Clustering algorithm-based machine maintenance grouping method, equipment, medium and product

Abstract

The invention provides a machine maintenance grouping method and device based on a clustering algorithm, a medium and a product. The method comprises the following steps: acquiring maintenance data of each part in a to-be-grouped machine in a preset time period; preprocessing the maintenance data to obtain standardized data; performing clustering processing on the standardized data of each to-be-grouped machine by using a clustering algorithm to obtain a clustering result; and based on the cluster label of each to-be-grouped machine in the clustering result, generating a visual interface of each to-be-grouped machine so as to display the grouping result and / or the grouping reason of the to-be-grouped machines. According to the technical scheme, each to-be-grouped machine is clustered by using the clustering algorithm, and the to-be-grouped machines are grouped based on the clustering result. Therefore, reasonable maintenance strategies can be formulated for different machines, the normal working time of the machines is prolonged, and the output efficiency of the machines is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a machine maintenance grouping method, device, medium and product based on a clustering algorithm. Background Art

[0002] In recent years, with the rapid development of science and technology and the rapid rise of devices such as smartphones, the business of the semiconductor manufacturing industry has gradually increased.

[0003] In the semiconductor industry, machine maintenance is very important. If there is a problem with a part in the machine, it is usually necessary to shut down for repair or replacement, which will cause the production line to stagnate and affect the overall production efficiency. The longer the downtime, the fewer semiconductor chips are produced, which affects the total output of the factory. Effective maintenance and upkeep of the machine is an important part of ensuring production efficiency and product quality. However, in the process of semiconductor chip production, a large number of machines are used, which will cause the problem that manual maintenance plans are not timely and scientific. Therefore, how to formulate reasonable maintenance and upkeep strategies for different machines is a technical problem that technicians in this field need to solve urgently. Summary of the invention

[0004] One purpose of the present application is to provide a machine maintenance grouping method, equipment, medium and product based on a clustering algorithm, at least to solve the problem of automatic processing after a machine defect alarm occurs. The purpose of the present application is to provide a new machine maintenance grouping method based on a clustering algorithm. The method obtains the maintenance data of each component in the machine to be grouped within a preset time period, uses a clustering algorithm to cluster each machine to be grouped, and generates a visual interface of each machine to be grouped based on the cluster label of each machine to be grouped in the clustering result to group the machines to be grouped. Thereby, it is possible to formulate reasonable maintenance and maintenance strategies for different machines, extend the normal working time of the machine, and improve the output efficiency of the machine.

[0005] To achieve the above objectives, some embodiments of the present application provide the following aspects: In a first aspect, some embodiments of the present application further provide a machine maintenance grouping method based on a clustering algorithm, the method comprising: Obtain maintenance data of each component in the grouped machines within a preset period of time; Preprocessing the maintenance data to obtain standardized data; Use a clustering algorithm to perform clustering processing on the standardized data of each machine to be grouped to obtain a clustering result; Based on the cluster label of each machine to be grouped in the clustering result, a visualization interface of each machine to be grouped is generated to display the grouping result and / or grouping reason of the machine to be grouped.

[0006] In a second aspect, some embodiments of the present application further provide an electronic device, comprising: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, cause the processor to perform the steps of the method described above.

[0007] In a third aspect, some embodiments of the present application further provide a computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method as described above.

[0008] In a fourth aspect, some embodiments of the present application further provide a computer program product, comprising a computer program / instruction, which implements the steps of the method described above when executed by a processor.

[0009] Compared with the prior art, the solution provided by the embodiment of the present application obtains the maintenance data of each component in the machine to be grouped within a preset period, uses a clustering algorithm to perform clustering processing on each machine to be grouped, and generates a visual interface of each machine to be grouped based on the cluster label of each machine to be grouped in the clustering result to group the machines to be grouped. Thus, it is possible to formulate reasonable maintenance and care strategies for different machines, extend the normal working time of the machines, and improve the output efficiency of the machines. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of a machine maintenance grouping method based on a clustering algorithm provided in the first embodiment of the present application; Figure 2 It is a flowchart of a machine maintenance grouping method based on a clustering algorithm provided in the second embodiment of the present application; Figure 3 It is a flow chart of machine maintenance grouping based on clustering algorithm provided by the preferred embodiment; Figure 4 An exemplary structural diagram of the electronic device is disclosed. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0012] The technical solution provided by the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0013] Embodiment 1 Figure 1 FIG. 1 is a flow chart of a machine maintenance grouping method based on a clustering algorithm provided in the first embodiment of the present application. Figure 1 As shown, the specific steps include: The process includes: Step S101, obtaining maintenance data of each component in the machines to be grouped within a preset period of time; The machine can be a device used to produce chips. The machines to be grouped can be all the production equipment involved in each link or stage of generating chips. Since customized maintenance and servicing plans are required, grouping them is conducive to determining the maintenance and servicing plans for each group. The number of machines to be grouped can be one or more.

[0014] The preset period may be a preset historical reference period, such as 30 days, 60 days or 180 days. The maintenance data may be data recorded during the historical maintenance process. For example, the maintenance data may record the operating time of a certain component of a certain machine, replacement information, and the addition of lubricant during maintenance.

[0015] The machine for producing chips contains many complex parts. The following are some of the main parts: 1. Photolithography machine, including: light source system, such as laser, produces high-intensity, specific wavelength light source, such as deep ultraviolet light or extreme ultraviolet light. Its stability and power are crucial to the accuracy of photolithography. Optical components, including mirrors, lenses, etc., are used to focus and guide the light source to ensure that the light is accurately irradiated on the chip wafer. Mask stage and wafer stage, such as mask stage, are used to fix and accurately move the photolithography mask to ensure that the pattern on the mask accurately corresponds to the position on the wafer. Wafer stage, which carries the chip wafer and can be accurately moved in a high-precision three-dimensional space to achieve photolithography of different areas. Projection objective system, such as composed of multiple complex optical lenses, is responsible for reducing the pattern on the mask and projecting it onto the wafer. Its resolution determines the minimum feature size of the chip. 2. Etching machine, including: reaction chamber, which provides a sealed environment for etching reaction. Usually made of corrosion-resistant materials to withstand the erosion of various chemical etchants. It is equipped with gas nozzles, electrodes and other components for introducing etching gas and generating plasma. The RF power supply provides energy for the etching process and excites the etching gas to form plasma. The stability of its power and frequency has an important influence on the etching rate and uniformity. The gas delivery system, including gas storage tanks, valves, flow meters, etc., is used to accurately control the flow and mixing ratio of the etching gas. Different etching gases can achieve different etching effects. 3. Thin film deposition equipment, including: a reaction chamber, similar to the reaction chamber of an etcher, for thin film deposition reaction. It can be different process types such as physical vapor deposition (PVD), chemical vapor deposition (CVD) or atomic layer deposition (ALD). It is equipped with heating devices, gas nozzles, electrodes and other components, which are configured according to different process requirements. Target material or precursor source, in PVD equipment, the target material is a substance that is bombarded by ions to produce deposition material. The quality and purity of the target material have a great influence on the performance of the deposited film. In CVD and ALD equipment, the precursor source is a chemical substance that provides deposition material, and its stability and purity are also crucial. Vacuum system, in order to ensure the quality and uniformity of thin film deposition, the equipment needs to operate in a high vacuum environment. The vacuum system includes vacuum pumps, valves, pressure sensors and other components to maintain the vacuum level inside the equipment. 4. Cleaning equipment, including: a cleaning chamber, which is used to hold chip wafers and perform cleaning operations. It is usually made of corrosion-resistant materials and is equipped with nozzles, turntables and other components to ensure that the wafers can be fully cleaned. The cleaning agent delivery system, including cleaning agent storage tanks, pumps, valves, etc., is used to deliver cleaning agents to the cleaning chamber. Different cleaning agents can remove different types of contaminants. Drying system, after cleaning, the wafer needs to be dried to avoid residual moisture affecting chip performance. The drying system can be dried by thermal drying, centrifugal drying or nitrogen drying.5. Inspection equipment, including: Optical inspection system, including microscopes, cameras, light sources and other components, used for optical inspection of chip wafers. The surface morphology, defects, dimensional accuracy, etc. of the chip can be inspected. Electron beam inspection system, which uses electron beam to inspect the chip, can provide higher resolution and inspection accuracy. Electron beam inspection system usually includes electron gun, scanning coil, detector and other components. Probe station, used to test the electrical properties of the chip. The probe station is equipped with tiny probes that can contact the electrodes on the chip to measure the current, voltage and other parameters of the chip.

[0016] These are just some of the main components in the machines that produce chips. In fact, chip production equipment is a highly complex and sophisticated system that also includes many other auxiliary components and control systems to ensure the efficiency, stability and precision of the entire production process.

[0017] In this solution, optionally, the maintenance data includes at least one of operating time, fault records, and replacement frequency.

[0018] The operating time may include the continuous operating time of the current component, the total operating time, the ratio of the operating time to the rest time, etc. The fault record may include the record of minor faults that occurred in the current component, that is, the record of faults that can be repaired without replacement, and the record of replacement after a major fault occurred in the component in the entire machine. The replacement frequency may be the number of replacements within the entire preset period, the time interval between replacements, and the method and time of each replacement.

[0019] Through such a setting, this solution can make the maintenance data more representative of the information required for the maintenance and upkeep of the machine, and provide a data basis for the subsequent formulation of scientific maintenance and upkeep strategies.

[0020] Step S102, preprocessing the maintenance data to obtain standardized data; After obtaining the maintenance data, it needs to be preprocessed. For example, the units of various maintenance data can be unified and the data can be normalized. For example, some records are 53 days, and some records are 12 weeks. They all need to be unified in days. In this way, putting all maintenance records together will make sense for comparison, and it can also simplify subsequent calculations.

[0021] In this solution, optionally, the maintenance data is preprocessed to obtain standardized data, including: The maintenance data is cleaned to remove noise and missing values ​​to obtain standardized data.

[0022] In the process of data analysis and processing, cleaning the data to remove noise and missing values ​​is a very important step. It can improve the quality and reliability of the data and provide a better foundation for subsequent analysis and modeling. The following are some common methods to deal with noise and missing values: 1. Remove noise The methods of outlier detection mainly include: Statistical methods, by calculating the mean, median, standard deviation and other statistics of the data, identify data points that deviate greatly from these statistics as outliers. For example, the three standard deviation method can be used to consider data points that exceed the mean plus or minus three standard deviations as outliers.

[0023] The box plot method uses the interquartile range (IQR) of the box plot to identify outliers. Data points outside the upper and lower whisker range of the box plot are usually considered outliers.

[0024] Cluster analysis clusters the data, and data points far away from the cluster center may be regarded as outliers.

[0025] The main methods of smoothing include: Moving average method, for time series data, the moving average method can be used to smooth the data. That is, take the data points of a certain window size for average, and use the average value to replace the data point in the center of the window.

[0026] The weighted moving average method assigns different weights to different data points based on the moving average method. Generally, the closer the data point is to the current data point, the greater the weight.

[0027] Exponential smoothing, a special weighted moving average method, gives greater weight to recent data and smaller weight to distant data, adapting to data changes by continuously updating the smoothed value.

[0028] The filtering methods mainly include: Low-pass filtering: For data containing high-frequency noise, low-pass filtering can be used to remove high-frequency components and retain low-frequency signals. Common low-pass filters include Butterworth filters and Chebyshev filters.

[0029] Median filtering, for image data or one-dimensional data, median filtering can be used to remove salt and pepper noise, etc. Median filtering replaces the value of each data point with the median value of the data points in its neighborhood.

[0030] 2. Dealing with missing values The first is the deletion method, which includes: row deletion. If a row in the data set has a large number of missing values, you can consider deleting the row. However, this method may lead to a reduction in the amount of data, especially when there are many missing values, which may result in a large loss of useful information. Column deletion. If a variable has a high proportion of missing values, you can consider deleting the variable. However, caution is also required because important features may be lost.

[0031] Then there are the filling methods, which include: mean filling. For numerical variables, the mean of the variable can be used to fill missing values. This method is simple and fast, but it may introduce bias, especially when there are outliers in the data. Median filling is similar to mean filling, but the median is used instead of the mean, which is more robust for data with outliers. Mode filling. For categorical variables, the mode of the variable can be used to fill missing values. Interpolation method. For time series data or data with a certain order, interpolation method can be used to fill missing values. For example, linear interpolation, cubic spline interpolation, etc. Model prediction method: Machine learning algorithms, such as regression models, decision trees, etc., can be used to predict missing values ​​based on other variables. This method usually requires sufficient data and a suitable model.

[0032] When cleaning data, you need to choose the appropriate method based on the characteristics of the data and the purpose of analysis. At the same time, you also need to pay attention to the following points: Data cleaning is an iterative process, and you may need to try different methods many times to get satisfactory results. When dealing with missing values, you should consider the causes of missing values ​​to avoid introducing unnecessary biases. For important data, it is best to back up before cleaning to prevent data loss due to misoperation. The cleaned data needs to be verified and evaluated to ensure the effectiveness of the cleaning method and the quality of the data.

[0033] Through such a setting, this scheme can make the data input to the clustering algorithm more standardized, avoid the output results of the clustering algorithm being biased due to the input of erroneous data, and improve the accuracy of the output results of the clustering algorithm.

[0034] Step S103, using a clustering algorithm to perform clustering processing on the standardized data of each machine to be grouped to obtain a clustering result; Use a clustering algorithm, such as kmeans++, to cluster the features of the machines and obtain clustering results.

[0035] It can be known that after obtaining the clustering results, the machines in the same class can adopt the same care and maintenance strategy, such as determining the maintenance cycle, determining maintenance precautions, and so on.

[0036] Since there are many machines to be grouped, the number of each class in the clustering results of the machines to be grouped will affect the final output results. Therefore, the number of each clustering result can be set manually or implemented by some algorithms, such as using the Elbow Method or Silhouette Coefficient to determine the optimal number of clusters.

[0037] Step S104: Based on the cluster label of each to-be-grouped machine in the clustering result, a visualization interface of each to-be-grouped machine is generated to display the grouping result and / or grouping reason of the to-be-grouped machine.

[0038] Cluster labels can help us better understand the grouping of data for further analysis and decision making. Using clustering algorithms, such as K-Means algorithm, is a widely used clustering algorithm. After running the K-Means algorithm, each data point is assigned to a specific cluster. These clusters can be represented by integer labels such as 0, 1, 2, etc. The cluster labels for each data point can be obtained by looking at the output of the algorithm or using functions provided by specific programming language libraries. For example, in Python, you can use the sklearn.cluster.KMeans library to run the K-Means algorithm and get the cluster labels through the labels_ attribute.

[0039] After the grouping is completed, a visualization interface can be generated, which can be used to display the grouping results and / or grouping reasons of each machine, such as showing which group a machine is divided into, and due to which indicators the machine is divided into the current group.

[0040] In this solution, the clustering results can be visualized using two-dimensional or three-dimensional graphics to help understand the characteristics of different groups.

[0041] The technical solution provided in this embodiment obtains the maintenance data of each component in the machines to be grouped within a preset period, uses a clustering algorithm to perform clustering processing on each machine to be grouped, and generates a visual interface of each machine to be grouped based on the cluster label of each machine to be grouped in the clustering result to group the machines to be grouped. Thus, it is possible to formulate reasonable maintenance and care strategies for different machines, extend the normal working time of the machines, and improve the output efficiency of the machines.

[0042] On the basis of the above technical solutions, optionally, the method further includes: Determine the update cycle of the clustering algorithm; After reaching the update cycle, the clustering algorithm is iterated using the new maintenance data of the machines to be grouped within the update cycle.

[0043] In this solution, an update cycle can be determined for the clustering algorithm, such as one week, one month, etc. After the update cycle is reached, all the current machines to be grouped will generate new maintenance data within this update cycle. Therefore, the new maintenance data can be used as training samples to iteratively train the clustering algorithm to obtain a more accurate clustering algorithm. At the same time, it ensures that the maintenance data is the most capable of reflecting the actual usage of each machine, so that the output result of the clustering algorithm is more accurate.

[0044] On the basis of the above technical solutions, optionally, after using a clustering algorithm to perform clustering processing on the standardized data of each to-be-grouped machine and obtaining a clustering result, the method further includes: According to the clustering results, maintenance plan recommendation information of each to-be-grouped machine in each clustering result is determined.

[0045] After obtaining the clustering results, maintenance plan recommendation information for each machine to be grouped can be generated based on the clustering results, such as maintenance cycle, maintenance content, and core tasks of each maintenance.

[0046] For example, for a group of machines with short operating time, high failure rate, and high parts replacement rate, a frequent preventive maintenance plan can be formulated. On the contrary, for a group of machines with long operating time, low failure rate, and low parts replacement rate, a more relaxed maintenance plan can be formulated.

[0047] Through such a setting, this solution can assist staff in formulating more scientific maintenance plans for each machine, provide guarantees for the normal operation of the machine, improve the output efficiency of the machine, reduce the failure rate of the machine, and at the same time, it can also improve the yield of chips or chip parts produced by the machine to a certain extent.

[0048] Embodiment 2 Figure 2 FIG. 1 is a flow chart of a machine maintenance grouping method based on a clustering algorithm provided in the second embodiment of the present application. Figure 2 As shown, the specific steps include: Step S201, obtaining maintenance data of each component in the machines to be grouped within a preset period of time; Step S202, preprocessing the maintenance data to obtain standardized data; Step S203, using a clustering algorithm to vectorize the standardized data of each to-be-grouped machine to obtain the vector coordinates of each to-be-grouped machine; Vectorizing the standardized data of each machine to be grouped can convert the data into vector form for further processing and analysis in machine learning and data analysis. The following are some common vectorization processing methods. For example, the vectorization of numerical data can be achieved by direct conversion. For a single numerical data, it can be directly converted into a one-dimensional vector. For example, the value 5 can be converted into a vector [5]. If there are multiple numerical variables, they can be combined into a multidimensional vector. For example, there are two variables x and y, with values ​​of 3 and 4 respectively, which can be converted into a vector [3, 4]. Standardized vectorization can also be performed, such as standardizing the numerical data, such as standardizing with a mean of 0 and a variance of 1, or mapping the data to a specific interval. The standardized data can be vectorized according to the above method. For example, the standardized values ​​-0.5 and 1.2 can be converted into the vector [-0.5, 1.2]. In this way, the vector representation of each machine to be grouped can be obtained, that is, the vector coordinates of each machine to be grouped can be obtained.

[0049] Step S204, determining the number of clusters of each clustering result according to a predetermined grouping rule; Before grouping, the number of clusters for each clustering result can be determined preferentially.

[0050] In this embodiment, optionally, the predetermined grouping rule includes the elbow rule or the silhouette coefficient rule.

[0051] Among them, the Elbow Method is a method for determining the number of clusters. In cluster analysis, it is necessary to determine the appropriate number of clusters to achieve a better clustering effect. The Elbow Method determines a more appropriate number of clusters by observing the change in the sum of squared errors (SSE) or other evaluation indicators as the number of clusters increases in the clustering results. The principle is that when the number of clusters is small, there are more data points in each cluster, the difference between the data points is large, and the SSE will also be large. As the number of clusters increases, the number of data points in each cluster gradually decreases, the difference between the data points will gradually decrease, and the SSE will gradually decrease. However, when the number of clusters increases to a certain extent, the effect of continuing to increase the number of clusters on reducing SSE will become less obvious. At this time, the SSE change curve will have an inflection point similar to the elbow. The number of clusters corresponding to this inflection point is the more appropriate number of clusters. First, perform cluster analysis and select different numbers of clusters for multiple experiments. Calculate the SSE or other evaluation indicators for each experiment. Draw a curve with the number of clusters as the horizontal axis and SSE or evaluation index as the vertical axis. Observe the curve, find the inflection point, and determine the appropriate number of clusters. The advantage of the elbow rule is that it is relatively simple and intuitive, does not require much prior knowledge of the data, and can help determine the number of clusters to a certain extent. For some complex data distributions, it may not be easy to find an obvious inflection point; and this method depends on specific evaluation indicators, and different evaluation indicators may produce different results.

[0052] Silhouette Coefficient is an indicator used to evaluate clustering effect. It combines the concepts of cohesion and separation, and measures the closeness of a data point to its cluster and the degree of separation from other clusters. For a data point, the separation can be expressed by the minimum value of the average distance from the data point to other data points in its cluster and the average distance from the data point to all data points in other clusters. When the silhouette coefficient is close to 1, it means that the data point is closely integrated with its cluster and well separated from other clusters; when the silhouette coefficient is close to -1, it means that the data point may be incorrectly assigned to a cluster; when the silhouette coefficient is close to 0, it means that the data point is on the boundary of two clusters and it is difficult to determine its affiliation. Perform cluster analysis to obtain clustering results. For each data point, calculate its silhouette coefficient. Calculate the average value of the silhouette coefficients of all data points as the silhouette coefficient of the entire clustering result. Compare the silhouette coefficients under different numbers of clusters, and select the number of clusters with the largest silhouette coefficient as the optimal number of clusters. The advantage of the silhouette coefficient is that it takes into account both cohesion and separation, and can evaluate the clustering effect more comprehensively; it has good adaptability to clusters of different shapes and sizes. However, the calculation is relatively complex, especially for large-scale data sets; it also depends on a specific distance measurement method, and different distance measurements may affect the results of the silhouette coefficient.

[0053] This solution provides two calculation methods, which can better determine the number of clusters in each clustering result, so as to obtain more accurate clustering results. In a clustering result, the similarity of the maintenance required by each machine is greater, and the formulation of the maintenance strategy is more scientific.

[0054] Step S205, clustering the vector coordinates of each machine to be grouped based on the cluster number to obtain a clustering result; In the process of clustering processing, clustering processing can be performed according to the determined number of clusters, so as to obtain a more accurate clustering result.

[0055] Step S206 , based on the cluster label of each to-be-grouped machine in the clustering result, a visualization interface of each to-be-grouped machine is generated to display the grouping result and / or grouping reason of the to-be-grouped machine.

[0056] Based on the above embodiments, this embodiment provides a specific method for determining the number of clusters and performing clustering processing based on the number of clusters. By adopting this solution, the grouping of each machine can be more reasonable, in line with actual maintenance needs, reduce the failure rate of the machine, and improve the output efficiency of the machine.

[0057] In order to enable those skilled in the art to understand the present solution more clearly, the present solution provides a preferred embodiment.

[0058] Figure 3 FIG. 1 is a flow chart of the machine maintenance grouping based on the clustering algorithm provided by the preferred embodiment. Figure 3 As shown, the specific steps include: S1: Data collection and preparation.

[0059] 1. Data collection: Collect the parts behavior data of all relevant machines for the past 180 days, including the running time, failure records, replacement frequency, etc. of the parts.

[0060] The following table is a maintenance data collection table for a certain component of the machine:

[0061] 2. Data preprocessing: Clean the data to remove noise and missing values, and standardize the data to make different features comparable.

[0062] S2: Use a clustering algorithm (such as kmeans++) to cluster the features of the machines and obtain clustering results. The number of clusters is determined by using the Elbow Method or Silhouette Coefficient to determine the optimal number of clusters.

[0063] S3: Feature visualization: Use 2D or 3D graphs to visualize clustering results and help understand the characteristics of different groups.

[0064] 1. For machine groups with short operating time, high failure rate, and high parts replacement rate, a frequent preventive maintenance plan can be formulated.

[0065] 2. For machine groups with long operating time, low failure rate, and low parts replacement rate, a more relaxed maintenance plan can be formulated.

[0066] This preferred embodiment uses a clustering algorithm to group machines, which can improve the efficiency of maintenance management. Based on the similar usage patterns of the machines, a more accurate and efficient maintenance plan can be formulated. In addition, this patent mines features through the maintenance history records of the machines, and the clustering results of the machines are more accurate. Through the visualization of machine features, the analysis and guidance of engineers are more suggestive.

[0067] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be a digital computer in various forms, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, etc. The electronic device may also be a mobile device in various forms, such as a personal digital assistant, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0068] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein when the computer program instructions are executed, the processor executes the steps of the method provided in any one or more of the above embodiments. Figure 4 An exemplary structural diagram of the electronic device is disclosed. Figure 4 As shown, the electronic device includes: one or more processors 401, a memory 402, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Among them, the components shown in this article, their connections and relationships, and their functions are only used as examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0069] The electronic device may further include: an input device 403 and an output device 404. The processor 401, the memory 402, the input device 403 and the output device 404 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0070] The input device 403 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 404 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0071] To provide interaction with a user, the electronic device may be a computer. The computer has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0072] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium, and when the computer program / instruction is executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0073] The memory 402 can be used as a non-transient computer-readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules. The processor 401 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 402, so as to implement the program instructions / modules corresponding to the method provided by any one or more of the above embodiments in the embodiments of the present application.

[0074] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory 402 may optionally include a memory remotely arranged relative to the processor 401, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0075] It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0076] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. 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 technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0077] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0078] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. For example, an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device may be used to implement the embodiments. In some embodiments, the software program of the present application may be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including related data structures) may be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present application may be implemented by hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

[0079] The computer program product provided in the embodiment of the present application includes one or more computer programs / instructions, which, when executed by the processor, generate in whole or in part the process or function described in the embodiment of the present application. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0080] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0081] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0082] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A machine maintenance grouping method based on clustering algorithm, characterized in that: The method comprises: Obtaining maintenance data of each component in a machine to be grouped within a preset period of time; the machine is used for chip production; Preprocessing the maintenance data to obtain standardized data; Use a clustering algorithm to perform clustering processing on the standardized data of each machine to be grouped to obtain a clustering result; Based on the cluster label of each machine to be grouped in the clustering result, a visualization interface of each machine to be grouped is generated to display the grouping result and / or grouping reason of the machine to be grouped.

2. The method according to claim 1, characterized in that Use the clustering algorithm to cluster the standardized data of each machine to be grouped, and obtain the clustering results, including: Use a clustering algorithm to vectorize the standardized data of each machine to be grouped, and obtain the vector coordinates of each machine to be grouped; Determine the number of clusters for each clustering result according to a predetermined grouping rule; Based on the cluster number, cluster processing is performed on the vector coordinates of each machine to be grouped to obtain a clustering result.

3. The method according to claim 2, characterized in that The predetermined grouping rule includes an elbow rule or a silhouette coefficient rule.

4. The method according to claim 1, characterized in that: The method further comprises: Determine the update cycle of the clustering algorithm; After reaching the update cycle, the clustering algorithm is iterated using the new maintenance data of the machines to be grouped within the update cycle.

5. The method according to claim 1, characterized in that Preprocessing the maintenance data to obtain standardized data includes: The maintenance data is cleaned to remove noise and missing values ​​to obtain standardized data.

6. The method according to claim 1, characterized in that The maintenance data includes at least one of operating time, fault records, and replacement frequency.

7. The method according to claim 1, characterized in that After clustering the standardized data of each to-be-grouped machine using a clustering algorithm to obtain a clustering result, the method further includes: According to the clustering results, maintenance plan recommendation information of each to-be-grouped machine in each clustering result is determined.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 7.

9. A computer readable medium having a computer program / instructions stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images