Production data identification method, system, equipment and medium based on industrial Internet of Things

Abstract

The present invention discloses a production data identification method, system, device and medium based on industrial Internet of Things, which relates to the technical field of industrial Internet of Things data processing, including obtaining data acquisition nodes and continuous time series, obtaining initial production data series, and dividing the initial production data series into multiple first production data segments; obtaining first production data fluctuation index and first overall fluctuation index based on fluctuation state model; sending the first production data segment to the data identification node, and taking the received first production data segment as the second production data segment; obtaining second production data fluctuation index and second overall fluctuation index based on fluctuation state model; obtaining production data identification result according to first production data fluctuation index, second production data fluctuation index, first overall fluctuation index and second overall fluctuation index. The present invention has the advantages of rapid and accurate identification of abnormal data and assisting subsequent data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things data processing, and in particular to a production data identification method, system, equipment and medium based on the industrial Internet of Things. Background Art

[0002] With the rapid development of the Industrial Internet of Things (IIoT), the collection, processing and analysis of production data have become key links in improving the level of intelligent manufacturing. In many industrial application scenarios, the acquisition of production data mainly depends on data collection nodes distributed in various production links. These nodes can capture various parameters and states of the production process in real time, providing an important basis for subsequent decision-making optimization.

[0003] However, in actual applications, due to the wide distribution of the Industrial Internet of Things, it is often necessary to transmit a large amount of production data from one end to another node of the Industrial Internet of Things over long distances. The transmission conditions are demanding. During the transmission process, the data is easily interfered by various external factors, such as network attacks, data tampering, etc., which leads to serious threats to the authenticity and validity of the data. On this basis, traditional data identification often focuses on data integrity verification, but it is unable to verify the authenticity and validity of the data. Especially in the face of complex and changeable industrial production environments, traditional data identification methods are difficult to accurately determine whether the data has been tampered with or forged, and cannot accurately and quickly locate abnormal data, and cannot promptly discover and deal with missing values, abnormal values ​​and other problems, and cannot provide certain help for subsequent production data processing. Summary of the invention

[0004] In view of the defects in the prior art, the present invention provides a production data identification method, system, device and medium based on industrial Internet of Things.

[0005] A production data identification method based on industrial Internet of Things includes: obtaining data collection nodes and continuous time series under the industrial Internet of Things, and obtaining an initial production data series collected by the data collection node according to the continuous time series, and dividing the initial production data series into multiple first production data segments, wherein the first production data segment includes multiple production data; obtaining a first production data fluctuation index associated with the first production data segment based on a fluctuation state model and the first production data segment, and obtaining a first overall fluctuation index based on the multiple first production data fluctuation indexes; sending the multiple first production data segments to data identification nodes in the industrial Internet of Things respectively, and sending the first overall fluctuation index and the multiple first production data fluctuation indexes to the data identification node, and using the received first production data segment as a second production data segment at the data identification node; obtaining a second production data fluctuation index associated with the second production data segment based on the fluctuation state model and the second production data segment, and obtaining a second overall fluctuation index based on the multiple second production data fluctuation indexes; obtaining a production data identification result according to the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index, and the second overall fluctuation index.

[0006] Preferably, obtaining the identification result according to the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index includes: obtaining the first difference according to the first overall fluctuation index and the second overall fluctuation index, and judging whether the first difference exceeds the first threshold value; if not, reconstructing the multiple second production data segments in time order and forming a production data sequence to be processed, and outputting the production data sequence to be processed; if exceeded, obtaining the second difference according to the first production data fluctuation index and the second production data fluctuation index associated with each second production data segment, obtaining the second production data segment whose second difference exceeds the second threshold value and using it as an abnormal production data segment, obtaining the second production data segment whose second difference does not exceed the second threshold value and using it as a normal production data segment, and outputting the abnormal production data segment and the normal production data segment.

[0007] Preferably, obtaining the first production data fluctuation index associated with the first production data segment based on the fluctuation state model and the first production data segment includes: obtaining the i-th first production data segment ; Calculation based on the wave state model The local fluctuation value of each production data in the calculation based on the fluctuation state model Fluctuation trend; based on the fluctuation state model, local fluctuation value and fluctuation trend The first indicator of production data fluctuations.

[0008] Preferably, the calculation is based on the wave state model The fluctuation state model in the local fluctuation value of each production data is expressed as: ;in, for Middle The local fluctuation value of production data, for Middle Production data, for Middle Production data.

[0009] Preferably, the calculation is based on the wave state model The fluctuation state model in the fluctuation trend of is expressed as: ;in, for The fluctuation trend of for Middle Production data, for The average value of all production data, for The amount of production data.

[0010] Preferably, based on the fluctuation state model, local fluctuation value and fluctuation trend, The fluctuation state model of the first production data fluctuation index is expressed as: ;in, for The first indicator of production data fluctuations, and is the weight coefficient.

[0011] Preferably, dividing the initial production data sequence into a plurality of first production data segments includes: dividing the initial production data sequence into a plurality of first production data segments in sequence based on a preset time window, or dividing the initial production data sequence into a plurality of first production data segments in sequence based on production event time nodes.

[0012] A production data identification system based on the industrial Internet of Things is also provided. The system includes a management platform, a sensor network platform and an object platform that are sequentially connected in communication. The sensor network platform includes: an object acquisition module, which is used to acquire data acquisition nodes and continuous time series under the industrial Internet of Things, and acquire an initial production data sequence acquired by the data acquisition node according to the continuous time series, and divide the initial production data sequence into multiple first production data segments, wherein the first production data segment includes multiple production data; a first model calculation module, which is used to acquire a first production data fluctuation index associated with the first production data segment based on a fluctuation state model and the first production data segment, and acquire a first overall fluctuation index according to the multiple first production data fluctuation indexes. Indicators; a data transmission module, used to send multiple first production data segments to the data identification node in the industrial Internet of Things respectively, and send the first overall fluctuation index and multiple first production data fluctuation indexes to the data identification node, and use the received first production data segment as the second production data segment at the data identification node; a second model calculation module, used to obtain the second production data fluctuation index associated with the second production data segment based on the fluctuation state model and the second production data segment, and obtain the second overall fluctuation index based on the multiple second production data fluctuation indicators; an identification processing module, used to obtain the production data identification result based on the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index.

[0013] An electronic device is also provided, comprising: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the above-mentioned production data identification method based on the industrial Internet of Things.

[0014] A non-temporary computer-readable storage medium is also provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned production data identification method based on the industrial Internet of Things is implemented.

[0015] The beneficial effects of the present invention are embodied in:

[0016] In the entire production data identification method based on industrial Internet of Things, a large amount of continuous initial production data is first divided into multiple smaller data segments, which reduces the complexity of data processing and improves the flexibility of data transmission, so that data can be transmitted more reliably under different network conditions; further, by introducing the fluctuation state model, the method can capture and quantify the volatility of production data, providing a solid foundation for the authenticity and validity verification of the data; further, after the data is transmitted to the data identification node, by comparing the data fluctuation indicators before and after the transmission, it can be accurately judged whether the data has been tampered with or missing during the transmission process. In addition, the overall fluctuation indicator and the fluctuation indicator of the specific data segment are comprehensively considered to provide a comprehensive evaluation of the integrity and accuracy of the data; therefore, the entire identification method not only improves the efficiency of data processing, but also enhances the security and reliability of the data, provides strong technical support for production data processing in the industrial Internet of Things environment, ensures the authenticity, accuracy and timeliness of the production data, and provides a solid foundation for subsequent production decision-making and optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0018] Figure 1 A schematic diagram of the steps of a production data identification method based on the industrial Internet of Things according to an embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of step S5 in the production data identification method based on industrial Internet of Things of the present invention;

[0020] Figure 3 It is a schematic diagram of step S2 in the production data identification method based on industrial Internet of Things of the present invention;

[0021] Figure 4 It is a schematic diagram of the steps of the production data identification method based on the industrial Internet of Things in another embodiment of the present invention;

[0022] Figure 5 It is a schematic diagram of the composition of the production data identification system based on the industrial Internet of Things of the present invention;

[0023] Figure 6 It is a schematic diagram of the composition of the optimized industrial Internet of Things involved in the present invention;

[0024] Figure 7 The present invention is a block diagram of an electronic device according to an embodiment of the present invention.

[0025] Reference numerals:

[0026] 700 - electronic device, 701 - processor, 702 - memory, 703 - multimedia component, 704 - input / output (I / O) interface, 705 - communication component. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0028] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In addition, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0030] like Figure 1 As shown, a production data identification method based on industrial Internet of Things is provided, including:

[0031] S1. Obtain a data collection node and a continuous time series under the industrial Internet of Things, and obtain an initial production data sequence collected by the data collection node according to the continuous time series, and divide the initial production data sequence into a plurality of first production data segments, wherein the first production data segment includes a plurality of production data;

[0032] S2. acquiring a first production data fluctuation index associated with the first production data segment based on the fluctuation state model and the first production data segment, and acquiring a first overall fluctuation index based on the plurality of first production data fluctuation indexes;

[0033] S3, sending the multiple first production data segments to the data identification nodes in the industrial Internet of Things respectively, sending the first overall fluctuation index and the multiple first production data fluctuation indexes to the data identification node, and using the received first production data segment as the second production data segment at the data identification node;

[0034] S4, obtaining a second production data fluctuation index associated with the second production data segment based on the fluctuation state model and the second production data segment, and obtaining a second overall fluctuation index based on the plurality of second production data fluctuation indexes;

[0035] S5. Obtain a production data identification result according to the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index.

[0036] In this embodiment, it should be noted that in S1, data collection nodes are determined from the industrial Internet of Things environment. These nodes are widely distributed in different production links and continuously collect production data; then, the system will record the initial production data collected by these nodes based on the continuous time series to form a data sequence arranged in chronological order, that is, the initial production data sequence; then, the initial production data sequence will be further subdivided into multiple first production data segments, each of which contains several production data that are continuous in time. Suppose that multiple sensors are installed on the production line of a certain automobile manufacturing plant to monitor the temperature of each link in the assembly process. The system collects data from each sensor every minute to form a continuous time series. During a production cycle of one day, the system may collect thousands of data points, which are divided into multiple first production data segments, each of which may contain all the data within an hour, which is convenient for subsequent data analysis and processing.

[0037] In summary, by dividing a large amount of initial production data into multiple smaller data segments, the segmented data is easier to process in parallel, which can reduce the complexity of data processing. At the same time, this segmented processing method also helps to improve the flexibility of data transmission, so that data can be transmitted more reliably under different network conditions, reducing data loss or delays caused by network problems; the formation of multiple first production data segments also lays the foundation for the comparison of indicators in the subsequent data identification process.

[0038] In S2, the fluctuation state model is a mathematical model used to describe the characteristics of data changing over time. In the industrial Internet of Things, it can capture and quantify the volatility of production data, which may be caused by a variety of factors. For each first production data segment, the fluctuation state model is used to calculate the corresponding production data fluctuation index. This index is unique and can represent the fluctuation characteristics of the data in the data segment. For example, the standard deviation, variance or other statistics can be used to measure the discreteness and volatility of the data. After obtaining the fluctuation indicators of multiple first production data segments, the overall fluctuation of these indicators is further calculated, that is, the first overall fluctuation index. This index is also unique and can represent the fluctuation characteristics of the entire initial production data sequence. It can be a comprehensive consideration of the average, maximum, minimum and other statistical quantities of the fluctuation indicators of each data segment, which can be obtained through mathematical methods such as weighted average, standard deviation or extreme value statistics. Due to the uniqueness of the first production data fluctuation index and the first overall fluctuation index, they can provide a solid foundation for the subsequent S3, S4 and S5 identification processes. By comparing the fluctuation indicators before and after transmission, it can be accurately determined whether the first production data segment has been tampered with or missing during the transmission process.

[0039] In S3, it is first necessary to send the previously divided multiple first production data segments from the data collection node or data storage center to the data identification node in the industrial Internet of Things. This data identification node may be a dedicated server or a group of servers, which are responsible for receiving, storing and processing these first production data segments composed of production data. At the same time, it is also necessary to send the first overall fluctuation index and multiple first production data fluctuation indexes to the data identification node. These fluctuation indexes are calculated in the S2 stage. At the data identification node, the received first production data segment is renamed as the second production data segment. In this way, the data identification node has the interrelated first production data segment, the second production data segment and the corresponding first production data fluctuation index, which provides a solid foundation for the subsequent data authenticity, validity verification and anomaly detection.

[0040] In summary, the strategy of sending multiple first production data segments separately improves the flexibility of data transmission. Due to the complex and changeable environment of the Industrial Internet of Things, network conditions may change at any time, such as bandwidth fluctuations, signal interference, etc. By sending data in segments, it can better adapt to these network conditions and ensure that data can be transmitted more reliably in different network environments; considering that the first production data segment may be affected by various factors and change during the transmission process, such as data tampering, loss or errors, etc., the received first production data segment is renamed as the second production data segment at the data identification node, in order to clearly distinguish it from the original first production data segment, so as to carry out subsequent identification and processing work.

[0041] In S4, the data identification node will use the same fluctuation state model in S2 to analyze the received second production data segment (i.e., the first production data segment after transmission). This analysis process is the same as that in S2, but the object at this time is the data after transmission. Through the fluctuation state model, the data identification node can calculate the second production data fluctuation index corresponding to each second production data segment. These indicators quantify the volatility of each data segment after transmission. After completing the calculation of the second production data fluctuation index, the data identification node will further obtain the second overall fluctuation index based on these indicators. This index is obtained after comprehensive consideration of all second production data fluctuation indicators, and it reflects the fluctuation characteristics of the entire data sequence after transmission.

[0042] In S5, the data identification node will use the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index calculated previously to identify the production data. These indicators together constitute the key basis for evaluating the integrity and accuracy of data transmission. By comparing the first production data fluctuation index with the second production data fluctuation index, it can be determined whether each specific data segment has undergone significant changes during the transmission process. At the same time, by comparing the first overall fluctuation index with the second overall fluctuation index, it can be evaluated whether the overall fluctuation characteristics of the entire data sequence after transmission are consistent with the original data. Specifically, if the second production data fluctuation index is not much different from the corresponding first production data fluctuation index, and the second overall fluctuation index is also similar to the first overall fluctuation index, it can be considered that the data transmission process maintains a high degree of stability and accuracy, and the production data identification result is "consistent" or "unchanged"; on the contrary, if there is a significant difference between the fluctuation indicators, or the overall fluctuation index has changed significantly, it may mean that the data has been interfered with or tampered with during the transmission process, and the production data identification result is "inconsistent" or "changed". At this time, further data verification or recovery operations are required to ensure the correctness of the data.

[0043] Furthermore, the data identification node will first compare and analyze the first overall volatility index and the second overall volatility index; these two indicators represent the overall volatility characteristics of the original data sequence and the data sequence after transmission, respectively. If the difference between the two is very small, that is, within the acceptable error range, this usually means that the production data maintains a high degree of stability and consistency during the transmission process, and it can be preliminarily judged that the production data is true and correct. In this case, the first production data volatility index and the second production data volatility index of each data segment can be omitted, because the consistency of the overall volatility has provided strong evidence for the authenticity of the data.

[0044] More importantly, after the production data identification results are formed, the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index can also help in the subsequent production data processing in many aspects, thereby greatly saving computing resources and improving data processing efficiency and effect. For example, according to the fluctuation index, an early warning mechanism can be set, the quality of production data can be evaluated, the trend of future production data can be predicted, and abnormal operation or potential failures of equipment can be discovered in a timely manner.

[0045] To sum up, in the entire production data identification method based on industrial Internet of Things, a large amount of continuous initial production data is first divided into multiple smaller data segments, which reduces the complexity of data processing and improves the flexibility of data transmission, so that data can be transmitted more reliably under different network conditions; further, by introducing the fluctuation state model, the method can capture and quantify the volatility of production data, providing a solid foundation for the authenticity and validity verification of the data; further, after the data is transmitted to the data identification node, by comparing the data fluctuation indicators before and after the transmission, it can be accurately judged whether the data has been tampered with or missing during the transmission process. In addition, the overall fluctuation index and the fluctuation index of the specific data segment are comprehensively considered to provide a comprehensive evaluation of the integrity and accuracy of the data; therefore, the entire identification method not only improves the efficiency of data processing, but also enhances the security and reliability of the data, provides strong technical support for production data processing in the industrial Internet of Things environment, ensures the authenticity, accuracy and timeliness of the production data, and provides a solid foundation for subsequent production decision-making and optimization.

[0046] like Figure 2 As shown, in one embodiment, S5 includes:

[0047] S51. Obtain a first difference according to the first overall volatility index and the second overall volatility index, and determine whether the first difference exceeds a first threshold;

[0048] S52, if not exceeding, reconstructing the plurality of second production data segments in time order to form a production data sequence to be processed, and outputting the production data sequence to be processed;

[0049] S53. If exceeded, obtain the second difference according to the first production data fluctuation index and the second production data fluctuation index associated with each second production data segment, obtain the second production data segment whose second difference exceeds the second threshold value and use it as the abnormal production data segment, obtain the second production data segment whose second difference does not exceed the second threshold value and use it as the normal production data segment, and output the abnormal production data segment and the normal production data segment.

[0050] In this embodiment, it should be noted that, in S51, firstly, the difference between the first overall volatility index and the second overall volatility index calculated previously, i.e., the first difference, is calculated; this first difference reflects the difference in overall volatility between the original data sequence (composed of the first production data segment) and the transmitted data sequence (composed of the second production data segment). After calculating the first difference, it is then necessary to compare it with a preset first threshold value, which is set according to the actual application scenario and data characteristics, and represents an acceptable range of volatility differences; if the first difference is less than or equal to the first threshold value, it means that the transmitted data is consistent with the original data in overall volatility, the data transmission process is relatively stable, and it can be considered that the production data has not been tampered with or missing; if the first difference is greater than the first threshold value, it means that the transmitted data is significantly different from the original data in overall volatility, which may mean that the data has been interfered with or tampered with during the transmission process, and further analysis and processing are required.

[0051] In S52, after confirming that the data transmission is stable, it is first necessary to sort the received multiple second production data segments in chronological order, because the production data is generated in a continuous time series during the production process; the sorted second production data segments are spliced ​​to reconstruct a complete production data sequence, which should be relatively consistent with the original first production data sequence in terms of overall volatility and data points, and finally the production data sequence to be processed is output, which can now serve as the basis for subsequent data analysis, processing or storage.

[0052] In S53, when the first difference exceeds the first threshold, it indicates that there may be instability or abnormality in the data transmission process. In order to further locate these problems, it is necessary to calculate the fluctuation index difference between each second production data segment and their corresponding first production data segment, that is, the second difference; this second difference is calculated by comparing the first production data fluctuation index and the second production data fluctuation index of each second production data segment; after calculating the second difference, it is compared with a preset second threshold, which is set according to data characteristics and analysis requirements, and is used to determine whether the fluctuation index difference is acceptable.

[0053] If the second difference exceeds the second threshold, it means that there is a significant difference between the second production data segment and the corresponding first production data segment, which may mean that the production data has been interfered with or tampered with during the transmission process, so the second production data segment is marked as an abnormal production data segment; if the second difference does not exceed the second threshold, it means that the second production data segment is consistent with the corresponding first production data segment, and the data transmission process is relatively stable, so it is marked as a normal production data segment.

[0054] Finally, the abnormal production data segment and the normal production data segment are output. According to the judgment result of the second difference, the system outputs the abnormal production data segment and the normal production data segment. These outputs can be used for subsequent data analysis, processing or corrective measures.

[0055] like Figure 3 As shown, in one embodiment, obtaining the first production data fluctuation index associated with the first production data segment based on the fluctuation state model and the first production data segment in S2 includes:

[0056] S21, obtaining the i-th first production data segment ;

[0057] S22, calculation based on the fluctuation state model The local fluctuation value of each production data;

[0058] S23, calculation based on the fluctuation state model Fluctuation trend;

[0059] S24, based on the fluctuation state model, local fluctuation value and fluctuation trend acquisition The first indicator of production data fluctuations.

[0060] In this embodiment, it should be noted that in S21, ; Similarly, the i-th second production data segment is , n and m represent and The number of production data in the general case, .in, for The jth production data in , j is the index of the production data, which can also represent a time point; similarly, for The lth production data in the table, l is the index of the production data, and can also represent a time point; once the index or time point is determined, the specific production data can be located.

[0061] In S22, the local fluctuation value refers to the data segment The volatility measurement of each production data and its previous production data, that is, quantifying the difference between each production data and all the production data before it in continuous time, to reflect the local fluctuation of the data segment. It reflects the real-time fluctuation degree of the data and is an important indicator for the calculation of the fluctuation state model.

[0062] In S23, the fluctuation trend is the overall change trend of the quantitative data segment. The fluctuation trend can reveal whether the data is rising, falling or remaining stable, which is very important for judging the trend changes in the production process, such as whether the output is increasing, whether the temperature is rising or falling, etc.

[0063] In S24, the local fluctuation value calculated in S22 and the fluctuation trend calculated in S23 are integrated. The local fluctuation value reflects the fluctuation degree of each data point in the data segment, while the fluctuation trend describes the change direction and speed of the data segment as a whole. In summary, the first production data fluctuation index comprehensively considers the local fluctuation value and the fluctuation trend and gives a quantitative value. Therefore, the fluctuation characteristics of the production data can be fully and quickly reflected, which is helpful to improve the recognition efficiency and effect of the production data. At the same time, the calculated first production data fluctuation index can also be used to improve the subsequent processing efficiency and effect of the production data.

[0064] It should also be noted that the second production data fluctuation index associated with the second production data segment is obtained based on the fluctuation state model and the second production data segment in S4, and the steps here are also used to complete the processing to ensure the consistency of index generation.

[0065] In one embodiment, based on the fluctuation state model calculation The fluctuation state model in the local fluctuation value of each production data is expressed as: ;in, for Middle The local fluctuation value of production data, for Middle Production data, for Middle Production data.

[0066] In this embodiment, it should be noted that The formula quantifies the local volatility of the data point by calculating the absolute difference between the j-th production data and all previous production data and finding the average value. This setting ensures that the fluctuation value of each data point is based on a comprehensive consideration of all previous data, rather than relying solely on adjacent data points, thereby more comprehensively reflecting the local fluctuation of the data segment.

[0067] Assume there is a first production data segment Contains the following production data (unit: tons): ; Now we want to calculate the local fluctuation value of the fourth production data (i.e. 105 tons) .

[0068] .

[0069] Therefore, the local fluctuation value of the 4th production data (105 tons) is 3. This value reflects the average degree of difference between this production data and the previous production data, and provides important information about data fluctuations to production managers.

[0070] In one embodiment, based on the fluctuation state model calculation The fluctuation state model in the fluctuation trend of is expressed as: ;in, for The fluctuation trend of for Middle Production data, for The average value of all production data, for The amount of production data.

[0071] In this embodiment, it should be noted that in the fluctuation state model here, by considering the difference between the data point and its average value and the position of the data point in the data segment, the formula can effectively identify the fluctuation trend of the data segment; by dividing by the sum of the squares of the distance from the data point to the midpoint of the data segment, the formula normalizes the fluctuation trend, making the fluctuation trends between different data segments comparable.

[0072] The final output It represents the average rate at which production data changes over time. If is positive, indicating that the data increases over time; if A negative value indicates that the data decreases over time. The size of indicates how fast the data changes. The larger it is, the faster the data changes. The smaller it is, the slower the data changes. The positive or negative sign and size jointly determine the direction and intensity of data changes.

[0073] Assume there is a first production data segment Contains the following production data (unit: tons): Now we want to calculate of .

[0074] First, calculate , Then, calculate , according to the formula:

[0075] Then finally Fluctuation trend for .

[0076] In one embodiment, based on the fluctuation state model, the local fluctuation value and the fluctuation trend, The fluctuation state model of the first production data fluctuation index is expressed as: ;in, for The first indicator of production data fluctuations, and is the weight coefficient.

[0077] In this embodiment, it should be noted that in this fluctuation state model, by weighted average , integrating multiple local fluctuation values ​​to ensure that the model can capture subtle changes in data at different times or under different conditions. At the same time, adding fluctuation trend terms , the long-term trend of data fluctuation is taken into account, making the model more comprehensive. and , the proportion of local fluctuations and overall trends in the final fluctuation index can be flexibly adjusted according to actual conditions to meet the needs of different production scenarios.

[0078] Based on the examples in the above implementation mode, it is known that =1.343, local fluctuation value =0, =1, =0.5, =3, =3, =1.5, n=6, set =0.7, =0.3. Then the final calculation is .

[0079] like Figure 4 As shown, in one embodiment, dividing the initial production data sequence into a plurality of first production data segments in S1 includes:

[0080] S11. Divide the initial production data sequence into a plurality of first production data segments in sequence based on a preset time window, or divide the initial production data sequence into a plurality of first production data segments in sequence based on production event time nodes.

[0081] In this embodiment, it should be noted that there may be multiple ways to divide the initial production data sequence into multiple first production data segments in S1, and two of them are proposed here.

[0082] The first method is to divide the initial production data sequence into multiple first production data segments in sequence based on a preset time window. The preset time window refers to a fixed time period, such as one day, one week, one month, etc., which is used to divide the initial production data sequence into data segments of equal length. The purpose of this division method is to align the production data with the time axis to facilitate the observation of data changes over time.

[0083] The second method is to divide the initial production data sequence into multiple first production data segments based on the time nodes of production events. Production events refer to key events that occur in the production process, such as equipment startup, shutdown, maintenance, shift change, etc. These events usually lead to significant changes in production data, so using them as the basis for dividing data segments can more accurately reflect the actual situation of the production process.

[0084] In practical applications, the above two division methods can be flexibly selected or combined according to the characteristics of production data and analysis requirements. For example, for production processes with strong periodicity, the division method based on preset time windows can be selected; while for event-driven production processes, the division method based on production event time nodes is more suitable. At the same time, you can also consider combining the two methods to more comprehensively capture the characteristics of production data.

[0085] like Figure 5 As shown, a production data identification system based on the industrial Internet of Things is also provided. The system includes a service platform, a management platform and a sensor network platform which are sequentially connected in communication. The management platform includes:

[0086] An object acquisition module is used to acquire a data acquisition node and a continuous time series under the industrial Internet of Things, and acquire an initial production data sequence acquired by the data acquisition node according to the continuous time series, and divide the initial production data sequence into a plurality of first production data segments, wherein the first production data segment includes a plurality of production data;

[0087] a first model calculation module, configured to obtain a first production data fluctuation index associated with the first production data segment based on the fluctuation state model and the first production data segment, and to obtain a first overall fluctuation index based on the plurality of first production data fluctuation indexes;

[0088] A data transmission module, used to send the plurality of first production data segments to data identification nodes in the industrial Internet of Things respectively, send the first overall fluctuation index and the plurality of first production data fluctuation indexes to the data identification node, and use the received first production data segment as the second production data segment at the data identification node;

[0089] a second model calculation module, configured to obtain a second production data fluctuation index associated with the second production data segment based on the fluctuation state model and the second production data segment, and obtain a second overall fluctuation index based on the plurality of second production data fluctuation indexes;

[0090] The identification processing module is used to obtain the production data identification result according to the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index.

[0091] In this embodiment, it should be noted that, regarding the above-mentioned production data identification system based on industrial Internet of Things, the specific method of performing the operation has been described in detail in the implementation of the production data identification method based on industrial Internet of Things, and will not be elaborated here.

[0092] It should also be noted that the entire industrial Internet of Things-based production data identification system can be applied to the optimized industrial Internet of Things, such as Figure 6 As shown, the optimized industrial Internet of Things includes a user platform, a service platform, a management platform, a sensor network platform and an object platform that establish communication in sequence;

[0093] The user platform is configured to provide front-end service functions to users; users obtain the required perceived service information through the user platform, process the perceived service information, and convert it into user perceived information; users analyze the user perceived information and make corresponding decisions based on their own wishes, and convert the user perceived information into user control information through the corresponding information system and send it to the service platform, thereby expressing the user's corresponding service demand intention.

[0094] The physical entities of the user platform include various user terminals, such as mobile phones, computers, dedicated terminals, etc., which realize user-side services through integration with user information system software.

[0095] The service platform is configured as an API server or other server used to establish communication between the management platform and the user platform to implement corresponding functions; the physical entity of the service platform includes various servers.

[0096] The management platform is configured to perform at least one of equipment operation status monitoring management, data monitoring management, equipment parameter management, and life cycle management; the management platform is an operational coordination platform for the Internet of Things, which may include various management sub-platforms, and different management sub-platforms perform different management services; the physical entities of the management platform include various servers.

[0097] The sensor network platform is configured to perform at least one of network management, command management, device status management, data protocol management, data analysis, data classification, data transmission monitoring, and data transmission security management. The sensor network platform provides data communication, analysis, identification, classification, and other functions, avoiding the direct aggregation of data from various object platforms on the management platform, resulting in redundant data on the management platform and low data processing efficiency; the physical entities of the object platform include various gateways, edge computing devices, etc.

[0098] The object platform is configured to carry out specific production work such as production control, detection, and measurement; the physical entities of the production objects include various production equipment, sensors, etc.

[0099] Figure 7 is a block diagram of an electronic device showing a production data identification method based on the industrial Internet of Things according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 may include: a processor 701 , a memory 702 . The electronic device 700 may also include one or more of a multimedia component 703 , an input / output (I / O) interface 704 , and a communication component 705 .

[0100] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned production data identification method based on the industrial Internet of Things. The memory 702 is used to store various types of data to support the operation of the electronic device 700. For example, these data may include instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, messages sent and received, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0101] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned production data identification method based on industrial Internet of Things.

[0102] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned production data identification method based on the industrial Internet of Things are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned production data identification method based on the industrial Internet of Things.

[0103] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned production data identification method based on the industrial Internet of Things when executed by the programmable device.

[0104] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0105] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0106] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A production data identification method based on industrial Internet of Things, characterized in that: include: Acquire a data collection node and a continuous time series under the industrial Internet of Things, and acquire an initial production data sequence collected by the data collection node according to the continuous time series, and divide the initial production data sequence into a plurality of first production data segments, wherein the first production data segment includes a plurality of production data; Acquire a first production data fluctuation index associated with the first production data segment based on the fluctuation state model and the first production data segment, and acquire a first overall fluctuation index based on the plurality of first production data fluctuation indexes; Wherein, the step of obtaining the first production data fluctuation index associated with the first production data segment based on the fluctuation state model and the first production data segment comprises: obtaining the i-th first production data segment ; Calculation based on the wave state model The local fluctuation value of each production data in the calculation based on the fluctuation state model Fluctuation trend; based on the fluctuation state model, local fluctuation value and fluctuation trend The first production data fluctuation indicator; Wherein, the calculation based on the fluctuation state model The fluctuation state model in the local fluctuation value of each production data is expressed as: ;in, for Middle The local fluctuation value of production data, for Middle Production data, for Middle Production data; Wherein, the calculation based on the fluctuation state model The fluctuation state model in the fluctuation trend of is expressed as: ;in, for The fluctuation trend of for Middle Production data, for The average value of all production data, for The amount of production data in sending the plurality of first production data segments to data identification nodes in the industrial Internet of Things respectively, sending the first overall fluctuation index and the plurality of first production data fluctuation indexes to the data identification node, and using the received first production data segment as the second production data segment at the data identification node; acquiring a second production data fluctuation index associated with the second production data segment based on the fluctuation state model and the second production data segment, and acquiring a second overall fluctuation index based on the plurality of second production data fluctuation indexes; The production data identification result is obtained according to the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index.

2. The production data identification method based on industrial Internet of Things according to claim 1 is characterized in that: The obtaining of the identification result according to the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index comprises: Obtaining a first difference according to the first overall volatility index and the second overall volatility index, and determining whether the first difference exceeds a first threshold; If not, reconstructing the plurality of second production data segments in time order to form a production data sequence to be processed, and outputting the production data sequence to be processed; If it exceeds, the second difference is obtained according to the first production data fluctuation index and the second production data fluctuation index associated with each second production data segment, the second production data segment whose second difference exceeds the second threshold is obtained and used as the abnormal production data segment, the second production data segment whose second difference does not exceed the second threshold is obtained and used as the normal production data segment, and the abnormal production data segment and the normal production data segment are output.

3. The production data identification method based on industrial Internet of Things according to claim 1 is characterized in that: The method is based on the fluctuation state model, the local fluctuation value and the fluctuation trend to obtain The fluctuation state model of the first production data fluctuation index is expressed as: in, for The first indicator of production data fluctuations, and is the weight coefficient.

4. The production data identification method based on industrial Internet of Things according to claim 1 is characterized in that: The step of dividing the initial production data sequence into a plurality of first production data segments comprises: The initial production data sequence is divided into a plurality of first production data segments in sequence based on a preset time window, or the initial production data sequence is divided into a plurality of first production data segments in sequence based on production event time nodes.

5. A production data identification system based on industrial Internet of Things, characterized in that: The system includes a service platform, a management platform and a sensor network platform which are connected in sequence, and the management platform includes: An object acquisition module is used to acquire a data acquisition node and a continuous time series under the industrial Internet of Things, and acquire an initial production data sequence acquired by the data acquisition node according to the continuous time series, and divide the initial production data sequence into a plurality of first production data segments, wherein the first production data segment includes a plurality of production data; a first model calculation module, configured to obtain a first production data fluctuation index associated with the first production data segment based on the fluctuation state model and the first production data segment, and to obtain a first overall fluctuation index based on the plurality of first production data fluctuation indexes; The first model calculation module is also used to: obtain the i-th first production data segment ; Calculation based on the wave state model The local fluctuation value of each production data in the calculation based on the fluctuation state model Fluctuation trend; based on the fluctuation state model, local fluctuation value and fluctuation trend The first production data fluctuation indicator; Wherein, the calculation based on the fluctuation state model The fluctuation state model in the local fluctuation value of each production data is expressed as: ;in, for Middle The local fluctuation value of production data, for Middle Production data, for Middle Production data; Wherein, the calculation based on the fluctuation state model The fluctuation state model in the fluctuation trend of is expressed as: ;in, for The fluctuation trend of for Middle Production data, for The average value of all production data, for The amount of production data in A data transmission module, used to send the plurality of first production data segments to data identification nodes in the industrial Internet of Things respectively, send the first overall fluctuation index and the plurality of first production data fluctuation indexes to the data identification node, and use the received first production data segment as the second production data segment at the data identification node; a second model calculation module, configured to obtain a second production data fluctuation index associated with the second production data segment based on the fluctuation state model and the second production data segment, and to obtain a second overall fluctuation index based on the plurality of second production data fluctuation indexes; The identification processing module is used to obtain the production data identification result according to the first production data fluctuation index, the second production data fluctuation index, the first overall fluctuation index and the second overall fluctuation index.

6. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the production data identification method based on the industrial Internet of Things as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the production data identification method based on the industrial Internet of Things described in any one of claims 1 to 4 is implemented.

Images