A Method for Defect Identification and Source Tracing Based on Multi-Source Curve Correlation Analysis

The correlation diagnostic model constructed through multi-source curve correlation analysis solves the problem of insufficient multi-source information fusion in existing technologies, realizes automatic judgment of product quality anomalies and accurate assessment of equipment health status, and improves the diagnostic efficiency and fault diagnosis accuracy of industrial production.

CN123113705APending Publication Date: 2026-11-17UNIV OF SCI & TECH BEIJING
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610990061.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-07-03
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing technologies struggle to achieve multi-source information fusion in industrial production, making it difficult to accurately pinpoint the root cause of product quality anomalies. This results in low diagnostic efficiency and slow response times, a lack of continuous tracking capabilities for equipment wear and thermal deformation, and difficulty in conducting fault warnings and assessing equipment health status.

Method used

By using multi-source curve correlation analysis, a correlation diagnostic model is constructed for measurement results, control processes, and equipment status. Various types of data are acquired and normalized, correlation indicators are calculated, and a ternary status judgment matrix is ​​constructed to achieve automatic judgment and traceability of product quality status and defect sources.

Benefits of technology

It enables automatic decoupling analysis and precise source tracing between product defects and control anomalies, as well as equipment anomalies, improving the efficiency of defect diagnosis and the accuracy of fault diagnosis, and providing equipment health status assessment and early warning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123113705A_ABST
    Figure CN123113705A_ABST
Patent Text Reader

Abstract

This invention discloses a method and apparatus for determining and tracing production defects based on multi-source curve correlation analysis, relating to the field of industrial data processing and process monitoring technology. The method includes: acquiring measurement result data, control command data, and equipment status data during the production cycle of hot-rolled strip; constructing measurement result curves, control process curves, and equipment status curves based on each data source; normalizing each curve according to its corresponding standard reference curve, and outputting the normalized curves; calculating the correlation index between the normalized curves and the corresponding standard reference curves to obtain the measurement result correlation coefficient, control correlation coefficient, and equipment status correlation coefficient, and constructing a ternary status determination matrix; determining the product quality status and defect source based on the ternary status determination matrix, and outputting the defect diagnosis result. Using this invention can improve the efficiency of defect diagnosis and the accuracy of fault diagnosis in industrial production processes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of industrial data processing and process monitoring technology, and in particular to a method and apparatus for determining and tracing production defects based on multi-source curve correlation analysis. Background Technology

[0002] With the development of industrial automation and intelligent manufacturing technologies, modern industrial production processes have formed a complex closed-loop control system composed of automated control systems, equipment execution systems, and online detection systems.

[0003] In existing technologies, the monitoring of product quality anomalies typically employs the following methods: (1) threshold alarm methods based on single measurement results; (2) anomaly detection methods based on statistical process control; (3) fault diagnosis methods based on equipment condition monitoring; and (4) data comparison and analysis methods based on human experience. However, the above methods generally suffer from the following shortcomings: When product quality anomalies occur, only the abnormal results can be detected, but it is impossible to further determine whether the anomaly is caused by incorrect control model parameter settings, equipment degradation, or a combination of both. There is a lack of a unified correlation analysis mechanism between the control system, equipment system, and product quality system. A large amount of troubleshooting still relies on manual retrieval of historical data for experience analysis, resulting in low diagnostic efficiency and slow response speed. Existing methods usually analyze a single data source, failing to achieve multi-source information fusion and automatic root cause localization. There is a lack of continuous tracking capability for the slow evolution of equipment wear or thermal deformation, making it difficult to achieve fault early warning and equipment health status assessment.

[0004] Therefore, there is an urgent need to propose an intelligent diagnostic method that can simultaneously integrate measurement result information, control process information, and equipment status information, and realize automatic defect identification, automatic root cause tracing, and equipment status prediction. Summary of the Invention

[0005] To address the technical problems of low diagnostic efficiency and slow response speed in existing technologies, which make it difficult to achieve fault early warning and equipment health status assessment, this invention provides a method and apparatus for determining and tracing production defects based on multi-source curve correlation analysis. The technical solution is as follows: On the one hand, a method for determining and tracing production defects based on multi-source curve correlation analysis is provided. This method is implemented by a production defect determination and tracing device based on multi-source curve correlation analysis, and includes: S1. Acquire measurement result data, control command data, and equipment status data during the hot-rolled strip production cycle; construct measurement result curves, control process curves, and equipment status curves based on the data. S2. Based on the standard reference curves corresponding to each curve, normalize each curve and output the normalized measurement result curve, the normalized control process curve, and the normalized equipment status curve. S3. Calculate the correlation index between the normalized curve and the corresponding standard reference curve to obtain the correlation coefficient of the measurement result, the correlation coefficient of the control, and the correlation coefficient of the equipment status. S4. Construct a ternary state determination matrix based on the correlation coefficient of measurement results, the correlation coefficient of control, and the correlation coefficient of equipment status. S5. Based on the ternary state determination matrix, determine the product quality status and defect source, and output the defect diagnosis result.

[0006] On the other hand, a production defect identification and tracing device based on multi-source curve correlation analysis is provided. This device is applied to a production defect identification and tracing method based on multi-source curve correlation analysis. The device includes: The acquisition and construction module is used to acquire measurement result data, control command data, and equipment status data during the hot-rolled strip production cycle; and to construct measurement result curves, control process curves, and equipment status curves based on the data. The preprocessing module is used to normalize each curve according to the standard reference curve corresponding to each curve, and output the normalized measurement result curve, the normalized control process curve, and the normalized equipment status curve. The calculation module is used to calculate the correlation index between the normalized curve and the corresponding standard reference curve, and to obtain the correlation coefficient of the measurement result, the correlation coefficient of the control, and the correlation coefficient of the equipment status. The module is used to construct a ternary state determination matrix based on the correlation coefficient of measurement results, the correlation coefficient of control, and the correlation coefficient of equipment status. The determination and output module is used to determine the product quality status and defect source based on the ternary state determination matrix, and output the defect diagnosis result.

[0007] On the other hand, a production defect determination and tracing device based on multi-source curve correlation analysis is provided. The production defect determination and tracing device based on multi-source curve correlation analysis includes: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-described production defect determination and tracing methods based on multi-source curve correlation analysis is implemented.

[0008] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the above-described methods for determining and tracing production defects based on multi-source curve correlation analysis.

[0009] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: This invention establishes a diagnostic model linking measurement results, control processes, and equipment status to achieve automatic decoupling analysis and precise tracing between product defects and control anomalies, as well as equipment anomalies, thereby improving the efficiency of defect diagnosis and the accuracy of fault investigation in industrial production processes. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0011] Figure 1 This is a flowchart of a production defect determination and tracing method based on multi-source curve correlation analysis provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of a ternary state determination matrix provided in an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the analysis of equipment risk index and equipment degradation trend provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the cause-and-effect chain analysis of hot-rolled strip shape defects provided in an embodiment of the present invention; Figure 5 This is a block diagram of a production defect determination and tracing device based on multi-source curve correlation analysis provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of a production defect identification and tracing device based on multi-source curve correlation analysis provided in an embodiment of the present invention. Detailed Implementation

[0012] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0013] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0014] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0015] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0016] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0017] This invention provides a method for determining and tracing production defects based on multi-source curve correlation analysis. This method can be implemented using a production defect determination and tracing device based on multi-source curve correlation analysis, which can be a terminal or a server. Figure 1 The flowchart shown is for a production defect identification and tracing method based on multi-source curve correlation analysis. The processing flow of this method may include the following steps: S1. Obtain measurement result data, control command data, and equipment status data during the hot-rolled strip production cycle; construct measurement result curves, control process curves, and equipment status curves based on each data.

[0018] In this embodiment of the invention, the straightness defect tracing in the hot-rolled strip production process is taken as an example.

[0019] In one feasible implementation, the measurement result curve is the strip straightness variation curve detected by a straightness measuring instrument at the mill exit. The transverse straightness distribution of the strip is obtained through the straightness measuring instrument, and the measurement result curve is constructed. Among them, the control process curve is the curve of the change in the position of the work roll shifting and the bending force of the work roll set by the control model. The control process curve is formed by obtaining the distribution of the position of the work roll shifting and the distribution of the bending force of the work roll from the automatic control system. Among them, the equipment state curve is the superposition state curve of the actual thermal roll shape and the wear roll shape of the working roll during operation. The equipment state curve is constructed by obtaining the wear roll shape and the thermal expansion roll shape of the working roll.

[0020] In one feasible implementation, the process of constructing a standard baseline curve includes: Extract continuous M volumes of high-quality product data from the historical production database; Based on the continuous M-volume high-quality product data, a standard benchmark curve is constructed and expressed by the following formula (1): (1) in, Represents the standard reference curve; This represents the historical high-quality product curve; M is the number of samples participating in the statistics, M≥100.

[0021] In one feasible implementation, the standard reference curve can be updated periodically; wherein the update process is represented by the following formula (2): (2) in, This represents the updated standard baseline curve; This represents the standard baseline curve before the update. This represents the standard baseline curve for newly added high-quality products in the current production cycle, or the latest calculated reference curve. This represents the update coefficient.

[0022] S2. Based on the standard reference curves corresponding to each curve, normalize each curve and output the normalized measurement result curve, the normalized control process curve, and the normalized equipment status curve.

[0023] In one feasible implementation, since the length and width of the product are different, the coordinates are mapped to the [0, 1] interval using a normalization method based on each curve, as expressed by the following formula (3): (3) in, Original coordinates For normalized coordinates, The minimum value of the curve coordinates; This represents the maximum value of the curve coordinates.

[0024] In particular, normalization can eliminate the impact of differences in product width, sampling length and measurement range on correlation calculation.

[0025] S3. Calculate the correlation index between the normalized curve and the corresponding standard reference curve to obtain the correlation coefficient of the measurement result, the correlation coefficient of the control, and the correlation coefficient of the equipment status.

[0026] Optionally, the correlation metrics include one or more of the following: Pearson correlation coefficient, dynamic time-warped similarity, root mean square error, frequency domain similarity, and curve shape matching metrics.

[0027] For trend consistency evaluation, the Pearson correlation coefficient is used and expressed by the following formula (4): (4) in, Represents the actual curve. This represents the standard baseline curve, and R represents the trend correlation coefficient. This represents the average value of all sampled points on the actual curve. This represents the average value of all sampling points on the standard reference curve; n represents...

[0028] In one feasible implementation, when two curves exhibit local offset, peak drift, or nonlinear stretching, a dynamic time warping similarity method is used to calculate the curve morphological similarity. The specific process includes: The dynamic time-warped cumulative distance is calculated using the following formula (5): (5) in, Indicates the distance between two points; Indicates the dynamic time-normalized cumulative distance; Convert the dynamic time warped cumulative distance into a morphological similarity score. It can be expressed by the following formula (6): (6) in, The final dynamic time-warped cumulative distance is N, where N is the path length.

[0029] In one feasible implementation, the root mean square error is used to evaluate the curve amplitude deviation; wherein the root mean square error is expressed by the following formula (7): (7) Convert the root mean square error into an error score. It can be expressed by the following formula (8): (8) Among them, the smaller the root mean square error, the closer the error score is to 1.

[0030] In one feasible implementation, a weighted fusion method is used to construct a comprehensive correlation coefficient to comprehensively evaluate the overall matching degree between the curve and the standard benchmark curve. It can be expressed by the following formula (9): (9) in, The first weighting coefficient; This is the second weighting coefficient; This is the third weighting coefficient.

[0031] Specifically, based on the calculation process of the above-mentioned comprehensive correlation coefficient, root mean square error, dynamic time warping cumulative distance, and Pearson correlation coefficient, the correlation coefficient of measurement results, the correlation coefficient of control, and the correlation coefficient of equipment status are obtained.

[0032] S4. Based on the correlation coefficient of measurement results, the correlation coefficient of control, and the correlation coefficient of equipment status, construct a ternary state determination matrix.

[0033] Among them, such as Figure 2 The figure shown is a schematic diagram of the ternary state determination matrix provided in an embodiment of the present invention.

[0034] S5. Based on the ternary state determination matrix, determine the product quality status and defect source, and output the defect diagnosis result. The determination matrix is ​​represented by the following formula (10): M=(Score res Score ctrl Score eq (10) Among them, Score res The score represents the correlation coefficient of the measurement results. ctrl Represents the control correlation coefficient; Score eq This represents the correlation coefficient of equipment status.

[0035] Optionally, S5 determines the product quality status and defect source based on the ternary state decision matrix, and outputs the defect diagnosis results, including: When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is not lower than the preset threshold corresponding to the equipment correlation coefficient, the product is determined to have a defect, and the defect originates from an abnormal control process or an error in the instruction issuance, as expressed by the following formula (11): →Control anomaly (11) in, This represents the preset threshold corresponding to the correlation coefficient of the measurement results; This indicates the preset threshold corresponding to the control correlation coefficient; This indicates the preset threshold corresponding to the device correlation coefficient.

[0036] In one feasible implementation, control anomalies can be verified based on a ternary state decision matrix; if the calculation finds... Deviation from the benchmark, and If normal, further judgment is made based on the process mechanism: when the control model issues an excessive positive spurious amount command, if the compensation command is too extreme, it will directly cause the generation of mid-wave. In this case, the production defect judgment and traceability system based on multi-source curve correlation analysis will automatically trace and alarm the system to indicate "abnormal working roll spurious setting model".

[0037] When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is not lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is lower than the preset threshold corresponding to the equipment correlation coefficient, the product is determined to have a defect, and the defect originates from the deterioration of the equipment's own condition or local physical distortion, as expressed by the following formula (12): →Equipment malfunction (12) In one feasible implementation, equipment degradation can be verified based on a ternary state determination matrix: if the calculation shows that Scoreq deviates from the baseline, while Scorectrl is normal, further analysis of Ceq reveals that the actual measured peak thermal expansion of the work roll is approximately 0.45 mm, significantly higher than the theoretically predicted peak thermal expansion of 0.25 mm in the standard basic model. This large discrepancy between the actual equipment thermal state and the expected thermal expansion state leads to excessively small local roll gaps. The system automatically traces and issues an alarm indicating "abnormal equipment thermal expansion state," guiding the troubleshooting of the cooling water system, rather than blindly modifying the automation control code.

[0038] When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is lower than the preset threshold corresponding to the equipment correlation coefficient, the product is determined to have a defect, and the defect originates from the coupling fault between the equipment status and the control system, as expressed by the following formula (13): →Coupling fault (13) In one feasible implementation, a ternary state determination matrix can be used to verify coupled faults: if Scoreq deviates from the baseline, Scorectrl also deviates from the baseline. In-depth system analysis of Ceq reveals that the actual measured peak thermal expansion of the work roll is approximately 0.45 mm, significantly higher than the theoretically calculated peak thermal expansion of 0.25 mm predicted in the standard basic model. This large discrepancy between the actual equipment thermal state and the expected thermal expansion state leads to excessively small local roll gaps. Furthermore, it is found that the control model has issued excessively large positive skew commands. The system automatically traces and issues alarms indicating "abnormal equipment thermal expansion state" and "abnormal work roll skew setting model," guiding technicians to investigate the causes of the quality problem from both the equipment and the control model perspectives.

[0039] Optionally, after S5 determines the product quality status and defect source based on the ternary state decision matrix and outputs the defect diagnosis result, it also includes: Based on the changing trends of correlation coefficients of measurement results, control correlation coefficients, and equipment status correlation coefficients, an equipment risk index is constructed. Alternatively, the equipment risk index can be expressed by the following formula (14): Risk=w r (1-Score res )+w c (1-Score ctrl )+w e (1-Score eq (14) Risk represents the equipment risk index; Score res The score represents the correlation coefficient of the measurement results. ctrl Represents the control correlation coefficient; Score eq w represents the correlation coefficient of equipment status. r Indicates the first weighting coefficient; w c Indicates the second weighting coefficient; w e This represents the third weighting coefficient.

[0040] Risk levels are classified according to the equipment risk index; Optionally, risk levels can be classified based on equipment risk indices, including: When the equipment risk index is less than 0.2, it is classified as Level 1 risk. When 0.2 ≤ Equipment Risk Index < 0.5, it is classified as Level 2 risk; When the equipment risk index is ≥0.5, it is classified as Level 3 risk.

[0041] Based on the correlation coefficient of equipment status in continuous production cycles, an equipment deterioration trend is constructed; whereby the equipment deterioration trend is used to characterize the trend of equipment status changes and the risk of future deterioration.

[0042] Among them, such as Figure 3 The diagram shown is a schematic diagram of equipment risk index and equipment degradation trend analysis provided in an embodiment of the present invention.

[0043] Alternatively, the equipment degradation trend can be represented by the following formula (15): (15) in, Indicates a trend of equipment degradation; This represents the correlation coefficient of equipment status; N is the number of consecutive production cycles.

[0044] When Trend < -0.02 occurs continuously, the device is determined to have entered the degradation stage, and a maintenance warning is automatically generated.

[0045] Among them, such as Figure 4 The diagram shown is a schematic diagram of the causal chain analysis of hot-rolled strip shape defects provided in an embodiment of the present invention.

[0046] In the hot-rolled strip production process, the equipment condition determines the roll gap condition, and the strip shape condition is determined by the roll gap condition, thus forming the equipment condition. Roll gap condition Causal links in plate-shaped states.

[0047] In one feasible implementation, during the production process of a hot rolling mill, a flatness tester detected a significant waviness defect. Using the method provided in this embodiment of the invention, the score was calculated as follows: res =0.62, Score ctrl =0.58, Score eq =0.95.

[0048] Let T r =0.80, T c =0.80, T e =0.80. Therefore, the following condition is met: Score res <T r Score ctrl <T c Score eq ≥T e .

[0049] Based on the judgment formula, the defect was determined to originate from an anomaly in the control system. Further analysis revealed that the compensation amount for work roll misalignment exceeded the allowable range of the standard model, thus outputting the message "Work roll misalignment setting model abnormal".

[0050] In another production cycle: Score res =0.55, Score ctrl =0.91, Score eq =0.60

[0051] Based on the judgment formula, the equipment was determined to be in an abnormal state. Further investigation revealed that the peak thermal expansion of the work roll reached 0.45 mm, while the standard model predicted a value of only 0.25 mm. Therefore, the message "Abnormal thermal expansion of the work roll; it is recommended to check the cooling system" was displayed.

[0052] This invention establishes a diagnostic model linking measurement results, control processes, and equipment status to achieve automatic decoupling analysis and precise tracing between product defects and control anomalies, as well as equipment anomalies, thereby improving the efficiency of defect diagnosis and the accuracy of fault investigation in industrial production processes.

[0053] Figure 5 This is a block diagram of a production defect identification and tracing device based on multi-source curve correlation analysis provided in an embodiment of the present invention. This device is used for a production defect identification and tracing method based on multi-source curve correlation analysis. (Refer to...) Figure 5 The device includes an acquisition and construction module 510, a preprocessing module 520, a calculation module 530, a construction module 540, and a judgment and output module 550. Wherein: The acquisition and construction module 510 is used to acquire measurement result data, control command data, and equipment status data during the hot-rolled strip production cycle; and to construct measurement result curves, control process curves, and equipment status curves based on the data. The preprocessing module 520 is used to normalize each curve according to the standard reference curve corresponding to each curve, and output the normalized measurement result curve, the normalized control process curve, and the normalized equipment status curve. The calculation module 530 is used to calculate the correlation index between the normalized curve and the corresponding standard reference curve, and to obtain the correlation coefficient of the measurement result, the correlation coefficient of the control, and the correlation coefficient of the equipment status. Module 540 is used to construct a ternary state determination matrix based on the correlation coefficient of measurement results, the correlation coefficient of control, and the correlation coefficient of equipment status. The judgment and output module 550 is used to determine the product quality status and defect source based on the ternary state judgment matrix and output the defect diagnosis result.

[0054] Optionally, the correlation index includes one or more of the following: Pearson correlation coefficient, dynamic time warping (DTW) similarity, root mean square error (RMSE), frequency domain similarity index, or curve shape matching index.

[0055] Optionally, the determination and output module 550 is used for: When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is not lower than the preset threshold corresponding to the equipment correlation coefficient, it is determined that the product has a defect, and the defect originates from an abnormal control process or an error in the instruction issuance. When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is not lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is lower than the preset threshold corresponding to the equipment correlation coefficient, it is determined that the product has a defect, and the defect originates from the deterioration of the equipment's own condition or local physical distortion. When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is lower than the preset threshold corresponding to the equipment correlation coefficient, it is determined that the product has a defect, and the defect originates from the coupling failure between the equipment status and the control system.

[0056] Optionally, after the step of determining the product quality status and defect source based on the ternary state determination matrix and outputting the defect diagnosis result, the method further includes: Based on the changing trends of correlation coefficients of measurement results, control correlation coefficients, and equipment status correlation coefficients, an equipment risk index is constructed. Risk levels are classified according to the equipment risk index; Based on the correlation coefficient of equipment status in continuous production cycles, an equipment deterioration trend is constructed; whereby the equipment deterioration trend is used to characterize the trend of equipment status changes and the risk of future deterioration.

[0057] Optionally, the equipment risk index is expressed by the following formula (16): Risk=w r (1-Score res )+w c (1-Score ctrl )+w e (1-Score eq (16) Risk represents the equipment risk index; Score res The score represents the correlation coefficient of the measurement results. ctrl Represents the control correlation coefficient; Score eq w represents the correlation coefficient of equipment status. r Indicates the first weighting coefficient; w c Indicates the second weighting coefficient; w e This represents the third weighting coefficient.

[0058] Optionally, the step of classifying risk levels based on equipment risk index includes: When the equipment risk index is less than 0.2, it is classified as Level 1 risk. When 0.2 ≤ Equipment Risk Index < 0.5, it is classified as Level 2 risk; When the equipment risk index is ≥0.5, it is classified as Level 3 risk.

[0059] Optionally, the degradation trend of the equipment is represented by the following formula (17): (17) in, Indicates a trend of equipment degradation; This represents the correlation coefficient of equipment status; N is the number of consecutive production cycles.

[0060] This invention establishes a diagnostic model linking measurement results, control processes, and equipment status to achieve automatic decoupling analysis and precise tracing between product defects and control anomalies, as well as equipment anomalies, thereby improving the efficiency of defect diagnosis and the accuracy of fault investigation in industrial production processes.

[0061] Figure 6 This is a schematic diagram of a production defect identification and tracing device based on multi-source curve correlation analysis provided in an embodiment of the present invention, as shown below. Figure 6 As shown, the production defect identification and tracing equipment based on multi-source curve correlation analysis may include the above-mentioned... Figure 5 The illustrated production defect identification and tracing device is based on multi-source curve correlation analysis. Optionally, the production defect identification and tracing device 610 based on multi-source curve correlation analysis may include a first processor 2001.

[0062] Optionally, the production defect identification and tracing device 610 based on multi-source curve correlation analysis may also include a memory 2002 and a transceiver 2003.

[0063] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0064] The following is combined Figure 6 The following is a detailed introduction to each component of the production defect identification and tracing equipment 610 based on multi-source curve correlation analysis: The first processor 2001 is the control center of the production defect determination and traceability device 610 based on multi-source curve correlation analysis. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0065] Optionally, the first processor 2001 can execute various functions of the production defect determination and traceability device 610 based on multi-source curve correlation analysis by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0066] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 6 CPU0 and CPU1 are shown in the diagram.

[0067] In a specific implementation, as one example, the production defect determination and tracing device 610 based on multi-source curve correlation analysis may also include multiple processors, for example... Figure 6 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0068] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0069] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or exist independently, and may be connected via an interface circuit of the production defect determination and tracing device 610 based on multi-source curve correlation analysis. Figure 6 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0070] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0071] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 6 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0072] Optionally, the transceiver 2003 can be integrated with the first processor 2001 or exist independently, and can be connected to the interface circuit of the production defect determination and traceability device 610 based on multi-source curve correlation analysis. Figure 6 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0073] It should be noted that, Figure 6 The structure of the production defect determination and tracing device 610 based on multi-source curve correlation analysis shown in the figure does not constitute a limitation on the router. The actual production defect determination and tracing device based on multi-source curve correlation analysis may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0074] Furthermore, the technical effect of the production defect determination and traceability device 610 based on multi-source curve correlation analysis can be referred to the technical effect of the production defect determination and traceability method based on multi-source curve correlation analysis described in the above method embodiments, and will not be repeated here.

[0075] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be 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. The general-purpose processor may be a microprocessor, or it may be any conventional processor, etc.

[0076] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0077] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0078] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0079] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0080] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers 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.

[0081] 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.

[0082] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0083] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of 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 device, or some features may be ignored or not executed. Furthermore, the 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.

[0084] 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 according to actual needs.

[0085] In addition, 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.

[0086] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0087] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for determining and tracing the source of production defects based on multi-source curve correlation analysis, characterized in that, The method includes: S1. Acquire measurement result data, control command data, and equipment status data during the hot-rolled strip production cycle; construct measurement result curves, control process curves, and equipment status curves based on the data. S2. Based on the standard reference curves corresponding to each curve, normalize each curve and output the normalized measurement result curve, the normalized control process curve, and the normalized equipment status curve. S3. Calculate the correlation index between the normalized curve and the corresponding standard reference curve to obtain the correlation coefficient of the measurement result, the correlation coefficient of the control, and the correlation coefficient of the equipment status. S4. Construct a ternary state determination matrix based on the correlation coefficient of measurement results, the correlation coefficient of control, and the correlation coefficient of equipment status. S5. Based on the ternary state determination matrix, determine the product quality status and defect source, and output the defect diagnosis result.

2. The method for determining and tracing production defects based on multi-source curve correlation analysis according to claim 1, characterized in that, The correlation indicators include one or more of the following: Pearson correlation coefficient, dynamic time warping (DTW) similarity, root mean square error (RMSE), frequency domain similarity index, or curve shape matching index.

3. The method for determining and tracing production defects based on multi-source curve correlation analysis according to claim 1, characterized in that, S5 determines the product quality status and defect source based on the ternary state determination matrix, and outputs the defect diagnosis result, including: When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is not lower than the preset threshold corresponding to the equipment correlation coefficient, it is determined that the product has a defect, and the defect originates from an abnormal control process or an error in the instruction issuance. When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is not lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is lower than the preset threshold corresponding to the equipment correlation coefficient, it is determined that the product has a defect, and the defect originates from the deterioration of the equipment's own condition or local physical distortion. When the correlation coefficient of the measurement result is lower than the preset threshold corresponding to the correlation coefficient of the measurement result, the control correlation coefficient is lower than the preset threshold corresponding to the control correlation coefficient, and the equipment correlation coefficient is lower than the preset threshold corresponding to the equipment correlation coefficient, it is determined that the product has a defect, and the defect originates from the coupling failure between the equipment status and the control system.

4. The method for determining and tracing production defects based on multi-source curve correlation analysis according to claim 1, characterized in that, After step S5, which determines the product quality status and defect source based on the ternary state determination matrix and outputs the defect diagnosis result, the method further includes: Based on the changing trends of correlation coefficients of measurement results, control correlation coefficients, and equipment status correlation coefficients, an equipment risk index is constructed. Risk levels are classified according to the equipment risk index; Based on the correlation coefficient of equipment status in continuous production cycles, an equipment deterioration trend is constructed; whereby the equipment deterioration trend is used to characterize the trend of equipment status changes and the risk of future deterioration.

5. The method for determining and tracing production defects based on multi-source curve correlation analysis according to claim 4, characterized in that, The equipment risk index is expressed by the following formula (1): Risk = w r (1 - Score res ) + w c (1 - Score ctrl ) + w e (1 - Score eq ) (1) wherein, Risk represents a device risk index; Score res represents a measurement correlation coefficient; Score ctrl represents a control correlation coefficient; Score eq represents a device status correlation coefficient; w r represents a first weight coefficient; w c represents a second weight coefficient; w e represents a third weight coefficient.

6. The method for determining and tracing production defects based on multi-source curve correlation analysis according to claim 4, characterized in that, The classification of risk levels based on equipment risk index includes: When the equipment risk index is less than 0.2, it is classified as Level 1 risk. When 0.2 ≤ Equipment Risk Index < 0.5, it is classified as Level 2 risk; When the equipment risk index is ≥0.5, it is classified as Level 3 risk.

7. The method for determining and tracing production defects based on multi-source curve correlation analysis according to claim 4, characterized in that, The equipment degradation trend is represented by the following formula (2): (2) in, Indicates a trend of equipment degradation; This represents the correlation coefficient of equipment status; N is the number of consecutive production cycles.

8. A production defect identification and tracing device based on multi-source curve correlation analysis, wherein the production defect identification and tracing device based on multi-source curve correlation analysis is used to implement the production defect identification and tracing method based on multi-source curve correlation analysis as described in any one of claims 1-7, characterized in that, The device includes: The acquisition and construction module is used to acquire measurement result data, control command data, and equipment status data during the hot-rolled strip production cycle; and to construct measurement result curves, control process curves, and equipment status curves based on the data. The preprocessing module is used to normalize each curve according to the standard reference curve corresponding to each curve, and output the normalized measurement result curve, the normalized control process curve, and the normalized equipment status curve. The calculation module is used to calculate the correlation index between the normalized curve and the corresponding standard reference curve, and to obtain the correlation coefficient of the measurement result, the correlation coefficient of the control, and the correlation coefficient of the equipment status. The module is used to construct a ternary state determination matrix based on the correlation coefficient of measurement results, the correlation coefficient of control, and the correlation coefficient of equipment status. The determination and output module is used to determine the product quality status and defect source based on the ternary state determination matrix, and output the defect diagnosis result.

9. A production defect identification and tracing device based on multi-source curve correlation analysis, characterized in that, The production defect identification and tracing equipment based on multi-source curve correlation analysis includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 7.