Hard alloy wear-resistant block production fluctuation analysis method

Abstract

The invention is applicable to the technical field of alloy material production, and particularly relates to a hard alloy wear-resistant block production fluctuation analysis method which comprises the following steps: acquiring hard alloy wear-resistant block production information; wherein the production information of the hard alloy wear-resistant block comprises a product quality set of the hard alloy wear-resistant block and a production parameter set corresponding to each production link; generating a fluctuation analysis task based on the product quality set; wherein the fluctuation analysis task is used for indicating a production link needing to be analyzed currently; analyzing based on the fluctuation analysis task and the corresponding production parameter set to obtain a fluctuation parameter set; wherein the fluctuation parameter set is used for reflecting fluctuation characteristics of production parameters which enable the production of the hard alloy wear-resistant block to fluctuate; generating an analysis result based on the fluctuation parameter set; wherein the analysis result is used for reflecting the source of fluctuation of the production parameters. According to the method, a clear improvement direction is provided for production optimization, and targeted measures can be quickly formulated.

Description

Technical Field

[0001] The present application belongs to the technical field of alloy material production, and in particular relates to a method for analyzing production fluctuations of cemented carbide wear-resistant blocks. Background Art

[0002] As critical and vulnerable components in heavy-duty machinery like construction machinery and mining equipment, cemented carbide wear blocks' quality and stability directly impact the overall machine's operating efficiency and service life. The production of cemented carbide wear blocks involves multiple steps, including mixing, forming, sintering, and fine grinding. Fluctuations in production parameters at each step (such as mixing ratio, sintering temperature, and holding time) can lead to product quality deviations, manifesting as substandard hardness, insufficient wear resistance, and excessive dimensional accuracy.

[0003] Currently, there is a considerable amount of technical expertise in analyzing production fluctuations in cemented carbide wear-resistant blocks. The industry's commonly used data-driven approach involves collecting production parameters and product quality inspection data from each stage and applying statistical analysis tools (such as correlation analysis and trend charting). This approach, which analyzes fluctuations in each production stage individually, is not only complex and requires processing large amounts of data, but can also lead to deviations in the root causes ultimately identified. Summary of the Invention

[0004] The embodiment of the present application provides a method for analyzing production fluctuations of cemented carbide wear-resistant blocks, which can solve the problems of low efficiency and inaccurate fluctuation tracing in the analysis method of production fluctuations of cemented carbide wear-resistant blocks.

[0005] In a first aspect, an embodiment of the present application provides a method for analyzing production fluctuations of cemented carbide wear-resistant blocks, comprising: Acquire production information of cemented carbide wear-resistant blocks; wherein the production information of cemented carbide wear-resistant blocks includes a product quality set of cemented carbide wear-resistant blocks and a production parameter set corresponding to each production link; Generating a fluctuation analysis task based on the product quality set; wherein the fluctuation analysis task is used to indicate the production link that currently needs to be analyzed; Performing analysis based on the fluctuation analysis task and the corresponding production parameter set to obtain a fluctuation parameter set; wherein the fluctuation parameter set is used to reflect the fluctuation characteristics of the production parameters that cause fluctuations in the production of cemented carbide wear-resistant blocks; An analysis result is generated based on the fluctuation parameter set; wherein the analysis result is used to reflect the root cause of the fluctuation of the production parameters.

[0006] The above technical solutions in the embodiments of the present application have at least the following technical effects: The present application provides a method for analyzing the production fluctuation of cemented carbide wear-resistant blocks. The method obtains the production information of cemented carbide wear-resistant blocks, including the product quality set of cemented carbide wear-resistant blocks and the production parameter set corresponding to each production link; then generates a fluctuation analysis task based on the product quality set to indicate the production link that needs to be analyzed; then, based on the fluctuation analysis task and the corresponding production parameter set, a fluctuation parameter set is obtained to reflect the fluctuation characteristics of the production parameters that cause fluctuations in the production of cemented carbide wear-resistant blocks; finally, based on the fluctuation parameter set, an analysis result is generated to reflect the root cause of the fluctuation of the production parameters. This method obtains the fluctuation characteristics of the production parameters by parsing the obtained fluctuation parameter set, realizes in-depth mining from "parameter value fluctuation" to "fluctuation law and influence", and provides a richer basis for tracing the source; by associating "quality data-production link-parameter characteristics-fluctuation root" throughout the entire process, a closed-loop analysis link is formed, which effectively solves the fluctuation traceability problem caused by multi-link parameter coupling. In the production of cemented carbide wear-resistant blocks, a certain quality indicator may be affected by multiple links such as mixing and sintering. This method uses the correlation between product quality sets and production links, and then quickly locates the fluctuating parameters through parameter analysis corresponding to the production links, and finally traces the specific root causes. Compared with analyzing the "parameter fluctuations" of each production link and simply equating "fluctuating parameters" with the "root causes of fluctuations", this method can quickly and effectively find the problems that cause production fluctuations. At the same time, it provides a clear improvement direction for production optimization, which helps to quickly formulate targeted measures, thereby reducing quality fluctuations and improving product consistency. It is especially suitable for production scenarios of products such as cemented carbide wear-resistant blocks that have strict requirements on material properties.

[0007] In a possible implementation of the first aspect, generating a fluctuation analysis task based on the product quality set includes: Determine a key quality indicator based on the product quality set; wherein the key quality indicator is used to indicate the main quality indicator of the quality data fluctuation exceeding the standard; Establishing a quality-link mapping rule, and obtaining a candidate production link corresponding to the key quality indicator based on the quality-link mapping rule; wherein the candidate production link is used to reflect a collection of multiple production links; A fluctuation analysis task is obtained based on the candidate production link.

[0008] In a possible implementation of the first aspect, determining a key quality indicator based on the product quality set includes: The product quality set is divided into a basic index layer and a performance index layer; wherein the basic index layer is used to reflect the inherent attribute data of the cemented carbide wear-resistant block, and the performance index layer is used to reflect the dynamic attribute data of the cemented carbide wear-resistant block; Calculating the standard deviation of the basic indicator layer and the performance indicator layer respectively to obtain a first fluctuation coefficient and a second fluctuation coefficient; wherein the first fluctuation coefficient is used to reflect the degree of data fluctuation corresponding to the basic indicator layer, and the second fluctuation coefficient is used to reflect the degree of data fluctuation corresponding to the performance indicator layer; A key quality indicator is determined based on the first coefficient of fluctuation and the second coefficient of fluctuation.

[0009] In a possible implementation of the first aspect, determining a key quality indicator based on the first fluctuation coefficient and the second fluctuation coefficient includes: Comparing the first fluctuation coefficient with a first threshold, and comparing the second fluctuation coefficient with a second threshold, to obtain a comparison result; wherein the first threshold is a critical value of the fluctuation of the basic indicator layer data, and the second threshold is a critical value of the fluctuation of the performance indicator layer data; Key quality indicators are determined based on the comparison results.

[0010] In a possible implementation of the first aspect, determining a key quality indicator based on the comparison result includes: If the comparison result is that the first fluctuation coefficient is greater than the first threshold, and the second fluctuation coefficient is greater than the second threshold, generating associated quality indicators of the basic indicator layer and the performance indicator layer, and determining the associated quality indicators as key quality indicators; If the comparison result is that only the first fluctuation coefficient is greater than the first threshold, determining the quality indicator corresponding to the basic indicator layer as a key quality indicator; If the comparison result is that only the second fluctuation coefficient is greater than the second threshold, the quality indicator corresponding to the performance indicator layer is determined as a key quality indicator.

[0011] In a possible implementation of the first aspect, establishing a quality-link mapping rule includes: Establishing a link-parameter comparison table; wherein the link-parameter comparison table is used to reflect the production process corresponding to each production process; Generate a correlation matrix based on historical production fluctuation data; wherein the correlation matrix is ​​used to reflect the co-occurrence frequency of parameter fluctuations and quality index exceeding the standard; A quality-link mapping rule is established based on the association matrix and the link-parameter comparison table.

[0012] In a possible implementation of the first aspect, obtaining a fluctuation analysis task based on the candidate production link includes: Generate multiple fluctuation transmission chains based on the process connection relationship of the candidate production links; wherein the fluctuation transmission chain is used to reflect the transmission path of the parameter fluctuation of the preceding link to the parameter abnormality of the subsequent link through the process coupling relationship; Calculating the fluctuation contribution of each of the fluctuation transmission chains; wherein the fluctuation contribution is used to reflect the cumulative impact of the co-occurrence probability of each production link in the fluctuation transmission chain; A fluctuation analysis task is obtained based on the fluctuation contribution.

[0013] In a possible implementation of the first aspect, obtaining the fluctuation analysis task based on the fluctuation contribution includes: sorting the plurality of fluctuation transmission chains based on the fluctuation contribution to obtain a transmission chain sequence; Determine the core fluctuation chain based on the transmission chain sequence; A fluctuation analysis task is obtained based on the core fluctuation chain.

[0014] In a possible implementation of the first aspect, obtaining a fluctuation analysis task based on the core fluctuation chain includes: Calculating the correlation between each candidate production link and the key quality indicator based on the order position of each candidate production link in the core fluctuation chain; The candidate production link with the greatest correlation is determined as the fluctuation analysis task.

[0015] In a possible implementation of the first aspect, the performing parsing based on the fluctuation analysis task and the corresponding production parameter set to obtain the fluctuation parameter set includes: Matching the fluctuation analysis task with the corresponding production parameter set to obtain a parameter analysis target; wherein the parameter analysis target is used to indicate the production parameter in the production parameter set corresponding to the fluctuation analysis task; Extracting time series fluctuation data within a preset time window based on the parameter analysis target; wherein the time series fluctuation data includes parameter collection time points and corresponding parameter values; Feature extraction is performed based on the time series fluctuation data to obtain a fluctuation parameter set; wherein the fluctuation parameter set includes time domain features and fluctuation morphology features.

[0016] In a second aspect, an embodiment of the present application provides a cemented carbide wear-resistant block production fluctuation analysis system, comprising: An acquisition module is used to acquire production information of cemented carbide wear-resistant blocks; wherein the production information of cemented carbide wear-resistant blocks includes a product quality set of cemented carbide wear-resistant blocks and a production parameter set corresponding to each production link; A first generating module is configured to generate a fluctuation analysis task based on the product quality set; wherein the fluctuation analysis task is used to indicate a production link that currently needs to be analyzed; An analysis module, configured to perform analysis based on the fluctuation analysis task and the corresponding production parameter set to obtain a fluctuation parameter set; wherein the fluctuation parameter set is configured to reflect fluctuation characteristics of the production parameters that cause fluctuations in the production of cemented carbide wear-resistant blocks; The second generating module is used to generate an analysis result based on the fluctuation parameter set; wherein the analysis result is used to reflect the root cause of the fluctuation of the production parameters.

[0017] In a third aspect, an embodiment of the present application provides a cemented carbide wear-resistant block production fluctuation analysis device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the methods described in the first aspect above when executing the computer program.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above-mentioned first aspects is implemented.

[0019] In the fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a cemented carbide wear-resistant block production fluctuation analysis device, the cemented carbide wear-resistant block production fluctuation analysis device enables the cemented carbide wear-resistant block production fluctuation analysis method described in any one of the above-mentioned first aspects.

[0020] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 1 is a flow chart of a method for analyzing production fluctuations of cemented carbide wear-resistant blocks provided in an embodiment of the present application; Figure 2 This is a schematic diagram of the implementation process of the method for analyzing the production fluctuation of cemented carbide wear-resistant blocks provided in an embodiment of the present application; Figure 3 This is a schematic diagram of the structure of the cemented carbide wear-resistant block production fluctuation analysis system provided in an embodiment of the present application; Figure 4 It is a structural schematic diagram of the cemented carbide wear-resistant block production fluctuation analysis equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0024] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0025] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0026] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if the described condition or event is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of the described condition or event" or "in response to detecting the described condition or event," depending on the context.

[0027] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0029] Currently, a certain amount of technical expertise has been accumulated regarding analytical methods for analyzing production fluctuations in cemented carbide wear-resistant blocks. The data-driven approach commonly used within the industry involves collecting production parameters and product quality inspection data from each link, and applying statistical analysis tools (such as correlation analysis and trend charting) to identify correlations between parameter fluctuations and changes in quality indicators. For example, by comparing sintering temperature data from different batches with product hardness test results, the effects of temperature fluctuations on hardness can be identified; or, based on historical data, a threshold range for parameter fluctuations can be established, triggering an alert when real-time parameters exceed the threshold. This method analyzes fluctuations in each production link individually, resulting in a complex process and requiring a large amount of data to be processed. Furthermore, it can lead to deviations in the root cause ultimately identified. When parameters in multiple links fluctuate simultaneously, it is difficult to quickly identify the dominant influencing factor.

[0030] To solve the above problems, an embodiment of the present application provides a method for analyzing the production fluctuation of cemented carbide wear-resistant blocks. In this method, the production information of cemented carbide wear-resistant blocks is obtained, including the product quality set of cemented carbide wear-resistant blocks and the production parameter set corresponding to each production link; then, based on the product quality set, a fluctuation analysis task is generated to indicate the production link that needs to be analyzed; then, based on the fluctuation analysis task and the corresponding production parameter set, a fluctuation parameter set is obtained to reflect the fluctuation characteristics of the production parameters that cause fluctuations in the production of cemented carbide wear-resistant blocks; finally, based on the fluctuation parameter set, an analysis result is generated to reflect the root cause of the fluctuation of the production parameters. This method obtains the fluctuation characteristics of the production parameters by parsing the fluctuation parameter set, and realizes in-depth mining from "parameter value fluctuations" to "fluctuation laws and impacts". Compared with the traditional method of only focusing on whether the parameters exceed the standard, this method can capture key characteristics of the fluctuations, such as frequency, duration, and conduction path, and provide a richer basis for traceability; by associating the "quality data-production link-parameter characteristics-fluctuation root cause" throughout the process, a closed-loop analysis link is formed, which effectively solves the problem of fluctuation traceability caused by multi-link parameter coupling. In the production of cemented carbide wear-resistant blocks, a certain quality indicator may be affected by multiple links such as mixing and sintering. This method locks the related links through the task generation link, and then locates the core fluctuation parameters through parameter analysis, and finally traces them back to specific root causes such as equipment, raw materials or operations. Compared with the one-sided judgment that simply equates "parameter fluctuation" with "root cause of fluctuation", it provides a clear improvement direction for production optimization, helps to quickly formulate targeted measures, thereby reducing quality fluctuations and improving product consistency. It is especially suitable for product production scenarios such as cemented carbide wear-resistant blocks that have strict requirements on material performance.

[0031] The cemented carbide wear-resistant block production fluctuation analysis method provided in the embodiment of the present application can be applied to the cemented carbide wear-resistant block production fluctuation analysis equipment. At this time, the cemented carbide wear-resistant block production fluctuation analysis equipment is the executor of the cemented carbide wear-resistant block production fluctuation analysis method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the cemented carbide wear-resistant block production fluctuation analysis equipment.

[0032] For example, the production fluctuation analysis device of cemented carbide wear-resistant blocks can be on terminal devices such as mobile phones, tablet computers, wearable devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), desktop computers, smart large screens, smart TVs, handheld devices with wireless communication functions, computing devices or other processing devices connected to wireless modems, Internet of Things terminals, computers, laptops, handheld communication devices, handheld computing devices, satellite wireless devices, wireless modem cards, customer premise equipment (CPE) and / or other devices for communicating on wireless systems and next-generation communication systems, such as mobile terminals in 5G networks or mobile terminals in future evolved public land mobile networks (PLMN), etc.

[0033] In order to better understand the method for analyzing the production fluctuation of cemented carbide wear-resistant blocks provided in the embodiment of the present application, the specific implementation process of the method for analyzing the production fluctuation of cemented carbide wear-resistant blocks provided in the embodiment of the present application is exemplarily introduced below.

[0034] Figure 1 and Figure 2 A schematic flow chart of a method for analyzing production fluctuations of cemented carbide wear-resistant blocks provided in an embodiment of the present application is shown. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks includes: S100, obtaining production information of cemented carbide wear-resistant blocks; wherein the production information of cemented carbide wear-resistant blocks includes a product quality set of cemented carbide wear-resistant blocks and a production parameter set corresponding to each production link.

[0035] It is understood that the product quality set of cemented carbide wear blocks refers to the collection of quality data for the finished products of continuously produced cemented carbide wear blocks, and includes multi-dimensional quality data, such as hardness test values, wear resistance dynamic property data (such as weight loss wear, friction coefficient), dimensional accuracy, etc. The product quality set can be obtained from the inspection database, manually entered, etc., but is not limited to these. The inspection database contains the inspection data of each cemented carbide wear block, and the corresponding inspection quality data can be directly obtained by establishing a communication connection with the inspection equipment.

[0036] A production parameter set refers to the collection of process parameters corresponding to each production link (i.e., production process). For example, the mixing step includes the powder ratio, stirring speed, and mixing time; the molding step includes the pressing pressure and holding time; and the sintering step includes the heating rate, sintering temperature, holding time, and cooling rate. Production parameter sets can be acquired in real time through a communication connection with production equipment or manually entered, among other methods, but are not limited to these.

[0037] S200, generating a fluctuation analysis task based on a product quality set; wherein the fluctuation analysis task is used to indicate a production link that currently needs to be analyzed.

[0038] It can be understood that the quality data of different attributes may correspond to one or more production processes or production parameters. For example, if the dynamic attribute data of wear resistance fluctuates significantly, it may be related to the holding time of the sintering process or the particle size distribution of the raw materials; if the hardness and wear resistance fluctuate at the same time, the influence of the mixing uniformity or molding pressure needs to be considered.

[0039] For example, by analyzing a product quality set, we can identify the quality data that causes fluctuations or the quality data that causes the most severe fluctuations. Based on the fluctuating quality data, we can then identify multiple production links associated with that quality data. The fluctuation analysis task can then be performed by analyzing the production links to identify the production links that primarily cause the fluctuations. Alternatively, we can segment the product quality set according to time (e.g., hourly), synchronously record the parameter change timestamps of each production link, and use the Apriori algorithm to mine the temporal association rule of "parameter fluctuation → quality fluctuation" (e.g., "hardness fluctuation occurs 2 hours after sintering temperature fluctuation" with a support of ≥ 0.8). Production links that meet these rules can be listed as analysis targets, forming a dynamic fluctuation analysis task. This approach is not limited to the examples presented here.

[0040] In a possible implementation, in step S200, generating a fluctuation analysis task based on a product quality set includes: S210, determining key quality indicators based on the product quality set; wherein the key quality indicators are used to indicate the main quality indicators of the quality data that exceed the fluctuation standard.

[0041] It can be understood that key quality indicators are the analytical indicators used to analyze this fluctuation. For example, the product quality set can be divided into multiple hierarchical indicators based on attributes, and the degree of fluctuation of each hierarchical indicator can be analyzed separately. Finally, the key quality indicators are determined based on the degree of fluctuation of each hierarchical indicator. Alternatively, the "quality fluctuation entropy weight method" can be used to quantify the importance of indicators. This means that each indicator in the product quality set is treated as a random variable, and its objective weight is determined by calculating information entropy. Then, the indicator with the highest weight is selected as the key quality indicator, and so on, but is not limited to this.

[0042] In one possible implementation, in step S210, determining key quality indicators based on the product quality set includes: S211, dividing the product quality set into a basic index layer and a performance index layer; wherein the basic index layer is used to reflect the inherent attribute data of the cemented carbide wear-resistant block, and the performance index layer is used to reflect the dynamic attribute data of the cemented carbide wear-resistant block.

[0043] Understandably, this stratification approach is a scientific classification logic based on the material properties and service requirements of carbide wear blocks, aiming to accurately capture the source of quality fluctuations from different dimensions. The basic indicator layer focuses on the inherent properties of the material itself. In addition to hardness data, it also extends to parameters such as density, compactness, and porosity. These indicators are directly determined by the material composition and molding process and form the "innate foundation" of product performance. For example, hardness data is measured at five different points on the product cross-section (edge, center, and trisection) using a microhardness tester, and the average value is taken as the basic indicator value for the batch. The performance indicator layer focuses on the product's service performance under actual operating conditions. In addition to wear resistance, it also includes dynamic performance indicators such as impact toughness and corrosion resistance. Taking wear resistance as an example, a pin-on-disc wear tester is used to test the product under a specific load (e.g., 50N) and speed (e.g., 200r / min). The wear loss (in mg) within one hour is recorded, and the wear loss is used as a proxy for quantitative wear resistance. After stratification, the indicators of each layer are standardized (for example, indicators of different units are converted into dimensionless values ​​in the interval [0,1]).

[0044] S212, respectively calculating the standard deviation of the basic indicator layer and the performance indicator layer to obtain a first fluctuation coefficient and a second fluctuation coefficient; wherein the first fluctuation coefficient is used to reflect the degree of data fluctuation corresponding to the basic indicator layer, and the second fluctuation coefficient is used to reflect the degree of data fluctuation corresponding to the performance indicator layer.

[0045] It can be understood that calculating the standard deviation of the basic index layer and the performance index layer to obtain the coefficient of fluctuation is the core step in transforming the degree of fluctuation of quality data from qualitative description to quantitative analysis. Its essence is to quantify the degree of dispersion of data through statistical methods. Taking hardness data as an example, after obtaining the standard deviation, the standard deviation is compared with the process standard center value of the index (such as 200HV) to obtain the relative fluctuation ratio, such as σ 基础 =5HV, the hardness fluctuation coefficient =5 / 200=2.5%.

[0046] S213 , determining a key quality indicator based on the first fluctuation coefficient and the second fluctuation coefficient.

[0047] For example, the fluctuation degree of the first fluctuation coefficient and the second fluctuation coefficient can be compared with the preset thresholds respectively, and the main fluctuation degree can be determined by the difference, and the key quality indicators can be determined based on the main fluctuation degree; the key quality indicators can also be determined by constructing a two-dimensional model of "fluctuation contribution-process sensitivity". The model uses the first and second fluctuation coefficients as the vertical axis (representing the fluctuation contribution), and the sensitivity of the indicator to the process parameters as the horizontal axis (the higher the sensitivity, the larger the horizontal axis value). The indicator priority is ranked by quadrant division, namely the first quadrant (high fluctuation contribution + high sensitivity): for example, the hardness fluctuation coefficient in the basic indicator layer is 5% (exceeding the threshold by 2%), and its sensitivity to the sintering temperature is 0.4HV / ℃ (for every 1℃ fluctuation in temperature, the hardness fluctuates by 0.4HV). Such indicators are listed as key quality indicators; the second quadrant (high fluctuation contribution + low sensitivity): for example, the wear resistance fluctuation coefficient in the performance indicator layer is 6% (exceeding the threshold by 2%), but the sensitivity to the fine grinding roughness is only 0.1mg / μm (for every 1μm change in roughness, the wear amount fluctuates by 0.1mg). Such indicators are listed as sub-key indicators; the third quadrant (low fluctuation contribution + low sensitivity), the indicator does not need to be listed as key, only routine monitoring is required, the fourth quadrant (low fluctuation contribution + high sensitivity), includes potential key indicators, and so on, but not limited to this.

[0048] With this setting, by dividing the product quality set into a basic indicator layer and a performance indicator layer, calculating the fluctuation coefficient and determining the key quality indicators respectively, a hierarchical focus on the traceability of quality fluctuations is achieved: the basic indicator layer focuses on the impact of the front-end process on the inherent properties, and the performance indicator layer locks the effect of the back-end process and service scenarios on the dynamic properties. The combination of the two can not only accurately locate the source of fluctuations in a single link, but also reveal the implicit correlation of "the transmission of inherent property fluctuations to dynamic properties", greatly improving the targeting and efficiency of fluctuation analysis, while providing a clear direction for differentiated process optimization and reducing the cost of invalid analysis.

[0049] In a possible implementation, in step S213, determining a key quality indicator based on the first fluctuation coefficient and the second fluctuation coefficient includes: S2131, compare the first fluctuation coefficient with the first threshold, and compare the second fluctuation coefficient with the second threshold to obtain a comparison result; wherein the first threshold is the critical value of the basic indicator layer data fluctuation, and the second threshold is the critical value of the performance indicator layer data fluctuation.

[0050] It is understood that the first and second thresholds can be determined based on a comprehensive consideration of the product's application scenario, process capabilities, and quality objectives. Specifically, the first threshold (basic indicator layer) should be based on the inherent process stability of the product's properties. By analyzing the fluctuation data of the basic indicators of qualified batches over the past three months, the 3σ value is used as the initial threshold (for example, a 3σ value of 6HV for hardness corresponds to a first threshold of 3%, or 6 / 200). For high-precision applications (such as aerospace), this value can be tightened to 2σ (a threshold of 2%). The second threshold (performance indicator layer) should be based on the service requirements of dynamic properties. For example, the wear resistance of wear-resistant blocks used in mining and submarine engineering construction must ensure fluctuations of no more than 5% (otherwise, the service life will be shortened by more than 20%), so the second threshold is set at 5%. For wear-resistant blocks used in general machinery, this can be relaxed to 8%. Furthermore, the thresholds need to be dynamically updated: as process improvements (such as the introduction of an automated mixing system) reduce the fluctuation of the basic indicators, the 3σ value should be recalculated and the first and second thresholds adjusted downward.

[0051] S2132, determine key quality indicators based on the comparison results.

[0052] For example, the corresponding quality indicator is determined as the housekeeper quality indicator by comparing the different situations, that is, when the first fluctuation coefficient is greater than the first threshold and the second fluctuation coefficient is less than or equal to the second threshold, it indicates that the inherent property fluctuation is the main contradiction. At this time, the specific indicator with the most significant fluctuation can be screened from the basic indicator layer (such as the hardness fluctuation coefficient of 4.5% is greater than 3%, and the density fluctuation coefficient of 2.1% is less than or equal to 3%, then "hardness" is locked); if the second fluctuation coefficient is greater than the second threshold and the first fluctuation coefficient is less than or equal to the first threshold, it indicates that the dynamic property fluctuation is more critical, then it can be selected from the performance indicator layer (such as the wear resistance fluctuation coefficient of 6% is greater than 5%, then "wear resistance" is locked); if both exceed the threshold, further judgment can be made and one of the two can be determined as the key quality indicator; or both can be used as key quality indicators, and so on.

[0053] This setup, through the combination of threshold comparison and correlation analysis, ensures that the determination of key quality indicators is both objective and logical. Its technical benefits are as follows: First, differentiated thresholds (first and second thresholds) distinguish between control standards for inherent and dynamic properties, reducing misjudgments caused by a "one-size-fits-all" approach (e.g., applying a stricter threshold for wear resistance, which directly impacts service life); Second, through scenario-based decision-making (single-layer fluctuation / both-layer fluctuation), key indicators can address both the core issues of independent fluctuations and the implicit correlations of coordinated fluctuations; Third, it provides clear guidance for subsequent analysis (e.g., if the key indicator is "hardness," focus on molding / sintering; if it is "wear resistance," focus on sintering / fine grinding), reducing invalid analysis and improving traceability efficiency. This approach shifts quality control from "full-indicator monitoring" to "targeted governance."

[0054] In one possible implementation, in step S2132, determining a key quality indicator based on the comparison result includes: S21321a: If the comparison result is that the first fluctuation coefficient is greater than the first threshold and the second fluctuation coefficient is greater than the second threshold, generating associated quality indicators of the basic indicator layer and the performance indicator layer, and determining the associated quality indicators as key quality indicators.

[0055] It can be understood that when both the first and second fluctuation coefficients exceed the corresponding thresholds, it indicates that there is a coordinated fluctuation between the basic indicator layer and the performance indicator layer, and it is necessary to capture this implicit cross-level correlation by generating associated quality indicators. The generation of associated quality indicators requires exploring the intrinsic connection between the two based on the process mechanism: for example, when the hardness of the basic indicator layer and the wear resistance of the performance indicator layer both fluctuate, analysis shows that "insufficient mixing uniformity will lead to uneven hardness distribution, which in turn reduces local wear resistance." Therefore, the associated quality indicator can be defined as "co-fluctuation of mixing uniformity-hardness-wear resistance." The specific generation process is: through the process flow chart, the potential transmission links between the basic indicator layer and the performance indicator layer are sorted out, for example, from "raw material purity → mixing uniformity → hardness distribution → grain boundary strength → wear resistance", clarifying the cause and effect relationship of each link (for example, fluctuations in raw material purity will amplify mixing unevenness). In the confirmed transmission link, the core process parameters that have a significant impact on both layers of indicators are selected as associated nodes. For example, in the "mixing uniformity-hardness-wear resistance" link, mixing time (affecting uniformity) and sintering temperature (affecting hardness and grain boundary strength) are key nodes. Fluctuations in their parameters will simultaneously cause abnormalities in both layers of indicators. The core node is then combined with the associated two layers of indicators to form the name of the associated quality indicator, such as "mixing time-sintering temperature → hardness-wear resistance coordinated fluctuations."

[0056] S21321b: If the comparison result is that only the first fluctuation coefficient is greater than the first threshold, the quality indicator corresponding to the basic indicator layer is determined as the key quality indicator.

[0057] It can be understood that when only the first fluctuation coefficient exceeds the first threshold, it indicates that the fluctuation is primarily due to the inherent properties of the material. In this case, the quality indicators corresponding to the basic indicator layer should be listed as key indicators as a whole and further refined to specific parameters. For example, when the basic indicator layer includes hardness, density, and compactness, the fluctuation contribution of each parameter should be calculated (for example, hardness fluctuation contribution is 60%, density 30%), and the parameter with the highest contribution (such as hardness) should be designated as the core key indicator.

[0058] S21321c: If the comparison result is that only the second fluctuation coefficient is greater than the second threshold, the quality indicator corresponding to the performance indicator layer is determined as a key quality indicator.

[0059] It can be understood that when only the second fluctuation coefficient exceeds the second threshold, it indicates that the fluctuation is concentrated in the product's dynamic service performance. The quality indicators corresponding to the performance indicator layer need to be identified as key and correlated with the back-end process and usage scenarios. For example, if the wear resistance of the performance indicator layer fluctuates, wear resistance is identified as a key quality indicator.

[0060] With this setting, key quality indicators are determined by different scenarios. When the fluctuations of the basic indicator layer and the performance indicator layer both exceed the standard, related quality indicators are generated to capture the implicit correlation of cross-level collaborative fluctuations. When only a single indicator layer fluctuates, the corresponding level indicator is locked. This ensures accurate coverage of the common root causes of collaborative fluctuations and achieves focused analysis of independent fluctuations. It significantly improves the comprehensiveness and pertinence of key quality indicator identification, provides clear directional guidance for subsequent tracing of production fluctuations, and effectively reduces analysis inefficiencies caused by indicator fragmentation or omissions.

[0061] S220, establishing a quality-link mapping rule, and obtaining candidate production links corresponding to key quality indicators based on the quality-link mapping rule; wherein the candidate production links are used to reflect a collection of multiple production links.

[0062] It can be understood that quality-link mapping rules refer to a set of structured rules that clarify the correspondence between "quality indicator fluctuations" and "production links" by systematically analyzing the process logic and historical data of the entire cemented carbide wear-resistant block production process. This process can be established by first establishing rules for comparing links and parameters to identify the key controllable parameters in each link. Then, through correlation analysis (such as calculating the Pearson correlation coefficient), the strength of the correlation between parameter fluctuations and quality indicator violations is quantified. Finally, the rationality of the correlation is verified by combining process mechanisms to form a structured quality-link mapping rule. Alternatively, a machine learning model can be used to extract time-series parameters from the entire production process (such as sintering temperature curves and pressing pressure change rates) and quality inspection data, construct a dataset containing more than 5,000 batches, and perform time-domain and frequency-domain feature extraction on the parameters. For example, the fluctuation entropy of sintering temperature and the spectral characteristics of mixing power are calculated to enhance the model's ability to perceive fluctuation patterns. Feature engineering is then used to process production time-series and static parameters, and a multimodal fusion model is constructed to learn the impact of parameters on quality indicators. This establishes quality-link mapping rules, and other methods are also available, but are not limited to these. By inputting the key quality indicators into the quality mapping rules, the corresponding candidate production links can be obtained.

[0063] In a possible implementation, in step S220, a quality-link mapping rule is established, including: S221, establishing a link-parameter comparison table; wherein the link-parameter comparison table is used to reflect the production process corresponding to each production process.

[0064] It can be understood that the establishment of the link-parameter comparison table can adopt the hierarchical method of "process decomposition-parameter clustering", decomposing the cemented carbide wear-resistant block production chain into four major stages: raw material pretreatment (such as ball milling, drying), forming (such as molding, cold isostatic pressing), sintering (such as vacuum sintering, hot isostatic pressing), and post-processing (such as heat treatment, surface coating). Each stage is further subdivided into specific processes (such as the sintering stage includes three processes of heating, insulation, and cooling). For each process, the key parameters are identified through process FMEA (failure mode and effect analysis) to form a link-parameter comparison table.

[0065] S222, generating a correlation matrix based on historical production fluctuation data; wherein the correlation matrix is ​​used to reflect the co-occurrence frequency of parameter fluctuations and quality indicator exceeding the standard.

[0066] It's understandable that the data should first be standardized (e.g., parameter fluctuations and quality indicator exceedances are uniformly converted to dimensionless values ​​in the range [0, 1]), and then the co-occurrence frequency can be calculated using sliding window statistics. Specifically, for example, production data from the past 12 months (containing parameter records and corresponding quality test results for at least 500 batches) can be extracted from a historical database. Parameter fluctuation events (e.g., "ball milling time deviates from the standard by ±10%) and quality indicator exceedance events (e.g., "wear resistance exceeds the standard by >5%)" can be aligned by production batch. The percentage of times these two events occur simultaneously within the same batch is then calculated to form a "parameter-indicator" co-occurrence frequency matrix. For example, if 24 of 30 ball milling time fluctuation events were accompanied by wear resistance exceeding the standard, the co-occurrence frequency of the two is 80%.

[0067] S223: Establish quality-link mapping rules based on the association matrix and the link-parameter comparison table.

[0068] It can be understood that we can first extract the highly correlated parameters (such as sintering temperature and molding pressure) corresponding to a certain quality indicator (such as hardness) from the correlation matrix; then, reversely query the production links to which these parameters belong through the link-parameter comparison table (such as sintering temperature corresponds to the sintering link, and molding pressure corresponds to the molding link); finally, integrate to form structured rules, such as "when the hardness exceeds the standard, the associated parameters are sintering temperature (sintering link) and molding pressure (molding link), and the parameter stability of these two links needs to be checked first."

[0069] This setup clarifies the correspondence between production processes and process parameters through a link-parameter comparison table, and quantifies the correlation between parameter fluctuations and quality violations using an association matrix. The resulting quality-link mapping rules enable traceable and verifiable associations between quality indicators and production links. This reduces the subjectivity of relying solely on empirical judgment and addresses the lack of process interpretability inherent in pure data association. When quality indicators fluctuate, the rules can quickly identify the associated production links and core parameters, significantly shortening traceability time. This also provides clear guidance for targeted process optimization (such as focusing on sintering temperature control to reduce hardness fluctuations), improving the accuracy and efficiency of production quality control.

[0070] S230, obtaining a fluctuation analysis task based on the candidate production link.

[0071] For example, multiple fluctuation transmission chains can be generated based on the process connections between multiple candidate production links. The most influential fluctuation transmission chain is then determined based on the impact of each fluctuation transmission chain on the current key quality indicator, and the fluctuation analysis task is then determined based on this fluctuation transmission chain. Alternatively, candidate production links and key quality indicators can be input into a learning model, which then outputs the corresponding fluctuation analysis task, and so on, but is not limited to these. The learning model is trained using multiple sets of training data, each of which includes candidate production links, key quality indicators, and corresponding fluctuation analysis tasks.

[0072] With this setup, by determining the key quality indicators that indicate excessive quality data fluctuations from the product quality set, and then establishing quality-link mapping rules to obtain candidate production links corresponding to the key quality indicators, and finally generating fluctuation analysis tasks based on the candidate production links, accurate traceability from quality data to production links is achieved: the determination of key quality indicators focuses on core fluctuation issues, the quality-link mapping rules establish a bridge between quality and production, and the candidate production links narrow the analysis scope. The combination of the three greatly improves the targeting and efficiency of fluctuation analysis, provides a clear analysis direction and targeted solutions for quality fluctuations in the production of cemented carbide wear-resistant blocks, reduces invalid analysis costs, and helps optimize production processes and improve quality stability.

[0073] In a possible implementation, in step S230, obtaining a fluctuation analysis task based on the candidate production link includes: S231, generating multiple fluctuation transmission chains based on the process connection relationship of the candidate production links; wherein the fluctuation transmission chain is used to reflect the transmission path of the parameter fluctuation of the preceding link causing the parameter abnormality of the subsequent link through the process coupling relationship.

[0074] It can be understood that the generation of a fluctuation transmission chain based on the process connection relationship of the candidate production links is to construct a complete path of "pre-order fluctuation → mid-order transmission → post-order anomaly" by sorting out the pre-order dependencies and parameter coupling relationships between the links. For example, when the candidate production links are mixing, molding, and sintering, the process connection relationship is "mixing uniformity → molding body density → sintering grain growth". The resulting fluctuation transmission chain can be: mixing time fluctuation → uneven powder mixing → abnormal molding pressure distribution → body density deviation → local excessive grain size during sintering → hardness and wear resistance fluctuations. It can also be insufficient mixing speed → uneven dispersion of WC and Co particles → excessive cobalt content in the local molded body → aggregation of low-melting-point phase (Co phase) during sintering → decreased grain boundary bonding strength → synchronous fluctuations in impact toughness and wear resistance, and so on.

[0075] S232, calculating the fluctuation contribution of each fluctuation transmission chain; wherein the fluctuation contribution is used to reflect the cumulative impact of the co-occurrence probability of each production link in the fluctuation transmission chain.

[0076] As can be understood, the local contribution of each link in the chain is first calculated: the co-occurrence probability of parameter fluctuation in one link and parameter anomaly in the next link (for example, the co-occurrence probability of mixing anomaly and molding density deviation is 70%). The cumulative contribution is then calculated through chain multiplication (for example, the contribution of mixing → molding → sintering = 70% × 65% × 80% = 36.4%). At the same time, weight coefficients can be introduced to adjust the influence of each link (for example, the weight of the sintering link on final quality is 0.4, which is higher than the 0.2 of the mixing link). The final contribution is = cumulative co-occurrence probability × sum of weights. For example, if the cumulative co-occurrence probability of a transmission chain is 36.4% and the sum of weights is 1.2, the fluctuation contribution = 36.4% × 1.2 = 43.7%. This method can be used to compare the fluctuation contributions of multiple transmission chains horizontally (for example, chain A has 43.7%, chain B has 28.5%).

[0077] S233, obtaining a fluctuation analysis task based on the fluctuation contribution.

[0078] For example, the primary volatility transmission chains can be identified based on their volatility contribution, and the volatility analysis tasks can be determined based on these primary volatility transmission chains. Alternatively, a dynamic threshold can be set based on volatility contribution, and all volatility transmission chains with contributions exceeding the threshold will be included in the analysis scope, with analysis resources allocated based on their contribution percentage. For example, if the threshold is set at 30%, and if the contributions of chain A (43.7%), chain C (39.2%), and chain D (32%) all exceed the threshold, then all three chains will be included in the analysis.

[0079] This setup reveals the patterns of fluctuation transmission throughout the production chain through the fluctuation transmission chain. Using the fluctuation contribution metric to quantify the impact weights of each path, the resulting fluctuation analysis task focuses on core transmission paths and key links, reducing the need for indiscriminate investigations across the entire process. This enhanced targeted analysis task can quickly pinpoint the root cause of issues such as "abnormal mixing parameters leading to fluctuations throughout the entire process." Clear testing standards and priorities guide production personnel through prioritized investigations, significantly shortening the fluctuation analysis cycle and providing precise guidance for timely adjustment of process parameters and stabilizing product quality.

[0080] In a possible implementation, in step S233, obtaining a fluctuation analysis task based on the fluctuation contribution includes: S2331, sorting multiple fluctuation transmission chains based on fluctuation contribution to obtain a transmission chain sequence.

[0081] It can be understood that when sorting, the "numerical value descending + dynamic stratification" method can be used to generate the transmission chain sequence. Specifically, all fluctuation transmission chains are first sorted from high to low according to the fluctuation contribution (such as A chain 43.7%, C chain 39.2%, D chain 32%, B chain 28.5%), and then divided into levels through clustering algorithms (such as K-means): contribution ≥40% is the first layer (A chain), 30%-40% is the second layer (C chain, D chain), <30% is the third layer (B chain), and it can also be sorted directly according to the numerical value in descending order, etc., but not limited to this.

[0082] S2332, determining a core fluctuation chain based on the transfer chain sequence.

[0083] Understandably, all first-tier transfer chains (e.g., chain A) are prioritized as core chains. If the cumulative contribution of second-tier transfer chains exceeds 50% (e.g., chain C 39.2% + chain D 32% = 71.2%), the entire second tier is included in the core chain. If a third-tier transfer chain (e.g., chain B 28.5%) has a low contribution but correlates with key performance indicators (such as impact toughness, which directly impacts product safety), it is also upgraded to a core chain. At the same time, secondary chains are excluded through a "contribution difference test": if the difference in contribution between two adjacent chains is less than 5% (e.g., chain C 39.2% and chain D 32% have a 7.2% difference, they are retained; if chain D 32% and chain B 28.5% have a 3.5% difference, only chain D is retained), this avoids the dispersion of analysis resources due to an excessive number of core chains. Finally, a clear list of core fluctuation chains must be formed, such as "core chain 1: A chain (43.7%, first layer); core chain 2: C chain (39.2%, second layer)", and the corresponding quality indicator influence range must be marked (such as A chain affects hardness and wear resistance, C chain affects density and compactness).

[0084] S2333, obtain the fluctuation analysis task based on the core fluctuation chain.

[0085] For example, the degree of correlation between each candidate production link and the key quality indicator in the core fluctuation chain can be calculated, and the candidate production link with the greatest correlation can be determined as the fluctuation analysis task; the core fluctuation chain can also be decomposed into three-level nodes of "link-parameter-quality indicator" according to the process sequence, and then the key quality indicators can be matched to obtain the corresponding fluctuation analysis link, etc., but not limited to this.

[0086] With this setup, the priority hierarchy is clarified through transfer chain sorting, and the key fluctuation paths are focused on with the help of core chain screening. The final disassembled fluctuation analysis task achieves the precise implementation of "from macro chain to micro parameters". The clear division of link and parameter-level tasks allows step-by-step execution without redundant judgment. While the analysis efficiency is improved, the dynamic stratification and cross-validation mechanism ensures that the task can adapt to changes in process fluctuations, providing an iterative analysis framework for continuous and stable product quality.

[0087] In one possible implementation, in step S2333, obtaining a fluctuation analysis task based on the core fluctuation chain includes: S23331, calculate the correlation between each candidate production link and the key quality indicator based on the sequence position of each candidate production link in the core fluctuation chain.

[0088] It's understandable that the order of the core fluctuation chain is numbered according to the process flow (e.g., mixing is 1, molding is 2, and sintering is 3). A lower order indicates a process is closer to the front end and has a more fundamental impact on subsequent links. The calculation formula is: Correlation = (1 / order) × Process Fluctuation Transmission Coefficient × Key Quality Indicator Sensitivity. For example, in the core chain "mixing (1) → molding (2) → sintering (3)", the fluctuation transmission coefficient of the sintering link (sequence position 3) is 0.8 (that is, there is an 80% probability that the fluctuation in this link will be transmitted to the next link), and the sensitivity to the key quality indicator hardness is 0.7 (70% of the hardness fluctuation can be explained by this link), then the correlation degree = (1 / 3) × 0.8 × 0.7 ≈ 0.187; the molding link (sequence position 2) has a transmission coefficient of 0.6 and a sensitivity of 0.5, and the correlation degree = (1 / 2) × 0.6 × 0.5 = 0.15; the mixing link (sequence position 1) has a transmission coefficient of 0.5 and a sensitivity of 0.3, and the correlation degree = 1 × 0.5 × 0.3 = 0.15.

[0089] S23332, determine the candidate production link with the greatest correlation as the fluctuation analysis task.

[0090] This setup, through weighted correlation calculation based on sequential positions, not only reflects the transmission patterns of process fluctuations (front-end impacts back-end), but also highlights the links that most directly impact key quality indicators, significantly improving the targeting of fluctuation analysis tasks. Correlation calculation quantifies the contribution of each link to quality, reducing the misselection of links caused by subjective judgment. Focusing tasks on a single core link reduces the resource consumption of parallel analysis of multiple links, improving detection efficiency and providing precise task guidance for quickly locating and resolving production fluctuations.

[0091] S300, performing analysis based on the fluctuation analysis task and the corresponding production parameter set to obtain a fluctuation parameter set; wherein the fluctuation parameter set is used to reflect the fluctuation characteristics of the production parameters that cause fluctuations in the production of cemented carbide wear-resistant blocks.

[0092] For example, all production parameters in the fluctuation analysis task can be analyzed to obtain fluctuation data of each production parameter, and the fluctuation parameters and corresponding fluctuation characteristics can be screened out based on the fluctuation data; In a possible implementation, in step S300, analysis is performed based on the fluctuation analysis task and the corresponding production parameter set to obtain a fluctuation parameter set, including: S310, matching the fluctuation analysis task with the corresponding production parameter set to obtain a parameter analysis target; wherein the parameter analysis target is used to indicate the production parameter in the production parameter set that corresponds to the fluctuation analysis task.

[0093] It can be understood that matching the fluctuation analysis task with the corresponding production parameter set to obtain the parameter analysis target precisely targets the production parameters to be analyzed by establishing a correspondence between the task and the parameter. For example, if the fluctuation analysis task is "Sintering Process Parameter Fluctuation Detection," the corresponding production parameter set includes parameters such as sintering temperature, holding time, and furnace atmosphere pressure. Through matching, the parameter analysis target can be determined as "Sintering Temperature, Holding Time, and Furnace Atmosphere Pressure." The matching process is based on the "process-parameter" relationship defined in the quality-process mapping rules (e.g., the sintering process is strongly associated with parameters such as temperature and time).

[0094] S320, extracting the time series fluctuation data within a preset time window based on the parameter analysis target; wherein the time series fluctuation data includes the parameter collection time point and the corresponding parameter value.

[0095] It's understood that the preset time window should be set based on the production process cycle (e.g., if the sintering cycle is 4 hours, the time window should be set to 4 hours) and should also cover the period of quality fluctuations associated with the fluctuation analysis task (e.g., if a batch of products is known to experience hardness fluctuations 2 hours after sintering, the time window should include that 2-hour period). The time granularity of time series fluctuation data extraction should be consistent with the parameter collection frequency (e.g., if the temperature parameter is collected every 5 minutes, the data should include each 5-minute time point and the corresponding temperature value).

[0096] S330, performing feature extraction based on the time series fluctuation data to obtain a fluctuation parameter set; wherein the fluctuation parameter set includes time domain features and fluctuation morphology features.

[0097] It can be understood that extracting features from time-series fluctuation data to obtain a set of fluctuation parameters is a process of quantitatively analyzing the fluctuation patterns of parameters and extracting features that reflect the nature of the fluctuations. Time-domain features include the parameter's mean, standard deviation, range, fluctuation amplitude (such as the difference between the maximum and minimum temperature values), and fluctuation frequency (such as the number of times per hour that fluctuations exceed a threshold), which describe the overall fluctuation of the parameter's value. Fluctuation morphological features include the rise / fall rate (such as the rate at which the temperature rises from 1400°C to 1420°C in 10 minutes), the duration (such as the duration that the pressure remains below the standard value), and the periodicity (such as a small temperature fluctuation every 20 minutes), which characterize the dynamic pattern of parameter fluctuations.

[0098] This setup precisely targets the analysis object through parameter matching, avoiding interference from irrelevant parameters. Time series data extraction within a preset time window ensures the complete capture of fluctuations. The combination of time domain and morphological features comprehensively characterizes the nature of parameter fluctuations, enabling the fluctuation parameter set to both quantify the degree of fluctuation and describe its pattern. Precise matching of parameter analysis targets reduces ineffective parameter analysis; targeted extraction of time series data enables more timely and accurate capture of fluctuation features. Multi-dimensional feature extraction provides a rich basis for subsequent diagnosis of fluctuation causes, improving the accuracy of production fluctuation tracing and providing specific feature references for process parameter adjustments (e.g., determining temperature control accuracy based on fluctuation amplitude), facilitating stable control of production quality.

[0099] S400, generating analysis results based on the fluctuation parameter set; wherein the analysis results are used to reflect the root cause of the fluctuation of the production parameters.

[0100] It's understandable that the analysis results generated based on the fluctuation parameter set are based on correlating the characteristics of the fluctuation parameters with the production process mechanism, equipment operating status, and environmental factors, thereby tracing the root cause of production parameter fluctuations. Specifically, the fluctuation parameter set provides the parameters' temporal characteristics (such as fluctuation amplitude and frequency) and morphological characteristics (such as rise rate and duration). These characteristics provide key clues to root cause identification. For example, if the fluctuation parameter set indicates a sintering temperature fluctuation of ±15°C, exceeding the threshold three times per hour, and a rise rate of 5°C / min, a comprehensive assessment should be made based on the sintering furnace's heating system principles (such as the stability of the heater power), equipment maintenance records (such as the time of the most recent furnace calibration), and environmental factors (such as fluctuations in the workshop voltage). If the time series curves of voltage and temperature fluctuations are highly consistent (with a correlation coefficient of 0.9), unstable workshop voltage can be identified as the root cause of the temperature fluctuation. If the voltage is normal but the heater resistance exceeds the specified value, the root cause is abnormal power output caused by heater aging. The analysis results must clearly identify the type of source of fluctuation (e.g., equipment failure, incorrect parameter settings, environmental interference), specific location (e.g., sintering furnace heating module, raw material delivery pump), and influencing mechanism (e.g., aging of the heating wire causing a decrease in temperature control accuracy), providing a direct basis for subsequent corrective measures. During the analysis process, a matching rule library of "fluctuation characteristics-root cause types" can be established. For example, when parameter fluctuations show "sudden jumps + no periodicity", they are preferentially associated with "sensor failure" or "instantaneous voltage shock"; when fluctuations show "gradual offset + continuous expansion", they tend to be associated with "equipment wear" or "raw material batch differences".

[0101] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean 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 this application.

[0102] Fluctuation analysis was conducted on 30 consecutive batches of products from a production line for BAUCAST25x200x20 carbide wear-resistant blocks, covering eight core steps: mixing, forming, and sintering. Data was acquired through a combination of automatic data collection from the MES system and manual review. Manual review employed a "full parameter statistics + empirical judgment" model. For specific data, please refer to Table 1 below: Table 1 Batch number Key Quality Indicators Fluctuation analysis task Fluctuation parameters and characteristics Actual sources of fluctuations Manual inspection time (H) Manual root cause analysis Analysis time for this application (H) This application analyzes the root causes 20250403 Hardness: Fluctuation coefficient 4.2%; Wear resistance: Fluctuation coefficient 6.1% Mixing, molding, sintering Mixing: stirring time fluctuation ±12 minutes, fluctuation frequency 2 times / hour; sintering: temperature fluctuation ±8℃ (fluctuation morphology characteristics: rising rate 3℃ / min) The unstable speed of the mixing motor leads to abnormal mixing time, and the aging of the heating wire of the sintering furnace leads to temperature fluctuations. 2 Mixing problems and abnormal molding pressure parameters 0.17 Accurately locate mixing and sintering problems (accuracy 95%) 20250421 Density: Fluctuation coefficient 3.8% Molding, raw material pretreatment Molding: Pressing pressure fluctuation ±18MPa Uneven pressure distribution due to mold wear 0.5 The problem was located in the forming process, but the analysis showed that the hydraulic system pressure was unstable. 0.08 Identify mold wear as the root cause (99% accuracy) 20250511 Impact toughness: Fluctuation coefficient 7.2% Sintering and post-processing Sintering: Holding time fluctuation ±20 minutes (fluctuation morphology characteristics: duration exceeds 1 hour) The sintering furnace timer failure leads to inaccurate holding time 0.1 The problem was located in the sintering process, but the root cause was not found. 0.03 Accurately identify timer failures (95% accuracy) 20250515 Density: Fluctuation coefficient 3.5%; Friction coefficient: Fluctuation coefficient 5.8% Raw material pretreatment, mixing, and sintering Raw material pretreatment: Powder particle size fluctuation ±15μm; Mixing: Ball-to-material ratio fluctuation ±0.3 (periodic fluctuation) The particle size of the raw material supplier's batch is unstable, and the control system of the mixer's ball-to-material ratio is deviated. 1.5 Only found mixing problems, missing raw material problems 0.2 Simultaneously locate the source of raw materials and mixtures (94% accuracy)

[0103] As shown in Table 1, the method for analyzing the production fluctuations of cemented carbide wear-resistant blocks of the present application has greatly reduced the time cost of tracing the source of fluctuations compared to manual analysis in terms of analysis efficiency, especially in scenarios with multi-indicator collaborative fluctuations (such as batch 20250515). In terms of analysis accuracy, manual analysis is prone to misjudgment, partial positioning, or omission of key factors. The present application has greatly improved the accuracy through core fluctuation chain locking, parameter feature extraction, and other logic, and can accurately locate the source of fluctuations in multiple links (such as simultaneously identifying problems with the mixing motor and sintering furnace), effectively reducing the subjectivity and one-sidedness of manual analysis. The closed-loop analysis link of "quality data-production link-parameter feature-source of fluctuations" of the present application focuses on core issues through key quality indicators, narrows the scope of analysis through quality-link mapping rules, and locks specific parameters through fluctuation transmission chains and parameter feature extraction, ultimately achieving accurate tracing from quality fluctuations to the source, providing reliable support for rapid process optimization of cemented carbide wear-resistant block production.

[0104] Corresponding to the cemented carbide wear-resistant block production fluctuation analysis method described in the above embodiment, the embodiment of the present application also provides a cemented carbide wear-resistant block production fluctuation analysis system, and the various modules of the system can implement the various steps of the cemented carbide wear-resistant block production fluctuation analysis method. Figure 3 A structural block diagram of a cemented carbide wear-resistant block production fluctuation analysis system provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0105] Reference Figure 3 The cemented carbide wear block production fluctuation analysis system includes: The acquisition module is used to obtain the production information of cemented carbide wear-resistant blocks; wherein the production information of cemented carbide wear-resistant blocks includes the product quality set of cemented carbide wear-resistant blocks and the production parameter set corresponding to each production link.

[0106] The first generating module is used to generate a fluctuation analysis task based on a product quality set; wherein the fluctuation analysis task is used to indicate a production link that currently needs to be analyzed.

[0107] The analysis module is used to perform analysis based on the fluctuation analysis task and the corresponding production parameter set to obtain a fluctuation parameter set; wherein the fluctuation parameter set is used to reflect the fluctuation characteristics of the production parameters that cause fluctuations in the production of cemented carbide wear-resistant blocks.

[0108] The second generation module is used to generate analysis results based on the fluctuation parameter set; wherein the analysis results are used to reflect the root cause of the fluctuation of the production parameters.

[0109] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above modules is used as an example for illustration. In actual applications, the above functions can be distributed and completed by different modules as needed, that is, the internal structure of the system can be divided into different modules to complete all or part of the functions described above. The modules in the embodiment can be integrated into one processing unit, or each module can exist physically alone, or two or more modules can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the modules are only for the convenience of distinguishing each other and are not used to limit the scope of protection of this application. The specific working process of the modules in the above system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0111] The embodiment of the present application also provides a device for analyzing the production fluctuation of cemented carbide wear-resistant blocks, such as Figure 4 As shown, the cemented carbide wear-resistant block production fluctuation analysis device 6 of this embodiment includes: at least one processor 60 ( Figure 4 Only one is shown), at least one memory 61 ( Figure 4 Only one is shown) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the cemented carbide wear-resistant block production fluctuation analysis device 6 implements the steps of any of the above-mentioned cemented carbide wear-resistant block production fluctuation analysis method embodiments, or implements the functions of each module in the above-mentioned system embodiments.

[0112] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to implement the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the cemented carbide wear-resistant block production fluctuation analysis device 6.

[0113] The cemented carbide wear block production fluctuation analysis device 6 can be a computing device such as a desktop computer, a notebook, a palmtop computer, a cloud server, etc. The cemented carbide wear block production fluctuation analysis device can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that Figure 4 It is only an example of the cemented carbide wear-resistant block production fluctuation analysis device 6 and does not constitute a limitation of the cemented carbide wear-resistant block production fluctuation analysis device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, buses, etc.

[0114] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0115] In some embodiments, the memory 61 may be an internal storage unit of the cemented carbide wear-resistant block production fluctuation analysis device 6, such as a hard disk or memory of the cemented carbide wear-resistant block production fluctuation analysis device 6. In other embodiments, the memory 61 may also be an external storage device of the cemented carbide wear-resistant block production fluctuation analysis device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the cemented carbide wear-resistant block production fluctuation analysis device 6. Furthermore, the memory 61 may also include both an internal storage unit and an external storage device of the cemented carbide wear-resistant block production fluctuation analysis device 6. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0116] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0117] An embodiment of the present application provides a computer program product. When the computer program product is run on a cemented carbide wear-resistant block production fluctuation analysis device, the cemented carbide wear-resistant block production fluctuation analysis device can implement the steps of any of the above-mentioned method embodiments.

[0118] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the cemented carbide wear-resistant block production fluctuation analysis equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0119] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] In the embodiments provided in the present application, it should be understood that the disclosed cemented carbide wear-resistant block production fluctuation analysis equipment and system can be implemented in other ways. For example, the embodiment of the cemented carbide wear-resistant block production fluctuation analysis system described above is only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0122] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0123] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for analyzing production fluctuations of cemented carbide wear-resistant blocks, characterized in that: include: Acquire production information of cemented carbide wear-resistant blocks; wherein the production information of cemented carbide wear-resistant blocks includes a product quality set of cemented carbide wear-resistant blocks and a production parameter set corresponding to each production link; Generate a fluctuation analysis task based on the product quality set; wherein the fluctuation analysis task is used to indicate the production link that currently needs to be analyzed; Performing analysis based on the fluctuation analysis task and the corresponding production parameter set to obtain a fluctuation parameter set; wherein the fluctuation parameter set is used to reflect the fluctuation characteristics of the production parameters that cause fluctuations in the production of cemented carbide wear-resistant blocks; An analysis result is generated based on the fluctuation parameter set; wherein the analysis result is used to reflect the root cause of the fluctuation of the production parameters.

2. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 1, wherein: Generating a fluctuation analysis task based on the product quality set includes: Determine a key quality indicator based on the product quality set; wherein the key quality indicator is used to indicate the main quality indicator of the quality data fluctuation exceeding the standard; Establishing a quality-link mapping rule, and obtaining a candidate production link corresponding to the key quality indicator based on the quality-link mapping rule; wherein the candidate production link is used to reflect a collection of multiple production links; A fluctuation analysis task is obtained based on the candidate production link.

3. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 2, wherein: The determining of key quality indicators based on the product quality set includes: The product quality set is divided into a basic index layer and a performance index layer; wherein the basic index layer is used to reflect the inherent attribute data of the cemented carbide wear-resistant block, and the performance index layer is used to reflect the dynamic attribute data of the cemented carbide wear-resistant block; Calculating the standard deviation of the basic indicator layer and the performance indicator layer respectively to obtain a first fluctuation coefficient and a second fluctuation coefficient; wherein the first fluctuation coefficient is used to reflect the degree of data fluctuation corresponding to the basic indicator layer, and the second fluctuation coefficient is used to reflect the degree of data fluctuation corresponding to the performance indicator layer; A key quality indicator is determined based on the first coefficient of fluctuation and the second coefficient of fluctuation.

4. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 3, wherein: The determining of a key quality indicator based on the first fluctuation coefficient and the second fluctuation coefficient includes: Comparing the first fluctuation coefficient with a first threshold, and comparing the second fluctuation coefficient with a second threshold, to obtain a comparison result; wherein the first threshold is a critical value of the fluctuation of the basic indicator layer data, and the second threshold is a critical value of the fluctuation of the performance indicator layer data; Key quality indicators are determined based on the comparison results.

5. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 4, wherein: Determining key quality indicators based on the comparison results includes: If the comparison result is that the first fluctuation coefficient is greater than the first threshold, and the second fluctuation coefficient is greater than the second threshold, generating associated quality indicators of the basic indicator layer and the performance indicator layer, and determining the associated quality indicators as key quality indicators; If the comparison result is that only the first fluctuation coefficient is greater than the first threshold, determining the quality indicator corresponding to the basic indicator layer as a key quality indicator; If the comparison result is that only the second fluctuation coefficient is greater than the second threshold, the quality indicator corresponding to the performance indicator layer is determined as a key quality indicator.

6. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 2, wherein: The establishment of quality-link mapping rules includes: Establishing a link-parameter comparison table; wherein the link-parameter comparison table is used to reflect the production process corresponding to each production process; Generate a correlation matrix based on historical production fluctuation data; wherein the correlation matrix is ​​used to reflect the co-occurrence frequency of parameter fluctuations and quality index exceeding the standard; A quality-link mapping rule is established based on the association matrix and the link-parameter comparison table.

7. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 2, wherein: The fluctuation analysis task obtained based on the candidate production link includes: Generate multiple fluctuation transmission chains based on the process connection relationship of the candidate production links; wherein the fluctuation transmission chain is used to reflect the transmission path of the parameter fluctuation of the preceding link to the parameter abnormality of the subsequent link through the process coupling relationship; Calculating the fluctuation contribution of each of the fluctuation transmission chains; wherein the fluctuation contribution is used to reflect the cumulative impact of the co-occurrence probability of each production link in the fluctuation transmission chain; A fluctuation analysis task is obtained based on the fluctuation contribution.

8. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 7, wherein: The obtaining of the fluctuation analysis task based on the fluctuation contribution includes: sorting the plurality of fluctuation transmission chains based on the fluctuation contribution to obtain a transmission chain sequence; Determine the core fluctuation chain based on the transmission chain sequence; A fluctuation analysis task is obtained based on the core fluctuation chain.

9. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 8, wherein: The fluctuation analysis task obtained based on the core fluctuation chain includes: Calculating the correlation between each candidate production link and the key quality indicator based on the order position of each candidate production link in the core fluctuation chain; The candidate production link with the greatest correlation is determined as the fluctuation analysis task.

10. The method for analyzing production fluctuations of cemented carbide wear-resistant blocks according to claim 1, wherein: The analysis based on the fluctuation analysis task and the corresponding production parameter set is performed to obtain a fluctuation parameter set, including: Matching the fluctuation analysis task with the corresponding production parameter set to obtain a parameter analysis target; wherein the parameter analysis target is used to indicate the production parameter in the production parameter set corresponding to the fluctuation analysis task; Extracting time series fluctuation data within a preset time window based on the parameter analysis target; wherein the time series fluctuation data includes parameter collection time points and corresponding parameter values; Feature extraction is performed based on the time series fluctuation data to obtain a fluctuation parameter set; wherein the fluctuation parameter set includes time domain features and fluctuation morphology features.

Images