Index anomaly identification method and device, equipment and storage medium

Abstract

The invention provides an index anomaly identification method and device, equipment and a storage medium, and the method comprises the steps: obtaining all index parameters in a production process in a current time period and all corresponding production parameters; calculating an index sequence formed by each process capability index corresponding to each index parameter and each production parameter, namely a first sequence and a second sequence; screening the abnormal process capability indexes in the first sequence according to a preset abnormal rule, and determining a first abnormal interval; and screening each process capability index in the second sequence based on the first abnormal interval, determining a second abnormal interval, and determining an index abnormality reason based on the second abnormal interval. Therefore, the index abnormality can be quickly positioned and the abnormality reason can be quickly determined while the index abnormality identification is realized, so that the index parameter control level is improved, and the production quality is ensured.

Description

Technical Field

[0001] The present application relates to the field of process control technology, and in particular to an indicator abnormality identification method, device, equipment and storage medium. Background Art

[0002] In modern manufacturing, process control and quality management are key links to ensure product quality and production efficiency. Traditional quality control systems usually rely on the test results of the final product, that is, the quality of the product is judged by sampling and testing the finished product. Although this method can ensure the quality of the factory products to a certain extent, it has significant limitations. First, its feedback mechanism has a lag, and it is impossible to find and correct problems in time during the production process, resulting in an increase in defective products and an increase in production costs; second, the limitations of sampling inspection may cause some quality problems to be missed, affecting the stability of the overall quality of the product; finally, the lack of in-depth understanding and real-time monitoring of the production process makes it difficult for enterprises to solve quality problems from the root and improve production efficiency. In related technologies, in order to solve this problem, the concept of Process Capability Index (PCI) is introduced in the real-time monitoring of the production process. As an important tool for evaluating the stability and capability of the production process, it can timely reflect the fluctuations and anomalies of the production process data, and is an intuitive indicator for monitoring whether the production process meets the preset specifications.

[0003] However, the current production process monitoring methods based on process capability index, on the one hand, are difficult to quickly locate and analyze the causes of abnormalities when abnormalities occur in the production process, resulting in the inability to take effective measures to correct them in time and unable to ensure the stability of the production process and product quality; on the other hand, they are mostly limited to the monitoring of a single indicator and lack comprehensive analysis of multiple indicators, resulting in problems with the accuracy and efficiency of abnormality identification. Summary of the invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] In view of the above-mentioned shortcomings of the prior art, the present application discloses an indicator abnormality identification method, device, equipment and storage medium to solve at least one of the above-mentioned technical problems.

[0006] In a first aspect, the present application provides an indicator abnormality identification method, the method comprising: obtaining each indicator parameter and each production parameter in a production process within a current time period, wherein a mapping relationship exists between the indicator parameter and the production parameter; calculating a process capability index corresponding to each target parameter subsequence in a target parameter sequence, and obtaining an index sequence formed by each process capability index, wherein the target parameter sequence is a sequence formed by continuous target parameters, each target parameter subsequence includes a preset first number of target parameters, and adjacent target parameter subsequences are spaced at intervals of a preset second number of target parameters, and the target parameter is the indicator parameter or the production parameter; matching the first sequence according to a preset abnormal rule to determine a first abnormal interval, wherein the preset abnormal rule is used to screen the abnormal process capability index in the first sequence, and the first sequence is the index sequence corresponding to the indicator parameter; screening each process capability index in the second sequence based on the first abnormal interval to determine a second abnormal interval, so as to determine a cause of the indicator abnormality based on the second abnormal interval, wherein a mapping relationship exists between each process capability index included in the first sequence and the second sequence, and the second sequence is the index sequence corresponding to the production parameter.

[0007] In one embodiment of the present application, the process capability index corresponding to each target parameter subsequence in the target parameter sequence is calculated, including: using the preset first number as the size of the sliding window, so that the sliding window includes the preset first number of the indicator parameters or the production parameters; sliding forward on the indicator parameter sequence based on the sliding window, and calculating the process capability index corresponding to the indicator parameter in the sliding window at each sliding, the indicator parameter sequence is obtained by sorting the indicator parameters in the current time period from front to back according to time, and the sliding interval of the sliding window is the preset second number; sliding forward on the production parameter sequence based on the sliding window, and calculating the process capability index corresponding to the production parameter in the sliding window at each sliding, the production parameter sequence is obtained by sorting the production parameters in the current time period from front to back according to time.

[0008] In one embodiment of the present application, the first sequence is judged according to the preset abnormal rule to determine the first abnormal interval, including: taking the process capability index corresponding to the indicator parameter as the first process index; if a preset third number of consecutive first process indices in the first sequence are all less than a preset index lower limit, then determining that the preset third number of first process indices conform to the preset abnormal rule and serving as the first abnormal interval; if the variance, range or standard deviation between a preset third number of consecutive first process indices is less than the corresponding preset threshold value, then determining that the preset third number of first process indices conform to the preset abnormal rule and serving as the first abnormal interval.

[0009] In one embodiment of the present application, determining the cause of the indicator abnormality based on the second abnormal interval includes: screening each of the process capability indexes in the second abnormal interval according to a preset ranking to obtain each production abnormality index; determining the production parameters corresponding to each of the production abnormality indexes, and using them as the cause of the indicator abnormality.

[0010] In one embodiment of the present application, the first sequence is matched according to preset standard rules to determine a first standard interval, and the preset standard rules are used to screen the process capability indexes in the first sequence that meet the preset standards; the second sequence is screened based on the first standard interval to determine the second standard interval; the first average value of each process capability index in the second abnormal interval and the second average value of each process capability index in the second standard interval are calculated; if there are multiple second abnormal intervals, the average deviations between each second abnormal interval and the second standard interval are compared, and the process capability index in the first abnormal interval with the largest average deviation is used as the production abnormality index, and the average deviation is determined by the first average value and the second average value; the production parameters corresponding to each production abnormality index are determined and used as the cause of the indicator abnormality.

[0011] In one embodiment of the present application, the process capability index includes a first process capability index; calculating the first process capability index includes: determining an upper specification limit, a lower specification limit, a process mean and a process standard deviation of a preset first number of target parameters, wherein the target parameters are the indicator parameters or production parameters; calculating the process upper limit capability index based on the difference between the upper specification limit and the process mean, and the process standard deviation; calculating the process lower limit capability index based on the difference between the process mean and the lower specification limit, and the process standard deviation; and taking the minimum value between the process upper limit capability index and the process lower limit capability index as the first process capability index.

[0012] In one embodiment of the present application, the process capability index includes a process performance index; calculating the process performance index includes: determining the sample mean and sample standard deviation of all the target parameters; calculating the process upper limit performance index based on the difference between the upper specification limit and the sample mean, and the sample standard deviation; calculating the process lower limit performance index based on the difference between the sample mean and the lower specification limit, and the sample standard deviation; and taking the minimum value between the process upper limit performance index and the process lower limit performance index as the process performance index.

[0013] In a second aspect, the present application provides an indicator abnormality identification device, the device comprising: an acquisition module, used to acquire each indicator parameter and each production parameter in the production process within the current time period, and there is a mapping relationship between the indicator parameter and the production parameter; a process capability index calculation module, used to calculate the process capability index corresponding to each target parameter subsequence in the target parameter sequence, and obtain an index sequence formed by each process capability index, the target parameter sequence is a sequence formed by continuous target parameters, each target parameter subsequence includes a preset first number of target parameters, and adjacent target parameter subsequences are spaced by a preset second number of target parameters, and the target parameter is the indicator parameter or the production parameter; an abnormal matching module, used to match the first sequence according to a preset abnormal rule, and determine a first abnormal interval, the preset abnormal rule is used to screen the abnormal process capability index in the first sequence, and the first sequence is the index sequence corresponding to the indicator parameter; an abnormal determination module, used to screen each process capability index in the second sequence based on the first abnormal interval, and determine a second abnormal interval, so as to determine the cause of the indicator abnormality based on the second abnormal interval, there is a mapping relationship between each process capability index included in the first sequence and the second sequence, and the second sequence is the index sequence corresponding to the production parameter.

[0014] In a third aspect, the present application also provides an electronic device comprising: a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement the indicator abnormality identification method as described in the above embodiment.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer executes the indicator anomaly identification method as described in the above embodiments.

[0016] Beneficial effects of the present application: The present application proposes an index abnormality identification method, device, equipment and storage medium. First, by respectively calculating the index sequences corresponding to each index parameter and each production parameter, namely the first sequence and the second sequence, the production process is finely monitored, and the subtle changes of each index parameter and each production parameter in the production process are obtained, thereby improving the sensitivity and accuracy of index monitoring; second, by determining the abnormal process capability index corresponding to each index parameter in the first sequence calculated in real time, the changes and abnormalities of the index parameters in the production process can be timely identified, which significantly improves the efficiency of abnormality identification, so as to facilitate the rapid positioning of the index parameter abnormality and timely intervention, and the stability and level of quality control in the production process are high; third, after identifying the abnormality of the index parameter, that is, after completing the abnormal screening of the index capability index corresponding to the index parameter, the second abnormal interval corresponding to the production parameter is screened according to the first abnormal interval corresponding to the index parameter, thereby quickly locating the specific production parameter causing the abnormality of the index, realizing the rapid tracing of the abnormal cause, so that the relevant personnel can intervene in the abnormality of the index parameter in a targeted manner, which helps to improve production efficiency and product quality.

[0017] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0019] Figure 1 is a flow chart of an indicator abnormality identification method shown in an exemplary embodiment of the present application;

[0020] Figure 2 is a block diagram of an indicator abnormality identification device shown in an exemplary embodiment of the present application;

[0021] Figure 3 It is a structural diagram of a computer system suitable for implementing the electronic device of the present application, shown as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.

[0023] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the form, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0024] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0025] It should be noted that with the rapid development of modern manufacturing, the increasing complexity of products and the increasing quality requirements of consumers, traditional quality control methods can no longer meet the needs of efficient and accurate production. The traditional quality control system mainly relies on sampling and testing of final products. Although this method can guarantee product quality to a certain extent, it also has obvious lags and cannot reflect problems that arise in the production process in a timely manner. Due to the lack of real-time monitoring of the production process, potential quality problems in the production process cannot be solved in the early stages. Problems can only be discovered after the product is completed, and timely intervention cannot be made in the production process, thus affecting the overall quality of the product and production efficiency.

[0026] In order to overcome the above problems, the process capability index (PCI) is widely used in real-time monitoring of the production process. It is an important indicator to measure the stability and capability of the production process. Through continuous monitoring of the production process, it can timely reflect the fluctuations and anomalies in the production process, allowing managers to take measures early to prevent further deterioration of quality problems. However, although the application of the process capability index has significant advantages in real-time monitoring, the current monitoring method based on the process capability index still has some shortcomings: First, the limitation of single indicator monitoring, most of which focuses on the monitoring of a single indicator parameter or production parameter, ignores the interaction between multiple indicators and their comprehensive impact on product quality, and is difficult to fully reflect the true state of the production process, limiting the accuracy and efficiency of indicator abnormality identification; second, the ability to identify and analyze indicator abnormalities is insufficient. When an indicator is abnormal, it can only indicate that there is a deviation from the normal state, but it is difficult to quickly locate the specific link or production parameter where the abnormality occurs, and it is even more difficult to provide in-depth analysis of the cause of the abnormality, which makes it difficult for enterprises to take effective measures to correct the deviation in time and restore the stability of the production process. Taking the production of electronic components as an example, different processes and production parameters (such as welding temperature, welding time, etc.) may affect the final product quality. If the quality is controlled only by the final test results of the product, it is often difficult to timely discover and intervene in the problems in the production process, resulting in low production efficiency and unstable product quality. Therefore, a more efficient indicator abnormality identification method is needed to monitor and adjust in real time during the production process to improve the overall production efficiency and product quality.

[0027] Based on this, the present application proposes an indicator anomaly identification method to achieve abnormal identification and cause tracing of indicator parameters.

[0028] See also Figure 1 , is a flow chart of an indicator abnormality identification method shown in an exemplary embodiment of the present application. The indicator abnormality identification method can be executed by a computer device, such as Figure 1 As shown, in an exemplary embodiment, the indicator abnormality identification method at least includes steps S110 to S140, which are described in detail as follows:

[0029] Step S110, obtaining various index parameters and various production parameters in the production process within the current time period, and there is a mapping relationship between the index parameters and the production parameters.

[0030] In one embodiment of the present application, the index parameter is used to measure and evaluate the key index of a specific target or process. It is a quantitative parameter, which can be set according to actual needs, that is, different index parameters are customized according to different production objects, production line stages or production nodes, and this is not limited here. The setting of the index parameters is closely centered on the production goals and product quality requirements. Taking hot rolling production as an example, the index parameters may include mechanical performance indicators such as yield strength, tensile strength, etc.; taking cold rolling production as an example, the index parameters may include iron loss indicators, etc. Production parameters are process production parameters associated with each index parameter, which act on the production process to ensure that the product reaches the established performance indicators. Usually, an index parameter (such as product quality characteristics) corresponds to one or more production parameters. At the same time, there is also a situation where an index parameter is associated with multiple other types of index parameters, showing the complexity and interrelationship of the production process. Taking the key index parameter of yield strength in hot rolling production as an example, it involves the precise control of multiple production parameters, which at least include finishing rolling inlet temperature, finishing rolling outlet temperature, layer cooling intermediate upper surface temperature, layer cooling intermediate lower surface temperature, layer cooling outlet upper surface temperature, and coiling temperature. This facilitates the subsequent comprehensive analysis of different indicator parameters and their corresponding production parameters, thereby improving the accuracy and efficiency of abnormality identification and cause location.

[0031] Step S120, calculate the process capability index corresponding to each target parameter subsequence in the target parameter sequence, and obtain an index sequence formed by each process capability index. The target parameter sequence is a sequence formed by continuous target parameters. Each target parameter subsequence includes a preset first number of target parameters, and adjacent target parameter subsequences are spaced apart by a preset second number of target parameters. The target parameters are indicator parameters or production parameters.

[0032] Specifically, a preset first number is used as the size of the sliding window, so that the sliding window includes a preset first number of indicator parameters or production parameters; based on the sliding window sliding forward on the indicator parameter sequence in chronological order, and calculating the process capability index corresponding to the indicator parameter in the sliding window at each sliding, the indicator parameter sequence is obtained by sorting the indicator parameters in the current time period from front to back according to time; based on the sliding window sliding forward on the production parameter sequence in chronological order, and calculating the process capability index corresponding to the production parameter in the sliding window at each sliding, the production parameter sequence is obtained by sorting the production parameters in the current time period from front to back according to time.

[0033] In one embodiment of the present application, the sliding window technique is applied to the calculation of the process capability index. The sliding window technique is a technique commonly used in fields such as data stream processing and time series analysis, which allows dynamic observation and analysis of a subset of data, which slides forward as the data continues to flow in; the process capability index (PCI) is a quantitative indicator that measures the ability of a process to meet specific specification requirements in process capability analysis.

[0034] In one embodiment of the present application, when new data, i.e., new indicator parameters or production parameters, accumulate to a certain number, the first sequence or the second sequence is recalculated. For example, the cumulative number is set to k, and for each newly added k data, the nk data after the last acquired data sequence (indicator parameter sequence or production parameter sequence) are retained, and a new data sequence is formed with the newly added k data, and the sliding window is controlled to slide forward from the latest data sequence to recalculate the process capability index of the data in the sliding window to form a new first sequence or second sequence. Ensure the real-time and dynamic nature of abnormal identification. Among them, the setting of the cumulative number needs to match the speed of data inflow to ensure that the changes in process capability can be reflected in a timely manner. The preset first number needs to be determined according to the actual needs of the abnormal analysis and the characteristics of the data, so as to avoid a sliding window that is too small to capture the long-term trend of the process, or a sliding window that is too large to cover the short-term fluctuations of the process, so as to improve the reliability and accuracy of abnormal identification.

[0035] Specifically, the process capability index includes a first process capability index; calculating the first process capability index includes: determining the upper specification limit, lower specification limit, process mean and process standard deviation of all target parameters involved in the process capability index calculation, the target parameters are indicator parameters or production parameters; calculating the process upper limit capability index according to the difference between the upper specification limit and the process mean, and the process standard deviation; calculating the process lower limit capability index according to the difference between the process mean and the lower specification limit, and the process standard deviation; and taking the minimum value between the process upper limit capability index and the process lower limit capability index as the first process capability index.

[0036] In one embodiment of the present application, the expression for calculating the first process capability index (CPK) is as follows:

[0037]

[0038] Among them, CPK in formula (1) represents the first process capability index, USL represents the upper specification limit, LSL represents the lower specification limit, μ represents the process mean, and σ represents the process standard deviation. The process mean is the average value of the indicator parameter or production parameter associated with the product in the production process. Ideally, the process mean should be between the upper specification limit and the lower specification limit of the product. Different types of products are configured with different specification limits to ensure the production quality of the product. The mean standard deviation is a statistic that measures the distribution range of data (indicator parameters or production parameters). The smaller the standard deviation, the more concentrated the data and the more stable the process.

[0039] In one embodiment of the present application, CPK is a statistical indicator that reflects the centralization of the process and the variability of the process, and is used to evaluate whether the internal variation of the production process (variability caused by the process itself) is small enough so that the produced products will hardly exceed the specification limit. The higher the CPK value, the more the process can meet the specification requirements, that is, it meets the actual indicator requirements corresponding to the indicator parameters or the actual production requirements corresponding to the production parameters.

[0040] Specifically, the process capability index includes the process performance index; calculating the process performance index includes: determining the sample mean and sample standard deviation of a preset first number of target parameters; calculating the process upper limit performance index based on the difference between the upper specification limit and the sample mean, and the sample standard deviation; calculating the process lower limit performance index based on the difference between the sample mean and the lower specification limit, and the sample standard deviation; and taking the minimum value between the process upper limit performance index and the process lower limit performance index as the process performance index.

[0041] In one embodiment of the present application, the expression for calculating the Performance Process Capability Index (PPK) is as follows:

[0042]

[0043] Wherein, PPK in formula (2) represents the process performance index, USL represents the upper specification limit, and LSL represents the lower specification limit. represents the sample mean, and S represents the sample standard deviation.

[0044] In one embodiment of the present application, PPK is similar to CPK, but it is calculated based on sample data distributed throughout the entire process and uses the sample standard deviation to estimate process performance. It reflects whether the process can consistently produce products that meet specifications and focuses more on long-term process performance. It takes into account long-term process variability rather than just the variability within the process.

[0045] Step S130, matching the first sequence according to a preset abnormal rule to determine a first abnormal interval, the preset abnormal rule is used to screen abnormal process capability indexes in the first sequence, and the first sequence is an index sequence corresponding to the indicator parameter.

[0046] Specifically, the process capability index corresponding to the indicator parameter is used as the first process index; if the first process indexes of the third consecutive number preset in the first sequence are all less than the preset index lower limit, it is determined that the first process indexes of the third consecutive number preset meet the preset abnormal rule and are used as the first abnormal interval; if the variance, range or standard deviation between the first process indexes of the third consecutive number preset is less than the corresponding preset threshold, it is determined that the first process indexes of the third consecutive number preset meet the preset abnormal rule and are used as the first abnormal interval. Among them, the preset abnormal rule can be adjusted according to the actual situation and is not limited to the above judgment method.

[0047] In one embodiment of the present application, an abnormal first process index is determined from the first sequence, and the first process index can indirectly reflect the abnormal index parameter, thereby quickly locating the abnormal index. Among them, the preset abnormal rule can be formulated according to actual needs, such as flexible adjustment according to different production lines, different types of index parameters and different production nodes, which is not limited here. In this way, by customizing differentiated preset abnormal rules for different production lines, different index parameters and different production periods, it is possible to more accurately identify the index abnormalities occurring in the production process. For example, on a production line, if m consecutive first process indexes are all lower than 0.8, it can be judged as abnormal, and the preset abnormal rules of the first abnormal interval of these first process indexes can be used; on another production line with higher requirements for product quality, the preset index lower limit may be set to 0.7, and if m consecutive first process indexes are all lower than 0.7, it is considered abnormal.

[0048] Step S140, based on the first abnormal interval, the process capability indexes in the second sequence are screened to determine the second abnormal interval, so as to determine the cause of the indicator abnormality based on the second abnormal interval. There is a mapping relationship between the process capability indexes included in the first sequence and the second sequence respectively, and the second sequence is an index sequence corresponding to the production parameters.

[0049] Specifically, each process capability index in the second abnormal interval is screened according to a preset ranking to obtain each production abnormality index; and the production parameter corresponding to each production abnormality index is determined and used as the cause of the indicator abnormality.

[0050] In one embodiment of the present application, the process capability indexes corresponding to the production parameters in all the first abnormal intervals can be compared to determine the abnormality of each production parameter, wherein the smaller the process capability index is, the higher the abnormality of the corresponding production parameter is. Therefore, the process capability index within the preset ranking is used as the production abnormality index, and the production parameter corresponding to the production abnormality index is determined as the cause of the indicator abnormality, and the preset ranking is arranged in ascending order.

[0051] Specifically, the first sequence is matched according to preset standard rules to determine the first standard interval, and the preset standard rules are used to screen the process capability indices that meet the preset standards in the first sequence; the second sequence is screened based on the first standard interval to determine the second standard interval; the first average value of each process capability index in the second abnormal interval and the second average value of each process capability index in the second standard interval are calculated; if there are multiple second abnormal intervals, the average deviations between each second abnormal interval and the second standard interval are compared, and the process capability index in the first abnormal interval with the largest average deviation is used as the production abnormality index, and the average deviation is determined by the first average value and the second average value; the production parameters corresponding to each production abnormality index are determined, and used as the cause of the indicator abnormality.

[0052] In one embodiment of the present application, the preset standard rules can refer to the preset abnormal rules, the difference is that the thresholds involved in the screening are different, for example, if the first process indexes of the third consecutive number preset in the first sequence are all less than the preset index upper limit, then the first process indexes of the third consecutive number preset are determined to meet the preset standard rules and serve as the first standard interval; if the variance, range or standard deviation between the first process indexes of the third consecutive number preset is less than the corresponding preset standard deviation value, then the first process indexes of the third consecutive number preset are determined to meet the preset standard rules and serve as the first standard interval. The preset standard rules can also be adjusted according to actual needs or other screening methods can be used. If multiple first standard intervals are matched, each first standard interval is screened again to determine the first standard interval of a target and participate in subsequent processing.

[0053] In one embodiment of the present application, the expression for determining the average deviation is as follows:

[0054]

[0055] Wherein, AD in formula (3) represents the average deviation, represents the second mean value, Indicates the first average value. Select multiple production parameters with the largest AD, that is, the most obvious decrease relative to the standard control, as the cause of the abnormal indicator.

[0056] Through the above method, the control level of indicator parameters can be monitored in real time. Compared with the ordinary single indicator threshold abnormal monitoring method, the abnormal trend of the indicator can be discovered in time before the indicator parameter is seriously deviated, and the corresponding abnormal production parameters can be obtained at the same time, thereby avoiding the occurrence of problem products and improving the control level of production quality.

[0057] The index anomaly identification method provided by the present application has the following advantages: first, by respectively calculating the index sequences corresponding to each index parameter and each production parameter, namely the first sequence and the second sequence, the production process is finely monitored, the subtle changes of each index parameter and each production parameter in the production process are obtained, and the sensitivity and accuracy of the index monitoring are improved; second, the abnormal process capability index corresponding to each index parameter is determined in the first sequence calculated in real time, so that the changes and anomalies of the index parameters in the production process can be timely identified, and the efficiency of anomaly identification is significantly improved, so as to facilitate the rapid positioning of the index parameter anomaly and timely intervention, and the stability and level of quality control in the production process are high; third, after identifying the abnormality of the index parameter, that is, after completing the abnormal screening of the index capability index corresponding to the index parameter, the second abnormal interval corresponding to the production parameter is screened according to the first abnormal interval corresponding to the index parameter, so as to quickly locate the specific production parameter causing the abnormality of the index, and realize the rapid tracing of the cause of the abnormality, so that the relevant personnel can intervene in the abnormality of the index parameter in a targeted manner, which is helpful to improve production efficiency and product quality.

[0058] See also Figure 2 , is a block diagram of an indicator abnormality identification device shown in an exemplary embodiment of the present application. Figure 2 As shown, in an exemplary embodiment, the indicator abnormality identification device at least includes an acquisition module 210, a process capability index calculation module 220, an abnormality matching module 230 and an abnormality determination module 240, which are described in detail as follows:

[0059] An acquisition module 210 is used to acquire various index parameters and various production parameters in the production process within the current time period, and there is a mapping relationship between the index parameters and the production parameters;

[0060] The process capability index calculation module 220 is used to calculate the process capability index corresponding to each target parameter subsequence in the target parameter sequence, and obtain an index sequence formed by each process capability index. The target parameter sequence is a sequence formed by each continuous target parameter. Each target parameter subsequence includes a preset first number of target parameters, and adjacent target parameter subsequences are spaced by a preset second number of target parameters. The target parameters are indicator parameters or production parameters.

[0061] An abnormal matching module 230 is used to match the first sequence according to a preset abnormal rule to determine a first abnormal interval, wherein the preset abnormal rule is used to screen abnormal process capability indexes in the first sequence, and the first sequence is an index sequence corresponding to the indicator parameter;

[0062] The abnormality determination module 240 is used to screen the process capability indexes in the second sequence based on the first abnormal interval, determine the second abnormal interval, and determine the cause of the indicator abnormality based on the second abnormal interval. There is a mapping relationship between the process capability indexes included in the first sequence and the second sequence respectively, and the second sequence is an index sequence corresponding to the production parameters.

[0063] It should be noted that the indicator anomaly identification device provided in the above embodiment and the indicator anomaly identification method provided in the above embodiment belong to the same concept, wherein the contents of the operations performed by each module have been described in detail in the method embodiment and will not be repeated here.

[0064] The present application also provides an electronic device, comprising: a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement the indicator abnormality identification method as in the above embodiment.

[0065] See also Figure 3 , shows a schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application. It should be noted that, Figure 3 The computer system 300 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0066] like Figure 3 As shown, the computer system 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method in the above embodiment. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0067] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 309 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0068] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the system of the present application are executed.

[0069] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor of a computer, causes the computer to execute the above-mentioned method for identifying abnormal indicators. The computer-readable storage medium may be included in the electronic device described in the above-mentioned embodiment, or may exist independently without being assembled into the electronic device.

[0070] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, system or device. A computer program contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0071] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0072] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0073] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A method for identifying abnormal indicators, characterized in that: Methods include: Acquire various index parameters and various production parameters in the production process within the current time period, wherein there is a mapping relationship between the index parameters and the production parameters; Calculate the process capability index corresponding to each target parameter subsequence in the target parameter sequence to obtain an index sequence formed by each process capability index, wherein the target parameter sequence is a sequence formed by each continuous target parameter, each target parameter subsequence includes a preset first number of target parameters, and adjacent target parameter subsequences are spaced at intervals of a preset second number of target parameters, and the target parameters are the indicator parameters or the production parameters; Matching the first sequence according to a preset abnormal rule to determine a first abnormal interval, wherein the preset abnormal rule is used to screen the abnormal process capability index in the first sequence, and the first sequence is the index sequence corresponding to the indicator parameter; Based on the first abnormal interval, the process capability indexes in the second sequence are screened to determine the second abnormal interval, so as to determine the cause of the indicator abnormality based on the second abnormal interval. There is a mapping relationship between the process capability indexes included in the first sequence and the second sequence respectively, and the second sequence is the index sequence corresponding to the production parameters.

2. The method for identifying abnormal indicators according to claim 1, characterized in that: The process capability index corresponding to each target parameter subsequence in the target parameter sequence is calculated, including: Using the preset first quantity as the size of the sliding window, so that the sliding window includes the preset first quantity of the indicator parameters or the production parameters; Based on the sliding window sliding forward on the indicator parameter sequence, and calculating the process capability index corresponding to the indicator parameter in the sliding window at each sliding, the indicator parameter sequence is obtained by sorting the indicator parameters in the current time period from front to back according to time, and the sliding interval of the sliding window is the preset second number; Based on the sliding window sliding forward on the production parameter sequence, and calculating the process capability index corresponding to the production parameter in the sliding window at each sliding, the production parameter sequence is obtained by sorting the production parameters in the current time period from front to back according to time.

3. The method for identifying abnormal indicators according to claim 1, characterized in that: The judging the first sequence according to a preset abnormal rule to determine the first abnormal interval includes: Using the process capability index corresponding to the indicator parameter as the first process index; If a third number of consecutive first process indexes in the first sequence are all less than a preset index lower limit, it is determined that the third number of first process indexes meet the preset abnormal rule and are used as the first abnormal interval; If the variance, range or standard deviation between a consecutive preset third number of the first process indices is less than the corresponding preset threshold, it is determined that the preset third number of the first process indices conform to the preset abnormality rule and is used as the first abnormality interval.

4. The method for identifying abnormal indicators according to claim 1, characterized in that: The determining the cause of the indicator abnormality based on the second abnormal interval includes: Screening each of the process capability indexes in the second abnormal interval according to a preset ranking to obtain each production abnormality index; The production parameters corresponding to each of the production abnormality indexes are determined and used as the causes of the abnormality of the indexes.

5. The method for identifying abnormal indicators according to claim 4, characterized in that: The determining the cause of the indicator abnormality based on the second abnormal interval includes: Matching the first sequence according to a preset standard rule to determine a first standard interval, wherein the preset standard rule is used to screen the process capability index in the first sequence that meets the preset standard; Screening the second sequence based on the first standard interval to determine a second standard interval; Calculating a first average value of each of the process capability indexes in the second abnormal interval and a second average value of each of the process capability indexes in the second standard interval; If there are multiple second abnormal intervals, compare the average deviations between each of the second abnormal intervals and the second standard interval, and use the process capability index in the first abnormal interval with the largest average deviation as the production abnormality index, wherein the average deviation is determined by the first average value and the second average value; The production parameters corresponding to each of the production abnormality indexes are determined and used as the causes of the abnormality of the indexes.

6. The method for identifying abnormal indicators according to any one of claims 1 to 5, characterized in that: The process capability index includes a first process capability index; Calculating the first process capability index includes: Determine an upper specification limit, a lower specification limit, a process mean, and a process standard deviation of a preset first number of target parameters, wherein the target parameters are the indicator parameters or production parameters; Calculating a process upper limit capability index based on a difference between the upper specification limit and the process mean, and the process standard deviation; Calculating a process lower limit capability index based on a difference between the process mean and the lower specification limit and the process standard deviation; The minimum value between the process upper limit capability index and the process lower limit capability index is used as the first process capability index.

7. The method for identifying abnormal indicators according to claim 6, characterized in that: The process capability index includes a process performance index; Calculating the process performance index includes: Determining the sample mean and sample standard deviation of all the target parameters; Calculating a process upper limit performance index based on a difference between the upper specification limit and the sample mean, and the sample standard deviation; Calculating a process lower limit performance index based on a difference between the sample mean and the lower specification limit, and the sample standard deviation; The minimum value between the process upper limit performance index and the process lower limit performance index is taken as the process performance index.

8. An indicator abnormality identification device, characterized in that: The device comprises: An acquisition module, used to acquire various index parameters and various production parameters in the production process within the current time period, and there is a mapping relationship between the index parameters and the production parameters; A process capability index calculation module is used to calculate the process capability index corresponding to each target parameter subsequence in the target parameter sequence, and obtain an index sequence formed by each of the process capability indices, wherein the target parameter sequence is a sequence formed by continuous target parameters, each of the target parameter subsequences includes a preset first number of the target parameters, and adjacent target parameter subsequences are spaced at intervals of a preset second number of the target parameters, and the target parameters are the indicator parameters or the production parameters; an abnormal matching module, used for matching the first sequence according to a preset abnormal rule to determine a first abnormal interval, wherein the preset abnormal rule is used for screening the abnormal process capability index in the first sequence, and the first sequence is the index sequence corresponding to the indicator parameter; An abnormality determination module is used to screen each of the process capability indexes in the second sequence based on the first abnormal interval, determine the second abnormal interval, and determine the cause of the indicator abnormality based on the second abnormal interval. There is a mapping relationship between each of the process capability indexes included in the first sequence and the second sequence, and the second sequence is the index sequence corresponding to the production parameters.

9. An electronic device, characterized in that: include: processor, memory, and communication bus; The communication bus is used to connect the processor and the memory; The processor is configured to execute the computer program stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is used to make a computer execute the method according to any one of claims 1 to 7.

Images