Data collection and analysis method, device, equipment and storage medium for industrial Internet of Things

Abstract

The present invention relates to the technical field of data processing, and discloses a data collection and analysis method, device, equipment and storage medium for industrial Internet of Things. The data collection and analysis method for industrial Internet of Things includes: collecting structural layout information of the industrial environment where each industrial equipment and sensor network are located, and searching for data processing strategies corresponding to the structural layout information in a preset database; dividing the screened data processing strategies into functional areas to obtain multiple data analysis dimensions; based on different multiple data analysis dimensions, integrating current industrial scene requirements and operator preferences, and formulating corresponding data processing instructions through preset machine learning algorithms; performing characteristic analysis on the data processing instructions to obtain corresponding equipment control characteristics; the present invention can optimize production processes, improve production efficiency, and reduce resource waste by real-time analysis and integration of equipment and environmental data.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a data collection and analysis method, device, equipment and storage medium for industrial Internet of Things. Background Art

[0002] With the rapid development of Industrial Internet of Things (IIoT) technology, data collection and analysis of industrial equipment and its sensor networks have become key technical challenges in the manufacturing and automation fields. In IIoT systems, effectively managing and analyzing massive amounts of data from different devices and sensors is essential for optimizing production processes, improving equipment efficiency, and reducing maintenance costs. Traditional industrial data collection and analysis methods usually rely on fixed data processing strategies, which are often not flexible enough to meet the specific needs of different industrial environments, limiting the depth and breadth of data analysis. In the existing technology, some solutions attempt to integrate and analyze data from industrial equipment and sensors through software platforms. These platforms can provide basic data processing and analysis functions such as data visualization, simple statistical analysis, and alarm systems based on predefined rules. However, these systems often lack an in-depth understanding of the structural layout of the industrial environment, resulting in data processing strategies that cannot fully meet actual application requirements. In addition, they are usually also inflexible and cannot implement customized data analysis based on specific scenario requirements and operator preferences.

[0003] The main technical defects of the existing technology are its lack of flexibility and limited analytical depth. First, the lack of consideration of the structural layout of different industrial environments makes the data processing strategy often have weak generalization ability and cannot be optimized for specific environments. Secondly, there is a lack of effective mechanism to integrate the current industrial scene requirements and operator preferences, resulting in the generated data processing instructions unable to meet specific application requirements. Finally, the traditional method cannot provide sufficient data correction mechanism and dynamic parameter adjustment, which limits the accuracy and efficiency of data collection.

[0004] Therefore, there is an urgent need for an industrial Internet of Things data collection and analysis method to solve the above-mentioned problems. Summary of the invention

[0005] The present invention provides a data collection and analysis method, device, equipment and storage medium for an industrial Internet of Things, which are used to solve the technical problem of how to achieve more optimized data collection and performance processing under different industrial environment structure layouts.

[0006] A first aspect of the present invention provides a data collection and analysis method for an industrial Internet of Things, the data collection and analysis method for the industrial Internet of Things comprising: Collecting the structural layout information of the industrial environment where each industrial equipment and sensor network is located, and searching for a data processing strategy corresponding to the structural layout information in a preset database; wherein the database stores corresponding data processing strategy search rules according to the structural layout information of different industrial environments; The screened data processing strategies are divided into functional areas to obtain multiple data analysis dimensions; based on different multiple data analysis dimensions, the current industrial scene requirements and operator preferences are integrated, and corresponding data processing instructions are formulated through a preset machine learning algorithm; the data processing instructions are analyzed for characteristics to obtain corresponding equipment control features; Capturing scene images of the industrial environment to obtain initial visualization data; analyzing the initial visualization data to identify data feature layout of the industrial environment to obtain corresponding scene image features; Inputting the device control characteristics and the scene image characteristics into a preset data acquisition parameter configuration model to obtain preliminary data acquisition parameters; Based on a preset data correction rule, the preliminary data acquisition parameters are corrected to obtain corrected data acquisition parameters; The corrected data acquisition parameters are input into the trained dynamic parameter adjustment model to obtain an optimized data acquisition parameter configuration scheme; wherein the dynamic parameter adjustment model is obtained through advance optimization.

[0007] Optionally, in a first implementation of the first aspect of the present invention, the method further includes: Collecting equipment control feedback data of industrial equipment and real-time image data of industrial environment; analyzing the equipment control feedback data of industrial equipment and the real-time image data of industrial environment respectively to obtain first characteristic data and second characteristic data; The first characteristic data and the second characteristic data are merged to obtain environment and device behavior characteristic data; Inputting the environment and device behavior characteristic data into a preset hybrid data analysis model, wherein the hybrid data analysis model combines a convolutional neural network, a long short-term memory network, and a recurrent neural network to complete in-depth learning and analysis of hybrid data characteristics; Using a convolutional neural network to perform preliminary feature extraction on the input environment and device behavior characteristic data, thereby constructing a preliminary feature data set; The preliminary feature data set is sequentially passed to the long short-term memory network and the recurrent neural network to successively simulate the data acquisition response characteristics of industrial equipment under different industrial environments, and generate a target feature data set that describes the data acquisition behavior during the startup and operation of the industrial equipment; Based on the preliminary feature data set and the target feature data set, the data acquisition parameter composition diagrams during the startup and operation of industrial equipment are respectively formulated and mapped; Based on the data acquisition parameter composition diagram during the startup and operation of industrial equipment, optimization is performed through a preset optimization algorithm framework, and the optimal data acquisition parameter combination that adapts to the current industrial environment is generated to form an adaptive data acquisition strategy; wherein, the data acquisition strategy is used to accurately control the data acquisition and monitoring of industrial equipment and optimize data acquisition efficiency.

[0008] Optionally, in a second implementation of the first aspect of the present invention, the training process of the dynamic parameter adjustment model includes: Collecting data acquisition performance indicators of industrial equipment in various industrial environments, and pre-storing the data acquisition performance indicators in a comprehensive performance indicator database; Conduct in-depth analysis of data collection performance indicators to identify the data sensitivity and response efficiency of industrial equipment under specific monitoring conditions; Record data sensitivity at different response efficiency levels to create a data response signature map; Based on a preset multivariate analysis algorithm, analyze the key weight factors in the data response characteristic map; wherein the key weight factors reveal the intrinsic relationship between different response efficiency levels and device performance; Calculate a comprehensive score for each characteristic spectrum line based on the key weight factors and data response characteristic spectrum obtained by analysis, obtain the score result, and present each score result through a visual chart to generate a performance analysis spectrum; The generated performance analysis graph is imported into the initial dynamic parameter adjustment model for deep learning to obtain an optimized and trained dynamic parameter adjustment model; wherein the dynamic parameter adjustment model is used to adjust the data acquisition parameters of industrial equipment in real time to maximize monitoring efficiency and data accuracy.

[0009] Optionally, in a third implementation manner of the first aspect of the present invention, the fusing the first characteristic data with the second characteristic data to obtain environment and device behavior characteristic data includes: Initializing the importance weights of the first characteristic data and the second characteristic data; wherein the importance weights reflect the contribution of the first characteristic data and the second characteristic data in the overall performance evaluation, and the importance weights at least include the importance weights of the industrial equipment operation frequency data and the importance weights of the environmental impact factor data; The first characteristic data and the second characteristic data are standardized by using a preset weight parameter to generate a standardized device behavior and environment response vector set; Applying a preset data fusion technology to comprehensively process the standardized device behavior and environmental response vector set to generate a weighted feature vector representing the comprehensive device effectiveness; wherein the preset data fusion technology at least includes a weighted average algorithm, a principal component analysis algorithm or a linear discriminant analysis algorithm; The generated weighted feature vector is evaluated using a preset performance evaluation algorithm to generate environmental and equipment behavior characteristic data for the overall operating effect and environmental adaptability of the industrial equipment.

[0010] Optionally, in a fourth implementation of the first aspect of the present invention, the environment and equipment behavior characteristic data are used to reflect the actual performance of each industrial equipment in the industrial environment and the efficiency of the interaction between each industrial equipment and the industrial environment.

[0011] A second aspect of the present invention provides a data collection and analysis device for an industrial Internet of Things, the data collection and analysis device for the industrial Internet of Things comprising: A collection module, used to collect the structural layout information of the industrial environment where each industrial equipment and sensor network is located, and search for a data processing strategy corresponding to the structural layout information in a preset database; wherein the database stores corresponding data processing strategy search rules according to the structural layout information of different industrial environments; The analysis module is used to divide the screened data processing strategies into functional areas to obtain multiple data analysis dimensions; based on different multiple data analysis dimensions, the current industrial scene requirements and operator preferences are integrated, and corresponding data processing instructions are formulated through a preset machine learning algorithm; the data processing instructions are characteristically analyzed to obtain corresponding equipment control features; The recognition module is used to capture scene images of the industrial environment to obtain initial visualization data; analyze the initial visualization data to identify the data feature layout of the industrial environment to obtain corresponding scene image features; An input module, used to input the device control characteristics and the scene image characteristics into a preset data acquisition parameter configuration model to obtain preliminary data acquisition parameters; A correction module, used for performing correction processing on the preliminary data acquisition parameters based on a preset data correction rule to obtain the corrected data acquisition parameters; The prediction module is used to input the corrected data acquisition parameters into the trained dynamic parameter adjustment model to obtain the most optimized data acquisition parameter configuration scheme; wherein the dynamic parameter adjustment model is obtained through advance optimization.

[0012] The third aspect of the present invention provides a data collection and analysis device for an industrial Internet of Things, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the data collection and analysis device for the industrial Internet of Things executes the above-mentioned data collection and analysis method for the industrial Internet of Things.

[0013] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned industrial Internet of Things data collection and analysis method.

[0014] The technical solution provided by the present invention has the following beneficial effects: the present invention provides a data collection and analysis method, device, equipment and storage medium for the industrial Internet of Things, which collects the structural layout information of the industrial environment where each industrial equipment and sensor network are located, searches for the data processing strategy corresponding to the structural layout information in a preset database; divides the screened data processing strategy into functional areas to obtain multiple data analysis dimensions; based on different multiple data analysis dimensions, integrates the current industrial scene requirements and operator preferences, and formulates corresponding data processing instructions through a preset machine learning algorithm; performs feature analysis on the data processing instructions to obtain corresponding equipment control features; captures scene images of the industrial environment to obtain initial visualization data; and According to the analysis, the data feature layout of the industrial environment is identified to obtain the corresponding scene image features; the device control features and the scene image features are input into the preset data acquisition parameter configuration model to obtain preliminary data acquisition parameters; based on the preset data correction rules, the preliminary data acquisition parameters are corrected to obtain the corrected data acquisition parameters; the corrected data acquisition parameters are input into the trained dynamic parameter adjustment model to obtain the optimal data acquisition parameter configuration scheme; the present invention provides a more flexible and in-depth data acquisition analysis method by introducing data processing strategy matching and optimization based on different industrial environment structure layout information, as well as a customized processing instruction generation mechanism that integrates current industrial scene requirements and operator preferences. By capturing scene images and analyzing features of industrial environments, as well as optimizing based on preset data correction rules and dynamic parameter adjustment models, more accurate and efficient data acquisition parameter configuration can be achieved, thereby providing more optimized data acquisition and processing performance, bringing significant technological progress to the application of industrial Internet of Things. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 A schematic diagram of an embodiment of a data collection and analysis method for the industrial Internet of Things in an embodiment of the present invention; Figure 2 Schematic diagram of an embodiment of a data collection and analysis device for the industrial Internet of Things in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] Embodiments of the present invention provide a data collection and analysis method, device, equipment and storage medium for an industrial Internet of Things. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0016] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the data collection and analysis method of the industrial Internet of Things in an embodiment of the present invention includes: Step 101: Collect the structural layout information of the industrial environment where each industrial device and sensor network is located, and search for a data processing strategy corresponding to the structural layout information in a preset database; wherein the database stores corresponding data processing strategy search rules according to the structural layout information of different industrial environments; It is understandable that the execution subject of the present invention may be a data collection and analysis device of the industrial Internet of Things, or may be a terminal or a server, which is not specifically limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0017] Specifically, step 101 is implemented as follows: Collect the structural layout information of the industrial environment where each industrial equipment and sensor network is located: a. Structural layout information collection: Through on-site surveys or real-time monitoring of sensor networks, the layout information of various industrial equipment in the industrial environment is obtained, including equipment location, connection method, combination relationship, etc. This information can be obtained through laser scanning, camera monitoring, sensor data, etc.

[0018] b. Data integration and processing: Integrate and process the collected structural layout information into structured data to facilitate subsequent database query and data processing strategy matching.

[0019] Search the preset database for the data processing strategy corresponding to the structural layout information: a. Data processing strategy storage: The preset database stores the data processing strategy search rules corresponding to the structural layout information of different industrial environments, including data collection frequency, data transmission method, data processing algorithm, etc.

[0020] b. Data processing strategy matching: Based on the collected structural layout information, the corresponding data processing strategy is searched in the database to determine how to process and analyze the collected data.

[0021] For example: laser scanning is used to obtain the layout information of industrial equipment in the workshop, including the equipment placement, the connection relationship between equipment, etc., and then the corresponding data processing strategy is searched in the preset database, such as real-time monitoring of equipment connection status, prediction of equipment operation failure, etc.

[0022] Step 102: divide the selected data processing strategies into functional areas to obtain multiple data analysis dimensions; based on the different multiple data analysis dimensions, integrate the current industrial scene requirements and operator preferences, and formulate corresponding data processing instructions through a preset machine learning algorithm; perform characteristic analysis on the data processing instructions to obtain corresponding equipment control characteristics; Specifically, step 102 is implemented as follows: The selected data processing strategies are divided into functional areas to obtain multiple data analysis dimensions: a. Data processing strategy decomposition: Decompose and analyze the selected data processing strategy to determine its functional modules and operational dimensions.

[0023] b. Functional area division: According to the functional modules of the data processing strategy, they are differentiated and classified to obtain multiple data analysis dimensions, such as data collection, data transmission, data storage, data analysis, etc.

[0024] Based on multiple data analysis dimensions, integrating current industrial scenario requirements and operator preferences, corresponding data processing instructions are formulated through preset machine learning algorithms: a. Data analysis dimension fusion: Combining different data analysis dimensions, comprehensively considering current industrial scenario requirements and operator preferences, and using machine learning algorithms to automatically generate and optimize data processing instructions.

[0025] b. Formulate data processing instructions: Based on the fusion results, formulate specific data processing instructions, including data processing flow, parameter settings, operating specifications, etc.

[0026] The data processing instructions are analyzed to obtain the corresponding device control characteristics: a. Data processing instruction characteristic analysis: Conduct characteristic analysis on the formulated data processing instructions, including evaluation of the real-time performance, accuracy, stability, etc. of the instructions.

[0027] b. Equipment control feature extraction: Based on the results of data processing instruction characteristic analysis, the corresponding equipment control features are extracted for equipment operation control and monitoring.

[0028] For example: data processing strategies are divided into dimensions such as data collection, data transmission, and data storage. Based on current industrial needs and operator preferences, data processing instructions are formulated based on machine learning algorithms. Finally, equipment control characteristics such as real-time performance and accuracy are obtained through feature analysis.

[0029] Step 103: Capture scene images of the industrial environment to obtain initial visualization data; analyze the initial visualization data to identify data feature layout of the industrial environment to obtain corresponding scene image features; Specifically, step 103 is implemented as follows: Capture scene images of industrial environments to obtain initial visualization data: a. Scene image capture: Use a camera or other image capture device to capture the industrial environment and obtain image data in the environment.

[0030] b. Data processing and storage: The captured image data is processed to remove noise and interference, and then stored in a database for subsequent analysis.

[0031] The initial visualization data is analyzed to identify the data feature layout of the industrial environment and obtain the corresponding scene image features: a. Data feature analysis: Analyze the initial visualization data through image processing and computer vision technology to identify the equipment, objects and their layout features in the industrial environment.

[0032] b. Scene image feature extraction: Based on the data feature analysis results, the features of the industrial environment scene image are extracted, such as equipment location, channel distribution, equipment spacing, etc.

[0033] For example: the image data of the workshop is captured by a camera, the image is processed and analyzed, and the location and layout of the equipment in the workshop are identified to obtain scene image features such as equipment arrangement and channel layout.

[0034] Step 104: input the device control characteristics and the scene image characteristics into a preset data acquisition parameter configuration model to obtain preliminary data acquisition parameters; Specifically, step 104 is implemented as follows: Input the device control characteristics and the scene image characteristics into a preset data acquisition parameter configuration model: a. Equipment control feature input: The previously obtained equipment control features, including parameters such as real-time performance and accuracy, are input into the data acquisition parameter configuration model.

[0035] b. Scene image feature input: The identified scene image features, such as device location, channel layout and other information, are also input into the data acquisition parameter configuration model.

[0036] Get preliminary data collection parameters: a. Parameter configuration model operation: The model calculates and analyzes the input device control characteristics and scene image characteristics to determine the optimal data acquisition parameter configuration.

[0037] b. Generate preliminary data collection parameters: Generate preliminary data collection parameter configuration based on the model's calculation results, including data collection frequency, data collection accuracy, etc.

[0038] For example: the previously obtained equipment control characteristics such as real-time, accuracy parameters and scene image characteristics such as equipment location, channel layout and other information are input into the data acquisition parameter configuration model, and the preliminary data acquisition parameters are obtained through model calculation, including data acquisition frequency and accuracy.

[0039] Step 105: Based on a preset data correction rule, the preliminary data acquisition parameters are corrected to obtain corrected data acquisition parameters; Specifically, step 105 is implemented as follows: Based on the preset data correction rules, the preliminary data collection parameters are corrected: a. Data correction rule setting: According to the preset rule base, determine the specific method and processing flow of data correction, including data modification, data adjustment and other operations.

[0040] b. Correction of preliminary data collection parameters: Apply the preliminary data collection parameters to the set correction rules and perform corresponding correction processing to ensure the accuracy and reliability of the data.

[0041] Get the data acquisition parameters after correction: a. Data correction processing: According to the set correction rules, the preliminary data collection parameters are corrected or adjusted to eliminate the deviations that may occur during the data collection process.

[0042] b. Generation of parameters after correction: After data correction, the corrected data collection parameters are obtained. These parameters are more accurate and reliable and suitable for subsequent data collection and analysis.

[0043] For example: According to the preset data correction rules, the preliminary data collection parameters are corrected, such as correcting the data collection frequency or adjusting the data collection accuracy to ensure the accuracy of the data. After the rule processing, the corrected data collection parameters are obtained.

[0044] Step 106: input the corrected data acquisition parameters into the trained dynamic parameter adjustment model to obtain an optimized data acquisition parameter configuration scheme; wherein the dynamic parameter adjustment model is obtained by prior optimization.

[0045] Specifically, step 106 is implemented as follows: Input the corrected data acquisition parameters into the trained dynamic parameter adjustment model: a. Data acquisition parameter input: Input the data acquisition parameters after deviation correction, including data acquisition frequency, accuracy and other information, into the dynamic parameter adjustment model.

[0046] Get the most optimized data acquisition parameter configuration scheme: a. Dynamic parameter adjustment model calculation: The pre-optimized dynamic parameter adjustment model calculates the input data acquisition parameters to dynamically adjust and optimize the parameters.

[0047] b. Generation of the optimal parameter configuration scheme: Based on the model operation results, the optimal data acquisition parameter configuration scheme is obtained, which can make the data acquisition process more effective and efficient.

[0048] For example: input the corrected data acquisition parameters into the pre-optimized dynamic parameter adjustment model, and generate the most optimized data acquisition parameter configuration plan after model operation to improve the accuracy and efficiency of data acquisition.

[0049] Another embodiment of the data collection and analysis method of the industrial Internet of Things in the embodiment of the present invention includes: Collecting equipment control feedback data of industrial equipment and real-time image data of industrial environment; analyzing the equipment control feedback data of industrial equipment and the real-time image data of industrial environment respectively to obtain first characteristic data and second characteristic data; The first characteristic data and the second characteristic data are merged to obtain environment and device behavior characteristic data; Inputting the environment and device behavior characteristic data into a preset hybrid data analysis model, wherein the hybrid data analysis model combines a convolutional neural network, a long short-term memory network, and a recurrent neural network to complete in-depth learning and analysis of hybrid data characteristics; Using a convolutional neural network to perform preliminary feature extraction on the input environment and device behavior characteristic data, thereby constructing a preliminary feature data set; The preliminary feature data set is sequentially passed to the long short-term memory network and the recurrent neural network to successively simulate the data acquisition response characteristics of industrial equipment under different industrial environments, and generate a target feature data set that describes the data acquisition behavior during the startup and operation of the industrial equipment; Based on the preliminary feature data set and the target feature data set, the data acquisition parameter composition diagrams during the startup and operation of industrial equipment are respectively formulated and mapped; Based on the data acquisition parameter composition diagram during the startup and operation of industrial equipment, optimization is performed through a preset optimization algorithm framework, and the optimal data acquisition parameter combination that adapts to the current industrial environment is generated to form an adaptive data acquisition strategy; wherein, the data acquisition strategy is used to accurately control the data acquisition and monitoring of industrial equipment and optimize data acquisition efficiency.

[0050] Specific, important terminology explanations: Equipment control feedback data: refers to the information obtained from industrial equipment, covering the current status of the equipment, operation history, fault diagnostic codes, etc., aiming to reflect the real-time operation status of the equipment.

[0051] Real-time image data: refers to the visual information obtained in real time through image capture devices (such as cameras) installed in industrial environments, which is used for real-time monitoring and analysis of industrial environments and equipment conditions.

[0052] Environmental and device behavior characteristic data: refers to the data obtained through analysis after combining device control feedback data and real-time image data, which shows the behavior and response mode of the device in a specific environment.

[0053] Hybrid data analysis model: a composite model that integrates multiple neural network technologies (including at least convolutional neural networks, long short-term memory networks, and recurrent neural networks) to perform in-depth analysis and learning of fused data and reveal deeper data features and patterns.

[0054] Application scenarios: Production process monitoring: Implementing this technical solution on the production line can monitor the equipment status and production environment in real time, adjust the production strategy in time, and improve production efficiency and product quality.

[0055] Equipment failure prediction: Through in-depth analysis of equipment control feedback data and real-time image data, potential equipment failure points can be predicted, preventive maintenance can be achieved, and unexpected downtime can be reduced.

[0056] Detailed description of the technical solution: Advanced data preprocessing: Before fusing device control feedback data and real-time image data, advanced data preprocessing techniques, including data cleaning, normalization, and enhancement, are used to ensure data quality and improve the accuracy and reliability of subsequent analysis.

[0057] Model self-optimization mechanism: The hybrid data analysis model will have the ability of self-learning and optimization, and can automatically adjust network parameters according to the newly received data, continuously improving the analysis accuracy and adaptability of the model.

[0058] Data visualization interface: Develop an intuitive data visualization interface to present complex data analysis results in the form of graphics and charts, helping operators and managers to quickly understand the real-time status of equipment and environment and make effective decisions.

[0059] Cross-domain data fusion capability: Optimize data fusion algorithms to achieve efficient fusion of data from different devices and sensors, provide a more comprehensive analysis perspective, and enhance the comprehensiveness and accuracy of data analysis.

[0060] Beneficial effects of the technical solution derivation: Improve operational efficiency: By optimizing data collection parameters, accurate control of industrial equipment data collection and monitoring can be achieved, thereby greatly improving the efficiency of production operations.

[0061] Improve equipment utilization: Insights revealed by hybrid data analytics models can lead to more efficient use of equipment and resources, reduced downtime, and increased equipment utilization.

[0062] Reduce maintenance costs: By implementing predictive maintenance, expensive repair costs and downtime losses caused by equipment failure or improper operation are reduced.

[0063] Enhanced production transparency: Through comprehensive analysis of equipment control feedback data and real-time image data of the industrial environment, a comprehensive perspective on the production process can be provided, enhancing the transparency and controllability of the production process.

[0064] Another embodiment of the data collection and analysis method of the industrial Internet of Things in the embodiment of the present invention includes: The training process of the dynamic parameter adjustment model includes: Collecting data acquisition performance indicators of industrial equipment in various industrial environments, and pre-storing the data acquisition performance indicators in a comprehensive performance indicator database; Conduct in-depth analysis of data collection performance indicators to identify the data sensitivity and response efficiency of industrial equipment under specific monitoring conditions; Record data sensitivity at different response efficiency levels to create a data response signature map; Based on a preset multivariate analysis algorithm, analyze the key weight factors in the data response characteristic map; wherein the key weight factors reveal the intrinsic relationship between different response efficiency levels and device performance; Calculate a comprehensive score for each characteristic spectrum line based on the key weight factors and data response characteristic spectrum obtained by analysis, obtain the score result, and present each score result through a visual chart to generate a performance analysis spectrum; The generated performance analysis graph is imported into the initial dynamic parameter adjustment model for deep learning to obtain an optimized and trained dynamic parameter adjustment model; wherein the dynamic parameter adjustment model is used to adjust the data acquisition parameters of industrial equipment in real time to maximize monitoring efficiency and data accuracy.

[0065] Specific, important terminology explanations: Data collection performance indicators: This is a key parameter to measure the ability of industrial equipment to collect data under different environmental conditions, including the speed, accuracy and reliability of data collection.

[0066] Comprehensive performance index database: A database that stores data collection performance indicators of various industrial equipment in different industrial environments, used to analyze equipment performance and optimize data collection strategies.

[0067] Data response characteristic map: By analyzing the data collection performance indicators of the device, a comprehensive view of the data sensitivity and response efficiency of the device under specific conditions is depicted.

[0068] Dynamic parameter adjustment model: A model that dynamically adjusts data acquisition parameters based on data acquisition performance indicators and data response characteristic maps to improve the efficiency and accuracy of data acquisition.

[0069] Application scenarios: Multi-environment equipment monitoring: Monitor the data collection performance of equipment in changing industrial environments, such as different temperatures, humidity or noise levels, to ensure data accuracy and reliability.

[0070] Device performance optimization: Based on the device’s performance indicators in different environments, adjust the device settings or parameters to adapt to specific monitoring conditions and optimize its overall performance.

[0071] Further detailed explanation of the technical solution: Deep analysis of performance indicators: Use advanced analytical techniques (such as machine learning algorithms) to deeply analyze the data collected from the comprehensive performance indicator database to identify and understand the data sensitivity and response efficiency of equipment in different industrial environments.

[0072] Feature map creation and analysis: Create a data response feature map based on the data response performance of the device, and use a multivariate analysis algorithm to deeply analyze the key weight factors in the map to reveal the intrinsic connection between device performance and response efficiency.

[0073] Performance analysis graph: Combines the data response feature graph and the analysis results of key weight factors to generate a performance analysis graph, and displays it in the form of a visual chart to facilitate understanding and analysis of the performance score of each device.

[0074] Model optimization and real-time adjustment: Import performance analysis graphs into the dynamic parameter adjustment model and further optimize the model through deep learning. The optimized model can adjust data collection parameters in real time to adapt to different monitoring conditions and maximize monitoring efficiency and data accuracy.

[0075] Beneficial effects of the technical solution derivation: Enhanced data collection flexibility: By dynamically adjusting data collection parameters, this technical solution can enable the equipment to adapt to various industrial environments more flexibly and improve the adaptability and flexibility of data collection.

[0076] Improve data accuracy and reliability: Optimized data collection parameters can ensure that the data collected under different environmental conditions is more accurate and reliable, thereby improving the data quality of the entire system.

[0077] Optimize equipment performance: Through in-depth analysis of the equipment's performance indicators and response characteristics, it is possible to more accurately identify the equipment's strengths and weaknesses, and then optimize the equipment in a targeted manner to improve its overall performance.

[0078] Improve monitoring efficiency: The dynamic parameter adjustment model can automatically optimize data based on real-time performance feedback.

[0079] Another embodiment of the data collection and analysis method of the industrial Internet of Things in the embodiment of the present invention includes: fusing the first characteristic data with the second characteristic data to obtain environment and equipment behavior characteristic data, including: Initializing the importance weights of the first characteristic data and the second characteristic data; wherein the importance weights reflect the contribution of the first characteristic data and the second characteristic data in the overall performance evaluation, and the importance weights at least include the importance weights of the industrial equipment operation frequency data and the importance weights of the environmental impact factor data; The first characteristic data and the second characteristic data are standardized by using a preset weight parameter to generate a standardized device behavior and environment response vector set; Applying a preset data fusion technology to comprehensively process the standardized device behavior and environmental response vector set to generate a weighted feature vector representing the comprehensive device effectiveness; wherein the preset data fusion technology at least includes a weighted average algorithm, a principal component analysis algorithm or a linear discriminant analysis algorithm; The generated weighted feature vector is evaluated using a preset performance evaluation algorithm to generate environmental and equipment behavior characteristic data for the overall operating effect and environmental adaptability of the industrial equipment.

[0080] Specific, important terminology explanations: Importance weight: This is a coefficient used to measure the relative importance of specific data in the overall analysis. In this technical solution, the importance weight is used to determine the contribution of device control feedback data and real-time image data in the comprehensive device performance evaluation.

[0081] Standardization: This is a data preprocessing technique that aims to adjust data from different sources and ranges to a unified standard or range for effective comparison and analysis.

[0082] Device behavior and environmental response vector set: This is a multidimensional data set that comprehensively reflects device behavior and environmental response. By analyzing these vector sets, we can have a more comprehensive understanding of the performance of the device under specific environmental conditions.

[0083] Weighted feature vector: This is a vector generated by applying data fusion technology and combining importance weights. It represents the device performance and environmental adaptability after comprehensive consideration of various characteristic data.

[0084] Application scenarios: Smart Manufacturing: In a smart factory, the machine and environmental conditions on the production line are monitored and analyzed in real time to achieve intelligent optimization and control of the production process.

[0085] Preventive maintenance: By analyzing the behavioral characteristics and environmental factors of equipment, possible equipment failures can be predicted, so that preventive maintenance measures can be implemented to reduce unexpected downtime.

[0086] Further detailed explanation of the technical solution: Weight initialization: The importance weights of the first characteristic data (device control feedback data) and the second characteristic data (real-time image data) are initialized based on the actual influence of the device operation frequency and environmental factors.

[0087] Data standardization: Apply preset weight parameters to the first characteristic data and the second characteristic data for standardization to ensure the consistency and comparability of the data during fusion analysis.

[0088] Application of data fusion technology: Use data fusion technologies such as weighted average, principal component analysis or linear discriminant analysis to comprehensively process the standardized equipment behavior and environmental response vector set to generate a weighted feature vector representing the comprehensive performance of the equipment.

[0089] Performance evaluation: Use the preset performance evaluation algorithm to analyze the generated weighted feature vector to evaluate the overall operating effect and environmental adaptability of the industrial equipment, and form environmental and equipment behavior characteristic data.

[0090] Beneficial effects of the technical solution derivation: Accurate equipment monitoring and control: Through comprehensive analysis of equipment control feedback data and real-time image data, accurate monitoring and control of industrial equipment status can be achieved, improving equipment operation efficiency and stability.

[0091] Enhanced environmental adaptability: By considering the impact of environmental factors on equipment performance, this technical solution can help equipment better adapt to complex and changing industrial environments and improve its environmental adaptability and reliability.

[0092] Optimized production process: Through real-time analysis and integration of equipment and environmental data, this technical solution can optimize the production process, improve production efficiency and reduce resource waste.

[0093] Another embodiment of the data collection and analysis method of the industrial Internet of Things in the embodiment of the present invention includes: The environment and equipment behavior characteristic data are used to reflect the actual performance of each industrial equipment in the industrial environment and the efficiency of the interaction between each industrial equipment and the industrial environment.

[0094] The above describes the data collection and analysis method of the industrial Internet of Things in the embodiment of the present invention. The following describes the data collection and analysis device of the industrial Internet of Things in the embodiment of the present invention. Figure 2 , an embodiment of the data collection and analysis device of the industrial Internet of Things in the embodiment of the present invention includes: A collection module, used to collect the structural layout information of the industrial environment where each industrial equipment and sensor network is located, and search for a data processing strategy corresponding to the structural layout information in a preset database; wherein the database stores corresponding data processing strategy search rules according to the structural layout information of different industrial environments; The analysis module is used to divide the screened data processing strategies into functional areas to obtain multiple data analysis dimensions; based on different multiple data analysis dimensions, the current industrial scene requirements and operator preferences are integrated, and corresponding data processing instructions are formulated through a preset machine learning algorithm; the data processing instructions are characteristically analyzed to obtain corresponding equipment control features; The recognition module is used to capture scene images of the industrial environment to obtain initial visualization data; analyze the initial visualization data to identify the data feature layout of the industrial environment to obtain corresponding scene image features; An input module, used to input the device control characteristics and the scene image characteristics into a preset data acquisition parameter configuration model to obtain preliminary data acquisition parameters; A correction module, used for performing correction processing on the preliminary data acquisition parameters based on a preset data correction rule to obtain the corrected data acquisition parameters; The prediction module is used to input the corrected data acquisition parameters into the trained dynamic parameter adjustment model to obtain the most optimized data acquisition parameter configuration scheme; wherein the dynamic parameter adjustment model is obtained through advance optimization.

[0095] The present invention also provides a data collection and analysis device for an industrial Internet of Things, the data collection and analysis device for the industrial Internet of Things comprising a memory and a processor, the memory storing computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the data collection and analysis method for the industrial Internet of Things in the above-mentioned embodiments.

[0096] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the data collection and analysis method of the industrial Internet of Things.

[0097] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0099] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data collection and analysis method for industrial Internet of Things, characterized in that: The following steps are involved: Collecting the structural layout information of the industrial environment where each industrial equipment and sensor network is located, and searching for a data processing strategy corresponding to the structural layout information in a preset database; wherein the database stores corresponding data processing strategy search rules according to the structural layout information of different industrial environments; The screened data processing strategies are divided into functional areas to obtain multiple data analysis dimensions; based on different multiple data analysis dimensions, the current industrial scene requirements and operator preferences are integrated, and corresponding data processing instructions are formulated through a preset machine learning algorithm; the data processing instructions are analyzed for characteristics to obtain corresponding equipment control features; Capturing scene images of the industrial environment to obtain initial visualization data; analyzing the initial visualization data to identify data feature layout of the industrial environment to obtain corresponding scene image features; Inputting the device control characteristics and the scene image characteristics into a preset data acquisition parameter configuration model to obtain preliminary data acquisition parameters; Based on a preset data correction rule, the preliminary data acquisition parameters are corrected to obtain corrected data acquisition parameters; The corrected data acquisition parameters are input into the trained dynamic parameter adjustment model to obtain an optimized data acquisition parameter configuration scheme; wherein the dynamic parameter adjustment model is obtained through advance optimization.

2. The data collection and analysis method of the industrial Internet of Things according to claim 1 is characterized in that: Also includes: Collect equipment control feedback data of industrial equipment and real-time image data of industrial environment; The equipment control feedback data of the industrial equipment and the real-time image data of the industrial environment are analyzed respectively to obtain the first characteristic data and the second characteristic data; The first characteristic data and the second characteristic data are integrated to obtain environment and device behavior characteristic data; Inputting the environment and device behavior characteristic data into a preset hybrid data analysis model, wherein the hybrid data analysis model combines a convolutional neural network, a long short-term memory network, and a recurrent neural network to complete in-depth learning and analysis of hybrid data characteristics; Using a convolutional neural network to perform preliminary feature extraction on the input environment and device behavior characteristic data, thereby constructing a preliminary feature data set; The preliminary feature data set is sequentially passed to the long short-term memory network and the recurrent neural network to successively simulate the data acquisition response characteristics of industrial equipment under different industrial environments, and generate a target feature data set that describes the data acquisition behavior during the startup and operation of the industrial equipment; Based on the preliminary feature data set and the target feature data set, the data acquisition parameter composition diagrams during the startup and operation of industrial equipment are respectively formulated and mapped; Based on the data acquisition parameter composition diagram during the startup and operation of industrial equipment, optimization is performed through a preset optimization algorithm framework, and the optimal data acquisition parameter combination that adapts to the current industrial environment is generated to form an adaptive data acquisition strategy; wherein, the data acquisition strategy is used to accurately control the data acquisition and monitoring of industrial equipment and optimize data acquisition efficiency.

3. The data collection and analysis method of the industrial Internet of Things according to claim 1 is characterized in that: The training process of the dynamic parameter adjustment model includes: Collecting data acquisition performance indicators of industrial equipment in various industrial environments, and pre-storing the data acquisition performance indicators in a comprehensive performance indicator database; Conduct in-depth analysis of data collection performance indicators to identify the data sensitivity and response efficiency of industrial equipment under specific monitoring conditions; Record data sensitivity at different response efficiency levels to create a data response signature map; Based on a preset multivariate analysis algorithm, analyze the key weight factors in the data response characteristic map; wherein the key weight factors reveal the intrinsic relationship between different response efficiency levels and device performance; Calculate a comprehensive score for each characteristic spectrum line based on the key weight factors and data response characteristic spectrum obtained by analysis, obtain the score result, and present each score result through a visual chart to generate a performance analysis spectrum; The generated performance analysis graph is imported into the initial dynamic parameter adjustment model for deep learning to obtain an optimized and trained dynamic parameter adjustment model; wherein the dynamic parameter adjustment model is used to adjust the data acquisition parameters of industrial equipment in real time to maximize monitoring efficiency and data accuracy.

4. The data collection and analysis method of the industrial Internet of Things according to claim 2 is characterized in that: The step of fusing the first characteristic data with the second characteristic data to obtain environment and device behavior characteristic data includes: Initializing the importance weights of the first characteristic data and the second characteristic data; wherein the importance weights reflect the contribution of the first characteristic data and the second characteristic data in the overall performance evaluation, and the importance weights at least include the importance weights of the industrial equipment operation frequency data and the importance weights of the environmental impact factor data; The first characteristic data and the second characteristic data are standardized by using a preset weight parameter to generate a standardized device behavior and environment response vector set; Applying a preset data fusion technology to comprehensively process the standardized device behavior and environmental response vector set to generate a weighted feature vector representing the comprehensive device effectiveness; wherein the preset data fusion technology at least includes a weighted average algorithm, a principal component analysis algorithm or a linear discriminant analysis algorithm; The generated weighted feature vector is evaluated using a preset performance evaluation algorithm to generate environmental and equipment behavior characteristic data for the overall operating effect and environmental adaptability of the industrial equipment.

5. The data collection and analysis method of the industrial Internet of Things according to claim 4 is characterized in that: The environment and equipment behavior characteristic data are used to reflect the actual performance of each industrial equipment in the industrial environment and the efficiency of the interaction between each industrial equipment and the industrial environment.

6. A data collection and analysis device for industrial Internet of Things, characterized in that: The data collection and analysis device of the industrial Internet of Things comprises: A collection module, used to collect the structural layout information of the industrial environment where each industrial equipment and sensor network is located, and search for a data processing strategy corresponding to the structural layout information in a preset database; wherein the database stores corresponding data processing strategy search rules according to the structural layout information of different industrial environments; The analysis module is used to divide the screened data processing strategies into functional areas to obtain multiple data analysis dimensions; based on different multiple data analysis dimensions, the current industrial scene requirements and operator preferences are integrated, and corresponding data processing instructions are formulated through a preset machine learning algorithm; the data processing instructions are characteristically analyzed to obtain corresponding equipment control features; The recognition module is used to capture scene images of the industrial environment to obtain initial visualization data; analyze the initial visualization data to identify the data feature layout of the industrial environment to obtain corresponding scene image features; An input module, used to input the device control characteristics and the scene image characteristics into a preset data acquisition parameter configuration model to obtain preliminary data acquisition parameters; A correction module, used for performing correction processing on the preliminary data acquisition parameters based on a preset data correction rule to obtain the corrected data acquisition parameters; The prediction module is used to input the corrected data acquisition parameters into the trained dynamic parameter adjustment model to obtain the most optimized data acquisition parameter configuration scheme; wherein the dynamic parameter adjustment model is obtained through advance optimization.

7. A data collection and analysis device for industrial Internet of Things, characterized in that: The data collection and analysis device of the industrial Internet of Things includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instruction in the memory so that the data collection and analysis device of the industrial Internet of Things executes the data collection and analysis method of the industrial Internet of Things according to any one of claims 1 to 5.

8. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the data collection and analysis method of the industrial Internet of Things according to any one of claims 1 to 5 is implemented.

Images