Intelligent management method, device and equipment for intelligent power protection spare parts

Abstract

The invention relates to the field of electric power overhaul, and discloses an intelligent management method, device and equipment for intelligent power protection spare parts, and the method comprises the steps: obtaining the identity information of a user through a camera, and opening a power protection spare part cabinet; through a weight sensor of each storage grid in the power protection spare part cabinet, the type and the number of the power protection spare parts taken by the user are judged; according to the types and the number of the power protection spare parts taken by the user, predicting a fault maintenance type through a fault maintenance type prediction model; according to the predicted fault maintenance type, judging whether the type and the number of the power protection spare parts taken by the user are abnormal or not; and when the types and the number of the power guarantee spare parts taken by the user are judged to be abnormal, alarm prompt information is generated, so that effective management of the power guarantee spare parts is realized, the omission or wrong taking conditions of maintainers are reduced, and the efficiency of electric power maintenance is improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power maintenance, and in particular to an intelligent management method, device and equipment for intelligent power protection spare parts. Background Art

[0002] Power supply spare parts cabinets play an important role in power systems. They are used to store various spare parts, such as opening and closing coils, DC contactors, travel switches, transfer switches, etc., to ensure that these key items are properly kept. When a power system fails, the required spare parts can be quickly taken out for repair or replacement, shortening the power outage time and improving the reliability and response speed of the system. However, power supply spare parts cabinets in the prior art lack real-time monitoring of the outbound process and cannot accurately record the use of items and the person responsible. Traditional inventory management usually relies on regular inventory and manual updates, resulting in inaccurate inventory data. In addition, due to unfamiliarity with the type of fault or maintenance work, maintenance personnel often easily miss the required spare parts or use the wrong spare parts, resulting in unreasonable extension of maintenance time. Summary of the invention

[0003] In view of this, the present invention provides an intelligent management method for intelligent power supply spare parts, which solves the technical problems in the prior art that the power supply spare parts cabinet cannot accurately record the usage of items and the responsible persons and maintenance personnel are prone to miss taking the required spare parts or take the spare parts incorrectly.

[0004] According to a first aspect of the present invention, there is provided a method for intelligent management of intelligent power supply spare parts, comprising:

[0005] The user's identity information is obtained through the camera to open the power supply spare parts cabinet;

[0006] The type and quantity of power supply spare parts taken by the user are determined through the weight sensor of each storage grid in the power supply spare parts cabinet;

[0007] According to the type and quantity of power supply spare parts used by users, the fault maintenance type is predicted through the fault maintenance type prediction model;

[0008] According to the predicted fault maintenance type, determine whether the type and quantity of power supply spare parts used by the user are abnormal;

[0009] When it is determined that the type and quantity of power supply spare parts used by the user are abnormal, an alarm prompt message is generated; when it is determined that the type and quantity of power supply spare parts used by the user are normal, a normal prompt message is generated.

[0010] According to a second aspect of the present invention, there is provided an intelligent management device for intelligent power supply spare parts, comprising:

[0011] Identity authentication module, used to obtain the user's identity information through the camera to open the power supply spare parts cabinet;

[0012] The spare parts detection module determines the type and quantity of spare parts taken by the user through the weight sensor of each storage grid in the spare parts cabinet;

[0013] The fault maintenance type prediction module is used to predict the fault maintenance type through the fault maintenance type prediction model according to the type and quantity of power supply spare parts taken by the user;

[0014] The abnormality detection module is used to determine whether the type and quantity of power supply spare parts taken by the user are abnormal according to the predicted fault maintenance type;

[0015] The prompt alarm module is used to generate an alarm prompt message when it is determined that the type and quantity of power supply spare parts taken by the user are abnormal; when it is determined that the type and quantity of power supply spare parts taken by the user are normal, it generates a normal prompt message.

[0016] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned intelligent management method for intelligent power supply spare parts when executing the computer program.

[0017] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent management method for intelligent power supply spare parts.

[0018] Through the above technical scheme, the present invention provides an intelligent management method, device, equipment and medium for intelligent power spare parts, which obtains the user's identity information through a camera to open the power spare parts cabinet; determines the type and quantity of power spare parts taken by the user through the weight sensor of each storage grid in the power spare parts cabinet; predicts the fault repair type according to the type and quantity of power spare parts taken by the user through a fault repair type prediction model; determines whether the type and quantity of power spare parts taken by the user are abnormal according to the predicted fault repair type; generates an alarm prompt message when it is determined that the type and quantity of power spare parts taken by the user are abnormal, thereby realizing effective management and tracing of power spare parts, reducing the occurrence of omissions or incorrect use by maintenance personnel, and improving the efficiency of power maintenance.

[0019] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, and to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0021] Figure 1 A schematic diagram of a power-saving spare parts cabinet provided in an embodiment of the present invention is shown;

[0022] Figure 2 A schematic diagram of a process flow of an intelligent power supply spare parts intelligent management method provided in an embodiment of the present invention is shown;

[0023] Figure 3 A schematic structural diagram of an intelligent power-saving spare parts intelligent management device provided in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] The specific implementation of the present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0025] An intelligent management method for intelligent power supply spare parts provided by the embodiment of the present invention can be applied to Figure 1 A power supply spare parts cabinet, as shown in the figure, is provided with a camera, and a plurality of grids are provided in the power supply spare parts cabinet. Each storage grid corresponds to a different type of power supply spare parts, and a weight sensor is provided at the bottom of the grid. The weight sensor is used to preliminarily judge the type and quantity of the power supply spare parts taken out by the user according to the weight change of the weight sensor before and after the power supply spare parts are taken out. A control circuit board is built into the power supply spare parts cabinet, and a processor is provided on the control circuit board. The processor executes an intelligent power supply spare parts intelligent management method provided in an embodiment of the present invention, obtains the user's identity information through a camera to open the power supply spare parts cabinet; judges the type and quantity of power supply spare parts taken by the user through the weight sensor of each storage grid in the power supply spare parts cabinet; predicts the fault inspection and repair type according to the type and quantity of power supply spare parts taken by the user through a fault inspection and repair type prediction model; judges whether the type and quantity of power supply spare parts taken by the user are abnormal according to the predicted fault inspection and repair type; generates an alarm prompt message when it is judged that the type and quantity of power supply spare parts taken by the user are abnormal, and generates a normal prompt message when it is judged that the type and quantity of power supply spare parts taken by the user are normal, thereby realizing effective management and tracing of power supply spare parts, reducing the occurrence of omissions or incorrect use by maintenance personnel, and improving the efficiency of power maintenance.

[0026] Embodiment 1:

[0027] like Figure 2 As shown, an intelligent management method for intelligent power supply spare parts provided in an embodiment of the present invention includes:

[0028] Step 201, obtaining the user's identity information through a camera to open the power supply spare parts cabinet;

[0029] Step 202: Determine the type and quantity of power supply spare parts taken by the user through the weight sensor of each storage compartment in the power supply spare parts cabinet;

[0030] Step 203: predict the fault maintenance type through a fault maintenance type prediction model according to the type and quantity of power supply spare parts used by the user;

[0031] In order to generate the fault repair type prediction model in advance, before step 203, the following steps are specifically included:

[0032] Step 203-1, obtaining the types and quantities of power supply spare parts used by the user in the past;

[0033] Step 203-2: Perform cluster analysis on the types and quantities of power supply spare parts historically used by the user to identify combinations of different power supply spare parts;

[0034] Step 203-3: associate and map the combinations of different power supply spare parts with the fault maintenance types to generate a fault maintenance type prediction model.

[0035] Among them, the combination of different power supply spare parts is associated with the fault maintenance type. This process can be completed by an expert system or implemented by manual labeling. For example, the corresponding relationship between the fault maintenance type and the combination of power supply spare parts is as follows:

[0036] (1) When the circuit breaker fails, a "control circuit disconnection" signal is sent, and the spare parts used include "opening and closing coils", "DC contactors", "travel switches", "converter switches", etc.;

[0037] (2) After the five-protection unlocking, the mechanical lock cannot be opened, and the spare parts used are "locking coil", "tongue piece" and "reed piece";

[0038] (3) The equipment sends a "bus voltage low" signal, which may be caused by the primary fuse of the current transformer blowing. The spare parts include "fuse tubes" and the corresponding fuses are configured for different equipment.

[0039] (4) During maintenance, it is found that the contacts are burned, deformed, cracked, etc., and there will be different numbers and models of contacts and contact fingers.

[0040] Associate and map the clustering results with the fault troubleshooting type. For example, if "opening and closing coils" and "DC contactors" are frequently used in combination, and these combinations are often associated with "control circuit break" faults, they can be marked as a model of the fault troubleshooting type. Assume that the analysis results show the following clustering combinations:

[0041] Combination A: ["opening and closing coil", "DC contactor"] can be associated with the fault repair type of control circuit disconnection;

[0042] Combination B: ["locking coil", "tongue"] can be associated with the fault repair type of mechanical locking fault;

[0043] Combination C: ["Fuse"] The associated fault repair type is the bus voltage low signal.

[0044] Through such cluster analysis, a prediction model for fault inspection and maintenance types can be formed. For example, when the system sends a "control circuit break" signal, it can automatically recommend "opening and closing coils" and "DC contactors" as spare parts to improve fault handling efficiency. Combined with the M-DBSCAN algorithm for cluster analysis of historical usage data, it can effectively identify the usage patterns of power-saving spare parts and provide intelligent prediction and decision support for fault inspection and maintenance.

[0045] Step 204: According to the predicted fault maintenance type, determine whether the type and quantity of power supply spare parts used by the user are abnormal;

[0046] Step 205: When it is determined that the type and quantity of power supply spare parts used by the user are abnormal, an alarm prompt message is generated;

[0047] In step 205, when it is determined that the type and quantity of power-saving spare parts taken by the user are abnormal, Figure 1 The display screen of the power-saving spare parts cabinet in the system displays the types and quantities of power-saving spare parts that may need to be taken, so as to remind the maintenance personnel to confirm whether the spare parts corresponding to the fault maintenance type are taken correctly.

[0048] Step 206: When it is determined that the type and quantity of the power-saving spare parts used by the user are normal, a normal prompt message is generated.

[0049] An intelligent management method for intelligent power spare parts provided by an embodiment of the present invention obtains the identity information of the user through a camera to open the power spare parts cabinet; the type and quantity of power spare parts taken by the user are judged through the weight sensor of each storage grid in the power spare parts cabinet; the fault repair type is predicted according to the type and quantity of power spare parts taken by the user through the fault repair type prediction model; according to the predicted fault repair type, it is judged whether the type and quantity of power spare parts taken by the user are abnormal; when it is judged that the type and quantity of power spare parts taken by the user are abnormal, an alarm prompt message is generated, so that effective management and retrieval of power spare parts are realized, the occurrence of omissions or erroneous use by maintenance personnel is reduced, and the efficiency of power maintenance is improved. The method in the example of the present invention has been put into operation in a certain substation for one year, realizing the intelligent and lean management of the distributed warehouse of spare parts, reducing the workload of power equipment fault repair, and shortening the fault repair time.

[0050] Embodiment 2:

[0051] Due to the uncertainty of the fault repair type and the uncertainty of the type and quantity of the spare parts in stock, it is impossible to specify the number of clusters in the clustering algorithm. In addition, due to the occasional wrong use by the search personnel, noise is easily introduced into the historical data samples. Therefore, in the second embodiment of the present invention, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is introduced to implement the clustering analysis in the implementation of the present invention. Accordingly, step 203-2 specifically includes:

[0052] Step 203-21, classify the number of power supply spare parts used in history into numerical data, and classify the type of power supply spare parts used in history into character data;

[0053] Step 203-22, using Euclidean distance to calculate the similarity of numerical data, and using a string similarity algorithm based on edit distance to calculate the similarity of character data;

[0054] Step 203-23, determine the comprehensive distance metric between samples in the data set;

[0055] Among them, the comprehensive distance measurement between samples in the data set is

[0056] Among them, n is the number of attributes of the sample, k is the kth attribute, ω k is the weight of the kth attribute. When the kth attribute is missing, ε k = 0, when the kth attribute is not missing ε k =1,x nk and nkThe k-th attribute of sample X and sample Y is a numeric value, x ck and ck Respectively represent that the k-th attribute of sample X and sample Y is a character value.

[0057] Step 203-24, estimating the parameters Eps and MinPts of the DBSCAN algorithm according to the comprehensive distance metric;

[0058] Among them, eps represents the scanning radius, and minPts represents the minimum number of included points;

[0059] Step 203-25, using the estimated parameter values ​​to perform DBSCAN density-based cluster analysis on the types and quantities of power supply spare parts historically used by the user;

[0060] Step 203-26: Identify the combination pattern of the types and quantities of power supply spare parts historically used by the user based on the clustering results.

[0061] Embodiment 2 of the present invention can process and analyze different types of data more accurately by dividing the number of power supply spare parts into numerical data and the type of power supply spare parts into character data. This distinction allows the algorithm to adopt the most appropriate similarity measurement method for different data characteristics. Using Euclidean distance to calculate the similarity of numerical data and using an algorithm based on edit distance to calculate the similarity of character data can more accurately reflect the actual differences and similarities between data points. This helps to improve the accuracy and reliability of clustering results. By determining a comprehensive distance metric between samples in a data set, the method can integrate similarity metrics for numerical and character data and provide a comprehensive perspective on the distance between samples because it takes into account all relevant dimensions of the data. This comprehensive metric is the key to achieving effective clustering. The parameters Eps (scanning radius) and MinPts (minimum number of included points) of the DBSCAN algorithm are estimated based on the comprehensive distance metric, making the clustering process more automated and adaptable. This parameter estimation method helps to automatically adjust the algorithm to adapt to the actual distribution of data without a clear number of clusters. Using the estimated parameter values ​​to perform DBSCAN cluster analysis can effectively identify high-density areas in the data as clusters and identify points in low-density areas as noise points. Through the clustering results, the combination patterns of the types and quantities of power supply spare parts historically used by users can be identified, providing strong data support for inventory management and combined prediction of the types and quantities of power supply spare parts.

[0062] Embodiment three:

[0063] The DBSCAN parameters are crucial for optimal clustering accuracy and outlier detection. The parameters Eps and MinPts in the second embodiment of the present invention are estimated more by manual labor and experience. The DBSCAN algorithm is particularly sensitive to the Eps parameter. A small change in Eps may lead to a huge difference in clustering results. In addition, since the types and quantities of power supply spare parts used historically are small sample data, outliers (noise) are incorrectly classified into clusters, or they are simply marked as noise and ignored, which may lose important information and cause large errors in the prediction model. Therefore, the DBSCAN clustering algorithm is optimized in the third embodiment of the present invention. Accordingly, steps 203-24 in the second embodiment specifically include:

[0064] Steps 203-241, set the data set, neighborhood radius parameter Eps, minimum point number parameter MinPts, and number of iterations;

[0065] The dataset D is a set of data points. The neighborhood radius parameter Eps, i.e., the distance threshold (Epsilon (ε)), is generated by the linear congruential LCM method. The minimum number of points parameter MinPts is the minimum number of points required to form a dense area, which is determined by a random algorithm. The number of iterations is the number of recursive calls to DBSCAN. The output of this method is the cluster set in the dataset. The output noise point is the set of data points marked as noise. The linear congruential method (LCM) is an algorithm for generating pseudo-random numbers, which can be used to generate the distance threshold (Epsilon). Its basic formula is X n+1 =(aX n +c)modm, where X n is the currently generated random number, X n+1 For the next random number generated, the multiplier a is usually selected to ensure randomness, the increment c is usually set to a constant, the modulus m defines the range of the generated random number, and the appropriate parameters a, c, m and a seed value X are selected. 0 . These parameters can be adjusted as needed to obtain better randomness. Generate random numbers: Use the above formula to iteratively generate multiple random numbers. For example, set the range to [0.1, 1.5], linearly transform the generated random numbers to adapt them to the target range, and calculate the distance threshold. The generated random numbers can be directly used as Epsilon values, or appropriately scaled to ensure that they are within the specified range, for example

[0066] Steps 203-242, traverse each point in the data set as a core point;

[0067] Among them, each unvisited point P in the data set is traversed, and the visited point P is marked as visited.

[0068] Steps 203-243, for each unvisited core point P, calculate all points in its Eps neighborhood;

[0069] Steps 203-244: If the number of points in the neighborhood of Eps is less than MinPts, the core point P is marked as noise;

[0070] Steps 203-245, if the number of points in the Eps neighborhood is greater than or equal to MinPts, create a new cluster C (new cluster), traverse each point Q in the Eps neighborhood of P, and for each point Q in the Eps neighborhood, calculate the Eps neighborhood of Q;

[0071] Among them, traverse each point Q in the ε neighborhood of P. If point Q has not been visited, mark it as visited, calculate the ε neighborhood of point Q, and if the number of points in the ε neighborhood of Q is greater than or equal to MinPts, add these points to the ε neighborhood of point P. If the number of points in the ε neighborhood of Q is less than MinPts, mark Q as a noise point and do not add it to the ε neighborhood of Q. Continue to judge if point Q is not a member of any cluster under the condition that the number of points in the ε neighborhood of Q is greater than or equal to MinPts. If Q is already a member of a cluster, skip it directly to avoid repeated addition. In some implementations, if Q connects two different clusters, the two clusters can be merged into a larger cluster to improve the connectivity and accuracy of the clustering.

[0072] Step 203-246: If the cluster has not changed, then increase the counter; if the counter reaches the iteration number threshold, then output the final parameters Eps and MinPts.

[0073] For example, if the iteration number threshold is 3, it means that after three consecutive iterations, if the clustering results do not change, it means that the algorithm is stable, and the cluster set and noise point set as well as the current parameters Eps and MinPts are returned.

[0074] An improved DBSCAN clustering algorithm provided in the third embodiment of the present invention uses the linear congruential method (LCM) to dynamically determine the key parameters of the algorithm, Epsilon (Eps) and Min-Points (MinPts), and generates Epsilon and MinPts through the linear congruential method, thereby eliminating the complexity of manual tuning, adapting to the characteristics of different data sets, and being able to automatically adjust the Eps and MinPts parameters without manual intervention, thereby optimizing the clustering process. Through the dynamically adjusted parameters, the present invention effectively identifies and reduces the outliers in the data set, improves the accuracy of the clustering results, and according to the specific characteristics and requirements of the data set, although the clustering effect is improved, the time complexity of the improved DBSCAN clustering algorithm is comparable to that of the traditional DBSCAN, without increasing the computational complexity. The present invention can balance the sensitivity of clustering and the processing of noise, thereby improving the overall quality of clustering, and can adapt to various different data sets, whether in scale or in dimensional changes, showing good adaptability and robustness. Compared with the DBSCAN algorithm in the prior art, the third embodiment of the present invention improves the efficiency of the clustering algorithm while keeping the time complexity basically unchanged. The method has a high degree of automation, which reduces the burden on users in parameter selection and adjustment, making it easy for even non-professionals to apply the algorithm for data analysis.

[0075] Embodiment 4:

[0076] Since the usage frequencies of different types of power supply spare parts are different, in order to avoid the shortage of frequently used spare parts during fault maintenance, it is necessary to replenish the inventory of frequently used spare parts. Therefore, after step 203-1, the following steps are specifically included:

[0077] Calculate the utilization rate of different types of power supply spare parts;

[0078] When the utilization rate of power supply spare parts is greater than a preset threshold, a prompt message is generated to increase the inventory of corresponding power supply spare parts.

[0079] In the fourth embodiment of the present invention, by calculating the utilization rate of different types of power-saving spare parts, dynamic monitoring and management of high-frequency spare parts are achieved. When it is found that the utilization rate of a certain spare part exceeds the preset threshold, the system will promptly generate an inventory replenishment reminder. This mechanism effectively prevents the problem of spare part shortage or conflict of use by multiple people, ensures that sufficient spare parts support can always be provided during fault inspection and repair, thereby improving the efficiency and reliability of equipment maintenance.

[0080] Further, as Figure 2 The specific implementation of the method, the embodiment of the present invention provides an intelligent power protection spare parts intelligent management device, such as Figure 3As shown, the device comprises:

[0081] The spare parts detection module 310 determines the type and quantity of the spare parts for power protection taken by the user through the weight sensor of each storage compartment in the spare parts cabinet for power protection;

[0082] The fault maintenance type prediction module 320 is used to predict the fault maintenance type through the fault maintenance type prediction model according to the type and quantity of power supply spare parts taken by the user;

[0083] The abnormality detection module 330 is used to determine whether the type and quantity of power supply spare parts taken by the user are abnormal according to the predicted fault maintenance type;

[0084] The prompt alarm module 340 is used to generate an alarm prompt message when it is determined that the type and quantity of power supply spare parts taken by the user are abnormal; when it is determined that the type and quantity of power supply spare parts taken by the user are normal, generate a normal prompt message.

[0085] In an embodiment of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of implementing the intelligent management method of intelligent power supply spare parts include:

[0086] The user's identity information is obtained through the camera to open the power supply spare parts cabinet;

[0087] The type and quantity of power supply spare parts taken by the user are determined through the weight sensor of each storage grid in the power supply spare parts cabinet;

[0088] According to the type and quantity of power supply spare parts used by users, the fault maintenance type is predicted through the fault maintenance type prediction model;

[0089] According to the predicted fault maintenance type, determine whether the type and quantity of power supply spare parts used by the user are abnormal;

[0090] When it is determined that the type and quantity of power supply spare parts used by the user are abnormal, an alarm prompt message is generated; when it is determined that the type and quantity of power supply spare parts used by the user are normal, a normal prompt message is generated.

[0091] In an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0092] The user's identity information is obtained through the camera to open the power supply spare parts cabinet;

[0093] The type and quantity of power supply spare parts taken by the user are determined through the weight sensor of each storage grid in the power supply spare parts cabinet;

[0094] According to the type and quantity of power supply spare parts used by users, the fault maintenance type is predicted through the fault maintenance type prediction model;

[0095] According to the predicted fault maintenance type, determine whether the type and quantity of power supply spare parts used by the user are abnormal;

[0096] When it is determined that the type and quantity of power supply spare parts used by the user are abnormal, an alarm prompt message is generated; when it is determined that the type and quantity of power supply spare parts used by the user are normal, a normal prompt message is generated.

[0097] It should be noted that the above embodiments only use common maintenance types as examples to illustrate the principles and implementation steps of the embodiments of the present invention, and do not specifically limit the actual application scenarios. Regarding the functions or steps that can be implemented by computer-readable storage media or computer devices, please refer to the above-mentioned method embodiments. To avoid repetition, they will not be described one by one here.

[0098] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0099] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0100] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An intelligent management method for intelligent power supply spare parts, characterized in that: include: The user's identity information is obtained through the camera to open the power supply spare parts cabinet; The type and quantity of power supply spare parts taken by the user are determined by the weight sensor of each storage grid in the power supply spare parts cabinet; According to the type and quantity of power supply spare parts used by users, the fault maintenance type is predicted through the fault maintenance type prediction model; According to the predicted fault maintenance type, determine whether the type and quantity of power supply spare parts used by the user are abnormal; When it is determined that the type and quantity of power supply spare parts used by the user are abnormal, an alarm prompt message is generated; when it is determined that the type and quantity of power supply spare parts used by the user are normal, a normal prompt message is generated.

2. The intelligent management method of intelligent power supply spare parts according to claim 1 is characterized in that: Before the step of predicting the fault repair type by using the fault repair type prediction model according to the type and quantity of the power supply spare parts taken by the user, the method includes: Obtain the types and quantities of power supply spare parts that users have historically used; Conduct cluster analysis on the types and quantities of power supply spare parts used by users in the past to identify the combinations of different power supply spare parts; The combinations of different power supply spare parts are associated with the fault maintenance types to generate a fault maintenance type prediction model.

3. The intelligent management method of intelligent power supply spare parts according to claim 2 is characterized in that: The steps of performing cluster analysis on the types and quantities of power supply spare parts historically used by users to identify the combinations of different power supply spare parts include: The number of power supply spare parts used in history is classified into numerical data, and the type of power supply spare parts used in history is classified into character data; The similarity of numerical data is calculated using Euclidean distance, and the similarity of character data is calculated using a string similarity algorithm based on edit distance; Determine a comprehensive distance metric between samples in a dataset; The parameters Eps and MinPts of the DBSCAN algorithm are estimated based on the comprehensive distance metric, where eps represents the scanning radius and minPts represents the minimum number of included points; Use the estimated parameter values ​​to perform DBSCAN density-based clustering analysis on the types and quantities of power supply spare parts historically used by users; Based on the clustering results, the combination patterns of the types and quantities of power supply spare parts historically used by users are identified.

4. The intelligent management method of intelligent power supply spare parts according to claim 3 is characterized in that: The step of estimating the parameters Eps and MinPts of the DBSCAN algorithm according to the comprehensive distance metric includes: Set the data set, neighborhood radius parameter Eps, minimum point number parameter MinPts, and number of iterations; Traverse each point in the data set as a core point; For each unvisited core point, calculate all points in its Eps neighborhood; If the number of points in the Eps neighborhood is less than MinPts, the core point is marked as noise; If the number of points in the Eps neighborhood is greater than or equal to MinPts, a new cluster is created. For each point Q in the Eps neighborhood, if Q has not been visited, Q is marked as visited and added to the cluster; If the cluster has not changed, the counter is increased. If the counter reaches the number of iterations, the final parameters Eps and MinPts are output.

5. The intelligent management method of intelligent power supply spare parts according to claim 3 is characterized in that: Determine the comprehensive distance measure between samples in the data set as Among them, n is the number of attributes of the sample, k is the kth attribute, ω k is the weight of the kth attribute. When the kth attribute is missing, ε k = 0, when the kth attribute is not missing ε k =1,x nk and nk The k-th attribute of sample X and sample Y is a numeric value, x ck and ck Respectively represent that the k-th attribute of sample X and sample Y is a character value.

6. The intelligent management method of intelligent power supply spare parts according to claim 1 is characterized in that: The step of generating an alarm prompt message when it is determined that the type and quantity of power-saving spare parts taken by the user are abnormal includes: When it is determined that the type and quantity of power-saving spare parts taken by the user are abnormal, the type and quantity of power-saving spare parts that may still need to be taken are displayed on the display screen of the power-saving spare parts cabinet.

7. The intelligent management method of intelligent power supply spare parts according to claim 2 is characterized in that: After the step of obtaining the types and quantities of power supply spare parts used by the user in history, the method further includes: Calculate the utilization rate of different types of power supply spare parts; When the utilization rate of power supply spare parts is greater than a preset threshold, a prompt message is generated to increase the inventory of corresponding power supply spare parts.

8. An intelligent management device for intelligent power supply spare parts, characterized in that: include: Identity authentication module, used to obtain the user's identity information through the camera to open the power supply spare parts cabinet; A spare parts detection module, which determines the type and quantity of spare parts for power protection taken by the user through the weight sensor of each storage grid in the spare parts cabinet for power protection; The fault maintenance type prediction module is used to predict the fault maintenance type through the fault maintenance type prediction model according to the type and quantity of power supply spare parts taken by the user; The abnormality detection module is used to determine whether the type and quantity of power supply spare parts taken by the user are abnormal according to the predicted fault maintenance type; The prompt alarm module is used to generate an alarm prompt message when it is determined that the type and quantity of power supply spare parts taken by the user are abnormal; when it is determined that the type and quantity of power supply spare parts taken by the user are normal, it generates a normal prompt message.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent management method of intelligent power supply spare parts as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the intelligent management method of intelligent power supply spare parts as claimed in any one of claims 1 to 7 are implemented.

Images