Pierced billet abnormity tracing method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of pierced billet production anomaly analysis, in particular to a pierced billet anomaly tracing method and device, electronic equipment and a storage medium. Then, for each first monitoring data queue, determining a first anomaly indication value representing the anomaly degree of the first monitoring data queue in a mode of performing slip comparison with a plurality of second monitoring data queues; constructing the plurality of first monitoring data queues into a first matrix, and determining a plurality of target items from a plurality of production parameter items through the first matrix and a co-correlation analysis method; and finally, according to the plurality of first abnormal indication values and the plurality of target items, determining abnormal production parameter items. According to the method, the production parameter items causing the pierced billet abnormity are determined through the slip comparison and parameter item redundancy screening method, the reason causing the pierced billet abnormity can be rapidly and accurately determined, and the yield of the pierced billet can be improved.

Description

Technical Field

[0001] This invention relates to the field of anomaly analysis technology in raw pipe production, and in particular to a method, device, electronic equipment, and storage medium for tracing the source of anomalies in raw pipe production. Background Technology

[0002] Rough tubes, as the initial tubular products emerging from the piercing mill, have a relatively rough surface, and their dimensional accuracy and surface quality do not yet meet the requirements of the final product. They are primarily formed by transforming a solid steel billet into a hollow tube through a piercing process, hence the name "rough tube." Rough tubes typically require further rolling and leveling processes to improve their quality and precision, ultimately resulting in seamless steel pipes with high dimensional accuracy and a relatively smooth surface.

[0003] The inner and outer surfaces of the rough pipe are not smooth, covered with a thick layer of iron oxide scale, and the wall thickness error is relatively large. At the same time, the rough pipe has more abnormalities and quality problems than other steel pipe processing procedures.

[0004] By analyzing the causes of anomalies in raw pipe production, targeted improvements to the processing technology and parameters can significantly increase the yield of raw pipes. Currently, methods such as fishbone diagrams and frequency domain analysis of parameter data are often used to analyze the causes of raw pipe anomalies. However, these methods either provide a general overview of the causes or only offer good guidance for certain types of anomalies, making it difficult to keep pace with the analysis of anomalies and parameter adjustments in raw pipe production.

[0005] Therefore, it is necessary to develop and design a method for tracing the source of abnormalities in waste management. Summary of the Invention

[0006] The present invention provides a method, apparatus, electronic device and storage medium for tracing the source of abandoned pipe anomalies, which solves the problem that the causes of abandoned pipe anomalies are not easy to find in the prior art.

[0007] In a first aspect, embodiments of the present invention provide a method for tracing the source of abnormalities in waste management, including: Multiple first monitoring data queues are obtained, where each first monitoring data queue corresponds to a production parameter item of the abnormal waste management, and the data in the queue is sorted according to the corresponding time node; For each first monitoring data queue, a first anomaly indication value is determined by sliding comparison with multiple second monitoring data queues, which represents the degree of anomaly of the first monitoring data queue. The second monitoring data queues correspond to the same production parameter item as the first monitoring data queues, and the second monitoring data queues are derived from the normal production process of the raw pipe. The multiple first monitoring data queues are constructed into a first matrix. Using the first matrix and the co-correlation analysis method, multiple target items are determined from multiple production parameter items. Based on multiple first anomaly indication values ​​and the multiple target items, the abnormal production parameter items are determined.

[0008] In one possible implementation, determining a first anomaly indication value characterizing the degree of anomaly in each first monitoring data queue by sliding comparison with multiple second monitoring data queues includes: For each first monitoring data queue, perform the following steps: From the middle position of the first monitoring data queue, a data segment of a preset length is extracted to construct the first data segment; For each second monitoring data queue, multiple correlation values ​​are obtained by sliding out data segments from the second monitoring data queue and comparing them with the first data segment, and the maximum value among the multiple correlation values ​​is taken as the first correlation value; The average of multiple first correlation values ​​is used as the first anomaly indication value.

[0009] In one possible implementation, for each second monitoring data queue, obtaining multiple correlation values ​​by sliding data segments from the second monitoring data queue and comparing them with the first data segment, and taking the maximum value among the multiple correlation values ​​as the first correlation value, includes: For each second monitoring data queue, perform the following steps: Take a data segment of the same length as the first data segment from the first position of the second monitoring data queue, and use it as the second data segment; Based on the first formula, the first data segment, and the second data segment, relevant values ​​are determined and added to the relevant value queue. The first formula is:

[0010] In the formula, For relevant values, For the first data segment One data point, For the second data segment One data point, This represents the total number of data items in the first data segment. If the first position does not reach the end of the second monitoring data queue, the first position is offset and the process jumps to the step of retrieving a data segment of the same length as the first data segment from the first position of the second monitoring data queue as the second data segment. Otherwise, the maximum value is selected from the relevant value queue as the first relevant value.

[0011] In one possible implementation, the plurality of first monitoring data queues are constructed into a first matrix, and multiple target items are determined from multiple production parameter items using the first matrix and co-correlation analysis, including: Each first monitoring data queue is standardized, and the obtained standardized data is used to construct a first vector. Construct a first matrix from multiple first vectors; Based on the first matrix, the covariance matrix is ​​obtained through cocorrelation analysis; Calculate multiple eigenvalues ​​of the covariance matrix; The first contribution rate of the production parameter item is determined based on the multiple feature values, and multiple target items are determined from the multiple production parameter items based on the multiple first contribution rates.

[0012] In one possible implementation, the standardization of each first monitoring data queue includes: Data of the same position are extracted from the plurality of first monitoring data queues and arranged in a preset order to obtain a second vector; Each second monitoring vector is standardized according to the second formula to obtain the first vector, wherein the second formula is:

[0013] In the formula, For the first vector, the first... One element, For the second vector One element, Let be the mean of the multiple elements of the second vector. Let be the standard deviation of multiple elements of the second vector; The step of obtaining the covariance matrix based on the first matrix through cocorrelation analysis includes: If the first vector is used as a row vector to construct the first matrix, then the covariance matrix is ​​obtained by performing cocorrelation analysis on the first matrix according to the third formula, whereby the third formula is:

[0014] In the formula, Let covariance matrix be the variance matrix. This represents the total number of elements in the first vector. This is the first matrix; Otherwise, perform cocorrelation analysis on the first matrix according to the fourth formula to obtain the covariance matrix, wherein the fourth formula is:

[0015] In the formula, Let covariance matrix be the variance matrix. This represents the total number of elements in the first vector. This is the first matrix.

[0016] In one possible implementation, determining a first contribution rate for a production parameter item based on the plurality of feature values, and determining a plurality of target items from the plurality of production parameter items based on the plurality of first contribution rates, includes: The first contribution rate of the production parameter item is determined based on the fifth formula and the aforementioned multiple feature values, wherein the fifth formula is:

[0017] In the formula, For the first The highest contribution rate, For the first 1 eigenvalue, This represents the total number of production parameter items. Multiple contribution rates are selected from the plurality of first contribution rates in descending order to serve as multiple target contribution rates, wherein the ratio of the sum of the multiple target contribution rates to the sum of the multiple first contribution rates is greater than a threshold. For each row or column of the covariance matrix, summation is performed to obtain multiple first covariance sums; Multiple covariance sums are selected from the plurality of first covariance sums in ascending order to serve as multiple target covariance sums, wherein the number of the plurality of target covariance sums is the same as the number of the plurality of target contribution rates; The multiple target covariances and their corresponding production parameter terms are used as multiple target terms.

[0018] In one possible implementation, determining the abnormal production parameter item based on a plurality of first abnormality indication values ​​and the plurality of target items includes: The first anomaly indication value corresponding to the plurality of target items is used as a plurality of second anomaly indication values; The production parameter item corresponding to the maximum value among the plurality of second anomaly indication values ​​is taken as the anomaly factor item.

[0019] Secondly, embodiments of the present invention provide a wasteland management anomaly tracing device for implementing the wasteland management anomaly tracing method as described in the first aspect or any possible implementation thereof, the wasteland management anomaly tracing device comprising: The monitoring data acquisition module is used to acquire multiple first monitoring data queues, where each first monitoring data queue corresponds to a production parameter item of the abnormal waste management, and the data in the queue is sorted according to the corresponding time node; The anomaly analysis module is used to determine a first anomaly indication value that characterizes the degree of anomaly of each first monitoring data queue by sliding comparison with multiple second monitoring data queues. The second monitoring data queues correspond to the same production parameter item as the first monitoring data queues, and the second monitoring data queues are derived from the normal production process of the raw pipe. The production parameter item filtering module is used to construct a first matrix from the multiple first monitoring data queues, and to determine multiple target items from the multiple production parameter items using the first matrix and the co-correlation analysis method. as well as, An abnormal production parameter item determination module is used to determine abnormal production parameter items based on multiple first abnormal indication values ​​and the multiple target items.

[0020] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the computer program to implement the steps of the method as described in the first aspect or any possible implementation of the first aspect.

[0021] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect or any possible implementation thereof.

[0022] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: This invention discloses a method for tracing the source of abnormalities in uncultivated pipes. First, multiple first monitoring data queues are acquired, each corresponding to a production parameter item of the abnormal uncultivated pipe. The data in the queues are sorted according to their corresponding time nodes. Then, for each first monitoring data queue, a first anomaly indication value is determined by performing a sliding comparison with multiple second monitoring data queues. The second monitoring data queues correspond to the same production parameter item as the first monitoring data queues and originate from the production process of normal uncultivated pipes. Next, the multiple first monitoring data queues are constructed into a first matrix. Using the first matrix and co-correlation analysis, multiple target items are determined from the multiple production parameter items. Finally, based on the multiple first anomaly indication values ​​and the multiple target items, the abnormal production parameter item is determined. This method, through sliding comparison and parameter redundancy screening, identifies the production parameter item causing the uncultivated pipe abnormality, quickly and accurately clarifying the cause of the abnormality and helping to improve the yield of uncultivated pipes. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of the method for tracing the source of abnormalities in waste management provided by the embodiments of the present invention; Figure 2 This is a schematic diagram of the standardized monitoring data matrix construction process provided by the embodiments of the present invention; Figure 3 This is a functional block diagram of the wasteland anomaly tracing device provided in the embodiments of the present invention; Figure 4 This is a functional block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0025] In the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0026] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0027] The embodiments of the present invention will be described in detail below. This example is implemented based on the technical solution of the present invention, and provides detailed implementation methods and specific operation processes. However, the protection scope of the present invention is not limited to the following embodiments.

[0028] Figure 1 A flowchart of the method for tracing the source of abnormalities in waste management provided in an embodiment of the present invention.

[0029] like Figure 1 As shown, it illustrates the implementation flowchart of the waste management anomaly tracing method provided by the embodiments of the present invention, which is described in detail below: In step 101, multiple first monitoring data queues are obtained, wherein each first monitoring data queue corresponds to a production parameter item of the abnormal waste management, and the data in the queue is sorted according to the corresponding time node.

[0030] In step 102, for each first monitoring data queue, a first anomaly indication value is determined by sliding comparison with multiple second monitoring data queues, which represents the degree of anomaly of the first monitoring data queue. The second monitoring data queues correspond to the same production parameter item as the first monitoring data queues, and the second monitoring data queues are derived from the normal production process of the raw pipe.

[0031] In some implementations, determining a first anomaly indication value characterizing the degree of anomaly in each first monitoring data queue by performing a sliding comparison with multiple second monitoring data queues includes: For each first monitoring data queue, perform the following steps: From the middle position of the first monitoring data queue, a data segment of a preset length is extracted to construct the first data segment; For each second monitoring data queue, multiple correlation values ​​are obtained by sliding out data segments from the second monitoring data queue and comparing them with the first data segment, and the maximum value among the multiple correlation values ​​is taken as the first correlation value; The average of multiple first correlation values ​​is used as the first anomaly indication value.

[0032] In some implementations, for each second monitoring data queue, obtaining multiple correlation values ​​by sliding data segments from the second monitoring data queue and comparing them with the first data segment, and taking the maximum value among the multiple correlation values ​​as the first correlation value, includes: For each second monitoring data queue, perform the following steps: Take a data segment of the same length as the first data segment from the first position of the second monitoring data queue, and use it as the second data segment; Based on the first formula, the first data segment, and the second data segment, relevant values ​​are determined and added to the relevant value queue. The first formula is:

[0033] In the formula, For relevant values, For the first data segment One data point, For the second data segment One data point, This represents the total number of data items in the first data segment. If the first position does not reach the end of the second monitoring data queue, the first position is offset and the process jumps to the step of retrieving a data segment of the same length as the first data segment from the first position of the second monitoring data queue as the second data segment. Otherwise, the maximum value is selected from the relevant value queue as the first relevant value.

[0034] For example, this invention analyzes rough pipe anomalies based on a monitoring data queue, using correlation analysis and redundant parameter removal methods. The monitoring data queue is constructed from data obtained from production parameters corresponding to multiple time points. Some production parameters include measured billet temperature, roll rolling force, roll motor speed, roll motor current, roll motor torque, mandrel carriage speed, mandrel carriage current, mandrel carriage torque, and continuous rolling speed.

[0035] In reality, these parameters may contain redundant information in some scenarios. For example, when there are cracks in the raw tube, the torque and speed of the roll motor will fluctuate to some extent. How to filter out redundant information and retain the parameters that are most likely to affect the raw tube anomaly is an important step in tracing the source of the raw tube anomaly.

[0036] As mentioned above, the present invention achieves the initial determination of abnormal production parameters through correlation analysis. Specifically, since each production parameter corresponds to a first monitoring data queue, and at the same time, most of the multiple waste pipes produced continuously with the abnormal waste pipes do not have abnormalities, the present invention will use these monitoring data queues corresponding to normal waste pipes as reference items. That is to say, the monitoring data queues of normal waste pipes are used as the second monitoring data queues and compared with the first monitoring data queues to generate an indication value indicating the degree of abnormality of the first monitoring data queue.

[0037] Specifically, this invention extracts a data segment from the middle of the first monitoring data queue and performs a sliding comparison with the second monitoring data queue. After each sliding, a data segment of the same length as the data segment in the first monitoring data queue is extracted from the second monitoring data queue, and the correlation value between the two is calculated using the first formula.

[0038] In the formula, For relevant values, For the first data segment One data point, For the second data segment One data point, This represents the total number of data items in the first data segment.

[0039] This process is repeated until the data slides to the end of the second monitoring data queue. At this point, multiple correlation values ​​are obtained. We take the maximum value from these multiple correlation values ​​as the first correlation value, which represents the degree of correlation between the two monitoring data queues.

[0040] After each second monitoring data queue obtains a first correlation value, the average of these multiple first correlation values ​​is calculated as the first anomaly indication value. From the above steps, it can be seen that a normal first monitoring data queue should have a relatively large first anomaly indication value (close to 1, and the first anomaly indication value should be distributed in the range of -1 to 1). In other words, an abnormal first monitoring data queue should have a relatively small first anomaly indication value.

[0041] In step 103, the plurality of first monitoring data queues are constructed into a first matrix, and multiple target items are determined from multiple production parameter items using the first matrix and cocorrelation analysis.

[0042] In some embodiments, step 103 includes: In some implementations, the step of constructing a first matrix from the plurality of first monitoring data queues, and determining multiple target items from multiple production parameter items using the first matrix and co-correlation analysis, includes: Each first monitoring data queue is standardized, and the obtained standardized data is used to construct a first vector. Construct a first matrix from multiple first vectors; Based on the first matrix, the covariance matrix is ​​obtained through cocorrelation analysis; Calculate multiple eigenvalues ​​of the covariance matrix; The first contribution rate of the production parameter item is determined based on the multiple feature values, and multiple target items are determined from the multiple production parameter items based on the multiple first contribution rates.

[0043] In some implementations, the standardization of each first monitoring data queue includes: Data of the same position are extracted from the plurality of first monitoring data queues and arranged in a preset order to obtain a second vector; Each second monitoring vector is standardized according to the second formula to obtain the first vector, wherein the second formula is:

[0044] In the formula, For the first vector, the first... One element, For the second vector One element, Let be the mean of the multiple elements of the second vector. Let be the standard deviation of multiple elements of the second vector; The step of obtaining the covariance matrix based on the first matrix through cocorrelation analysis includes: If the first vector is used as a row vector to construct the first matrix, then the covariance matrix is ​​obtained by performing cocorrelation analysis on the first matrix according to the third formula, whereby the third formula is:

[0045] In the formula, Let covariance matrix be the variance matrix. This represents the total number of elements in the first vector. This is the first matrix; Otherwise, perform cocorrelation analysis on the first matrix according to the fourth formula to obtain the covariance matrix, wherein the fourth formula is:

[0046] In the formula, Let covariance matrix be the variance matrix. This represents the total number of elements in the first vector. This is the first matrix.

[0047] In some implementations, determining a first contribution rate for a production parameter item based on the plurality of feature values, and determining a plurality of target items from the plurality of production parameter items based on the plurality of first contribution rates, includes: The first contribution rate of the production parameter item is determined based on the fifth formula and the aforementioned multiple feature values, wherein the fifth formula is:

[0048] In the formula, For the first The highest contribution rate, For the first 1 eigenvalue, This represents the total number of production parameter items. Multiple contribution rates are selected from the plurality of first contribution rates in descending order to serve as multiple target contribution rates, wherein the ratio of the sum of the multiple target contribution rates to the sum of the multiple first contribution rates is greater than a threshold. For each row or column of the covariance matrix, summation is performed to obtain multiple first covariance sums; Multiple covariance sums are selected from the plurality of first covariance sums in ascending order to serve as multiple target covariance sums, wherein the number of the plurality of target covariance sums is the same as the number of the plurality of target contribution rates; The multiple target covariances and their corresponding production parameter terms are used as multiple target terms.

[0049] For example, as mentioned earlier, when there is an anomaly in the management system, there are often multiple anomaly first monitoring data queues, that is, there are redundant parameter items. How to filter and delete redundant parameter items is an important step in anomaly tracing.

[0050] The present invention constructs the first monitoring data queue into a matrix and uses cocorrelation analysis to remove redundant items and retain the core items from multiple production parameter items.

[0051] Figure 2 The diagram illustrates the principle of the standardized monitoring data matrix construction process provided by the embodiments of the present invention. Specifically, each first monitoring data queue 201 is first standardized, that is, data corresponding to the same position (the same time node, in the figure, data is extracted from time node t2) is extracted from each first monitoring data queue 201. These data are arranged in a predetermined order according to the corresponding parameter items to construct a second vector 202. These second vectors 202 are then standardized using a second formula to form a first vector 203. The second formula is:

[0052] In the formula, For the first vector, the first... One element, For the second vector One element, Let be the mean of the multiple elements of the second vector. Let be the standard deviation of multiple elements of the second vector.

[0053] The first vector 203 is ultimately added to the first matrix 204 as a row vector or column vector (in the figure, it is added to the first matrix 204 as a row vector).

[0054] Cocorrelation analysis is obtained by constructing the covariance matrix from the first matrix and extracting its eigenvalues. If the first matrix is ​​constructed by using the first vector as row vectors, then the covariance matrix is ​​calculated using the third formula:

[0055] In the formula, Let covariance matrix be the variance matrix. This represents the total number of elements in the first vector. This is the first matrix.

[0056] If the first matrix is ​​constructed by using the first vector as column vectors, then the covariance matrix is ​​calculated using the fourth formula:

[0057] In the formula, Let covariance matrix be the variance matrix. This represents the total number of elements in the first vector. This is the first matrix.

[0058] After obtaining the covariance matrix, we can calculate the eigenvalues ​​of the covariance matrix.

[0059] Then, the first contribution rate of the parameter term is calculated using the fifth formula and eigenvalues:

[0060] In the formula, For the first The highest contribution rate, For the first 1 eigenvalue, This represents the total number of production parameter items.

[0061] Sort the first contribution rates by value and select the largest ones as the target contribution rates. Note that the ratio of the sum of these target contribution rates to the sum of all first contribution rates must be greater than a threshold, for example, a threshold of 0.9.

[0062] In this way, we know the number of main parameter items (the same as the number of target contribution rates), in other words, we know the number of redundant items in the parameter items (the total number of parameter items minus the number of target contribution rates is the number of redundant items).

[0063] At this point, each row or column of the first covariance matrix (the first covariance matrix has a skew-symmetric structure, so summing by row and summing by column yields the same result) is summed to obtain multiple covariance sums. The order of these covariance sums (the order of row summing or column summing) is the same as the order of the parameter terms used when extracting data from the first monitoring data queue to construct the second vector. In other words, the correspondence between parameter terms is clarified from the order of the rows or columns corresponding to these covariance sums. These covariance sums are then sorted according to their values, and the multiple covariance sums with the smallest values ​​are selected as multiple target covariance sums. Note that the number of these multiple target covariance sums is the same as the number of target contribution rates obtained in the previous steps. Since there is a correspondence between the covariance sums and the parameter terms, the parameter terms that need to be retained are determined based on the target covariance sums. These terms will serve as target terms, and combined with the first anomaly indication value, the abnormal parameter terms are determined.

[0064] In step 104, abnormal production parameter items are determined based on multiple first abnormal indication values ​​and the multiple target items.

[0065] In some implementations, determining the abnormal production parameter item based on a plurality of first abnormality indication values ​​and the plurality of target items includes: The first anomaly indication value corresponding to the plurality of target items is used as a plurality of second anomaly indication values; The production parameter item corresponding to the maximum value among the plurality of second anomaly indication values ​​is taken as the anomaly factor item.

[0066] For example, the first abnormality indication value is found according to the target item, and it is used as the second abnormality indication value. The second abnormality indication value with the largest value is found from the second abnormality indication value. The production parameter item corresponding to the second abnormality indication value is the abnormal factor item. In other words, the production parameter item that causes the abnormality of the waste pipe is the abnormal factor item.

[0067] The present invention provides a method for tracing the source of abnormalities in uncultivated pipes. First, multiple first monitoring data queues are acquired, each corresponding to a production parameter item of the abnormal uncultivated pipe. The data in the queues are sorted according to their corresponding time nodes. Then, for each first monitoring data queue, a first anomaly indication value is determined by performing a sliding comparison with multiple second monitoring data queues. The second monitoring data queues correspond to the same production parameter item as the first monitoring data queues and originate from the production process of normal uncultivated pipes. Next, the multiple first monitoring data queues are constructed into a first matrix. Using the first matrix and co-correlation analysis, multiple target items are determined from the multiple production parameter items. Finally, based on the multiple first anomaly indication values ​​and the multiple target items, the abnormal production parameter item is determined. This method, through sliding comparison and parameter redundancy screening, identifies the production parameter item causing the uncultivated pipe abnormality, enabling rapid and accurate identification of the cause and contributing to improving the yield of uncultivated pipes.

[0068] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0069] The following are embodiments of the apparatus of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0070] Figure 3 This is a functional block diagram of the wasteland anomaly tracing device provided in an embodiment of the present invention, with reference to... Figure 3 The waste management anomaly tracing device includes: a monitoring data acquisition module 301, an anomaly analysis module 302, a production parameter item screening module 303, and an abnormal production parameter item determination module 304, wherein: The monitoring data acquisition module 301 is used to acquire multiple first monitoring data queues, wherein each first monitoring data queue corresponds to a production parameter item of the abnormal waste management, and the data in the queue is sorted according to the corresponding time node; Anomaly analysis module 302 is used to determine a first anomaly indication value characterizing the degree of anomaly of each first monitoring data queue by sliding comparison with multiple second monitoring data queues, wherein the second monitoring data queues correspond to the same production parameter item as the first monitoring data queues, and the second monitoring data queues originate from the normal raw pipe production process; The production parameter item screening module 303 is used to construct a first matrix from the multiple first monitoring data queues, and to determine multiple target items from multiple production parameter items through the first matrix and the co-correlation analysis method. The abnormal production parameter item determination module 304 is used to determine abnormal production parameter items based on multiple first abnormal indication values ​​and the multiple target items.

[0071] Figure 4 This is a functional block diagram of the electronic device provided in an embodiment of the present invention. For example... Figure 4 As shown, the electronic device 4 in this embodiment includes a processor 400 and a memory 401, wherein the memory 401 stores a computer program 402 that can run on the processor 400. When the processor 400 executes the computer program 402, it implements the steps in the various methods and embodiments for tracing the source of abnormalities in waste management, for example... Figure 1 Steps 101 to 104 are shown.

[0072] For example, the computer program 402 may be divided into one or more modules / units, which are stored in the memory 401 and executed by the processor 400 to complete the present invention.

[0073] The electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The electronic device 4 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 4 may also include input / output devices, network access devices, buses, etc.

[0074] The processor 400 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0075] The memory 401 can be an internal storage unit of the electronic device 4, such as a hard disk or memory. The memory 401 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 401 can include both internal and external storage units of the electronic device 4. The memory 401 is used to store the computer program 402 and other programs and data required by the electronic device 4. The memory 401 can also be used to temporarily store data that has been output or will be output.

[0076] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the aforementioned method embodiments, and will not be repeated here.

[0077] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0078] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0079] In the embodiments provided by this invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0080] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0081] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0082] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods and apparatus embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0083] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method of abnormality backtracking of a rough pipe, characterized by, The method comprises the following steps: acquiring a plurality of first monitoring data queues, wherein each first monitoring data queue corresponds to a production parameter item of an abnormal pipe, and the data in the queue is sorted according to the corresponding time node; for each first monitoring data queue, determining a first abnormality indication value representing the abnormality degree of the first monitoring data queue by means of a sliding comparison with a plurality of second monitoring data queues, wherein the second monitoring data queue corresponds to the same production parameter item as the first monitoring data queue, and the second monitoring data queue is derived from the production process of a normal pipe; constructing the plurality of first monitoring data queues into a first matrix, and determining a plurality of target items from a plurality of production parameter items by means of the first matrix and a co-correlation analysis method; determining an abnormal production parameter item according to a plurality of first abnormality indication values and the plurality of target items.

2. The pipe abnormality backtracking method according to claim 1, characterized by, The method further comprises the following steps: for each first monitoring data queue, the following steps are performed respectively: from the middle position of the first monitoring data queue, a data segment of a preset length is intercepted to construct a first data segment; for each second monitoring data queue, a plurality of correlation values are obtained by comparing the data segment obtained by sliding from the second monitoring data queue with the first data segment, and the maximum value in the plurality of correlation values is taken as a first correlation value; the average value of the plurality of first correlation values is taken as the first abnormality indication value.

3. The pipe abnormality backtracking method according to claim 2, characterized by, The method further comprises the following steps: for each second monitoring data queue, the following steps are performed respectively: a data segment with the same length as the first data segment is taken from the first position of the second monitoring data queue as a second data segment; a correlation value is determined according to a first formula, the first data segment and the second data segment, and the obtained correlation value is added to a correlation value queue, wherein the first formula is: wherein is a correlation value, is the first data segment, is the first data segment, is the second data segment, is the second data segment, is the total number of data in the first data segment; if the first position has not reached the end of the second monitoring data queue, the first position is offset, and the step of taking a data segment with the same length as the first data segment from the first position of the second monitoring data queue as a second data segment is jumped to; otherwise, the maximum value in the correlation value queue is selected as the first correlation value.

4. The method of claim 1, wherein: The method further comprises the following steps: standardizing each first monitoring data queue, and constructing the obtained standardized data into a first vector; constructing a plurality of first vectors into a first matrix; obtaining a covariance matrix by means of a co-correlation analysis according to the first matrix; calculating a plurality of eigenvalues of the covariance matrix; Determine a first contribution rate of a production parameter item according to the plurality of characteristic values, and determine a plurality of target items from the plurality of production parameter items according to the plurality of first contribution rates.

5. The method of claim 4, wherein: The standardization of each first monitoring data queue comprises: Extracting data of the same parity from the plurality of first monitoring data queues and arranging the data in a preset order to obtain a second vector; Standardizing each second monitoring vector according to a second formula to obtain a first vector, wherein the second formula is: wherein is the first element of the first vector, is the first element of the second vector, is the first element of the second vector, is the first element of the second vector, is the mean of the plurality of elements of the second vector, is the standard deviation of the plurality of elements of the second vector; The covariance matrix is obtained by the co-correlation analysis of the first matrix, comprising: If the first vector is used as a row vector to construct a first matrix, the covariance matrix is obtained by co-correlation analysis of the first matrix according to a third formula, wherein the third formula is: wherein is a covariance matrix, is the total number of elements in the first vector, is a first matrix; Otherwise, the covariance matrix is obtained by co-correlation analysis of the first matrix according to a fourth formula, wherein the fourth formula is: wherein is a covariance matrix, is the total number of elements in the first vector, is the first matrix.

6. The method of pipe abnormality backtracing according to claim 4, wherein, The determination of the first contribution rate of the production parameter item according to the plurality of characteristic values, and the determination of the plurality of target items from the plurality of production parameter items according to the plurality of first contribution rates, comprises: The first contribution rate of the production parameter item is determined according to a fifth formula and the plurality of characteristic values, wherein the fifth formula is: wherein is the first contribution rate, is the first contribution rate, is the first contribution rate, is the first contribution rate, is the total number of production parameter items; Selecting a plurality of contribution rates from the plurality of first contribution rates in descending order as a plurality of target contribution rates, wherein the ratio of the sum of the plurality of target contribution rates to the sum of the plurality of first contribution rates is greater than a threshold value; Summing each row or each column of the covariance matrix to obtain a plurality of first covariance sums; Selecting a plurality of covariance sums from the plurality of first covariance sums in ascending order as a plurality of target covariance sums, wherein the number of the plurality of target covariance sums is the same as the number of the plurality of target contribution rates; The production parameter items corresponding to the plurality of target covariance sums are used as a plurality of target items.

7. The raw pipe anomaly back-tracing method according to any one of claims 1 to 6, characterized by, The determination of the abnormal production parameter item according to the plurality of first abnormal indication values and the plurality of target items comprises: The first abnormal indication values corresponding to the plurality of target items are used as a plurality of second abnormal indication values; The production parameter item corresponding to the maximum value in the plurality of second abnormal indication values is used as an abnormal factor item.

8. A pipe anomaly backtracking device, characterized by, The pipe anomaly tracing device comprises: A monitoring data acquisition module is configured to acquire a plurality of first monitoring data queues, wherein each first monitoring data queue corresponds to a production parameter item of an abnormal pipe, and the data in the queue is sorted according to a corresponding time node; An anomaly analysis module is configured to determine, for each first monitoring data queue, a first abnormal indication value representing the abnormal degree of the first monitoring data queue by comparing the first monitoring data queue with a plurality of second monitoring data queues, wherein the second monitoring data queue corresponds to the same production parameter item as the first monitoring data queue, and the second monitoring data queue is derived from the production process of a normal pipe; A production parameter item screening module is configured to construct the plurality of first monitoring data queues into a first matrix, and determine a plurality of target items from the plurality of production parameter items by the first matrix and a co-correlation analysis method; and An abnormal production parameter item determining module is configured to determine an abnormal production parameter item according to the plurality of first abnormal indication values and the plurality of target items.

9. An electronic device comprising a memory and a processor, said memory having stored therein a computer program operable on said processor, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the method of any one of claims 1-7.

Images