Data Acquisition System for Industrial Digitalization

Abstract

The present invention relates to the field of industrial collection management technology, specifically to a data collection system for industrial digitalization, including a node collaborative interference analysis module, wherein the node collaborative interference analysis module combines historical collection data to analyze the data association relationship between the industrial collection nodes to which the collection data belongs and the abnormal analysis nodes before and after self-calibration, and constructs a quantitative data association chain and a self-calibration data association chain for each abnormal analysis node. After filtering out abnormal analysis nodes through collection data, the present invention combines historical collection data to analyze the data association relationship between the industrial collection nodes to which the collection data belongs and the abnormal analysis nodes before and after self-calibration, and constructs a quantitative data association chain and a self-calibration data association chain for each abnormal analysis node; realizes dynamic quantification of abnormal risk conditions of corresponding abnormal analysis nodes, and realizes updating of risk characteristic labels mapped to industrial collection nodes; so as to dynamically adjust the transmission structure and transmission bandwidth of the corresponding collection data of the industrial collection nodes.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial data collection management, in particular to a data collection system for industrial digitization. Background Art

[0002] Sensors are the basis of industrial data collection. They can convert physical quantities into electrical signals and transmit them to data centers through the network for analysis and processing. However, during the use of sensors, they may be affected by their own factors, resulting in large deviations in sensor monitoring results, which in turn may lead to misjudgment of subsequent analysis results obtained based on the collected data, affecting the subsequent industrial processes.

[0003] In the existing industrial digital data acquisition system, data cleaning is often performed on the collection results obtained by the industrial collection nodes before data analysis. However, this method has a major defect. If the sensor has continuous deviation data due to itself or external factors, it may not be filtered out during data cleaning, which will interfere with the subsequent data analysis results.

[0004] At the same time, the existing technology often transmits abnormal data together with normal data when transmitting collected data, and then screens the abnormal data from the overall transmitted data for analysis during data analysis. The screening process involves a large amount of data and a long screening time, which affects the timeliness of the subsequent data analysis result feedback. Summary of the invention

[0005] The object of the present invention is to provide a data acquisition system for industrial digitization to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a data acquisition system for industrial digitization, the system comprising:

[0007] An abnormal analysis node acquisition module, wherein the abnormal analysis node acquisition module acquires the acquisition data of the corresponding sensors in each industrial acquisition node at different times, and compares the acquired acquisition data with the acquisition threshold interval corresponding to the corresponding industrial acquisition node, and locks the abnormal acquisition data and the abnormal analysis node corresponding to the abnormal acquisition data;

[0008] A node collaborative interference analysis module, which combines historical collection data, analyzes the data association relationship between the industrial collection nodes and the abnormal analysis nodes before and after the collection data is self-calibrated, and constructs a quantitative data association chain and a self-calibration data association chain for each abnormal analysis node;

[0009] A risk determination analysis module, wherein the risk determination analysis module obtains the risk characteristic labels mapped to each industrial collection node in the current time database, the quantitative data association chain and the self-calibration data association chain of each abnormal analysis node, and analyzes the first risk assessment value and the second risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain and the self-calibration data association chain based on the collection data corresponding to each abnormal analysis node at the current time; and obtains the abnormal risk coefficient of each abnormal analysis node;

[0010] The risk feature update and transmission management module updates the risk feature label corresponding to each industrial collection node based on the abnormal risk coefficient of each abnormal analysis node; summarizes the abnormal analysis nodes, and adjusts the transmission structure and transmission bandwidth of the corresponding collection data of the industrial collection nodes.

[0011] Furthermore, the abnormal analysis node is an industrial collection node;

[0012] The collection threshold interval corresponding to the industrial collection node represents the preset interval corresponding to the collection data of the sensor in the corresponding industrial collection node under normal conditions;

[0013] When locking abnormal collected data, the collected data that does not belong to the collection threshold interval corresponding to the corresponding industrial collection node is recorded as abnormal data;

[0014] The industrial collection node corresponding to each abnormal collection data is recorded as the abnormal analysis node corresponding to the corresponding abnormal collection data, and each abnormal collection data corresponds to an abnormal analysis node.

[0015] Furthermore, the node cooperative interference analysis module includes a quantization data association chain construction unit and a self-calibration data association chain construction unit.

[0016] The quantitative data association chain construction unit combines historical collection data, analyzes the data association relationship between the industrial collection node to which the collection data belongs and the abnormal analysis node before self-calibration, and constructs a quantitative data association chain for each abnormal analysis node;

[0017] The self-calibration data association chain construction unit combines historical collection data, analyzes the data association relationship between the industrial collection node to which the collection data belongs after self-calibration and the abnormal analysis node, and constructs a self-calibration data association chain for each abnormal analysis node.

[0018] Further, the summary data of each industrial collected data before the self-calibration of the collected data is performed in the historical collected data is obtained, which is recorded as the non-self-calibrated summary data set; the summary data of each industrial collected data after the self-calibration of the collected data is performed in the historical collected data is recorded as the self-calibrated summary data set; the self-calibration operation is an operation to check the abnormal data caused by the sensor itself in the collected data;

[0019] When constructing the quantitative data association chain of each abnormal analysis node, any abnormal analysis node is recorded as Ap, and the time point at which abnormal data appears each time in the uncalibrated summary data set is obtained, and the time interval surrounded by the time points corresponding to the consecutive abnormal data is recorded as an abnormal time interval, and the corresponding abnormal time interval corresponding to the non-consecutive abnormal data only contains one time point;

[0020] Obtain all the abnormal analysis nodes in the remaining abnormal analysis nodes except Ap in the uncalibrated summary data set, whose corresponding abnormal time intervals and Apm have a non-empty intersection as the secondary association chain nodes of Ap based on Apm; the Apm represents the mth abnormal time interval corresponding to Ap; when the statistics m is different values, the elements in the union of each secondary association chain node of Ap based on Apm are all used as the secondary association chain nodes of Ap; the secondary association chain nodes of Ap are used as the analysis objects, and all the elements in the secondary association chain nodes of the analysis objects that do not belong to Ap and its secondary association chain nodes are used as the third-level association chain nodes of Ap, ..., and so on, until there is no abnormal analysis node associated with Ap, and the association chain nodes of each level corresponding to Ap are obtained; each association chain node in the association chain nodes of each level corresponding to Ap is connected with the chain nodes that have an intersection with the secondary association chain nodes of the previous level association chain nodes, to obtain the quantitative data association chain of Ap;

[0021] When constructing the self-calibration data association chain of each abnormal analysis node, the data association chain obtained by replacing the uncalibrated summary data set in the process of obtaining the quantitative data association chain of Ap with the self-calibration summary data set is recorded as the self-calibration data association chain of Ap.

[0022] The present invention constructs a quantitative data association chain and a self-calibration data association chain for each abnormal analysis node in order to analyze the abnormal risk situation of the abnormal analysis node data from different levels. The quantitative data association chain can reflect the risk situation of the abnormal data of the abnormal analysis node as a whole. However, the abnormal data appearing in this case is composed of two aspects. On the one hand, it is the abnormal quantitative result of the corresponding monitoring environment in the sensor monitoring scene, and on the other hand, it is the abnormal situation of the monitoring result caused by the sensor's own factors when the corresponding monitoring environment in the sensor monitoring scene is normal; and the self-calibration data association chain is the feedback of the risk situation of the abnormal data in the corresponding abnormal analysis node after excluding the abnormal situation of the monitoring result caused by the sensor's own factors.

[0023] Furthermore, the risk determination analysis module includes a risk assessment value analysis unit and an abnormal risk coefficient calculation unit.

[0024] The risk assessment value analysis unit obtains the risk characteristic labels mapped to each industrial collection node in the current time database, the quantitative data association chain and the self-calibration data association chain of each abnormal analysis node, and analyzes the first risk assessment value and the second risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain and the self-calibration data association chain based on the collection data corresponding to each abnormal analysis node at the current time;

[0025] The abnormal risk coefficient calculation unit obtains the abnormal risk coefficient of each abnormal analysis node based on the first risk assessment value and the second risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain and the self-calibration data association chain.

[0026] Furthermore, when analyzing each abnormal analysis node based on the first risk assessment value of the corresponding quantitative data association chain, the risk characteristic labels mapped by each industrial acquisition node in the current time database and the quantitative data association chain of each abnormal analysis node are obtained, and the risk characteristic labels include risk hidden danger status labels and safety status labels;

[0027] The first risk assessment value of the nth abnormal analysis node based on the corresponding quantitative data association chain is recorded as GFn.

[0028] ,

[0029] Wherein, Rn represents the number of chain nodes whose mapped risk characteristic labels are risk hidden danger status labels in the quantitative data association chain of the nth abnormal analysis node at the current time;

[0030] U(n, g) represents the set of link path segments from the g-th chain node to the n-th abnormal analysis node, where the risk characteristic label mapped is the risk hidden danger status label in the quantitative data association chain of the n-th abnormal analysis node at the current time; each link path segment corresponds to a path from the n-th abnormal analysis node to the g-th chain node, where the risk characteristic label mapped is the risk hidden danger status label in the quantitative data association chain of the n-th abnormal analysis node;

[0031] B {U（n，g），h} It represents the ratio of the number of chain nodes whose risk characteristic labels are mapped to risk potential status labels in the link segment corresponding to the h-th element in U (n, g) to the total number of chain nodes in the corresponding link segment; Hg represents the total number of elements in U (n, g);

[0032] NUMx {U（n，g），h} It indicates the number of times in the historical data that the same risk characteristic label as that mapped to each link node in the link segment corresponding to the hth element in U(n, g) appears;

[0033] NUMy {U（n，g），h}It indicates the number of times in the historical data that the risk characteristic labels mapped to the chain nodes in the link segment corresponding to the hth element in U (n, g) are the same, and the risk characteristic label mapped to the nth abnormal analysis node is the risk hidden danger status label;

[0034] When NUMx {U（n，g），h} =0,

[0035] ,

[0036] When NUMx {U（n，g），h} ≠0,

[0037] .

[0038] Further, when analyzing the second risk assessment value of each abnormal analysis node based on the corresponding self-calibration data association chain, the risk characteristic label mapped by each industrial acquisition node in the current time database and the self-calibration data association chain of each abnormal analysis node are obtained.

[0039] The second risk assessment value of the nth abnormal analysis node based on the corresponding self-calibration data association chain is recorded as GSn.

[0040] The calculation result obtained by replacing the analysis object in the calculation process of GFn from the quantitative data association chain of the nth abnormal analysis node to the self-calibration data association chain of the nth abnormal analysis node is recorded as GSn.

[0041] Furthermore, when obtaining the abnormal risk coefficient of each abnormal analysis node, the abnormal risk coefficient of the i-th abnormal analysis node is recorded as Yi,

[0042] Yi = GFn + μ · GSn,

[0043] Wherein, GFn represents the first risk assessment value of the nth abnormal analysis node based on the corresponding quantitative data association chain;

[0044] GSn represents the second risk assessment value of the nth abnormal analysis node based on the corresponding self-calibration data association chain;

[0045] μ represents the risk conversion factor.

[0046] Furthermore, the risk feature update and transmission management module includes a risk feature label update unit and a transmission management unit.

[0047] The risk characteristic label updating unit updates the risk characteristic label corresponding to each industrial collection node based on the abnormal risk coefficient of each abnormal analysis node;

[0048] The transmission management unit summarizes the abnormal analysis nodes and adjusts the transmission structure and transmission bandwidth of the industrial collection nodes corresponding to the collected data;

[0049] When the risk characteristic labels corresponding to the industrial acquisition nodes are updated, the abnormal risk coefficients of the abnormal analysis nodes are obtained, and the risk characteristic labels of all abnormal analysis nodes whose abnormal risk coefficients are greater than or equal to the preset abnormal risk coefficient value are adjusted to risk hidden danger state labels, and the risk characteristic labels of all remaining industrial acquisition nodes are adjusted to safe state labels;

[0050] In the present invention, the risk characteristic label corresponding to each industrial collection node is updated, which can provide data support for the subsequent management and control of abnormal analysis nodes in each industrial collection node.

[0051] When adjusting the transmission structure and transmission bandwidth of the collected data corresponding to the industrial collection node, the collected data obtained in the industrial collection node is transmitted to the nearest edge computing node, and the edge computing node adjusts the data transmission structure of the obtained collected data according to the updated risk characteristic label; the data transmission structure includes a first transmission channel and a second transmission channel; in the edge computing node, the collected data corresponding to all industrial collection nodes whose updated risk characteristic labels are safety status labels are transmitted to the data center through the first transmission channel, and the collected data corresponding to all industrial collection nodes whose updated risk characteristic labels are risk hidden danger status labels are transmitted to the data center through the second transmission channel; when adjusting the transmission bandwidth, when the total transmission bandwidth of the edge computing node remains unchanged, the transmission bandwidth of each transmission channel is adjusted in proportion to the capacity ratio of the data to be transmitted in the first transmission channel and the second transmission channel.

[0052] The present invention realizes regional aggregation of the collected data corresponding to the industrial collection nodes through edge computing nodes, and realizes dynamic adjustment of the data transmission structure and transmission bandwidth according to the updated risk characteristic labels of the industrial collection nodes described in the aggregated data.

[0053] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: after filtering out abnormal analysis nodes through collected data, the present invention combines historical collected data to analyze the data association relationship between the industrial collection nodes to which the collected data belongs and the abnormal analysis nodes before and after self-calibration, and constructs a quantitative data association chain and a self-calibration data association chain for each abnormal analysis node; and based on the conditions of each chain node in the quantitative data association chain and the self-calibration data association chain, respectively, realizes dynamic quantification of the abnormal risk conditions of the corresponding abnormal analysis nodes, and realizes the update of the risk characteristic labels mapped to the industrial collection nodes; so as to dynamically adjust the transmission structure and transmission bandwidth of the collected data corresponding to the industrial collection nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0055] Figure 1 It is a structural schematic diagram of the data acquisition system for industrial digitization of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] See also Figure 1 The present invention provides a technical solution: a data acquisition system for industrial digitization, the system comprising:

[0058] An abnormal analysis node acquisition module, wherein the abnormal analysis node acquisition module acquires the acquisition data of the corresponding sensors in each industrial acquisition node at different times, and compares the acquired acquisition data with the acquisition threshold interval corresponding to the corresponding industrial acquisition node, and locks the abnormal acquisition data and the abnormal analysis node corresponding to the abnormal acquisition data;

[0059] The abnormal analysis node is an industrial collection node;

[0060] The collection threshold interval corresponding to the industrial collection node represents the preset interval corresponding to the collection data of the sensor in the corresponding industrial collection node under normal conditions;

[0061] When locking abnormal collected data, the collected data that does not belong to the collection threshold interval corresponding to the corresponding industrial collection node is recorded as abnormal data;

[0062] The industrial collection node corresponding to each abnormal collection data is recorded as the abnormal analysis node corresponding to the corresponding abnormal collection data, and each abnormal collection data corresponds to an abnormal analysis node.

[0063] A node collaborative interference analysis module, wherein the node collaborative interference analysis module includes a quantized data association chain construction unit and a self-calibration data association chain construction unit,

[0064] The quantitative data association chain construction unit combines historical collection data, analyzes the data association relationship between the industrial collection node to which the collection data belongs and the abnormal analysis node before self-calibration, and constructs a quantitative data association chain for each abnormal analysis node;

[0065] The self-calibration data association chain construction unit combines historical collection data, analyzes the data association relationship between the industrial collection node to which the collection data belongs after self-calibration and the abnormal analysis node, and constructs a self-calibration data association chain for each abnormal analysis node.

[0066] Obtain summary data of each industrial collected data before self-calibration of collected data is performed in the historical collected data, and record it as a non-self-calibrated summary data set; obtain summary data of each industrial collected data after self-calibration of collected data is performed in the historical collected data, and record it as a self-calibrated summary data set;

[0067] The self-calibration operation in this embodiment is an operation to check for abnormal data in the collected data caused by the sensor's own factors, such as a situation where a certain monitoring result of the sensor has a large deviation due to its own accidental factors, but the subsequent monitoring result returns to normal; this situation is determined by the performance of the sensor itself, and the probability of avoiding it is low;

[0068] When constructing the quantitative data association chain of each abnormal analysis node, any abnormal analysis node is recorded as Ap, and the time point at which abnormal data appears each time in the uncalibrated summary data set is obtained, and the time interval surrounded by the time points corresponding to the consecutive abnormal data is recorded as an abnormal time interval, and the corresponding abnormal time interval corresponding to the non-consecutive abnormal data only contains one time point;

[0069] Obtain all the abnormal analysis nodes in the remaining abnormal analysis nodes except Ap in the uncalibrated summary data set, whose corresponding abnormal time intervals and Apm have a non-empty intersection as the secondary association chain nodes of Ap based on Apm; the Apm represents the mth abnormal time interval corresponding to Ap; when the statistics m is different values, the elements in the union of each secondary association chain node of Ap based on Apm are all used as the secondary association chain nodes of Ap; the secondary association chain nodes of Ap are used as the analysis objects, and all the elements in the secondary association chain nodes of the analysis objects that do not belong to Ap and its secondary association chain nodes are used as the third-level association chain nodes of Ap, ..., and so on, until there is no abnormal analysis node associated with Ap, and the association chain nodes of each level corresponding to Ap are obtained; each association chain node in the association chain nodes of each level corresponding to Ap is connected with the chain nodes that have an intersection with the secondary association chain nodes of the previous level association chain nodes, to obtain the quantitative data association chain of Ap;

[0070] In this embodiment, if there are five industrial collection nodes, namely, Ap, A, B, C, and D,

[0071] If Ap is an abnormal analysis node, and A and B are both the second-level associated nodes of Ap, B and C are both the second-level associated nodes of A, and D is not associated with Ap, A, B, and C respectively.

[0072] The quantitative data association chain corresponding to Ap includes two branches, namely: Ap→A→C, Ap→B; in this process, A is the secondary association chain node of Ap. From the perspective of A, although B is considered a tertiary association chain node of Ap, since B is already included in the secondary association node of Ap, B is still regarded as a secondary association chain node of Ap at this time. Therefore, the constructed branch chain is Ap→A→C, rather than Ap→A→C and Ap→A→B.

[0073] When constructing the self-calibration data association chain of each abnormal analysis node, the data association chain obtained by replacing the uncalibrated summary data set in the process of obtaining the quantitative data association chain of Ap with the self-calibration summary data set is recorded as the self-calibration data association chain of Ap.

[0074] A risk determination analysis module, the risk determination analysis module includes a risk assessment value analysis unit and an abnormal risk coefficient calculation unit,

[0075] The risk assessment value analysis unit obtains the risk characteristic labels mapped to each industrial collection node in the current time database, the quantitative data association chain and the self-calibration data association chain of each abnormal analysis node, and analyzes the first risk assessment value and the second risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain and the self-calibration data association chain based on the collection data corresponding to each abnormal analysis node at the current time;

[0076] The abnormal risk coefficient calculation unit obtains the abnormal risk coefficient of each abnormal analysis node based on the first risk assessment value and the second risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain and the self-calibration data association chain.

[0077] When analyzing the first risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain, the risk characteristic labels mapped by each industrial acquisition node in the current time database and the quantitative data association chain of each abnormal analysis node are obtained, wherein the risk characteristic labels include risk hidden danger status labels and safety status labels;

[0078] The first risk assessment value of the nth abnormal analysis node based on the corresponding quantitative data association chain is recorded as GFn.

[0079] ,

[0080] Wherein, Rn represents the number of chain nodes whose mapped risk characteristic labels are risk hidden danger status labels in the quantitative data association chain of the nth abnormal analysis node at the current time;

[0081] U(n, g) represents the set of link path segments from the g-th chain node to the n-th abnormal analysis node, where the risk characteristic label mapped is the risk hidden danger status label in the quantitative data association chain of the n-th abnormal analysis node at the current time; each link path segment corresponds to a path from the n-th abnormal analysis node to the g-th chain node, where the risk characteristic label mapped is the risk hidden danger status label in the quantitative data association chain of the n-th abnormal analysis node;

[0082] B {U（n，g），h} It represents the ratio of the number of chain nodes whose risk characteristic labels are mapped to risk potential status labels in the link segment corresponding to the h-th element in U (n, g) to the total number of chain nodes in the corresponding link segment; Hg represents the total number of elements in U (n, g);

[0083] NUMx {U（n，g），h} It indicates the number of times in the historical data that the same risk characteristic label as that mapped to each link node in the link segment corresponding to the hth element in U(n, g) appears;

[0084] NUMy {U（n，g），h} It indicates the number of times in the historical data that the risk characteristic labels mapped to the chain nodes in the link segment corresponding to the hth element in U (n, g) are the same, and the risk characteristic label mapped to the nth abnormal analysis node is the risk hidden danger status label;

[0085] When NUMx {U（n，g），h} =0,

[0086] ,

[0087] When NUMx {U（n，g），h} ≠0,

[0088] .

[0089] When analyzing the second risk assessment value of each abnormal analysis node based on the corresponding self-calibration data association chain, the risk characteristic label mapped by each industrial acquisition node in the current time database and the self-calibration data association chain of each abnormal analysis node are obtained.

[0090] The second risk assessment value of the nth abnormal analysis node based on the corresponding self-calibration data association chain is recorded as GSn.

[0091] The calculation result obtained by replacing the analysis object in the calculation process of GFn from the quantitative data association chain of the nth abnormal analysis node to the self-calibration data association chain of the nth abnormal analysis node is recorded as GSn.

[0092] When obtaining the abnormal risk coefficient of each abnormal analysis node, the abnormal risk coefficient of the i-th abnormal analysis node is recorded as Yi,

[0093] Yi = GFn + μ · GSn,

[0094] Wherein, GFn represents the first risk assessment value of the nth abnormal analysis node based on the corresponding quantitative data association chain;

[0095] GSn represents the second risk assessment value of the nth abnormal analysis node based on the corresponding self-calibration data association chain;

[0096] μ represents the risk conversion factor.

[0097] A risk feature update and transmission management module, the risk feature update and transmission management module includes a risk feature label update unit and a transmission management unit,

[0098] The risk characteristic label updating unit updates the risk characteristic label corresponding to each industrial collection node based on the abnormal risk coefficient of each abnormal analysis node;

[0099] The transmission management unit summarizes the abnormal analysis nodes and adjusts the transmission structure and transmission bandwidth of the industrial collection nodes corresponding to the collected data;

[0100] When the risk characteristic labels corresponding to the industrial acquisition nodes are updated, the abnormal risk coefficients of the abnormal analysis nodes are obtained, and the risk characteristic labels of all abnormal analysis nodes whose abnormal risk coefficients are greater than or equal to the preset abnormal risk coefficient value are adjusted to risk hidden danger state labels, and the risk characteristic labels of all remaining industrial acquisition nodes are adjusted to safe state labels;

[0101] When adjusting the transmission structure and transmission bandwidth of the collected data corresponding to the industrial collection node, the collected data obtained in the industrial collection node is transmitted to the nearest edge computing node, and the edge computing node adjusts the data transmission structure of the obtained collected data according to the updated risk characteristic label; the data transmission structure includes a first transmission channel and a second transmission channel; in the edge computing node, the collected data corresponding to all industrial collection nodes whose updated risk characteristic labels are safety status labels are transmitted to the data center through the first transmission channel, and the collected data corresponding to all industrial collection nodes whose updated risk characteristic labels are risk hidden danger status labels are transmitted to the data center through the second transmission channel; when adjusting the transmission bandwidth, when the total transmission bandwidth of the edge computing node remains unchanged, the transmission bandwidth of each transmission channel is adjusted in proportion to the capacity ratio of the data to be transmitted in the first transmission channel and the second transmission channel.

[0102] In this embodiment, the adjusted transmission bandwidth of the first transmission channel is equal to the ratio of the capacity of the data to be transmitted in the first transmission channel in the corresponding edge computing node to the total capacity of the data to be transmitted in the corresponding edge computing node multiplied by the total transmission bandwidth of the corresponding edge computing node; the adjusted transmission bandwidth of the second transmission channel is equal to the difference between the total transmission bandwidth of the corresponding edge computing node and the transmission bandwidth of the corresponding first transmission channel.

[0103] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0104] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Data acquisition system for industrial digitization, characterized in that: The system comprises: An abnormal analysis node acquisition module, wherein the abnormal analysis node acquisition module acquires the acquisition data of the corresponding sensors in each industrial acquisition node at different times, and compares the acquired acquisition data with the acquisition threshold interval corresponding to the corresponding industrial acquisition node, and locks the abnormal acquisition data and the abnormal analysis node corresponding to the abnormal acquisition data; A node collaborative interference analysis module, which combines historical collection data, analyzes the data association relationship between the industrial collection nodes and the abnormal analysis nodes before and after the collection data is self-calibrated, and constructs a quantitative data association chain and a self-calibration data association chain for each abnormal analysis node; A risk determination analysis module, wherein the risk determination analysis module obtains the risk characteristic labels mapped to each industrial collection node in the current time database, the quantitative data association chain and the self-calibration data association chain of each abnormal analysis node, and analyzes the first risk assessment value and the second risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain and the self-calibration data association chain based on the collection data corresponding to each abnormal analysis node at the current time; and obtains the abnormal risk coefficient of each abnormal analysis node; The risk feature update and transmission management module updates the risk feature label corresponding to each industrial collection node based on the abnormal risk coefficient of each abnormal analysis node; summarizes the abnormal analysis nodes, and adjusts the transmission structure and transmission bandwidth of the corresponding collection data of the industrial collection nodes.

2. The industrial digital data acquisition system according to claim 1, characterized in that: The abnormal analysis node is an industrial collection node; The collection threshold interval corresponding to the industrial collection node represents the preset interval corresponding to the collection data of the sensor in the corresponding industrial collection node under normal conditions; When locking abnormal collected data, the collected data that does not belong to the collection threshold interval corresponding to the corresponding industrial collection node is recorded as abnormal data; The industrial collection node corresponding to each abnormal collection data is recorded as the abnormal analysis node corresponding to the corresponding abnormal collection data, and each abnormal collection data corresponds to an abnormal analysis node.

3. The industrial digital data acquisition system according to claim 1, characterized in that: The node cooperative interference analysis module includes a quantized data association chain construction unit and a self-calibration data association chain construction unit. The quantitative data association chain construction unit combines historical collection data, analyzes the data association relationship between the industrial collection node to which the collection data belongs and the abnormal analysis node before self-calibration, and constructs a quantitative data association chain for each abnormal analysis node; The self-calibration data association chain construction unit combines historical collection data, analyzes the data association relationship between the industrial collection node to which the collection data belongs after self-calibration and the abnormal analysis node, and constructs a self-calibration data association chain for each abnormal analysis node.

4. The industrial digital data acquisition system according to claim 3, characterized in that: Obtain summary data of each industrial collected data before self-calibration of collected data is performed in the historical collected data, and record it as a non-self-calibrated summary data set; obtain summary data of each industrial collected data after self-calibration of collected data is performed in the historical collected data, and record it as a self-calibrated summary data set; When constructing the quantitative data association chain of each abnormal analysis node, any abnormal analysis node is recorded as Ap, and the time point at which abnormal data appears each time in the uncalibrated summary data set is obtained, and the time interval surrounded by the time points corresponding to the consecutive abnormal data is recorded as an abnormal time interval, and the corresponding abnormal time interval corresponding to the non-consecutive abnormal data only contains one time point; Obtain all the abnormal analysis nodes in the remaining abnormal analysis nodes except Ap in the uncalibrated summary data set, whose corresponding abnormal time intervals and Apm have a non-empty intersection as the secondary association chain nodes of Ap based on Apm; the Apm represents the mth abnormal time interval corresponding to Ap; when the statistics m is different values, the elements in the union of each secondary association chain node of Ap based on Apm are all used as the secondary association chain nodes of Ap; the secondary association chain nodes of Ap are used as the analysis objects, and all the elements in the secondary association chain nodes of the analysis objects that do not belong to Ap and its secondary association chain nodes are used as the third-level association chain nodes of Ap, ..., and so on, until there is no abnormal analysis node associated with Ap, and the association chain nodes of each level corresponding to Ap are obtained; each association chain node in the association chain nodes of each level corresponding to Ap is connected with the chain nodes that have an intersection with the secondary association chain nodes of the previous level association chain nodes, to obtain the quantitative data association chain of Ap; When constructing the self-calibration data association chain of each abnormal analysis node, the data association chain obtained by replacing the uncalibrated summary data set in the process of obtaining the quantitative data association chain of Ap with the self-calibration summary data set is recorded as the self-calibration data association chain of Ap.

5. The industrial digital data acquisition system according to claim 1, characterized in that: The risk determination analysis module includes a risk assessment value analysis unit and an abnormal risk coefficient calculation unit. The risk assessment value analysis unit obtains the risk characteristic labels mapped to each industrial collection node in the current time database, the quantitative data association chain and the self-calibration data association chain of each abnormal analysis node, and analyzes the first risk assessment value and the second risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain and the self-calibration data association chain based on the collection data corresponding to each abnormal analysis node at the current time; The abnormal risk coefficient calculation unit obtains the abnormal risk coefficient of each abnormal analysis node based on the first risk assessment value and the second risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain and the self-calibration data association chain.

6. The data acquisition system for industrial digitization according to claim 5, characterized in that: When analyzing the first risk assessment value of each abnormal analysis node based on the corresponding quantitative data association chain, the risk characteristic labels mapped by each industrial acquisition node in the current time database and the quantitative data association chain of each abnormal analysis node are obtained, wherein the risk characteristic labels include risk hidden danger status labels and safety status labels; The first risk assessment value of the nth abnormal analysis node based on the corresponding quantitative data association chain is recorded as GFn. ， Wherein, Rn represents the number of chain nodes whose mapped risk characteristic labels are risk hidden danger status labels in the quantitative data association chain of the nth abnormal analysis node at the current time; U(n, g) represents the set of link path segments from the g-th chain node to the n-th abnormal analysis node, where the risk characteristic label mapped is the risk hidden danger status label in the quantitative data association chain of the n-th abnormal analysis node at the current time; each link path segment corresponds to a path from the n-th abnormal analysis node to the g-th chain node, where the risk characteristic label mapped is the risk hidden danger status label in the quantitative data association chain of the n-th abnormal analysis node; B {U（n，g），h} It represents the ratio of the number of chain nodes whose risk characteristic labels are mapped to risk potential status labels in the link segment corresponding to the h-th element in U (n, g) to the total number of chain nodes in the corresponding link segment; Hg represents the total number of elements in U (n, g); NUMx {U（n，g），h} It indicates the number of times in the historical data that the same risk characteristic label as that mapped to each link node in the link segment corresponding to the hth element in U(n, g) appears; NUMy {U（n，g），h} It indicates the number of times in the historical data that the risk characteristic labels mapped to the chain nodes in the link segment corresponding to the hth element in U (n, g) are the same, and the risk characteristic label mapped to the nth abnormal analysis node is the risk hidden danger status label; When NUMx {U（n，g），h} =0, ， When NUMx {U（n，g），h} ≠0, 。 7. The industrial digital data acquisition system according to claim 5, characterized in that: When analyzing the second risk assessment value of each abnormal analysis node based on the corresponding self-calibration data association chain, the risk characteristic label mapped by each industrial acquisition node in the current time database and the self-calibration data association chain of each abnormal analysis node are obtained. The second risk assessment value of the nth abnormal analysis node based on the corresponding self-calibration data association chain is recorded as GSn. The calculation result obtained by replacing the analysis object in the calculation process of GFn from the quantitative data association chain of the nth abnormal analysis node to the self-calibration data association chain of the nth abnormal analysis node is recorded as GSn.

8. The data acquisition system for industrial digitization according to claim 5, characterized in that: When obtaining the abnormal risk coefficient of each abnormal analysis node, the abnormal risk coefficient of the i-th abnormal analysis node is recorded as Yi, Yi = GFn + μ · GSn, Wherein, GFn represents the first risk assessment value of the nth abnormal analysis node based on the corresponding quantitative data association chain; GSn represents the second risk assessment value of the nth abnormal analysis node based on the corresponding self-calibration data association chain; μ represents the risk conversion factor.

9. The data acquisition system for industrial digitization according to claim 6, characterized in that: The risk feature update and transmission management module includes a risk feature label update unit and a transmission management unit. The risk characteristic label updating unit updates the risk characteristic label corresponding to each industrial collection node based on the abnormal risk coefficient of each abnormal analysis node; The transmission management unit summarizes the abnormal analysis nodes and adjusts the transmission structure and transmission bandwidth of the industrial collection nodes corresponding to the collected data; When the risk characteristic labels corresponding to the industrial acquisition nodes are updated, the abnormal risk coefficients of the abnormal analysis nodes are obtained, and the risk characteristic labels of all abnormal analysis nodes whose abnormal risk coefficients are greater than or equal to the preset abnormal risk coefficient value are adjusted to risk hidden danger state labels, and the risk characteristic labels of all remaining industrial acquisition nodes are adjusted to safe state labels; When adjusting the transmission structure and transmission bandwidth of the collected data corresponding to the industrial collection node, the collected data obtained in the industrial collection node is transmitted to the nearest edge computing node, and the edge computing node adjusts the data transmission structure of the obtained collected data according to the updated risk characteristic label; The data transmission structure includes a first transmission channel and a second transmission channel; In the edge computing node, the collected data corresponding to all industrial collection nodes whose updated risk characteristic labels are safety status labels are transmitted to the data center through the first transmission channel, and the collected data corresponding to all industrial collection nodes whose updated risk characteristic labels are risk hidden danger status labels are transmitted to the data center through the second transmission channel; when adjusting the transmission bandwidth, when the total transmission bandwidth of the edge computing node remains unchanged, the transmission bandwidth of each transmission channel is adjusted in proportion to the capacity of the data to be transmitted in the first transmission channel and the second transmission channel.

Images