Component performance evaluation method, apparatus, device, and medium

Abstract

The application discloses a kind of element performance evaluation method, device, equipment and medium, wherein, method includes: in the energized state of the element to be measured, the running data of the element to be measured is acquired in real time, and preset health state category, wherein, running data includes electrical parameter characteristic data, shape characteristic data and temperature characteristic data, health state category includes excellent, good, attention, warning and failure;Determine the first membership degree of each running data belonging to each health state category;The first membership degree of the same health state category is weighted summation, and the evaluation vector value of each health state category is obtained;According to the evaluation vector value of each health state category, determine the health index of the element to be measured, wherein, health index is used to characterize the health degree of the element to be measured.The method detects electrical parameter characteristic data, shape characteristic data and temperature characteristic data under the energized working state of the element to be measured, and predicts the health index of element.

Description

Technical Field

[0001] This application belongs to the field of industrial heating technology, and in particular relates to a method, apparatus, equipment and medium for evaluating the performance of components. Background Technology

[0002] Traditional performance testing methods for electric heating elements rely entirely on offline laboratory testing. This requires removing the element from the equipment, placing it in a dedicated testing furnace, and heating it with an external heat source to measure parameters such as resistance and power. This approach is not only time-consuming and costly, but more importantly, laboratory conditions differ significantly from actual field conditions. For example, there are substantial differences in complex environments such as temperature fluctuations, voltage variations, and media corrosion, making the test results unable to accurately reflect the element's service condition.

[0003] Therefore, how to more realistically and accurately evaluate the performance of electric heating elements is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] The embodiments of this application provide a method, apparatus, device and medium for evaluating component performance, which can simultaneously detect electrical parameter characteristic data, shape characteristic data and temperature characteristic data in real time while the component is powered on, and predict the health index of the component with high accuracy.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to a first aspect of the embodiments of this application, a method for evaluating component performance is provided, comprising the following steps: When the device under test is powered on, the operating data of the device under test and the preset health status categories are acquired in real time. The operating data includes electrical parameter characteristic data, shape characteristic data and temperature characteristic data. The health status categories include excellent, good, attention, warning and failure. Determine the first membership degree of each type of operational data to each health status category; The first membership degree of the same health status category is weighted and summed to obtain the evaluation vector value of each health status category; Based on the evaluation vector value of each health status category, a health index is determined for the component under test, wherein the health index is used to characterize the health of the component under test.

[0007] Optionally, the electrical parameter characteristic data includes the rate of change of resistance and the power fluctuation coefficient; the shape characteristic data includes the steady-state creep rate and the residual deformation rate; the temperature characteristic data includes the temperature field uniformity and the rate of temperature rise decay; and determining the first membership degree of each type of operating data to each health state category further includes: Determine the second membership degree of each electrical parameter feature data to each health state category, and perform a weighted summation of the second membership degrees of the same health state category to obtain the first membership degree of each health state category under the electrical parameter feature data; The third membership degree of each shape feature data to each health status category is determined, and the third membership degrees of the same health status category are weighted and summed to obtain the first membership degree of each health status category under the shape feature data. Determine the fourth membership degree of each temperature feature data to each health state category, and perform a weighted summation of the fourth membership degrees of the same health state category to obtain the first membership degree of each health state category under each temperature feature data.

[0008] Optionally, determining the health index of the component under test based on the evaluation vector value of each health status category includes: The health index of the component under test is obtained by summing the evaluation vector value of each health status category and the preset vector coefficients corresponding to each health status category through a dot product.

[0009] Optionally, after determining the health index of the component under test, the method further includes: If the health index is greater than or equal to a preset first index threshold, then the health risk level of the component under test is determined to be low risk. If the health index is less than the first index threshold and greater than the preset second index threshold, the health risk level of the component under test is determined to be medium risk, and a mild emergency alarm is triggered. If the health index is less than or equal to the second index threshold, the health risk level of the component under test is determined to be high risk, and an emergency alarm is triggered.

[0010] Optionally, after determining the health index of the component under test, the method further includes: If the health index is greater than the preset first index threshold, then the resistance increment, creep strain and thermal fatigue damage of the component under test are determined. The remaining service life of the component under test is predicted based on the resistance increment, the creep strain, and the thermal fatigue damage degree.

[0011] Optionally, after acquiring the operating data of the component under test in real time, the method further includes: Based on the operational data, the functional state of the component under test is determined, including the effective state, oxidation failure state, thermal fatigue failure state, and creep failure state.

[0012] Optionally, determining the functional state of the component under test based on the operating data includes: The running data is input into a pre-built support vector machine model to obtain the functional state output by the support vector machine model; The support vector machine model is trained using a sample set, which includes experimental runtime sequence data and corresponding functional state labels.

[0013] According to a second aspect of the embodiments of this application, a component performance evaluation apparatus is provided, characterized in that the apparatus comprises: The acquisition module is used to acquire the operating data of the device under test and the preset health status category in real time when the device under test is powered on. The operating data includes electrical parameter characteristic data, shape characteristic data and temperature characteristic data, and the health status category includes excellent, good, attention, warning and failure. The first determination module is used to determine the first membership degree of each type of operational data to each health status category; The second determining module is used to perform a weighted summation of the first membership degrees of the same health status category to obtain the evaluation vector value of each health status category; The third determining module is used to determine the health index of the component under test based on the evaluation vector value of each health status category, wherein the health index is used to characterize the health of the component under test.

[0014] According to a third aspect of the embodiments of this application, an electronic device is provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described above.

[0015] According to a fourth aspect of the embodiments of this application, a storage medium is provided having a computer program stored thereon, characterized in that the program, when executed by a processor, implements the steps of the method described above.

[0016] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0017] In this embodiment, a component performance evaluation method, apparatus, device, and medium can acquire the operating data and preset health status categories of the component under test (DUT) in real time while the DUT is powered on. The system simulates the actual working conditions of the DUT during operation. It determines the first membership degree of each type of operating data to each health status category, and evaluates the health degree of each operating parameter based on this first membership degree. The first membership degrees of the same health status category are weighted and summed to obtain an evaluation vector value for each health status category, which represents the probability that the DUT is in each health status. Based on the evaluation vector value of each health status category, a health index of the DUT is determined. Finally, all possibilities are considered to evaluate the health degree of the DUT. The health index characterizes the health of the DUT, the operating data includes electrical parameter characteristic data, shape characteristic data, and temperature characteristic data, and the health status categories include excellent, good, caution, warning, and failure.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 This is a flowchart of a component performance evaluation method provided in an embodiment of this application; Figure 2 This is a structural block diagram of a component performance evaluation device provided in an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] Electrothermal alloy elements (iron-chromium-aluminum, nickel-chromium, etc.) are the "heart" of core equipment such as industrial heating furnaces, heat treatment equipment, photovoltaic sintering furnaces, and power battery material kilns. Their reliability directly determines the continuous operation capability of the production line and the consistency of product quality. Especially in high-end manufacturing fields such as photovoltaic silicon wafer sintering and power battery cathode material sintering, the loss from a single unplanned shutdown of electrothermal elements can reach over one million yuan. During long-term service at high temperatures, electrothermal alloy elements are simultaneously subjected to the coupled effects of three major failure mechanisms: oxidation corrosion, thermal stress fatigue, and creep deformation. Among these, short circuits and fractures caused by creep deformation account for more than 30% of the total failures of electrothermal elements in industrial kilns, making it the primary cause of unplanned shutdowns.

[0022] Traditional performance testing methods for electric heating elements rely entirely on offline laboratory testing. This requires removing the element from the equipment, placing it in a dedicated testing furnace, and heating it with an external heat source to measure parameters such as resistance and power. This approach is not only time-consuming and costly, but more importantly, laboratory conditions differ significantly from actual field conditions. For example, there are substantial differences in complex environments such as temperature fluctuations, voltage variations, and media corrosion, making the test results unable to accurately reflect the element's service condition.

[0023] Figure 1 This is a flowchart of a component performance evaluation method provided in an embodiment of this application. (Refer to...) Figure 1 This application provides a method for evaluating component performance. The executing entity can be a control system, which can be located in a terminal or a server. The terminal can include an in-vehicle terminal or a user terminal, and the server can be a server that communicates with the vehicle. No specific limitation is imposed; the following description uses a control system as the executing entity. The method may include: Step 110: With the device under test powered on, acquire the device's operating data and preset health status categories in real time.

[0024] The operational data includes electrical parameter characteristic data, shape characteristic data, and temperature characteristic data, and the health status categories include excellent, good, caution, warning, and failure.

[0025] In this embodiment, the power supply and operating condition simulation unit supplies power to the component under test (DUT), causing it to exhibit phenomena such as heating, deformation, and fatigue as if it were operating normally. This simulates actual operating conditions and allows for real-time acquisition of the DUT's operational data under power-on conditions. The power supply and operating condition simulation unit provides an adjustable AC / DC power supply from 0-380V and supports three control modes: constant power, constant current, and constant voltage. It can simulate complex operating conditions in industrial settings, such as voltage fluctuations, start-stop cycles, and power step changes.

[0026] The power supply and operating condition simulation unit adopts a programmable AC power supply + digital power controller architecture, with specific parameters as follows: Input voltage: Three-phase 380V±10%, 50Hz.

[0027] Output voltage: 0-380V continuously adjustable, single-phase / three-phase selectable.

[0028] Output power: 0-100kW continuously adjustable.

[0029] Control modes: Constant voltage, constant current, and constant power modes can be switched.

[0030] Voltage fluctuation simulation: can simulate voltage fluctuations of ±5%, ±10%, and ±15%.

[0031] Start-stop cycle control: On / off time is continuously adjustable from 0.1s to 9999h, and the number of cycles can be set from 1 to 99999.

[0032] Protection functions: overcurrent, overvoltage, overheat, and short circuit protection, with a response time of ≤10ms.

[0033] This unit can accurately simulate various complex power supply conditions in industrial settings, enabling the device under test to be tested under conditions completely consistent with the actual service environment, fundamentally solving the problem of inconsistent operating conditions caused by traditional heating methods.

[0034] The temperature characteristic data is detected using a full-surface temperature distribution detection unit. An infrared thermal imager (temperature range 0-1500℃, accuracy ±5℃) is used to detect the two-dimensional temperature field of the entire surface of the component under test in real time, identify local overheated areas and temperature gradients, and obtain temperature characteristic data such as temperature difference uniformity and heating rate decay rate to characterize the creep deformation degradation state.

[0035] The full surface temperature distribution detection unit uses a mid-wave infrared thermal imager, with the following specific parameters: Temperature measurement range: 0-1500℃ Temperature measurement accuracy: ±5℃ Resolution: 640×512 pixels Frame rate: 30Hz Spectral range: 3-5μm Output interface: Gigabit Ethernet Infrared thermal imagers acquire infrared thermal images of the components under test in real time. The surface temperature distribution of the components is extracted through image processing algorithms, and parameters such as average temperature, maximum temperature, minimum temperature, and temperature gradient are calculated. Local overheated areas are also identified.

[0036] High-precision electrical parameter acquisition units are used to collect characteristic electrical parameter data. Voltage / current transmitters with 0.1-level accuracy and synchronous sampling modules can be employed, with a sampling frequency ≥1kHz. Real-time acquisition of the instantaneous voltage and current of the component under test (DUT) is performed, and based on the voltage and current, real-time resistance, rate of resistance change, active power, power factor, and power fluctuation coefficient—characteristics of oxidation degradation—are calculated. The calculated real-time resistance may be inaccurate; therefore, temperature-dependent resistance calculations can be used to eliminate the influence of temperature changes on resistance and accurately extract resistance changes caused by oxidation and cross-sectional thinning.

[0037] The high-precision electrical parameter acquisition unit adopts synchronous sampling technology to achieve synchronous acquisition of voltage and current signals. The specific parameters are as follows: Voltage measurement range: 0-500V AC / DC, accuracy ±0.1% FS Current measurement range: 0-100A AC / DC, accuracy ±0.1% FS Sampling frequency: Adjustable from 1kHz to 10kHz Synchronization accuracy: ≤1μs Data output: RS-485 / Ethernet, supports Modbus TCP / IP protocol The resistance correction method is as follows: Since the heating element itself exhibits a significant temperature gradient along its length when heated, with local temperature differences reaching hundreds of degrees Celsius, the target temperature is calculated based on the temperatures at various measuring points of the element under test (DUT). The true impact of temperature on the overall resistance is then determined, and the temperature range within which the target temperature falls is identified. Because the surface oxide film thickens, the alloying elements in the matrix deplete, and the internal grains coarsen after long-term high-temperature service, the resistance temperature correction coefficient will continuously shift with the aging process. Therefore, the resistance temperature correction coefficient corresponding to this temperature range is determined, and this coefficient is used to correct the resistance. Different weights can be assigned to the temperatures of different measuring points, and then the temperatures of each measuring point are weighted and summed to obtain the target temperature. The weights can be set according to the cross-sectional thickness of each measuring point; for example, the greater the thickness, the smaller the weight. The correspondence between the temperature range and the resistance temperature correction coefficient is pre-calibrated, and different resistance temperature correction coefficients are used to eliminate the influence of DUT aging on the resistance calculation. Finally, the formula R is used... T =R0×(1+α×ΔT), calculate the resistance, where R T R0 is the real-time resistance, α is the initial resistance at room temperature, α is the resistance temperature correction coefficient, and ΔT is the difference between the target temperature and room temperature.

[0038] Non-contact shape deformation detection units are used to detect shape feature data. Measurement points can be arranged at equal intervals along the length of the component under test, and a laser displacement sensor array (accuracy ±0.01mm) can be placed at the measurement points. Alternatively, a high-resolution industrial camera + structured light system can be used to measure the deformation, lateral displacement, and torsion angle of the component under test in real time. Based on this, steady-state creep rate and residual deformation rate, etc., are calculated to characterize the creep deformation degradation state.

[0039] The non-contact shape deformation detection unit adopts a laser displacement sensor array solution, with the following specific configuration: Number of sensors: configured according to the length of the component under test, with a spacing of ≤200mm. Measurement range: 0-500mm Measurement accuracy: ±0.01mm Sampling frequency: 100Hz Output interface: Ethernet Each sensor is vertically aligned with the upper surface of the component to measure the vertical displacement at each point in real time. By interpolating and fitting the displacement data at each point, the complete deformation curve of the component is obtained, and parameters such as maximum deflection, average deflection, and deformation rate are calculated. For the detection of torsional deformation, a set of laser displacement sensor arrays can be arranged on each side of the component to measure the displacement difference between the two sides of the component and calculate the torsion angle.

[0040] The steady-state creep rate is calculated as follows: For each sampling moment, the vertical displacement value of each measuring point in the laser array is interpolated using cubic spline interpolation to obtain the complete deformation curve along the entire length of the element at each sampling moment. The maximum deflection value at each moment (usually located at the mid-span of the element) is extracted to form a "maximum deflection-time" time series. During continuous operation at constant temperature and power, the initial creep segment during the heating phase and the accelerated creep segment at the end of the lifespan are eliminated, locking in the interval where the deflection increases approximately linearly and stably with time; this interval is the steady-state interval. Linear fitting is performed on the maximum deflection-time data within the steady-state interval, and the slope of the fitted line is the steady-state creep rate of the element, usually expressed in mm / h, directly reflecting the rate of creep degradation.

[0041] The calculation method of residual deformation rate: In the initial stage of the test, the lateral displacement of each measuring point is collected at room temperature. The lateral displacement of each measuring point is fitted to obtain the maximum deflection y0 of the test element in the initial straight state, and it is used as the reference zero point. After completing one complete start-stop heating and cooling cycle (powering on to heat up to the rated temperature and holding it at that temperature, then powering off and cooling it completely to room temperature), the lateral displacement of each measuring point at room temperature is collected again, and the maximum deflection y1 at room temperature in the current stage is fitted again. Then, the permanent residual deformation Δy = y1 - y0 (i.e., the permanent deformation increment that cannot be elastically recovered after the cycle) is calculated. The residual deformation rate = Δy / L × 100%, where L is the effective support span (effective heating length) of the test element, which is a dimensionless ratio. The larger the value, the more severe the permanent damage caused by thermal fatigue-creep coupling.

[0042] Finally, the multiphysics data fusion and intelligent analysis unit performs preprocessing and other operations on the data detected by each unit to obtain the final running data. Preprocessing includes filtering, noise reduction, and time synchronization.

[0043] Step 120: Determine the first membership degree of each type of operational data to each health status category.

[0044] In this embodiment, if an operational data point indicates that the device under test is healthy, then the higher the first membership degree for an excellent operational parameter, and the lower the first membership degree for a failed one. This method is used to determine the first membership degree of each type of operational data belonging to each health state category. Since there are three categories of operational data—electrical parameter characteristic data, shape characteristic data, and temperature characteristic data—and there are five health state categories, a 3×5 first membership degree matrix can be obtained.

[0045] Step 130: Perform a weighted summation of the first membership degrees of the same health status category to obtain the evaluation vector value for each health status category.

[0046] Next, a first weight is assigned to each type of operational data in advance, and the sum of all first weights is 1; the product of the first weight and the first membership degree corresponding to each type of operational data under the same health status category is calculated, and then all products are summed to obtain an evaluation vector value for a health status category.

[0047] This can be understood as follows: the first weight A = [a1, a2, a3], where a1 is the first weight of the electrical parameter feature data, a2 is the first weight of the shape feature data, and a3 is the first weight of the temperature feature data. For example, [a1, a2, a3] = [0.35, 0.3, 0.35].

[0048] Where the first membership degree R = [R1, R2, R3]. The first membership degree R1 of the electrical parameter characteristic data = [r 11 ,r12 ,r 13 ,r 14 ,r 15 ], r 11 For electrical parameter characteristic data to belong to an excellent first membership degree, r 12 For electrical parameter characteristic data to have a good first membership degree, r 13 For electrical parameter feature data, the first membership degree of attention is r. 14 For electrical parameter characteristic data belonging to the first membership degree of the warning, r 15 The first membership degree of electrical parameter characteristic data belonging to failure. The first membership degree of shape characteristic data R2=[r 21 ,r 22 ,r 23 ,r 24 ,r 25 ], r 21 For shape feature data to have an excellent first membership degree, r 22 For shape feature data to have a good first membership degree, r 23 The first membership degree of shape feature data to attention, r 24 r represents the first membership degree of the shape feature data belonging to the warning. 25 The first membership degree of shape feature data belongs to the failure category. The first membership degree of temperature feature data is R3=[r 31 ,r 32 ,r 33 ,r 34 ,r 35 ], r 31 For temperature feature data to have an excellent first membership degree, r 32 For temperature feature data to have a good first membership degree, r 33 For temperature feature data, the first membership degree of attention is r. 34 r represents the first membership degree of the temperature feature data belonging to the warning. 35 The temperature characteristic data belongs to the first membership degree of failure.

[0049] Then, the excellent evaluation vector value b1 = a1 × r 11 +a1×r 21 +a1×r 31 A good evaluation vector value is b2 = a2 × r 12 +a2×r 22 +a2×r 32 Similarly, the evaluation vector values ​​b3 for attention, b4 for warning, and b5 for failure are calculated.

[0050] Step 140: Determine the health index of the component to be tested based on the evaluation vector value of each health status category.

[0051] Among them, the health index is used to characterize the health of the component under test.

[0052] Finally, based on the evaluation vector values ​​of Excellent, Good, Caution, Warning, and Failure, the health index of the component under test can be comprehensively determined. The method in this embodiment involves energizing the component under test and simulating actual operating conditions by controlling voltage, current, and power. The collected operating parameters more closely resemble those under real-world conditions, and the health index of the component under test can then be calculated more accurately based on these parameters.

[0053] Optionally, after step 110, the method further includes: Step 150: Based on the operating data, determine the functional status of the component under test. The functional status includes the effective status, oxidation failure status, thermal fatigue failure status, and creep failure status.

[0054] In the embodiments of this application, various operating data can also be analyzed to determine whether the function of the component under test has failed, and the failure status.

[0055] Optionally, step 150 includes: The running data is input into the pre-built support vector machine model to obtain the functional state output by the support vector machine model.

[0056] In this embodiment, Support Vector Machine (SVM) can be used to determine the functional state. SVM is a supervised multi-classification algorithm that can identify failure states based on multiple parameters. The core characteristics of oxidation failure are a continuous increase in resistance and a slow decay in the heating rate; the core characteristics of creep failure are a continuous increase in the deflection rate and a shift in the temperature field with deformation; the core characteristics of thermal fatigue failure are increased power fluctuations and an increase in the residual deformation increment during start-stop cycles. SVM analyzes electrical parameter feature data, shape feature data, and temperature feature data, mapping them as multi-dimensional feature vectors to a high-dimensional space. By finding the optimal classification hyperplane to maximize the classification interval between different failure states, it can not only determine the failure state but also output the confidence percentage of each of the three failure states.

[0057] The support vector machine model is trained using a sample set, which includes experimental runtime sequence data and corresponding functional state labels.

[0058] The support vector machine model is trained using supervised learning. The specific process is as follows: 1. Sample Construction and Labeling: With the component under test in the energized state, multiple sets of accelerated aging tests are carried out to obtain experimental running sequence data under different failure stages and failure states. Combined with the dissection analysis results of the component after failure (to confirm the oxide layer thickness, creep damage degree, and fatigue crack density), the failure state is labeled. The sample labels are divided into four categories: effective state, oxidation failure state, thermal fatigue failure state, and creep failure state.

[0059] 2. Feature Engineering: Core features such as resistance change rate, steady-state creep rate, temperature field uniformity, cyclic deformation increment, and power fluctuation coefficient are extracted from the experimental runtime sequence data and normalized to form a standardized feature vector.

[0060] 3. Model Training and Optimization: A one-to-one multi-classification strategy is adopted, and the RBF kernel function is selected to adapt to the nonlinear classification boundary. The penalty factor and kernel function parameters are optimized through cross-validation to minimize the classification error. After the system is put into use, field failure feedback data can be continuously added to the sample library and retrained regularly to improve the adaptability to working conditions.

[0061] For example, the support vector machine model analyzes the resistance change rate to exceed a certain value, outputting the oxidation failure state; the maximum deflection reaches the installation safety clearance limit, outputting the creep failure state; and the thermal fatigue damage degree ≥1, outputting the thermal fatigue failure state. Any failure state output is considered as the component reaching the end of its lifespan.

[0062] In the embodiments of this application, the electrical parameter characteristic data includes the resistance change rate and power fluctuation coefficient, the shape characteristic data includes the steady-state creep rate and residual deformation rate, and the temperature characteristic data includes the temperature field uniformity and the heating rate decay rate.

[0063] The resistance change rate, power fluctuation coefficient, temperature field uniformity, and heating rate decay rate selected here are all relative degradation characteristics. They eliminate individual differences in component specifications and reference values, and directly characterize the degree of degradation of the component relative to its initial state. This allows components of different batches and specifications to use the same method.

[0064] Among them, the resistance change rate refers to the increase of the current measured resistance relative to the initial cold resistance. The increase in value comes from the thickening of the surface oxide film and the thinning of the effective cross-sectional area of ​​the substrate, which directly reflects the degree of oxidation degradation. The smaller the value, the lighter the oxidation damage and the better the health status.

[0065] The power fluctuation coefficient refers to the proportion of the output power fluctuation amplitude to the rated power during steady-state operation. The fluctuation is mostly caused by poor wiring contact and micro-cracks in the substrate. The smaller the value, the better the operating stability, the lower the risk of fatigue damage and contact failure, and the better the health status.

[0066] Temperature field uniformity is the ratio of the difference between the highest and lowest temperatures within the effective heating range of an element to the average operating temperature. A larger value indicates a more uneven temperature distribution and more significant local overheating, which will accelerate local oxidation and creep degradation; a smaller value indicates a more uniform temperature distribution and a better health condition.

[0067] The rate of decrease in heating rate refers to the percentage decrease in the current heating rate compared to the initial reference heating rate under the same rated power conditions. The decrease is due to the reduction in electrothermal conversion efficiency and the increase in the thermal resistance of the oxide layer. The smaller the value, the less the efficiency degradation and the better the health status.

[0068] Steady-state creep rate refers to the linear growth rate of the maximum deflection of a component over time during the isothermal steady-state operation stage, directly reflecting the development speed of creep deformation; the smaller the value, the slower the creep damage development, the more sufficient the structural safety margin, and the better the health status.

[0069] The residual deformation rate refers to the proportion of permanent deflection deformation remaining at room temperature to the effective support span of the component after a complete start-stop heating and cooling cycle. It is caused by the accumulation of creep-fatigue coupled damage. The smaller the value, the lighter the cyclic damage, the longer the remaining fatigue life, and the better the health status.

[0070] Optionally, step 120 includes: Determine the second membership degree of each electrical parameter feature data to each health state category, and perform a weighted summation of the second membership degrees of the same health state category to obtain the first membership degree of each health state category under the electrical parameter feature data; determine the third membership degree of each shape feature data to each health state category, and perform a weighted summation of the third membership degrees of the same health state category to obtain the first membership degree of each health state category under the shape feature data; determine the fourth membership degree of each temperature feature data to each health state category, and perform a weighted summation of the fourth membership degrees of the same health state category to obtain the first membership degree of each health state category under the temperature feature data.

[0071] In this embodiment, the second membership degree of the resistance change rate to each health state category is obtained based on the relationship between the resistance change rate and the second membership degree. The relationship between the resistance change rate and the second membership degree is as follows: The resistance change rate is an excellent second membership degree: when the resistance change rate is ≤2%, the second membership degree is 1; when the resistance change rate is in the range of 2%-4%, the second membership degree decreases linearly from 1 to 0, and the second membership degree for other values ​​is 0. That is, when the resistance change rate is in the range of 2%-4%, the second membership degree is calculated by linear difference.

[0072] The resistance change rate exhibits a good second membership degree: when the resistance change rate is in the range of 2%-4%, the second membership degree linearly increases from 0 to 1; when the resistance change rate is in the range of 4%-6%, the second membership degree linearly decreases from 1 to 0; and for all other values, the second membership degree is 0.

[0073] The resistance change rate is considered as the second membership degree of attention: when the resistance change rate is in the range of 4%-6%, the second membership degree increases linearly from 0 to 1; when the resistance change rate is in the range of 6%-8%, the second membership degree decreases linearly from 1 to 0; and for all other values, the second membership degree is 0.

[0074] The second membership degree of the resistance change rate is a warning: when the resistance change rate is in the range of 6%-8%, the second membership degree increases linearly from 0 to 1; when the resistance change rate is in the range of 8%-12%, the second membership degree decreases linearly from 1 to 0; and the second membership degree is 0 for all other values.

[0075] The resistance change rate is considered the second membership degree of failure: when the resistance change rate is ≥12%, the second membership degree is 1; when the resistance change rate is in the range of 8%-12%, the second membership degree increases linearly from 0 to 1; and for all other values, the second membership degree is 0.

[0076] Based on the relationship between the power fluctuation coefficient and the second membership degree, the second membership degree of the power fluctuation coefficient belonging to each health state category is obtained. The relationship between the power fluctuation coefficient and the second membership degree is as follows: The power fluctuation coefficient has excellent second membership degree: when the power fluctuation coefficient is ≤0.5%, the second membership degree is 1; when the power fluctuation coefficient is in the range of 0.5%-1%, the second membership degree decreases linearly from 1 to 0, and the second membership degree for other values ​​is 0. That is, when the power fluctuation coefficient is in the range of 0.5%-1%, the second membership degree is calculated by linear difference.

[0077] The power fluctuation coefficient exhibits good second membership: when the power fluctuation coefficient is in the range of 0.5% to 1%, the second membership increases linearly from 0 to 1; when the power fluctuation coefficient is in the range of 1% to 2%, the second membership decreases linearly from 1 to 0; and for all other values, the second membership is 0.

[0078] The power fluctuation coefficient is considered as a second membership degree: when the power fluctuation coefficient is in the range of 1% to 2%, the second membership degree increases linearly from 0 to 1; when the power fluctuation coefficient is in the range of 2% to 3%, the second membership degree decreases linearly from 1 to 0; and for all other values, the second membership degree is 0.

[0079] The second membership degree of the power fluctuation coefficient is a warning: when the power fluctuation coefficient is in the range of 2% to 3%, the second membership degree increases linearly from 0 to 1; when the power fluctuation coefficient is in the range of 3% to 5%, the second membership degree decreases linearly from 1 to 0; and the second membership degree of all other values ​​is 0.

[0080] The power fluctuation coefficient is the second membership degree of the failure: when the power fluctuation coefficient is ≥5%, the second membership degree is 1; when the power fluctuation coefficient is in the range of 3%~5%, the second membership degree increases linearly from 0 to 1; and the second membership degree of other values ​​is 0.

[0081] Based on the relationship between steady-state creep rate and the second membership degree, the second membership degree of steady-state creep rate to each health state category is obtained. The relationship between steady-state creep rate and the second membership degree is as follows: The steady-state creep rate is an excellent second membership degree: when the steady-state creep rate is ≤0.5%, the second membership degree is 1; when the steady-state creep rate is in the range of 0.5%-1%, the second membership degree decreases linearly from 1 to 0, and the second membership degree for other values ​​is 0. That is, when the steady-state creep rate is in the range of 0.5%-1%, the second membership degree is calculated by linear difference.

[0082] The steady-state creep rate exhibits good second membership: when the steady-state creep rate is in the range of 0.5% to 1%, the second membership increases linearly from 0 to 1; when the steady-state creep rate is in the range of 1% to 2%, the second membership decreases linearly from 1 to 0; and for all other values, the second membership is 0.

[0083] The steady-state creep rate is considered as the second membership degree of attention: when the steady-state creep rate is in the range of 1% to 2%, the second membership degree increases linearly from 0 to 1; when the steady-state creep rate is in the range of 2% to 3%, the second membership degree decreases linearly from 1 to 0; and for all other values, the second membership degree is 0.

[0084] The second membership degree of the steady-state creep rate is a warning: when the steady-state creep rate is in the range of 2% to 3%, the second membership degree increases linearly from 0 to 1; when the steady-state creep rate is in the range of 3% to 5%, the second membership degree decreases linearly from 1 to 0; and the second membership degree is 0 for all other values.

[0085] The steady-state creep rate is the second membership degree of failure: when the steady-state creep rate is ≥5%, the second membership degree is 1; when the steady-state creep rate is in the range of 3% to 5%, the second membership degree increases linearly from 0 to 1; and for other values, the second membership degree is 0.

[0086] Based on the relationship between residual deformation rate and the second membership degree, the second membership degree of residual deformation rate belonging to each health state category is obtained. The relationship between residual deformation rate and the second membership degree is as follows: The residual deformation rate is an excellent second membership degree: when the residual deformation rate is ≤0.1%, the second membership degree is 1; when the residual deformation rate is in the range of 0.1%~0.3%, the second membership degree decreases linearly from 1 to 0, and the second membership degree for other values ​​is 0. That is, when the residual deformation rate is in the range of 0.1%~0.3%, the second membership degree is calculated by linear difference.

[0087] The residual deformation rate exhibits good second membership: when the residual deformation rate is in the range of 0.1% to 0.3%, the second membership increases linearly from 0 to 1; when the residual deformation rate is in the range of 0.3% to 0.6%, the second membership decreases linearly from 1 to 0; and for all other values, the second membership is 0.

[0088] The residual deformation rate is considered as the second membership degree of attention: when the residual deformation rate is in the range of 0.3% to 0.6%, the second membership degree increases linearly from 0 to 1; when the residual deformation rate is in the range of 0.6% to 1%, the second membership degree decreases linearly from 1 to 0; and the second membership degree is 0 for all other values.

[0089] The residual deformation rate is a warning level. The second membership degree is as follows: when the residual deformation rate is in the range of 0.6% to 1%, the second membership degree increases linearly from 0 to 1; when the residual deformation rate is in the range of 1% to 1.5%, the second membership degree decreases linearly from 1 to 0; and the second membership degree is 0 for all other values.

[0090] The residual deformation rate is the second membership degree of failure: when the residual deformation rate is ≥1.5%, the second membership degree is 1; when the residual deformation rate is in the range of 1% to 1.5%, the second membership degree increases linearly from 0 to 1; and the second membership degree of other values ​​is 0.

[0091] Based on the relationship between temperature field uniformity and the fourth membership degree, the fourth membership degree of temperature field uniformity belonging to each health state category is obtained. The relationship between temperature field uniformity and the fourth membership degree is as follows: The temperature field uniformity is excellent for the fourth membership degree: when the temperature field uniformity is ≤3%, the fourth membership degree is 1; when the temperature field uniformity is in the range of 3% to 5%, the fourth membership degree decreases linearly from 1 to 0, and the fourth membership degree for other values ​​is 0. That is, when the temperature field uniformity is in the range of 3% to 5%, the fourth membership degree is calculated by linear difference.

[0092] Temperature field uniformity has a good fourth membership degree: when the temperature field uniformity is in the range of 3% to 5%, the fourth membership degree increases linearly from 0 to 1; when the temperature field uniformity is in the range of 5% to 8%, the fourth membership degree decreases linearly from 1 to 0; and the fourth membership degree is 0 for all other values.

[0093] Temperature field uniformity is considered as the fourth membership degree: when the temperature field uniformity is in the range of 5% to 8%, the fourth membership degree increases linearly from 0 to 1; when the temperature field uniformity is in the range of 8% to 12%, the fourth membership degree decreases linearly from 1 to 0; and for all other values, the fourth membership degree is 0.

[0094] Temperature field uniformity falls under the fourth membership degree of the warning: when the temperature field uniformity is in the range of 8% to 12%, the fourth membership degree increases linearly from 0 to 1; when the temperature field uniformity is in the range of 12% to 15%, the fourth membership degree decreases linearly from 1 to 0; and the fourth membership degree is 0 for all other values.

[0095] Temperature field uniformity is the fourth membership degree of failure: when the temperature field uniformity is ≥15%, the fourth membership degree is 1; when the temperature field uniformity is in the range of 12%~15%, the fourth membership degree increases linearly from 0 to 1; and the fourth membership degree of other values ​​is 0.

[0096] Based on the relationship between the rate of temperature decay and the fourth membership degree, the fourth membership degree of the rate of temperature decay belonging to each health state category is obtained. The relationship between the rate of temperature decay and the fourth membership degree is as follows: The heating rate decay rate is an excellent fourth membership degree: when the heating rate decay rate is ≤3%, the fourth membership degree is 1; when the heating rate decay rate is in the range of 3% to 6%, the fourth membership degree decreases linearly from 1 to 0, and the fourth membership degree for other values ​​is 0. That is, when the heating rate decay rate is in the range of 3% to 6%, the fourth membership degree is calculated by linear difference.

[0097] The rate of decrease in heating rate is a good fourth membership degree: when the rate of decrease in heating rate is in the range of 3% to 6%, the fourth membership degree increases linearly from 0 to 1; when the rate of decrease in heating rate is in the range of 6% to 10%, the fourth membership degree decreases linearly from 1 to 0; and the fourth membership degree is 0 for all other values.

[0098] The rate of decrease in heating rate is considered as the fourth membership degree: when the rate of decrease in heating rate is in the range of 6% to 10%, the fourth membership degree increases linearly from 0 to 1; when the rate of decrease in heating rate is in the range of 10% to 15%, the fourth membership degree decreases linearly from 1 to 0; and for all other values, the fourth membership degree is 0.

[0099] The fourth membership degree of the heating rate decay rate is a warning: when the heating rate decay rate is in the range of 10% to 15%, the fourth membership degree increases linearly from 0 to 1; when the heating rate decay rate is in the range of 15% to 20%, the fourth membership degree decreases linearly from 1 to 0; and the fourth membership degree is 0 for all other values.

[0100] The rate of decrease in heating rate is the fourth membership degree of failure: when the rate of decrease in heating rate is ≥15%, the fourth membership degree is 1; when the rate of decrease in heating rate is in the range of 15%~20%, the fourth membership degree increases linearly from 0 to 1; and the fourth membership degree of other values ​​is 0.

[0101] Next, a second weight is assigned to each electrical parameter feature data, each shape feature data, and each temperature feature data. The sum of the second weights of all electrical parameter feature data is 1, the sum of the second weights of all shape feature data is 1, and the sum of the second weights of all temperature feature data is 1.

[0102] For example, the second weight of the resistance change rate is 0.6 and the second weight of the power fluctuation coefficient is 0.4, the second weight of the steady-state creep rate is 0.5 and the second weight of the residual deformation rate is 0.5, the second weight of the temperature field uniformity is 0.7 and the second weight of the heating rate decay rate is 0.3.

[0103] In this embodiment, the sum of the products of the second membership degree of all electrical parameter feature data and their corresponding second weights is calculated to obtain the first membership degree of each health state category under the electrical parameter feature data; the sum of the products of the third membership degree of all shape feature data and their corresponding second weights is calculated to obtain the first membership degree of each health state category under the shape feature data; the sum of the products of the second weights of all temperature feature data is calculated to obtain the first membership degree of each health state category under the temperature feature data.

[0104] The five second membership degrees of the rate of change of resistance are represented as C1=[c 11 ,c 12 ,c 13 ,c 14 ,c 15 The five second membership degrees of the power fluctuation coefficient are represented as C1=[c 21 ,c 22 ,c 23 ,c 24 ,c 25 The second weights for the resistance change rate and power fluctuation coefficient are represented as D=[d1,d2]. Then, the electrical parameter characteristic data belong to the excellent first membership degree r. 11 =c 11 ×d1+c 21 ×d1, and so on, to calculate the first membership degree of the electrical parameter characteristic data to other health status categories.

[0105] Similarly, the first membership degree of shape feature data and temperature feature data to each health state category is calculated.

[0106] In this embodiment of the application, the first weight and the second weight can be dynamically adjusted according to the material grade and service conditions of the component under test.

[0107] Optionally, step 140 includes: The health index of the component under test is obtained by summing the dot product of the evaluation vector value of each health status category and the preset vector coefficients corresponding to each health status category.

[0108] In this embodiment of the application, the vector coefficient V=[V1,V2,V3,V4,V5] corresponding to each health status category is set in advance. For example, the vector coefficient V=[1.0,0.75,0.5,0.25,0].

[0109] In this system, the evaluation vector value for each health status category is denoted as B=[b1,b2,b3,b4,b5]. Then, the health index HI is calculated as V1×b1+V2×b2+V3×b3+V4×b4+V5×b5. Specifically, the system calculates the first product of the excellent evaluation vector value and the excellent vector coefficient, the second product of the good evaluation vector value and the good vector coefficient, the third product of the attentive evaluation vector value and the attentive vector coefficient, the first product of the warning evaluation vector value and the warning vector coefficient, and the first product of the failure evaluation vector value and the failure vector coefficient. Finally, the first, second, third, fourth, and fifth products are added together to obtain the health index of the component under test.

[0110] Optionally, after step 140, the method further includes: If the health index is greater than or equal to the preset first index threshold, the health risk level of the component under test is determined to be low risk; if the health index is less than the first index threshold but greater than the preset second index threshold, the health risk level of the component under test is determined to be medium risk, and a mild emergency alarm is triggered; if the health index is less than or equal to the second index threshold, the health risk level of the component under test is determined to be high risk, and a very urgent alarm is triggered.

[0111] In this embodiment, the higher the health index, the healthier the component under test.

[0112] For example, the first exponential threshold can be 0.75 or 0.8, and the second exponential threshold can be 0.4 or 0.45.

[0113] Optionally, after step 140, the method further includes: If the health index is greater than the preset first index threshold, the resistance increment, creep strain and thermal fatigue damage of the component under test are determined; based on the resistance increment, creep strain and thermal fatigue damage, the remaining service life of the component under test is predicted.

[0114] In this embodiment, if the health index is greater than a preset first index threshold, it indicates that the device under test is relatively healthy and its remaining lifespan can be predicted; if the health index is less than or equal to the first index threshold, it indicates that the device under test is not very healthy and there is no need to predict its remaining lifespan.

[0115] In the embodiments of this application, the calculation methods for resistance increment, creep strain and thermal fatigue damage are existing technologies and will not be described again.

[0116] Then, based on the resistance increment, creep strain, and thermal fatigue damage, and the first weight, a weighted sum is performed to obtain the remaining service life of the device under test. That is, the product of the resistance increment with the first weight of the electrical parameter characteristic data, the product of the creep strain with the first weight of the shape characteristic data, and the product of the thermal fatigue damage with the first weight of the temperature characteristic data are calculated; the three products are added together to obtain the remaining service life of the device under test.

[0117] The component performance evaluation apparatus provided in this application is described below. The component performance evaluation apparatus described below can be referred to in correspondence with the component performance evaluation method described above.

[0118] Figure 2 This is a schematic diagram of the component performance evaluation device provided in an embodiment of this application. (Refer to...) Figure 2 The component performance evaluation device provided in this application embodiment may include an acquisition module 201, a first determination module 202, a second determination module 203 and a third determination module 204.

[0119] The acquisition module 201 is used to acquire the operating data of the component under test in real time and the preset health status category when the component under test is powered on. The operating data includes electrical parameter characteristic data, shape characteristic data and temperature characteristic data, and the health status category includes excellent, good, attention, warning and failure. The first determining module 202 is used to determine the first membership degree of each type of operational data to each health status category; The second determining module 203 is used to perform a weighted summation of the first membership degrees of the same health status category to obtain the evaluation vector value of each health status category; The third determining module 204 is used to determine the health index of the component under test based on the evaluation vector value of each health status category, wherein the health index is used to characterize the health of the component under test.

[0120] Optionally, the electrical parameter characteristic data includes the rate of change of resistance and the power fluctuation coefficient; the shape characteristic data includes the steady-state creep rate and the residual deformation rate; and the temperature characteristic data includes the temperature field uniformity and the rate of temperature rise decay. The first determining module 202 is also used for: Determine the second membership degree of each electrical parameter feature data to each health state category, and perform a weighted summation of the second membership degrees of the same health state category to obtain the first membership degree of each health state category under the electrical parameter feature data; Determine the third membership degree of each shape feature data to each health status category, and perform a weighted summation of the third membership degrees of the same health status category to obtain the first membership degree of each health status category under the shape feature data; Determine the fourth membership degree of each temperature feature data to each health state category, and perform a weighted summation of the fourth membership degrees of the same health state category to obtain the first membership degree of each health state category under each electrical parameter feature data.

[0121] Optionally, the third determining module 204 is also used for: The health index of the component under test is obtained by summing the dot product of the evaluation vector value of each health status category and the preset vector coefficients corresponding to each health status category.

[0122] Optionally, the device 200 further includes a fourth determining module for: If the health index is greater than or equal to the preset first index threshold, the health risk level of the component under test is determined to be low risk. If the health index is less than the first index threshold and greater than the preset second index threshold, the health risk level of the component under test is determined to be medium risk, and a mild emergency alarm is triggered. If the health index is less than or equal to the second index threshold, the health risk level of the component under test is determined to be high risk, and an emergency alarm is triggered.

[0123] Optionally, the device 200 further includes a fifth determining module for: If the health index is greater than the preset first index threshold, then the resistance increment, creep strain and thermal fatigue damage of the component under test are determined. The remaining service life of the component under test is predicted based on the resistance increment, creep strain, and thermal fatigue damage.

[0124] Optionally, the device 200 further includes a sixth determining module for: Based on the operating data, the functional status of the component under test is determined. The functional status includes the effective status, oxidation failure status, thermal fatigue failure status, and creep failure status.

[0125] Optionally, the sixth determining module is also used for: The running data is input into the pre-built support vector machine model to obtain the functional state output by the support vector machine model; The support vector machine model is trained using a sample set, which includes experimental runtime sequence data and corresponding functional state labels.

[0126] Specifically, the component performance evaluation device provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0127] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operations described above.

[0128] Based on the same inventive concept, this application also provides an electronic device, which may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a component performance evaluation method. Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0129] On the other hand, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the component performance evaluation methods provided by the methods described above. In another aspect, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to perform the steps of the component performance evaluation method provided by the above methods.

[0130] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0132] It should also be noted that the terms "first," "second," etc., used in the embodiments of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, and the number of objects is not limited. For example, the first object can be one or more.

[0133] In the embodiments of this application, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0134] In this application's embodiments, "determine B based on A" means that factor A must be considered when determining B. It is not limited to "B can be determined based solely on A," but should also include: "determine B based on A and C," "determine B based on A, C, and E," "determine C based on A, and further determine B based on C," etc. Additionally, it can include using A as a condition for determining B, for example, "when A meets the first condition, determine B using the first method"; another example, "when A meets the second condition, determine B," etc.; another example, "when A meets the third condition, determine B based on the first parameter," etc. Of course, it can also be a condition where A is a factor in determining B, for example, "when A meets the first condition, determine C using the first method, and further determine B based on C," etc.

[0135] In the embodiments of this application, the term "multiple" refers to two or more, and other quantifiers are similar.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for evaluating component performance, characterized in that, include: When the device under test is powered on, the operating data of the device under test and the preset health status categories are acquired in real time. The operating data includes electrical parameter characteristic data, shape characteristic data and temperature characteristic data. The health status categories include excellent, good, attention, warning and failure. Determine the first membership degree of each type of operational data to each health status category; The first membership degree of the same health status category is weighted and summed to obtain the evaluation vector value of each health status category; Based on the evaluation vector value of each health status category, a health index is determined for the component under test, wherein the health index is used to characterize the health of the component under test.

2. The method according to claim 1, characterized in that, The electrical parameter characteristic data includes the rate of change of resistance and the power fluctuation coefficient; the shape characteristic data includes the steady-state creep rate and the residual deformation rate; the temperature characteristic data includes the temperature field uniformity and the rate of temperature rise decay; and determining the first membership degree of each type of operating data to each health state category further includes: Determine the second membership degree of each electrical parameter feature data to each health state category, and perform a weighted summation of the second membership degrees of the same health state category to obtain the first membership degree of each health state category under the electrical parameter feature data; The third membership degree of each shape feature data to each health status category is determined, and the third membership degrees of the same health status category are weighted and summed to obtain the first membership degree of each health status category under the shape feature data. Determine the fourth membership degree of each temperature feature data to each health state category, and perform a weighted summation of the fourth membership degrees of the same health state category to obtain the first membership degree of each health state category under each temperature feature data.

3. The method according to claim 1, characterized in that, Determining the health index of the component under test based on the evaluation vector value of each health status category includes: The health index of the component under test is obtained by summing the evaluation vector value of each health status category and the preset vector coefficients corresponding to each health status category through a dot product.

4. The method according to claim 1, characterized in that, After determining the health index of the component under test, the method further includes: If the health index is greater than or equal to a preset first index threshold, then the health risk level of the component under test is determined to be low risk. If the health index is less than the first index threshold and greater than the preset second index threshold, the health risk level of the component under test is determined to be medium risk, and a mild emergency alarm is triggered. If the health index is less than or equal to the second index threshold, the health risk level of the component under test is determined to be high risk, and an emergency alarm is triggered.

5. The method according to claim 1, characterized in that, After determining the health index of the component under test, the method further includes: If the health index is greater than the preset first index threshold, then the resistance increment, creep strain and thermal fatigue damage of the component under test are determined. The remaining service life of the component under test is predicted based on the resistance increment, the creep strain, and the thermal fatigue damage degree.

6. The method according to claim 1, characterized in that, After acquiring the operating data of the component under test in real time, the method further includes: Based on the operational data, the functional state of the component under test is determined, including the effective state, oxidation failure state, thermal fatigue failure state, and creep failure state.

7. The method according to claim 6, characterized in that, Determining the functional state of the component under test based on the operational data includes: The running data is input into a pre-built support vector machine model to obtain the functional state output by the support vector machine model; The support vector machine model is trained using a sample set, which includes experimental runtime sequence data and corresponding functional state labels.

8. A component performance evaluation device, characterized in that, The device includes: The acquisition module is used to acquire the operating data of the device under test and the preset health status category in real time when the device under test is powered on. The operating data includes electrical parameter characteristic data, shape characteristic data and temperature characteristic data, and the health status category includes excellent, good, attention, warning and failure. The first determination module is used to determine the first membership degree of each type of operational data to each health status category; The second determining module is used to perform a weighted summation of the first membership degrees of the same health status category to obtain the evaluation vector value of each health status category; The third determining module is used to determine the health index of the component under test based on the evaluation vector value of each health status category, wherein the health index is used to characterize the health of the component under test.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method of any one of claims 1-7.

10. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images