A method and system for evaluating performance of ferromagnetic shape memory metal

Abstract

The present invention discloses a method and system for evaluating the performance of ferromagnetic shape memory metals. By obtaining the morphological parameters of standard samples and deformation data within the limit stress range, the deformation amount-temperature-recovery rate relationship is determined. Based on this relationship, the efficient recovery temperature range is identified, and the historical deformation data of the sample within a preset time period is restored and analyzed. A deformation recovery prediction model is constructed using the LSTM algorithm to predict the deformation recovery of the metal to be evaluated. Finally, the fatigue of the metal is evaluated based on the prediction results to determine its service life. This method improves the accuracy of the performance evaluation of ferromagnetic shape memory metals and provides scientific usage suggestions.

Description

Technical Field

[0001] The present invention relates to the technical field of metal performance evaluation, and in particular to a ferromagnetic shape memory metal performance evaluation method and system. Background Art

[0002] Ferromagnetic shape memory metals (FSMAs) are a type of smart material that can achieve shape recovery through changes in magnetic field or temperature under certain conditions. This type of material combines the characteristics of ferromagnetism and shape memory effect, and has broad application prospects in aerospace, mechanical manufacturing, biomedicine and other fields. Ferromagnetic shape memory metals can deform under the action of external forces and return to their initial shape when the external forces disappear or under certain conditions. They have good fatigue resistance and long life. However, as the number of uses increases, ferromagnetic shape memory metals may gradually decline in performance or even fail due to fatigue, stress relaxation and other reasons. Therefore, how to accurately evaluate their performance, fatigue and remaining life has become an important topic in current research and application.

[0003] Most of the existing ferromagnetic shape memory metal performance evaluation methods focus on single performance tests in laboratory environments, such as tensile, compression, bending and other mechanical performance tests. However, these tests often cannot fully reflect the complex working conditions of the material in actual applications and the performance changes after long-term use. At the same time, traditional evaluation methods rely more on manual judgment, lack of systematicity and intelligence, and are difficult to meet the modern industry's requirements for efficiency, accuracy and operability in the application of smart materials.

[0004] In order to improve the application performance and safety of ferromagnetic shape memory metals, a full life cycle performance evaluation method and system based on intelligent algorithms is urgently needed. By combining the shape memory effect with advanced machine learning algorithms, the performance changes of materials at different stages of use can be more accurately predicted, and a scientific basis can be provided for the use, maintenance and update of materials. This will help extend the service life of ferromagnetic shape memory metals, reduce maintenance costs, and improve the reliability of the overall system.

[0005] Therefore, this paper proposes a ferromagnetic shape memory metal performance evaluation method and system, aiming to achieve comprehensive performance evaluation of ferromagnetic shape memory metals through multi-dimensional data analysis and intelligent algorithm prediction. This method will combine the shape memory characteristics, stress-strain relationship, temperature response and other information of the material to provide a scientific, intelligent and operational evaluation method, providing strong support for the performance monitoring and optimization of ferromagnetic shape memory metals in practical applications. Summary of the invention

[0006] In order to solve at least one of the above technical problems, the present invention proposes a method and system for evaluating the performance of ferromagnetic shape memory metals.

[0007] The first aspect of the present invention provides a method for evaluating the performance of a ferromagnetic shape memory metal, comprising:

[0008] Obtaining a standard production sample of a ferromagnetic shape memory metal, extracting initial morphological parameters of the standard production sample, and obtaining standard morphological data of the ferromagnetic shape memory metal;

[0009] Obtaining the ultimate stress of the ferromagnetic shape memory metal, performing stress testing on the standard production sample within the ultimate stress range to obtain a deformed production sample, performing heat treatment on the deformed production sample, obtaining the recovery rate of the deformed sample at different temperatures, and determining the relationship between the deformation recovery and temperature of the production samples with different deformation amounts, to obtain deformation amount-temperature-recovery rate relationship data;

[0010] Identify the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts according to the deformation amount-temperature-recovery rate relationship data, and use the efficient recovery temperature range as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal;

[0011] Acquire historical deformation data of the ferromagnetic shape memory metal within a preset time period, and restore the deformation of the ferromagnetic shape memory metal within the preset time period according to the recommended temperature range for deformation recovery to obtain historical deformation recovery change data;

[0012] A deformation recovery prediction model is constructed based on the LSTM algorithm and historical deformation recovery change data, and the deformation recovery of the ferromagnetic shape memory metal to be evaluated is predicted according to the deformation recovery prediction model to obtain a deformation recovery prediction result;

[0013] A metal fatigue evaluation is performed on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result to obtain an evaluation result, and an update time of the magnetic shape memory metal is determined according to the evaluation result.

[0014] In this solution, the standard production sample of the ferromagnetic shape memory metal is obtained, and the initial morphological parameters of the standard production sample are extracted to obtain the standard morphological data of the ferromagnetic shape memory metal, specifically:

[0015] Obtaining a standard production sample of a ferromagnetic shape memory metal, obtaining laser scanning data of the standard production sample, and constructing a three-dimensional model of the standard production sample according to the laser scanning data;

[0016] Divide the surface of the three-dimensional model into N triangular meshes, obtain vertex coordinate information of each mesh, and calculate the normal vector of each triangular mesh according to the vertex coordinate information of each mesh;

[0017] Normalize the normal vector of each triangular mesh to obtain a triangular mesh with a normal vector length of 1;

[0018] Calculating the dot product of the normal vectors of two adjacent triangular meshes in the three-dimensional model according to the normalized normal vectors, and calculating the angle information of the two adjacent triangles according to the dot product of the normal vectors;

[0019] Mapping the angle information to the three-dimensional model, determining the angle change in the three-dimensional model, presetting an angle change threshold, marking the triangle edges whose angle change is greater than the angle change threshold, and drawing the contour of the three-dimensional model based on the marked triangle edges to obtain the contour morphology data of the standard production sample;

[0020] According to the contour morphology, the dimension data of the standard production sample is calculated in the image processing model, and the contour morphology data and the dimension data are integrated into the initial morphological parameters of the standard production sample, which are calibrated as the standard morphological data of the ferromagnetic shape memory metal.

[0021] In this scheme, the limit stress of the ferromagnetic shape memory metal is obtained, the standard production sample is subjected to stress testing within the limit stress range to obtain a deformed production sample, the deformed production sample is subjected to heat treatment, the recovery rate of the deformed sample at different temperatures is obtained, and the relationship between the deformation recovery and temperature of the production samples with different deformation amounts is determined to obtain the deformation amount-temperature-recovery rate relationship data, specifically:

[0022] Obtaining the limit stress of the ferromagnetic shape memory metal, evenly dividing the limit stress according to a preset step size, and determining a stress test data set within the limit stress range;

[0023] Obtaining quantity information of the test data in the stress test data set, and obtaining the same quantity of ferromagnetic shape memory metal standard production samples as the test data;

[0024] Apply different stress test forces to each standard production sample according to the stress test data set to obtain a deformed production sample;

[0025] Acquire a three-dimensional model of the deformed production sample and extract morphological data of the deformed sample, compare the morphological data of the deformed sample with standard morphological data of ferromagnetic shape memory metal, and obtain the deformation amount of each deformed production sample;

[0026] The production sample with the most serious deformation variable is subjected to heating treatment to obtain the temperature value required for the production sample with the most serious deformation variable to recover to the standard shape, and the temperature value is calibrated as the limit temperature value;

[0027] Dividing the limit temperature value into equal parts according to the preset value to determine the heating temperature gradient of the deformation production sample;

[0028] The deformed production sample under each deformation amount is subjected to a heating treatment according to the heating temperature gradient, and the deformation recovery sample morphology data after the heating treatment is obtained, and the deformation recovery sample morphology data is compared with the ferromagnetic shape memory metal standard morphology data to obtain the deformation amount of each deformation recovery production sample;

[0029] Calculating the deformation recovery rate according to the deformation amount of each deformation recovery production sample and the deformation amount of each deformation production sample to obtain the deformation recovery rates of the deformation production samples at different temperatures and with different deformation amounts;

[0030] According to the deformation recovery rates of the deformed production samples at different temperatures and with different deformation amounts, the relationship between the deformation recovery and temperature of the production samples with different deformation amounts is determined to obtain deformation amount-temperature-recovery rate relationship data.

[0031] In this solution, the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts is identified according to the deformation amount-temperature-recovery rate relationship data, and the efficient recovery temperature range is used as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal, specifically:

[0032] According to the deformation-temperature-recovery rate relationship data, the temperature-recovery rate relationship data sets under different deformations are standardized to obtain a two-dimensional relationship data set;

[0033] The DBSCAN clustering algorithm is introduced to classify data with similar temperature-recovery rates into one category. The Manhattan distance between each data point and other data points in the two-dimensional relationship data set is calculated based on the DBSCAN algorithm to find the Kth nearest neighbor distance of each data point.

[0034] The nearest neighbor distance of each data point is sorted in ascending order, and the sorted nearest neighbor distance is plotted in a nearest neighbor distance change curve to obtain a K-distance graph;

[0035] Determine the inflection point of the K-distance graph, calibrate the nearest neighbor value corresponding to the inflection point as the neighborhood radius ε, and determine the minimum number of samples minPts within the neighborhood radius according to the data dimension of the two-dimensional relationship data set;

[0036] Mark each data point in the two-dimensional relational dataset as unvisited, and create an empty cluster set and a noise point set;

[0037] Visit each data point in the two-dimensional data set in turn, mark the data point that enters the visit state as data point P, and mark P as visited, find all points in the ε neighborhood of P according to the neighborhood radius, and mark them as a set NP;

[0038] If the data point in NP is less than minPts, P is marked as a noise point. If the data point in NP is not less than minPts, P is marked as a core point, a new cluster C is created, and the data point P is added to cluster C.

[0039] For each data point Q in cluster C, if Q is a core point, find all points NQ in the ε neighborhood of Q. If the data points of NQ are not less than minPts, add all points in NQ to cluster C until all data points in the two-dimensional data set are visited, and obtain the clustering result of temperature-recovery rate;

[0040] Perform recovery performance analysis on each clustering result according to the recovery rate of each clustering result, retain the clustering results with recovery performance higher than the preset value and mark them with recovery performance labels, and determine the deformation variable to which the temperature-recovery rate in each clustering result belongs;

[0041] According to the recovery performance label of each clustering result and the corresponding deformation amount, the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts is determined and calibrated as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal.

[0042] In this solution, the historical deformation data of the ferromagnetic shape memory metal within a preset time period is obtained, and the deformation of the ferromagnetic shape memory metal within the preset time period is restored according to the recommended temperature range for deformation recovery, so as to obtain the historical deformation recovery change data, specifically:

[0043] Determine the heating power and temperature controllable range required for deformation recovery of the ferromagnetic shape memory metal according to the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal, and construct a heating system for deformation recovery of the ferromagnetic shape memory metal according to the heating power and temperature controllable range;

[0044] Acquire multiple historical deformation data of the ferromagnetic shape memory metal within a preset time period, and when each deformation occurs, restore each deformation of the ferromagnetic shape memory metal within the preset time period according to the recommended temperature range for deformation recovery, and acquire the morphological data of the ferromagnetic shape memory metal after deformation recovery according to the recommended temperature range for deformation recovery;

[0045] The recovery rate of each deformation recovery is determined according to the morphological data of the ferromagnetic shape memory metal after deformation recovery, and the recovery rate of each deformation recovery is sorted according to a time series to obtain historical deformation recovery change data within a preset time period.

[0046] In this solution, the deformation recovery prediction model is constructed based on the LSTM algorithm and the historical deformation recovery change data, and the deformation recovery of the ferromagnetic shape memory metal to be evaluated is predicted according to the deformation recovery prediction model to obtain the deformation recovery prediction result, which is specifically:

[0047] A deformation recovery prediction model is built based on the LSTM algorithm. The input data shape of the model input layer is determined according to the data format of the historical deformation recovery change data. The LSTM layer, Dropout layer, fully connected layer and output layer are built. The mean square error is used as the model loss function, and Adam is selected as the model optimizer.

[0048] The historical deformation recovery data is divided into a training set and a test set according to a preset ratio, the training set is imported into the deformation recovery prediction model for model training, the model performance is monitored through the test set, and the model parameters are adjusted according to the prediction accuracy of the test set, wherein the model parameters include a learning rate, a number of LSTM layers, and a Dropout rate;

[0049] The deformation recovery change data of the ferromagnetic shape memory metal to be evaluated for performance in the current time period is obtained, the deformation recovery change data in the current time period is imported into the deformation recovery prediction model, the deformation recovery rate of the ferromagnetic shape memory metal to be evaluated for performance in a future preset time period is predicted, and the deformation recovery prediction result is obtained.

[0050] In this solution, the metal fatigue evaluation of the ferromagnetic shape memory metal to be evaluated is performed according to the deformation recovery prediction result to obtain an evaluation result, and the update time of the magnetic shape memory metal is determined according to the evaluation result, specifically:

[0051] Performing a metal fatigue evaluation on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result, calculating the remaining life of the ferromagnetic shape memory metal to be evaluated for performance according to the metal fatigue, and obtaining a performance evaluation result of the ferromagnetic shape memory metal;

[0052] Obtaining performance requirement data of the ferromagnetic shape memory metal, and judging whether the ferromagnetic shape memory metal meets the performance requirement according to the performance evaluation result of the ferromagnetic shape memory metal, and if not, performing an update operation on the ferromagnetic shape memory metal;

[0053] If satisfied, determine the time point at which the performance requirement threshold is reached according to the performance evaluation result of the ferromagnetic shape memory metal, determine the remaining usable time of the ferromagnetic shape memory metal, and perform an update operation on the ferromagnetic shape memory metal according to the time point at which the performance requirement threshold is reached;

[0054] A usable time length threshold is preset, and when the usable time length is greater than the usable time length threshold, the ferromagnetic shape memory metal is marked as a first-class product; when the usable time length is less than the usable time length threshold, the ferromagnetic shape memory metal is marked as a second-class product;

[0055] According to the deformation recovery prediction results, the downward trend of the deformation recovery rate of the first and second category products is determined, and according to the downward trend, the periodic performance inspection frequency and inspection items of the first and second category products are determined to obtain a periodic performance inspection plan.

[0056] The second aspect of the present invention further provides a ferromagnetic shape memory metal performance evaluation system, the system comprising: a memory, a processor, the memory comprising a ferromagnetic shape memory metal performance evaluation method program, the ferromagnetic shape memory metal performance evaluation method program when executed by the processor, implements the following steps:

[0057] Obtaining a standard production sample of a ferromagnetic shape memory metal, extracting initial morphological parameters of the standard production sample, and obtaining standard morphological data of the ferromagnetic shape memory metal;

[0058] Obtaining the ultimate stress of the ferromagnetic shape memory metal, performing stress testing on the standard production sample within the ultimate stress range to obtain a deformed production sample, performing heat treatment on the deformed production sample, obtaining the recovery rate of the deformed sample at different temperatures, and determining the relationship between the deformation recovery and temperature of the production samples with different deformation amounts, to obtain deformation amount-temperature-recovery rate relationship data;

[0059] Identify the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts according to the deformation amount-temperature-recovery rate relationship data, and use the efficient recovery temperature range as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal;

[0060] Acquire historical deformation data of the ferromagnetic shape memory metal within a preset time period, and restore the deformation of the ferromagnetic shape memory metal within the preset time period according to the recommended temperature range for deformation recovery to obtain historical deformation recovery change data;

[0061] A deformation recovery prediction model is constructed based on the LSTM algorithm and historical deformation recovery change data, and the deformation recovery of the ferromagnetic shape memory metal to be evaluated is predicted according to the deformation recovery prediction model to obtain a deformation recovery prediction result;

[0062] A metal fatigue evaluation is performed on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result to obtain an evaluation result, and an update time of the magnetic shape memory metal is determined according to the evaluation result.

[0063] The present invention discloses a method and system for evaluating the performance of ferromagnetic shape memory metals. By obtaining the morphological parameters of standard samples and deformation data within the limit stress range, the deformation amount-temperature-recovery rate relationship is determined. Based on this relationship, the efficient recovery temperature range is identified, and the historical deformation data of the sample within a preset time period is restored and analyzed. A deformation recovery prediction model is constructed using the LSTM algorithm to predict the deformation recovery of the metal to be evaluated. Finally, the fatigue of the metal is evaluated based on the prediction results to determine its service life. This method improves the accuracy of the performance evaluation of ferromagnetic shape memory metals and provides scientific usage suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flow chart showing a method for evaluating the performance of a ferromagnetic shape memory metal according to the present invention is shown;

[0065] Figure 2 A flow chart showing the present invention for obtaining historical deformation recovery situation change data;

[0066] Figure 3 A flow chart showing the deformation recovery prediction result obtained by the present invention is shown;

[0067] Figure 4 A block diagram of a ferromagnetic shape memory metal performance evaluation system of the present invention is shown. DETAILED DESCRIPTION

[0068] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0069] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0070] Figure 1 A flow chart of a ferromagnetic shape memory metal performance evaluation method of the present invention is shown.

[0071] like Figure 1 As shown, the first aspect of the present invention provides a method for evaluating the performance of a ferromagnetic shape memory metal, comprising:

[0072] S102, obtaining a standard production sample of the ferromagnetic shape memory metal, extracting initial morphological parameters of the standard production sample, and obtaining standard morphological data of the ferromagnetic shape memory metal;

[0073] S104, obtaining the limit stress of the ferromagnetic shape memory metal, performing stress testing on the standard production sample within the limit stress range to obtain a deformed production sample, performing heat treatment on the deformed production sample, obtaining the recovery rate of the deformed sample at different temperatures, and determining the relationship between the deformation recovery and temperature of the production samples with different deformation amounts, to obtain deformation amount-temperature-recovery rate relationship data;

[0074] S106, identifying an efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts according to the deformation amount-temperature-recovery rate relationship data, and using the efficient recovery temperature range as a recommended temperature range for deformation recovery of the ferromagnetic shape memory metal;

[0075] S108, obtaining historical deformation data of the ferromagnetic shape memory metal within a preset time period, and restoring the deformation of the ferromagnetic shape memory metal within the preset time period according to a deformation recovery recommended temperature range, to obtain historical deformation recovery change data;

[0076] S110, constructing a deformation recovery prediction model based on the LSTM algorithm and historical deformation recovery change data, and predicting the deformation recovery of the ferromagnetic shape memory metal to be evaluated according to the deformation recovery prediction model to obtain a deformation recovery prediction result;

[0077] S112, performing a metal fatigue evaluation on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result to obtain an evaluation result, and determining an update time of the magnetic shape memory metal according to the evaluation result.

[0078] It should be noted that by determining the standard morphological data of ferromagnetic shape memory metals and determining the relationship between deformation recovery and temperature of production samples with different deformation variables, the efficient recovery temperature range of ferromagnetic shape memory metals under different deformation variables can be identified, and the optimal recovery temperature range of ferromagnetic shape memory metals under different deformation variables can be accurately identified. The determination of this efficient recovery temperature range enables metal materials to obtain the best deformation recovery effect in practical applications, avoid unnecessary energy consumption and incomplete recovery, and improve recovery efficiency and accuracy; the LSTM (long short-term memory) algorithm has the advantage of processing time series data and can capture the deformation recovery trend of ferromagnetic shape memory metals in different time periods. By learning from the historical deformation recovery situation, the model can predict the future deformation recovery situation; through the prediction results of the deformation recovery situation, the use strategy of ferromagnetic shape memory metals can be dynamically adjusted. For example, when it is predicted that the material may not achieve the expected recovery effect in a certain period of time in the future, preventive measures can be taken in advance, such as reducing the stress load or increasing the recovery cycle, to prevent the material from failing prematurely. This dynamic adjustment capability makes material management more flexible and able to cope with complex and changing usage environments; through accurate prediction of deformation recovery, the update time of ferromagnetic shape memory metals can be scientifically determined, avoiding the waste of resources due to premature material updates, and preventing the risk of performance degradation or failure due to late updates.

[0079] According to an embodiment of the present invention, the step of obtaining a standard production sample of a ferromagnetic shape memory metal, extracting initial morphological parameters of the standard production sample, and obtaining standard morphological data of the ferromagnetic shape memory metal is specifically as follows:

[0080] Obtaining a standard production sample of a ferromagnetic shape memory metal, obtaining laser scanning data of the standard production sample, and constructing a three-dimensional model of the standard production sample according to the laser scanning data;

[0081] Divide the surface of the three-dimensional model into N triangular meshes, obtain vertex coordinate information of each mesh, and calculate the normal vector of each triangular mesh according to the vertex coordinate information of each mesh;

[0082] Normalize the normal vector of each triangular mesh to obtain a triangular mesh with a normal vector length of 1;

[0083] Calculating the dot product of the normal vectors of two adjacent triangular meshes in the three-dimensional model according to the normalized normal vectors, and calculating the angle information of the two adjacent triangles according to the dot product of the normal vectors;

[0084] Mapping the angle information to the three-dimensional model, determining the angle change in the three-dimensional model, presetting an angle change threshold, marking the triangle edges whose angle change is greater than the angle change threshold, and drawing the contour of the three-dimensional model based on the marked triangle edges to obtain the contour morphology data of the standard production sample;

[0085] According to the contour morphology, the dimension data of the standard production sample is calculated in the image processing model, and the contour morphology data and the dimension data are integrated into the initial morphological parameters of the standard production sample, which are calibrated as the standard morphological data of the ferromagnetic shape memory metal.

[0086] It should be noted that by constructing a three-dimensional model of ferromagnetic shape memory metal and calculating the angle change of the normal vectors of adjacent triangular meshes, it is possible to accurately identify the areas of drastic changes in surface morphology in the three-dimensional model and effectively extract the true contour morphology of the sample. Ferromagnetic shape memory metals usually have complex geometric morphologies. By analyzing the angle changes of triangular meshes, this method can adapt to different shape features. Whether it is a smooth surface or a sharp boundary, its contour can be determined by the angle change. The drawn contour morphology data is combined with the size data calculated by the image processing model, integrated into the initial morphological parameters of the standard production sample, and calibrated as the standard morphological data of the ferromagnetic shape memory metal. The standard morphological data extracted by this method can more accurately reflect the initial morphology of the ferromagnetic shape memory metal.

[0087] According to an embodiment of the present invention, the limit stress of the ferromagnetic shape memory metal is obtained, the standard production sample is subjected to stress testing within the limit stress range to obtain a deformed production sample, the deformed production sample is subjected to heat treatment, the recovery rate of the deformed sample at different temperatures is obtained, and the relationship between the deformation recovery and temperature of the production samples with different deformation amounts is determined to obtain the deformation amount-temperature-recovery rate relationship data, specifically:

[0088] Obtaining the limit stress of the ferromagnetic shape memory metal, evenly dividing the limit stress according to a preset step size, and determining a stress test data set within the limit stress range;

[0089] Obtaining quantity information of the test data in the stress test data set, and obtaining the same quantity of ferromagnetic shape memory metal standard production samples as the test data;

[0090] Apply different stress test forces to each standard production sample according to the stress test data set to obtain a deformed production sample;

[0091] Acquire a three-dimensional model of the deformed production sample and extract morphological data of the deformed sample, compare the morphological data of the deformed sample with standard morphological data of ferromagnetic shape memory metal, and obtain the deformation amount of each deformed production sample;

[0092] The production sample with the most serious deformation variable is subjected to heating treatment to obtain the temperature value required for the production sample with the most serious deformation variable to recover to the standard shape, and the temperature value is calibrated as the limit temperature value;

[0093] Dividing the limit temperature value into equal parts according to the preset value to determine the heating temperature gradient of the deformation production sample;

[0094] The deformed production sample under each deformation amount is subjected to a heating treatment according to the heating temperature gradient, and the deformation recovery sample morphology data after the heating treatment is obtained, and the deformation recovery sample morphology data is compared with the ferromagnetic shape memory metal standard morphology data to obtain the deformation amount of each deformation recovery production sample;

[0095] Calculating the deformation recovery rate according to the deformation amount of each deformation recovery production sample and the deformation amount of each deformation production sample to obtain the deformation recovery rates of the deformation production samples at different temperatures and with different deformation amounts;

[0096] According to the deformation recovery rates of the deformed production samples at different temperatures and with different deformation amounts, the relationship between the deformation recovery and temperature of the production samples with different deformation amounts is determined to obtain deformation amount-temperature-recovery rate relationship data.

[0097] It should be noted that by evenly dividing the ultimate stress into multiple stress test points according to a preset step size, different stress conditions ranging from low stress to ultimate stress can be covered. This comprehensive stress test data set can fully characterize the deformation characteristics of ferromagnetic shape memory metals under various stress conditions, and the same is true for determining the heating temperature gradient; by clarifying the relationship between deformation and temperature, the temperature control of the heating treatment can be optimized. Different deformations correspond to different optimal recovery temperatures, which helps to formulate more accurate heating plans, improve the efficiency and effect of deformation recovery, avoid unnecessary overheating or insufficient heating, thereby saving energy and reducing costs; by mastering the recovery rate of different deformations at specific temperatures, the optimal temperature conditions can be selected to maximize the deformation recovery effect. This means that in practical applications, the heating temperature can be adjusted according to the specific deformation amount to ensure that the material returns to the ideal shape and improve product quality and service life; the heating treatment of each deformed production sample according to the heating temperature gradient is to heat a deformed production sample according to the heating temperature gradient. When a deformed production sample A is heated at one of the temperatures in the heating temperature gradient, a deformation recovery effect will occur. Therefore, the deformed production sample A can no longer be used for subsequent heating treatment at this time. It is only necessary to record the deformation recovery of the deformed production sample A, and then obtain a standard production sample for stress testing. The sample after the test reaches the deformation rate of the deformed production sample A, and then the sample is used to heat according to the untested temperature in the heating temperature gradient until all the tested temperatures in the heating temperature gradient are used for heating treatment, and the deformation recovery rate of the deformed production samples with different deformation amounts when heated at different temperatures is obtained.

[0098] According to an embodiment of the present invention, the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts is identified according to the deformation amount-temperature-recovery rate relationship data, and the efficient recovery temperature range is used as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal, specifically:

[0099] According to the deformation-temperature-recovery rate relationship data, the temperature-recovery rate relationship data sets under different deformations are standardized to obtain a two-dimensional relationship data set;

[0100] The DBSCAN clustering algorithm is introduced to classify data with similar temperature-recovery rates into one category. The Manhattan distance between each data point and other data points in the two-dimensional relationship data set is calculated based on the DBSCAN clustering algorithm to find the Kth nearest neighbor distance of each data point.

[0101] The nearest neighbor distance of each data point is sorted in ascending order, and the sorted nearest neighbor distance is plotted in a nearest neighbor distance change curve to obtain a K-distance graph;

[0102] Determine the inflection point of the K-distance graph, calibrate the nearest neighbor value corresponding to the inflection point as the neighborhood radius ε, and determine the minimum number of samples minPts within the neighborhood radius according to the data dimension of the two-dimensional relationship data set;

[0103] Mark each data point in the two-dimensional relational dataset as unvisited, and create an empty cluster set and a noise point set;

[0104] Visit each data point in the two-dimensional data set in turn, mark the data point that enters the visit state as data point P, and mark P as visited, find all points in the ε neighborhood of P according to the neighborhood radius, and mark them as a set NP;

[0105] If the data point in NP is less than minPts, P is marked as a noise point. If the data point in NP is not less than minPts, P is marked as a core point, a new cluster C is created, and the data point P is added to cluster C.

[0106] For each data point Q in cluster C, if Q is a core point, find all points NQ in the ε neighborhood of Q. If the data points of NQ are not less than minPts, add all points in NQ to cluster C until all data points in the two-dimensional data set are visited, and obtain the clustering result of temperature-recovery rate;

[0107] Perform recovery performance analysis on each clustering result according to the recovery rate of each clustering result, retain the clustering results with recovery performance higher than the preset value and mark them with recovery performance labels, and determine the deformation variable to which the temperature-recovery rate in each clustering result belongs;

[0108] According to the recovery performance label of each clustering result and the corresponding deformation amount, the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts is determined and calibrated as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal.

[0109] It should be noted that the DBSCAN algorithm is a density-based clustering algorithm that can handle nonlinear and complex distributed data. In the deformation-temperature-recovery rate relationship data of ferromagnetic shape memory metals, each data point may have a complex distribution pattern, and the efficient recovery temperature range under different deformations may not show a simple linear relationship. DBSCAN can identify clustering areas of different densities, which is suitable for processing such nonlinear relationships and helps to accurately determine the efficient recovery temperature range under different deformations; DBSCAN clusters points with similar recovery rates and temperatures into clusters based on the density of data points, so that it can accurately identify the efficient recovery temperature range under different deformations. High-density areas usually indicate that within this temperature range, the deformation recovery rate is high, thereby improving the recovery efficiency; DBSCAN does not require the user to pre-specify the number of clusters, but adaptively determines the cluster structure through density and distance. This enables the optimal recovery temperature range to be automatically identified when facing complex data distributions under different deformations, rather than relying on manually set parameters; by identifying the efficient recovery temperature range, the heating and cooling process of ferromagnetic shape memory metals can be optimized. In practical applications, the use of these identified efficient recovery intervals can improve the recovery speed and efficiency, thereby improving the overall material performance and reliability; the K is a preset value, representing the distance from the data point of the kth nearest neighbor to the current point; the neighborhood radius is the search radius of the data point. Data points within this radius are considered neighbors, and the minimum number of samples is within the neighborhood radius. If the number of neighbors of a data point reaches the minimum number of samples, then this point is considered a core point; the horizontal axis of the K-distance graph represents the index of the data point, and the vertical axis represents the corresponding nearest neighbor distance.

[0110] Figure 2 A flow chart of obtaining historical deformation recovery situation change data of the present invention is shown.

[0111] According to an embodiment of the present invention, the historical deformation data of the ferromagnetic shape memory metal within a preset time period is obtained, and the deformation of the ferromagnetic shape memory metal within the preset time period is restored according to the recommended temperature range for deformation recovery, so as to obtain the historical deformation recovery change data, specifically:

[0112] S202, determining the heating power and temperature controllable range required for deformation recovery of the ferromagnetic shape memory metal according to the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal, and constructing a heating system for deformation recovery of the ferromagnetic shape memory metal according to the heating power and temperature controllable range;

[0113] S204, obtaining multiple historical deformation data of the ferromagnetic shape memory metal within a preset time period, and when each deformation occurs, restoring each deformation of the ferromagnetic shape memory metal within the preset time period according to the recommended temperature range for deformation recovery, and obtaining morphological data of the ferromagnetic shape memory metal after deformation recovery according to the recommended temperature range for deformation recovery;

[0114] S206, determining the recovery rate of each deformation recovery according to the morphological data of the ferromagnetic shape memory metal after deformation recovery, and sorting the recovery rate of each deformation recovery according to a time series to obtain historical deformation recovery change data within a preset time period.

[0115] It should be noted that the ferromagnetic shape memory metal undergoes repeated deformation and repeated deformation recovery during actual use; therefore, a thermal system is constructed to heat the ferromagnetic shape memory metal according to the recommended temperature range for deformation recovery each time it is deformed, thereby ensuring that the deformation is restored to the original form of the ferromagnetic shape memory metal. By recovering within the recommended temperature range, the internal stress and fatigue of the material caused by temperature discomfort are reduced, thereby extending the service life of the ferromagnetic shape memory metal; however, due to the repetition of long-term deformation and deformation recovery, the ferromagnetic shape memory metal will produce metal fatigue, so that the deformed ferromagnetic shape memory metal cannot be completely restored to its original form even if it is deformed and recovered according to the recommended temperature range for deformation recovery. Therefore, the recovery rate of each deformation recovery is determined by obtaining the morphological data of the ferromagnetic shape memory metal after deformation recovery according to the recommended temperature range for deformation recovery, and finally the historical deformation recovery change data within a preset time period can be obtained.

[0116] Figure 3 A flow chart of the deformation recovery prediction result obtained by the present invention is shown.

[0117] According to an embodiment of the present invention, a deformation recovery prediction model is constructed based on the LSTM algorithm and historical deformation recovery change data, and the deformation recovery of the ferromagnetic shape memory metal to be evaluated is predicted according to the deformation recovery prediction model to obtain a deformation recovery prediction result, which is specifically:

[0118] S302, constructing a deformation recovery prediction model based on the LSTM algorithm, determining the input data shape of the model input layer according to the data format of the historical deformation recovery change data, constructing the LSTM layer, the Dropout layer, the fully connected layer and the output layer, taking the mean square error as the model loss function, and selecting Adam as the model optimizer;

[0119] S304, dividing the historical deformation recovery data into a training set and a test set according to a preset ratio, importing the training set into the deformation recovery prediction model for model training, monitoring the model performance through the test set, and adjusting the model parameters according to the prediction accuracy of the test set, wherein the model parameters include a learning rate, a number of LSTM layers, and a Dropout rate;

[0120] S306, obtaining deformation recovery change data of the ferromagnetic shape memory metal to be evaluated for performance within the current time period, importing the deformation recovery change data within the current time period into the deformation recovery prediction model, predicting the deformation recovery rate of the ferromagnetic shape memory metal to be evaluated for performance within a future preset time period, and obtaining a deformation recovery prediction result.

[0121] It should be noted that the LSTM (Long Short-Term Memory) algorithm can effectively process long-term dependencies in time series data, accurately capture the changing patterns of historical deformation recovery, and thus accurately predict future deformation recovery rates; it can understand possible recovery performance issues in advance, so that appropriate measures can be taken in the performance evaluation stage to reduce risks and uncertainties.

[0122] According to an embodiment of the present invention, the metal fatigue evaluation of the ferromagnetic shape memory metal to be evaluated is performed according to the deformation recovery prediction result to obtain an evaluation result, and the update time of the magnetic shape memory metal is determined according to the evaluation result, specifically:

[0123] Performing a metal fatigue evaluation on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result, calculating the remaining life of the ferromagnetic shape memory metal to be evaluated for performance according to the metal fatigue, and obtaining a performance evaluation result of the ferromagnetic shape memory metal;

[0124] Obtaining the performance requirement data of the ferromagnetic shape memory metal, and judging whether the ferromagnetic shape memory metal meets the performance requirement according to the performance evaluation result of the ferromagnetic shape memory metal, if not, then;

[0125] If satisfied, determine the time point at which the performance requirement threshold is reached according to the performance evaluation result of the ferromagnetic shape memory metal, determine the remaining usable time of the ferromagnetic shape memory metal, and perform an update operation on the ferromagnetic shape memory metal according to the time point at which the performance requirement threshold is reached;

[0126] A usable time length threshold is preset, and when the usable time length is greater than the usable time length threshold, the ferromagnetic shape memory metal is marked as a first-class product; when the usable time length is less than the usable time length threshold, the ferromagnetic shape memory metal is marked as a second-class product;

[0127] According to the deformation recovery prediction results, the downward trend of the deformation recovery rate of the first and second category products is determined, and according to the downward trend, the periodic performance inspection frequency and inspection items of the first and second category products are determined to obtain a periodic performance inspection plan.

[0128] It should be noted that by analyzing the deformation recovery prediction results, the deformation recovery of ferromagnetic shape memory metals under different deformation amounts and use conditions can be understood. These data help to accurately assess the fatigue level of the metal and identify the fatigue problems that may be encountered in actual use; the results of the metal fatigue assessment can be used to calculate the remaining life of the ferromagnetic shape memory metal. Accurate prediction of the remaining life helps to make reasonable plans for equipment maintenance and replacement, thereby avoiding unexpected failures and downtime; based on the fatigue assessment results, the update operation of the ferromagnetic shape memory metal can be reasonably arranged. For metal parts that do not meet the performance requirements, timely updates can avoid equipment failures due to metal fatigue and ensure the reliability and safety of the equipment; based on the comparison of the remaining use time with the preset threshold, the ferromagnetic shape memory metal is marked as a Class I or Class II product. This classification management helps to formulate different maintenance and update strategies, and adopt different management measures for different categories of metal parts; different periodic inspection frequencies are determined for different performance conditions of Class I and Class II products. For Class I products with better performance, the inspection frequency can be reduced to reduce unnecessary maintenance interventions. For Class II products with obvious performance degradation, increasing the inspection frequency will help to detect potential problems in a timely manner; by optimizing the inspection frequency, resources can be effectively utilized, avoiding excessive or insufficient inspection, thereby improving maintenance and inspection efficiency.

[0129] Figure 4 A block diagram of a ferromagnetic shape memory metal performance evaluation system of the present invention is shown.

[0130] The second aspect of the present invention further provides a ferromagnetic shape memory metal performance evaluation system 4, the system comprising: a memory 41, a processor 42, the memory comprising a ferromagnetic shape memory metal performance evaluation method program, the ferromagnetic shape memory metal performance evaluation method program when executed by the processor, implements the following steps:

[0131] Obtaining a standard production sample of a ferromagnetic shape memory metal, extracting initial morphological parameters of the standard production sample, and obtaining standard morphological data of the ferromagnetic shape memory metal;

[0132] Obtaining the ultimate stress of the ferromagnetic shape memory metal, performing stress testing on the standard production sample within the ultimate stress range to obtain a deformed production sample, performing heat treatment on the deformed production sample, obtaining the recovery rate of the deformed sample at different temperatures, and determining the relationship between the deformation recovery and temperature of the production samples with different deformation amounts, to obtain deformation amount-temperature-recovery rate relationship data;

[0133] Identify the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts according to the deformation amount-temperature-recovery rate relationship data, and use the efficient recovery temperature range as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal;

[0134] Acquire historical deformation data of the ferromagnetic shape memory metal within a preset time period, and restore the deformation of the ferromagnetic shape memory metal within the preset time period according to the recommended temperature range for deformation recovery to obtain historical deformation recovery change data;

[0135] A deformation recovery prediction model is constructed based on the LSTM algorithm and historical deformation recovery change data, and the deformation recovery of the ferromagnetic shape memory metal to be evaluated is predicted according to the deformation recovery prediction model to obtain a deformation recovery prediction result;

[0136] A metal fatigue evaluation is performed on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result to obtain an evaluation result, and an update time of the magnetic shape memory metal is determined according to the evaluation result.

[0137] The present invention discloses a method and system for evaluating the performance of ferromagnetic shape memory metals. By obtaining the morphological parameters of standard samples and deformation data within the limit stress range, the deformation amount-temperature-recovery rate relationship is determined. Based on this relationship, the efficient recovery temperature range is identified, and the historical deformation data of the sample within a preset time period is restored and analyzed. A deformation recovery prediction model is constructed using the LSTM algorithm to predict the deformation recovery of the metal to be evaluated. Finally, the fatigue of the metal is evaluated based on the prediction results to determine its service life. This method improves the accuracy of the performance evaluation of ferromagnetic shape memory metals and provides scientific usage suggestions.

[0138] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0139] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0140] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0141] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0142] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0143] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for evaluating the performance of ferromagnetic shape memory metals, characterized in that: The following steps are involved: Obtaining a standard production sample of a ferromagnetic shape memory metal, extracting initial morphological parameters of the standard production sample, and obtaining standard morphological data of the ferromagnetic shape memory metal; Obtaining the ultimate stress of the ferromagnetic shape memory metal, performing stress testing on the standard production sample within the ultimate stress range to obtain a deformed production sample, performing heat treatment on the deformed production sample, obtaining the recovery rate of the deformed sample at different temperatures, and determining the relationship between the deformation recovery and temperature of the production samples with different deformation amounts, to obtain deformation amount-temperature-recovery rate relationship data; Identify the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts according to the deformation amount-temperature-recovery rate relationship data, and use the efficient recovery temperature range as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal; Acquire historical deformation data of the ferromagnetic shape memory metal within a preset time period, and restore the deformation of the ferromagnetic shape memory metal within the preset time period according to the recommended temperature range for deformation recovery to obtain historical deformation recovery change data; A deformation recovery prediction model is constructed based on the LSTM algorithm and historical deformation recovery change data, and the deformation recovery of the ferromagnetic shape memory metal to be evaluated is predicted according to the deformation recovery prediction model to obtain a deformation recovery prediction result; A metal fatigue evaluation is performed on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result to obtain an evaluation result, and an update time of the magnetic shape memory metal is determined according to the evaluation result.

2. A ferromagnetic shape memory metal performance evaluation method according to claim 1, characterized in that: The step of obtaining a standard production sample of the ferromagnetic shape memory metal, extracting the initial morphological parameters of the standard production sample, and obtaining the standard morphological data of the ferromagnetic shape memory metal is as follows: Obtaining a standard production sample of a ferromagnetic shape memory metal, obtaining laser scanning data of the standard production sample, and constructing a three-dimensional model of the standard production sample according to the laser scanning data; Divide the surface of the three-dimensional model into N triangular meshes, obtain vertex coordinate information of each mesh, and calculate the normal vector of each triangular mesh according to the vertex coordinate information of each mesh; Normalize the normal vector of each triangular mesh to obtain a triangular mesh with a normal vector length of 1; Calculating the dot product of the normal vectors of two adjacent triangular meshes in the three-dimensional model according to the normalized normal vectors, and calculating the angle information of the two adjacent triangles according to the dot product of the normal vectors; Mapping the angle information to the three-dimensional model, determining the angle change in the three-dimensional model, presetting an angle change threshold, marking the triangle edges whose angle change is greater than the angle change threshold, and drawing the contour of the three-dimensional model based on the marked triangle edges to obtain the contour morphology data of the standard production sample; According to the contour morphology, the dimension data of the standard production sample is calculated in the image processing model, and the contour morphology data and the dimension data are integrated into the initial morphological parameters of the standard production sample, which are calibrated as the standard morphological data of the ferromagnetic shape memory metal.

3. A ferromagnetic shape memory metal performance evaluation method according to claim 1, characterized in that: The ultimate stress of the ferromagnetic shape memory metal is obtained, the standard production sample is subjected to stress testing within the ultimate stress range to obtain a deformed production sample, the deformed production sample is subjected to heat treatment, the recovery rate of the deformed sample at different temperatures is obtained, and the relationship between the deformation recovery and temperature of the production samples with different deformation amounts is determined to obtain deformation amount-temperature-recovery rate relationship data, specifically: Obtaining the limit stress of the ferromagnetic shape memory metal, evenly dividing the limit stress according to a preset step size, and determining a stress test data set within the limit stress range; Obtaining quantity information of the test data in the stress test data set, and obtaining the same quantity of ferromagnetic shape memory metal standard production samples as the test data; Apply different stress test forces to each standard production sample according to the stress test data set to obtain a deformed production sample; Acquire a three-dimensional model of the deformed production sample and extract morphological data of the deformed sample, compare the morphological data of the deformed sample with standard morphological data of ferromagnetic shape memory metal, and obtain the deformation amount of each deformed production sample; The production sample with the most serious deformation variable is subjected to heating treatment to obtain the temperature value required for the production sample with the most serious deformation variable to recover to the standard shape, and the temperature value is calibrated as the limit temperature value; Dividing the limit temperature value into equal parts according to the preset value to determine the heating temperature gradient of the deformation production sample; The deformed production sample under each deformation amount is subjected to a heating treatment according to the heating temperature gradient, and the deformation recovery sample morphology data after the heating treatment is obtained, and the deformation recovery sample morphology data is compared with the ferromagnetic shape memory metal standard morphology data to obtain the deformation amount of each deformation recovery production sample; Calculating the deformation recovery rate according to the deformation amount of each deformation recovery production sample and the deformation amount of each deformation production sample to obtain the deformation recovery rates of the deformation production samples at different temperatures and with different deformation amounts; According to the deformation recovery rates of the deformed production samples at different temperatures and with different deformation amounts, the relationship between the deformation recovery and temperature of the production samples with different deformation amounts is determined to obtain deformation amount-temperature-recovery rate relationship data.

4. The method for evaluating the performance of ferromagnetic shape memory metal according to claim 1, characterized in that: The method of identifying the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts according to the deformation amount-temperature-recovery rate relationship data, and using the efficient recovery temperature range as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal, is specifically: According to the deformation-temperature-recovery rate relationship data, the temperature-recovery rate relationship data sets under different deformations are standardized to obtain a two-dimensional relationship data set; The DBSCAN clustering algorithm is introduced to classify data with similar temperature-recovery rates into one category. The Manhattan distance between each data point and other data points in the two-dimensional relationship data set is calculated based on the DBSCAN algorithm to find the Kth nearest neighbor distance of each data point. The nearest neighbor distance of each data point is sorted in ascending order, and the sorted nearest neighbor distance is plotted in a nearest neighbor distance change curve to obtain a K-distance graph; Determine the inflection point of the K-distance graph, calibrate the nearest neighbor value corresponding to the inflection point as the neighborhood radius ε, and determine the minimum number of samples minPts within the neighborhood radius according to the data dimension of the two-dimensional relationship data set; Mark each data point in the two-dimensional relational dataset as unvisited, and create an empty cluster set and a noise point set; Visit each data point in the two-dimensional data set in turn, mark the data point that enters the visit state as data point P, and mark P as visited, find all points in the ε neighborhood of P according to the neighborhood radius, and mark them as a set NP; If the data point in NP is less than minPts, P is marked as a noise point. If the data point in NP is not less than minPts, P is marked as a core point, a new cluster C is created, and the data point P is added to cluster C. For each data point Q in cluster C, if Q is a core point, find all points NQ in the ε neighborhood of Q. If the data points of NQ are not less than minPts, add all points in NQ to cluster C until all data points in the two-dimensional data set are visited, and obtain the clustering result of temperature-recovery rate; Perform recovery performance analysis on each clustering result according to the recovery rate of each clustering result, retain the clustering results with recovery performance higher than the preset value and mark them with recovery performance labels, and determine the deformation variable to which the temperature-recovery rate in each clustering result belongs; According to the recovery performance label of each clustering result and the corresponding deformation amount, the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts is determined and calibrated as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal.

5. The method for evaluating the performance of ferromagnetic shape memory metal according to claim 1, characterized in that: The historical deformation data of the ferromagnetic shape memory metal within a preset time period is obtained, and the deformation of the ferromagnetic shape memory metal within the preset time period is restored according to the recommended temperature range for deformation recovery, so as to obtain the historical deformation recovery change data, specifically: Determine the heating power and temperature controllable range required for deformation recovery of the ferromagnetic shape memory metal according to the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal, and construct a heating system for deformation recovery of the ferromagnetic shape memory metal according to the heating power and temperature controllable range; Acquire multiple historical deformation data of the ferromagnetic shape memory metal within a preset time period, and when each deformation occurs, restore each deformation of the ferromagnetic shape memory metal within the preset time period according to the recommended temperature range for deformation recovery, and acquire the morphological data of the ferromagnetic shape memory metal after deformation recovery according to the recommended temperature range for deformation recovery; The recovery rate of each deformation recovery is determined according to the morphological data of the ferromagnetic shape memory metal after deformation recovery, and the recovery rate of each deformation recovery is sorted according to a time series to obtain historical deformation recovery change data within a preset time period.

6. A ferromagnetic shape memory metal performance evaluation method according to claim 1, characterized in that: The deformation recovery prediction model is constructed based on the LSTM algorithm and the historical deformation recovery change data, and the deformation recovery of the ferromagnetic shape memory metal to be evaluated is predicted according to the deformation recovery prediction model to obtain the deformation recovery prediction result, which is specifically: A deformation recovery prediction model is built based on the LSTM algorithm. The input data shape of the model input layer is determined according to the data format of the historical deformation recovery change data. The LSTM layer, Dropout layer, fully connected layer and output layer are built. The mean square error is used as the model loss function, and Adam is selected as the model optimizer. The historical deformation recovery data is divided into a training set and a test set according to a preset ratio, the training set is imported into the deformation recovery prediction model for model training, the model performance is monitored through the test set, and the model parameters are adjusted according to the prediction accuracy of the test set, wherein the model parameters include a learning rate, a number of LSTM layers, and a Dropout rate; The deformation recovery change data of the ferromagnetic shape memory metal to be evaluated for performance in the current time period is obtained, the deformation recovery change data in the current time period is imported into the deformation recovery prediction model, the deformation recovery rate of the ferromagnetic shape memory metal to be evaluated for performance in a future preset time period is predicted, and the deformation recovery prediction result is obtained.

7. The method for evaluating the performance of ferromagnetic shape memory metal according to claim 1, characterized in that: The metal fatigue evaluation of the ferromagnetic shape memory metal to be evaluated for performance is performed according to the deformation recovery prediction result to obtain an evaluation result, and the update time of the magnetic shape memory metal is determined according to the evaluation result, specifically: Performing a metal fatigue evaluation on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result, calculating the remaining life of the ferromagnetic shape memory metal to be evaluated for performance according to the metal fatigue, and obtaining a performance evaluation result of the ferromagnetic shape memory metal; Obtaining performance requirement data of the ferromagnetic shape memory metal, and judging whether the ferromagnetic shape memory metal meets the performance requirement according to the performance evaluation result of the ferromagnetic shape memory metal, and if not, performing an update operation on the ferromagnetic shape memory metal; If satisfied, determine the time point at which the performance requirement threshold is reached according to the performance evaluation result of the ferromagnetic shape memory metal, determine the remaining usable time of the ferromagnetic shape memory metal, and perform an update operation on the ferromagnetic shape memory metal according to the time point at which the performance requirement threshold is reached; A usable time length threshold is preset, and when the usable time length is greater than the usable time length threshold, the ferromagnetic shape memory metal is marked as a first-class product, and when the usable time length is less than the usable time length threshold, the ferromagnetic shape memory metal is marked as a second-class product; According to the deformation recovery prediction results, the downward trend of the deformation recovery rate of the first and second category products is determined, and according to the downward trend, the periodic performance inspection frequency and inspection items of the first and second category products are determined to obtain a periodic performance inspection plan.

8. A ferromagnetic shape memory metal performance evaluation system, characterized in that: The ferromagnetic shape memory metal performance evaluation system includes a storage device and a processor. The storage device includes a ferromagnetic shape memory metal performance evaluation method program. When the ferromagnetic shape memory metal performance evaluation method program is executed by the processor, the following steps are implemented: Obtaining a standard production sample of a ferromagnetic shape memory metal, extracting initial morphological parameters of the standard production sample, and obtaining standard morphological data of the ferromagnetic shape memory metal; Obtaining the ultimate stress of the ferromagnetic shape memory metal, performing stress testing on the standard production sample within the ultimate stress range to obtain a deformed production sample, performing heat treatment on the deformed production sample, obtaining the recovery rate of the deformed sample at different temperatures, and determining the relationship between the deformation recovery and temperature of the production samples with different deformation amounts, to obtain deformation amount-temperature-recovery rate relationship data; Identify the efficient recovery temperature range of the ferromagnetic shape memory metal under different deformation amounts according to the deformation amount-temperature-recovery rate relationship data, and use the efficient recovery temperature range as the recommended temperature range for deformation recovery of the ferromagnetic shape memory metal; Acquire historical deformation data of the ferromagnetic shape memory metal within a preset time period, and restore the deformation of the ferromagnetic shape memory metal within the preset time period according to the recommended temperature range for deformation recovery to obtain historical deformation recovery change data; A deformation recovery prediction model is constructed based on the LSTM algorithm and historical deformation recovery change data, and the deformation recovery of the ferromagnetic shape memory metal to be evaluated is predicted according to the deformation recovery prediction model to obtain a deformation recovery prediction result; A metal fatigue evaluation is performed on the ferromagnetic shape memory metal to be evaluated for performance according to the deformation recovery prediction result to obtain an evaluation result, and an update time of the magnetic shape memory metal is determined according to the evaluation result.

Images