Equipment health state assessment method and system, electronic equipment and storage medium
By using the status evaluation model and sparrow search algorithm in the equipment, the signals to be tested are analyzed to evaluate the health status of the equipment, and the problem of difficulty in detecting the decline in equipment health in the prior art is solved, and more accurate and reliable monitoring of the equipment health status is achieved to ensure the safe operation of the equipment.
Patent Information
- Application Number
- CN202411580954.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-07
- Publication Date
- 2025-03-11
AI Technical Summary
It is difficult for the prior art to discover that the health of the equipment has decreased in advance, which affects the safe operation of the entire set of devices and leads to maintenance delays and economic losses.
By obtaining the signal to be tested of the device to be evaluated, input it into the status evaluation model, obtaining the health status evaluation value, and determining the health status of the device based on the difference between the standard health status value and the evaluation value. This method uses a feedforward neural network as the state evaluation model and optimizes the model parameters through the sparrow search algorithm.
It improves the accuracy and reliability of determining the health status of the equipment, promptly detects the sub-health or failure status of the equipment, reduces downtime and economic losses, and ensures the safe operation of the equipment.
Smart Images
Figure CN119598362A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to a device health status assessment method, system, electronic device and storage medium. Background Art
[0002] During the operation of the equipment, the utilization rate of the equipment will inevitably increase. Due to the changing operating environment, the aging of various system components will be accelerated, resulting in a shortened remaining service life. In addition, the sub-healthy state of the equipment is also worthy of attention. If the equipment is often operated in a sub-healthy state, it will cause an increase in system energy consumption. Among them, the energy loss in the sub-healthy state accounts for about 10-40% of the total energy consumption of the cooling system. Complex and changeable working conditions will also affect the system environment quality and equipment reliability.
[0003] If the equipment's health deterioration is not discovered in advance, once a failure occurs during the execution of the mission, not only will the equipment be unable to be repaired in time due to lack of maintenance conditions and professionals, but it will also affect the execution of the mission and cause a large amount of waste of manpower and financial resources. At the same time, the system has been operating under adverse conditions such as pressure and corrosion for a long time. The causes of its failures are complex and the types of failures are diverse, which has a great impact on the overall health of the system and greatly reduces the system's working life and efficiency. If not handled in time, it will endanger the safe operation of the entire device, causing the device to stop production, causing significant economic losses, and even affecting the safety of the entire equipment. Summary of the invention
[0004] The present invention provides a method, system, electronic device and storage medium for evaluating the health status of equipment, so as to solve the defect in the prior art that the health status decline of equipment is not discovered in advance, thus affecting the safe operation of the whole device.
[0005] The present invention provides a method for evaluating the health status of an equipment, comprising the following steps: Obtain the signal to be tested of the device to be evaluated; Inputting the signal to be tested into a state assessment model to obtain a health state assessment value of the signal to be tested output by the state assessment model; The device health status of the device to be evaluated is determined based on the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value.
[0006] According to a device health status assessment method provided by the present invention, the device health status of the device to be assessed is determined based on the difference between a normal signal corresponding to a standard health status value and a signal to be measured corresponding to the health status assessment value, including: Determining a target distance based on a distance between a normal signal corresponding to the standard health status value and a signal to be measured corresponding to the health status assessment value; Based on the target distance, a device health status of the device to be evaluated is determined.
[0007] According to a device health status assessment method provided by the present invention, the distance between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value is determined based on Euclidean distance or Manhattan distance.
[0008] According to a device health status assessment method provided by the present invention, determining the device health status of the device to be assessed based on the target distance includes: When the target distance is less than a first threshold, determining that the device health status of the device to be evaluated is a normal status; When the target distance is greater than or equal to the first threshold and less than the second threshold, determining that the device health state of the device to be evaluated is a sub-health state; When the target distance is greater than or equal to the second threshold and less than a third threshold, determining that the device health state of the device to be evaluated is an abnormal state; When the target distance is greater than or equal to the third threshold and less than a fourth threshold, it is determined that the device health state of the device to be evaluated is a fault state.
[0009] According to a device health status assessment method provided by the present invention, the training step of the status assessment model includes: Obtaining a sample test signal of the device to be evaluated, and a tag health status value of the sample test signal, and determining an initial status evaluation model; the tag health status value includes a standard normal status value, a tag sub-health status value, a tag abnormal status value, and a tag fault status value; Inputting the sample signal to be tested into the initial state assessment model to obtain a predicted health state assessment value output by the initial state assessment model; Based on the difference between the predicted health status evaluation value and the label health status value, a target loss is determined, and based on the target loss and a sparrow search algorithm, parameter iteration is performed on the initial state evaluation model to obtain the state evaluation model.
[0010] According to a method for evaluating the health status of equipment provided by the present invention, the status evaluation model is a feedforward neural network.
[0011] The present invention also provides an equipment health status assessment system, comprising the following modules: An acquisition unit, used for acquiring a signal to be tested from a device to be evaluated; An input unit, used for inputting the signal to be tested into a state assessment model to obtain a health state assessment value of the signal to be tested output by the state assessment model; The determination unit is used to determine the device health state of the device to be evaluated based on the difference between the normal signal corresponding to the standard health state value and the signal to be tested corresponding to the health state evaluation value.
[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-described device health status assessment methods is implemented.
[0013] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the device health status assessment method as described in any one of the above is implemented.
[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the device health status assessment method as described above is implemented.
[0015] The device health status assessment method, system, electronic device and storage medium provided by the present invention obtain the signal to be tested of the device to be evaluated; input the signal to be tested into the status assessment model to obtain the health status assessment value of the signal to be tested output by the status assessment model; and determine the device health status of the device to be evaluated based on the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value. This process can objectively reflect the difference between the current status of the device and the standard health status by comparing the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value, thereby improving the accuracy and reliability of determining the device health status of the device to be evaluated. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 It is a flow chart of the equipment health status assessment method provided by the present invention.
[0018] Figure 2 It is a schematic diagram of the structure of the feedforward neural network provided by the present invention.
[0019] Figure 3It is a schematic diagram of the Manhattan distance provided by the present invention.
[0020] Figure 4 It is a schematic diagram of the Euclidean distance provided by the present invention.
[0021] Figure 5 It is a schematic diagram of the sparrow search algorithm model provided by the present invention.
[0022] Figure 6 It is a structural schematic diagram of the equipment health status assessment system provided by the present invention.
[0023] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0025] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or precedence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type.
[0026] Figure 1 is a flow chart of the device health status assessment method provided by the present invention, such as Figure 1 As shown, the method includes step 110 , step 120 and step 130 .
[0027] Step 110: Acquire a signal to be tested of the device to be evaluated.
[0028] Specifically, in order to reduce maintenance costs, improve the overall reliability and safety of equipment, accurately understand the use and operation status of equipment in real time, and solve problems such as daily maintenance and fault diagnosis and repair of the system, the test signal of the equipment to be evaluated can be analyzed, and then the equipment health status corresponding to the equipment to be evaluated can be determined based on the test signal.
[0029] Here, the device to be evaluated is a device that needs to be evaluated for its health status, and the signal to be tested refers to a target signal that needs to be tested, analyzed or observed. The signal to be tested may include temperature, pressure, flow, etc., which is not specifically limited in the embodiment of the present invention.
[0030] Step 120, inputting the signal to be tested into a state assessment model to obtain a health state assessment value of the signal to be tested output by the state assessment model; Specifically, after the signal to be tested is obtained, the signal to be tested may be input into a state assessment model to obtain a health state assessment value of the signal to be tested output by the state assessment model.
[0031] Here, the health status evaluation value is used to reflect the health status evaluation of the device to be evaluated. The status evaluation model can be a feedforward neural network (FNN), or an LSTM (Long Short-Term Memory), or an RNN (Recurrent Neural Network), or a CNN (Convolutional Neural Network), etc., which is not specifically limited in the embodiment of the present invention.
[0032] Feedforward neural network, also known as feedforward network, is a type of artificial neural network. Figure 2 Schematic diagram of the structure of the feedforward neural network provided by the present invention. Figure 2 As shown in the figure, the feedforward neural network adopts a unidirectional multi-layer structure, in which each layer contains several neurons. In this neural network, each neuron can receive signals from the neurons in the previous layer and generate outputs to the next layer. The 0th layer is called the input layer, the last layer is called the output layer, and the other intermediate layers are called hidden layers (or hidden layers). The hidden layers can be one layer or multiple layers. There is no feedback in the entire network, and the signal propagates unidirectionally from the input layer to the output layer.
[0033] It is understandable that by using a specially trained state assessment model, the features in the signal to be tested can be analyzed more accurately, thereby more accurately assessing the health status of the equipment. The state assessment model is usually trained based on a large amount of data, which can capture the subtle differences in equipment state changes and improve the sensitivity of health status assessment.
[0034] Condition assessment models are usually able to quickly process the signals to be tested and provide health status assessment values in real time or near real time. This allows the maintenance team to respond quickly to any changes in equipment status and take necessary maintenance measures, reducing downtime and potential failures, thereby improving safety.
[0035] Step 130 : determining the device health status of the device to be evaluated based on the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value.
[0036] Specifically, after the health status evaluation value is output based on the status evaluation model, the device health status of the device to be evaluated can be determined based on the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value. Here, the device health status is used to reflect the health status of the device to be evaluated.
[0037] Here, the distance between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value can be calculated, and then the device health status of the device to be evaluated can be determined based on the distance between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value.
[0038] It should be noted that there is a mapping relationship between the standard health status value and the normal signal, and there is also a mapping relationship between the health status assessment value and the signal to be tested.
[0039] It can be understood that by comparing the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value, the difference between the current status of the device and the standard health status can be objectively reflected.
[0040] The method provided by the embodiment of the present invention obtains a signal to be tested of a device to be evaluated; inputs the signal to be tested into a state evaluation model to obtain a health state evaluation value of the signal to be tested output by the state evaluation model; and determines the device health state of the device to be evaluated based on the difference between a normal signal corresponding to a standard health state value and a signal to be tested corresponding to the health state evaluation value. This process can objectively reflect the difference between the current state of the device and the standard health state by comparing the difference between a normal signal corresponding to a standard health state value and a signal to be tested corresponding to a health state evaluation value, thereby improving the accuracy and reliability of determining the device health state of the device to be evaluated.
[0041] Based on the above embodiment, step 130 includes: Step 131, determining a target distance based on the distance between a normal signal corresponding to the standard health status value and a signal to be measured corresponding to the health status assessment value; Step 132: Determine the device health status of the device to be evaluated based on the target distance.
[0042] Specifically, the target distance may be determined based on the distance between a normal signal corresponding to a standard health status value and a signal to be measured corresponding to a health status assessment value.
[0043] Here, the distance between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value can be determined based on the Euclidean distance and the Manhattan distance.
[0044] Manhattan distance is the sum of the distances projected by the line segment formed by two points on the axis in the fixed rectangular coordinate system of Euclidean space. Figure 3 It is a schematic diagram of the Manhattan distance provided by the present invention, such as Figure 3 As shown, the red, yellow and blue lines are Manhattan distances.
[0045] The Manhattan distance calculation formula is: In the formula, is the Manhattan distance, , are the values of the two data, k is the number of data to be calculated.
[0046] It should be noted that the embodiment of the present invention uses the traditional Manhattan distance model to obtain the Manhattan distance between the normal signal and the signal to be tested through model calculation, and then sums up the distances of each signal to obtain the final distance, and makes a judgment based on the final distance to obtain the health status of the system and the fault diagnosis prediction.
[0047] It is understandable that the Manhattan distance is sensitive to all dimensions of the signal, so it can capture the difference between the signal under test and the normal signal in all dimensions, which helps to analyze the signal characteristics more comprehensively. By calculating the Manhattan distance between the signal under test and the normal signal, small deviations can be discovered in time. This is especially important for early fault detection, which helps to take necessary maintenance measures before serious problems occur in the system.
[0048] Furthermore, the Manhattan distance model can adapt to different signal characteristics. Whether it is time domain features, frequency domain features or other features, the similarity between signals can be evaluated by calculating the Manhattan distance.
[0049] Euclidean distance (also known as Euclidean metric) is a distance definition widely used in mathematics, referring to the real distance between two points in multidimensional space, or the natural length of a vector (that is, the distance from the point to the origin). Figure 4 is a schematic diagram of the Euclidean distance provided by the present invention, such as Figure 4 As shown, the Euclidean distance between two points in two-dimensional space is equal to the actual distance between the two points.
[0050] It should be noted that the embodiment of the present invention uses the traditional Euclidean distance model to obtain the Euclidean distance between the normal signal and the signal to be tested through model calculation, and then sums up the distances of each signal to obtain the final distance, and makes a judgment based on the final distance to obtain the health status of the system and the fault diagnosis prediction.
[0051] Based on the above embodiment, step 132 includes: When the target distance is less than a first threshold, determining that the device health status of the device to be evaluated is a normal status; When the target distance is greater than or equal to the first threshold and less than the second threshold, determining that the device health state of the device to be evaluated is a sub-health state; When the target distance is greater than or equal to the second threshold and less than a third threshold, determining that the device health state of the device to be evaluated is an abnormal state; When the target distance is greater than or equal to the third threshold and less than a fourth threshold, it is determined that the device health state of the device to be evaluated is a fault state.
[0052] Specifically, when the target distance is less than a first threshold, the device health status of the device to be evaluated is determined to be a normal state; when the target distance is greater than or equal to the first threshold and less than a second threshold, the device health status of the device to be evaluated is determined to be a sub-healthy state; when the target distance is greater than or equal to the second threshold and less than a third threshold, the device health status of the device to be evaluated is determined to be an abnormal state; when the target distance is greater than or equal to the third threshold and less than a fourth threshold, the device health status of the device to be evaluated is determined to be a fault state.
[0053] Here, the sub-health state means that the performance of the device to be evaluated has declined, but has not yet reached the level of failure and can still maintain operation. The settings of the first threshold, the second threshold, the third threshold and the fourth threshold can be adjusted according to actual scenarios, and the embodiments of the present invention do not specifically limit this.
[0054] It is understandable that by setting different thresholds, the health status of the equipment to be evaluated can be subdivided into multiple levels such as normal, sub-healthy, abnormal and faulty. This clear classification helps to quickly identify the current status of the equipment and take corresponding maintenance measures.
[0055] When the device to be evaluated is in a sub-healthy or abnormal state, although it has not yet reached a fault state, it can be judged by the threshold. This helps to discover potential problems in advance and take preventive measures to prevent the device from further deteriorating to a fault state.
[0056] In addition, different health states correspond to different maintenance requirements, which optimizes resource allocation. For example, equipment in a normal state may only require routine inspections, while equipment in a subhealthy or abnormal state may require more frequent monitoring or maintenance. Through threshold judgment, maintenance plans can be formulated more accurately and resource allocation can be optimized.
[0057] Based on the above embodiment, the training step of the state assessment model includes: Step 210, obtaining a sample test signal of the device to be evaluated and a tag health status value of the sample test signal, and determining an initial status evaluation model; the tag health status value includes a standard normal status value, a tag sub-health status value, a tag abnormal status value and a tag fault status value; Step 220, inputting the sample signal to be tested into an initial state assessment model to obtain a predicted health state assessment value output by the initial state assessment model; Step 230, based on the difference between the predicted health status evaluation value and the label health status value, determine the target loss, and based on the target loss and the sparrow search algorithm, perform parameter iteration on the initial state evaluation model to obtain the state evaluation model.
[0058] Specifically, in order to better obtain the state assessment model, training can be performed based on the following steps: First, obtain the sample test signal of the device to be evaluated and the tag health status value of the sample test signal, and determine the initial status evaluation model. Here, the tag health status value includes the standard normal status value, the tag sub-health status value, the tag abnormal status value and the tag fault status value.
[0059] Here, the parameters of the initial state assessment model may be preset or randomly generated, and this is not specifically limited in the embodiment of the present invention.
[0060] The sample signal to be tested is input into the initial state assessment model to obtain the predicted health state assessment value output by the initial state assessment model.
[0061] After obtaining the predicted health status assessment value based on the initial state assessment model, the target loss can be determined based on the difference between the predicted health status assessment value and the labeled health status value. Based on the target loss and the Sparrow Search Algorithm (SSA), the parameters of the initial state assessment model are iterated, and the initial state assessment model after the parameter iteration is used as the state assessment model.
[0062] Figure 5 It is a schematic diagram of the sparrow search algorithm model provided by the present invention, such as Figure 5As shown in the figure, the sparrow search algorithm is a new type of swarm intelligence optimization algorithm, which is mainly inspired by the foraging behavior and anti-predation behavior of sparrows. In the process of sparrow foraging, there are finders (explorers) and joiners (followers). The finders are responsible for finding food in the population and providing foraging areas and directions for the entire sparrow population, while the joiners use the finders to obtain food. In order to obtain food, sparrows can usually use the two behavioral strategies of finders and joiners for foraging. Individuals in the population will monitor the behavior of other individuals in the group, and the attackers in the population will compete for food resources with high-intake companions to increase their predation rate. In addition, when the sparrow population realizes the danger, it will perform anti-predation behavior. The sparrow search algorithm is very effective in finding the extreme value of the classic test function, and can quickly and accurately find the extreme point of the function.
[0063] The process of using the sparrow search algorithm is as follows: 1. Initialize the population and related parameters, and calculate the fitness value of the initial population; 2. Update the finder's location; 3. Update the joiner's location; 4. Update awareness of dangerous sparrow locations; 5. Determine whether the stopping condition is met. If so, output the optimal sparrow position, otherwise return to step 2.
[0064] It can be understood that the greater the difference between the predicted health status evaluation value and the labeled health status value, the greater the target loss; the smaller the difference between the predicted health status evaluation value and the labeled health status value, the smaller the target loss.
[0065] It should be noted that the sparrow search algorithm is very effective in finding extreme values of classic test functions. It can quickly and accurately find the extreme points of the function and speed up the algorithm's running efficiency.
[0066] Based on any of the above embodiments, a method for evaluating the health status of a device comprises the following steps: The first step is to obtain the signal to be tested of the device to be evaluated.
[0067] The second step is to obtain the sample test signal of the device to be evaluated, as well as the label health status value of the sample test signal, and determine the initial state evaluation model; the label health status value includes the standard normal state value, the label sub-health state value, the label abnormal state value and the label fault state value. Then input the sample test signal into the initial state evaluation model to obtain the predicted health state evaluation value output by the initial state evaluation model. Finally, based on the difference between the predicted health state evaluation value and the label health state value, determine the target loss. Based on the target loss and the sparrow search algorithm, perform parameter iteration on the initial state evaluation model to obtain the state evaluation model. Here, the state evaluation model is a feedforward neural network.
[0068] The third step is to input the signal to be tested into the state assessment model to obtain the health state assessment value of the signal to be tested output by the state assessment model.
[0069] The fourth step is to determine the target distance based on the distance between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value, wherein the distance between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value is determined based on the Euclidean distance or the Manhattan distance.
[0070] In the fifth step, when the target distance is less than the first threshold, the device health status of the device to be evaluated is determined to be a normal state; when the target distance is greater than or equal to the first threshold and less than the second threshold, the device health status of the device to be evaluated is determined to be a sub-healthy state; when the target distance is greater than or equal to the second threshold and less than the third threshold, the device health status of the device to be evaluated is determined to be an abnormal state; when the target distance is greater than or equal to the third threshold and less than the fourth threshold, the device health status of the device to be evaluated is determined to be a fault state.
[0071] The SSA-FNN health status assessment model provided by the embodiment of the present invention has a very good effect on finding extreme values of classic test functions, can quickly and accurately find the extreme points of the function, and speed up the operation efficiency of the algorithm. At the same time, the Manhattan distance model and the Euclidean distance model are used for calculation and analysis; finally, different upper limit values are set to distinguish normal, sub-healthy, abnormal and fault signals. Analysis shows that the Manhattan distance model and the Euclidean distance model have the advantages of fast calculation speed, stable results, and accurate prediction results, and can be used as the basis for judging the health status of equipment.
[0072] The method provided in the embodiment of the present invention is to reduce maintenance costs, improve the overall reliability and safety of equipment, accurately understand the use and operation status of equipment in real time, and solve the problems of daily maintenance and fault diagnosis and repair of the system. On the basis of analyzing the performance parameter testing method of the system, a quantitative evaluation module of the system health status is added to evaluate the health status of the equipment, so as to realize the function of timely grasping various information of the equipment and discovering the hidden dangers of equipment failure as early as possible.
[0073] The device health status assessment system provided by the present invention is described below. The device health status assessment system described below and the device health status assessment method described above can be referenced to each other.
[0074] Based on any of the above embodiments, the present invention provides a device health status assessment system. Figure 6 is a schematic diagram of the structure of the equipment health status assessment system provided by the present invention, such as Figure 6 As shown, the system includes: An acquisition unit 610 is used to acquire a signal to be tested of a device to be evaluated; An input unit 620, configured to input the signal to be tested into a state assessment model to obtain a health state assessment value of the signal to be tested output by the state assessment model; The determination unit 630 is used to determine the device health state of the device to be evaluated based on the difference between the normal signal corresponding to the standard health state value and the signal to be tested corresponding to the health state evaluation value.
[0075] The system provided by the embodiment of the present invention obtains the signal to be tested of the device to be evaluated; inputs the signal to be tested into the state evaluation model to obtain the health status evaluation value of the signal to be tested output by the state evaluation model; and determines the device health status of the device to be evaluated based on the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value. This process can objectively reflect the difference between the current state of the device and the standard health status by comparing the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value, thereby improving the accuracy and reliability of determining the device health status of the device to be evaluated.
[0076] Based on any of the foregoing embodiments, the determining unit 530 is specifically configured to: a target distance determination unit, configured to determine a target distance based on a distance between a normal signal corresponding to the standard health status value and a signal to be measured corresponding to the health status assessment value; The device health status determining unit is used to determine the device health status of the device to be evaluated based on the target distance.
[0077] Based on any of the above embodiments, the distance between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value is determined based on Euclidean distance or Manhattan distance.
[0078] Based on any of the above embodiments, the device health status determination unit is specifically configured to: When the target distance is less than a first threshold, determining that the device health status of the device to be evaluated is a normal status; When the target distance is greater than or equal to the first threshold and less than the second threshold, determining that the device health state of the device to be evaluated is a sub-health state; When the target distance is greater than or equal to the second threshold and less than a third threshold, determining that the device health state of the device to be evaluated is an abnormal state; When the target distance is greater than or equal to the third threshold and less than a fourth threshold, it is determined that the device health state of the device to be evaluated is a fault state.
[0079] Based on any of the above embodiments, it further includes a training unit, wherein the training unit is specifically used to: Obtaining a sample test signal of the device to be evaluated, and a tag health status value of the sample test signal, and determining an initial status evaluation model; the tag health status value includes a standard normal status value, a tag sub-health status value, a tag abnormal status value, and a tag fault status value; Inputting the sample signal to be tested into the initial state assessment model to obtain a predicted health state assessment value output by the initial state assessment model; Based on the difference between the predicted health status evaluation value and the label health status value, a target loss is determined, and based on the target loss and a sparrow search algorithm, parameter iteration is performed on the initial state evaluation model to obtain the state evaluation model.
[0080] Based on any of the above embodiments, the state assessment model is a feedforward neural network.
[0081] Figure 7 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the device health status assessment method, which includes: obtaining a signal to be tested of the device to be evaluated; inputting the signal to be tested into a status assessment model to obtain a health status assessment value of the signal to be tested output by the status assessment model; and determining the device health status of the device to be evaluated based on the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value.
[0082] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0083] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the equipment health status assessment method provided by the above methods, which method includes: obtaining a test signal of the equipment to be evaluated; inputting the test signal into a status assessment model to obtain a health status assessment value of the test signal output by the status assessment model; and determining the equipment health status of the equipment to be evaluated based on the difference between a normal signal corresponding to a standard health status value and a test signal corresponding to the health status assessment value.
[0084] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the equipment health status assessment method provided by the above-mentioned methods, the method comprising: obtaining a test signal of the equipment to be evaluated; inputting the test signal into a status assessment model to obtain a health status assessment value of the test signal output by the status assessment model; and determining the equipment health status of the equipment to be evaluated based on the difference between a normal signal corresponding to a standard health status value and the test signal corresponding to the health status assessment value.
[0085] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for evaluating the health status of equipment, characterized in that: include: Obtain the signal to be tested of the device to be evaluated; Inputting the signal to be tested into a state assessment model to obtain a health state assessment value of the signal to be tested output by the state assessment model; The device health status of the device to be evaluated is determined based on the difference between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status evaluation value.
2. The device health status assessment method according to claim 1, characterized in that: The determining the device health state of the device to be evaluated based on the difference between the normal signal corresponding to the standard health state value and the signal to be tested corresponding to the health state evaluation value includes: Determining a target distance based on a distance between a normal signal corresponding to the standard health status value and a signal to be measured corresponding to the health status assessment value; Based on the target distance, a device health status of the device to be evaluated is determined.
3. The device health status assessment method according to claim 2, characterized in that: The distance between the normal signal corresponding to the standard health status value and the signal to be tested corresponding to the health status assessment value is determined based on the Euclidean distance or the Manhattan distance.
4. The device health status assessment method according to claim 2, characterized in that: The determining, based on the target distance, the device health status of the device to be evaluated includes: When the target distance is less than a first threshold, determining that the device health status of the device to be evaluated is a normal status; When the target distance is greater than or equal to the first threshold and less than the second threshold, determining that the device health state of the device to be evaluated is a sub-health state; When the target distance is greater than or equal to the second threshold and less than a third threshold, determining that the device health state of the device to be evaluated is an abnormal state; When the target distance is greater than or equal to the third threshold and less than a fourth threshold, it is determined that the device health state of the device to be evaluated is a fault state.
5. The device health status assessment method according to any one of claims 1 to 4, characterized in that: The training step of the state assessment model includes: Obtaining a sample test signal of the device to be evaluated, and a tag health status value of the sample test signal, and determining an initial status evaluation model; the tag health status value includes a standard normal status value, a tag sub-health status value, a tag abnormal status value, and a tag fault status value; Inputting the sample signal to be tested into the initial state assessment model to obtain a predicted health state assessment value output by the initial state assessment model; Based on the difference between the predicted health status evaluation value and the label health status value, a target loss is determined, and based on the target loss and a sparrow search algorithm, parameter iteration is performed on the initial state evaluation model to obtain the state evaluation model.
6. The device health status assessment method according to any one of claims 1 to 4, characterized in that: The state assessment model is a feedforward neural network.
7. A device health status assessment system, characterized in that: include: An acquisition unit, used for acquiring a signal to be tested from a device to be evaluated; An input unit, used to input the signal to be tested into a state assessment model to obtain a health state assessment value of the signal to be tested output by the state assessment model; The determination unit is used to determine the device health state of the device to be evaluated based on the difference between the normal signal corresponding to the standard health state value and the signal to be tested corresponding to the health state evaluation value.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the device health status assessment method according to any one of claims 1 to 6 is implemented.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the device health status assessment method according to any one of claims 1 to 6 is implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the device health status assessment method according to any one of claims 1 to 6 is implemented.