Intelligent data acquisition and analysis control method and system

Abstract

The invention relates to the technical field of automatic control, in particular to an intelligent data acquisition and analysis control method and system. The method comprises the following steps: acquiring corresponding network dynamic change data and equipment operation state data of industrial equipment in a bottom operation equipment layer in an industrial production process through an industrial internet, and performing adaptive adjustment of acquisition frequency to obtain dynamic acquisition frequency of an industrial sensor; intelligent data acquisition is carried out on the industrial production process, potential association mining analysis and quality influence control analysis are carried out by utilizing the data analysis layer, and an industrial production product quality influence control program is generated; and responding to and acting on the corresponding industrial production process through the industrial production product quality influence control program, issuing an instruction to control the bottom operation equipment layer to perform operation optimization control, and generating an industrial production operation optimization control strategy so as to execute corresponding industrial production equipment optimization control operation. According to the invention, accurate acquisition and control of data in the industrial production process can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of automation control, and particularly to an intelligent data acquisition and analysis control method and system. Background Art

[0002] At present, with the booming development of the industrial Internet, the acquisition and analysis of massive data have become the key to realizing industrial intelligent control. Traditional data acquisition methods have many limitations. On the one hand, the accuracy and stability of acquisition devices are insufficient, resulting in errors and omissions in the acquired data, which are difficult to meet the requirements of industrial production for high-precision data. For example, in the precision manufacturing industry, tiny measurement errors can lead to serious problems in product quality. On the other hand, in terms of data analysis and control, existing methods mostly rely on simple statistical analysis and preset rules, and cannot fully explore the potential value behind the data. When facing a large amount of multi-source heterogeneous data generated in the industrial production process, it is difficult to achieve effective data fusion and in-depth analysis, resulting in the inability to quickly and accurately locate the root cause of problems and give effective control strategies. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide an intelligent data acquisition and analysis control method and system to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent data acquisition and analysis control method includes the following steps:

[0005] Step S1: Obtain the network dynamic change data and device operation state data corresponding to industrial devices in the underlying operation device layer during industrial production through the industrial Internet, and adaptively adjust the acquisition frequency of the sensor layer based on the network dynamic change data and device operation state data to obtain the dynamic acquisition frequency of industrial sensors;

[0006] Step S2: Based on the dynamic acquisition frequency of industrial sensors, use the sensor layer to intelligently acquire data during industrial production to obtain various types of industrial production data; upload various types of industrial production data to the data analysis layer, and use the data analysis layer to perform potential correlation mining analysis on various types of industrial production data to obtain the potential correlation relationships between various types of industrial production data;

[0007] Step S3: Based on the potential correlation relationships between various types of industrial production data, perform quality impact control analysis on the production line products corresponding to the industrial production process in the control program layer to generate an industrial production product quality impact control program;

[0008] Step S4: Through the industrial production product quality impact control program, it acts on the corresponding industrial production process and issues instructions to control the underlying operation equipment layer for operation optimization control, generating an industrial production operation optimization control strategy to execute the corresponding industrial production equipment optimization control operation.

[0009] Further, step S1 includes the following steps:

[0010] Step S11: Obtain the corresponding network dynamic change data and equipment operation status data of industrial equipment in the underlying operation equipment layer during industrial production through the industrial Internet. The network dynamic change data includes the network bandwidth utilization rate, delay, and packet loss rate corresponding to the industrial equipment on the industrial Internet communication link, and the equipment operation status data includes the operating temperature, operating pressure, and operating speed corresponding to the industrial equipment.

[0011] Step S12: Remove data noise from the network dynamic change data and equipment operation status data to obtain network change denoised data and equipment operation denoised data.

[0012] Step S13: Remove duplicates and standardize the network change denoised data and equipment operation denoised data to obtain network change standard data and equipment operation standard data.

[0013] Step S14: Perform time series synchronization analysis on the network change standard data and equipment operation standard data to obtain the corresponding network change data and equipment operation data within the same time series range.

[0014] Step S15: Based on the corresponding network change data and equipment operation data within the same time series range, adaptively adjust the acquisition frequency of the corresponding industrial sensors in the sensor layer to obtain the dynamic acquisition frequency of industrial sensors.

[0015] Further, step S15 includes the following steps:

[0016] Step S151: Perform time series change statistical analysis on the network bandwidth utilization rate, delay, and packet loss rate corresponding to the network change data to obtain the network time series change amplitude, including the network bandwidth utilization change amplitude, network delay change amplitude, and network packet loss change amplitude.

[0017] Step S152: Predict the equipment operation fluctuations of the corresponding industrial equipment in the underlying operation equipment layer based on the equipment operation data to obtain the equipment operation fluctuation duration.

[0018] Step S153: Calculate the acquisition frequency of the corresponding industrial sensors in the sensor layer based on the network time series change amplitude and equipment operation fluctuation duration using the sensing acquisition frequency calculation formula to obtain the initial acquisition frequency of industrial sensors.

[0019] Step S154: Perform a change trend prediction analysis on the corresponding network change data and device operation data within the same time series range to obtain the time series change trends corresponding to the network dynamic changes and the device operation status;

[0020] Step S155: Based on the time series change trends corresponding to the network dynamic changes and the device operation status, adaptively adjust the initial acquisition frequency of the industrial sensor to obtain the dynamic acquisition frequency of the industrial sensor.

[0021] Further, the specific formula for the sensing acquisition frequency in step S153 is:

[0022]

[0023] In the formula, f is the initial acquisition frequency of the industrial sensor, T b is the device operation fluctuation duration, ε d is the network bandwidth utilization change amplitude, ε y is the network delay change amplitude, ε b is the network packet loss change amplitude, and η is the correction coefficient of the initial acquisition frequency of the industrial sensor.

[0024] Further, the specific method of adaptively adjusting the initial acquisition frequency of the industrial sensor based on the time series change trends corresponding to the network dynamic changes and the device operation status in step S155 is as follows: when the network dynamic changes tend to be stable and the device operation status tends to be stable, increase a preset time step to increase the corresponding device operation fluctuation duration to reduce the acquisition frequency; when the network dynamic changes fluctuate greatly or the device operation status fluctuates greatly, reduce a preset time step to reduce the corresponding device operation fluctuation duration to increase the acquisition frequency, so as to obtain the dynamic acquisition frequency of the industrial sensor.

[0025] Further, step S2 includes the following steps:

[0026] Step S21: Based on the dynamic acquisition frequency of the industrial sensor, use the corresponding industrial sensors within the sensor layer to perform intelligent data acquisition on the industrial production process to obtain various types of industrial production data;

[0027] Step S22: Upload various types of industrial production data to the data analysis layer through the communication link corresponding to the industrial Internet;

[0028] Step S23: Use the data analysis layer to perform time segment division on various types of industrial production data to obtain various types of industrial data corresponding to the same time segment;

[0029] Step S24: Perform an association metric calculation between various types of industrial data corresponding to the same time segment to obtain the data correlation degree corresponding to various types of industrial data;

[0030] Step S25: Conduct potential association mining and analysis on various types of industrial production data based on the corresponding data association degrees between various types of industrial data, so as to compare and judge the corresponding data association degrees according to a preset association threshold. If the data association degree is greater than or equal to the preset association threshold, there is a potential association relationship between the corresponding industrial data; if the data association degree is less than the preset association threshold, there is no potential association relationship between the corresponding industrial data, and the potential association relationships between various types of industrial production data are obtained.

[0031] Further, the various types of industrial production data described in step S21 include industrial production temperature, industrial production rate, industrial production pressure, and industrial production product quality.

[0032] Further, step S3 includes the following steps:

[0033] Step S31: Analyze the quality influence law of the corresponding production line products in the industrial production process through the potential association relationships between various types of industrial production data within the control program layer, and obtain the quality influence laws of various types of industrial data corresponding to the industrial production process.

[0034] Step S32: Predict the product equipment failures of the corresponding industrial equipment in the industrial production process based on the quality influence laws of various types of industrial data corresponding to the industrial production process, so as to obtain the industrial equipment corresponding to the product quality influence failures.

[0035] Step S33: Use the control program layer to perform fault response control on the industrial equipment corresponding to the product quality influence failures, and generate an industrial production product quality influence control program.

[0036] Further, step S4 includes the following steps:

[0037] Step S41: By applying the industrial production product quality influence control program to the corresponding industrial production process, when it is detected that the product quality in the industrial production process is abnormal or deviates from the preset target, a corresponding industrial production control instruction is generated in response.

[0038] Step S42: Send the industrial production control instruction to control the corresponding industrial equipment in the underlying operation equipment layer to perform operation optimization control, generate an industrial production operation optimization control strategy, and realize the dynamic optimization of the control strategy according to the control deviation between the actual production control result and the expected target, so as to execute the corresponding industrial production equipment optimization control operation.

[0039] Further, the present invention also provides an intelligent data acquisition and analysis control system for executing the intelligent data acquisition and analysis control method as described above. The intelligent data acquisition and analysis control system includes:

[0040] A sensing acquisition frequency adjustment module, which is used to obtain the network dynamic change data and equipment operation status data corresponding to industrial equipment in the underlying operation equipment layer during industrial production through the industrial Internet, and adaptively adjust the acquisition frequency of the sensor layer based on the network dynamic change data and equipment operation status data, so as to obtain the dynamic acquisition frequency of industrial sensors;

[0041] An industrial data correlation mining and analysis module, which is used to intelligently collect industrial production process data by using the sensor layer based on the dynamic acquisition frequency of industrial sensors to obtain various industrial production data; upload various industrial production data to the data analysis layer, and use the data analysis layer to conduct potential correlation mining and analysis on various industrial production data, so as to obtain the potential correlation relationships between various industrial production data;

[0042] A production quality impact control module, which is used to generate an industrial production product quality impact control program by conducting quality impact control analysis on the corresponding production line products during industrial production in the control program layer based on the potential correlation relationships between various industrial production data;

[0043] An industrial production operation optimization control module, which is used to respond to the industrial production product quality impact control program and act on the corresponding industrial production process, issue instructions to control the underlying operation equipment layer for operation optimization control, generate an industrial production operation optimization control strategy, and execute the corresponding industrial production equipment optimization control operation.

[0044] The beneficial effects of the present invention:

[0045] 1. Compared with the prior art, the beneficial effect of the intelligent data acquisition and analysis control method proposed by the present invention is that by using the industrial Internet to obtain the network dynamic change data and equipment operation status data of industrial equipment in the underlying operation equipment layer, it is possible to more comprehensively understand various operating conditions faced by the equipment during the production process and continuously track the operation status of the equipment. This process helps to timely discover potential problems such as equipment failures, performance degradation, or resource waste, and then take corresponding measures for optimization. Next, based on these network dynamic change data and equipment operation status data, the acquisition frequency of the sensor layer can be adaptively adjusted. The acquisition frequency of traditional industrial sensors is usually fixed, but this approach may cause resource waste or fail to respond in a timely manner to changes in the equipment status, making it difficult to meet the requirements of industrial production for high-precision data. By dynamically adjusting the sensor acquisition frequency, it is possible to more accurately obtain the key operation data of the equipment. For example, when the equipment operation status is stable, the acquisition frequency can be reduced to avoid unnecessary data redundancy; when the equipment status changes drastically, the acquisition frequency can be increased to ensure that more key data can be obtained. Through this adaptive control, it can be ensured that the acquisition of the sensor layer is more accurate and stable, thereby reducing errors and omissions during the data acquisition process. Secondly, based on the previously obtained dynamic acquisition frequency of industrial sensors, the sensor layer can perform more intelligent production data acquisition. During this process, through the adaptive acquisition frequency, the sensor can perform data acquisition at more appropriate time points to ensure the acquisition of the most accurate and valuable production data. These data not only include traditional physical parameters such as temperature, pressure, and flow rate, but also cover more complex production process data, such as the speed of the production line, the energy efficiency of the equipment, and the consumption of raw materials. These diverse data provide rich input information for subsequent production analysis and optimization. The various industrial production data collected will then be uploaded to the data analysis layer for further exploration and analysis by data analysis tools. The core task of the data analysis layer is to find potential correlation relationships from these massive amounts of data, which can be achieved through various methods, including statistical analysis, machine learning, and artificial intelligence. Through these technologies, potential correlations between different data points can be automatically discovered. For example, there is an inherent connection between a change in a certain production parameter and the failure rate of the equipment, output fluctuations, or quality degradation. This can not only help production personnel better understand the laws behind the data but also provide a scientific basis for subsequent optimization control, thereby enabling the effective integration and in-depth analysis of various data.Then, based on the potential correlation relationships among various types of industrial production data obtained through analysis, the control program layer conducts impact control analysis on the quality of the products on the production line. By deeply analyzing the correlations between different production data, it can be determined which production variables have a significant impact on the quality of the final product. For example, factors such as temperature, pressure, and production line speed are significantly correlated with quality indicators such as product size, strength, and surface quality. Through the design and optimization of the control program, production parameters can be adjusted in real time to minimize quality fluctuations and ensure the stability of product quality. This quality impact control analysis based on data correlation makes the adjustment of the production process more scientific and efficient, avoiding quality problems caused by equipment failures or operational errors, and thus enabling the rapid and accurate positioning of the root cause of the problem and the provision of effective control strategies. Finally, the generated industrial production product quality impact control program will respond and act on the corresponding industrial production process, and control the underlying operation equipment layer to perform operation optimization control by issuing instructions, adjusting the operating parameters of various equipment on the production line in real time, such as adjusting the operating speed, temperature, pressure, etc. of the equipment, thereby ensuring that the product quality is within the predetermined standard range, minimizing the uncertain factors in production to the greatest extent, and improving production efficiency and quality.

[0046] 2. The intelligent data acquisition and analysis control system proposed by the present invention is generally composed of a sensing acquisition frequency adjustment module, an industrial data correlation mining and analysis module, a production quality impact control module, and an industrial production operation optimization control module. It can implement any intelligent data acquisition and analysis control method described in the present invention, and is used to realize the intelligent data acquisition and analysis control method through the operation cooperation between computer programs running on each module. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient intelligent data acquisition and analysis control process, thereby simplifying the operation process of the intelligent data acquisition and analysis control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Other features, objectives, and advantages of the present invention will become more apparent by reading the detailed description of the non-restrictive embodiments with reference to the following drawings:

[0048] Figure 1 It is a schematic flowchart of the steps of the intelligent data acquisition and analysis control method of the present invention;

[0049] Figure 2 For Figure 1 it is a detailed schematic flowchart of step S1 in

[0050] Figure 3 For Figure 2 it is a detailed schematic flowchart of step S15 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0052] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0053] It should be understood that although terms such as "first" and "second" may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0054] To achieve the above object, please refer to Figures 1 to 2 , the present invention provides an intelligent data acquisition and analysis control method, and the method includes the following steps:

[0055] Step S1: Obtain the network dynamic change data and device operation state data corresponding to industrial devices in the underlying operation device layer during industrial production through the industrial Internet, and adaptively adjust the acquisition frequency of the sensor layer based on the network dynamic change data and the device operation state data to obtain the dynamic acquisition frequency of industrial sensors;

[0056] Step S2: Use the sensor layer to perform intelligent data acquisition on the industrial production process based on the dynamic acquisition frequency of industrial sensors to obtain various types of industrial production data; upload the various types of industrial production data to the data analysis layer, and use the data analysis layer to perform potential association mining analysis on the various types of industrial production data to obtain the potential association relationships between the various types of industrial production data;

[0057] Step S3: Generate an industrial production product quality impact control program by performing quality impact control analysis on the production line products corresponding to the industrial production process in the control program layer based on the potential association relationships between the various types of industrial production data.

[0058] Step S4: Through the industrial production product quality impact control program, it responds and acts on the corresponding industrial production process and issues instructions to control the underlying operation equipment layer for operation optimization control, generating an industrial production operation optimization control strategy to execute the corresponding industrial production equipment optimization control operation.

[0059] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the step flow of the intelligent data acquisition and analysis control method of the present invention. In this example, the intelligent data acquisition and analysis control method includes the following steps:

[0060] Step S1: Obtain the network dynamic change data and equipment operation state data corresponding to industrial equipment in the underlying operation equipment layer during the industrial production process through the industrial Internet, and adaptively adjust the acquisition frequency of the sensor layer based on the network dynamic change data and equipment operation state data to obtain the industrial sensor dynamic acquisition frequency;

[0061] In the embodiment of the present invention, the network dynamic change data and equipment operation state data of various industrial equipment in the underlying operation equipment layer are obtained through the industrial Internet platform. First, the industrial equipment uses embedded sensors to monitor and transmit various operation parameters such as temperature, pressure, vibration, and rotation speed to the central control system in real time. These data are transmitted through the industrial Internet protocol to ensure the real-time and accuracy of the data. Then, based on the transmitted data, the operation state of the industrial equipment is dynamically monitored and analyzed, and the acquisition frequency is adaptively adjusted through algorithms. It will analyze the network transmission delay, data volume, and the change trend of the equipment operation. When the equipment load is heavy or the state fluctuates, the acquisition frequency of the sensor is automatically increased, while when the equipment is in a stable state, the acquisition frequency of the sensor is decreased, thereby realizing the dynamic acquisition frequency adjustment of the sensor layer. This measure can effectively optimize the data acquisition efficiency of the sensor, reduce unnecessary redundant data transmission, ensure that the acquisition frequency matches the actual needs of the equipment, improve the resource utilization efficiency of the system, and finally obtain the industrial sensor dynamic acquisition frequency.

[0062] Step S2: Based on the industrial sensor dynamic acquisition frequency, use the sensor layer to intelligently acquire data during the industrial production process to obtain various industrial production data; upload the various industrial production data to the data analysis layer, and use the data analysis layer to perform potential correlation mining analysis on the various industrial production data to obtain the potential correlation relationships between the various industrial production data;

[0063] In the embodiments of the present invention, based on the dynamically adjusted dynamic acquisition frequency of industrial sensors, the sensor layer is used to intelligently collect various data in the industrial production process. During the production process, the sensors continuously monitor the operating status of the equipment and collect multi-dimensional data such as equipment load, temperature, humidity, air pressure, vibration, and flow. After being preprocessed by the edge computing unit to filter out irrelevant data and ensure that the uploaded data has higher accuracy and relevance, the data is then uploaded to the data analysis layer in the cloud. Through machine learning algorithms, these data are deeply mined, and data mining methods such as association analysis, clustering analysis, and regression analysis are used to identify and reveal the potential association relationships between various industrial production data. For example, by analyzing the association between equipment temperature and product quality, or the relationship between vibration frequency and equipment failure, potential production bottlenecks or abnormal trends can be discovered, and ultimately the potential association relationships between various industrial production data are obtained.

[0064] Step S3: Based on the potential association relationships between various industrial production data, perform quality impact control analysis on the corresponding production line products in the industrial production process in the control program layer to generate an industrial production product quality impact control program.

[0065] In the embodiments of the present invention, based on the potential association relationships between various industrial production data obtained through the data analysis layer, perform impact analysis of quality control in the industrial production process within the control program layer. During this process, the control system first monitors the quality data of various products on the production line in real time, analyzes the key quality parameters in the production process (such as the appearance, size, weight, etc. of the products), and through machine learning and deep learning models, comprehensively analyzes different production links, equipment operating status, and production parameters to evaluate their potential impact on product quality. For example, by comparing the data of different production batches, the influence degree of factors such as temperature, humidity, and machine vibration on the quality of the final product is identified. Based on these association analyses, the control system can generate a targeted quality impact control program, and finally generate an industrial production product quality impact control program.

[0066] Step S4: Through the industrial production product quality impact control program, respond and act on the corresponding industrial production process and issue instructions to control the underlying operation equipment layer for operation optimization control, generate an industrial production operation optimization control strategy, and execute the corresponding industrial production equipment optimization control operation.

[0067] In the embodiments of the present invention, the generated quality impact control program for industrial production products will be responsive and act on each link in the production process, controlling the underlying operation equipment layer to optimize and adjust. Specifically, the quality impact control program issues control instructions to the production equipment, and dynamically adjusts the production process according to the equipment operation status and production requirements. For example, if a quality deviation occurs in a certain production link, the working state of the equipment can be adjusted according to the data analysis results in the early stage, such as adjusting parameters such as temperature, humidity, and pressure, or reducing production defects by adjusting parameters such as equipment operation speed and rotation speed. During this process, the industrial production operation optimization control strategy will be automatically generated and issued to each device to execute specific operation optimization tasks. The equipment layer adjusts the operation mode according to the optimization instructions to ensure a high degree of matching between the equipment operation parameters and the production requirements, and finally realizes the optimal control of the production process, improving the overall quality and production efficiency of the products.

[0068] Further, step S1 includes the following steps:

[0069] Step S11: Obtain the network dynamic change data and equipment operation status data corresponding to industrial equipment in the underlying operation equipment layer during industrial production through the industrial Internet. The network dynamic change data includes the network bandwidth utilization rate, delay, and packet loss rate corresponding to industrial equipment on the industrial Internet communication link, and the equipment operation status data includes the operating temperature, operating pressure, and operating rotation speed corresponding to industrial equipment;

[0070] Step S12: Remove data noise from the network dynamic change data and equipment operation status data to obtain network change denoised data and equipment operation denoised data;

[0071] Step S13: Remove duplicates and standardize the network change denoised data and equipment operation denoised data to obtain network change standard data and equipment operation standard data;

[0072] Step S14: Perform time series synchronization analysis on the network change standard data and equipment operation standard data to obtain the corresponding network change data and equipment operation data within the same time series range;

[0073] Step S15: Based on the corresponding network change data and equipment operation data within the same time series range, adaptively adjust the acquisition frequency of the corresponding industrial sensors in the sensor layer to obtain the dynamic acquisition frequency of industrial sensors.

[0074] As an embodiment of the present invention, refer to Figure 2 shown, for Figure 1 the detailed step flow diagram of step S1 in

[0075] Step S11: Obtain the network dynamic change data and device operation status data corresponding to industrial devices in the industrial production process in the underlying operation device layer through the industrial Internet. The network dynamic change data includes the network bandwidth utilization rate, latency, and packet loss rate corresponding to industrial devices on the industrial Internet communication link, and the device operation status data includes the operating temperature, operating pressure, and operating speed corresponding to industrial devices.

[0076] In the embodiment of the present invention, relevant data generated by industrial devices in the underlying operation device layer during the production process is obtained through the industrial Internet architecture. These data include the network dynamic change data and device operation status data of the devices on the industrial Internet communication link. The network dynamic change data includes the bandwidth utilization rate, transmission latency, and packet loss rate monitored during the network transmission process of the devices. To obtain these data, network traffic monitoring tools such as SNMP (Simple Network Management Protocol) or network protocol analyzers (such as Wireshark) can be used to collect the data transmission situation between the devices and the server in real time, and then calculate the bandwidth, latency, and packet loss rate. The device operation status data includes the temperature, pressure, and speed of the industrial devices during operation in the production process. Such data can be collected in real time through an integrated device monitoring system such as a PLC (Programmable Logic Controller) or SCADA (Supervisory Control and Data Acquisition) system, and the key operation data of the devices is obtained through sensors or data acquisition modules, and finally the corresponding network dynamic change data and device operation status data are obtained.

[0077] Step S12: Remove data noise points from the network dynamic change data and device operation status data to obtain network change denoised data and device operation denoised data.

[0078] In the embodiment of the present invention, the collected network dynamic change data and device operation status data need to be processed by removing noise points. This process can be carried out using data filtering methods. For the removal of noise points from the network dynamic change data, low-pass filtering or moving average algorithms can be used to remove short-term abnormal fluctuations or noise and ensure that the data is smoother. For the device operation status data, methods such as mean filtering and weighted average filtering can be used. During the processing, abnormal values caused by external environments or sensor errors are identified and corrected. For example, during the change process of the operating temperature, pressure, or speed, if a data mutation occurs, a threshold range can be set. If the data exceeds this range, the data is considered a noise point and removed. The denoised data will retain the normal fluctuation trend, and finally the network change denoised data and device operation denoised data are obtained.

[0079] Step S13: Remove duplicates and standardize the network change denoised data and device operation denoised data to obtain network change standard data and device operation standard data.

[0080] In an embodiment of the present invention, by performing deduplication and standardization processing on the denoised network dynamic change data and device operation state data, data deduplication mainly identifies and removes data collected repeatedly in the same time period through a time window or timestamp. For example, if the same device operation state data or network data is collected at the same time point, redundant information can be automatically identified and deleted to ensure the uniqueness of the data. Data standardization processing converts data with different dimensions into a unified standardized data format, enabling various types of data to be compared and analyzed on the same scale. The Z-score standardization method can be used to convert the data into a form with zero mean and unit variance, or the maximum-minimum standardization method can be used to convert the data into values within the range of [0, 1]. Finally, network change standard data and device operation standard data are obtained.

[0081] Step S14: Perform time series synchronization analysis on the network change standard data and the device operation standard data to obtain corresponding network change data and device operation data within the same time series range;

[0082] In an embodiment of the present invention, by performing time series synchronization analysis on the standardized network change data and device operation data, to ensure the synchronization of the two types of data on the time axis, first, the data needs to be matched through timestamps to ensure that records from different data sources can correspond to the same time point. On this basis, problems such as different time precisions or data loss may be encountered. Therefore, an interpolation algorithm is used to supplement and align the data. For example, if the acquisition frequency of the device operation state data is higher than that of the network dynamic data, the device data can be adjusted to the same time scale as the network data through linear interpolation or spline interpolation. Through time series synchronization, it can be ensured that the network change data and the device operation data can correspond to the same time period, forming consistent data pairs. Finally, corresponding network change data and device operation data within the same time series range are obtained.

[0083] Step S15: Based on the corresponding network change data and device operation data within the same time series range, adaptively adjust the acquisition frequency of the corresponding industrial sensors in the sensor layer to obtain the dynamic acquisition frequency of the industrial sensors.

[0084] In an embodiment of the present invention, by adapting and adjusting the dynamic acquisition frequency of industrial sensors in the sensor layer based on the synchronized network change data and device operation data, first, by comprehensively analyzing indicators such as network bandwidth, latency, and packet loss rate, the impact of the network condition on data transmission is evaluated to determine whether it is necessary to adjust the acquisition frequency of sensor data. For example, when the network bandwidth utilization is low or the latency is large, the acquisition frequency of sensor data can be reduced to reduce the network burden and prevent network overload. While when the network condition is good and the packet loss rate is low, the acquisition frequency can be appropriately increased to obtain more refined data. During the process of data frequency adjustment, the PID control algorithm can be used to dynamically adjust the acquisition frequency of the sensor to ensure that the acquisition frequency matches the network conditions and device status, avoiding data redundancy and information loss, and at the same time ensuring the real-time and accuracy of data acquisition, and finally obtaining the dynamic acquisition frequency of industrial sensors.

[0085] Further, step S15 includes the following steps:

[0086] Step S151: Conduct a time-series change statistical analysis on the corresponding network bandwidth utilization, latency, and packet loss rate in the network change data to obtain the network time-series change amplitude, including the network bandwidth utilization change amplitude, network latency change amplitude, and network packet loss change amplitude;

[0087] Step S152: Based on the device operation data, predict the operation fluctuations of the corresponding industrial devices in the underlying operation device layer to obtain the device operation fluctuation duration;

[0088] Step S153: Based on the network time-series change amplitude and the device operation fluctuation duration, use the sensing acquisition frequency calculation formula to calculate the acquisition frequency of the corresponding industrial sensors in the sensor layer to obtain the initial acquisition frequency of the industrial sensors;

[0089] Step S154: Conduct a change trend prediction analysis on the corresponding network change data and device operation data in the same time-series range to obtain the time-series change trends corresponding to the network dynamic change and device operation status;

[0090] Step S155: Based on the time-series change trends corresponding to the network dynamic change and device operation status, adaptively adjust the initial acquisition frequency of the industrial sensors to obtain the dynamic acquisition frequency of the industrial sensors.

[0091] As an embodiment of the present invention, referring to Figure 3 shown, for Figure 2 the detailed step flow schematic diagram of step S15 in

[0092] Step S151: Conduct time-series variation statistical analysis on the corresponding network bandwidth utilization rate, latency, and packet loss rate in the network change data to obtain the network time-series variation amplitude, including the network bandwidth utilization change amplitude, network latency change amplitude, and network packet loss change amplitude;

[0093] In the embodiment of the present invention, by analyzing the network change data in detail, time-series data containing information such as network bandwidth utilization rate, latency, and packet loss rate is extracted. In specific operations, a network monitoring system is used to continuously collect network performance indicators and convert them into a time-series dataset in chronological order. When conducting time-series variation statistical analysis, standard statistical methods (such as maximum value, minimum value, standard deviation, etc.) are used to analyze the network bandwidth utilization rate, latency, and packet loss rate in each time window. These data are then used to calculate the network bandwidth utilization change amplitude, network latency change amplitude, and network packet loss change amplitude, that is, the change amplitude is equal to the ratio between the difference between the maximum value and the minimum value and the standard deviation, so as to obtain the specific amplitude range of network changes in each time period. These amplitudes reflect the degree of network dynamic changes, and finally the network time-series variation amplitude is obtained, including the network bandwidth utilization change amplitude, network latency change amplitude, and network packet loss change amplitude.

[0094] Step S152: Based on the device operation data, perform device operation fluctuation prediction on the corresponding industrial devices in the underlying job device layer to obtain the device operation fluctuation duration;

[0095] In the embodiment of the present invention, by obtaining device operation data, such as key indicators such as the operating temperature, operating pressure, and operating speed of industrial devices, the device operation data collected in real time by sensors and monitoring devices in the device layer is input into the prediction model. Using historical device operation data, the device operation fluctuations are modeled through time series analysis or machine learning models (such as ARIMA, LSTM, etc.) to predict future device fluctuations. According to these prediction results, the device operation fluctuation duration can be estimated, that is, the fluctuation duration of the device within a period of time. Specifically, the implementation of this step can judge the stability of the device state by setting thresholds and predict the duration of the fluctuation when the device operation state fluctuates greatly, and finally obtain the device operation fluctuation duration.

[0096] Step S153: Based on the network time-series variation amplitude and the device operation fluctuation duration, use the sensing acquisition frequency calculation formula to calculate the acquisition frequency of the corresponding industrial sensors in the sensor layer to obtain the initial acquisition frequency of the industrial sensors;

[0097] In the embodiment of the present invention, by combining the change amplitude of network bandwidth utilization, the change amplitude of network latency, the change amplitude of network packet loss, the device operation fluctuation duration, and relevant parameters, a suitable sensing acquisition frequency calculation formula is constructed to calculate the acquisition frequency of the corresponding industrial sensors in the sensor layer, so as to quantitatively obtain the initial acquisition frequency of the industrial sensors. Finally, the initial acquisition frequency of the industrial sensors is obtained. In addition, this sensing acquisition frequency calculation formula can also use any acquisition frequency evaluation method in the field to replace the process of acquisition frequency calculation, and is not limited to this sensing acquisition frequency calculation formula.

[0098] Step S154: Perform a change trend prediction analysis on the corresponding network change data and device operation data within the same time sequence range to obtain the time sequence change trends corresponding to the network dynamic changes and the device operation status.

[0099] In the embodiment of the present invention, by predicting the change trend of the time sequence of network change data and device operation data, first, the data of the network time sequence change amplitude and the device operation fluctuation duration are input into the trend prediction model. This model can, based on historical data and in combination with time sequence analysis methods (such as the sliding window method, trend line fitting, etc.), predict the future network dynamic change trend and device operation status change trend. These prediction results can provide forward-looking information on the network and device state changes, enabling the potential fluctuation periods or stable periods to be identified in advance. Specifically, when the change trends of network bandwidth utilization, latency, or packet loss rate tend to be stable, the device operation fluctuations also tend to be stable. This trend can be predicted and preparations can be made for the next acquisition frequency adjustment. Finally, the time sequence change trends corresponding to the network dynamic changes and the device operation status are obtained.

[0100] Step S155: Perform an adaptive adjustment on the initial acquisition frequency of the industrial sensors based on the time sequence change trends corresponding to the network dynamic changes and the device operation status to obtain the dynamic acquisition frequency of the industrial sensors.

[0101] In the embodiment of the present invention, by performing an adaptive adjustment on the initial acquisition frequency of the industrial sensors based on the network dynamic change trend and the time sequence change trend of the device operation status. Specifically, first, according to the aforementioned trend prediction, the stability of the network and the device is judged. When the network dynamic changes tend to be stable and the device operation status is stable, a preset time step (for example, 15s) is increased to increase the device operation fluctuation duration, thereby reducing the acquisition frequency; conversely, when the network changes fluctuate greatly or the device operation status fluctuates greatly, a preset time step is reduced to shorten the device operation fluctuation duration, thereby increasing the acquisition frequency. This adaptive adjustment algorithm can dynamically adjust the acquisition frequency of the sensor according to the real-time monitored data and the predicted trend to achieve the optimization of data acquisition and the efficient utilization of resources. Finally, the dynamic acquisition frequency of the industrial sensors is obtained.

[0102] Further, the specific formula for calculating the sensing acquisition frequency described in step S153 is as follows:

[0103]

[0104] In the formula, f is the initial acquisition frequency of the industrial sensor, T b is the fluctuation duration of the equipment operation, ε d is the change amplitude of the network bandwidth utilization, ε y is the change amplitude of the network delay, ε b is the change amplitude of the network packet loss, and η is the correction coefficient of the initial acquisition frequency of the industrial sensor.

[0105] The present invention obtains a sensing acquisition frequency calculation formula through the use of a specific mathematical model and verification, which is used to calculate the acquisition frequency of the corresponding industrial sensors in the sensor layer. This sensing acquisition frequency calculation formula combines network change data (such as bandwidth utilization rate, delay, packet loss rate) with the equipment operation fluctuation duration. The formula provides a dynamic and accurate initial acquisition frequency for industrial sensors. Traditional fixed acquisition frequencies cannot effectively cope with the fluctuations of network and equipment operation states. By introducing the change amplitudes of network parameters, this calculation formula can flexibly adjust the acquisition frequency of sensors according to the actual situation to adapt to environmental changes. The formula comprehensively considers the impacts of equipment fluctuations and network fluctuations, avoiding ineffective acquisitions at too high frequencies or data losses caused by too low frequencies. By optimizing the acquisition frequency according to the equipment fluctuation duration and network change amplitudes, it can balance the comprehensiveness and efficiency of data acquisition, ensuring that the sensors can capture key data without wasting redundant data due to excessive acquisitions. The formula provides an adaptive adjustment ability for the initial acquisition frequency of sensors, especially when facing network fluctuations and equipment operation fluctuations. By introducing the influence of the correction coefficient and network change amplitudes, the formula allows the acquisition frequency to be adjusted according to different operation and network environments, which can cope with uncertain changes and maximize data acquisition quality. In summary, the formula fully considers the initial acquisition frequency f of the industrial sensor, the equipment operation fluctuation duration T b , the change amplitude ε of the network bandwidth utilization d , the change amplitude ε of the network delay y , the change amplitude ε of the network packet loss b , and the correction coefficient η of the initial acquisition frequency of the industrial sensor. A functional relationship is formed according to the mutual correlation between the initial acquisition frequency f of the industrial sensor and the above parameters This formula can implement the process of calculating the acquisition frequency of the corresponding industrial sensors in the sensor layer. At the same time, by introducing the correction coefficient η of the initial acquisition frequency of the industrial sensors, it can be adjusted according to the error situation in the calculation process, thereby improving the accuracy and applicability of the formula for calculating the sensing acquisition frequency.

[0106] Further, the specific method for adaptively adjusting the initial acquisition frequency of the industrial sensors based on the network dynamic changes and the corresponding time-series change trend of the device operating state in step S155 is as follows: when the network dynamic changes tend to be stable and the device operating state tends to be stable, add a preset time step to increase the corresponding device operating fluctuation duration to reduce the acquisition frequency; when the network dynamic changes fluctuate greatly or the device operating state fluctuates greatly, reduce a preset time step to reduce the corresponding device operating fluctuation duration to increase the acquisition frequency, so as to obtain the dynamic acquisition frequency of the industrial sensors.

[0107] Further, step S2 includes the following steps:

[0108] Step S21: Based on the dynamic acquisition frequency of the industrial sensors, use the corresponding industrial sensors in the sensor layer to perform intelligent data acquisition on the industrial production process to obtain various types of industrial production data;

[0109] In the embodiment of the present invention, by arranging multiple industrial sensors in the production process to collect key production data in real time, the types of industrial sensors used include temperature sensors, pressure sensors, flow sensors, rate sensors, etc. These sensors are installed in different production links, such as furnace temperature control, compressor pressure monitoring, production line rate control, etc. The sensors will collect data at a certain period according to the dynamically quantified industrial sensor dynamic acquisition frequency obtained previously. The data acquisition frequency is dynamically adjusted based on production requirements or changes in the device state. For example, for temperature data, the sensor collects data once per second, while for pressure data, it is collected more frequently when the device load changes. The collected data includes temperature, pressure, production rate, product quality, etc., covering the real-time monitoring of the entire production process, and finally obtaining various types of industrial production data.

[0110] Step S22: Upload various types of industrial production data to the data analysis layer through the communication link corresponding to the industrial Internet;

[0111] In the embodiments of the present invention, various real-time data generated during the industrial production process need to be transmitted to the data analysis layer in a timely manner. At this time, the industrial Internet communication link plays a key role. The communication methods adopted include industrial Ethernet, 4G / 5G wireless networks, LPWAN (Low Power Wide Area Network), etc. Each sensor packs the data through the local gateway and uploads it to the cloud or the local data processing center through the communication link. During the upload process, the data will be encrypted to ensure the security and integrity during the transmission. In addition, the data transmission frequency matches the monitoring requirements of industrial production. For important data, such as pressure and temperature, the transmission frequency is higher; while for product quality data, the transmission frequency is arranged according to the production cycle. This step realizes the data transmission channel from the sensor layer to the data analysis layer, ensuring that various industrial production data can reach in real time for subsequent analysis and processing.

[0112] Step S23: Use the data analysis layer to divide various industrial production data into time segments to obtain corresponding various industrial data within the same time segment;

[0113] In the embodiments of the present invention, for the uploaded various industrial production data, segmentation processing will be performed according to a preset time interval. For example, for the collected temperature data, pressure data, and rate data, the analysis system will segment the data in units of seconds, minutes, or hours. This segmentation can be set based on production batches, work shifts, or equipment operation cycles to ensure accurate data analysis within a specific production time period. For example, within a one-hour production cycle, the temperature data collected by all sensors will be divided into multiple small time segments, and each time segment represents the data summary result within that time period. Through this time segmentation processing, it is convenient for subsequent data statistics, trend analysis, and comparison of production situations in different time periods, and finally corresponding various industrial data within the same time segment can be obtained.

[0114] Step S24: Perform correlation metric calculations between the corresponding various industrial data within the same time segment to obtain the corresponding data correlation degrees between various industrial data;

[0115] In the embodiments of the present invention, different data within the same time period are analyzed for relevance through a correlation measurement algorithm. The correlation measurement methods used include statistical methods such as the Pearson correlation coefficient and the Spearman rank correlation coefficient, which are used to evaluate the similarity and correlation between various types of industrial data. For example, for temperature and pressure data within a certain time period, the strength of the correlation between these two data will be calculated. The correlation measurement calculation process will consider multiple factors such as the change trend and fluctuation degree of the data to ensure that a true and effective correlation degree result is obtained. If the change trends of the temperature and pressure data are highly consistent, the correlation measurement value will be relatively high; otherwise, it will be relatively low. The core objective of this step is to accurately measure the relationships between various types of data in the industrial production process through mathematical models and algorithms, and finally obtain the corresponding data correlation degrees between various types of industrial data.

[0116] Step S25: Conduct potential association mining analysis on various types of industrial production data based on the corresponding data correlation degrees between various types of industrial data, and compare and judge the corresponding data correlation degrees according to a preset association threshold. If the data correlation degree is greater than or equal to the preset association threshold, there is a potential association relationship between the corresponding industrial data; if the data correlation degree is less than the preset association threshold, there is no potential association relationship between the corresponding industrial data, and the potential association relationships between various types of industrial production data are obtained.

[0117] In the embodiments of the present invention, through the correlation degrees between various types of industrial data obtained previously, further potential association mining analysis can be carried out. According to a preset correlation degree threshold, it is judged whether there is a potential association relationship between different industrial data. For example, when the calculated value of the correlation degree between temperature and pressure is greater than or equal to the preset threshold, it can be determined that there is a strong potential association relationship between temperature and pressure, which is the result of factors such as the equipment operation state and the production environment; if the correlation degree of the data is less than the threshold, it can be determined that there is no significant potential association between these two types of data. On this basis, production data pairs with high correlation degrees will be automatically marked, potential association rules will be generated, and further used as the basis for production optimization, fault warning, or quality control. Through this step, the potential relationships in the industrial production process can be revealed, and finally the potential association relationships between various types of industrial production data are obtained.

[0118] Furthermore, the various types of industrial production data described in step S21 include industrial production temperature, industrial production rate, industrial production pressure, and industrial production product quality.

[0119] Furthermore, step S3 includes the following steps:

[0120] Step S31: Based on the potential correlation relationships among various types of industrial production data, analyze the quality impact laws of the corresponding production line products during the industrial production process within the control program layer, so as to obtain the product quality impact laws corresponding to various types of industrial data in the industrial production process;

[0121] In the embodiment of the present invention, by combining the potential correlation relationships among various types of industrial production data (including industrial production temperature, industrial production rate, industrial production pressure, and industrial production product quality) obtained from previous analysis, based on the correlation among these data, a multivariate regression model or a machine learning algorithm can be established to identify the impact laws between different parameters and the final product quality. For example, in a production process, if the production temperature, rate, or production pressure of the raw materials changes, it may lead to unqualified product strength or size. Through in-depth analysis of these data, a detailed quality impact law can be obtained to clarify the specific impact degree of each data factor on the product quality, and finally, the product quality impact laws corresponding to various types of industrial data in the industrial production process are obtained.

[0122] Step S32: Based on the product quality impact laws corresponding to various types of industrial data in the industrial production process, predict the product equipment failures of the corresponding industrial equipment during the industrial production process to obtain the industrial equipment corresponding to the product quality impact failures;

[0123] In the embodiment of the present invention, by based on the previously obtained impact laws of industrial production data and product quality, further monitor and analyze the operating status of industrial equipment. In this process, the operating data of the equipment (such as temperature, pressure, vibration, power consumption, etc.) will be collected in real time and compared and analyzed with the product quality impact laws. By constructing a fault prediction model, such as a prediction model based on support vector machine (SVM) or deep neural network (DNN), combined with historical fault data, analyze the relationship between the change of equipment status and quality defects. When an abnormal parameter of a certain equipment appears and it is predicted according to the quality impact law that it will lead to product quality problems, this equipment can be automatically identified as a potential faulty equipment, and a prompt for repair or adjustment is required. This step minimizes the quality fluctuations during the production process through early warning of equipment failures, and finally obtains the industrial equipment corresponding to the product quality impact failures.

[0124] Step S33: Use the control program layer to perform fault response control on the industrial equipment corresponding to the product quality impact failures to generate an industrial production product quality impact control program.

[0125] In an embodiment of the present invention, once a device failure that affects product quality is identified, the control program layer immediately activates the fault response control mechanism. By analyzing the real-time monitoring data of the device and the fault mode, a corresponding fault response strategy is generated. For example, when a warning occurs in a certain device, the control program will automatically adjust the operating parameters of the device (such as temperature, rotation speed, etc.) and optimize the adjustment of its working state. At this time, the system can use a predetermined optimization algorithm, such as Particle Swarm Optimization (PSO) or Genetic Algorithm (GA), to generate control instructions for the device adjustment operation to ensure that the device operation returns to the normal state and avoid the occurrence of product quality problems. This fault response process is completed without manual intervention, ensuring the efficient operation of the production line and the stability of product quality, and finally generating an industrial production product quality impact control program in response.

[0126] Further, step S4 includes the following steps:

[0127] Step S41: By applying the industrial production product quality impact control program response to the corresponding industrial production process, when it is detected that the product quality in the industrial production process is abnormal or deviates from the preset target, a corresponding industrial production control instruction is generated in response.

[0128] In an embodiment of the present invention, based on the previously generated industrial production product quality impact control program, the control program layer monitors the production process in real time. When it is found that a certain product has quality abnormalities (such as dimensional deviation, color difference, etc.), the control program will immediately respond and issue corresponding control instructions to the production process. These instructions will guide the production equipment to adjust parameters to ensure that the product quality returns to the preset target. For example, when it is detected that the thickness deviation of the product in the production line exceeds the set value, the control program will automatically adjust the pressure or speed of the equipment and quickly bring the product back to the quality standard range. This process is dynamic and can be adjusted according to the real-time production data to ensure that the product meets the requirements and maintains the production efficiency, and finally generating a corresponding industrial production control instruction in response.

[0129] Step S42: Send the industrial production control instruction to the corresponding industrial equipment in the underlying operation equipment layer of the control to perform operation optimization control, generate an industrial production operation optimization control strategy, and realize the dynamic optimization of the control strategy according to the control deviation between the actual production control result and the expected target to execute the corresponding industrial production equipment optimization control operation.

[0130] In an embodiment of the present invention, the industrial production control instructions generated by the previous response are sent to the underlying operation devices for specific operation optimization. After receiving the control instructions, the operation devices adjust the working state of the devices according to the optimization control strategy. This adjustment is based on a feedback mechanism of control deviation. By calculating the difference between the actual production result and the expected target, a new control strategy is generated, and dynamic optimization operations are performed on the devices. For example, when the control instructions require reducing the production speed to improve product accuracy, the operation devices adjust the movement trajectory of the robotic arm, the speed of material transportation, or the processing parameters, etc. After each optimization cycle, the gap between the actual result and the target is compared, and the control strategy is adjusted through the feedback mechanism to make the production process continuously tend to the optimal state, ensuring the stability of product quality and the improvement of production efficiency, and finally performing the corresponding industrial production equipment optimization control operation.

[0131] Furthermore, the present invention also provides an intelligent data acquisition and analysis control system for executing the intelligent data acquisition and analysis control method as described above. The intelligent data acquisition and analysis control system includes:

[0132] A sensing acquisition frequency adjustment module, which is used to obtain the network dynamic change data and device operation state data corresponding to industrial devices in the underlying operation device layer during industrial production through the industrial Internet, and adaptively adjust the acquisition frequency of the sensor layer based on the network dynamic change data and device operation state data, so as to obtain the dynamic acquisition frequency of industrial sensors;

[0133] An industrial data correlation mining and analysis module, which is used to intelligently acquire industrial production data during industrial production through the sensor layer based on the dynamic acquisition frequency of industrial sensors to obtain various types of industrial production data; upload various types of industrial production data to the data analysis layer, and use the data analysis layer to perform potential correlation mining and analysis on various types of industrial production data, so as to obtain the potential correlation relationships between various types of industrial production data;

[0134] A production quality impact control module, which is used to perform quality impact control analysis on the products of the production line corresponding to the industrial production process in the control program layer based on the potential correlation relationships between various types of industrial production data, so as to generate an industrial production product quality impact control program;

[0135] An industrial production operation optimization control module, which is used to act on the corresponding industrial production process through the industrial production product quality impact control program and send instructions to control the underlying operation device layer for operation optimization control, generate an industrial production operation optimization control strategy, so as to perform the corresponding industrial production equipment optimization control operation.

[0136] Therefore, in all aspects, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0137] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent data collection and analysis control method, characterized in that: Applied to the industrial Internet, the industrial Internet includes a sensor layer, a data analysis layer, a control program layer and an underlying operating equipment layer, and the intelligent data collection and analysis control method includes the following steps: Step S1: Obtain the network dynamic change data and equipment operation status data corresponding to the industrial equipment in the bottom operation equipment layer during the industrial production process through the industrial Internet, and adjust the collection frequency of the sensor layer based on the network dynamic change data and the equipment operation status data to obtain the dynamic collection frequency of the industrial sensor; Step S2: Based on the dynamic acquisition frequency of industrial sensors, the sensor layer is used to perform intelligent data acquisition on the industrial production process to obtain various types of industrial production data; the various types of industrial production data are uploaded to the data analysis layer, and the data analysis layer is used to perform potential correlation mining analysis on the various types of industrial production data to obtain the potential correlation relationship between the various types of industrial production data; Step S3: Based on the potential correlation between various types of industrial production data, quality impact control analysis is performed on the corresponding production line products in the industrial production process at the control program layer to generate an industrial production product quality impact control program; Step S4: The industrial production product quality impact control program responds to the corresponding industrial production process and issues instructions to control the underlying operation equipment layer to perform operation optimization control, generate an industrial production operation optimization control strategy, and execute the corresponding industrial production equipment optimization control operation.

2. The intelligent data acquisition and analysis control method according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtaining network dynamic change data and equipment operation status data corresponding to industrial equipment in the bottom operation equipment layer during the industrial production process through the industrial Internet, wherein the network dynamic change data includes the network bandwidth utilization, delay and packet loss rate corresponding to the industrial equipment on the industrial Internet communication link, and the equipment operation status data includes the operating temperature, operating pressure and operating speed corresponding to the industrial equipment; Step S12: removing data noise from the network dynamic change data and the device operation status data to obtain network change denoised data and device operation denoised data; Step S13: De-duplicate and standardize the network change denoised data and the device operation denoised data to obtain network change standard data and device operation standard data; Step S14: Performing time sequence synchronization analysis on the network change standard data and the equipment operation standard data to obtain the corresponding network change data and equipment operation data within the same time sequence range; Step S15: Based on the corresponding network change data and equipment operation data in the same time range, the acquisition frequency of the corresponding industrial sensors in the sensor layer is adaptively adjusted to obtain the dynamic acquisition frequency of the industrial sensors.

3. The intelligent data acquisition and analysis control method according to claim 2 is characterized in that: Step S15 includes the following steps: Step S151: Performing time series variation statistical analysis on the network bandwidth utilization, delay and packet loss rate corresponding to the network variation data to obtain the network time series variation amplitude, including the network bandwidth utilization variation amplitude, the network delay variation amplitude and the network packet loss variation amplitude; Step S152: predicting equipment operation fluctuations of corresponding industrial equipment in the bottom operation equipment layer based on the equipment operation data to obtain equipment operation fluctuation duration; Step S153: Based on the network timing variation amplitude and the equipment operation fluctuation duration, the sensor acquisition frequency calculation formula is used to calculate the acquisition frequency of the corresponding industrial sensors in the sensor layer to obtain the initial acquisition frequency of the industrial sensors; Step S154: performing change trend prediction analysis on the corresponding network change data and device operation data in the same time range to obtain the time series change trend corresponding to the network dynamic change and device operation status; Step S155: Adaptively adjust the initial acquisition frequency of the industrial sensor based on the dynamic changes of the network and the time series change trend corresponding to the operation status of the equipment to obtain the dynamic acquisition frequency of the industrial sensor.

4. The intelligent data acquisition and analysis control method according to claim 3 is characterized in that: The calculation formula of the sensing acquisition frequency in step S153 is specifically: Where f is the initial acquisition frequency of the industrial sensor, T b is the fluctuation duration of equipment operation, ε d is the variation amplitude of network bandwidth utilization, ε y is the network delay variation amplitude, ε b is the amplitude of network packet loss change, and η is the correction coefficient of the initial acquisition frequency of the industrial sensor.

5. The intelligent data acquisition and analysis control method according to claim 3 is characterized in that: The step S155 described in which the initial acquisition frequency of the industrial sensor is adaptively adjusted based on the timing change trend corresponding to the dynamic change of the network and the operating status of the equipment is specifically as follows: when the dynamic change of the network tends to be stable and the operating status of the equipment tends to be stable, a preset time step is added to increase the corresponding equipment operation fluctuation duration to reduce the acquisition frequency; when the dynamic change of the network fluctuates greatly or the operating status of the equipment fluctuates greatly, a preset time step is reduced to reduce the corresponding equipment operation fluctuation duration to increase the acquisition frequency, thereby obtaining the dynamic acquisition frequency of the industrial sensor.

6. The intelligent data acquisition and analysis control method according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Based on the dynamic acquisition frequency of the industrial sensor, the corresponding industrial sensor in the sensor layer is used to perform intelligent data acquisition on the industrial production process to obtain various types of industrial production data; Step S22: Upload various types of industrial production data to the data analysis layer through the communication link corresponding to the industrial Internet; Step S23: using the data analysis layer to divide various types of industrial production data into time segments, so as to obtain various types of industrial data corresponding to the same time segment; Step S24: performing correlation metric calculation between various types of industrial data corresponding to the same time segment to obtain the corresponding data correlation between various types of industrial data; Step S25: Based on the corresponding data correlation between various types of industrial data, potential correlation mining analysis is performed on various types of industrial production data to judge the corresponding data correlation according to the preset correlation threshold. If the data correlation is greater than or equal to the preset correlation threshold, there is a potential correlation relationship between the corresponding industrial data; if the data correlation is less than the preset correlation threshold, there is no potential correlation relationship between the corresponding industrial data, and the potential correlation relationship between various types of industrial production data is obtained.

7. The intelligent data collection and analysis control method according to claim 6, characterized in that: The various types of industrial production data in step S21 include industrial production temperature, industrial production rate, industrial production pressure and industrial production product quality.

8. The intelligent data collection and analysis control method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Based on the potential correlation between various types of industrial production data, the quality influence law of the corresponding production line products in the industrial production process is analyzed in the control program layer to obtain the product quality influence law corresponding to various types of industrial data in the industrial production process; Step S32: predicting product equipment failures of industrial equipment corresponding to the industrial production process based on the product quality influencing rules corresponding to various types of industrial data in the industrial production process, so as to obtain industrial equipment corresponding to product quality influencing failures; Step S33: Utilize the control program layer to perform fault response control on industrial equipment corresponding to the fault affecting product quality, and generate an industrial production product quality impact control program.

9. The intelligent data collection and analysis control method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: by applying the industrial production product quality impact control program response to the corresponding industrial production process, when the product quality in the industrial production process is abnormal or deviates from the preset target, the corresponding industrial production control instruction is generated in response; Step S42: Send the industrial production control instructions to control the industrial equipment corresponding to the bottom-level operation equipment layer to perform operation optimization control, generate the industrial production operation optimization control strategy, and realize dynamic optimization of the control strategy according to the control deviation between the actual production control result and the expected target, so as to execute the corresponding industrial production equipment optimization control operation.

10. An intelligent data acquisition and analysis control system, characterized in that: Used to execute the intelligent data acquisition and analysis control method as claimed in claim 1, the intelligent data acquisition and analysis control system comprises: The sensor acquisition frequency adjustment module is used to obtain the network dynamic change data and equipment operation status data corresponding to the industrial equipment in the bottom operation equipment layer during the industrial production process through the industrial Internet, and to adaptively adjust the acquisition frequency of the sensor layer based on the network dynamic change data and equipment operation status data, so as to obtain the dynamic acquisition frequency of the industrial sensor; The industrial data association mining and analysis module is used to use the sensor layer to perform intelligent data collection on the industrial production process based on the dynamic collection frequency of industrial sensors to obtain various types of industrial production data; upload various types of industrial production data to the data analysis layer, and use the data analysis layer to perform potential association mining and analysis on various types of industrial production data, so as to obtain the potential association relationship between various types of industrial production data; The production quality impact control module is used to generate an industrial production product quality impact control program by performing quality impact control analysis on the corresponding production line products in the industrial production process at the control program layer based on the potential correlation between various types of industrial production data; The industrial production operation optimization control module is used to act on the corresponding industrial production process through the industrial production product quality impact control program response and issue instructions to control the underlying operation equipment layer to perform operation optimization control, generate industrial production operation optimization control strategies, and execute corresponding industrial production equipment optimization control operations.

Images