regression analysis based on the equipment operation prediction data set, determines the equipment operation efficiency data set, and generates operation optimization suggestions, simulates the operation of the equipment based on the operation optimization suggestions, generates simulation operation results, and sends the results to the remote terminal for analysis, obtains remote control instructions, executes remote control instructions to perform remote intelligent visual monitoring and management of factory equipment and other technical means, and achieves the technical effect of improving the level of remote monitoring and management through intelligent monitoring and analysis means.

[0038] In the above, refer to Figure 1 The present invention is described in detail based on the Internet of Things (IoT) factory data remote monitoring and management system. Figure 2 A remote monitoring and management method for factory data based on the Internet of Things according to an embodiment of the present invention is described.

[0039] The factory data remote monitoring and management method based on the Internet of Things according to the embodiment of the present invention is used to solve the technical problem of the lack of intelligent management means in the existing factory remote monitoring data management, resulting in insufficient management level, and achieve the technical effect of improving the remote monitoring management level through intelligent monitoring and analysis means. The factory data remote monitoring and management method based on the Internet of Things includes: Through the Internet of Things platform, production data is recorded, tracked and sensed on the device side to obtain multiple equipment operation data sets; the multiple equipment operation data sets are transmitted to the data acquisition cloud gateway for data processing to obtain multiple equipment operation prediction data sets; the factory production environment information is introduced, and regression analysis is performed based on the multiple equipment operation prediction data sets combined with the factory production environment information to determine the operation efficiency data sets of multiple devices, and operation optimization suggestions are generated based on the operation efficiency data sets; based on the operation optimization suggestions, operation simulation is performed on multiple devices to generate simulation operation results, and the simulation operation results are sent to a remote terminal for analysis to obtain remote control instructions; the remote control instructions are executed to perform remote intelligent visual monitoring and management of multiple devices in the factory.

[0040] Among them, transmitting the multiple device operation data sets to the data acquisition cloud gateway for data processing to obtain multiple device operation prediction data sets can further include: transmitting the multiple device operation data sets to the data acquisition cloud gateway for data storage classification to generate multiple data indexes; retrieving historical operation data sets of multiple devices according to the multiple data indexes, performing operation timing analysis based on the historical operation data sets of multiple devices, and generating operation trends of multiple devices; performing operation prediction based on the operation trends of multiple devices combined with the multiple device operation data sets to generate the multiple device operation prediction data sets.

[0041] Among them, the factory production environment information may further include: based on the Internet of Things platform, activating multiple sensor devices to perform environmental sensing of the factory to obtain multiple real-time environmental data; synchronizing the multiple real-time environmental data according to the data collection sequence to obtain multiple real-time environmental synchronization data; based on the multiple real-time environmental synchronization data combined with the multiple equipment operation data sets, performing impact analysis to generate multiple environmental impact coefficients; based on the multiple environmental impact coefficients, the multiple real-time environmental synchronization data are data-associated with the multiple equipment operation data sets, and the factory production environment information is generated according to the correlation factors.

[0042] Among them, performing regression analysis based on the multiple equipment operation prediction data sets in combination with the factory production environment information to determine the operation efficiency data sets of multiple equipment can further include: performing variable analysis based on the multiple equipment operation prediction data sets to determine independent variables; performing variable analysis based on the factory production environment information to determine dependent variables; performing data segmentation according to correlation factors based on the independent variables and the dependent variables to generate a data training set and a data test set; performing iterative training based on the data training set to generate training results, verifying the training results in combination with the data test set, and constructing a multivariate regression model based on the verification results; synchronizing the multiple equipment operation prediction data sets in combination with the factory production environment information to the multivariate regression model for calculation to generate the operation efficiency data sets of multiple equipment.

[0043] Among them, iterative training is performed based on the data training set to generate training results, the training results are combined with the data test set for verification, and a multivariate regression model is constructed according to the verification results, which can further include: randomly extracting first training data, second training data...Nth training data based on the data training set, performing gradient descent analysis based on the first training data, the second training data...the Nth training data to generate first training results, second training results...the Nth training results, the first training results, the second training results...the Nth training results have a corresponding relationship with the first training data, the second training data...the Nth training data, and N is an integer greater than 1; introducing a loss function to combine the first training result, the second training data...the Nth training data The result...the Nth training result calculates the first training data, the second training data...the Nth training data to generate a first regression coefficient, a second regression coefficient...the Nth regression coefficient; according to the data test set, it is determined in turn whether the first regression coefficient, the second regression coefficient...the Nth regression coefficient meets the expected regression interval, and the regression coefficients that meet the expected regression interval are extracted to determine the first multiple regression coefficient of the multiple regression model; according to the first multiple regression coefficient of the multiple regression model, the regression coefficients that do not meet the expected regression interval are adjusted to generate a second multiple regression coefficient; according to the second multiple regression coefficient, the multiple regression model is constructed in combination with the first training result, the second training result...the Nth training result.

[0044] Among them, based on the operation optimization suggestions, operation simulation of multiple devices is performed to generate simulation operation results, which can further include: initializing based on the cloud platform in combination with the factory production environment information to generate factory production simulation environment information, and the factory production simulation environment information includes a simulation operation starting point and a simulation operation end point; synchronizing the operation optimization suggestions to the cloud platform for optimization identification to generate multiple operation parameters to be optimized; mapping multiple devices according to the factory production simulation environment information in combination with the multiple operation parameters to be optimized to generate multiple device simulation operation groups; according to the simulation operation starting point, activating the multiple device simulation operation groups for monitoring until the simulation operation end point ends, and generating the simulation operation results.

[0045] Among them, sending the simulation operation result to the remote terminal for analysis to obtain the remote control instruction can further include: packaging the simulation operation result to generate a data packet, sending the data packet to the remote terminal for parsing, and generating a plurality of deconstructed data; classifying and managing the plurality of deconstructed data to generate a plurality of data categories, extracting features of the simulation operation result according to the plurality of data categories, and determining a plurality of operation features; conducting a risk assessment on the simulation operation result according to the simulation operation starting point, the simulation operation ending point and the plurality of operation features in combination with the plurality of operation features, and generating a plurality of operation risk parameters; conducting equipment operation analysis according to the plurality of operation risk parameters in combination with the simulation operation result, and generating a control instruction; verifying the control instruction through the remote terminal, generating a verification token, updating the control instruction according to the verification token, and generating the remote control instruction.

[0046] The factory data remote monitoring and management system based on the Internet of Things provided in the embodiment of the present invention can execute the factory data remote monitoring and management method based on the Internet of Things provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0047] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0048] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The factory data remote monitoring and management system based on the Internet of Things is characterized by: The factory data remote monitoring and management system based on the Internet of Things is connected to the equipment end, the Internet of Things platform, the data acquisition cloud gateway, and the remote terminal in communication, and the system includes: A production data recording and tracking sensing module, wherein the production data recording and tracking sensing module is used to perform production data recording and tracking sensing on the device end through the Internet of Things platform to obtain multiple equipment operation data sets; A data processing module, the data processing module is used to transmit the multiple device operation data sets to the data acquisition cloud gateway for data processing to obtain multiple device operation prediction data sets; An operation optimization suggestion generation module, the operation optimization suggestion generation module is used to introduce factory production environment information, perform regression analysis based on the multiple equipment operation prediction data sets combined with the factory production environment information, determine the operation efficiency data sets of multiple equipment, and generate operation optimization suggestions based on the operation efficiency data sets; An operation simulation module, the operation simulation module is used to perform operation simulation on multiple devices based on the operation optimization suggestion, generate simulation operation results, send the simulation operation results to the remote terminal for analysis, and obtain remote control instructions; A visual monitoring and management module is used to execute the remote control instructions to perform remote intelligent visual monitoring and management on multiple devices in the factory.

2. The factory data remote monitoring and management system based on the Internet of Things as claimed in claim 1, characterized in that: The data processing module is used for: Transmitting the plurality of equipment operation data sets to the data acquisition cloud gateway for data storage classification, and generating a plurality of data indexes; Retrieving historical operation data sets of multiple devices according to the multiple data indexes, performing operation timing analysis based on the historical operation data sets of the multiple devices, and generating operation trends of the multiple devices; Operation prediction is performed based on the operation trends of the multiple devices in combination with the multiple device operation data sets to generate the multiple device operation prediction data sets.

3. The factory data remote monitoring and management system based on the Internet of Things as claimed in claim 1, characterized in that: The operation optimization suggestion generation module is used for: Based on the IoT platform, multiple sensor devices are activated to sense the factory environment and obtain multiple real-time environmental data; Synchronize the multiple real-time environment data according to the data collection time sequence to obtain multiple real-time environment synchronization data; Performing an impact analysis based on the multiple real-time environment synchronization data combined with the multiple equipment operation data sets to generate multiple environmental impact coefficients; According to the multiple environmental impact coefficients, the multiple real-time environmental synchronization data are data-associated with the multiple equipment operation data sets, and the factory production environment information is generated according to the association factors.

4. The factory data remote monitoring and management system based on the Internet of Things as claimed in claim 3, characterized in that: The operation optimization suggestion generation module is used for: Performing variable analysis based on the plurality of equipment operation prediction data sets to determine independent variable parameters; Perform variable analysis based on the factory production environment information to determine dependent parameters; Perform data segmentation according to the independent variable parameter and the dependent variable parameter according to the correlation factor to generate a data training set and a data test set; Perform iterative training based on the data training set to generate training results, verify the training results in combination with the data test set, and construct a multivariate regression model based on the verification results; The multiple equipment operation prediction data sets are combined with the factory production environment information and synchronized to the multivariate regression model for calculation to generate the operation efficiency data sets of the multiple equipment.

5. The factory data remote monitoring and management system based on the Internet of Things as claimed in claim 4, characterized in that: The operation optimization suggestion generation module is used for: Randomly extracting first training data, second training data...Nth training data based on the data training set, performing gradient descent analysis based on the first training data, the second training data...the Nth training data, generating a first training result, a second training result...the Nth training result, the first training result, the second training result...the Nth training result and the first training data, the second training data...the Nth training data have a corresponding relationship, and N is an integer greater than 1; Introducing a loss function to calculate the first training data, the second training data, ... the Nth training data in combination with the first training result, the second training result ... the Nth training result to generate a first regression coefficient, a second regression coefficient ... the Nth regression coefficient; Determine in sequence according to the data test set whether the first regression coefficient, the second regression coefficient ... the Nth regression coefficient meet the expected regression interval, and extract the regression coefficient meeting the expected regression interval to determine the first multiple regression coefficient of the multiple regression model; According to the first multiple regression coefficient of the multiple regression model, the regression coefficient that does not meet the expected regression interval is adjusted to generate a second multiple regression coefficient; The multivariate regression model is constructed according to the second multivariate regression coefficient in combination with the first training result, the second training result, ... the Nth training result.

6. The factory data remote monitoring and management system based on the Internet of Things as claimed in claim 1, characterized in that: The operation simulation module is used for: Initialization is performed based on the cloud platform in combination with the factory production environment information to generate factory production simulation environment information, wherein the factory production simulation environment information includes a simulation operation start point and a simulation operation end point; Synchronizing the operation optimization suggestion to the cloud platform for optimization identification, and generating a plurality of operation parameters to be optimized; According to the factory production simulation environment information and the multiple operating parameters to be optimized, multiple equipment are mapped to generate multiple equipment simulation operation groups; According to the simulation operation starting point, the plurality of equipment simulation operation groups are activated for monitoring until the simulation operation ending point is reached, and the simulation operation result is generated.

7. The factory data remote monitoring and management system based on the Internet of Things as claimed in claim 6, characterized in that: The operation simulation module is used for: Packaging the simulation operation results into data packets to generate data packets, and sending the data packets to the remote terminal for parsing to generate a plurality of deconstructed data; Classify and manage the multiple deconstructed data to generate multiple data categories, extract features of the simulation operation results according to the multiple data categories, and determine multiple operation features; Performing risk assessment on the simulation operation result according to the simulation operation starting point, the simulation operation ending point and the multiple operation characteristics to generate multiple operation risk parameters; Performing equipment operation analysis according to the multiple operation risk parameters combined with the simulation operation results, and generating control instructions; The control instruction is verified through the remote terminal to generate a verification token, and the control instruction is updated according to the verification token to generate the remote control instruction.

8. A remote monitoring and management method for factory data based on the Internet of Things, characterized in that: The method is implemented by the factory data remote monitoring and management system based on the Internet of Things according to any one of claims 1 to 7, and the method comprises: Record and track production data on the equipment side through the IoT platform to obtain multiple equipment operation data sets; Transmitting the multiple equipment operation data sets to a data acquisition cloud gateway for data processing to obtain multiple equipment operation prediction data sets; Introducing factory production environment information, performing regression analysis based on the multiple equipment operation prediction data sets combined with the factory production environment information, determining the operation efficiency data sets of the multiple equipment, and generating operation optimization suggestions based on the operation efficiency data sets; Based on the operation optimization suggestion, operation simulation is performed on multiple devices to generate simulation operation results, and the simulation operation results are sent to a remote terminal for analysis to obtain remote control instructions; The remote control instructions are executed to perform remote intelligent visual monitoring and management of multiple devices in the factory.

Images