Memory alloy part durability experiment data analysis method and system

Abstract

The invention discloses a memory alloy part durability experiment data analysis method and system, relates to the technical field of data processing, and aims to solve the problem of poor alloy performance detection effect caused by environmental noise interference and signal scattering of existing memory alloy durability experiment data. A differential signal processing strategy is adopted to carry out noise reduction optimization on multi-dimensional performance response data, characteristic factors representing deformation recovery, residual deformation and energy dissipation are extracted and corrected, and combined logic of the characteristic factors is dynamically judged by combining a recognition rule set based on an application scene so as to determine a specific performance degradation mode. Corresponding residual use cycle prediction models are constructed according to different degradation modes, the credibility range is calculated, finally, a performance optimization strategy is generated through matching, and full-process closed-loop analysis from data preprocessing and feature extraction to degradation mode recognition, service life prediction and strategy generation is achieved. And the performance prediction precision and the reliability evaluation efficiency of the memory alloy part under the complex working condition are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method and system for analyzing experimental data on the durability of shape memory alloy parts. Background Technology

[0002] In modern industrial production, accurate assessment of material properties is crucial for ensuring product quality and safety. Particularly in fields with specific material requirements, such as furniture manufacturing, shape memory alloys, due to their unique shape memory and superelasticity, are widely used in movable components requiring flexible deformation and reliable support, such as height-adjustable leisure table supports and folding camping tables and chairs. The durability of these shape memory alloy components directly affects product safety and lifespan; therefore, accurate and efficient assessment of their durability is of paramount importance.

[0003] However, in actual durability tests of shape memory alloy parts, repeated loading and unloading cycles are typically performed under different environmental pressures, generating a large amount of experimental data, such as deformation recovery rate and load-displacement response. This data often exhibits significant dispersion; even materials from the same batch under similar test conditions can show considerable fluctuations. Traditional analytical methods are inefficient in processing this multifaceted and nonlinear data, struggling to extract clear and consistent patterns. This leads to significant biases in judging material performance degradation trends and remaining service life, ultimately affecting the accuracy of product reliability design and quality control.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] This invention addresses the problem of poor alloy performance testing results caused by environmental noise interference and signal scattering in existing shape memory alloy durability test data. It proposes a method and system for analyzing shape memory alloy component durability test data. By employing a differential signal processing strategy to denoise and optimize multidimensional performance response data, it extracts and corrects characteristic factors representing deformation recovery, residual deformation, and energy dissipation. Combined with an application scenario-based identification rule set, it dynamically discriminates the combination logic of characteristic factors to determine specific performance degradation modes. Then, based on different degradation modes, it constructs corresponding remaining service life prediction models and calculates the confidence range. Finally, it matches and generates performance optimization strategies, achieving a closed-loop analysis from data preprocessing and feature extraction to degradation mode identification, life prediction, and strategy generation. This significantly improves the performance prediction accuracy and reliability assessment efficiency of shape memory alloy components under complex working conditions.

[0006] In a first aspect, one technical solution provided in the embodiments of the present invention is: a method for analyzing experimental data on the durability of shape memory alloy parts, comprising: Multiple performance response data of shape memory alloy parts generated in durability tests are obtained. Differential signal processing strategy is used to optimize the multiple performance response data. Multiple feature information reflecting the performance state changes of shape memory alloy parts is extracted from the optimized performance response data. The feature information includes a recovery factor characterizing deformation recovery capability, a cumulative factor characterizing residual deformation, and an evolution factor characterizing energy dissipation. A specific performance degradation mode of the shape memory alloy part is determined based on a combination of multiple features, the specific performance degradation mode including changes in energy dissipation mechanisms or increases in plastic deformation; Based on the specific performance degradation mode, the remaining service life of the shape memory alloy part is predicted, and the confidence range of the remaining service life is determined. The corresponding performance optimization strategy is determined based on the specific performance degradation mode, remaining usage period, and confidence range.

[0007] Preferably, the step of using a differential signal processing strategy to optimize various performance response data to obtain multiple feature information reflecting changes in the performance state of the shape memory alloy part includes: Time-frequency analysis was performed on the performance response data to distinguish performance degradation characteristic signals from environmental noise signals; The amplitude of the identified performance degradation characteristic signal is enhanced according to the preset gain function; The amplitude of the identified environmental noise signal is attenuated according to a preset suppression function; and, The amplified feature signal and the suppressed noise signal are combined to obtain the optimized performance response data.

[0008] Preferably, the deformation recovery capability recovery factor includes the deformation recovery rate and the deformation recovery trend; the residual deformation accumulation factor includes the residual deformation accumulation rate and the residual deformation accumulation trend; the energy dissipation evolution factor includes the energy dissipation evolution rate and the evolution trend; the step of determining the specific performance degradation mode of the shape memory alloy part based on the combination of multiple feature information includes: Receive application scenario information for the shape memory alloy component to be evaluated, including furniture product type and component working environment; Based on the application scenario information, a set of identification rules matching the application scenario information is retrieved from a preset scenario rule base. The set of identification rules defines the judgment thresholds and combination logic for the deformation recovery capability, the accumulation factor of residual deformation, and the evolution factor of energy dissipation for the application scenario. Based on the identification rule set, the recovery factor of the deformation recovery capability, the accumulation factor of the residual deformation, and the evolution factor of energy dissipation are combined and judged to identify the specific performance degradation mode of the shape memory alloy part. The specific performance degradation mode includes changes in the energy dissipation mechanism or an increase in plastic deformation.

[0009] Based on this, this application further proposes the following step: Based on the aforementioned identification rule set, combining and judging the recovery factor of the deformation recovery capability, the accumulation factor of the residual deformation, and the evolution factor of energy dissipation to identify the specific performance degradation mode of the shape memory alloy part, including: Determine whether the cumulative factor of the residual deformation satisfies the first criterion defined in the set of identification rules, which characterizes irreversible structural damage to the material. If the first determination condition is met, the specific performance degradation mode is identified as an increase in plastic deformation; If the first determination condition is not met, then determine whether the recovery factor of the deformation recovery capability and the evolution factor of the energy dissipation jointly satisfy the second determination condition defined in the identification rule set, which characterizes the abnormal energy dissipation mechanism of the material. If the second determination condition is met, then the discrimination logic is executed based on whether the cumulative rate of residual deformation meets the stability condition defined in the identification rule set; otherwise, the alloy performance state is determined to be normal. When the stability condition is met, the current state is determined to be a pseudo signal caused by environmental interference; When the stability condition is not met, the specific performance degradation mode is identified as a change in the energy dissipation mechanism.

[0010] In some preferred embodiments, the step of predicting the remaining service life of the shape memory alloy component based on the specific performance degradation mode and determining the confidence range of the remaining service life includes: When the specific performance degradation mode is identified as an increase in plastic deformation, the current residual deformation and the accumulation factor of the residual deformation are obtained. The remaining service life is determined based on the preset failure residual deformation threshold, the current residual deformation, and the accumulation factor of the residual deformation. When the specific performance degradation mode is identified as a change in the energy dissipation mechanism, and the cumulative factor of the residual deformation does not show accelerated growth, the prediction of the remaining service life is paused and an environmental disturbance warning is generated. Based on the fluctuation range of the cumulative rate of residual deformation within a preset historical data window, the confidence interval corresponding to the remaining service life is calculated.

[0011] In some preferred embodiments, the step of determining the remaining service life based on a preset residual deformation threshold, the current residual deformation, and a cumulative factor for the residual deformation includes: Based on the residual deformation accumulation trend contained in the residual deformation accumulation factor, the growth pattern of the current residual deformation is determined; When the growth pattern is determined to be accelerated growth, an exponential growth prediction model is constructed based on the current residual deformation, the cumulative rate of residual deformation, and the acceleration parameter. The preset residual deformation threshold is used as the input to the exponential growth prediction model, and the remaining service life is obtained by reverse calculation. When the growth pattern is determined to be uniform growth, the remaining service life is determined based on the ratio of the difference between the current residual deformation and the failure residual deformation threshold to the current average cumulative rate contained in the cumulative factor of the residual deformation.

[0012] In some preferred embodiments, the step of calculating the confidence interval corresponding to the remaining service life based on the fluctuation range of the residual deformation accumulation rate within a preset historical data window includes: A historical data window for statistical analysis is determined, the window containing the cumulative rate of residual deformation corresponding to a preset number of consecutive cycles; The standard deviation of the cumulative rate of all residual deformation within the window is used as a quantitative indicator to characterize its fluctuation range. Using the remaining usage period as the center of the predicted value, the upper and lower limits of the confidence interval are determined based on the quantitative indicators and the preset confidence level.

[0013] Preferably, the step of determining the corresponding performance optimization strategy based on the specific performance degradation mode, remaining usage period, and confidence range includes: Based on the specific performance degradation mode, the target type of the optimization strategy is determined, including material improvement strategies or structural improvement strategies for delaying structural degradation, or strategies for isolating or compensating for environmental disturbances. Based on the comparison between the remaining usage period and the preset lifespan safety threshold, and the scale of the confidence range, the priority of the optimization strategy is determined. Based on the target type and priority, at least one specific performance optimization strategy is matched and generated from a preset optimization strategy knowledge base.

[0014] In some preferred embodiments, the step of extracting multiple feature information reflecting changes in the performance state of shape memory alloy parts from the optimized performance response data includes: From the optimized performance response data, extract the deformation recovery rate, residual deformation, and load-displacement data for each test cycle; The output value of the displacement sensor under zero load is periodically acquired as the current zero offset, and the zero offset is used to correct all extracted deformation recovery rate and residual deformation in real time to obtain the corrected deformation recovery rate and corrected residual deformation. Based on the corrected deformation recovery rate, the corresponding deformation recovery rate and deformation recovery trend are calculated respectively. Based on the corrected residual deformation, calculate the cumulative rate of residual deformation and the cumulative trend of residual deformation in consecutive cycles. Based on the load-displacement data for each cycle, the hysteresis loop area is calculated by numerical integration, and the evolution rate and trend of energy dissipation are determined based on the hysteresis loop area change data of continuous cycles.

[0015] Secondly, an embodiment of the present invention also provides a technical solution: a durability test data analysis system for shape memory alloy parts, applicable to a durability test data analysis method for shape memory alloy parts as described in any of the first aspects, comprising: Data acquisition module: used to acquire various performance response data of shape memory alloy parts during durability tests; Data preprocessing module: The differential signal processing strategy is used to optimize the various performance response data, and multiple feature information reflecting the performance state changes of shape memory alloy parts is extracted from the optimized performance response data; Degradation mode determination module: Determines the specific performance degradation mode of the shape memory alloy part based on the combination of multiple feature information; Lifetime prediction module: Based on the specific performance degradation mode, predict the remaining service life of the shape memory alloy part and determine the confidence range of the remaining service life; Strategy generation module: Determines the corresponding performance optimization strategy based on the specific performance degradation mode, remaining usage period, and confidence range.

[0016] The present invention has at least the following substantial beneficial effects: (1) This application optimizes the original data by employing a differential signal processing strategy. First, time-frequency analysis is used to accurately distinguish between performance degradation characteristic signals and environmental noise signals. Then, the amplitudes of the two types of signals are adjusted by gain and suppression functions respectively to achieve noise reduction. At the same time, combined with real-time zero-point offset correction technology, three types of feature factors containing rate and trend dimensions—recovery, accumulation, and evolution—are extracted from the optimized data. This method effectively removes environmental noise interference, eliminates the systematic error caused by sensor zero-point offset, and completely solves the pain point that traditional methods cannot extract effective performance features from scattered data. It significantly improves the processing accuracy and efficiency of multidimensional experimental data, enabling the extracted feature factors to accurately and dynamically reflect the actual performance state of shape memory alloy parts.

[0017] (2) This application receives application scenario information such as furniture product type and component working environment, retrieves matching recognition rule sets from a preset library, defines judgment thresholds and combination logic for feature factors, and then uses hierarchical and progressive combination discrimination logic to complete degradation pattern recognition. At the same time, it identifies false signals caused by environmental interference based on the stability of the residual deformation accumulation rate. This method achieves scenario-based accurate recognition of two specific degradation modes: increased plastic deformation and altered energy dissipation mechanism. It effectively eliminates false signal interference, making the degradation pattern recognition results highly consistent with the actual application conditions and real performance degradation state of shape memory alloy parts. This solves the technical problems of traditional judgment methods lacking adaptability and having large result deviations.

[0018] (3) This application constructs a customized life prediction model based on the identified specific performance degradation modes. For cases of increased plastic deformation, an exponential or uniform growth model is constructed according to the residual deformation growth mode to calculate the remaining cycle. For cases where the energy dissipation mechanism changes and there is no accelerated growth of residual deformation, the prediction is paused and an environmental interference warning is generated. At the same time, the confidence interval is calculated by using the fluctuation range of the residual deformation accumulation rate in the historical data window to quantify the credibility. Then, the degradation mode, life results, and credibility are combined to determine the optimization target type and priority, and a targeted performance optimization strategy is generated. This method achieves accurate prediction and credible quantification of the remaining service life. The generated optimization strategy is both targeted and prioritized, and a closed-loop analysis system from data preprocessing to strategy generation is constructed. This significantly improves the performance prediction accuracy and reliability assessment efficiency of shape memory alloy parts under complex working conditions, and provides full-process scientific and technological support for the reliability design and quality control of related products.

[0019] The above description of the invention is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0020] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. The drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings.

[0021] Figure 1 This is a flowchart of a method for analyzing experimental data on the durability of shape memory alloy parts according to an embodiment of the present invention.

[0022] Figure 2 This is a flowchart illustrating the logic for determining a specific performance degradation mode of a shape memory alloy component in an embodiment of the present invention.

[0023] Figure 3 This is a block diagram of a durability test data analysis system for shape memory alloy parts according to an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only one preferred embodiment of this invention and are only used to explain this invention. They do not limit the scope of protection of this invention. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0025] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations (or steps) can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it may also have additional steps not included in the figures; the process may correspond to a method, function, procedure, subroutine, subroutine, etc.

[0026] In modern industrial production, accurate assessment of material properties is crucial for ensuring product quality and safety. Especially in fields with specific material requirements, such as furniture manufacturing, shape memory alloys, due to their unique shape memory and superelasticity, are widely used in movable components requiring flexible deformation and reliable support, such as height-adjustable leisure table supports and folding camping tables and chairs. The durability of these shape memory alloy components directly affects product safety and lifespan; therefore, accurate and efficient assessment of their durability is paramount. However, in actual durability tests of shape memory alloy components, repeated loading and unloading cycles under varying environmental pressures are typically conducted, generating a large amount of experimental data, such as deformation recovery rate and load-displacement response. This data often exhibits significant dispersion; even materials from the same batch under similar test conditions can show considerable fluctuations. Traditional analytical methods are inefficient in processing this multifaceted and nonlinear data, struggling to extract clear and consistent patterns. This leads to significant deviations in judging material performance degradation trends and remaining service life, ultimately affecting the accuracy of product reliability design and quality control.

[0027] In response, this application proposes a method for analyzing experimental data on the durability of shape memory alloy parts, such as... Figure 1 As shown, it includes: S1. Obtain various performance response data of shape memory alloy parts generated in durability tests, and use differential signal processing strategy to optimize the various performance response data. Extract multiple feature information reflecting the performance state changes of shape memory alloy parts from the optimized performance response data. The feature information includes a recovery factor characterizing deformation recovery capability, a cumulative factor characterizing residual deformation, and an evolution factor characterizing energy dissipation. S2. Determine a specific performance degradation mode of the shape memory alloy part based on the combination of multiple feature information, wherein the specific performance degradation mode includes changes in energy dissipation mechanism or increases in plastic deformation; S3. Based on the specific performance degradation mode, predict the remaining service life of the shape memory alloy part and determine the confidence range of the remaining service life; S4. Determine the corresponding performance optimization strategy based on the specific performance degradation mode, remaining usage period, and confidence range.

[0028] The method for analyzing durability test data of shape memory alloy parts proposed in this application acquires various performance response data generated during durability tests and optimizes these data using a differential signal processing strategy. This effectively removes noise and interference, resulting in cleaner and more accurate performance response data. Multiple characteristic information, such as the deformation recovery factor, the cumulative factor of residual deformation, and the evolution factor of energy dissipation, are extracted from the optimized data. This characteristic information comprehensively and multidimensionally reflects the performance state changes of the shape memory alloy parts.

[0029] Furthermore, by analyzing the combinations of these characteristic information, specific performance degradation modes of shape memory alloy components can be accurately determined, such as changes in energy dissipation mechanisms or increases in plastic deformation. This pattern recognition capability enables a deeper understanding of the failure mechanisms of shape memory alloy components, thus providing a solid foundation for subsequent life prediction and strategy development.

[0030] Based on this, and using the identified specific performance degradation patterns, the remaining service life of shape memory alloy components can be predicted, and the reliability range of the prediction results can be determined. This not only provides a quantitative lifespan assessment but also quantifies the reliability of the assessment results, enabling users to make more informed decisions.

[0031] Ultimately, based on the specific performance degradation pattern, remaining service life, and confidence level, a corresponding performance optimization strategy can be determined. This strategy is highly customized and can provide targeted solutions to specific degradation problems of shape memory alloy components, thereby effectively extending their service life and improving their reliability.

[0032] Understandably, traditional durability test data analysis often relies on empirical judgment or simple statistical analysis, making it difficult to handle complex and variable performance response data. Furthermore, its ability to identify performance degradation patterns is limited, resulting in low accuracy in lifespan prediction and a lack of targeted optimization strategies. This application significantly improves the depth and breadth of data analysis by introducing advanced technologies such as differential signal processing, multi-feature information extraction, degradation pattern recognition, and reliability assessment. For example, when processing scattered performance response data, traditional filtering methods may not effectively distinguish performance degradation feature signals from environmental noise signals. The differential signal processing strategy of this application can more accurately optimize the data, thereby extracting more representative feature information. In addition, this application can identify specific performance degradation patterns, making the proposed optimization strategy more instructive and practical, fundamentally solving the durability problem of shape memory alloy parts, rather than merely delaying their failure. Therefore, this application represents a significant technological advancement and innovation in improving the accuracy, efficiency, and reliability of shape memory alloy part durability assessment.

[0033] In order to better understand the technical solutions proposed in this application, it is necessary to explain some key terms involved therein.

[0034] "Memory alloy parts" refer to components made of alloy materials that have shape memory effect or superelasticity effect, such as springs, rods, or sheets made of nickel-titanium alloys. These components can recover their original shape or exhibit large recoverable deformation under specific temperature or stress conditions.

[0035] "Durability testing" refers to experiments that evaluate the performance stability and lifespan of shape memory alloy parts under long-term use by simulating cyclic loading and unloading processes in a real working environment.

[0036] "Performance response data" refers to various data reflecting the changes in the state of shape memory alloy parts, such as displacement, load, temperature, and resistance, which are collected in real time by sensors and other equipment during durability testing.

[0037] "Specific performance degradation mode" refers to the performance decline trend of shape memory alloy parts in durability tests, which is dominated by a specific mechanism, such as increased plastic deformation caused by microcrack propagation, or energy dissipation caused by changes in phase transformation characteristics.

[0038] In some embodiments described above, this application proposes optimizing various performance response data generated during durability tests of shape memory alloy parts to extract feature information reflecting changes in their performance state. However, in actual durability testing environments, the acquired performance response data is often affected by various environmental noises, such as mechanical vibration, electromagnetic interference, or temperature fluctuations. If these noise signals are not effectively distinguished from the true performance degradation feature signals and processed accordingly, the optimized performance response data may still contain significant noise components, thus affecting the accuracy and reliability of subsequent feature information extraction.

[0039] In this regard, this application further proposes that the steps of using differential signal processing strategies to optimize various performance response data to obtain multiple characteristic information reflecting changes in the performance state of shape memory alloy parts include: Time-frequency analysis was performed on the performance response data to distinguish performance degradation characteristic signals from environmental noise signals; The amplitude of the identified performance degradation characteristic signal is enhanced according to the preset gain function; The amplitude of the identified environmental noise signal is attenuated according to a preset suppression function; and, The amplified feature signal and the suppressed noise signal are combined to obtain the optimized performance response data.

[0040] Specifically, time-frequency analysis of performance response data refers to transforming the signal from the time domain to the time-frequency domain, thereby enabling simultaneous observation of the signal's distribution characteristics in time and frequency. This process can employ methods such as short-time Fourier transform, wavelet transform, or Hilberbert-Huang transform. The aim is to effectively distinguish and identify the two types of signals by utilizing the differences in frequency, energy distribution, or temporal duration between performance degradation characteristic signals and environmental noise signals.

[0041] The amplitude enhancement of the identified performance degradation characteristic signals based on a preset gain function refers to applying a specific mathematical function (i.e., a gain function) to amplify the amplitude of these signals after identifying the signal components representing the performance degradation of shape memory alloy parts through time-frequency analysis. The gain function can be preset based on experience, experimental data, or model prediction. Its purpose is to improve the signal-to-noise ratio of the performance degradation characteristic signals, making them more significant in subsequent processing and preventing them from being masked by weak noise.

[0042] In practical applications, amplitude attenuation of identified environmental noise signals based on a preset suppression function refers to applying a specific mathematical function (i.e., the suppression function) to reduce the amplitude of environmental noise components identified through time-frequency analysis. The suppression function is designed to minimize noise while minimizing its impact on performance degradation characteristic signals. For example, band-stop filters, adaptive noise cancellation algorithms, or threshold-based soft / hard thresholding methods can be used. The aim is to effectively reduce noise interference in data analysis and improve data purity.

[0043] Furthermore, synthesizing the amplified feature signal and the suppressed noise signal to obtain optimized performance response data involves recombining these two signals after separately enhancing the feature signal and attenuating the noise signal. This synthesis process is typically performed in the time-frequency domain or after an inverse transformation back to the time domain to generate comprehensive data that retains key performance degradation information while significantly reducing the impact of noise. Therefore, the resulting optimized performance response data can more accurately reflect the true performance changes of shape memory alloy components.

[0044] This embodiment effectively solves the problem of inaccurate feature information extraction caused by noise interference in traditional optimization processing by introducing a combined strategy of time-frequency analysis, gain function enhancement, and suppression function attenuation. First, time-frequency analysis decomposes the original performance response data into a two-dimensional space of time and frequency, allowing performance degradation feature signals and environmental noise signals to be distinguished due to their inherent time-frequency characteristics. For example, performance degradation signals may exhibit slow changes or periodic patterns within a specific frequency range, while environmental noise may exhibit broadband random fluctuations or specific high-frequency spikes. Once distinguished, the amplitude of the feature signal representing performance degradation can be specifically enhanced to make it more dominant in the data, thereby highlighting its changing trend and pattern. Simultaneously, amplitude attenuation of the identified environmental noise signal can minimize its negative impact on data analysis. Finally, by synthesizing the enhanced feature signal and the attenuated noise signal, the resulting optimized performance response data can more purely and accurately reflect the true performance degradation process of the shape memory alloy component, providing high-quality input for subsequent feature information extraction.

[0045] In some preferred embodiments, it is assumed that load-displacement curve data for each cycle are acquired using displacement and force sensors during durability tests on shape memory alloy components. This raw data may be affected by environmental noise such as test bench vibration and power supply fluctuations.

[0046] First, time-frequency analysis is performed on these raw load-displacement data. For example, continuous wavelet transform can be used to decompose the signal, and by selecting appropriate wavelet basis functions, the signal can be decomposed into different frequency scales. By analyzing the energy distribution and time-domain characteristics at different scales, low-frequency or specific frequency range signal components related to deformation recovery, residual deformation accumulation, and energy dissipation of shape memory alloy parts can be identified as performance degradation characteristic signals, while high-frequency random fluctuations or periodic interference at specific frequencies can be identified as environmental noise signals.

[0047] Secondly, for the identified performance degradation characteristic signals, amplitude enhancement can be performed based on a preset gain function. For example, a bandpass filter with high gain within the characteristic signal frequency range can be designed, or an adaptive gain strategy based on signal energy density can be adopted to amplify the amplitude of these key signals.

[0048] Meanwhile, the amplitude of the identified environmental noise signal can be attenuated according to a preset suppression function. For example, a band-stop filter can be used to filter out periodic noise at a specific frequency, or a wavelet thresholding method can be used to perform soft or hard thresholding on the wavelet coefficients of the noise component, thereby effectively reducing its amplitude.

[0049] Finally, the gain-processed feature signal is synthesized with the noise-suppressed signal. This can be reconstructed back into the time domain using inverse wavelet transform, resulting in optimized load-displacement data that significantly removes noise interference while highlighting performance degradation characteristics. Based on this optimized data, the recovery factor of deformation recovery capability, the accumulation factor of residual deformation, and the evolution factor of energy dissipation can be calculated more accurately.

[0050] In some embodiments described above, the determination of specific performance degradation modes of shape memory alloy parts is based on combinations of multiple feature information or preset fixed rules. However, shape memory alloy parts face diverse scenarios in practical applications, such as different types of furniture products or the working environments of components. These scenarios may have significantly different performance requirements and degradation tolerance for shape memory alloy parts. If a uniform or fixed rule is used to determine the performance degradation mode, it may not be able to fully adapt to the characteristics of different application scenarios, resulting in insufficient accuracy and specificity in degradation mode identification, thereby affecting the effectiveness of subsequent lifespan prediction and optimization strategies.

[0051] In this regard, this application further proposes that the deformation recovery capability recovery factor includes the deformation recovery rate and the deformation recovery trend; the residual deformation accumulation factor includes the residual deformation accumulation rate and the residual deformation accumulation trend; the energy dissipation evolution factor includes the energy dissipation evolution rate and the evolution trend; the step of determining the specific performance degradation mode of the shape memory alloy part based on the combination of multiple feature information includes: Receive application scenario information for the shape memory alloy component to be evaluated, including furniture product type and component working environment; Based on the application scenario information, a set of identification rules matching the application scenario information is retrieved from a preset scenario rule base. The set of identification rules defines the judgment thresholds and combination logic for the deformation recovery capability, the accumulation factor of residual deformation, and the evolution factor of energy dissipation for the application scenario. Based on the identification rule set, the recovery factor of the deformation recovery capability, the accumulation factor of the residual deformation, and the evolution factor of energy dissipation are combined and judged to identify the specific performance degradation mode of the shape memory alloy part. The specific performance degradation mode includes changes in the energy dissipation mechanism or an increase in plastic deformation.

[0052] Specifically, the deformation recovery factor is an indicator that measures the ability of a shape memory alloy part to recover its original or predetermined shape after deformation. Among them, the deformation recovery rate refers to the change in the amount of deformation recovery per unit time, reflecting the speed of the recovery process; the deformation recovery trend describes the direction and pattern of deformation recovery capability changes with time or number of cycles, such as whether it remains stable, gradually decreases, or decreases rapidly.

[0053] The residual deformation accumulation factor is used to characterize the amount of irreversible deformation accumulated in shape memory alloy parts over each cycle or period of time. The residual deformation accumulation rate refers to the rate at which the residual deformation increases per unit time, reflecting the cumulative efficiency of plastic deformation; the residual deformation accumulation trend describes how the residual deformation accumulation pattern changes over time or the number of cycles, such as linear growth, accelerated growth, or decelerated growth.

[0054] The evolution factor of energy dissipation reflects the changes in internal energy loss of shape memory alloy components during cyclic loading. The evolution rate of energy dissipation refers to the rate of change in energy dissipation per unit time; the evolution trend describes the direction of change in the energy dissipation pattern over time or the number of cycles, such as stabilization, increase, or decrease.

[0055] When determining the specific performance degradation mode of shape memory alloy parts, the first step is to compare the cumulative factor of residual deformation with a preset threshold to preliminarily determine whether the shape memory alloy part has entered the structural degradation stage. This threshold is usually set based on a large amount of experimental data and experience. When the cumulative factor exceeds this threshold, it indicates that the macroscopic structure of the shape memory alloy part may have undergone significant changes.

[0056] If the structural degradation stage has not yet been determined, the deformation recovery trend and energy dissipation evolution factors of the shape memory alloy component are further obtained. These factors are compared with their respective preset thresholds. For example, when the deformation recovery trend shows a significant decrease and the energy dissipation evolution factor shows abnormal changes, it can be determined that the shape memory alloy component may have entered an early warning stage of altered energy dissipation mechanisms. This indicates that the microstructure or phase transition mechanism inside the shape memory alloy component may be changing, but has not yet led to macroscopic structural damage.

[0057] Specifically, receiving application scenario information for the shape memory alloy component to be evaluated means obtaining detailed data on the actual usage environment and purpose of the component. This application scenario information can be understood as a specific description of the working environment of the shape memory alloy component and its function. For example, the furniture product type could refer to the shape memory alloy component being used in different types of furniture such as smart height-adjustable desks, adjustable sofas, or folding chairs; the component's working environment could refer to external conditions such as temperature, humidity, load type (e.g., cyclic load, impact load), load magnitude, and usage frequency. This information is crucial for accurately assessing the performance degradation of shape memory alloy components.

[0058] The process involves retrieving a set of recognition rules that match the application scenario information from a pre-defined scenario rule base. The aim is to provide customized degradation pattern recognition standards for different application scenarios. The scenario rule base is a pre-built database that stores recognition rule sets for various typical application scenarios. Each recognition rule set includes specific judgment thresholds and combinational logic. These thresholds and logic are determined based on extensive experimental data and expert experience analysis, taking into account factors such as the expected performance, failure modes, and safety requirements of shape memory alloy parts in that scenario. For example, the judgment threshold may be set more strictly for medical device applications with high reliability requirements, while it may be relatively lenient for ordinary consumer product applications.

[0059] In practical applications, based on the aforementioned identification rule set, the recovery factor of deformation recovery capability, the cumulative factor of residual deformation, and the evolution factor of energy dissipation are combined and judged. The purpose is to accurately identify specific performance degradation modes of shape memory alloy parts according to scenario-customized standards. The combined judgment process involves comparing the recovery factor, cumulative factor, and evolution factor extracted from the performance response data with judgment thresholds defined in the identification rule set, and performing a comprehensive analysis according to the combination logic defined in the rule set. For example, in a specific scenario, if the cumulative factor of residual deformation exceeds a certain threshold, and the evolution factor of energy dissipation also shows an abnormal increase, it may be identified as a degradation mode of increased plastic deformation.

[0060] This embodiment achieves customized and accurate identification of specific performance degradation modes of shape memory alloy parts by introducing application scenario information and using a scenario rule base for matching. Specifically, when receiving application scenario information of the shape memory alloy part to be evaluated, the system no longer relies on a single general judgment standard, but intelligently retrieves the most matching set of identification rules from a preset scenario rule base based on the characteristics of the scenario. This set of identification rules includes judgment thresholds and combination logic optimized for specific application scenarios. Therefore, when combining and judging the recovery factor of deformation recovery capability, the accumulation factor of residual deformation, and the evolution factor of energy dissipation, the standards used are highly consistent with actual usage requirements. For example, for a medical device application scenario requiring high precision, the thresholds in the identification rule set will be more stringent, and any minor performance degradation may be identified promptly; while for a furniture component application scenario with relatively relaxed durability requirements, the thresholds may allow for a larger range of performance fluctuations. This scenario-based customized judgment mechanism makes the identification results of degradation modes more targeted and accurate, avoiding misjudgments or omissions that may be caused by general rules.

[0061] In some preferred embodiments, the step of further extracting multiple feature information reflecting changes in the performance state of the shape memory alloy component from the optimized performance response data includes: From the optimized performance response data, extract the deformation recovery rate, residual deformation, and load-displacement data for each test cycle; The output value of the displacement sensor under zero load is periodically acquired as the current zero offset, and the zero offset is used to correct all extracted deformation recovery rate and residual deformation in real time to obtain the corrected deformation recovery rate and corrected residual deformation. Based on the corrected deformation recovery rate, the corresponding deformation recovery rate and deformation recovery trend are calculated respectively. Based on the corrected residual deformation, calculate the cumulative rate of residual deformation and the cumulative trend of residual deformation in consecutive cycles. Based on the load-displacement data for each cycle, the hysteresis loop area is calculated by numerical integration, and the evolution rate and trend of energy dissipation are determined based on the hysteresis loop area change data of continuous cycles.

[0062] As can be understood, deformation recovery rate refers to the degree to which a shape memory alloy part recovers its original shape after deformation through heating or other means. It is usually quantified by measuring the ratio of the recovered deformation to the total deformation. Residual deformation refers to the permanent deformation of the shape memory alloy part that it fails to fully recover after unloading; this is an important indicator for measuring the accumulation of plasticity and fatigue damage in materials. Furthermore, load-displacement data refers to the relationship between the load applied to the shape memory alloy part and the resulting displacement in durability tests. These data are usually presented as curves, reflecting the mechanical response characteristics of the material. Zero-point offset refers to the non-zero output value of the displacement sensor under ideal zero-load conditions due to environmental factors, sensor drift, or installation errors. Accurately acquiring and correcting the zero-point offset is crucial for ensuring the accuracy of deformation measurement.

[0063] Furthermore, the deformation recovery rate refers to the rate at which the deformation recovery rate changes over time or the number of cycles, reflecting the dynamic characteristics of the recovery capability of shape memory alloy parts. The deformation recovery trend refers to the overall direction of change of the deformation recovery rate over continuous cycles or a period of time, such as whether it gradually decreases, remains stable, or exhibits abnormal fluctuations.

[0064] Furthermore, the residual deformation accumulation rate refers to the rate at which the residual deformation increases with the number of cycles, reflecting the speed at which plastic deformation accumulates.

[0065] Furthermore, the cumulative trend of residual deformation refers to the overall change pattern of residual deformation in continuous cycles, such as linear growth, accelerated growth, or decelerated growth.

[0066] Furthermore, the hysteresis loop area refers to the area enclosed by a complete loading-unloading cycle on the load-displacement curve. This area represents the energy dissipated by the shape memory alloy component in one cycle and is a key indicator for measuring the material's damping characteristics and energy dissipation capacity.

[0067] Furthermore, the evolution rate of energy dissipation refers to the rate at which the hysteresis loop area changes with the number of cycles, reflecting the dynamic changes in the energy dissipation mechanism within the shape memory alloy component. The evolution trend refers to the overall pattern of energy dissipation change in continuous cycles, such as whether it gradually decreases, remains stable, or experiences an abnormal increase.

[0068] This embodiment, through refined processing and multi-dimensional feature extraction of the raw performance response data, can comprehensively and accurately capture the performance degradation process of shape memory alloy parts in durability tests. Specifically, firstly, by extracting the deformation recovery rate, residual deformation, and load-displacement data for each test cycle, a foundation is laid for subsequent feature calculations. Secondly, the output value of the displacement sensor under zero load is periodically acquired as the current zero-point offset, and this zero-point offset is used to correct all extracted deformation recovery rates and residual deformation in real time, effectively eliminating the influence of sensor drift and environmental interference on the measurement results, ensuring the accuracy and reliability of the data. Based on this, the deformation recovery rate and trend are calculated using the corrected deformation recovery rate, enabling the quantification of the dynamic changes in the recovery capability of shape memory alloy parts. The cumulative rate and trend of residual deformation are calculated using the corrected residual deformation, allowing for precise tracking of the accumulation process of plastic deformation. Simultaneously, by numerically integrating the load-displacement data for each cycle to calculate the hysteresis loop area, and by determining the evolution rate and trend of energy dissipation based on the hysteresis loop area changes across consecutive cycles, the evolution law of the internal energy dissipation mechanism of shape memory alloy parts is revealed. Through these multi-dimensional characteristic information, a more comprehensive and in-depth understanding of the performance degradation mechanism of shape memory alloy parts can be achieved.

[0069] Through the above technical solution, this application provides a more accurate and comprehensive method for extracting performance status characteristic information of shape memory alloy parts. In particular, the introduction of a real-time zero-point offset correction mechanism significantly improves the accuracy of deformation recovery rate and residual deformation data, effectively avoiding measurement errors caused by sensor drift or environmental factors, thereby making subsequent performance degradation pattern identification and life prediction more reliable. Furthermore, by simultaneously extracting the rate and trend information of deformation recovery, residual deformation, and energy dissipation, the performance degradation characteristics of shape memory alloy parts can be comprehensively reflected from different perspectives, providing rich data support for in-depth analysis of their degradation mechanisms, and thus improving the accuracy of durability experimental data analysis and prediction.

[0070] In some embodiments described above in this application, multiple feature information reflecting changes in the performance state of shape memory alloy parts is extracted from optimized performance response data, and a specific performance degradation mode of the shape memory alloy parts is determined based on the combination of these feature information. To improve the accuracy and precision of degradation mode determination, further description is needed regarding the specific composition of these feature information and the degradation mode identification process.

[0071] In this regard, such as Figure 2As shown, this application further proposes a step of identifying a specific performance degradation mode of the shape memory alloy part by combining and judging the recovery factor of the deformation recovery capability, the accumulation factor of the residual deformation, and the evolution factor of energy dissipation based on the identification rule set. The steps include: Determine whether the cumulative factor of the residual deformation satisfies the first criterion defined in the set of identification rules, which characterizes irreversible structural damage to the material. If the first determination condition is met, the specific performance degradation mode is identified as an increase in plastic deformation; If the first determination condition is not met, then determine whether the recovery factor of the deformation recovery capability and the evolution factor of the energy dissipation jointly satisfy the second determination condition defined in the identification rule set, which characterizes the abnormal energy dissipation mechanism of the material. If the second determination condition is met, then the discrimination logic is executed based on whether the cumulative rate of residual deformation meets the stability condition defined in the identification rule set; otherwise, the alloy performance state is determined to be normal. When the stability condition is met, the current state is determined to be a pseudo signal caused by environmental interference; When the stability condition is not met, the specific performance degradation mode is identified as a change in the energy dissipation mechanism.

[0072] Specifically, the first criterion is the core basis for judging macroscopic structural damage of shape memory alloy parts. This criterion is set based on the material properties, usage requirements and failure criteria of shape memory alloy parts in the corresponding application scenarios. Its threshold is related to the critical cumulative state of irreversible plastic deformation of the material. When the cumulative factor of residual deformation reaches this criterion, it indicates that irreversible structural damage has occurred inside the shape memory alloy part. Macroscopically, it is manifested as a continuous increase in plastic deformation, which is a substantial structural failure characteristic of the performance degradation of shape memory alloy parts.

[0073] The second criterion is a joint criterion for judging abnormal microscopic energy dissipation mechanisms in shape memory alloy parts. Unlike the macroscopic structural damage judgment of the first criterion, this criterion focuses on performance abnormality warning when the material has not suffered irreversible structural damage. It requires that the recovery factor of deformation recovery capability and the evolution factor of energy dissipation simultaneously meet the preset threshold requirements. The joint judgment of the two can accurately capture microscopic performance degradation signals such as changes in material phase transformation characteristics and abnormal internal energy loss patterns, avoiding the random deviation caused by single factor judgment.

[0074] Stability conditions are a crucial criterion for distinguishing between false signals from environmental interference and genuine performance degradation signals. These stability conditions are quantitative standards for judgment; they are not universal thresholds but rather predefined criteria regarding the cumulative rate of residual deformation, matched from a set of identification rules in a scenario rule base based on the application scenario information of the shape memory alloy component being evaluated (furniture product type, component working environment). They are set around the variation and fluctuation range of the cumulative rate of residual deformation within a preset experimental cycle / time window, serving as a supplementary verification of the second judgment condition. Since environmental factors such as mechanical vibration, electromagnetic interference, and temperature fluctuations during the experiment can cause abnormal fluctuations in characteristic factors, easily misjudged as performance degradation, stability verification of the cumulative rate of residual deformation can effectively distinguish between temporary signal anomalies caused by environmental interference and genuine changes in the material's own energy dissipation mechanism.

[0075] Typical stability criteria include (which may be adjusted depending on the application scenario): A1. The fluctuation range of the cumulative rate of residual deformation is less than or equal to the preset threshold, that is, the difference between the maximum and minimum values ​​of the rate within the window does not exceed the customized standard of the identification rule set. A2. The cumulative rate does not show a continuous unidirectional trend (such as continuous increase / decrease), but only exhibits stable random small fluctuations; A3. The average deviation of the cumulative rate is less than or equal to the preset threshold, meaning that the average rate within the window is within a reasonable range from the reference cumulative rate of the shape memory alloy part under normal operating conditions.

[0076] It should be noted that the core quantitative object of the stability condition is the cumulative rate of residual deformation. This is because the cumulative rate of residual deformation is the core characterization of the development of residual deformation in shape memory alloy parts. It directly reflects the cumulative law of plastic deformation of the material itself. Its change is a direct manifestation of the evolution of the internal properties of the material, rather than a volatile indicator of external interference. It is suitable as the core basis for identifying false signals.

[0077] In practical applications, this hierarchical and progressive combination discrimination logic follows the principle of macroscopic to microscopic analysis and determining true degradation before identifying false signals. First, it quickly identifies degradation modes caused by increased plastic deformation due to structural damage using a first judgment condition. For samples that do not meet this condition, a second judgment condition is used to filter out samples suspected of having abnormal energy dissipation mechanisms. Finally, a stability condition is used to identify false signals in suspected samples, and only samples that do not meet the stability condition are judged as having degradation modes with altered energy dissipation mechanisms. This layered and interconnected discrimination logic ensures the accuracy of performance degradation mode identification while effectively eliminating misjudgments caused by environmental interference. The identification results closely match the actual performance degradation state of the shape memory alloy parts, effectively distinguishing between performance decline caused by the degradation of the shape memory alloy parts themselves and fluctuations caused by external environmental interference, avoiding misjudgments, ensuring the accuracy of degradation mode judgment, and adapting to the recognition rule set requirements of different application scenarios, thus improving the scenario adaptability and practicality of the discrimination logic.

[0078] In some of the embodiments described above in this application, the prediction logic under different degradation modes is related to potential environmental disturbances, which may affect the accuracy and reliability of the prediction results.

[0079] In response, this application further proposes a step for predicting the remaining service life of shape memory alloy parts based on the specific performance degradation mode, and determining the confidence range of the remaining service life, including: When the specific performance degradation mode is identified as an increase in plastic deformation, the current residual deformation and the accumulation factor of the residual deformation are obtained. The remaining service life is determined based on the preset failure residual deformation threshold, the current residual deformation, and the accumulation factor of the residual deformation. When the specific performance degradation mode is identified as a change in the energy dissipation mechanism, and the cumulative factor of the residual deformation does not show accelerated growth, the prediction of the remaining service life is paused and an environmental disturbance warning is generated. Based on the fluctuation range of the cumulative rate of residual deformation within a preset historical data window, the confidence interval corresponding to the remaining service life is calculated.

[0080] Specifically, when a specific performance degradation mode of a shape memory alloy component is identified as an increase in plastic deformation, the system acquires the current residual deformation and its accumulation factor. The current residual deformation refers to the amount of irreversible deformation exhibited by the shape memory alloy component at the end of the current test cycle or service phase. The accumulation factor reflects the growth trend and rate of residual deformation over time or cycle count. Based on a preset failure residual deformation threshold, the current residual deformation, and the accumulation factor, the remaining service life of the shape memory alloy component can be quantitatively predicted. The failure residual deformation threshold is the critical value at which a shape memory alloy component is considered to have failed.

[0081] Furthermore, when a specific performance degradation mode is identified as a change in energy dissipation mechanism, but the accumulation factor of residual deformation does not show accelerated growth, this usually means that the internal structure or material properties of the shape memory alloy part have changed, but have not yet led to significant accumulation of macroscopic plastic deformation. In this case, to avoid misjudgments caused by environmental factors (such as temperature fluctuations, changes in external loads, etc.), the system will pause the prediction of the remaining service life and generate an environmental interference warning, suggesting that the external environment or test conditions be checked.

[0082] Furthermore, to improve the reliability of the remaining service life prediction results, this application also calculates the confidence interval corresponding to the remaining service life based on the fluctuation range of the residual deformation accumulation rate within a preset historical data window. Here, the residual deformation accumulation rate refers to the rate at which the residual deformation increases per unit cycle or unit time. The preset historical data window refers to a continuous segment of historical data used for statistical analysis. By analyzing the fluctuation of the residual deformation accumulation rate within this window, the uncertainty of the prediction can be quantified, thereby determining the confidence interval of the remaining service life and providing the user with a prediction range rather than a single value.

[0083] This embodiment addresses the potential limitation of basic solutions in predicting remaining service life by differentiating between different performance degradation modes and employing targeted prediction strategies. Specifically, when an increase in plastic deformation is identified, the system can perform quantitative predictions based on key residual deformation parameters, ensuring the relevance of the predictions. Furthermore, for special cases where energy dissipation mechanisms change but plastic deformation does not accelerate, this application can intelligently identify these as potential environmental disturbances and suspend uncertain predictions, avoiding misjudgments and unnecessary interventions. Moreover, by introducing the fluctuation range of the residual deformation accumulation rate to calculate the confidence interval for the remaining service life, this application further enhances the reliability and practicality of the prediction results, providing decision-makers with more comprehensive information.

[0084] In some embodiments described above, the remaining service life of shape memory alloy parts is determined based on a preset residual deformation threshold, the current residual deformation, and a cumulative factor for the residual deformation. However, in practical applications, the accumulation process of residual deformation in shape memory alloy parts may exhibit different growth patterns, such as uniform growth or accelerated growth. If these different growth patterns are not accurately identified and adapted to, using only a single prediction model may result in insufficient accuracy in predicting the remaining service life, thereby affecting the accurate assessment of the performance status of shape memory alloy parts and the formulation of subsequent maintenance strategies.

[0085] In this regard, this application further proposes the following steps for determining the remaining service life based on a preset residual deformation threshold, the current residual deformation, and a cumulative factor for the residual deformation: Based on the residual deformation accumulation trend contained in the residual deformation accumulation factor, the growth pattern of the current residual deformation is determined; When the growth pattern is determined to be accelerated growth, an exponential growth prediction model is constructed based on the current residual deformation, the cumulative rate of residual deformation, and the acceleration parameter. The preset residual deformation threshold is used as the input to the exponential growth prediction model, and the remaining service life is obtained by reverse calculation. When the growth pattern is determined to be uniform growth, the remaining service life is determined based on the ratio of the difference between the current residual deformation and the failure residual deformation threshold to the current average cumulative rate contained in the cumulative factor of the residual deformation.

[0086] Specifically, the accumulation factor of residual deformation includes not only the current rate of accumulation of residual deformation but also the trend of accumulation. This trend can be identified by fitting and analyzing historical residual deformation data, such as through linear regression, multinomial regression, or exponential regression, to determine its pattern of change over time or cycle count. Based on this trend, it can be determined whether the current growth pattern of residual deformation is uniform or accelerating. When it is determined to be an accelerating growth pattern, it means that the performance degradation of the shape memory alloy part is accelerating. In this case, to more accurately predict the remaining service life, an exponential growth prediction model needs to be constructed. This model uses the current residual deformation as the starting point, combined with the rate of accumulation of residual deformation and the acceleration parameter obtained through historical data analysis, to simulate the nonlinear growth of residual deformation over time or cycle count. Using a preset failure residual deformation threshold as the termination condition of this exponential growth prediction model, the remaining service life required for the shape memory alloy part to reach the failure threshold can be obtained through inverse solving.

[0087] In practical applications, when the degradation pattern is determined to be uniform, it indicates that the performance degradation of shape memory alloy components is relatively stable. In this case, determining the remaining service life can be simplified to dividing the difference between the current residual deformation and the failure residual deformation threshold by the current average accumulation rate included in the accumulation factor of the residual deformation. For example, if the current residual deformation is X, the failure residual deformation threshold is Y, and the average accumulation rate is Z, then the remaining service life can be calculated as (YX) / Z. This method is suitable for cases where the degradation process is relatively linear and can provide intuitive and effective predictions.

[0088] This application's solution effectively addresses the limitations of traditional single prediction models when facing complex degradation behaviors by introducing the judgment of residual deformation growth patterns and adopting corresponding prediction models based on different growth patterns. Specifically, when the residual deformation of shape memory alloy parts exhibits an accelerating growth trend, its performance degradation rate is not constant. If a uniform growth model is still used for prediction, the remaining service life will be overestimated, posing a safety hazard. By constructing an exponential growth prediction model, this nonlinear accelerated degradation characteristic can be captured more accurately, thus providing more conservative and safer prediction results. Conversely, when the residual deformation exhibits a uniform growth trend, using a linear prediction model based on the average cumulative rate ensures prediction accuracy while simplifying the calculation process and improving efficiency. Therefore, this solution can dynamically adjust the prediction strategy according to the actual degradation state of the shape memory alloy parts, ensuring the reliability of the prediction results.

[0089] In some preferred embodiments, a specific example is given below. Suppose a durability test is being conducted on a shape memory alloy hinge for smart furniture. During the test, its residual deformation is continuously monitored. At a certain monitoring point, the current residual deformation is 0.5 mm, and the preset failure residual deformation threshold is 2.0 mm. First, the system analyzes the cumulative trend of the residual deformation based on historical data.

[0090] Scenario 1: If the analysis results show that the residual deformation accumulation trend exhibits an accelerating growth pattern, for example, in the most recent 1000 cycles, the residual deformation accumulation rate increases from 0.001 mm / cycle to 0.003 mm / cycle, with a significant acceleration parameter, then the system will construct an exponential growth prediction model based on the current residual deformation of 0.5 mm, the current accumulation rate of 0.003 mm / cycle, and the calculated acceleration parameter. By substituting the failure residual deformation threshold of 2.0 mm into this model for back-calculation, for example, the remaining service life is calculated to be 5000 cycles. This prediction result is more conservative and accurate than simple linear extrapolation, reflecting the actual situation of accelerated degradation.

[0091] Scenario 2: If the analysis results show that the residual deformation accumulation trend exhibits a uniform growth pattern, for example, in the most recent 1000 cycles, the residual deformation accumulation rate is stable at 0.002 mm / cycle without significant acceleration, the system will adopt a uniform growth prediction model. The remaining service life will be determined by calculating (failure residual deformation threshold - current residual deformation) / current average accumulation rate, i.e., (2.0 mm - 0.5 mm) / 0.002 mm / cycle = 750 cycles. By comparing the above two scenarios, the solution of this application can provide a more accurate prediction of the remaining service life based on the actual degradation mode of the shape memory alloy part, thereby guiding users to make appropriate maintenance or replacement decisions.

[0092] Furthermore, the step of calculating the confidence interval corresponding to the remaining service life based on the fluctuation range of the residual deformation accumulation rate within a preset historical data window includes: A historical data window for statistical analysis is determined, the window containing the cumulative rate of residual deformation corresponding to a preset number of consecutive cycles; The standard deviation of the cumulative rate of all residual deformation within the window is used as a quantitative indicator to characterize its fluctuation range. Using the remaining usage period as the center of the predicted value, the upper and lower limits of the confidence interval are determined based on the quantitative indicators and the preset confidence level.

[0093] It should be noted that the historical data window refers to a period of time or a series of cycles used to collect and analyze the cumulative rate of residual deformation of shape memory alloy parts. This window is set to include the cumulative rate of residual deformation corresponding to a preset number of consecutive cycles. The purpose is to obtain sufficient data samples for effective statistical analysis, thereby reflecting the dynamic changes and uncertainties of shape memory alloy parts during recent performance degradation. The preset number of consecutive cycles can be adjusted according to the actual application scenario, the material properties of the shape memory alloy parts, and the density of experimental data; for example, it can be set to data from the most recent 100 cycles or the most recent 500 cycles.

[0094] Furthermore, the standard deviation of the cumulative rate of all residual deformation within the window is used as a quantitative indicator characterizing its fluctuation range. Standard deviation is a statistic that measures the degree of data dispersion; a larger value indicates greater volatility in the cumulative rate of residual deformation and higher prediction uncertainty. By calculating the standard deviation, the randomness and variability in the performance degradation process of shape memory alloy parts can be quantified, providing key parameters for subsequent confidence interval calculations.

[0095] Based on this, using the remaining service life as the central predicted value, the upper and lower limits of the confidence interval are determined based on the quantitative indicator (i.e., standard deviation) and a preset confidence level. The confidence level refers to the required reliability of the prediction result, such as 90%, 95%, or 99%. By using the remaining service life as the central predicted value, and combining the fluctuation range (standard deviation) of the residual deformation accumulation rate with the selected confidence level, an interval can be constructed that contains the true remaining service life of the shape memory alloy part with a certain probability. For example, at a 95% confidence level, an interval can be determined, indicating that there is a 95% certainty that the true remaining service life of the shape memory alloy part falls within this interval.

[0096] This embodiment introduces the concept of a historical data window and uses the standard deviation of the cumulative rate of residual deformation within the window as a quantitative indicator, enabling a more precise capture of the dynamic uncertainties in the performance degradation process of shape memory alloy parts. Traditional methods may rely solely on a single predicted value, neglecting the inherent volatility of material performance degradation in practical applications. Because the cumulative rate of residual deformation is not constant but fluctuates due to various factors, a single predicted value may not fully reflect its reliability. By statistically analyzing the cumulative rate within the historical data window and calculating its standard deviation, this application quantifies this volatility, thus providing a more practically meaningful confidence interval for predicting the remaining service life. This method ensures that the prediction result includes not only a point estimate but also a range, better reflecting the uncertainty of the prediction and improving its practical value.

[0097] Through the above approach, this application provides a more comprehensive and reliable prediction of the remaining service life of shape memory alloy components. By considering the fluctuation range of the cumulative rate of residual deformation within a historical data window and quantifying it as a standard deviation, the uncertainty of the prediction can be effectively assessed. Therefore, the determined remaining service life is no longer a single value, but an interval with a clearly defined confidence range, which significantly enhances the reliability of the prediction results and its decision support capabilities. This method helps users more accurately understand the actual lifespan risk of shape memory alloy components, avoiding misjudgments that may arise from a single predicted value, thus providing a more solid data foundation for maintenance planning, replacement decisions, and the formulation of performance optimization strategies.

[0098] In some of the embodiments described above in this application, although performance optimization strategies are proposed based on specific performance degradation modes, remaining service life, and confidence range, the lack of a systematic and refined strategy generation mechanism during implementation can lead to optimization strategies that are not specific enough or targeted enough, making it difficult to effectively guide actual maintenance and improvement work. This may directly result in resource waste and even fail to prevent or delay the performance degradation of shape memory alloy parts in a timely manner.

[0099] In response, this application further proposes steps for determining the corresponding performance optimization strategy based on the specific performance degradation mode, remaining usage period, and confidence range, including: Based on the specific performance degradation mode, the target type of the optimization strategy is determined, including material improvement strategies or structural improvement strategies for delaying structural degradation, or strategies for isolating or compensating for environmental disturbances. Based on the comparison between the remaining usage period and the preset lifespan safety threshold, and the scale of the confidence range, the priority of the optimization strategy is determined. Based on the target type and priority, at least one specific performance optimization strategy is matched and generated from a preset optimization strategy knowledge base.

[0100] Specifically, when determining the target type of optimization strategy, it is categorized based on the specific performance degradation mode identified in the shape memory alloy (MMA) component. For example, when the degradation mode is primarily characterized by an increase in plastic deformation, this usually indicates that the internal structure of the MMA component is undergoing irreversible changes. In this case, the target type of optimization strategy would be determined as "material improvement strategy or structural improvement strategy to delay structural degradation." This might involve optimizing the composition of the MMA material, adjusting the heat treatment process, or redesigning the geometry of the MMA component to distribute stress. On the other hand, if the degradation mode is primarily characterized by a change in energy dissipation mechanisms, and the cumulative factor of residual deformation does not show accelerated growth, this may suggest that external environmental factors (such as temperature fluctuations, humidity changes, corrosive media, etc.) have affected the performance of the MMA component. In this case, the target type of optimization strategy would be determined as "strategy to isolate environmental interference or strategy to compensate for environmental interference." This might include improving encapsulation, adding protective coatings, adjusting operating environment parameters, or introducing compensation mechanisms to offset environmental impacts.

[0101] When determining the urgency and intensity of optimization strategies, the comparison between the remaining service life of the shape memory alloy component and the preset life safety threshold, as well as the breadth of the confidence range for the remaining service life, are comprehensively considered. For example, if the remaining service life is significantly lower than the life safety threshold and the confidence range is narrow (indicating highly reliable prediction results), the urgency of the optimization strategy will be set high, and the intensity of implementation will be correspondingly increased, potentially requiring immediate intervention. Conversely, if the remaining service life is significantly higher than the life safety threshold and the confidence range is wide (indicating significant uncertainty in the prediction), the urgency of the optimization strategy may be lower, and the intensity of implementation will be relatively mild, allowing for observation or preventative maintenance measures. The life safety threshold can be understood as the minimum service life requirement that shape memory alloy components must meet in a specific application scenario; once it falls below this threshold, a high risk of failure is considered. The breadth of the confidence range reflects the uncertainty of the remaining service life prediction; the narrower the range, the more reliable the prediction.

[0102] In practical applications, after determining the target type, urgency, and implementation intensity of the optimization strategy, the system matches and generates strategies from a pre-set optimization strategy knowledge base. This knowledge base is a database containing various optimization schemes for different degradation modes, urgency levels, and intensity levels. For example, the knowledge base may store specific strategies such as "replacing with high-strength shape memory alloy materials" or "increasing structural support" for "increased plastic deformation, high urgency, and high strength." Through matching algorithms or methods, the system can retrieve at least one specific performance optimization strategy that best meets the conditions from the knowledge base based on the specific situation of the current shape memory alloy component, thereby providing users with accurate and actionable suggestions.

[0103] This embodiment overcomes the potential blindness and generalization problems of traditional methods in generating optimization strategies by deeply integrating three key pieces of information: the specific performance degradation mode of the shape memory alloy component, its remaining service life, and its confidence range. Specifically, firstly, by identifying the specific performance degradation mode (e.g., structural degradation or environmental interference), the fundamental goal of the optimization strategy can be accurately determined, avoiding the one-sided approach of "treating the symptoms rather than the root cause." Secondly, by comparing the remaining service life with the lifetime safety threshold and combining it with the breadth of the confidence range, the risk level of the current situation and the reliability of the prediction can be quantitatively assessed, thereby reasonably setting the urgency and implementation intensity of the strategy. This allows for efficient allocation of resources, ensuring that the most appropriate action is taken when it is most needed. Finally, by matching and generating from a pre-set optimization strategy knowledge base, it ensures that the proposed strategy is specific, executable, and verified, avoiding the generation of abstract or difficult-to-implement suggestions.

[0104] In some preferred embodiments, it is assumed that a shape memory alloy component is used in the lifting mechanism of smart furniture. Using the method of this application, the specific performance degradation mode of the shape memory alloy component is first identified as "increased plastic deformation," indicating that its structural integrity is being affected. Simultaneously, its remaining service life is predicted to be 3 months, while the preset safe service life threshold is 6 months, and the confidence range for the remaining service life is narrow, indicating that the prediction results are highly reliable.

[0105] Based on this information, the system first determines the target type of the optimization strategy as "a material improvement strategy or structural improvement strategy to delay structural degradation." Since the remaining service life is far below the safety threshold and the prediction is reliable, the system determines the urgency of the optimization strategy to be "high" and the implementation intensity to be "strong." Subsequently, the system matches and generates specific strategies from a pre-set optimization strategy knowledge base. For example, the knowledge base might suggest: B1. Immediately replace the component with one made of a new high-strength shape memory alloy material; B2. Strengthen the existing lifting mechanism, for example, by adding support rods or optimizing the design of stress points; B3. Develop a detailed schedule for regular inspections and replacements to complete component replacements within 3 months; In this way, the generated strategy not only clarifies the direction but also provides specific action plans, ensuring timely and effective intervention before shape memory alloy components fail, thereby guaranteeing the long-term stable operation of smart furniture.

[0106] An optional embodiment also provided in this invention is: a durability test data analysis system for shape memory alloy parts, applicable to the methods described in any of the above aspects, such as... Figure 3 As shown, it includes: Data acquisition module 101: used to acquire various performance response data of shape memory alloy parts during durability tests; Data preprocessing module 102: Uses differential signal processing strategy to optimize various performance response data, and extracts multiple feature information reflecting the performance state changes of shape memory alloy parts from the optimized performance response data; Degradation mode determination module 103: Determines the specific performance degradation mode of the shape memory alloy part based on the combination of multiple feature information; Lifetime prediction module 104: Based on the specific performance degradation mode, predict the remaining service life of the shape memory alloy part and determine the confidence range of the remaining service life; Strategy generation module 105: Determines the corresponding performance optimization strategy based on the specific performance degradation mode, remaining usage period, and confidence range.

[0107] Understandably, the data acquisition module can be seen as the interface between the system and the experimental equipment. Its purpose is to collect various raw performance response data generated by shape memory alloy parts during durability tests in real time or in batches, such as load-displacement curves, temperature changes, and deformation recovery rates. In practical applications, this module can integrate various sensor interfaces, data acquisition cards, or interface with existing experimental data management systems to ensure the integrity and accuracy of the data.

[0108] Furthermore, the data preprocessing module is responsible for refining the acquired raw performance response data. Specifically, this module employs a differential signal processing strategy to optimize the data, aiming to effectively distinguish performance degradation characteristic signals from environmental noise signals. Through amplitude enhancement and attenuation techniques, it improves the signal-to-noise ratio of the characteristic signals, thereby accurately extracting multiple feature information reflecting changes in the performance state of the shape memory alloy component from the optimized data. This feature information includes the deformation recovery factor, the cumulative factor of residual deformation, and the evolution factor of energy dissipation.

[0109] Furthermore, the degradation mode determination module, based on multiple feature information extracted by the data preprocessing module, identifies the specific performance degradation mode of the shape memory alloy component through preset combination logic and judgment thresholds. For example, this module can distinguish different degradation modes such as changes in energy dissipation mechanisms or increases in plastic deformation, providing a basis for subsequent lifetime prediction and strategy formulation.

[0110] Furthermore, after identifying a specific performance degradation pattern, the lifespan prediction module predicts the remaining service life of the shape memory alloy component based on that pattern. Simultaneously, the module also determines the reliability range of the remaining service life based on historical data and statistical analysis, providing users with more valuable prediction results.

[0111] Furthermore, the strategy generation module is the final output of the system. Its purpose is to match and generate specific performance optimization strategies from a pre-set knowledge base based on the determined specific performance degradation mode, the predicted remaining service life, and the confidence range. These strategies may include material improvement suggestions, structural optimization schemes, environmental interference isolation measures, or compensation strategies, aiming to effectively delay the performance degradation of shape memory alloy parts or improve their reliability.

[0112] This embodiment automates and automates the entire analysis process by breaking down the complex durability test data analysis method for shape memory alloy parts into collaborative modules. The data acquisition module, acting as the front end, ensures accurate input of raw data; the data preprocessing module performs deep cleaning and feature extraction on this raw data, laying a high-quality foundation for subsequent analysis. It is precisely because of the optimized processing of performance response data and the extraction of key feature information that the degradation mode determination module can accurately identify specific performance degradation modes of shape memory alloy parts. Based on this, the life prediction module can scientifically predict the remaining service life based on the identified degradation modes, combined with historical data and statistical models, and quantify its reliability. Finally, the strategy generation module integrates these analysis results to provide users with targeted performance optimization strategies. This modular design not only improves the efficiency and accuracy of the analysis but also gives the entire system good scalability and maintainability, enabling it to adapt to the data analysis needs of different experimental conditions and shape memory alloy part types.

[0113] Through the above-described scheme, the system of this application can transform the originally complex and time-consuming manual analysis process into an automated and standardized workflow, significantly improving the efficiency and accuracy of durability test data analysis for shape memory alloy parts. The system ensures the continuity and reliability of the entire data flow and logic execution chain, from data acquisition to strategy generation, through close collaboration between modules. Furthermore, by providing a confidence range for the remaining service life, the system provides decision-makers with more comprehensive information, helping them make more prudent and scientific judgments in engineering applications. This integrated system solution not only reduces reliance on professional analysts but also enables real-time monitoring and early warning of the performance status of shape memory alloy parts, thereby effectively extending their service life. Through the description of the above embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the specific device can be divided into different functional modules to complete all or part of the functions described above.

[0114] In the embodiments provided in this application, it should be understood that the disclosed structures and methods can be implemented in other ways. For example, the structural embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another structure, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between structures or units, and may be electrical, mechanical, or other forms.

[0115] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] Furthermore, in the embodiments of this application, the functional units can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0117] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of 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.

[0118] The specific embodiments described above are preferred embodiments of the method and system for analyzing the durability test data of shape memory alloy parts according to the present invention, and are not intended to limit the specific scope of the present invention. The scope of the present invention includes but is not limited to the specific embodiments described above. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A method for analyzing experimental data on the durability of shape memory alloy parts, characterized in that, include: Multiple performance response data of shape memory alloy parts generated in durability tests are obtained. Differential signal processing strategy is used to optimize the multiple performance response data. Multiple feature information reflecting the performance state changes of shape memory alloy parts is extracted from the optimized performance response data. The feature information includes a recovery factor characterizing deformation recovery capability, a cumulative factor characterizing residual deformation, and an evolution factor characterizing energy dissipation. A specific performance degradation mode of the shape memory alloy part is determined based on a combination of multiple features, the specific performance degradation mode including changes in energy dissipation mechanisms or increases in plastic deformation; Based on the specific performance degradation mode, the remaining service life of the shape memory alloy part is predicted, and the confidence range of the remaining service life is determined. The corresponding performance optimization strategy is determined based on the specific performance degradation mode, remaining usage period, and confidence range.

2. The method for analyzing durability test data of shape memory alloy parts according to claim 1, characterized in that, The step of using a differential signal processing strategy to optimize various performance response data to obtain multiple feature information reflecting changes in the performance state of shape memory alloy parts includes: Time-frequency analysis was performed on the performance response data to distinguish performance degradation characteristic signals from environmental noise signals; The amplitude of the identified performance degradation characteristic signal is enhanced according to the preset gain function; The amplitude of the identified environmental noise signal is attenuated according to a preset suppression function; and, The amplified feature signal and the suppressed noise signal are combined to obtain the optimized performance response data.

3. The method for analyzing durability test data of shape memory alloy parts according to claim 1, characterized in that, The deformation recovery capability recovery factor includes the deformation recovery rate and the deformation recovery trend; the residual deformation accumulation factor includes the residual deformation accumulation rate and the residual deformation accumulation trend; the energy dissipation evolution factor includes the energy dissipation evolution rate and the evolution trend. The step of determining the specific performance degradation mode of the shape memory alloy part based on the combination of multiple feature information includes: Receive application scenario information for the shape memory alloy component to be evaluated, including furniture product type and component working environment; Based on the application scenario information, a set of identification rules matching the application scenario information is retrieved from a preset scenario rule base. The set of identification rules defines the judgment thresholds and combination logic for the deformation recovery capability, the accumulation factor of residual deformation, and the evolution factor of energy dissipation for the application scenario. Based on the identification rule set, the recovery factor of the deformation recovery capability, the accumulation factor of the residual deformation, and the evolution factor of energy dissipation are combined and judged to identify the specific performance degradation mode of the shape memory alloy part. The specific performance degradation mode includes changes in the energy dissipation mechanism or an increase in plastic deformation.

4. The method for analyzing durability test data of shape memory alloy parts according to claim 3, characterized in that, The steps for identifying specific performance degradation modes of the shape memory alloy component by combining and judging the recovery factor of the deformation recovery capability, the accumulation factor of the residual deformation, and the evolution factor of energy dissipation according to the identification rule set include: Determine whether the cumulative factor of the residual deformation satisfies the first criterion defined in the set of identification rules, which characterizes irreversible structural damage to the material. If the first determination condition is met, the specific performance degradation mode is identified as an increase in plastic deformation; If the first determination condition is not met, then determine whether the recovery factor of the deformation recovery capability and the evolution factor of the energy dissipation jointly satisfy the second determination condition defined in the identification rule set, which characterizes the abnormal energy dissipation mechanism of the material. If the second determination condition is met, then the discrimination logic is executed based on whether the cumulative rate of residual deformation meets the stability condition defined in the identification rule set; otherwise, the alloy performance state is determined to be normal. When the stability condition is met, the current state is determined to be a pseudo signal caused by environmental interference; When the stability condition is not met, the specific performance degradation mode is identified as a change in the energy dissipation mechanism.

5. A method for analyzing experimental data on the durability of shape memory alloy parts according to claim 3 or 4, characterized in that, The step of predicting the remaining service life of the shape memory alloy component based on the specific performance degradation mode, and determining the confidence range of the remaining service life, includes: When the specific performance degradation mode is identified as an increase in plastic deformation, the current residual deformation and the accumulation factor of the residual deformation are obtained. The remaining service life is determined based on the preset failure residual deformation threshold, the current residual deformation, and the accumulation factor of the residual deformation. When the specific performance degradation mode is identified as a change in the energy dissipation mechanism, and the cumulative factor of the residual deformation does not show accelerated growth, the prediction of the remaining service life is paused and an environmental disturbance warning is generated. Based on the fluctuation range of the cumulative rate of residual deformation within a preset historical data window, the confidence interval corresponding to the remaining service life is calculated.

6. The method for analyzing durability test data of shape memory alloy parts according to claim 5, characterized in that, The step of determining the remaining service life based on a preset failure residual deformation threshold, the current residual deformation, and a cumulative factor for the residual deformation includes: Based on the residual deformation accumulation trend contained in the residual deformation accumulation factor, the growth pattern of the current residual deformation is determined; When the growth pattern is determined to be accelerated growth, an exponential growth prediction model is constructed based on the current residual deformation, the cumulative rate of residual deformation, and the acceleration parameter. The preset residual deformation threshold is used as the input to the exponential growth prediction model, and the remaining service life is obtained by reverse calculation. When the growth pattern is determined to be uniform growth, the remaining service life is determined based on the ratio of the difference between the current residual deformation and the failure residual deformation threshold to the current average cumulative rate contained in the cumulative factor of the residual deformation.

7. The method for analyzing durability test data of shape memory alloy parts according to claim 5, characterized in that, The step of calculating the confidence interval corresponding to the remaining service life based on the fluctuation range of the cumulative rate of residual deformation within a preset historical data window includes: A historical data window for statistical analysis is determined, the window containing the cumulative rate of residual deformation corresponding to a preset number of consecutive cycles; The standard deviation of the cumulative rate of all residual deformation within the window is used as a quantitative indicator to characterize its fluctuation range. Using the remaining usage period as the center of the predicted value, the upper and lower limits of the confidence interval are determined based on the quantitative indicators and the preset confidence level.

8. The method for analyzing durability test data of shape memory alloy parts according to claim 1, characterized in that, The step of determining the corresponding performance optimization strategy based on the specific performance degradation mode, remaining usage period, and confidence range includes: Based on the specific performance degradation mode, the target type of the optimization strategy is determined, including material improvement strategies or structural improvement strategies for delaying structural degradation, or strategies for isolating or compensating for environmental disturbances. Based on the comparison between the remaining usage period and the preset lifespan safety threshold, and the scale of the confidence range, the priority of the optimization strategy is determined. Based on the target type and priority, at least one specific performance optimization strategy is matched and generated from a preset optimization strategy knowledge base.

9. A method for analyzing experimental data on the durability of shape memory alloy parts according to claim 1, 2, or 3, characterized in that, The step of extracting multiple feature information reflecting changes in the performance state of shape memory alloy parts from the optimized performance response data includes: From the optimized performance response data, extract the deformation recovery rate, residual deformation, and load-displacement data for each test cycle; The output value of the displacement sensor under zero load is periodically acquired as the current zero offset, and the zero offset is used to correct all extracted deformation recovery rate and residual deformation in real time to obtain the corrected deformation recovery rate and corrected residual deformation. Based on the corrected deformation recovery rate, the corresponding deformation recovery rate and deformation recovery trend are calculated respectively. Based on the corrected residual deformation, calculate the cumulative rate of residual deformation and the cumulative trend of residual deformation in consecutive cycles. Based on the load-displacement data for each cycle, the hysteresis loop area is calculated by numerical integration, and the evolution rate and trend of energy dissipation are determined based on the hysteresis loop area change data of continuous cycles.

10. A durability test data analysis system for shape memory alloy parts, applicable to the durability test data analysis method for shape memory alloy parts as described in any one of claims 1 to 9, characterized in that, include: Data acquisition module: used to acquire various performance response data of shape memory alloy parts during durability tests; Data preprocessing module: The differential signal processing strategy is used to optimize the various performance response data, and multiple feature information reflecting the performance state changes of shape memory alloy parts is extracted from the optimized performance response data; Degradation mode determination module: Determines the specific performance degradation mode of the shape memory alloy part based on the combination of multiple feature information; Lifetime prediction module: Based on the specific performance degradation mode, predict the remaining service life of the shape memory alloy part and determine the confidence range of the remaining service life; Strategy generation module: Determines the corresponding performance optimization strategy based on the specific performance degradation mode, remaining usage period, and confidence range.

Images