Equipment reliability analysis method and system based on data fusion and evidence network

Abstract

The application relates to the field of equipment reliability engineering technology, and relates to an equipment reliability analysis method and system based on data fusion and an evidence network, which comprises the following steps: obtaining a multi-source numerical set based on a multi-source data set, obtaining an initial probability set based on the multi-source numerical set, obtaining a first normal evaluation value and a first failure evaluation value by using the initial probability set and a pre-constructed evidence network model; obtaining a weight factor based on a first initial history set, a second initial history set, a first initial experiment set and a second initial experiment set, obtaining a second normal evaluation value and a second failure evaluation value based on the weight factor, obtaining a comprehensive normal evaluation value based on the first normal evaluation value and the second normal evaluation value, obtaining a comprehensive failure evaluation value based on the first failure evaluation value and the second failure evaluation value, and obtaining a reliability evaluation state of equipment by using the comprehensive normal evaluation value and the comprehensive failure evaluation value. The application can improve the accuracy and reliability of equipment reliability analysis.

Description

Technical Field

[0001] This invention relates to the field of equipment reliability engineering technology, and in particular to an equipment reliability analysis method and system based on data fusion and evidence networks. Background Technology

[0002] Equipment reliability is a key indicator for measuring its performance and quality, directly affecting its operating costs and maintenance difficulty. Therefore, equipment reliability analysis is an indispensable and crucial part of equipment lifecycle management, and improving equipment reliability is a vital guarantee for ensuring that equipment performs its intended functions under specified conditions and within a specified timeframe.

[0003] Currently, reliability analysis of equipment often employs a single analysis method. However, single analysis methods have drawbacks such as limitations, low accuracy, poor adaptability, and difficulty in comprehensive evaluation.

[0004] While the methods described above can perform reliability analysis on equipment, they suffer from limitations and low accuracy due to their reliance on a single analytical approach. Therefore, the accuracy and reliability of equipment reliability analysis need to be improved. Summary of the Invention

[0005] This invention provides a method for equipment reliability analysis based on data fusion and evidence networks, and a computer-readable storage medium, the main purpose of which is to improve the accuracy and reliability of equipment reliability analysis.

[0006] To achieve the above objectives, this invention provides an equipment reliability analysis method based on data fusion and evidence networks, comprising: Receive a reliability analysis command, and obtain a multi-source dataset of the equipment based on the reliability analysis command. The multi-source dataset includes multiple multi-source data, wherein the multi-source data are historical data or experimental data with detection time. Obtain multi-source numerical sets based on multi-source datasets; The first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are obtained based on multi-source numerical sets. Using a pre-constructed fitted coordinate system, the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are selected respectively to obtain the first history set, the second history set, the first experiment set, and the second experiment set; An initial probability set is obtained based on the first historical set, the second historical set, the first experimental set, and the second experimental set. The initial probability set includes four initial probabilities, which are: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. The four initial probabilities in the initial probability set are all input into the pre-constructed evidence network model to obtain the first normal evaluation value and the first fault evaluation value. Weighting factors are obtained based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set. The weighting factors include historical weighting factors and experimental weighting factors. The second normal evaluation value and the second failure evaluation value are obtained based on the historical weighting factor, the experimental weighting factor, and the pre-constructed reliability evaluation formula. The average of the first and second normal assessment values ​​is calculated to obtain the comprehensive normal assessment value. A comprehensive fault assessment value is obtained based on the first fault assessment value and the second fault assessment value. The reliability assessment status of the equipment is obtained using the comprehensive normal assessment value and the comprehensive fault assessment value. The reliability assessment status is either the normal state of the equipment or the fault state of the equipment.

[0007] Optionally, obtaining the multi-source numerical set based on the multi-source dataset includes: Perform the following operation on each multi-source dataset: Identify the data types of the multi-source data in the multi-source dataset. If the data type of the multi-source data is numerical, then confirm the multi-source data as multi-source numerical data, summarize the multi-source numerical data, and obtain the multi-source numerical set.

[0008] Optionally, obtaining the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set based on multi-source data sets includes: Using a preset first partitioning identifier, the multi-source values ​​in the multi-source value set are identified as initial historical values ​​or initial experimental values. The initial historical values ​​and initial experimental values ​​are then summarized to obtain the historical value set and the experimental value set. Using a preset second partitioning identifier, the initial historical values ​​in the historical value set are identified as either the initial historical first value or the initial historical second value. The initial historical first value and the initial historical second value are then summarized to obtain the first initial historical set and the second initial historical set. Using a preset third partitioning identifier, the initial experimental values ​​in the experimental value set are identified as the first initial experimental value or the second initial experimental value. The first initial experimental value and the second initial experimental value are then summarized to obtain the first initial experimental set and the second initial experimental set.

[0009] Optionally, the step of using a pre-constructed fitted coordinate system to filter the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set to obtain the first history set, the second history set, the first experiment set, and the second experiment set includes: Sort the initial history values ​​in the first initial history set in ascending order to obtain the initial history sequence; The first initial historical value is extracted sequentially from the initial historical sequence, and the following operations are performed on the extracted first initial historical value: Using the extracted initial historical first value, the initial position is determined in the initial historical sequence. The extracted initial historical first value and the initial position are associated to obtain the fitted coordinate points. The fitted coordinate points are then summarized to obtain the fitted coordinate point set. A coordinate system is constructed with the initial position as the x-axis and the initial historical first value as the y-axis. All the fitted coordinate points in the fitted coordinate point set are mapped to the coordinate system to obtain the mapped coordinate point set. The first initial historical value is extracted sequentially from the initial historical sequence, and the following operation is performed on each extracted first initial historical value: Based on the extracted initial historical first value, a target historical first value is identified in the initial historical sequence, wherein the target historical first value is adjacent to and lags behind the extracted initial historical first value. Based on the initial historical first value and the target historical first value, the initial mapping coordinate point and the target mapping coordinate point are identified in the set of mapping coordinate points. Connect the initial mapped coordinate point and the target mapped coordinate point to obtain a polyline segment. Use the target historical first value as the extracted initial historical first value, and return to the step of confirming the target historical first value in the initial historical sequence based on the extracted initial historical first value. Summarize the polyline segments to obtain multiple polyline segments. Perform the following operation on each of the multiple polyline segments: Obtain the slope of the line segment, get the evaluation slope, and determine whether the evaluation slope is zero; If the slope is zero, then either of the two fitted coordinate points corresponding to the broken line segment will be marked as a repeated coordinate point. Remove the initial historical first value corresponding to duplicate coordinate points from the initial historical sequence to obtain the updated historical sequence. Use the updated historical sequence as the initial historical sequence and return to the step of extracting the initial historical first value from the initial historical sequence in sequence until the evaluation slope is not zero. Use the initial historical first value in the updated historical sequence as the first historical set. The second initial history set, the first initial experiment set, and the second initial experiment set are obtained using the second initial history set, the first initial experiment set, and the second initial experiment set, respectively.

[0010] Optionally, obtaining the initial probability set based on the first history set, the second history set, the first experimental set, and the second experimental set includes: Extract the initial historical first value sequentially from the first historical set, and perform the following operation on each extracted initial historical first value: Based on the detection time corresponding to the extracted initial historical first value, a search is performed in the second historical set. If there is a detection time in the second historical set that is the same as the detection time corresponding to the initial historical second value, then the initial historical first value and the initial historical second value are associated to obtain historical value nodes. The historical value nodes are then summarized to obtain a set of historical value nodes. Obtain the first reference value and the second reference value when the equipment is in normal state; obtain the first reference half-axis based on the first reference value; obtain the second reference half-axis based on the second reference value. The first reference value is associated with the second reference value to obtain the fitting center coordinate point. The fitting center coordinate point, the first reference half-axis, the pre-constructed reference coordinate system and the second reference half-axis are used to construct a reference region. All historical numerical nodes in the historical numerical node set are mapped to the reference coordinate system to obtain the discrimination coordinate node set. The discrimination coordinate node set includes multiple discrimination coordinate nodes and the discrimination coordinate nodes correspond one-to-one with the historical numerical nodes. Based on the reference area and the set of discriminant coordinate nodes, a set of qualified historical data nodes is identified, wherein the set of qualified historical data nodes includes multiple qualified historical nodes, and the qualified historical nodes are located within the reference area. A set of discriminative historical numerical nodes is obtained using the first initial history set and the second initial history set, wherein the set of discriminative historical numerical nodes includes multiple discriminative historical numerical nodes; Based on the qualified historical value node set, a target historical value node set is identified in the discrimination historical value node set, wherein the target historical value node set includes multiple target historical value nodes. The number of target historical data nodes in the target historical data node set and the number of discriminative historical data nodes in the discrimination historical data node set are counted separately to obtain the number of qualified historical data nodes and the total number of historical data nodes. The ratio of the number of qualified historical data nodes to the total number of historical data nodes is calculated to obtain the historical ratio value. The historical ratio value is used to determine the historical normal probability and historical failure probability corresponding to the historical data set, where the historical normal probability and historical failure probability are respectively: ; ; in, Indicates the normal probability in history. This represents the initial ratio value. Indicates the probability of historical failures; The normal experimental probability and the experimental failure probability are obtained based on the first experimental set, the second experimental set, the first initial experimental set, the second initial experimental set, and the reference region, wherein the normal experimental probability and the experimental failure probability are respectively: ; ; in, Indicates the normal probability of the experiment. Indicates the experimental ratio value. Indicates the probability of experimental failure; By summarizing the historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability, an initial probability set is obtained.

[0011] Optionally, the reference area is as follows: ; in, Indicates the first reference value. Indicates the second reference value. Indicates the first reference half-axis, Indicates the second reference half-axis. Represents the x-coordinate of the reference coordinate system. This represents the ordinate of the reference coordinate system.

[0012] Optionally, obtaining the weighting factors based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set includes: The first historical weight and the first experimental weight are obtained based on the first initial historical set, the first initial experimental set, the first reference value, and the pre-constructed entropy weight method. The second historical weight and the second experimental weight are obtained based on the second initial historical set, the second initial experimental set, the second reference value, and the entropy weight method. Calculate the mean of the first historical weight and the second historical weight to obtain the historical weight factor. Calculate the mean of the first experimental weight and the second experimental weight to obtain the experimental weight factor.

[0013] Optionally, the reliability evaluation formula is as follows: ; ; in, This indicates the second normal assessment value. Represents historical weighting factors. Indicates the experimental weighting factor. This indicates the second fault assessment value.

[0014] Optionally, obtaining the equipment's reliability assessment status using a combination of normal performance evaluation values ​​and a combination of failure evaluation values ​​includes: Compare the overall normal assessment value with the preset normal assessment threshold: If the comprehensive normal assessment value is greater than or equal to the normal assessment threshold, the equipment reliability assessment status is determined to be the normal equipment status. If the overall normal assessment value is less than the normal assessment threshold, and the overall fault assessment value is less than or equal to the preset fault assessment threshold, then the equipment's reliability assessment status is determined to be an equipment fault status.

[0015] To achieve the above objectives, the present invention also provides an equipment reliability analysis system based on data fusion and evidence networks, comprising: The data acquisition and preprocessing module is used to receive reliability analysis instructions and acquire multi-source datasets of the equipment based on the reliability analysis instructions. The multi-source datasets include multiple multi-source data, wherein the multi-source data are historical data or experimental data with detection time. Obtain multi-source numerical sets based on multi-source datasets; The data filtering module is used to obtain the first initial historical set, the second initial historical set, the first initial experimental set, and the second initial experimental set based on multi-source numerical sets. Using a pre-constructed fitted coordinate system, the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are selected respectively to obtain the first history set, the second history set, the first experiment set, and the second experiment set; The evaluation value acquisition module is used to obtain an initial probability set based on the first historical set, the second historical set, the first experimental set, and the second experimental set. The initial probability set includes four initial probabilities, which are: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. The four initial probabilities in the initial probability set are all input into the pre-constructed evidence network model to obtain the first normal evaluation value and the first fault evaluation value. Weighting factors are obtained based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set. The weighting factors include historical weighting factors and experimental weighting factors. The second normal evaluation value and the second failure evaluation value are obtained based on the historical weighting factor, the experimental weighting factor, and the pre-constructed reliability evaluation formula. The comprehensive evaluation module is used to calculate the average of the first normal evaluation value and the second normal evaluation value to obtain the comprehensive normal evaluation value, obtain the comprehensive fault evaluation value based on the first fault evaluation value and the second fault evaluation value, and obtain the reliability evaluation status of the equipment using the comprehensive normal evaluation value and the comprehensive fault evaluation value, wherein the reliability evaluation status is the normal state of the equipment or the fault state of the equipment.

[0016] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the equipment reliability analysis method based on data fusion and evidence networks described above.

[0017] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned equipment reliability analysis method based on data fusion and evidence networks.

[0018] To address the problems described in the background art, this invention receives a reliability analysis command and acquires a multi-source dataset of equipment based on the command. The multi-source dataset includes multiple data sources, which are either historical data or experimental data identified by a detection time. A multi-source numerical set is then acquired based on this dataset. Therefore, this invention analyzes equipment reliability using multi-source data. Multi-source data provides richer information, reduces the limitations of a single data source, and integrates the data from multiple data sources into a multi-source numerical set, facilitating subsequent analysis and processing. This invention acquires data based on a multi-source numerical set. The first initial history set, the second initial history set, the first initial experimental set, and the second initial experimental set are selected using a pre-constructed fitted coordinate system to obtain the first history set, the second history set, the first experimental set, and the second experimental set. Based on these sets, an initial probability set is obtained, comprising four initial probabilities: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. These four initial probabilities are then used to... Initial probabilities are input into a pre-constructed evidence network model to obtain a first normal assessment value and a first fault assessment value. This invention improves data processing efficiency by filtering duplicate data. The invention obtains weighting factors based on a first initial historical set, a second initial historical set, a first initial experimental set, and a second initial experimental set. These weighting factors include historical weighting factors and experimental weighting factors. A second normal assessment value and a second fault assessment value are obtained based on these historical weighting factors, experimental weighting factors, and a pre-constructed reliability assessment formula. The mean of the first and second normal assessment values ​​is calculated to obtain a comprehensive normal assessment value. A comprehensive fault assessment value is obtained based on the first and second fault assessment values. The comprehensive normal assessment value and the comprehensive fault assessment value are used to obtain the equipment's reliability assessment status, where the reliability assessment status is either the equipment's normal state or its fault state. This invention uses the entropy weighting method to obtain weighting factors, where the weights are entirely determined by the characteristics of the data itself, avoiding interference from human factors and making the weights more objective and reliable. This improves the objectivity and accuracy of the evaluation results. The evaluation results obtained through both weighted averaging and the evidence network model can be analyzed from multiple perspectives, reducing the limitations of a single method and increasing reliability. Therefore, this invention can improve the accuracy and reliability of equipment reliability analysis. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating an embodiment of the equipment reliability analysis method based on data fusion and evidence networks provided by the present invention. Figure 2A functional block diagram of an equipment reliability analysis system based on data fusion and evidence networks provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device that implements the equipment reliability analysis method based on data fusion and evidence networks, according to an embodiment of the present invention.

[0020] Explanation of reference numerals in the attached figures: 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0023] This application provides a method for equipment reliability analysis based on data fusion and evidence networks. The executing entity of this method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0024] Reference Figure 1 The diagram shown is a flowchart illustrating an equipment reliability analysis method based on data fusion and evidence networks according to an embodiment of the present invention. In this embodiment, the equipment reliability analysis method based on data fusion and evidence networks includes: S1. Receive a reliability analysis command and obtain a multi-source dataset of the equipment based on the reliability analysis command. The multi-source dataset includes multiple multi-source data, wherein the multi-source data are historical data with detection time or experimental data with detection time.

[0025] Understandably, the reliability analysis instruction is issued by personnel performing the equipment reliability analysis, and this personnel confirms the multi-source data used for the equipment reliability analysis. The multi-source data can be historical data with identified testing times or experimental data with identified testing times. Optionally, the equipment can be a digital multimeter. Optionally, in order to distinguish between historical data and experimental data, this embodiment of the invention uses data from 6 months prior to the equipment reliability analysis as historical data and data from 1 month prior as experimental data. For example, assuming a reliability analysis of the digital multimeter is planned for October 2024, testing data from September 2024 is used as experimental data, and testing data from April 2024 is used as historical data.

[0026] For example, in order to obtain multi-source data for analyzing the reliability of a digital multimeter, the voltage and current ranges of the digital multimeter are used as the analysis objects. A standard voltage signal and a standard current signal are set, and the standard voltage signal and the standard current signal are measured respectively. The time of each measurement is recorded. Here, the standard voltage signal and the standard current signal are used to characterize the standard voltage and the standard current to be measured, respectively. The measured voltage value and the measured current value are identified by the measurement time, and a set of data with the detection time is obtained.

[0027] For example, at time B, a digital multimeter is used to measure the standard voltage set to 5V and the standard current set to 2A, respectively, to obtain a test current value of 1.99A and a test voltage value of 5V. The test current value can be identified by time as B-1.99A, and the test voltage value can be identified by time as B-5V.

[0028] S2. Obtain multi-source numerical sets based on multi-source datasets.

[0029] It should be explained that obtaining multi-source numerical sets based on multi-source datasets includes: Perform the following operation on each multi-source dataset: Identify the data types of the multi-source data in the multi-source dataset. If the data type of the multi-source data is numerical, then confirm the multi-source data as multi-source numerical data, summarize the multi-source numerical data, and obtain the multi-source numerical set.

[0030] Understandably, data types are identifiers used to distinguish different types of data. Numerical data represents quantity or measurement and can be used for mathematical operations and quantitative analysis. Multi-source numerical data is numerical data.

[0031] For example, if the multi-source dataset is represented as {t1-10.0V, t1-5.0A, t2-10.1V, t2-5.1A, t3-10V, t3-3A}, t1, t2, and t3 all represent the detection time corresponding to the multi-source data, and 10.0V, 5.0A, 10.1V, 5.1A, 10V, and 3A all represent the data obtained after detecting the equipment. The detected data is identified using a pre-built data type discrimination model to obtain different data types, and numerical multi-source data is selected based on the identification results. The multi-source data with data values ​​are: {t1-10.0V, t1-5.0A, t2-10.1V, t2-5.1A}.

[0032] It should be understood that a data type discrimination model is a model that can distinguish the type of data. Optionally, a machine learning model can be used as the data type discrimination model; other techniques can also achieve the same effect, which will not be elaborated upon here. Generally speaking, when testing equipment, different personal habits may lead to different ways of recording data. The purpose of filtering out numerical multi-source data is to ensure that the filtered multi-source data is all numerical, thereby improving the efficiency of processing the filtered multi-source data.

[0033] S3. Obtain the first initial history set, the second initial history set, the first initial experimental set, and the second initial experimental set based on the multi-source numerical set.

[0034] Furthermore, the step of obtaining the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set based on multi-source numerical sets includes: Using a preset first partitioning identifier, the multi-source values ​​in the multi-source value set are identified as initial historical values ​​or initial experimental values. The initial historical values ​​and initial experimental values ​​are then summarized to obtain the historical value set and the experimental value set. Using a preset second partitioning identifier, the initial historical values ​​in the historical value set are identified as either the initial historical first value or the initial historical second value. The initial historical first value and the initial historical second value are then summarized to obtain the first initial historical set and the second initial historical set. Using a preset third partitioning identifier, the initial experimental values ​​in the experimental value set are identified as the first initial experimental value or the second initial experimental value. The first initial experimental value and the second initial experimental value are then summarized to obtain the first initial experimental set and the second initial experimental set.

[0035] It should be understood that the multi-source numerical set consists of historical data or experimental data with a detection time identifier. The month identifier in the detection time serves as the first dividing identifier to distinguish between the initial historical data and the initial experimental data, and this first dividing identifier needs to be set in conjunction with the time of equipment analysis. For example, if several multi-source values ​​in the multi-source numerical set are {04.01-10: 01-9.9V, 04.01-10: 02-9.9V, 04.01-10: 03-10.1V, 04.01-10: 04-10.0V, 04.01-10: 01-5.0A, 04.01-10: 02-5.0A, 04.01-10: 03-4.9A, 04.01-1...} 0:04-5.1A, 09.01-10:01-9.8V, 09.01-10:02-9.8V, 09.01-10:03-10.1V, 09.01-10:04-10.0V, 09.01-10:01-5.1A, 09.01-10:02-5.1A, 09.01-10:03-4.9A, 09.01-10:04-5.0A}. Here, we only take 04.01-10:01-9.9V as an example, where 04.01-10:01-9.9V represents the voltage value of 9.9V measured at 10:01 AM on April 1st. The other multi-source values ​​can achieve the same effect as 04.01-10:01-9.9V, and will not be described in detail here. The first partition identifier can be 09 or 04. Here, we will take 09 as an example. We will use 09 to search in the multi-source data set. If there is an identifier in the multi-source data set that is the same as the first partition identifier 09, the multi-source data corresponding to the identifier 09 will be confirmed as the initial experimental data. Otherwise, the multi-source data will be confirmed as the initial experimental data.

[0036] Understandably, multiple multi-source values ​​will be obtained during actual analysis. Therefore, after filtering by the first partitioning identifier, multiple initial experimental values ​​and multiple initial historical values ​​will be obtained. The initial experimental values ​​and initial historical values ​​are then summarized to obtain a historical value set and an experimental value set. The second and third partitioning identifiers are V and A, respectively. Here, V and A represent the units corresponding to different values, and the second and third partitioning identifiers can be set in conjunction with the multi-source values ​​measured on the equipment. Using V and A, the initial historical values ​​in the historical value set are divided into the first initial historical value corresponding to V or the second initial historical value corresponding to A. Similarly, using V and A, the initial experimental values ​​in the experimental value set are divided into the first initial experimental value corresponding to V or the second initial experimental value corresponding to A. The first initial historical value and the second initial historical value are then summarized to obtain a first initial historical set and a second initial historical set. Finally, the first initial experimental value and the second initial experimental value are summarized to obtain a first initial experimental set and a second initial experimental set.

[0037] S4. Using the pre-constructed fitted coordinate system, filter the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set respectively to obtain the first history set, the second history set, the first experiment set, and the second experiment set.

[0038] It should be explained that the step of using a pre-constructed fitted coordinate system to filter the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set to obtain the first history set, the second history set, the first experiment set, and the second experiment set includes: Sort the initial history values ​​in the first initial history set in ascending order to obtain the initial history sequence; The first initial historical value is extracted sequentially from the initial historical sequence, and the following operations are performed on the extracted first initial historical value: Using the extracted initial historical first value, the initial position is determined in the initial historical sequence. The extracted initial historical first value and the initial position are associated to obtain the fitted coordinate points. The fitted coordinate points are then summarized to obtain the fitted coordinate point set. A coordinate system is constructed with the initial position as the x-axis and the initial historical first value as the y-axis. All the fitted coordinate points in the fitted coordinate point set are mapped to the coordinate system to obtain the mapped coordinate point set. The first initial historical value is extracted sequentially from the initial historical sequence, and the following operation is performed on each extracted first initial historical value: Based on the extracted initial historical first value, a target historical first value is identified in the initial historical sequence, wherein the target historical first value is adjacent to and lags behind the extracted initial historical first value. Based on the initial historical first value and the target historical first value, the initial mapping coordinate point and the target mapping coordinate point are identified in the set of mapping coordinate points. Connect the initial mapped coordinate point and the target mapped coordinate point to obtain a polyline segment. Use the target historical first value as the extracted initial historical first value, and return to the step of confirming the target historical first value in the initial historical sequence based on the extracted initial historical first value. Summarize the polyline segments to obtain multiple polyline segments. Perform the following operation on each of the multiple polyline segments: Obtain the slope of the line segment, get the evaluation slope, and determine whether the evaluation slope is zero; If the slope is zero, then either of the two fitted coordinate points corresponding to the broken line segment will be marked as a repeated coordinate point. Remove the initial historical first value corresponding to duplicate coordinate points from the initial historical sequence to obtain the updated historical sequence. Use the updated historical sequence as the initial historical sequence and return to the step of extracting the initial historical first value from the initial historical sequence in sequence until the evaluation slope is not zero. Use the initial historical first value in the updated historical sequence as the first historical set. The second initial history set, the first initial experiment set, and the second initial experiment set are obtained using the second initial history set, the first initial experiment set, and the second initial experiment set, respectively.

[0039] For example, if the first initial history set is represented as {04.01-10:01-9.9V, 04.01-10:02-9.9V, 04.01-10:03-10.1V, 04.01-10:04-10.0V}, where the multiple initial history first values ​​are 9.9, 9.9, 10.0, and 10.1 respectively, sorting the multiple initial history first values ​​yields the initial history sequence {9.9, 9.9, 10.0, 10.1}. In the initial historical sequence {9.9, 9.9, 10.0, 10.1}, the initial position of each initial historical first value is determined. For example, the initial position of the first initial historical first value 9.9 is 1, and the initial position of the second initial historical first value 9.9 is 2. The corresponding fitted coordinate points are (1, 9.9) and (2, 9.9). The fitted coordinate points in the fitted coordinate point set are mapped to a coordinate system constructed with the initial position as the abscissa and the initial historical first value as the ordinate, resulting in the mapped coordinate point set S={(1, 9.9), (2, 9.9), (3, 10.0), (4, 10.1)}. Optionally, a Cartesian coordinate system is used as the coordinate system. Other techniques can achieve the same effect, which will not be elaborated here.

[0040] For example, given the initial historical sequence {9.9, 9.9, 10.0, 10.1}, and the set of mapped coordinate points S = {(1, 9.9), (2, 9.9), (3, 10.0), (4, 10.1)}, the first initial historical value 9.9 is extracted from the initial historical sequence. Then, the initial historical value adjacent to and lagging behind the first initial historical value 9.9 is identified as 9.9. Here, the target historical value is the second initial historical value 9.9. Based on the initial historical value 9.9, the corresponding initial mapped coordinate point is identified as (1, 9.9) in the set of mapped coordinate points. Based on the target historical value 9.9, the corresponding target mapped coordinate point is identified as (2, 9.9) in the set of mapped coordinate points. Connecting the initial mapped coordinate point (1, 9.9) and the target mapped coordinate point (2, 9.9) yields... Once the line segment is reached, the target historical first value of 9.9 is used as the extracted initial historical first value. The corresponding target historical first value of 10.0 is then determined based on the initial historical first value of 9.9 and the target historical first value of 10.0. Based on the initial historical first value of 9.9 and the target historical first value of 10.0, the initial mapping coordinate point (2, 9.9) and the target mapping coordinate point (3, 10.0) are determined in the mapping coordinate point set, respectively. Connecting the initial mapping coordinate point (2, 9.9) and the target mapping coordinate point (3, 10.0) yields the second line segment. This process is repeated until all points in the mapping coordinate point set correspond to line segments, resulting in multiple line segments.

[0041] It should be understood that if the ordinates of two fitted coordinate points are the same, the slope of the line segment is zero. The ordinate of the fitted coordinate point represents the initial historical first value. A slope of zero indicates that the initial historical first values ​​of the two fitted coordinate points constituting the line segment are the same. Either of the two fitted coordinate points is marked as a duplicate coordinate point. The initial historical first value corresponding to the duplicate coordinate point is removed from the initial historical sequence to obtain an updated historical sequence. The updated historical sequence is used as the initial historical sequence, and the step of extracting the initial historical first value from the initial historical sequence is returned until the slope is not zero. The purpose of removing duplicate fitted coordinate points here is to improve the efficiency of subsequent data filtering. For specific filtering methods, please refer to the following embodiments.

[0042] For example, if the slope of the line segment formed by the mapped coordinate points (1, 9.9) and (2, 9.9) is zero, then any coordinate point is marked as a duplicate coordinate point. A 9.9 is removed from the initial historical sequence {9.9, 9.9, 10.0, 10.1}, resulting in the updated historical sequence {9.9, 10.0, 10.1}. Using this updated historical sequence as the initial historical sequence {9.9, 10.0, 10.1}, the step of sequentially extracting the first initial historical value from the initial historical sequence is returned. It is confirmed that the slopes of the multiple line segments obtained from {9.9, 10.0, 10.1} are all non-zero, indicating that {9.9, 10.0, 10.1}... All duplicate values ​​in the dataset have been removed, resulting in the first history set as {04.01-10:02-9.9V, 04.01-10:03-10.1V, 04.01-10:04-10.0V}. Similarly, the processes for obtaining the second history set, the first experimental set, and the second experimental set are the same as those for obtaining the first history set, and will not be repeated here.

[0043] S5. Obtain an initial probability set based on the first historical set, the second historical set, the first experimental set, and the second experimental set. The initial probability set includes four initial probabilities, which are: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability.

[0044] It should be understood that obtaining the initial probability set based on the first historical set, the second historical set, the first experimental set, and the second experimental set includes: Extract the initial historical first value sequentially from the first historical set, and perform the following operation on each extracted initial historical first value: Based on the detection time corresponding to the extracted initial historical first value, a search is performed in the second historical set. If there is a detection time in the second historical set that is the same as the detection time corresponding to the initial historical second value, then the initial historical first value and the initial historical second value are associated to obtain historical value nodes. The historical value nodes are then summarized to obtain a set of historical value nodes. Obtain the first reference value and the second reference value when the equipment is in normal state; obtain the first reference half-axis based on the first reference value; obtain the second reference half-axis based on the second reference value. The first reference value is associated with the second reference value to obtain the fitting center coordinate point. The fitting center coordinate point, the first reference half-axis, the pre-constructed reference coordinate system and the second reference half-axis are used to construct a reference region. All historical numerical nodes in the historical numerical node set are mapped to the reference coordinate system to obtain the discrimination coordinate node set. The discrimination coordinate node set includes multiple discrimination coordinate nodes and the discrimination coordinate nodes correspond one-to-one with the historical numerical nodes. Based on the reference area and the set of discriminant coordinate nodes, a set of qualified historical data nodes is identified, wherein the set of qualified historical data nodes includes multiple qualified historical nodes, and the qualified historical nodes are located within the reference area. A set of discriminative historical numerical nodes is obtained using the first initial history set and the second initial history set, wherein the set of discriminative historical numerical nodes includes multiple discriminative historical numerical nodes; Based on the qualified historical value node set, a target historical value node set is identified in the discrimination historical value node set, wherein the target historical value node set includes multiple target historical value nodes. The number of target historical data nodes in the target historical data node set and the number of discriminative historical data nodes in the discrimination historical data node set are counted separately to obtain the number of qualified historical data nodes and the total number of historical data nodes. The ratio of the number of qualified historical data nodes to the total number of historical data nodes is calculated to obtain the historical ratio value. The historical ratio value is used to determine the historical normal probability and historical failure probability corresponding to the historical data set, where the historical normal probability and historical failure probability are respectively: ; ; in, Indicates the normal probability in history. This represents the initial ratio value. Indicates the probability of historical failures; The normal experimental probability and the experimental failure probability are obtained based on the first experimental set, the second experimental set, the first initial experimental set, the second initial experimental set, and the reference region, wherein the normal experimental probability and the experimental failure probability are respectively: ; ; in, Indicates the normal probability of the experiment. Indicates the experimental ratio value. Indicates the probability of experimental failure; By summarizing the historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability, an initial probability set is obtained.

[0045] For example, the first history set is represented as {04.01-10:02-9.9V, 04.01-10:03-10.1V, 04.01-10:04-10.0V}, and the second history set is represented as {04.01-10:02-5.0A, 04.01-10:03-4.9A, 04.01-10:04-5.1A}. The detection time 04.01-10:02 corresponding to the first initial historical value 9.9 is extracted from the second historical set. Using 04.01-10:02 as the search condition, the initial historical second value 5.0 in 04.01-10:02-5.0A corresponding to the same search time 04.01-10:02 is retrieved in the second historical set. The initial historical first value 9.9 and the initial historical second value 5.0 are associated to obtain a historical value node (9.9, 5.0). Multiple historical value nodes can be obtained using the detection time, namely (9.9, 5.0), (10.1, 4.9), and (10.0, 5.1). The set of historical value nodes is composed of multiple historical value nodes.

[0046] It should be explained that the reference area is as follows: ; in, Indicates the first reference value. Indicates the second reference value. Indicates the first reference half-axis, Indicates the second reference half-axis. Represents the x-coordinate of the reference coordinate system. This represents the ordinate of the reference coordinate system.

[0047] It should be understood that the first and second reference values ​​can be standard values ​​used when acquiring multi-source data. The horizontal axis can be used to represent the first reference value, and the vertical axis can be used to represent the second reference value. For example, when testing a digital multimeter, in order to determine whether the multimeter is accurate, a first reference value of 5A representing current and a second reference value of 10V representing voltage are set. Generally, under ideal conditions, i.e., when the digital multimeter is accurate, the reading displayed when testing the signal or unit corresponding to the first reference value should be 5A, and the reading displayed for the second reference value should be... When testing the corresponding signal or unit, the displayed reading should be 10V. However, due to potential malfunctions or other factors, digital multimeters may exhibit inaccurate measurements. Therefore, it is necessary to filter the data obtained by the digital multimeter. The filtering process is as follows: Associate the first reference value and the second reference value to obtain the fitting center coordinate point (10, 5). Use the fitting center coordinate point (10, 5) as the center point of the reference area. Obtain the second reference half-axis using the standard voltage of 10V and the maximum permissible error of the standard voltage of 10V. If the maximum permissible error is... The second reference half-axis is the product of the second reference value and the absolute value of the maximum permissible error, which is 0.1. The method of obtaining the first reference half-axis is the same as that of obtaining the second reference half-axis, and can achieve the same effect, so it will not be described again here.

[0048] It should be understood that the definitions of the historical data nodes and target historical data nodes are the same as those of the coordinate nodes, and will not be repeated here. A target historical data node is one that is identical to a qualified historical data node in the set of qualified historical data nodes.

[0049] For example, all historical numerical nodes in the historical numerical node set are mapped to a reference coordinate system, resulting in a discriminant coordinate node set in the reference coordinate system, which is (9.9, 5.0), (10.1, 4.9), and (10.0, 5.1). By determining whether the discriminant coordinate node in the discriminant coordinate node set is within the elliptical region corresponding to the reference region, it is found that (9.9, 5.0) is within the elliptical region. Therefore, the number of target historical numerical nodes is 1. The ratio of the number of target historical numerical nodes (1) to the number of discriminant historical numerical nodes (3) is calculated, resulting in a historical ratio of 1 / 3, which represents the historical normal probability corresponding to the historical numerical set. =1 / 3, historical failure probability 1 / 3 = 2 / 3. Similarly, the method for obtaining the normal probability and the failure probability of the experiment is the same as the method for obtaining the historical normal probability and the historical failure probability, which will not be repeated here. By summarizing the historical normal probability, the historical failure probability, the normal probability of the experiment, and the failure probability of the experiment, we obtain the probability set.

[0050] S6. Input all four initial probabilities from the initial probability set into the pre-constructed evidence network model to obtain the first normal evaluation value and the first fault evaluation value.

[0051] It should be understood that the evidence network model is a graphical model based on evidence theory and probabilistic reasoning, and that the evidence network model is existing technology. In this embodiment of the invention, the evidence network model is used to fuse four initial probabilities from the initial probability set to obtain the first normal assessment value and the first fault assessment value of the entire equipment system. The first normal assessment value is used to characterize the probability that the equipment's reliability assessment state is in a normal state, and the first fault assessment value is used to characterize the probability that the equipment's reliability assessment state is in a fault state.

[0052] S7. Obtain weighting factors based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set, wherein the weighting factors include: historical weighting factors and experimental weighting factors.

[0053] Furthermore, the step of obtaining weighting factors based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set includes: The first historical weight and the first experimental weight are obtained based on the first initial historical set, the first initial experimental set, the first reference value, and the pre-constructed entropy weight method. The second historical weight and the second experimental weight are obtained based on the second initial historical set, the second initial experimental set, the second reference value, and the entropy weight method. Calculate the mean of the first historical weight and the second historical weight to obtain the historical weight factor. Calculate the mean of the first experimental weight and the second experimental weight to obtain the experimental weight factor.

[0054] It should be understood that the entropy weight method is an objective weighting method. It calculates the absolute difference between the first initial historical value and the first reference value in the first initial historical set, and the absolute difference between the second initial historical value and the first reference value in the second initial historical set. A deviation matrix is ​​then constructed using the calculated absolute differences. Based on this deviation matrix, the first historical weight and the first experimental weight are obtained. The entropy weight method is existing technology and will not be elaborated further here. Similarly, the second historical weight and the second experimental weight are obtained based on the first initial experimental set, the second initial experimental set, the second reference value, and the entropy weight method. The first historical weight and the first experimental weight represent the weights of the first initial historical set and the first initial experimental set when evaluating the equipment, respectively. The definitions of the second historical weight and the second experimental weight are the same as those of the first historical weight and the first experimental weight, and will not be elaborated further here. This embodiment of the invention uses the entropy weight method to obtain weighting factors. The weights are entirely determined by the characteristics of the data itself, avoiding interference from human factors, making the weights more objective and reliable, and improving the objectivity and accuracy of the evaluation results. The historical weight factor represents the proportion of the historical data set in the equipment reliability analysis, and the experimental weight factor represents the proportion of the historical data set in the equipment reliability analysis.

[0055] S8. Obtain the second normal evaluation value and the second failure evaluation value based on the historical weighting factor, the experimental weighting factor and the pre-constructed reliability evaluation formula.

[0056] It should be explained that the reliability assessment formula is as follows: ; ; in, This indicates the second normal assessment value. Represents historical weighting factors. Indicates the experimental weighting factor. This indicates the second fault assessment value.

[0057] It should be understood that the reliability assessment formula is a calculation formula based on weighted average to obtain the assessment value. It can comprehensively consider historical weight factors to obtain the equipment reliability assessment value. The second normal assessment value represents the equipment normal assessment value obtained based on weighted average, and the second failure assessment value represents the equipment failure assessment value obtained based on weighted average.

[0058] S9. Calculate the average of the first normal assessment value and the second normal assessment value to obtain the comprehensive normal assessment value. Obtain the comprehensive fault assessment value based on the first fault assessment value and the second fault assessment value. Use the comprehensive normal assessment value and the comprehensive fault assessment value to obtain the reliability assessment status of the equipment, wherein the reliability assessment status is the normal state of the equipment or the fault state of the equipment.

[0059] It should be understood that the comprehensive normal assessment value is the average of the first normal assessment value and the second normal assessment value, reflecting the comprehensive probability that the equipment is in a normal state. The comprehensive fault assessment value is the average of the first fault assessment value and the second fault assessment value, reflecting the comprehensive probability that the equipment is in a fault state. It integrates the assessment results obtained by weighted averaging and evidence network model, and analyzes from multiple perspectives, which can reduce the limitations of a single method and increase credibility.

[0060] It should be explained that the method of obtaining the equipment's reliability assessment status using comprehensive normal assessment values ​​and comprehensive fault assessment values ​​includes: Compare the overall normal assessment value with the preset normal assessment threshold: If the comprehensive normal assessment value is greater than or equal to the normal assessment threshold, the equipment reliability assessment status is determined to be the normal equipment status. If the overall normal assessment value is less than the normal assessment threshold, and the overall fault assessment value is less than or equal to the preset fault assessment threshold, then the equipment's reliability assessment status is determined to be an equipment fault status.

[0061] For example, the normal assessment threshold is set to 0.9, the fault assessment threshold is set to 0.5, and the comprehensive normal assessment value is 0.95. If the comprehensive normal assessment value is greater than the normal assessment threshold, the reliability assessment status of the equipment is determined to be the normal state, indicating that the equipment can be used normally.

[0062] Generally speaking, when equipment is under overload, there may be situations where the overall normal assessment value is less than the normal assessment threshold and the overall normal assessment value is greater than the fault assessment threshold. Therefore, setting a judgment condition that the overall normal assessment value is less than the normal assessment threshold and the overall fault assessment value is less than or equal to the fault assessment threshold can improve the accuracy of judging whether the equipment reliability assessment status is in a fault state.

[0063] To address the problems described in the background art, this invention receives a reliability analysis command and acquires a multi-source dataset of equipment based on the command. The multi-source dataset includes multiple data sources, which are either historical data or experimental data identified by a detection time. A multi-source numerical set is then acquired based on this dataset. Therefore, this invention analyzes equipment reliability using multi-source data. Multi-source data provides richer information, reduces the limitations of a single data source, and integrates the data from multiple data sources into a multi-source numerical set, facilitating subsequent analysis and processing. This invention acquires data based on a multi-source numerical set. The first initial history set, the second initial history set, the first initial experimental set, and the second initial experimental set are selected using a pre-constructed fitted coordinate system to obtain the first history set, the second history set, the first experimental set, and the second experimental set. Based on these sets, an initial probability set is obtained, comprising four initial probabilities: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. These four initial probabilities are then used to... Initial probabilities are input into a pre-constructed evidence network model to obtain a first normal assessment value and a first fault assessment value. This invention improves data processing efficiency by filtering duplicate data. The invention obtains weighting factors based on a first initial historical set, a second initial historical set, a first initial experimental set, and a second initial experimental set. These weighting factors include historical weighting factors and experimental weighting factors. A second normal assessment value and a second fault assessment value are obtained based on these historical weighting factors, experimental weighting factors, and a pre-constructed reliability assessment formula. The mean of the first and second normal assessment values ​​is calculated to obtain a comprehensive normal assessment value. A comprehensive fault assessment value is obtained based on the first and second fault assessment values. The comprehensive normal assessment value and the comprehensive fault assessment value are used to obtain the equipment's reliability assessment status, where the reliability assessment status is either the equipment's normal state or its fault state. This invention uses the entropy weighting method to obtain weighting factors, where the weights are entirely determined by the characteristics of the data itself, avoiding interference from human factors and making the weights more objective and reliable. This improves the objectivity and accuracy of the evaluation results. The evaluation results obtained through both weighted averaging and the evidence network model can be analyzed from multiple perspectives, reducing the limitations of a single method and increasing reliability. Therefore, this invention can improve the accuracy and reliability of equipment reliability analysis.

[0064] like Figure 2 The diagram shown is a functional block diagram of an equipment reliability analysis system based on data fusion and evidence network provided in an embodiment of the present invention.

[0065] The equipment reliability analysis system 100 based on data fusion and evidence networks described in this invention can be installed in an electronic device. Depending on the functions implemented, the equipment reliability analysis system 100 based on data fusion and evidence networks may include a data acquisition and preprocessing module 101, a data filtering module 102, an evaluation value acquisition module 103, and a comprehensive evaluation module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0066] The data acquisition and preprocessing module 101 is used to receive a reliability analysis command and acquire a multi-source dataset of the equipment based on the reliability analysis command. The multi-source dataset includes multiple multi-source data, wherein the multi-source data is historical data with a detection time or experimental data with a detection time. Obtain multi-source numerical sets based on multi-source datasets; The data filtering module 102 is used to obtain a first initial historical set, a second initial historical set, a first initial experimental set, and a second initial experimental set based on a multi-source numerical set. Using a pre-constructed fitted coordinate system, the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are selected respectively to obtain the first history set, the second history set, the first experiment set, and the second experiment set; The evaluation value acquisition module 103 is used to acquire an initial probability set based on the first historical set, the second historical set, the first experimental set, and the second experimental set. The initial probability set includes four initial probabilities, which are: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. The four initial probabilities in the initial probability set are all input into the pre-constructed evidence network model to obtain the first normal evaluation value and the first fault evaluation value. Weighting factors are obtained based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set. The weighting factors include historical weighting factors and experimental weighting factors. The second normal evaluation value and the second failure evaluation value are obtained based on the historical weighting factor, the experimental weighting factor, and the pre-constructed reliability evaluation formula. The comprehensive evaluation module 104 is used to calculate the average of the first normal evaluation value and the second normal evaluation value to obtain a comprehensive normal evaluation value, obtain a comprehensive fault evaluation value based on the first fault evaluation value and the second fault evaluation value, and obtain the reliability evaluation status of the equipment using the comprehensive normal evaluation value and the comprehensive fault evaluation value, wherein the reliability evaluation status is the normal state of the equipment or the fault state of the equipment.

[0067] In detail, the modules in the equipment reliability analysis system 100 based on data fusion and evidence networks described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method used is the same as the equipment reliability analysis method based on data fusion and evidence networks described in the article, and can produce the same technical effect, so it will not be repeated here.

[0068] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements a method for equipment reliability analysis based on data fusion and evidence networks, according to an embodiment of the present invention.

[0069] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as an equipment reliability analysis method program based on data fusion and evidence networks.

[0070] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of an equipment reliability analysis method program based on data fusion and evidence networks, but also to temporarily store data that has been output or will be output.

[0071] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., equipment reliability analysis methods based on data fusion and evidence networks) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0072] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0073] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0074] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0075] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0076] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0077] The equipment reliability analysis method program based on data fusion and evidence networks stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following: Receive a reliability analysis command, and obtain a multi-source dataset of the equipment based on the reliability analysis command. The multi-source dataset includes multiple multi-source data, wherein the multi-source data are historical data or experimental data with detection time. Obtain multi-source numerical sets based on multi-source datasets; The first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are obtained based on multi-source numerical sets. Using a pre-constructed fitted coordinate system, the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are selected respectively to obtain the first history set, the second history set, the first experiment set, and the second experiment set; An initial probability set is obtained based on the first historical set, the second historical set, the first experimental set, and the second experimental set. The initial probability set includes four initial probabilities, which are: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. The four initial probabilities in the initial probability set are all input into the pre-constructed evidence network model to obtain the first normal evaluation value and the first fault evaluation value. Weighting factors are obtained based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set. The weighting factors include historical weighting factors and experimental weighting factors. The second normal evaluation value and the second failure evaluation value are obtained based on the historical weighting factor, the experimental weighting factor, and the pre-constructed reliability evaluation formula. The average of the first normal assessment value and the second normal assessment value is calculated to obtain the comprehensive normal assessment value. The comprehensive fault assessment value is obtained based on the first fault assessment value and the second fault assessment value. The reliability assessment status of the equipment is obtained using the comprehensive normal assessment value and the comprehensive fault assessment value. The reliability assessment status is either the normal state of the equipment or the fault state of the equipment.

[0078] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0079] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0080] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: Receive a reliability analysis command, and obtain a multi-source dataset of the equipment based on the reliability analysis command. The multi-source dataset includes multiple multi-source data, wherein the multi-source data are historical data or experimental data with detection time. Obtain multi-source numerical sets based on multi-source datasets; The first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are obtained based on multi-source numerical sets. Using a pre-constructed fitted coordinate system, the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are selected respectively to obtain the first history set, the second history set, the first experiment set, and the second experiment set; An initial probability set is obtained based on the first historical set, the second historical set, the first experimental set, and the second experimental set. The initial probability set includes four initial probabilities, which are: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. The four initial probabilities in the initial probability set are all input into the pre-constructed evidence network model to obtain the first normal evaluation value and the first fault evaluation value. Weighting factors are obtained based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set. The weighting factors include historical weighting factors and experimental weighting factors. The second normal evaluation value and the second failure evaluation value are obtained based on the historical weighting factor, the experimental weighting factor, and the pre-constructed reliability evaluation formula. The average of the first normal assessment value and the second normal assessment value is calculated to obtain the comprehensive normal assessment value. The comprehensive fault assessment value is obtained based on the first fault assessment value and the second fault assessment value. The reliability assessment status of the equipment is obtained using the comprehensive normal assessment value and the comprehensive fault assessment value. The reliability assessment status is either the normal state of the equipment or the fault state of the equipment.

[0081] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0082] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0083] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0084] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for equipment reliability analysis based on data fusion and evidence networks, characterized in that, The method includes: Receive a reliability analysis command, and obtain a multi-source dataset of the equipment based on the reliability analysis command. The multi-source dataset includes multiple multi-source data, wherein the multi-source data are historical data or experimental data with detection time. Obtain multi-source numerical sets based on multi-source datasets; The first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are obtained based on multi-source numerical sets. Using a pre-constructed fitted coordinate system, the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are selected respectively to obtain the first history set, the second history set, the first experiment set, and the second experiment set; The process of using a pre-constructed fitted coordinate system to filter the first initial history set, the second initial history set, the first initial experimental set, and the second initial experimental set to obtain the first history set, the second history set, the first experimental set, and the second experimental set includes: Sort the initial history values ​​in the first initial history set in ascending order to obtain the initial history sequence; The first initial historical value is extracted sequentially from the initial historical sequence, and the following operations are performed on the extracted first initial historical value: Using the extracted initial historical first value, the initial position is determined in the initial historical sequence. The extracted initial historical first value and the initial position are associated to obtain the fitted coordinate points. The fitted coordinate points are then summarized to obtain the fitted coordinate point set. A coordinate system is constructed with the initial position as the x-axis and the initial historical first value as the y-axis. All the fitted coordinate points in the fitted coordinate point set are mapped to the coordinate system to obtain the mapped coordinate point set. The first initial historical value is extracted sequentially from the initial historical sequence, and the following operation is performed on each extracted first initial historical value: Based on the extracted initial historical first value, a target historical first value is identified in the initial historical sequence, wherein the target historical first value is adjacent to and lags behind the extracted initial historical first value. Based on the initial historical first value and the target historical first value, the initial mapping coordinate point and the target mapping coordinate point are identified in the set of mapping coordinate points. Connect the initial mapped coordinate point and the target mapped coordinate point to obtain a polyline segment. Use the target historical first value as the extracted initial historical first value, and return to the step of confirming the target historical first value in the initial historical sequence based on the extracted initial historical first value. Summarize the polyline segments to obtain multiple polyline segments. Perform the following operation on each of the multiple polyline segments: Obtain the slope of the line segment, get the evaluation slope, and determine whether the evaluation slope is zero; If the slope is zero, then either of the two fitted coordinate points corresponding to the broken line segment will be marked as a repeated coordinate point. Remove the initial historical first value corresponding to duplicate coordinate points from the initial historical sequence to obtain the updated historical sequence. Use the updated historical sequence as the initial historical sequence and return to the step of extracting the initial historical first value from the initial historical sequence in sequence until the evaluation slope is not zero. Use the initial historical first value in the updated historical sequence as the first historical set. The second initial history set, the first initial experiment set, and the second initial experiment set are obtained respectively using the second initial history set, the first initial experiment set, and the second initial experiment set; An initial probability set is obtained based on the first historical set, the second historical set, the first experimental set, and the second experimental set. The initial probability set includes four initial probabilities, namely: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. The four initial probabilities in the initial probability set are input into the pre-constructed evidence network model to obtain the first normal evaluation value and the first failure evaluation value. Weighting factors are obtained based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set. The weighting factors include historical weighting factors and experimental weighting factors. The second normal evaluation value and the second failure evaluation value are obtained based on the historical weighting factor, the experimental weighting factor, and the pre-constructed reliability evaluation formula. The average of the first normal assessment value and the second normal assessment value is calculated to obtain the comprehensive normal assessment value. The comprehensive fault assessment value is obtained based on the first fault assessment value and the second fault assessment value. The reliability assessment status of the equipment is obtained using the comprehensive normal assessment value and the comprehensive fault assessment value. The reliability assessment status is either the normal state of the equipment or the fault state of the equipment.

2. The equipment reliability analysis method based on data fusion and evidence networks as described in claim 1, characterized in that, The process of obtaining multi-source numerical sets based on multi-source datasets includes: Perform the following operation on each multi-source dataset: Identify the data types of the multi-source data in the multi-source dataset. If the data type of the multi-source data is numerical, then confirm the multi-source data as multi-source numerical data, summarize the multi-source numerical data, and obtain the multi-source numerical set.

3. The equipment reliability analysis method based on data fusion and evidence networks as described in claim 2, characterized in that, The process of obtaining the first initial history set, the second initial history set, the first initial experimental set, and the second initial experimental set based on multi-source numerical sets includes: Using a preset first partitioning identifier, the multi-source values ​​in the multi-source value set are identified as initial historical values ​​or initial experimental values. The initial historical values ​​and initial experimental values ​​are then summarized to obtain the historical value set and the experimental value set. Using a preset second partitioning identifier, the initial historical values ​​in the historical value set are identified as either the initial historical first value or the initial historical second value. The initial historical first value and the initial historical second value are then summarized to obtain the first initial historical set and the second initial historical set. Using a preset third partitioning identifier, the initial experimental values ​​in the experimental value set are identified as the first initial experimental value or the second initial experimental value. The first initial experimental value and the second initial experimental value are then summarized to obtain the first initial experimental set and the second initial experimental set.

4. The equipment reliability analysis method based on data fusion and evidence networks as described in claim 3, characterized in that, The process of obtaining the initial probability set based on the first historical set, the second historical set, the first experimental set, and the second experimental set includes: Extract the initial historical first value sequentially from the first historical set, and perform the following operation on each extracted initial historical first value: Based on the detection time corresponding to the extracted initial historical first value, a search is performed in the second historical set. If there is a detection time in the second historical set that is the same as the detection time corresponding to the initial historical second value, then the initial historical first value and the initial historical second value are associated to obtain historical value nodes. The historical value nodes are then summarized to obtain a set of historical value nodes. Obtain the first reference value and the second reference value when the equipment is in normal state; obtain the first reference half-axis based on the first reference value; obtain the second reference half-axis based on the second reference value. The first reference value is associated with the second reference value to obtain the fitting center coordinate point. The fitting center coordinate point, the first reference half-axis, the pre-constructed reference coordinate system and the second reference half-axis are used to construct a reference region. All historical numerical nodes in the historical numerical node set are mapped to the reference coordinate system to obtain the discrimination coordinate node set. The discrimination coordinate node set includes multiple discrimination coordinate nodes and the discrimination coordinate nodes correspond one-to-one with the historical numerical nodes. Based on the reference area and the set of discriminant coordinate nodes, a set of qualified historical data nodes is identified, wherein the set of qualified historical data nodes includes multiple qualified historical nodes, and the qualified historical nodes are located within the reference area. A set of discriminative historical numerical nodes is obtained using the first initial history set and the second initial history set, wherein the set of discriminative historical numerical nodes includes multiple discriminative historical numerical nodes; Based on the qualified historical value node set, a target historical value node set is identified in the discrimination historical value node set, wherein the target historical value node set includes multiple target historical value nodes. The number of target historical data nodes in the target historical data node set and the number of discriminative historical data nodes in the discrimination historical data node set are counted separately to obtain the number of qualified historical data nodes and the total number of historical data nodes. The ratio of the number of qualified historical data nodes to the total number of historical data nodes is calculated to obtain the historical ratio value. The historical ratio value is used to determine the historical normal probability and historical failure probability corresponding to the historical data set, where the historical normal probability and historical failure probability are respectively: ； ； in, Indicates the normal probability in history. This represents the initial ratio value. Indicates the probability of historical failures; The normal experimental probability and the experimental failure probability are obtained based on the first experimental set, the second experimental set, the first initial experimental set, the second initial experimental set, and the reference region, wherein the normal experimental probability and the experimental failure probability are respectively: ； ； in, Indicates the normal probability of the experiment. Indicates the experimental ratio value. Indicates the probability of experimental failure; By summarizing the historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability, an initial probability set is obtained.

5. The equipment reliability analysis method based on data fusion and evidence networks as described in claim 4, characterized in that, The reference area is shown below: ； in, Indicates the first reference value. Indicates the second reference value. Indicates the first reference half-axis, Indicates the second reference half-axis. Represents the x-coordinate of the reference coordinate system. This represents the ordinate of the reference coordinate system.

6. The equipment reliability analysis method based on data fusion and evidence networks as described in claim 5, characterized in that, The process of obtaining weighting factors based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set includes: The first historical weight and the first experimental weight are obtained based on the first initial historical set, the first initial experimental set, the first reference value, and the pre-constructed entropy weight method. The second historical weight and the second experimental weight are obtained based on the second initial historical set, the second initial experimental set, the second reference value, and the entropy weight method. Calculate the mean of the first historical weight and the second historical weight to obtain the historical weight factor. Calculate the mean of the first experimental weight and the second experimental weight to obtain the experimental weight factor.

7. The equipment reliability analysis method based on data fusion and evidence networks as described in claim 6, characterized in that, The reliability assessment formula is as follows: ； ； in, This indicates the second normal assessment value. Represents historical weighting factors. Indicates the experimental weighting factor. This indicates the second fault assessment value.

8. The equipment reliability analysis method based on data fusion and evidence networks as described in claim 7, characterized in that, The process of obtaining the equipment's reliability assessment status using comprehensive normal assessment values ​​and comprehensive fault assessment values ​​includes: Compare the overall normal assessment value with the preset normal assessment threshold: If the comprehensive normal assessment value is greater than or equal to the normal assessment threshold, the equipment reliability assessment status is determined to be the normal equipment status. If the overall normal assessment value is less than the normal assessment threshold, and the overall fault assessment value is less than or equal to the preset fault assessment threshold, then the equipment's reliability assessment status is determined to be an equipment fault status.

9. An equipment reliability analysis system based on data fusion and evidence networks, characterized in that, The system includes: The data acquisition and preprocessing module is used to receive reliability analysis instructions and acquire multi-source datasets of the equipment based on the reliability analysis instructions. The multi-source datasets include multiple multi-source data, wherein the multi-source data are historical data or experimental data with detection time. Obtain multi-source numerical sets based on multi-source datasets; The data filtering module is used to obtain the first initial historical set, the second initial historical set, the first initial experimental set, and the second initial experimental set based on multi-source numerical sets. Using a pre-constructed fitted coordinate system, the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set are selected respectively to obtain the first history set, the second history set, the first experiment set, and the second experiment set; The process of using a pre-constructed fitted coordinate system to filter the first initial history set, the second initial history set, the first initial experimental set, and the second initial experimental set to obtain the first history set, the second history set, the first experimental set, and the second experimental set includes: Sort the initial history values ​​in the first initial history set in ascending order to obtain the initial history sequence; The first initial historical value is extracted sequentially from the initial historical sequence, and the following operations are performed on the extracted first initial historical value: Using the extracted initial historical first value, the initial position is determined in the initial historical sequence. The extracted initial historical first value and the initial position are associated to obtain the fitted coordinate points. The fitted coordinate points are then summarized to obtain the fitted coordinate point set. A coordinate system is constructed with the initial position as the x-axis and the initial historical first value as the y-axis. All the fitted coordinate points in the fitted coordinate point set are mapped to the coordinate system to obtain the mapped coordinate point set. The first initial historical value is extracted sequentially from the initial historical sequence, and the following operation is performed on each extracted first initial historical value: Based on the extracted initial historical first value, a target historical first value is identified in the initial historical sequence, wherein the target historical first value is adjacent to and lags behind the extracted initial historical first value. Based on the initial historical first value and the target historical first value, the initial mapping coordinate point and the target mapping coordinate point are identified in the set of mapping coordinate points. Connect the initial mapped coordinate point and the target mapped coordinate point to obtain a polyline segment. Use the target historical first value as the extracted initial historical first value, and return to the step of confirming the target historical first value in the initial historical sequence based on the extracted initial historical first value. Summarize the polyline segments to obtain multiple polyline segments. Perform the following operation on each of the multiple polyline segments: Obtain the slope of the line segment, get the evaluation slope, and determine whether the evaluation slope is zero; If the slope is zero, then either of the two fitted coordinate points corresponding to the broken line segment will be marked as a repeated coordinate point. Remove the initial historical first value corresponding to duplicate coordinate points from the initial historical sequence to obtain the updated historical sequence. Use the updated historical sequence as the initial historical sequence and return to the step of extracting the initial historical first value from the initial historical sequence in sequence until the evaluation slope is not zero. Use the initial historical first value in the updated historical sequence as the first historical set. The second initial history set, the first initial experiment set, and the second initial experiment set are obtained respectively using the second initial history set, the first initial experiment set, and the second initial experiment set; The evaluation value acquisition module is used to obtain an initial probability set based on the first historical set, the second historical set, the first experimental set, and the second experimental set. The initial probability set includes four initial probabilities, which are: historical normal probability, historical failure probability, experimental normal probability, and experimental failure probability. The four initial probabilities in the initial probability set are all input into the pre-constructed evidence network model to obtain the first normal evaluation value and the first fault evaluation value. Weighting factors are obtained based on the first initial history set, the second initial history set, the first initial experiment set, and the second initial experiment set. The weighting factors include historical weighting factors and experimental weighting factors. The second normal evaluation value and the second failure evaluation value are obtained based on the historical weighting factor, the experimental weighting factor, and the pre-constructed reliability evaluation formula. The comprehensive evaluation module is used to calculate the average of the first normal evaluation value and the second normal evaluation value to obtain the comprehensive normal evaluation value, obtain the comprehensive fault evaluation value based on the first fault evaluation value and the second fault evaluation value, and obtain the reliability evaluation status of the equipment using the comprehensive normal evaluation value and the comprehensive fault evaluation value, wherein the reliability evaluation status is the normal state of the equipment or the fault state of the equipment.

Images