Detection method and device of process equipment, storage medium and electronic equipment

Abstract

The invention discloses a process equipment detection method and device, a storage medium and electronic equipment, the method is applied to the field of equipment detection, and the method comprises the following steps: extracting multi-dimensional feature information corresponding to different working condition information from equipment operation data of target equipment, and dividing the multi-dimensional feature information into a plurality of data subsets; clustering the plurality of data subsets according to the multi-dimensional feature information, and determining a target curve in a multi-dimensional feature space according to a plurality of cluster centers obtained by clustering; determining a target equipment type of the target equipment, and determining at least one reference curve corresponding to the target equipment type in the reference curve set; and detecting the creep migration trend of the target equipment according to the curve information of the at least one reference curve and the curve information of the target curve to obtain a detection result. According to the method and the device, the problem that the detection result is inaccurate due to the fact that analysis is carried out only through single equipment characteristics when the creep migration trend of the process equipment is detected by a traditional creep migration detection algorithm in the related technology is solved.

Description

Technical Field

[0001] This application relates to the field of equipment testing, and more specifically, to a method, apparatus, storage medium, and electronic device for testing process equipment. Background Technology

[0002] During long-term operation, equipment is subject to slow and irreversible plastic deformation of its structural materials due to factors such as temperature fluctuations, continuous loads, and media corrosion. This phenomenon, known as "creep," causes the equipment's operating characteristics (such as key parameters like current, pressure, and power) to gradually deviate from their initial state, forming "creep migration." Initially, the migration rate is slow and easily overlooked; however, once the migration reaches a critical threshold, it enters a nonlinear accelerated degradation stage, directly affecting equipment energy efficiency and even causing serious malfunctions such as blade breakage and bearing seizure, threatening production safety.

[0003] Traditional physical testing methods, such as ultrasonic thickness measurement and stress-strain sensor monitoring, require shutdown or the installation of specialized hardware. They cannot achieve real-time, continuous creep tracking during equipment operation and can only obtain local structural parameters, making it difficult to reflect the migration patterns of the overall operating characteristics of the equipment.

[0004] Especially for process equipment such as power plant fans, their operating data presents a typical "linear distribution" in the multidimensional parameter space (corresponding to stable operating states under different working conditions). Traditional methods do not utilize this data characteristic and only analyze the fluctuation of a single parameter, which can easily lead to misjudgment of creep trends, resulting in increased equipment operation and maintenance costs or increased failure risks.

[0005] There is currently no effective solution to the problem that traditional creep migration detection algorithms in related technologies analyze the creep migration trend of equipment by relying on only a single equipment feature, resulting in inaccurate detection results. Summary of the Invention

[0006] The main objective of this application is to provide a method, apparatus, storage medium, and electronic device for detecting process equipment, in order to solve the problem that traditional creep migration detection algorithms in the related art only analyze a single equipment feature when detecting the creep migration trend of process equipment, resulting in inaccurate detection results.

[0007] To achieve the above objectives, according to one aspect of this application, a method for detecting process equipment is provided. The method includes: extracting multidimensional feature information corresponding to different operating conditions from the equipment operation data of a target equipment, and dividing the equipment operation data into multiple data subsets based on the multidimensional feature information, wherein the target equipment is a process equipment whose creeping migration trend is to be detected; clustering the multiple data subsets based on the multidimensional feature information, and determining a target curve in a multidimensional feature space based on the multiple cluster centers obtained from the clustering, wherein the multidimensional feature space is constructed based on the multidimensional feature information; determining the target equipment type of the target equipment, and determining at least one reference curve corresponding to the target equipment type in a set of reference curves; detecting the creeping migration trend of the target equipment based on the curve information of the at least one reference curve and the curve information of the target curve, and obtaining a detection result.

[0008] Furthermore, before determining at least one reference curve corresponding to the target equipment type in the reference curve set, the above method also includes: collecting historical operating data of the equipment over multiple time periods; extracting multi-dimensional feature information corresponding to different operating conditions from the historical operating data of the equipment to obtain historical datasets for multiple time periods, wherein the historical operating data of the equipment includes at least historical operating data of the target equipment type; dividing the historical datasets for multiple time periods according to the values ​​of the operating conditions in the historical datasets to obtain multiple historical data subsets corresponding to each time period; clustering the multiple historical data subsets corresponding to each time period according to the multi-dimensional feature information to obtain multiple cluster centers corresponding to each time period; mapping the multiple cluster centers corresponding to each time period to a multi-dimensional feature space, and constructing a reference curve corresponding to each time period in the multi-dimensional feature space based on the multiple cluster centers corresponding to each time period to obtain a reference curve set.

[0009] Further, determining at least one reference curve corresponding to the target equipment type in the reference curve set includes: determining the reference curve corresponding to the target equipment type in the reference curve set to obtain a first curve set; determining multiple first cluster centers contained in each first curve in the first curve set, as well as the operating condition information and multi-dimensional feature information of each first cluster center; calculating a first distance based on the same operating condition information in each first curve and the target curve, based on the multi-dimensional feature information corresponding to the operating condition information in the first curve and the multi-dimensional feature information corresponding to the operating condition information in the target curve; and determining at least one reference curve in the first curve set based on the first curve whose first distance is greater than a preset distance.

[0010] Further, the creep migration trend of the target device is detected based on the curve information of at least one reference curve and the curve information of the target curve to obtain the detection result, including: for each of the at least one reference curve, calculating the second distance between the reference curve and the target curve based on the curve information of the reference curve and the target curve to obtain the second distance between each reference curve and the target curve, wherein the second distance is used to quantify the creep migration degree of the target device; connecting the second distances between each reference curve and the target curve according to the time sequence to obtain the creep migration degree curve; calculating the slope of each data point in the creep migration degree curve to obtain multiple slopes; determining the creep migration trend of the target device based on the numerical relationship between the multiple slopes and the preset slope to obtain the detection result.

[0011] Further, the second distance between the reference curve and the target curve is calculated based on the curve information of the reference curve and the curve information of the target curve. This includes: for each target cluster center in the target curve, calculating the third distance between each reference cluster center and the target cluster center based on the multidimensional feature space of the target and each reference multidimensional feature information, and summing the third distances between each reference cluster center and the target cluster center to obtain the sum of the third distances corresponding to each target cluster center. Here, the target multidimensional feature information is the multidimensional feature information corresponding to the target cluster center, and each reference multidimensional feature information is the multidimensional feature information corresponding to each reference cluster center. The sum of the third distances corresponding to each target cluster center in the target curve is then summed to obtain the second distance between the reference curve and the target curve.

[0012] Furthermore, multi-dimensional feature information corresponding to different operating conditions is extracted from the equipment operation data of the target equipment, and the equipment operation data is divided into multiple data subsets based on the multi-dimensional feature information. This includes: determining key operating condition information affecting the target equipment, and determining operating condition elements based on the key operating condition information; determining equipment operation features that are dependent on the operating condition elements during the operation of the target equipment, and obtaining multiple feature elements; determining the values ​​of the operating condition elements and the values ​​of multiple feature elements based on the equipment operation data, and obtaining the equipment operation data set, wherein the ratio between the number of values ​​of the operating condition elements in the equipment operation data set and the number of values ​​included in the normal value range of the operating condition elements is greater than a preset ratio; determining multiple operating condition value intervals based on the normal value range of the operating condition elements, and dividing the equipment operation data set into multiple data subsets based on the values ​​of the operating condition elements and the multiple operating condition value intervals in the equipment operation data set.

[0013] Furthermore, multiple data subsets are clustered based on multidimensional feature information, and the target curve is determined in the multidimensional feature space based on the multiple cluster centers obtained from the clustering. This includes: using the K-means algorithm to cluster multiple data subsets to obtain the cluster corresponding to each data subset; calculating the cluster center of the cluster for each data subset to obtain the cluster center corresponding to each data subset; mapping the cluster center corresponding to each data subset to the multidimensional feature space; and connecting the cluster centers corresponding to each data subset in the multidimensional feature space based on the value of the working condition element corresponding to each data subset to obtain the target curve.

[0014] To achieve the above objectives, according to another aspect of this application, a detection apparatus for process equipment is provided. The apparatus includes: a first extraction unit, configured to extract multidimensional feature information corresponding to different operating conditions from the equipment operation data of a target equipment, and divide the equipment operation data into multiple data subsets based on the multidimensional feature information, wherein the target equipment is a process equipment whose creeping migration trend is to be detected; a first clustering unit, configured to cluster the multiple data subsets according to the multidimensional feature information, and determine a target curve in a multidimensional feature space based on the multiple cluster centers obtained from the clustering, wherein the multidimensional feature space is constructed based on the multidimensional feature information; a determination unit, configured to determine the target equipment type of the target equipment, and determine at least one reference curve corresponding to the target equipment type in a set of reference curves; and a detection unit, configured to detect the creeping migration trend of the target equipment based on the curve information of at least one reference curve and the curve information of the target curve, and obtain a detection result.

[0015] Furthermore, the aforementioned apparatus further includes: a second extraction unit, configured to collect historical operating data of the equipment over multiple time periods before determining at least one reference curve corresponding to the target equipment type in the reference curve set, extract multidimensional feature information corresponding to different operating conditions from the historical operating data of the equipment, and obtain historical datasets for multiple time periods, wherein the historical operating data of the equipment includes at least historical operating data of the target equipment type; a partitioning unit, configured to partition the historical datasets for multiple time periods according to the values ​​of the operating conditions in the historical datasets, and obtain multiple historical data subsets corresponding to each time period; a second clustering unit, configured to cluster the multiple historical data subsets corresponding to each time period according to the multidimensional feature information, and obtain multiple cluster centers corresponding to each time period; and a construction unit, configured to map the multiple cluster centers corresponding to each time period to a multidimensional feature space, and construct a reference curve corresponding to each time period in the multidimensional feature space according to the multiple cluster centers corresponding to each time period, and obtain a reference curve set.

[0016] Further, the determining unit includes: a first determining subunit, used to determine the reference curve corresponding to the target equipment type in the reference curve set, to obtain a first curve set; a second determining subunit, used to determine the multiple first cluster centers contained in each first curve in the first curve set, as well as the operating condition information and multi-dimensional feature information of each first cluster center; a first calculating subunit, used to calculate a first distance based on the same operating condition information in each first curve and the target curve, based on the multi-dimensional feature information corresponding to the operating condition information in the first curve and the multi-dimensional feature information corresponding to the operating condition information in the target curve; and a third determining subunit, used to determine at least one reference curve in the first curve set based on the first curve whose first distance is greater than a preset distance.

[0017] Further, the detection unit includes: a second calculation subunit, used to calculate a second distance between the reference curve and the target curve for each of the at least one reference curve, based on the curve information of the reference curve and the curve information of the target curve, to obtain the second distance between each reference curve and the target curve, wherein the second distance is used to quantify the creep migration degree of the target device; a first connection subunit, used to connect the second distances between each reference curve and the target curve according to the time sequence, to obtain a creep migration degree curve; a third calculation subunit, used to calculate the slope of each data point in the creep migration degree curve, to obtain multiple slopes; and a fourth determination subunit, used to determine the creep migration trend of the target device based on the numerical relationship between the multiple slopes and a preset slope, to obtain the detection result.

[0018] Further, the second calculation subunit includes: a first calculation module, used to calculate, for each target cluster center in the target curve, a third distance between each reference cluster center and the target cluster center based on the target multidimensional feature information and each reference multidimensional feature information in the multidimensional feature space, and summing the third distances between each reference cluster center and the target cluster center to obtain the sum of the third distances corresponding to each target cluster center, wherein the target multidimensional feature information is the multidimensional feature information corresponding to the target cluster center, and each reference multidimensional feature information is the multidimensional feature information corresponding to each reference cluster center; and a second calculation module, used to sum the sum of the third distances corresponding to each target cluster center in the target curve to obtain the second distance between the reference curve and the target curve.

[0019] Further, the first extraction unit includes: a fifth determining subunit, used to determine key operating condition information affecting the target equipment, and to determine operating condition elements based on the key operating condition information; a sixth determining subunit, used to determine equipment operating characteristics that are dependent on the operating condition elements during the operation of the target equipment, and to obtain multiple feature elements; a seventh determining subunit, used to determine the values ​​of the operating condition elements and the values ​​of multiple feature elements based on the equipment operating data, and to obtain an equipment operating data set, wherein the ratio between the number of values ​​of the operating condition elements in the equipment operating data set and the number of values ​​included in the normal value range of the operating condition elements is greater than a preset ratio; and an eighth determining subunit, used to determine multiple operating condition value intervals based on the normal value range of the operating condition elements, and to divide the equipment operating data set into multiple data subsets based on the values ​​of the operating condition elements and the multiple operating condition value intervals in the equipment operating data set.

[0020] Furthermore, the first clustering unit includes: a clustering subunit, used to cluster multiple data subsets using the K-means algorithm to obtain clusters corresponding to each data subset; a fourth calculation subunit, used to calculate the cluster center of each cluster for each data subset to obtain the cluster center corresponding to each data subset; a mapping subunit, used to map the cluster center corresponding to each data subset to a multi-dimensional feature space; and a second connection subunit, used to connect the cluster centers corresponding to each data subset in the multi-dimensional feature space according to the value of the working condition element corresponding to each data subset to obtain the target curve.

[0021] To achieve the above objectives, according to one aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the detection method for any of the above-described process devices, and when executed by a processor, implements the steps of the detection method for process devices in various embodiments of this application.

[0022] To achieve the above objectives, according to one aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including stored computer instructions, wherein the detection method of any of the above-described process apparatus is implemented when the computer instructions are executed by a processor.

[0023] To achieve the above objectives, according to one aspect of this application, an electronic device is provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the detection method of any of the above-described process devices.

[0024] This application employs the following steps: extracting multidimensional feature information corresponding to different operating conditions from the equipment operation data of the target equipment, and dividing the equipment operation data into multiple data subsets based on the multidimensional feature information, wherein the target equipment is the process equipment whose creep migration trend is to be detected; clustering the multiple data subsets based on the multidimensional feature information, and determining the target curve in the multidimensional feature space based on the multiple cluster centers obtained from the clustering, wherein the multidimensional feature space is constructed based on the multidimensional feature information; determining the target equipment type of the target equipment, and determining at least one reference curve corresponding to the target equipment type in the set of reference curves; detecting the creep migration trend of the target equipment based on the curve information of at least one reference curve and the curve information of the target curve, and obtaining the detection result. This solves the problem in related technologies where traditional creep migration detection algorithms analyze only a single equipment feature when detecting the creep migration trend of process equipment, resulting in inaccurate detection results.

[0025] By extracting multidimensional feature information containing different operating conditions from the equipment operation data of the target equipment, the complex performance of the equipment under various operating states can be systematically analyzed, achieving the technical effect of constructing a multidimensional data model that comprehensively reflects the operating characteristics of the equipment. Simultaneously, by dividing the equipment operation data into multiple data subsets based on the multidimensional feature information and then performing cluster analysis on these subsets, a deeper understanding of the subtle changes in the operating characteristics of the equipment under specific operating conditions can be achieved. This enables the determination of a target curve that accurately represents the current state of the equipment in a multidimensional feature space, effectively overcoming the limitations of traditional algorithms that rely on only a single feature for creep migration detection. This significantly improves the accuracy and reliability of the detection results, further refining the granularity of equipment state assessment and enhancing the accuracy of creep migration detection.

[0026] More importantly, by determining the specific type of the target equipment and selecting at least one reference curve that matches that type from the set of reference curves, a comparison standard based on equipment type and historical data can be provided for equipment status analysis, making the detection results more reliable and accurate. This achieves quantitative detection of the creep migration trend of the target equipment and further enhances the generalization ability of the detection algorithm and the technical effect of predicting the health status of the equipment. Attached Figure Description

[0027] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0028] Figure 1 This is a flowchart of a detection method for a process device according to Embodiment 1 of this application;

[0029] Figure 2This is a schematic diagram showing the distribution of multiple feature elements under different historical time periods and different working conditions, according to Embodiment 1 of this application.

[0030] Figure 3 This is a schematic diagram of the optional calculation process between the reference curve and the target curve according to Embodiment 1 of this application;

[0031] Figure 4 This is a schematic diagram of an optional multidimensional feature space provided according to Embodiment 1 of this application;

[0032] Figure 5 This is a schematic diagram of multiple data subsets after being divided according to the optional device operation data (or historical device operation data) provided in Embodiment 1 of this application;

[0033] Figure 6 This is a schematic diagram of the target curve formed by the cluster centers after clustering multiple optional data subsets according to Embodiment 1 of this application;

[0034] Figure 7 This is a schematic diagram of the detection device for the process equipment provided according to Embodiment 2 of this application;

[0035] Figure 8 This is a schematic diagram of a detection electronic device for a process device provided according to Embodiment 5 of this application. Detailed Implementation

[0036] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0037] It should be noted that the user information (including but not limited to user device information, user personal information, collected data, used data, generated data, processed data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, collected information, used information, generated information, processed information, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, it needs to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information only after receiving consent from the aforementioned user or organization.

[0038] It should be noted that this application provides users with a corresponding entry point for choosing to agree to or reject the automated decision-making results; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0039] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0040] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0041] Example 1

[0042] The present invention will now be described in conjunction with preferred implementation steps. Figure 1 This is a flowchart of a detection method for a process device according to Embodiment 1 of this application, as shown below. Figure 1 As shown, the method includes the following steps:

[0043] Step S101: Extract multi-dimensional feature information corresponding to different operating conditions from the equipment operation data of the target equipment, and divide the equipment operation data into multiple data subsets based on the multi-dimensional feature information. The target equipment is the process equipment whose creep migration trend is to be detected.

[0044] The executing entity in this embodiment can be a detection system for process equipment. The core function of this system is to accurately quantify the degree of creep migration experienced by process equipment during long-term operation and identify key nodes of creep acceleration. By collecting real-time operating data of the equipment and mapping it to a multi-dimensional operating condition space, the system uses advanced data analysis algorithms, including cluster analysis and operating characteristic curve construction, to achieve continuous monitoring of the equipment's health status.

[0045] In this first embodiment, multi-dimensional feature information corresponding to different operating conditions is first extracted from the equipment operation data of the target equipment. This feature information covers key physical quantities that can comprehensively describe the operating state of the equipment, including but not limited to operating condition elements (i.e., the different operating condition information mentioned above) and feature elements (i.e., the multi-dimensional feature information mentioned above). Subsequently, based on the obtained multi-dimensional feature information, the equipment operation data is subdivided into multiple data subsets. Each subset represents the operating record of the equipment within a specific operating condition range. In this way, it is ensured that the data segmentation follows the natural range of the operating condition elements and maintains the continuity of feature element changes. This step provides a clearly structured data foundation for subsequent cluster analysis and the construction of operating characteristic curves, enabling the algorithm to accurately identify subtle changes in the equipment over time, thereby effectively detecting creep migration trends, especially those gradually intensifying nonlinear migration characteristics.

[0046] Step S102: Cluster multiple data subsets based on multidimensional feature information, and determine the target curve in the multidimensional feature space based on the multiple cluster centers obtained from the clustering. The multidimensional feature space is constructed based on multidimensional feature information.

[0047] In this first embodiment, cluster analysis is performed on each data subset based on the constructed multidimensional feature space. The K-means clustering algorithm is used to determine the cluster centers of each data subset. These cluster centers are then connected in the multidimensional feature space to obtain the target curve. The key to this step is that the clustering is based on the multidimensional feature information of the equipment under different operating conditions, ensuring that the clustering results reflect the typical patterns of the equipment's operating status. The determination of the target curve provides a foundation for subsequent quantitative calculations of the equipment's creep migration degree. By comparing curves from different historical periods, the trend and acceleration points of creep migration can be accurately identified, thereby assessing the equipment's health status and predicting maintenance needs.

[0048] Step S103: Determine the target device type of the target device, and determine at least one reference curve corresponding to the target device type in the reference curve set.

[0049] In this first embodiment, the specific type of the equipment to be analyzed, i.e., the target equipment, is clearly defined. The target equipment type can be determined based on the equipment's design specifications, functional characteristics, and industry standards. Next, based on the target equipment type, at least one reference curve matching the target equipment type is selected from the reference curve set. The reference curve set contains a database of characteristic curves of various types of process equipment under different operating conditions, covering typical creep migration behaviors of different equipment types, representing the creep migration process of the process equipment throughout its complete service life.

[0050] By identifying at least one reference curve, a benchmark is provided for quantifying the degree of creep migration in the target equipment. By comparing the operating characteristic curve of the target equipment with the reference curve, the deviation of the current state of the target equipment from the expected or standard performance can be objectively assessed, thereby identifying whether creep migration has occurred, as well as the degree and trend of migration.

[0051] Step S104: Detect the creeping migration trend of the target device based on the curve information of at least one reference curve and the curve information of the target curve, and obtain the detection result.

[0052] In this first embodiment, the operating characteristic curve of the target device, i.e., the target curve, is compared and analyzed with at least one reference curve from the set of reference curves. This process first quantifies the difference between the target curve and each reference curve by calculating the distance between them in a multidimensional feature space, resulting in a series of distance indices. Subsequently, these distance indices are statistically analyzed, focusing on their trends over time. When the distance indices show a continuous and significant deviation between the target curve and the reference curve, it indicates that the operating characteristics of the target device are undergoing creep migration. In particular, if the deviation exhibits a non-linear accelerating characteristic, i.e., the growth rate of the distance indices suddenly increases, this signifies that the device may have entered a stage of accelerated degradation.

[0053] Ultimately, based on the above analysis, detection results regarding the creep migration trend of the target equipment can be obtained. These results not only reveal the evolution direction of the equipment's health status but also provide quantitative information on the degree and rate of equipment performance degradation, offering crucial references for developing equipment maintenance strategies and predicting remaining service life.

[0054] In summary, the process equipment detection method provided in Embodiment 1 of this application extracts multi-dimensional feature information corresponding to different operating conditions from the equipment operation data of the target equipment, and divides the equipment operation data into multiple data subsets based on the multi-dimensional feature information. The target equipment is the process equipment whose creep migration trend is to be detected. The multiple data subsets are clustered according to the multi-dimensional feature information, and the target curve is determined in the multi-dimensional feature space based on the multiple cluster centers obtained by clustering. The multi-dimensional feature space is constructed based on the multi-dimensional feature information. The target equipment type of the target equipment is determined, and at least one reference curve corresponding to the target equipment type is determined in the reference curve set. The creep migration trend of the target equipment is detected based on the curve information of at least one reference curve and the curve information of the target curve to obtain the detection result. This method solves the problem in the related technology that the traditional creep migration detection algorithm only analyzes a single equipment feature when detecting the creep migration trend of process equipment, resulting in inaccurate detection results.

[0055] By extracting multidimensional feature information containing different operating conditions from the equipment operation data of the target equipment, the complex performance of the equipment under various operating states can be systematically analyzed, achieving the technical effect of constructing a multidimensional data model that comprehensively reflects the operating characteristics of the equipment. Simultaneously, by dividing the equipment operation data into multiple data subsets based on the multidimensional feature information and then performing cluster analysis on these subsets, a deeper understanding of the subtle changes in the operating characteristics of the equipment under specific operating conditions can be achieved. This enables the determination of a target curve that accurately represents the current state of the equipment in a multidimensional feature space, effectively overcoming the limitations of traditional algorithms that rely on only a single feature for creep migration detection. This significantly improves the accuracy and reliability of the detection results, further refining the granularity of equipment state assessment and enhancing the accuracy of creep migration detection.

[0056] More importantly, by determining the specific type of the target equipment and selecting at least one reference curve that matches that type from the set of reference curves, a comparison standard based on equipment type and historical data can be provided for equipment status analysis, making the detection results more reliable and accurate. This achieves quantitative detection of the creep migration trend of the target equipment and further enhances the generalization ability of the detection algorithm and the technical effect of predicting the health status of the equipment.

[0057] Optionally, in the process equipment detection method provided in Embodiment 1 of this application, before determining at least one reference curve corresponding to the target equipment type in the reference curve set, the method further includes: collecting historical operating data of the equipment in multiple time periods, extracting multi-dimensional feature information corresponding to different operating conditions from the historical operating data of the equipment to obtain historical datasets for multiple time periods, wherein the historical operating data of the equipment includes at least historical operating data of the target equipment type; dividing the historical datasets for multiple time periods according to the values ​​of the operating conditions in the historical datasets to obtain multiple historical data subsets corresponding to each time period; clustering the multiple historical data subsets corresponding to each time period according to the multi-dimensional feature information to obtain multiple cluster centers corresponding to each time period; mapping the multiple cluster centers corresponding to each time period to a multi-dimensional feature space, and constructing a reference curve corresponding to each time period in the multi-dimensional feature space based on the multiple cluster centers corresponding to each time period to obtain a reference curve set.

[0058] In this first embodiment, the historical database interface is automatically invoked to import the equipment's operation logs from multiple historical stages in batches, covering all operating conditions throughout the equipment's lifecycle. Next, data mining techniques are used to efficiently extract multi-dimensional characteristic parameters closely related to different operating conditions from the massive historical data. These parameters include key elements reflecting the equipment's operating status, such as temperature, pressure, and current. It is important to note that for the same equipment type, different operating condition information and corresponding multi-dimensional feature information can be collected under specific operating conditions. For example, for a power plant induced draft fan, the unit load is defined as the operating condition element, and the induced draft fan blade position feedback, induced draft fan current, and induced draft fan inlet / outlet pressure difference are defined as multi-dimensional features. The induced draft fan blade position feedback, induced draft fan current, and induced draft fan inlet / outlet pressure difference are collected at different times under different unit loads to obtain historical datasets for multiple time periods.

[0059] Subsequently, based on the diverse characteristics of equipment operation and the dynamic range of operating parameters, the historical dataset was subdivided into multiple subsets to ensure that each subset focuses on the equipment's performance under specific operating conditions. This subdivision process takes into account the uniformity of data distribution and the natural boundaries of operating condition elements.

[0060] For example, Figure 2 This is a schematic diagram illustrating the distribution of multiple feature elements under different historical time periods and operating conditions, as provided in Embodiment 1 of this application. For example... Figure 2 As shown, assuming the process equipment is a power plant fan, the operating condition element... It could be the fan speed, with the X-axis representing the position feedback of the moving blades of the suction fan A (i.e., the characteristic element operating condition element). The Y-axis represents the current A of the suction fan (characteristic element). The Z-axis represents the pressure difference A (characteristic element). ). Figure 6 The data points of different colors represent the equipment operating status corresponding to four historical time periods, thus enabling direct observation of the equipment's creep migration trend and verifying the applicability of this embodiment to the creep quantitative analysis of actual equipment.

[0061] Next, the K-means algorithm (or other suitable data clustering algorithm) is used to perform clustering processing on each historical data subset, find and mark the center point of each historical data subset, i.e., the cluster center, as a representative sample of the equipment operating characteristics under this working condition.

[0062] Finally, all cluster centers obtained within each time period are projected onto the constructed multidimensional feature space coordinate system. Using curve fitting techniques, such as the least squares method, the cluster centers are connected to form a series of reference curves depicting the equipment's operating characteristics within a specific time period. This set of curves constitutes the reference curves for equipment health status assessment. Each reference curve not only reflects the normal operating trajectory of the equipment within a certain operating range but also implicitly suggests potential performance degradation trends over time.

[0063] Through the above steps, a set of reference curves was effectively established, providing a standardized benchmark for subsequent equipment condition monitoring and performance evaluation, and enabling systematic and refined monitoring of equipment creep migration trends. Simultaneously, the construction of the reference curve set also provides a unified data model for condition assessment of similar equipment, reducing the workload of repetitive analysis for different types of equipment and improving overall operation and maintenance efficiency.

[0064] Optionally, in the process equipment detection method provided in Embodiment 1 of this application, determining at least one reference curve corresponding to the target equipment type in the reference curve set includes: determining the reference curve corresponding to the target equipment type in the reference curve set to obtain a first curve set; determining multiple first cluster centers contained in each first curve in the first curve set, as well as the operating condition information and multidimensional feature information of each first cluster center; calculating a first distance based on the same operating condition information in each first curve and the target curve, based on the multidimensional feature information corresponding to the operating condition information in the first curve and the multidimensional feature information corresponding to the operating condition information in the target curve; and determining at least one reference curve in the first curve set based on the first curve whose first distance is greater than a preset distance.

[0065] In this first embodiment, in order to accurately quantify the creep migration degree of the target device and identify the key nodes of creep acceleration, firstly, a reference curve matching the type of the target device is located in the reference curve set to form a first curve set. Each curve represents the actual operating status of the same type of device in different historical periods, providing detailed benchmark data for subsequent comparative analysis.

[0066] Then, all cluster centers contained in each first curve in the first curve set are extracted, along with the operating condition information and multidimensional feature information associated with each cluster center. The cluster centers are determined by the clustering results of historical data and represent the average operating characteristics of the equipment under specific operating conditions. The combination of operating condition information and multidimensional feature information constitutes a multidimensional description of the equipment status, ensuring the comprehensiveness and accuracy of the comparative analysis.

[0067] Secondly, based on the operating condition information corresponding to the target curve, a first curve corresponding to the same operating condition information is determined from the first curve set. The distance between the multidimensional feature information of the two sets of curves under the same operating condition is calculated, i.e., the first distance. This calculation process ensures the rationality and effectiveness of the comparison by matching operating condition information. The quantitative result of the first distance reveals the degree of difference between the current operating condition of the target equipment and the historical baseline state.

[0068] Finally, based on the calculated first distance, a preset distance threshold is compared, and reference curves whose first distance exceeds the preset threshold are selected from the first set of curves. These curves are used as at least one reference curve for subsequent analysis. This selection step aims to identify historical stages that differ significantly from the current state of the target device. By comparing these reference curves, changes in the device's creep migration trend can be detected more sensitively, especially during acceleration phases.

[0069] Through the above steps, the degree of creep migration of the target equipment is accurately quantified, which aims to enhance the accuracy and reliability of the detection method, ensure that the analysis results can accurately reflect the health status of the equipment, provide strong data support for equipment operation and maintenance decisions, realize continuous monitoring and early warning of equipment status, further optimize the maintenance strategy of process equipment and extend its service life.

[0070] Optionally, in the process equipment detection method provided in Embodiment 1 of this application, detecting the creep migration trend of the target equipment based on the curve information of at least one reference curve and the curve information of the target curve to obtain the detection result includes: for each of the at least one reference curve, calculating a second distance between the reference curve and the target curve based on the curve information of the reference curve and the curve information of the target curve to obtain the second distance between each reference curve and the target curve, wherein the second distance is used to quantify the creep migration degree of the target equipment; connecting the second distances between each reference curve and the target curve according to the time sequence to obtain a creep migration degree curve; calculating the slope of each data point in the creep migration degree curve to obtain multiple slopes; determining the creep migration trend of the target equipment based on the numerical relationship between the multiple slopes and the preset slope to obtain the detection result.

[0071] In this first embodiment, to quantitatively evaluate the creep migration degree and its changing trend of the target device, firstly, a comparative analysis is performed on each previously determined reference curve to calculate the second distance between the reference curve and the current state curve of the target device (target curve). This distance is quantitatively calculated based on the positional differences of the device in the multidimensional feature space, intuitively reflecting the degree of migration of the device's characteristic parameters over time. The calculation results of the second distance for each reference curve provide a quantitative index of the creep migration of the target device at different historical stages, constructing a spatiotemporal perspective of the device's state changes.

[0072] Then, the calculated second distances are connected in time series to form a creep migration degree curve. The generation of this curve not only integrates the quantitative information of equipment creep migration, but also reveals the dynamic trend of equipment state evolution over time, providing a foundation for subsequent trend analysis.

[0073] Secondly, the slope of each data point on the creep migration curve is calculated to obtain a series of slope values. The slope represents the quantification of the equipment creep migration rate, reflects the speed and trend of equipment condition changes, and provides a key parameter for predicting equipment condition.

[0074] Finally, by comparing the calculated slope values ​​with preset slope thresholds, it is determined whether the creep migration of the target equipment has accelerated, and the specific timing of this acceleration. This process identifies significant changes in the slope, thereby pinpointing the turning point in the equipment performance degradation trend, providing a clear basis for preventative maintenance and condition prediction.

[0075] Through the above steps, a precise quantitative assessment of the creep migration degree of the target equipment and a clear identification of the creep acceleration trend are achieved, ensuring the scientific nature and timeliness of equipment maintenance decisions, thereby effectively improving the operational safety and stability of process equipment.

[0076] Optionally, in the detection method of the process equipment provided in Embodiment 1 of this application, calculating the second distance between the reference curve and the target curve based on the curve information of the reference curve and the curve information of the target curve includes: for each target cluster center in the target curve, calculating the third distance between each reference cluster center and the target cluster center based on the multidimensional feature space of the target and each reference multidimensional feature information, and summing the third distances between each reference cluster center and the target cluster center to obtain the sum of the third distances corresponding to each target cluster center, wherein the target multidimensional feature information is the multidimensional feature information corresponding to the target cluster center, and each reference multidimensional feature information is the multidimensional feature information corresponding to each reference cluster center; summing the sum of the third distances corresponding to each target cluster center in the target curve to obtain the second distance between the reference curve and the target curve.

[0077] In this first embodiment, to accurately quantify the creep migration degree of the target device relative to its historical operating state, firstly, for each target cluster center on the target curve, that is, the average position of the device in the multidimensional feature space under its current operating state. Then, within the multidimensional feature space, the target cluster center is compared one by one with each reference cluster center in the reference curve set, and a third distance between them is calculated. This distance calculation is based on the device's multidimensional feature information, ensuring the comprehensiveness and accuracy of the comparison.

[0078] Then, the third distance between the center of each reference cluster and the center of the target cluster in the reference curve is summed to obtain the third distance sum for that specific target cluster center. This summation operation essentially quantifies the overall difference between the target equipment and its historical operating state, making the assessment of equipment status more objective and quantitative.

[0079] Secondly, the above calculation process is repeated for each target cluster center on the target curve until the sum of the third distances corresponding to all target cluster centers is obtained. This step enhances the reliability and stability of the detection results by comprehensively analyzing the state changes of the equipment under various operating conditions.

[0080] Finally, the sum of the third distances corresponding to the centers of all target clusters in the target curve is calculated to obtain a measure representing the overall migration degree between the reference curve and the target curve, namely the second distance. This final distance index comprehensively reflects the overall creep migration degree of the equipment from its historical operating state to its current state, providing core data support for trend analysis and risk assessment of the equipment status.

[0081] For example, Figure 3 This is a schematic diagram illustrating an optional process for calculating the distance between a reference curve and a target curve, provided in Embodiment 1 of this application. Figure 3 As shown, object operating characteristic curve I is the equipment operating characteristic curve corresponding to the process equipment before creep migration, i.e., the reference curve mentioned above. Object operating characteristic curve II is the equipment operating characteristic curve corresponding to the process equipment after creep migration, i.e., the target curve mentioned above. First, calculate the Kth target cluster center in curve II (e.g., Figure 5 In ) and the center of the first reference cluster in curve I (e.g. Figure 5 In The third distance between (e.g.) Figure 5 In Then, the third distances between the Kth target cluster center and all reference cluster centers are summed to obtain the third distance sum for each target cluster center. Next, for each target cluster center (e.g., ... Figure 5 In , , The third distance (etc.) is added to obtain the second distance mentioned above, which is used to quantify the degree of creep migration of process equipment.

[0082] Through the above steps, not only can the difference between the target equipment and its historical operating state be accurately measured, but also the health status and operational efficiency of the equipment can be systematically assessed based on this difference, achieving refined monitoring of the degree of equipment creep migration. This technological achievement provides a solid scientific basis for the formulation and implementation of preventative maintenance strategies, effectively improving the quality and efficiency of process equipment operation and maintenance.

[0083] Optionally, in the process equipment detection method provided in Embodiment 1 of this application, multi-dimensional feature information corresponding to different operating conditions is extracted from the equipment operation data of the target equipment, and the equipment operation data is divided into multiple data subsets based on the multi-dimensional feature information. This includes: determining key operating condition information affecting the target equipment, and determining operating condition elements based on the key operating condition information; determining equipment operation features that are dependent on the operating condition elements during the operation of the target equipment, and obtaining multiple feature elements; determining the values ​​of the operating condition elements and the values ​​of the multiple feature elements based on the equipment operation data, and obtaining an equipment operation data set, wherein the ratio between the number of values ​​of the operating condition elements in the equipment operation data set and the number of values ​​included in the normal value range of the operating condition elements is greater than a preset ratio; determining multiple operating condition value intervals based on the normal value range of the operating condition elements, and dividing the equipment operation data set into multiple data subsets based on the values ​​of the operating condition elements and the multiple operating condition value intervals in the equipment operation data set.

[0084] In this first embodiment, to construct an analytical model that accurately reflects the degree of creep migration in the target equipment, the key operating condition information that has a decisive impact on equipment performance is first identified based on the equipment type and operating characteristics. This identification process ensures that subsequent analysis focuses on the core factors of equipment state changes, improving the relevance and efficiency of the analysis.

[0085] In one optional embodiment, the user can input multiple values ​​of the operating condition element and the values ​​of multiple feature elements corresponding to the operating condition element under different values ​​into an analysis tool or software, and the analysis tool can display the distribution of multiple feature elements in the multidimensional feature space. Figure 4 This is a schematic diagram of an optional multidimensional feature space provided according to Embodiment 1 of this application. For example... Figure 4 As shown, the operating condition element is set as follows: The multidimensional feature space includes the x-axis, y-axis, and z-axis, where the x-axis represents the feature element. The y-axis represents feature element X2, and the z-axis represents feature element X3. Figure 4 Multiple points in the data represent operating condition elements. Multiple eigenvalues ​​under different operating conditions The result after X2 and X3 are mapped to a multidimensional feature space, where the coordinates of each data point contain working condition elements. Multiple feature elements equal to a specific value The values ​​of X2 and X3.

[0086] When using the analysis tool, users can flexibly select different combinations of operating parameters for 3D analysis as needed. Specifically, the front-end page of the analysis tool has a checkbox area that lists all available operating parameters and feature elements. By selecting different operating parameters and feature element options, users can customize the composition of the multidimensional feature space to be analyzed (for example, defining the x-axis, y-axis, and z-axis in 3D space as different feature elements), thereby changing the analysis perspective. For example, in the initial state, the user selects operating parameters... (e.g., load level) and two feature elements (such as temperature) and (e.g., current) to form a three-dimensional operating space for equipment creep migration analysis. However, if the user wants to observe the equipment status from another perspective, such as focusing on the rotational speed (let's assume it's...), ) and vibration amplitude (assuming to be To check the effects of creep migration, simply uncheck the checkboxes in the interface. and Change the selection to the selection and If the analysis model is not updated immediately, the three-dimensional operating space is reconstructed using the new dimensional combination, and clustering and creep-variable analysis of the equipment status is performed based on this new space. This design greatly improves the flexibility and diversity of the analysis, allowing users to customize the most suitable analysis dimensions according to the specific conditions of the equipment and the analysis requirements, thereby obtaining more comprehensive and targeted equipment status assessment results.

[0087] Then, based on the key operating condition information, the equipment operation characteristics that have a clear dependency relationship with the key operating condition information are selected. Moreover, the equipment operation characteristics are not limited to a single parameter, but cover multiple feature elements that can characterize the equipment status from multiple dimensions.

[0088] Secondly, equipment operation data is collected during the normal operating cycle of the target equipment. From this data, the values ​​of operating condition elements and multiple feature elements are extracted to form an equipment operation data set. During the data collection phase, it is ensured that the proportion of the number of operating condition element values ​​to their normal value range exceeds a preset threshold, thereby enhancing the representativeness of the data sample and the reliability of the analysis results.

[0089] Finally, based on the normal value range of the operating condition elements, several operating condition value intervals were divided, and the data set was further subdivided into multiple data subsets according to the values ​​of the operating condition elements in the equipment operation data set. This subdivision process takes into account the natural boundaries of the operating conditions and the data distribution characteristics, ensuring that each subset can accurately reflect the operating status of the equipment within a specific interval, laying a data foundation for the next step of cluster analysis and creep migration degree calculation.

[0090] For example, Figure 5This is a schematic diagram illustrating multiple data subsets divided according to the optional device operation data (or historical device operation data) provided in Embodiment 1 of this application. For example... Figure 5 As shown, assuming the process equipment is a power plant fan, the operating condition element... It could be the fan speed. Assuming the fan speed varies between 600 rpm and 1200 rpm (the normal range, or feasible interval, mentioned above), it can be divided into several sub-ranges: 600 rpm to 700 rpm, 650 rpm to 750 rpm, 700 rpm to 800 rpm, 750 rpm to 850 rpm, 800 rpm to 900 rpm, 850 rpm to 950 rpm, 900 rpm to 1000 rpm, 950 rpm to 1050 rpm, 1000 rpm to 1100 rpm, and 1050 rpm to 1200 rpm. Figure 5 The working conditions are X0(1), X0(2), X0(3), etc.

[0091] Through the above steps, a set of equipment condition monitoring systems based on multi-dimensional feature information and operating condition dependencies was constructed, realizing refined analysis of changes in the operating status of target equipment. This enables the efficient extraction of key equipment condition information from massive historical data, providing detailed data support for the quantitative calculation and trend analysis of creep migration, and significantly improving the accuracy of equipment condition assessment and the scientific nature of preventive maintenance decisions.

[0092] Optionally, in the process equipment detection method provided in Embodiment 1 of this application, multiple data subsets are clustered based on multidimensional feature information, and a target curve is determined in the multidimensional feature space based on the multiple cluster centers obtained from the clustering. This includes: using the K-means algorithm to cluster multiple data subsets to obtain a cluster corresponding to each data subset; calculating the cluster center of the cluster for each data subset to obtain the cluster center corresponding to each data subset; mapping the cluster center corresponding to each data subset to the multidimensional feature space; and connecting the cluster centers corresponding to each data subset in the multidimensional feature space based on the value of the operating condition element corresponding to each data subset to obtain the target curve.

[0093] In this first embodiment, in order to construct an analytical model that can accurately reflect the operating status of the target equipment and its dynamic migration characteristics as operating conditions change, firstly, the K-means algorithm is used to independently perform clustering processing on multiple pre-divided data subsets. Through this algorithm, clusters corresponding to each data subset can be formed, and these clusters represent the operating mode and changing trend of the equipment under specific operating conditions.

[0094] Then, for each cluster corresponding to each subset of data, the centroid of each cluster is calculated. The calculation of the cluster center is based on the average eigenvalue of all data points within the cluster, ensuring that it accurately reflects the overall operating status of the cluster. This process transforms the abstract description of equipment operating data into concrete numerical values, providing a quantitative basis for subsequent analysis.

[0095] Secondly, the calculated cluster centers are mapped to a multi-dimensional feature space, which is constructed from key operating condition information and equipment operating characteristics, aiming to visualize the operating status of the equipment under different operating conditions. The position of the cluster centers in the multi-dimensional feature space directly reflects the average performance of the equipment under specific operating conditions.

[0096] Finally, based on the operating condition element values ​​corresponding to each data subset, the mapped cluster centers are connected in a multi-dimensional feature space to generate a target curve characterizing the equipment's operating characteristics at a specific historical stage. The construction of the target curve not only connects the cluster centers of the equipment under different operating conditions but also shows the dynamic migration path of equipment performance over time and operating conditions.

[0097] For example, Figure 6 This is a schematic diagram of the target curve formed by the cluster centers after clustering multiple optional data subsets according to Embodiment 1 of this application. Figure 6 As shown, This represents the cluster center after clustering the first data subset (such as multiple feature elements corresponding to working condition X0(1)). The cluster center represents the cluster center after the second data subset (such as multiple feature elements corresponding to working condition X0 (2)) is clustered, and so on. The dashed curve formed by connecting these cluster centers is the equipment operating characteristic curve, that is, the target districts and counties mentioned above, which intuitively reflects the operating pattern of the equipment in that period.

[0098] Through the above steps, a multidimensional dynamic model that can accurately reflect the operating characteristics of the target equipment was constructed, realizing the quantitative analysis of the degree of equipment creep migration. This helps to improve the accuracy and reliability of the analysis results, ensures the comprehensiveness of equipment condition assessment and the effectiveness of trend prediction, provides a scientific basis for the formulation of preventive maintenance strategies, and further optimizes the operating efficiency and maintenance costs of the equipment.

[0099] In one optional embodiment, for the induced draft fan of a power plant, a working condition element is selected. For the unit load, select the multidimensional feature elements of interest. , ...and then select key physical quantities from them that can be used for three-dimensional analysis. For example, characteristic elements. For suction blade position feedback, characteristic element For the current and characteristic elements of the suction fan To construct a three-dimensional operating space for the inlet and outlet pressure difference of the suction fan, if you need to switch to other three-dimensional operating conditions for analysis, you can select any other dimension combination in the checkboxes at the top of the interface (e.g., ...). Figure 4 In , , ).

[0100] Operational data of the induced draft fan were collected from four different historical periods. All data were projected onto the aforementioned three-dimensional operating space. The data exhibited a clear linear distribution in the space, and the distribution of data varied across different historical periods (e.g., ...). Figure 2 (Multiple data points in the data). Select the earliest historical data for the induced draft fan (covering most operating conditions), and categorize it by operating condition element. The feasible interval is divided into N equal subsets, with appropriate intersections between the subsets to ensure feature continuity. K-means clustering is used to cluster each subset, resulting in N clustering cores. These cores form the performance characteristic curve I (e.g., ...). Figure 6 (The curve in the middle).

[0101] Select the equipment operation data of the induced draft fan within one week, repeat the above steps of operating condition classification and cluster analysis, and obtain an operating characteristic curve II (or III, IV, etc.) for different time periods (e.g. Figure 5 The object running characteristic curve II). Calculate the comprehensive distance dk from each cluster core in curve II to all cluster cores in curve I (i.e., the third distance sum mentioned above), and then obtain the comprehensive distances d1, d2, d3, ... of each cluster core. Then sum these distances to obtain the overall distance index of the two curves, which is DI-II (i.e., the second distance mentioned above).

[0102] By comparing the numerical changes of DI-II, DII-III, DIII-IV, etc., if the growth rate from DI-II to DII-III is relatively slow, while the growth rate from DII-III to DIII-IV accelerates significantly, it indicates that the induced draft fan is experiencing accelerated creep migration in the third historical period, and this period is identified as a characteristic change point. A time-series trend line (i.e., the creep migration degree curve) is plotted based on the changes in the above distance indicators. The trend line changes only slightly during the long period of healthy equipment operation, but accelerates as the equipment materials and structure gradually age. When the slope of a data point on the trend line exceeds a preset threshold, the equipment is determined to have entered a high-risk operating period.

[0103] As demonstrated in this embodiment, the process equipment detection method provided in Embodiment 1 can accurately quantify the creep migration degree of power plant induced draft fans and identify characteristic change points of creep acceleration, providing a reliable basis for induced draft fan operation and maintenance decisions. Using this method, a power plant successfully identified the creep acceleration change point of one of its induced draft fans, arranging blade replacement and bearing maintenance three months in advance, avoiding blade breakage accidents caused by creep and reducing economic losses. Simultaneously, the extracted creep patterns were applied to two other induced draft fans of the same model in the same power plant, accurately predicting that one of the fans would enter the accelerated migration phase in the second half of 2026, achieving targeted operation and maintenance.

[0104] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0105] Example 2

[0106] This application also provides a process equipment testing device in Embodiment 2. It should be noted that the process equipment testing device in Embodiment 2 can be used to execute the process equipment testing method provided in Embodiment 1 of this application. The process equipment testing device provided in Embodiment 2 of this application will be described below.

[0107] Figure 7 This is a schematic diagram of the detection device for the process equipment provided according to Embodiment 2 of this application. Figure 7 As shown, the device includes: a first extraction unit 701, a first clustering unit 702, a determination unit 703, and a detection unit 704.

[0108] Specifically, the first extraction unit 701 is used to extract multi-dimensional feature information corresponding to different operating conditions from the equipment operation data of the target equipment, and divide the equipment operation data into multiple data subsets based on the multi-dimensional feature information, wherein the target equipment is the process equipment to be detected for creep migration trend.

[0109] The first clustering unit 702 is used to cluster multiple data subsets based on multidimensional feature information, and to determine the target curve in the multidimensional feature space based on the multiple cluster centers obtained by clustering. The multidimensional feature space is constructed based on multidimensional feature information.

[0110] The determining unit 703 is used to determine the target equipment type of the target equipment and to determine at least one reference curve corresponding to the target equipment type in the reference curve set.

[0111] The detection unit 704 is used to detect the creeping migration trend of the target device based on the curve information of at least one reference curve and the curve information of the target curve, and to obtain the detection result.

[0112] The process equipment detection device provided in Embodiment 2 of this application extracts multi-dimensional feature information corresponding to different operating conditions from the equipment operation data of the target equipment through a first extraction unit 701, and divides the equipment operation data into multiple data subsets based on the multi-dimensional feature information. The target equipment is the process equipment whose creep migration trend is to be detected. A first clustering unit 702 clusters the multiple data subsets according to the multi-dimensional feature information, and determines the target curve in the multi-dimensional feature space based on the multiple cluster centers obtained by clustering. The multi-dimensional feature space is constructed based on the multi-dimensional feature information. A determination unit 703 determines the target equipment type of the target equipment and determines at least one reference curve corresponding to the target equipment type in the reference curve set. A detection unit 704 detects the creep migration trend of the target equipment based on the curve information of at least one reference curve and the curve information of the target curve, and obtains the detection result. This solves the problem in the related technology that the traditional creep migration detection algorithm only analyzes a single equipment feature when detecting the creep migration trend of process equipment, resulting in inaccurate detection results.

[0113] By extracting multidimensional feature information containing different operating conditions from the equipment operation data of the target equipment, the complex performance of the equipment under various operating states can be systematically analyzed, achieving the technical effect of constructing a multidimensional data model that comprehensively reflects the operating characteristics of the equipment. Simultaneously, by dividing the equipment operation data into multiple data subsets based on the multidimensional feature information and then performing cluster analysis on these subsets, a deeper understanding of the subtle changes in the operating characteristics of the equipment under specific operating conditions can be achieved. This enables the determination of a target curve that accurately represents the current state of the equipment in a multidimensional feature space, effectively overcoming the limitations of traditional algorithms that rely on only a single feature for creep migration detection. This significantly improves the accuracy and reliability of the detection results, further refining the granularity of equipment state assessment and enhancing the accuracy of creep migration detection.

[0114] More importantly, by determining the specific type of the target equipment and selecting at least one reference curve that matches that type from the set of reference curves, a comparison standard based on equipment type and historical data can be provided for equipment status analysis, making the detection results more reliable and accurate. This achieves quantitative detection of the creep migration trend of the target equipment and further enhances the generalization ability of the detection algorithm and the technical effect of predicting the health status of the equipment.

[0115] Optionally, in the process equipment detection device provided in Embodiment 2 of this application, the device further includes: a second extraction unit, used to collect historical operating data of the equipment in multiple time periods before determining at least one reference curve corresponding to the target equipment type in the reference curve set, extract multi-dimensional feature information corresponding to different operating conditions from the historical operating data of the equipment, and obtain historical datasets for multiple time periods, wherein the historical operating data of the equipment includes at least the historical operating data of the target equipment type; a partitioning unit, used to partition the historical datasets for multiple time periods according to the values ​​of the operating conditions in the historical datasets, and obtain multiple historical data subsets corresponding to each time period; a second clustering unit, used to cluster the multiple historical data subsets corresponding to each time period according to the multi-dimensional feature information, and obtain multiple cluster centers corresponding to each time period; and a construction unit, used to map the multiple cluster centers corresponding to each time period to a multi-dimensional feature space, and construct a reference curve corresponding to each time period in the multi-dimensional feature space according to the multiple cluster centers corresponding to each time period, and obtain a reference curve set.

[0116] Optionally, in the process equipment detection device provided in Embodiment 2 of this application, the aforementioned determining unit 703 includes: a first determining subunit, used to determine a reference curve corresponding to the target equipment type in a set of reference curves to obtain a first curve set; a second determining subunit, used to determine multiple first cluster centers contained in each first curve in the first curve set, as well as the operating condition information and multidimensional feature information of each first cluster center; a first calculation subunit, used to calculate a first distance based on the same operating condition information in each first curve and the target curve, based on the multidimensional feature information corresponding to the operating condition information in the first curve and the multidimensional feature information corresponding to the operating condition information in the target curve; and a third determining subunit, used to determine at least one reference curve in the first curve set based on a first curve whose first distance is greater than a preset distance.

[0117] Optionally, in the detection device for process equipment provided in Embodiment 2 of this application, the detection unit 704 includes: a second calculation subunit, used to calculate a second distance between the reference curve and the target curve for each of the at least one reference curve, based on the curve information of the reference curve and the curve information of the target curve, to obtain the second distance between each reference curve and the target curve, wherein the second distance is used to quantify the creep migration degree of the target equipment; a first connection subunit, used to connect the second distances between each reference curve and the target curve according to the time sequence, to obtain a creep migration degree curve; a third calculation subunit, used to calculate the slope of each data point in the creep migration degree curve, to obtain multiple slopes; and a fourth determination subunit, used to determine the creep migration trend of the target equipment based on the numerical relationship between the multiple slopes and a preset slope, to obtain the detection result.

[0118] Optionally, in the detection device of the process equipment provided in Embodiment 2 of this application, the second calculation subunit mentioned above includes: a first calculation module, used for calculating, for each target cluster center in the target curve, a third distance between each reference cluster center and the target cluster center based on the multidimensional feature space of the target and each reference multidimensional feature information, and summing the third distances between each reference cluster center and the target cluster center to obtain the sum of the third distances corresponding to each target cluster center, wherein the target multidimensional feature information is the multidimensional feature information corresponding to the target cluster center, and each reference multidimensional feature information is the multidimensional feature information corresponding to each reference cluster center; and a second calculation module, used for summing the sum of the third distances corresponding to each target cluster center in the target curve to obtain the second distance between the reference curve and the target curve.

[0119] Optionally, in the process equipment detection device provided in Embodiment 2 of this application, the first extraction unit 701 mentioned above includes: a fifth determining subunit, used to determine key operating condition information affecting the target equipment, and determine operating condition elements based on the key operating condition information; a sixth determining subunit, used to determine equipment operating characteristics that are dependent on the operating condition elements during the operation of the target equipment, and obtain multiple feature elements; a seventh determining subunit, used to determine the values ​​of the operating condition elements and the values ​​of multiple feature elements based on the equipment operating data, and obtain an equipment operating data set, wherein the ratio between the number of values ​​of the operating condition elements in the equipment operating data set and the number of values ​​included in the normal value range of the operating condition elements is greater than a preset ratio; and an eighth determining subunit, used to determine multiple operating condition value intervals based on the normal value range of the operating condition elements, and divide the equipment operating data set into multiple data subsets based on the values ​​of the operating condition elements and the multiple operating condition value intervals in the equipment operating data set.

[0120] Optionally, in the detection device for process equipment provided in Embodiment 2 of this application, the first clustering unit 702 mentioned above includes: a clustering subunit, used to cluster multiple data subsets using the K-means algorithm to obtain clusters corresponding to each data subset; a fourth calculation subunit, used to calculate the cluster center of the cluster for each data subset to obtain the cluster center corresponding to each data subset; a mapping subunit, used to map the cluster center corresponding to each data subset to a multi-dimensional feature space; and a second connection subunit, used to connect the cluster centers corresponding to each data subset in the multi-dimensional feature space according to the value of the working condition element corresponding to each data subset to obtain the target curve.

[0121] The detection device of the process equipment includes a processor and a memory. The first extraction unit 701, the first clustering unit 702, the determination unit 703 and the detection unit 704 mentioned above are all stored in the memory as program units. The processor executes the program units stored in the memory to realize the corresponding functions.

[0122] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can improve the accuracy of creep migration trend detection results for process equipment.

[0123] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0124] Embodiment 3 of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements a method for detecting process equipment.

[0125] Embodiment 4 of the present invention provides a processor for running a program, wherein the program executes a method for detecting a process device during runtime.

[0126] Figure 8 This is a schematic diagram of the detection electronic equipment for the process equipment provided according to Embodiment 5 of this application. For example... Figure 8 As shown, Embodiment 5 of the present invention provides an electronic device. The device includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: extracting multi-dimensional feature information corresponding to different operating conditions from the device operation data of the target device, and dividing the device operation data into multiple data subsets based on the multi-dimensional feature information, wherein the target device is a process device whose creeping migration trend is to be detected; clustering the multiple data subsets based on the multi-dimensional feature information, and determining the target curve in the multi-dimensional feature space based on the multiple cluster centers obtained by clustering, wherein the multi-dimensional feature space is constructed based on the multi-dimensional feature information; determining the target device type of the target device, and determining at least one reference curve corresponding to the target device type in the reference curve set; detecting the creeping migration trend of the target device based on the curve information of at least one reference curve and the curve information of the target curve, and obtaining the detection result.

[0127] When the processor executes the program, it also performs the following steps: Before determining at least one reference curve corresponding to the target device type in the reference curve set, the above method further includes: collecting historical operating data of the device in multiple time periods, extracting multi-dimensional feature information corresponding to different operating conditions from the historical operating data of the device to obtain historical datasets for multiple time periods, wherein the historical operating data of the device includes at least the historical operating data of the target device type; dividing the historical datasets for multiple time periods according to the values ​​of the operating conditions in the historical datasets to obtain multiple historical data subsets corresponding to each time period; clustering the multiple historical data subsets corresponding to each time period according to the multi-dimensional feature information to obtain multiple cluster centers corresponding to each time period; mapping the multiple cluster centers corresponding to each time period to a multi-dimensional feature space, and constructing a reference curve corresponding to each time period in the multi-dimensional feature space based on the multiple cluster centers corresponding to each time period to obtain a reference curve set.

[0128] When the processor executes the program, it also performs the following steps: determining at least one reference curve corresponding to the target device type in the reference curve set, including: determining the reference curve corresponding to the target device type in the reference curve set to obtain a first curve set; determining multiple first cluster centers contained in each first curve in the first curve set, as well as the operating condition information and multidimensional feature information of each first cluster center; calculating a first distance based on the same operating condition information in each first curve and the target curve, based on the multidimensional feature information corresponding to the operating condition information in the first curve and the multidimensional feature information corresponding to the operating condition information in the target curve; and determining at least one reference curve in the first curve set based on the first curve whose first distance is greater than a preset distance.

[0129] When the processor executes the program, it also performs the following steps: detecting the creep migration trend of the target device based on the curve information of at least one reference curve and the curve information of the target curve, and obtaining the detection result, including: for each reference curve in the at least one reference curve, calculating the second distance between the reference curve and the target curve based on the curve information of the reference curve and the curve information of the target curve, and obtaining the second distance between each reference curve and the target curve, wherein the second distance is used to quantify the creep migration degree of the target device; connecting the second distances between each reference curve and the target curve according to the time sequence to obtain the creep migration degree curve; calculating the slope of each data point in the creep migration degree curve to obtain multiple slopes; determining the creep migration trend of the target device based on the numerical relationship between the multiple slopes and the preset slope, and obtaining the detection result.

[0130] When the processor executes the program, it also performs the following steps: calculating the second distance between the reference curve and the target curve based on the curve information of the reference curve and the curve information of the target curve, including: for each target cluster center in the target curve, calculating the third distance between each reference cluster center and the target cluster center based on the multidimensional feature space of the target and each reference multidimensional feature information, and summing the third distances between each reference cluster center and the target cluster center to obtain the sum of the third distances corresponding to each target cluster center, wherein the target multidimensional feature information is the multidimensional feature information corresponding to the target cluster center, and each reference multidimensional feature information is the multidimensional feature information corresponding to each reference cluster center; summing the sum of the third distances corresponding to each target cluster center in the target curve to obtain the second distance between the reference curve and the target curve.

[0131] When the processor executes the program, it also performs the following steps: extracting multi-dimensional feature information corresponding to different operating conditions from the device operation data of the target device, and dividing the device operation data into multiple data subsets based on the multi-dimensional feature information, including: determining key operating condition information affecting the target device, and determining operating condition elements based on the key operating condition information; determining device operation features that are dependent on the operating condition elements during the operation of the target device, and obtaining multiple feature elements; determining the values ​​of the operating condition elements and the values ​​of multiple feature elements based on the device operation data, and obtaining a device operation data set, wherein the ratio between the number of values ​​of the operating condition elements in the device operation data set and the number of values ​​included in the normal value range of the operating condition elements is greater than a preset ratio; determining multiple operating condition value intervals based on the normal value range of the operating condition elements, and dividing the device operation data set into multiple data subsets based on the values ​​of the operating condition elements and the multiple operating condition value intervals in the device operation data set.

[0132] When the processor executes the program, it also performs the following steps: clustering multiple data subsets based on multidimensional feature information, and determining the target curve in the multidimensional feature space based on the multiple cluster centers obtained from the clustering, including: using the K-means algorithm to cluster multiple data subsets to obtain the cluster corresponding to each data subset; calculating the cluster center of the cluster for each data subset to obtain the cluster center corresponding to each data subset; mapping the cluster center corresponding to each data subset to the multidimensional feature space; and connecting the cluster centers corresponding to each data subset in the multidimensional feature space based on the value of the operating condition element corresponding to each data subset to obtain the target curve.

[0133] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0134] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform a program that initializes all steps in a detection method such as a process device.

[0135] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0137] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0138] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0139] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0140] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0141] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0142] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for detecting process equipment, characterized in that, include: Multidimensional feature information corresponding to different operating conditions is extracted from the equipment operation data of the target equipment, and the equipment operation data is divided into multiple data subsets based on the multidimensional feature information. The target equipment is a process equipment with a creeping migration trend to be detected. The multiple data subsets are clustered based on the multidimensional feature information, and the target curve is determined in the multidimensional feature space based on the multiple cluster centers obtained from the clustering. The multidimensional feature space is constructed based on the multidimensional feature information. Determine the target device type of the target device, and determine at least one reference curve corresponding to the target device type from the reference curve set; The creep migration trend of the target device is detected based on the curve information of at least one reference curve and the curve information of the target curve, and the detection result is obtained.

2. The method according to claim 1, characterized in that, Before determining at least one reference curve corresponding to the target device type from the set of reference curves, the method further includes: Collect historical operating data of the equipment over multiple time periods, extract multidimensional feature information corresponding to different operating conditions from the historical operating data of the equipment, and obtain historical datasets for the multiple time periods, wherein the historical operating data of the equipment includes at least the historical operating data of the equipment of the target equipment type; Based on the values ​​of the working condition information in the historical dataset, the historical datasets for the multiple time periods are divided to obtain multiple subsets of historical data for each time period; Based on the multidimensional feature information, clustering is performed on multiple historical data subsets corresponding to each time period to obtain multiple cluster centers corresponding to each time period; The multiple cluster centers corresponding to each time period are mapped to the multidimensional feature space, and a reference curve corresponding to each time period is constructed in the multidimensional feature space based on the multiple cluster centers corresponding to each time period, thus obtaining the reference curve set.

3. The method according to claim 1, characterized in that, Determine at least one reference curve corresponding to the target device type from the set of reference curves, including: The reference curve corresponding to the target device type is determined from the set of reference curves to obtain the first set of curves; Determine the multiple first cluster centers contained in each first curve in the first curve set, as well as the working condition information and multidimensional feature information of each first cluster center; Based on the same working condition information in each first curve and the target curve, the first distance is calculated based on the multi-dimensional feature information corresponding to the working condition information in the first curve and the multi-dimensional feature information corresponding to the working condition information in the target curve. In the first set of curves, at least one reference curve is determined based on the first curve whose first distance is greater than a preset distance.

4. The method according to claim 1, characterized in that, Based on the curve information of the at least one reference curve and the curve information of the target curve, the creep migration trend of the target device is detected, and the detection result is obtained, including: For each of the at least one reference curve, a second distance between the reference curve and the target curve is calculated based on the curve information of the reference curve and the curve information of the target curve, thereby obtaining the second distance between each reference curve and the target curve, wherein the second distance is used to quantify the creep migration degree of the target device; By connecting the second distance between each reference curve and the target curve in chronological order, a creep migration degree curve is obtained; Calculate the slope of each data point in the creep migration curve to obtain multiple slopes; The peristaltic migration trend of the target device is determined based on the numerical relationship between the multiple slopes and the preset slope, and the detection result is obtained.

5. The method according to claim 4, characterized in that, Calculating the second distance between the reference curve and the target curve based on the curve information of the reference curve and the curve information of the target curve includes: For each target cluster center in the target curve, based on the multidimensional feature space, the third distance between each reference cluster center in the reference curve and the target cluster center is calculated according to the target multidimensional feature information and each reference multidimensional feature information. The third distances between each reference cluster center and the target cluster center are summed to obtain the third distance sum corresponding to each target cluster center. Here, the target multidimensional feature information is the multidimensional feature information corresponding to the target cluster center, and each reference multidimensional feature information is the multidimensional feature information corresponding to each reference cluster center. The third distances corresponding to the centers of each target cluster in the target curve are summed to obtain the second distance between the reference curve and the target curve.

6. The method according to claim 1, characterized in that, Extract multi-dimensional feature information corresponding to different operating conditions from the equipment operation data of the target equipment, and divide the equipment operation data into multiple data subsets based on the multi-dimensional feature information, including: Determine the key operating condition information affecting the target equipment, and determine the operating condition element based on the key operating condition information; During the operation of the target equipment, the equipment operation characteristics that are dependent on the operating condition elements are determined, and multiple feature elements are obtained; Based on the equipment operation data, the values ​​of the operating condition element and the values ​​of the multiple feature elements are determined to obtain an equipment operation data set, wherein the ratio between the number of values ​​of the operating condition element in the equipment operation data set and the number of values ​​included in the normal value range of the operating condition element is greater than a preset ratio. Multiple operating condition value intervals are determined based on the normal value range of the operating condition element, and the equipment operation data set is divided into multiple data subsets based on the value of the operating condition element and the multiple operating condition value intervals in the equipment operation data set.

7. The method according to claim 1, characterized in that, Based on the multidimensional feature information, the multiple data subsets are clustered respectively, and the target curve is determined in the multidimensional feature space based on the multiple cluster centers obtained from the clustering, including: The K-means algorithm is used to cluster the multiple data subsets respectively to obtain the cluster corresponding to each data subset; For each data subset, the cluster center of the cluster is calculated to obtain the cluster center of each data subset. Map the cluster center corresponding to each data subset to the multidimensional feature space; In the multidimensional feature space, the cluster centers corresponding to each data subset are connected according to the values ​​of the working condition elements corresponding to each data subset to obtain the target curve.

8. A detection device for process equipment, characterized in that, include: The first extraction unit is used to extract multi-dimensional feature information corresponding to different operating conditions from the equipment operation data of the target equipment, and divide the equipment operation data into multiple data subsets according to the multi-dimensional feature information, wherein the target equipment is a process equipment to be detected for creep migration trend; The first clustering unit is used to cluster the multiple data subsets according to the multidimensional feature information, and to determine the target curve in the multidimensional feature space based on the multiple cluster centers obtained by clustering, wherein the multidimensional feature space is constructed based on the multidimensional feature information; A determining unit is configured to determine the target device type of the target device and determine at least one reference curve corresponding to the target device type in a set of reference curves. The detection unit is used to detect the creeping migration trend of the target device based on the curve information of the at least one reference curve and the curve information of the target curve, and to obtain the detection result.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes stored computer instructions, wherein, when executed by a processor, the computer instructions implement the detection method of the process apparatus according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the detection method of the process equipment according to any one of claims 1 to 7.

Images