A method for processing intelligent procurement data of power equipment and materials

Abstract

The present disclosure relates to the field of power equipment procurement analysis, and more specifically, to a method for processing smart procurement data of power equipment and materials. The data collection and monitoring effects of the target power equipment are realized through the acquisition module and the monitoring module, and the inventory, use and loss of the power equipment and materials can be accurately grasped. Therefore, when the procurement data and procurement plan are generated in the later stage, it can better fit the actual use and loss of the enterprise's power materials. In addition, the working status and working time of the target power equipment under normal conditions are predicted through the prediction module and the big data model of the same industry, and the loss replacement amount and inventory remaining amount of the target power equipment are predicted in combination with the workload and working environment of the target power equipment. In the form of a first chart and a second chart, the relevant data can be better and more intuitively seen to see the procurement data, thereby achieving the effect of finding abnormal target equipment and materials when formulating a procurement plan based on the procurement data.

Description

Technical Field

[0001] The present disclosure relates to the field of power equipment procurement analysis, and more specifically, to a method for processing power equipment material intelligent procurement data. Background Art

[0002] With the continuous development of power companies, the control, use and reasonable procurement of power equipment and materials have become important tasks for enterprises. Although the traditional project procurement model is simple, fast, convenient and flexible, the types and varieties of power equipment and materials are numerous, and the loss during use will inevitably affect the subsequent procurement plans if the values ​​cannot be updated in time. In addition, in order to complete the entire routine procurement, the existing material procurement requires a lot of research, and each link requires direct participation of staff, and manual participation has a greater influence on the generation of procurement plans.

[0003] In addition, although digital production has become a common business model since the advent of the Fourth Industrial Revolution, and many power companies have kept pace with the times, the massive amount of data on power equipment and materials is bound to bring challenges to the efficiency of data processing. At the same time, due to the digital business model, various data in the same industry are actually made public, so the procurement data and procurement plans generated by this are difficult to fit the actual use and loss of the company's power materials, which in turn leads to large errors in the generated procurement data. Therefore, we propose a method for processing smart procurement data of power equipment and materials. Summary of the invention

[0004] In view of this, the embodiment of the present application at least provides a method for processing power equipment material intelligent procurement data, the method comprising the following steps:

[0005] Step S1, the acquisition module acquires the data related to the power equipment and materials generated by the input device, the data input by the user to the input device includes the actual use parameter CGsy, loss parameter CGsh, and equipment parameter CGkc of the power equipment and materials in different time periods t, the input device transmits the data related to the power equipment and materials to the output device, and the output device generates the inventory parameter KCmx;

[0006] Step S2, the monitoring module monitors the power equipment and materials through the monitoring device to obtain the power equipment and materials monitoring data, the power equipment and materials monitoring data includes the use parameter JKsy, shutdown parameter JKgt, and operation status parameter JKyx of the power equipment in different time periods t, the input device transmits the monitoring data to the output device, and the output device generates the monitoring parameter JKmx;

[0007] Step S3, the artificial intelligence model obtains the inventory parameter KCmx and the monitoring parameter JKmx. The artificial intelligence model analyzes and compares the inventory parameter KCmx and the monitoring parameter JKmx and generates power equipment material data, which is imported into the discrete model. The display device receives the power equipment material data discrete model and processes it to generate the first chart;

[0008] Step S4, the prediction module obtains the power equipment material data discrete model. The prediction module predicts the power equipment material-related data of the target power equipment at different time periods t according to the big data model. The prediction module predicts and generates the usage parameter YCsy, the loss parameter YCsh, and the equipment parameter YCkc. The input device transmits the power equipment material-related data to the output device, and the output device generates the prediction parameter YCmx;

[0009] Step S5, the power equipment material data discrete model is compared with the big data model to generate the usage parameter YCsy, the loss parameter YCsh, and the equipment parameter YCkc. The display device receives the model comparison result and generates the second chart;

[0010] The first chart is the real data chart of the target power equipment at different time periods t, and the second chart is the difference chart obtained by comparing the predicted analysis data with the real data at different time periods t.

[0011] According to an example of the embodiment of the present disclosure, the acquisition module acquires the manufacturer, quality, and quantity of the target power equipment materials. The calculation formula of the inventory parameter KCmx is:

[0012]

[0013] In the formula, a and b respectively represent the weight values of the usage parameter CGsy and the loss parameter CGsh, where c is the weight value of the equipment parameter CGkc, and 0 < a < 1, 0 < b < 1, 0 < c < 1. X represents the correction factor, which is a constant, and the specific data of a, b, c, and X are set according to actual needs;

[0014] The usage parameter CGsy plus the loss parameter CGsh divided by the equipment parameter CGkc constitutes the inventory parameter KCmx.

[0015] According to an example of the embodiment of the present disclosure, the monitoring module monitors the working status, time, load of the target power equipment, as well as the loss replacement amount and inventory remaining amount of the target power equipment. The calculation formula of the monitoring parameter JKmx is:

[0016]

[0017] Where: d and e respectively represent the weight values for shutting down parameter JKgt using parameter JKsy, and 0 < d < 1, 0 < e < 1. Y represents a correction factor, which is a constant, and the specific values of d, e, and Y are set according to actual requirements;

[0018] Subtract the shutdown parameter JKgt multiplied by the operating status parameter JKyx from the usage parameter JKsy to obtain the monitoring parameter JKmx. The monitoring data of the monitoring parameter JKmx is the data of the target power equipment that is operating, namely the operating quantity, operating time, and operating power.

[0019] According to an example of the embodiment of the present disclosure, wherein, the calculation formula of the discrete model of power equipment material data is:

[0020]

[0021] Where LXmx is the discrete model of power equipment material data, SL is the total quantity of power equipment materials, and SL is a constant, and the specific data is set according to actual requirements.

[0022] According to an example of the embodiment of the present disclosure, wherein, the prediction module predicts the normal working state and working time of the target power equipment based on the big data model, and predicts the loss replacement quantity and remaining inventory quantity of the target power equipment in combination with the working load and working environment of the target power equipment.

[0023] According to an example of the embodiment of the present disclosure, wherein, for the chart generated by the display device, the x-axis is the inventory parameter KCmx, the y-axis is the prediction parameter YCmx, and the z-axis is the monitoring parameter JKmx. Different coordinate points corresponding to different time periods t are displayed according to the input data of different time periods t. Observe the distribution and discrete state of the coordinate points, and then connect each coordinate point in the form of plotting points. Observe the area formed by the connection of the coordinate points. This area is the threshold range of the target power equipment.

[0024] According to an example of the embodiment of the present disclosure, wherein, the display device finds the two points with the largest difference according to the threshold range of the target power equipment, observes the sub-data corresponding to the inventory model, prediction analysis model, and monitoring model at these two points respectively, and then obtains the location of the abnormal data and the state of the target power equipment of the abnormal data.

[0025] According to an example of an embodiment of the present disclosure, the display device displays the location of abnormal data, and compares the data obtained by the predictive analysis model of the abnormal data with the data obtained by the inventory model at the same time t, and compares the obtained comparison data with the data obtained by the monitoring model on the same target power equipment at the same time t to verify the difference value Cz. If the difference value Cz is less than the threshold value Qz of the target power equipment, it means that the error is within a reasonable range, otherwise it is not.

[0026] According to an example of an embodiment of the present disclosure, the threshold Qz of the target power equipment and the threshold value of the target power equipment are empirical values ​​set for various types of power equipment in the artificial intelligence model, and different empirical values ​​are set for different target power equipment.

[0027] This application at least includes the following beneficial effects:

[0028] 1. The present application provides a method for processing intelligent procurement data of electric power equipment and materials. The acquisition module and the monitoring module are used to collect and monitor the data of the target electric power equipment, and the inventory, use, and loss of the electric power equipment and materials can be accurately grasped. Therefore, when generating procurement data and procurement plans in the later stage, it can better fit the actual use and loss of the enterprise's electric power materials. In addition, the prediction module and the big data model of the same industry are used to predict the working status and working time of the target electric power equipment under normal conditions, and the workload and working environment of the target electric power equipment are combined to predict the loss replacement amount and inventory remaining amount of the target electric power equipment. Then, the artificial intelligence model is used to generate a discrete model, and the relevant data is in the form of a first chart and a second chart, so that the procurement data can be better and more intuitively seen. By establishing a coordinate system with the x-axis as the inventory parameter KCmx, the y-axis as the prediction parameter YCmx, and the z-axis as the monitoring parameter JKmx, abnormal data points can be found, thereby achieving the effect of finding abnormal target equipment and materials when formulating a procurement plan based on procurement data.

[0029] 2. The present application provides a method for processing data of intelligent procurement of power equipment and materials, which is verified by the monitoring data of the monitoring module and compared with the data predicted by the big data model of power equipment in the same industry. It can not only reduce the error value of the data, but also infer the quality of the target power equipment, etc. The quality calculation can be carried out not only from the comparison of macro inventory parameters, monitoring parameters, and prediction parameters, but also from the usage parameters, loss parameters, operating status parameters, and shutdown parameters of its micro components and the predicted usage parameters, loss parameters, and equipment parameters, so as to achieve the effect of detecting the quality of the target power equipment.

[0030] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and other purposes, features and advantages of the embodiments of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0032] Figure 1 A method for processing intelligent procurement data of power equipment materials is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0034] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application is further elaborated in detail below in conjunction with the accompanying drawings and embodiments. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the following description, it is related to "optional implementation method", which describes a subset of all possible embodiments, but it can be understood that the "optional implementation method" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The term "first / second" involved is only to distinguish similar objects, and does not represent a specific order for the object. It can be understood that "first / second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of the present application. The terms used herein are only for the purpose of describing the present application and are not intended to limit the present application.

[0035] The first embodiment of the present application provides a method for processing power equipment material intelligent procurement data, the method comprising the following steps:

[0036] Step S1, the acquisition module obtains the data related to the materials of power equipment generated by the input device. The data input by the user through the input device includes the actual usage parameters CGsy, loss parameters CGsh, and equipment parameters CGkc of the power equipment materials at different time periods t. The input device transmits the data related to the power equipment materials to the output device, and the output device generates the inventory parameter KCmx;

[0037] The acquisition module collects the manufacturer, quality, and quantity of the target power equipment materials. The calculation formula for the inventory parameter KCmx is:

[0038]

[0039] In the formula, a and b respectively represent the weight values of the usage parameter CGsy and the loss parameter CGsh, c represents the weight value of the equipment parameter CGkc, and 0 < a < 1, 0 < b < 1, 0 < c < 1. X represents the correction factor, which is a constant, and the specific data of a, b, c, and X are set according to actual needs;

[0040] The usage parameter CGsy plus the loss parameter CGsh divided by the equipment parameter CGkc constitutes the inventory parameter KCmx;

[0041] The acquisition module is used to collect the manufacturer, quality, and quantity of the target power equipment materials, combined with the data input by the user through the input device, including the actual usage parameters CGsy, loss parameters CGsh, and equipment parameters CGkc of the power equipment materials at different time periods t. The input device transmits the data related to the power equipment materials to the output device, and the output device generates the inventory parameter KCmx. At this time, since the actual usage parameters CGsy, loss parameters CGsh, and equipment parameters CGkc of the power equipment are completed by the user according to the daily material statistics plan and material statistics analysis formulated by the power equipment enterprise, there are certain errors, but the data authenticity is reliable. Then the above data will be recorded and saved by the input device, and the input device is a networked storage medium.

[0042] It should be noted that the daily material statistics plan is formulated manually according to the production and operation status of the enterprise, which is an existing technology and will not be elaborated here;

[0043] Material statistics analysis is the final stage of material statistics work and an important part of the material statistics work process; Material statistics analysis is to use the principles and methods of statistical analysis, based on statistical data, starting from the analysis of quantity and price, to analyze and summarize the experience, lessons, and development laws of the material supply and material use processes, in order to facilitate the discovery of problems and find solutions. It includes:

[0044] (1) Group analysis method

[0045] This method is based on the research purpose. According to the selected criteria, statistical data is divided into several different groups, so that there are obvious differences between groups, while the units within the same group have relative homogeneity. Using the grouping method to anatomize things is of great significance. By grouping to divide types and the various components with different natures, the quantitative characteristics of each group can be reflected, the internal structure and essence of things can be revealed, and the interdependent relationship between things can be studied.

[0046] (2) Comparative analysis method

[0047] This method is to compare various statistical data with similar indicators, analyze the differences between things, and understand the essence of things. Before statistical figures are compared, it is difficult to fully explain the problem, and it is impossible to make specific judgments based on a single absolute number. Only through comparison can the gaps and weak links be found and the potential of the enterprise be tapped.

[0048] Step S2, the monitoring module monitors power equipment materials through monitoring devices to obtain power equipment material monitoring data. The power equipment material monitoring data includes the usage parameters JKsy, shutdown parameters JKgt, and operating status parameters JKyx of power equipment at different time periods t. The input device transmits the monitoring data to the output device, and the output device generates monitoring parameters JKmx;

[0049] The monitoring module monitors the working status, time, load of the target power equipment, as well as the loss replacement quantity and inventory remaining quantity of the target power equipment. The calculation formula for the monitoring parameter JKmx is:

[0050]

[0051] In the formula: d and e respectively represent the weight values of the usage parameter JKsy and the shutdown parameter JKgt, and 0 < d < 1, 0 < e < 1. Y represents a correction factor, which is a constant, and the specific data of d, e, and Y are set according to actual needs;

[0052] The usage parameter JKsy minus the shutdown parameter JKgt multiplied by the operating status parameter JKyx yields the monitoring parameter JKmx. The monitoring data of the monitoring parameter JKmx is the data of the target power equipment that is running, that is, the running quantity, running time, and running power;

[0053] The monitoring module mainly includes front-end acquisition equipment, signal transmission equipment, control equipment, display equipment, and video storage equipment.

[0054] The front-end acquisition equipment mainly includes security monitoring cameras and related equipment, which are responsible for obtaining video signals, images, voices, alarms, and status information. It can monitor the operating status of the target power equipment during operation, so as to facilitate comparison and analysis when searching for abnormal data in the later stage.

[0055] The signal transmission equipment is used to transmit the signals, control signals and status signals collected by the front end to the monitoring system, supports analog transmission and digital transmission methods, and then generates the usage parameters JKsy, shutdown parameters JKgt, and operating status parameters JKyx of the power equipment in different time periods t, where the operating status parameters JKyx include the parameters of the target power equipment in the usage and shutdown states.

[0056] The core functions of the control equipment include audio and video signal switching and distribution, pan / tilt (PTZ) control, resource allocation, etc., which are completed through operating keyboards and controlling communication interface conversion devices.

[0057] The display device outputs the video signal to terminal devices such as monitors, LCD displays, and projectors for display, and supports digital and analog display modes.

[0058] Video storage devices are responsible for storing and playing back digital video signals, including hard disk video recorders (DVRs), network hard disk video recorders (NVRs) and network storage devices. The storage solution is adjusted according to the size of the system.

[0059] Step S3, the artificial intelligence model obtains inventory parameters KCmx and monitoring parameters JKmx, analyzes and compares the inventory parameters KCmx and monitoring parameters JKmx, and generates power equipment material data and imports them into the discrete model. The display device receives the discrete model of power equipment material data and processes it to generate a first chart.

[0060] The calculation formula of the discrete model of power equipment material data is:

[0061]

[0062] Where LXmx is the discrete model of power equipment and materials data, SL is the total number of power equipment and materials, and SL is a constant. The specific data is set according to actual needs;

[0063] The working principle of the artificial intelligence model and the discrete model: The initial feature reinforcement neural network includes an initial data set feature extraction layer and an initial reinforcement factor feature extraction layer. The initial data set feature extraction layer is debugged by comparing the error generated by the monitoring parameter JKmx with the inventory parameter KCmx to obtain the debugged data set feature extraction layer. After obtaining the data set feature extraction layer, the multi-level target power state training representation vector of the target power equipment Internet of Things training data set is extracted based on the data set feature extraction layer, and the reinforcement factor training representation vector of the reinforcement factor training data set is extracted through the initial reinforcement factor feature extraction layer. For each level of the multi-level, according to the target power state training representation vector and the reinforcement factor training representation vector of the corresponding level, the template training representation vector under the corresponding level is embedded and mapped to obtain the multi-level training data set representation vector, and the multi-level training data set representation vector is analyzed at multiple levels to obtain the estimated feature reinforcement data set. The feature reinforcement error between the estimated feature reinforcement data set and the annotated feature reinforcement data set is determined, and the initial reinforcement factor feature extraction layer is debugged by the target power equipment error to obtain a feature reinforcement neural network including the data set feature extraction layer and the reinforcement factor feature extraction layer.

[0064] In the embodiment of the present application, the initial data set feature extraction layer is debugged through the production state error to obtain the data set feature extraction layer, and then the initial reinforcement factor feature extraction layer is debugged after the data set feature extraction layer is debugged. The two network layers are debugged independently of each other, and the multi-level target power equipment state training representation vector is extracted through the data set feature extraction layer. For each level of the multi-level, the template training representation vector under the corresponding level is embedded and mapped according to the production state training representation vector and the reinforcement factor training representation vector of the corresponding level to obtain the multi-level training data set representation vector, and the multi-level training data set representation vector is parsed at multi-level to obtain the estimated feature reinforcement data set, and the estimated feature reinforcement data set is determined. The feature enhancement error between the dataset and the annotated feature enhancement dataset is optimized, and the initial enhancement factor feature extraction layer is debugged through the production state error to obtain a feature enhancement neural network including the dataset feature extraction layer and the enhancement factor feature extraction layer, so that the debugged dataset feature extraction layer and the enhancement factor feature extraction layer are not involved with each other, so that when the feature enhancement neural network is applied, the dataset feature extraction layer can be called independently to generate a feature enhancement dataset with production status and random enhancement features. When the joint enhancement factor feature extraction layer is used, the set feature enhancement result information can be combined to accurately construct a feature enhancement dataset with production status and predetermined feature enhancement, so that the feature enhancement neural network can be applied to various usage environments.

[0065] The initial feature enhancement neural network is debugged by the estimated feature enhancement data set and the annotated feature enhancement data set to obtain the feature enhancement neural network, including: determining the target power equipment state error between the target power equipment state of the estimated feature enhancement data set and the target power equipment state of the annotated feature enhancement data set; determining the feature enhancement error between the feature enhancement result of the estimated feature enhancement data set and the feature enhancement result of the annotated feature enhancement data set; debugging the initial feature enhancement neural network based on the target power equipment state error and the feature enhancement error to obtain the feature enhancement neural network.

[0066] For example, the target power equipment state error between the target power equipment state of the estimated feature enhancement data set and the target power equipment state of the annotated feature enhancement data set is calculated, and the feature enhancement error between the feature enhancement result of the estimated feature enhancement data set and the feature enhancement result of the annotated feature enhancement data set is determined. The target error is determined based on the production state error and the feature enhancement error, and the parameters of the initial feature enhancement neural network are optimized through the target error. Then, the parameters are repeatedly adjusted until the convergence requirements are met to obtain the feature enhancement neural network.

[0067] Embodiment 2 of the present application specifically includes the following steps:

[0068] Step S4, the prediction module obtains the discrete model of the power equipment material data, and the prediction module predicts the power equipment material related data of the target power equipment in different time periods t according to the big data model. The prediction module generates the use parameter YCsy, the loss parameter YCsh, and the equipment parameter YCkc according to the big data model prediction, and the input device transmits the power equipment material related data to the output device, and the output device generates the prediction parameter YCmx;

[0069] Step S5, the power equipment material data discrete model is compared with the big data model using the parameters YCsy, the loss parameter YCsh, and the equipment parameter YCkc, and the display device receives the model comparison result and generates a second chart based on it;

[0070] The first chart is a chart of real data of the target power equipment in different time periods t, and the second chart is a chart of differences between the predicted analysis data and the real data in different time periods t;

[0071] The prediction module predicts the normal working status and working time of the target power equipment based on the big data model, and combines the workload and working environment of the target power equipment to predict the loss replacement amount and inventory remaining amount of the target power equipment.

[0072] The display device generates a chart with the x-axis representing the inventory parameter KCmx, the y-axis representing the forecast parameter YCmx, and the z-axis representing the monitoring parameter JKmx. The chart displays the different coordinate points corresponding to different time periods t based on the input data of different time periods t, observes the discrete distribution state of the coordinate points, and then connects the coordinate points in the form of plotting points, and observes the area formed by the connection of the coordinate points. This area is the threshold range of the target power equipment.

[0073] The display device finds the two points with the largest difference according to the threshold range of the target power equipment, observes the corresponding sub-data in the inventory model, forecasting analysis model, and monitoring model of the two points at this time, and then obtains the location of the abnormal data and the status of the target power equipment of the abnormal data.

[0074] The display device shows the location of the abnormal data, and compares the data obtained by the prediction analysis model of the abnormal data with the data obtained by the inventory model at the same time t. The obtained comparison data is compared with the data obtained by the monitoring model on the same target power equipment at the same time t to verify the difference value Cz. If the difference value Cz is less than the threshold value Qz of the target power equipment, it means that the error is within a reasonable range, otherwise it is not.

[0075] The threshold Qz of the target power equipment and the threshold value of the target power equipment are based on the empirical values ​​set for various types of power equipment in the artificial intelligence model, and the empirical values ​​set for different target power equipment are different.

[0076] It should be noted that the object information (including but not limited to the object's device information, corresponding personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0077] 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 the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0078] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above-mentioned embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of this application. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several deformations and improvements can be made, which all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be based on the attached claims.

Claims

1. A method for processing power equipment material intelligent procurement data, characterized in that: The method includes the following steps: Step S1, the acquisition module obtains the data related to power equipment materials generated by the input device. The data input by the user through the input device includes the actual usage parameters CGsy, loss parameters CGsh, and equipment parameters CGkc of power equipment materials at different time periods t. The input device transmits the data related to power equipment materials to the output device, and the output device generates inventory parameters KCmx; Step S2, the monitoring module monitors the power equipment materials through the monitoring device to obtain the monitoring data of power equipment materials. The monitoring data of power equipment materials includes the usage parameters JKSy, shutdown parameters JKgt, and operating status parameters JKy x of power equipment at different time periods t. The input device transmits the monitoring data to the output device, and the output device generates monitoring parameters JKmx; Step S3, the artificial intelligence model obtains the inventory parameters KCmx and the monitoring parameters JKmx. The artificial intelligence model analyzes and compares the inventory parameters KCmx and the monitoring parameters JKmx and generates the data of power equipment materials and imports them into the discrete model. The display device receives the discrete model of the data of power equipment materials and processes it to generate the first chart; Step S4, the prediction module obtains the discrete model of the data of power equipment materials. The prediction module predicts the data related to power equipment materials of the target power equipment at different time periods t according to the big data model. The prediction module predicts and generates the usage parameters YCsy, loss parameters YCsh, and equipment parameters YCkc according to the big data model. The input device transmits the data related to power equipment materials to the output device, and the output device generates prediction parameters YCmx; Step S5, the discrete model of the data of power equipment materials and the big data model generate the usage parameters YCsy, loss parameters YCsh, and equipment parameters YCkc for comparison. The display device receives the result of the model comparison and generates the second chart; The first chart is a chart of the real data of the target power equipment at different time periods t, and the second chart is a difference chart obtained by comparing the predicted analysis data with the real data at different time periods t; The acquisition module collects the manufacturer, quality, and quantity of the target power equipment materials. The calculation formula for the inventory parameter KCmx is: In the formula, a and b respectively represent the weight values of the usage parameter CGsy and the loss parameter CGsh, where c is the weight value of the equipment parameter CGkc, and 0 < a < 1, 0 < b < 1, 0 < c < 1. X represents a correction factor, which is a constant, and the specific data of a, b, c, and X are set according to actual needs; The usage parameter CGsy plus the loss parameter CGsh divided by the equipment parameter CGkc constitutes the inventory parameter KCmx; The monitoring module monitors the working status, time, load of the target power equipment, as well as the loss replacement amount and remaining inventory of the target power equipment. The calculation formula for the monitoring parameter JKmx is: Where: d and e respectively represent the weight values for shutting down parameter JKgt using parameter JKsy, and 0 < d < 1, 0 < e < 1. Y represents a correction factor, which is a constant, and the specific values of d, e, and Y are set according to actual requirements; Subtract the shutdown parameter JKgt multiplied by the operating status parameter JKyx from the parameter JKsy to obtain the monitoring parameter JKmx. The monitoring data of the monitoring parameter JKmx is the data of the target power equipment that is operating, namely the operating quantity, operating time, and operating power; The acquisition module and the monitoring module are data modules based on the Internet of Things. The target power equipment they acquire and monitor is connected to the network to achieve the real-time update function of relevant data; The calculation formula for the discrete model of power equipment material data is: Where LXmx is the discrete model of power equipment material data, SL is the total quantity of power equipment materials, and SL is a constant, and the specific data is set according to actual requirements.

2. A method for processing power equipment material intelligent procurement data according to claim 1, characterized in that: The prediction module predicts the normal working state and working time of the target power equipment according to the big data model, and combines the working load and working environment of the target power equipment to predict the loss replacement quantity and the remaining inventory quantity of the target power equipment.

3. A method for processing power equipment material intelligent procurement data according to claim 1, characterized in that: For the chart generated by the display device, its x-axis is the inventory parameter KCmx, y-axis is the prediction parameter YCmx, and z-axis is the monitoring parameter JKmx. According to the data input in different time periods t, different coordinate points corresponding to different time periods t are displayed. Observe the discrete state of the distribution of the coordinate points, and then connect each coordinate point in the form of plotting points. Observe the area formed by the connection of the coordinate points. This area is the threshold range of the target power equipment.

4. A method for processing power equipment material intelligent procurement data according to claim 3, characterized in that: The display device finds the two points with the largest difference according to the threshold range of the target power equipment, observes the sub-data corresponding to the inventory model, prediction analysis model, and monitoring model at these two points at this time, and then obtains the location of the abnormal data and the state of the target power equipment of the abnormal data.

5. A method for processing power equipment material intelligent procurement data according to claim 4, characterized in that: The display device displays the location of the abnormal data, and compares the data obtained from the prediction analysis model of this abnormal data with the data obtained from the inventory model at the same time t. The obtained comparison data is compared and verified with the data obtained from the monitoring model of the same target power equipment at the same time t to obtain the difference value Cz. If the difference value Cz is less than the threshold Qz of this target power equipment, it means that the error is within a reasonable range, otherwise it is not.

6. A method for processing power equipment material intelligent procurement data according to claim 5, characterized in that: The threshold Qz of the target power equipment and the threshold of the target power equipment are empirical values set according to various power equipment in the artificial intelligence model. The empirical values set for different target power equipment are different.

Images