Performance analysis method and device, electronic equipment and storage medium

Abstract

The invention relates to a performance analysis method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting a preset correlation index of a preset reference electric pile and a target correlation index of a target detection electric pile into a preset index conversion module, and carrying out the index standardization conversion of the target correlation index based on the preset correlation index, obtaining a standard index of the target detection galvanic pile; inputting the standard indexes and preset general model parameters of the preset general analysis model into a preset parameter updating module, and performing parameter updating on the preset general model parameters in the preset general analysis model based on the standard indexes to obtain a specific performance analysis model of the target detection galvanic pile; and inputting the target association index and the first preset environment data into a specific performance analysis model, and performing performance analysis on the basis of aging analysis on the target detection stack to obtain target performance analysis data of the target detection stack. According to the embodiment of the invention, the accuracy and efficiency of galvanic pile performance analysis can be improved.

Description

Technical Field

[0001] The present disclosure relates to fuel cell technology, and more particularly to a performance analysis method, device, electronic device, and storage medium. Background Art

[0002] The fuel cell stack is the main component of the fuel cell, and the performance of the fuel cell stack directly determines the energy conversion efficiency, power density and service life of the fuel cell.

[0003] Existing methods for analyzing battery stack performance mainly revolve around experimental testing and modeling simulation. Polarization curve analysis evaluates the overall output performance through the voltage-current density relationship, electrochemical impedance spectroscopy is used to analyze the interface reaction kinetics and mass transfer resistance distribution, and multi-physics field coupling simulation based on computational fluid dynamics explores the performance attenuation mechanism from the dimensions of component transport, thermal management, and current distribution. However, polarization curves cannot decouple the coupling effects of local electrochemical reactions and system mass transfer losses. The construction of equivalent circuit models for electrochemical impedance spectroscopy is highly dependent on prior assumptions and is difficult to match the dynamic changes of actual working conditions, while simulation models are limited by the accuracy of material parameters and the simplification of boundary conditions. Existing methods mostly focus on single-dimensional or static characteristic analysis, and lack a systematic correlation between the dynamic response of the battery stack, multi-scale coupling mechanisms, and life attenuation paths, resulting in low efficiency and poor accuracy in battery stack performance evaluation. Summary of the Invention

[0004] The present disclosure provides a performance analysis method, device, electronic device and storage medium to at least solve the problems of low efficiency and poor accuracy in battery stack performance evaluation in related technologies.

[0005] According to a first aspect of an embodiment of the present disclosure, a performance analysis method is provided, including: Obtaining a preset correlation index of a preset reference stack and a target correlation index of a target detection stack; Inputting the preset correlation index and the target correlation index into a preset index conversion module, performing index standardization conversion on the target correlation index based on the preset correlation index to obtain a standard index of the target detection stack; Inputting the standard indicator and the preset general model parameters of the preset general analysis model into a preset parameter updating module, and updating the preset general model parameters in the preset general analysis model based on the standard indicator to obtain a dedicated performance analysis model for the target detection stack, wherein the preset general analysis model is obtained based on the preset reference stack; The target-related index and the first preset environmental data are input into the exclusive performance analysis model, and performance analysis is performed on the basis of aging analysis of the target detection stack to obtain target performance analysis data of the target detection stack.

[0006] According to a second aspect of an embodiment of the present disclosure, there is provided a performance analysis device, comprising: A correlation index acquisition module, used to obtain a preset correlation index of a preset reference stack and a target correlation index of a target detection stack; a standard indicator acquisition module, configured to input the preset correlation indicator and the target correlation indicator into a preset indicator conversion module, perform indicator standardization conversion on the target correlation indicator based on the preset correlation indicator, and obtain a standard indicator for the target detection stack; a dedicated performance analysis model acquisition module, configured to input the standard indicator and the preset general model parameters of the preset general analysis model into a preset parameter updating module, and update the preset general model parameters in the preset general analysis model based on the standard indicator to obtain a dedicated performance analysis model for the target detection stack, wherein the preset general analysis model is obtained based on the preset reference stack; The target performance analysis data acquisition module is used to input the target related indicators and the first preset environmental data into the exclusive performance analysis model, perform performance analysis on the basis of aging analysis of the target detection stack, and obtain target performance analysis data of the target detection stack.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a method as described in any one of the first aspects above.

[0008] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any method described in the first aspect of the embodiment of the present disclosure. According to a fifth aspect of the embodiments of the present disclosure, a computer program product containing instructions is provided, which, when executed on a computer, enables the computer to execute any one of the methods described in the first aspect of the embodiments of the present disclosure.

[0009] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects: Through the preset indicator conversion module, the target-related indicators of the target detection stack are converted into standardized indicators based on the preset related indicators of the preset reference stack, which effectively solves the indicator heterogeneity problem between different stack systems and ensures data comparability. Through the preset parameter update module, the preset general model parameters in the preset general analysis model are updated based on the standard indicators, realizing the precise adaptation of the preset general analysis model to the exclusive performance analysis model of the target detection stack, inheriting the modeling experience of the preset reference stack while strengthening the individual analysis capability. Based on the exclusive performance analysis model combined with the target-related indicators and the first preset environmental data, performance analysis is performed on the basis of aging analysis of the target detection stack, significantly improving the accuracy and efficiency of performance analysis under complex degradation conditions.

[0010] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0012] Figure 1 is a flow chart showing a performance analysis method according to an exemplary embodiment; Figure 2 is a schematic diagram showing a process of obtaining a dedicated performance analysis model for a target detection stack according to an exemplary embodiment; Figure 3 is a schematic diagram showing another process of obtaining a dedicated performance analysis model for a target detection stack according to an exemplary embodiment; Figure 4 is a schematic diagram showing another process of obtaining a dedicated performance analysis model for a target detection stack according to an exemplary embodiment; Figure 5 is a schematic diagram of a process for obtaining a preset general analysis model according to an exemplary embodiment; Figure 6 is a schematic diagram showing another process of obtaining a preset general analysis model according to an exemplary embodiment; Figure 7 is a block diagram of a performance analysis device according to an exemplary embodiment; Figure 8 It is a block diagram of an electronic device for performance analysis according to an exemplary embodiment. DETAILED DESCRIPTION

[0013] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0014] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish between similar and different contents, and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.

[0015] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0016] Figure 1 FIG. 1 is a flow chart showing a performance analysis method according to an exemplary embodiment. Figure 1 As shown, the following steps are included: In step S101 , a preset correlation index of a preset reference stack and a target correlation index of a target detection stack are obtained.

[0017] In a specific embodiment, the preset correlation indicators are used to characterize the initial performance of a preset reference stack, and the target correlation indicators are used to characterize the initial performance of a target test stack. Specifically, the preset correlation indicators may include design parameters, electrochemical performance characterization data (used to quantify standardized test results of the core reaction activity and interface characteristics of the preset reference stack), and microstructural characterization data (used to describe at least one of the stack material morphology, pore distribution, and catalyst dispersion). For example, the design parameters may include at least one of the catalyst particle size, membrane thickness, and flow channel width of the preset reference stack. The electrochemical performance characterization data may include at least one of the electrochemical active area of ​​the preset reference stack (reflecting the number and availability of effective catalyst reaction sites in the preset reference stack, used to assess the catalyst's dispersion and ability to maintain active surface area), specific activity (characterizing the intrinsic activity of the catalytic reaction per unit electrochemical active area, reflecting the catalytic efficiency and reaction kinetics of the catalyst material itself), and electrochemical impedance spectroscopy (revealing the kinetic resistance and mass transfer impedance distribution of interface reactions within the preset reference stack, used to analyze the impact of ohmic polarization, charge transfer polarization, and other factors on the overall performance of the preset reference stack). The microstructure characterization data may include at least one of a scanning electron microscope image (a surface morphology image of a preset reference fuel cell stack, used to comprehensively display the overall surface characteristics of the preset reference fuel cell stack) and a transmission electron microscope image (an internal structure image of a preset reference fuel cell stack, used to display the phase distribution, interface structure, etc. inside the preset reference fuel cell stack).

[0018] In a specific embodiment, the specific refinement of the above-mentioned target association indicators can refer to the above-mentioned preset association indicators, which will not be repeated here.

[0019] In step S103, the preset correlation index and the target correlation index are input into a preset index conversion module, and the target correlation index is converted into an index standardization based on the preset correlation index to obtain a standard index of the target detection stack.

[0020] In a specific embodiment, the above-mentioned inputting the preset correlation indicators and the target correlation indicators into the preset indicator conversion module, performing indicator standardization conversion on the target correlation indicators based on the preset correlation indicators, and obtaining the standard indicators of the target detection stack can include: inputting the preset correlation indicators and the target correlation indicators into the preset indicator conversion module, the preset indicator conversion module first constructs a standardized benchmark system based on the design parameters, electrochemical performance characterization data, and microstructure characterization data of the preset reference stack included in the preset correlation indicators; then maps the same type of data in the target correlation indicators to the benchmark system item by item, and calculates the absolute deviation; then, based on the design parameter differences, corrects the performance indicators through the preset compensation model; and finally integrates all the corrected parameter deviations to generate multi-dimensional standard indicators.

[0021] In step S105, the standard indicators and the preset general model parameters of the preset general analysis model are input into the preset parameter updating module, and the preset general model parameters in the preset general analysis model are updated based on the standard indicators to obtain a dedicated performance analysis model for the target detection stack.

[0022] In a specific embodiment, the above-mentioned preset universal analysis model is obtained based on a preset reference fuel cell stack.

[0023] In a specific embodiment, Figure 2 As shown, the above-mentioned input of the standard indicators and the preset general model parameters of the preset general analysis model into the preset parameter update module, and the parameter update of the preset general model parameters in the preset general analysis model based on the standard indicators to obtain the exclusive performance analysis model of the target detection stack includes: In step S201, the standard indicators and the preset general model parameters are input into the preset parameter updating module, and the preset general model parameters in the preset general analysis model are updated based on the standard indicators to obtain an initial performance analysis model of the target detection stack.

[0024] In a specific embodiment, the above-mentioned inputting the standard indicators and the preset general model parameters into the preset parameter update module, and updating the preset general model parameters in the preset general analysis model based on the standard indicators to obtain the initial performance analysis model of the target detection stack may include: inputting the standard indicators and the preset general model parameters into the preset parameter update module, the preset parameter update module first compares the standard indicators with the original parameters of the preset general analysis model to identify the parameter items that need to be adjusted; then directly calculates the parameter adjustment amount based on the preset linear mathematical relationship; at the same time, corrects the result according to the design parameters of the target detection stack; finally, through basic logic verification, outputs the initial performance analysis model of the target detection stack.

[0025] In step S203, the target-related index and the second preset environmental data are input into the initial performance analysis model, and a performance analysis is performed on the target detection stack based on the aging analysis to obtain the first initial analysis data of the target detection stack.

[0026] In a specific embodiment, the first initial analysis data is a multi-dimensional quantitative evaluation result generated by coupling the aging state and performance characteristics of the target detection stack, reflecting the theoretical performance boundary and degradation trend of the target detection stack under a specific operating scenario. Specifically, the first initial analysis data may include at least one data such as an aging stage identifier (characterizing the degradation state of the target detection stack material), an aging factor ratio (reflecting the contribution weight of different factors to the overall performance degradation of the target detection stack), performance prediction parameters, an environmental adaptability index (quantifying the target detection stack's ability to maintain steady-state output under complex operating conditions such as sudden changes in temperature and humidity, and interference from gas impurities), and a degradation correlation feature (characterizing the correlation between the target detection stack's performance degradation and material micro-damage).

[0027] In a specific embodiment, the above-mentioned inputting the target-related indicators and the second preset environmental data into the initial performance analysis model, performing performance analysis on the basis of aging analysis of the target detection stack, and obtaining the first initial analysis data of the target detection stack may include: first inputting the target-related indicators and the second preset environmental data into the initial performance analysis model, and establishing a dynamic correlation mapping between environmental parameters and detection indicators through a multi-dimensional data integration engine; then calling the aging factor analysis algorithm, based on the microstructural degradation characteristics and performance degradation trajectory of the target detection stack, combined with the environmental acceleration model, quantifying the contribution ratio of each aging factor; further through the performance coupling modeling module, performing nonlinear fitting on the aging factor proportion weight and the electrochemical performance parameter, constructing the environment-aging-performance correlation equation, and finally outputting the first initial analysis data.

[0028] In step S205 , first actual operation data of the target detection stack under second preset environmental data within a first preset time period is obtained.

[0029] In step S207 , based on the first initial analysis data and the first actual operation data, performance deviation data corresponding to each of a plurality of preset dimensional performances of the target detection stack is determined.

[0030] In a specific embodiment, the above performance deviation data is used to characterize the model prediction accuracy deviation.

[0031] In a specific embodiment, the above-mentioned determination of the performance deviation data corresponding to multiple preset dimensional performances of the target detection stack based on the first initial analysis data and the first actual operation data may include: first aligning the first initial analysis data and the first actual operation data according to dimensions such as performance, structure and environment, calculating the absolute deviation and deviation rate, and classifying them as "acceptable deviation" or "abnormal deviation" based on a preset deviation level threshold table; further associating and mapping the performance deviation with the proportion of aging factors and the environmental response coefficient in the first initial analysis data, generating a deviation traceability report, and finally outputting structured multi-dimensional performance deviation data.

[0032] In step S209 , when the performance deviation data is greater than a preset threshold, target model parameters in the initial performance analysis model are updated based on the performance deviation data to obtain a dedicated performance analysis model.

[0033] In a specific embodiment, the above-mentioned updating of the target model parameters in the initial performance analysis model based on the performance deviation data when the performance deviation data is greater than a preset threshold to obtain an exclusive performance analysis model may include: when the performance deviation data is greater than the preset threshold, generating a parameter correction amount through a deviation-parameter sensitivity inverse mapping, injecting an individual characteristic compensation factor while retaining the inherent physical mechanism constraints of the initial performance analysis model, ensuring the output deviation convergence, until all performance dimensions meet the accuracy threshold, so as to obtain an exclusive performance analysis model.

[0034] In the above embodiment, the parameters of the preset general analysis model are initially updated by driving the standard indicators to generate an initial performance analysis model that is initially adapted to the target detection stack; then, the first initial analysis data output by the initial performance analysis model is compared item by item with the first actual operation data of the target detection stack within the first preset time period to determine the performance deviation data corresponding to each of the multiple preset dimensional performances, and the target model parameters in the initial performance analysis model are reversely corrected based on the performance deviation data to achieve dynamic calibration between the model prediction results and the actual operating status, gradually eliminating the problem of insufficient adaptability of the preset general analysis model under complex working conditions and individual differences, and finally generating a high-fidelity exclusive performance analysis model to ensure the accuracy of the performance analysis.

[0035] In a specific embodiment, Figure 3 As shown, the above method also includes: In step S301, parameter association data and standard indicators corresponding to multiple preset initial model parameters in the initial performance analysis model are input into a first preset parameter learning module for parameter priority analysis to obtain parameter priority information for the target detection stack.

[0036] In a specific embodiment, the parameter priority information represents the respective impacts of a plurality of preset initial model parameters on the performance analysis capability of the initial performance analysis model, and the plurality of preset initial model parameters include target model parameters.

[0037] In a specific embodiment, the parameter association data refers to data that exists between preset initial model parameters and key indicators that affect the model's performance analysis capabilities, used to reveal the effects and interactions between the parameters, describing how and to what extent the parameters drive or constrain model performance. Specifically, the parameter association data may include at least one type of data, including sensitivity data between parameters and performance indicators (characterizing the change in the predicted value of a specific standard performance indicator or model output result caused by a unit change in each preset initial model parameter within its feasible variation range, describing the impact between a single parameter and a single (or multiple) performance indicator), interaction effect data between parameters (characterizing the combined effect on a specific standard performance indicator when two or more preset initial model parameters change simultaneously within their value combination space, describing the nonlinear and holistic impact of the coupling between multiple parameters on the performance indicator), and dependency data on parameters in the model structure / process (depicting the position, action path, weight distribution, and dependency / constraint relationship of the preset initial model parameters with other parameters or intermediate variables in the internal computing architecture or execution logic process of the initial performance analysis model, characterizing the scope of influence and transmission mechanism of parameter changes, that is, describing the embeddedness of the parameters in the internal logic and topology of the model, the action path, and the propagation effect of their changes).

[0038] In a specific embodiment, the above-mentioned parameter association data and standard indicators corresponding to multiple preset initial model parameters in the initial performance analysis model are input into the first preset parameter learning module for parameter priority analysis and processing, and obtaining parameter priority information for the target detection stack may include: inputting the parameter association data and standard indicators corresponding to the initial model parameters into the first preset parameter learning module, performing multi-dimensional data feature alignment and contribution entropy value calculation, generating a priority ranking map based on the sensitivity of the parameters to the core indicators, and finally outputting the parameter priority information.

[0039] In a specific embodiment, the above-mentioned updating of target model parameters in the initial performance analysis model based on the performance deviation data to obtain the exclusive performance analysis model includes: In step S303, the identifier of the parameter to be updated is determined based on the parameter priority information.

[0040] In step S305 , the target model parameters in the initial performance analysis model are updated based on the performance deviation data and the identifier of the parameter to be updated, so as to obtain a dedicated performance analysis model.

[0041] In a specific embodiment, the above-mentioned parameter update of the target model parameters in the initial performance analysis model based on the performance deviation data and the parameter identifier to be updated to obtain the exclusive performance analysis model may include: locking the high-priority target model parameters based on the parameter identifier to be updated, generating physical constraint compensation using the performance deviation data as input, injecting individualized correction factors while maintaining the model mechanism framework, and realizing the accurate migration of the initial performance analysis model to the exclusive performance analysis model.

[0042] In the above embodiment, the parameter association data and standard indicators corresponding to each of the multiple preset initial model parameters in the initial performance analysis model are input into the first preset parameter learning module for parameter priority analysis and processing, and the influence weight of each preset initial model parameter on the model performance analysis capability is accurately quantified to form the parameter priority information of the target detection battery; then, based on the parameter priority information, the parameter identifiers to be updated are screened, and the high-impact parameters are focused on. The target model parameters in the initial performance analysis model are updated in combination with the performance deviation data. The exclusive performance analysis model finally constructed effectively enhances the adaptability to the target detection battery, and improves the balance between detection accuracy and model iteration efficiency while reducing redundant parameters and optimizing calculation amount.

[0043] In a specific embodiment, Figure 4 As shown, the above method also includes: In step S401 , historical operating data of a preset reference fuel cell stack and parameter update data of a preset general analysis model are obtained.

[0044] In a specific embodiment, the above-mentioned historical operating data is a multi-dimensional, multi-modal data set collected during the entire life cycle of the preset reference fuel cell, which is used to characterize the physical state, performance and aging evolution process of the preset reference fuel cell under different operating stages and environmental conditions.

[0045] In a specific embodiment, the above-mentioned parameter update data is a collection of historical records of the parameter optimization process of the preset general analysis model, which is used to describe the specific operations, contextual conditions and associated results of adjusting the parameters in the preset general analysis model during the training and calibration process of the preset general analysis model.

[0046] In step S403, the standard indicators, historical operating data and parameter update data are input into the second preset parameter learning module for update rule analysis and processing to obtain parameter update rules for the target detection stack.

[0047] In a specific embodiment, the parameter update rules describe the correspondence between performance deviation data and parameter update operations, guiding the adaptive correction of target model parameters. Essentially, they derive a model parameter optimization strategy for the target stack based on historical experience (historical updates of parameters in a pre-set general analysis model and corresponding changes in model output) and current stack characteristics (standard indicators of the target stack).

[0048] Exemplarily, the parameter update rule may include: when the deviation type is the voltage / current dynamic response difference of the second-level working condition switching, specifically, when ,in, for The lowest starting voltage in the first actual operating data, =The predicted minimum starting voltage in the first initial analysis data, the target parameters to be adjusted are the ice crystal blocking mass transfer impedance and the low temperature activation energy correction term. The specific adjustment operation is: the current ice crystal blocking mass transfer impedance*(1+0.18 ) → Adjusted ice crystal blocking mass transfer impedance, current low temperature activation energy correction term -0.004*( ) → Adjusted low-temperature activation energy correction term.

[0049] For example, the parameter update rule may include: when the deviation type is the temperature and humidity sudden change working condition performance fluctuation out of tolerance, specifically, when ,in is the peak current in the first initial analysis data, is the current peak value in the first actual operation data, For the preset rated working current, the target parameters to be adjusted are the proton conduction temperature variation coefficient and the contact resistance compensation value. The specific adjustment operation is: the current proton conduction temperature variation coefficient*(1-0.08* ) → After adjustment, the temperature variation coefficient of proton conduction is adjusted, and the current contact resistance compensation value is +0.0015* →Contact resistance compensation value after adjustment, where: is the actual temperature rise value in the trigger event.

[0050] In a specific embodiment, the above-mentioned input of standard indicators, historical operating data and parameter update data into the second preset parameter learning module for update rule analysis and processing to obtain parameter update rules for the target detection stack may include: by fusing the standard indicators of the target detection stack, the historical operating data and parameter update data of the preset reference stack, realizing structured migration of historical experience in the second preset parameter learning module, extracting a typical operating condition feature library based on historical operating data, combining the parameter adjustment operation causal chain extracted from the parameter update data, and dynamically calibrating the rule strength and applicable scope through standard indicators, and finally generating parameter update rules that can accurately guide the parameter update of the target detection stack.

[0051] In a specific embodiment, the above-mentioned updating of the target model parameters in the initial performance analysis model based on the performance deviation data and the identifier of the parameter to be updated to obtain the exclusive performance analysis model includes: In step S405 , the target model parameters in the initial performance analysis model are updated based on the performance deviation data, the identifier of the parameter to be updated and the parameter update rule to obtain a dedicated performance analysis model.

[0052] In a specific embodiment, the above-mentioned parameter update of the target model parameters in the initial performance analysis model based on the performance deviation data, the parameter identifier to be updated and the parameter update rules to obtain a dedicated performance analysis model may include: using the parameter update rules to map the performance deviation data into operation instructions, and accurately positioning the target model parameters in combination with the parameter identifier to be updated; realizing individualized reconstruction of the model parameters through quantitative compensation under physical constraints, and injecting the target fuel cell stack-specific characteristics while ensuring the integrity of the model mechanism to obtain a dedicated performance analysis model.

[0053] In the above embodiment, the historical operating data and parameter update data of the preset reference battery stack are jointly input into the second preset parameter learning module with the standard indicators to construct the parameter update rules and clarify the dynamic mapping relationship between the performance deviation data and the parameter adjustment amount; combined with the identifier to be updated by the parameter priority screening, the target model parameters in the initial performance analysis model are updated, so that the parameter update process of the exclusive performance analysis model inherits both the historical optimization experience and the current deviation characteristics, effectively avoiding the model oscillation caused by blind parameter adjustment, and enhancing the adaptation accuracy and stability of the update operation to the dynamic characteristics of the target detection battery stack.

[0054] In step S107, the target-related index and the first preset environmental data are input into the exclusive performance analysis model, and performance analysis is performed on the basis of aging analysis of the target detection stack to obtain target performance analysis data of the target detection stack.

[0055] In a specific embodiment, the specific details of the above-mentioned target performance analysis data can be found in the above-mentioned first initial analysis data, which will not be repeated here.

[0056] In a specific embodiment, the target-related indicators and the first preset environmental data are input into the exclusive performance analysis model, and performance analysis is performed on the basis of aging analysis of the target detection stack to obtain the specific refinement of the target performance analysis data of the target detection stack. Please refer to step S203, and the target-related indicators and the second preset environmental data are input into the initial performance analysis model. On the basis of aging analysis of the target detection stack, performance analysis is performed to obtain the first initial analysis data of the target detection stack. No further details will be given here.

[0057] In a specific embodiment, the above method further includes: Based on the target performance analysis data, at least one indicator of the target detection stack is updated to extend the service life of the target detection stack, and the target-related indicators include at least one indicator.

[0058] For example, the dimensional performance data corresponding to the design parameters in the target performance analysis data above show in the aging analysis that "the plate thickness thinning rate is 30% higher than the preset reference stack" and "the bipolar plate surface corrosion layer thickness growth rate is too rapid," resulting in reduced conductivity and insufficient structural stability. Accordingly, the target test stack's plate material thickness can be optimized (increasing the initial bipolar plate thickness from the preset 1.2mm to 1.5mm, while simultaneously applying a corrosion-resistant coating on the surface to reduce the corrosion rate) and flow channel structural parameters (to address the issue of decreased mass transfer efficiency, slightly increasing the flow channel width from 2mm to 2.3mm to increase the uniformity of the reaction gas distribution and reduce the risk of localized excessive corrosion).

[0059] For example, the dimensional performance data corresponding to the electrochemical performance characterization data in the target performance analysis data above show that "the exchange current density of the cathode catalyst layer decreases by 25%" and "the proton conductivity of the membrane electrode decreases by 15%", resulting in an accelerated decay rate of the stack output voltage (exceeding the preset threshold of 0.1mV / h). Accordingly, the catalyst loading and composition of the target stack can be detected (the platinum-based catalyst loading , and doped with ruthenium (Ru / Pt atomic ratio 1:5 to improve the catalyst's anti-poisoning ability and durability) and the proton exchange membrane thickness and sulfonic acid group density (reducing the membrane thickness from 50μm to 40μm (to improve proton conduction efficiency), while increasing the sulfonic acid group density in the membrane to slow down the mechanical damage and ion conduction attenuation caused by water absorption and expansion of the membrane) for optimization.

[0060] For example, the scanning electron microscope image corresponding to the microstructure characterization data in the above-mentioned target performance analysis data shows that "the porosity of the gas diffusion layer decreases by 10%" and "the size of the catalyst layer agglomerates increases by 20%", resulting in an increase in the mass transfer resistance of the reaction gas and a decrease in the active surface area. Accordingly, the porosity of the gas diffusion layer carbon paper and the hydrophobic layer ratio of the target detection stack can be optimized (adjusting the gas diffusion layer porosity from 75% to 80%, and increasing the polytetrafluoroethylene hydrophobic layer content (from 20% to 25%) to improve water management capabilities and avoid pore blockage and water flooding problems) and the catalyst layer preparation process parameters (by reducing the average particle size of the catalyst particles (from 50nm to 30nm) and optimizing the binder ratio (reducing the content from 30% to 25%) to inhibit agglomeration and increase the exposure rate of active sites) can be optimized.

[0061] In the above embodiment, the key performance attenuation points of the target detection stack are dynamically identified through target performance analysis data, and the adjustable indicators in the target-related indicators are updated, thereby delaying the aging process of the core components of the target detection stack, extending the service life, and ultimately improving the overall durability of the target detection stack.

[0062] In a specific embodiment, Figure 5 As shown, the above preset general analysis model is obtained in the following way: In step S501 , second actual operating data of a preset reference fuel cell stack under third preset environmental data within a second preset time period is obtained.

[0063] In a specific embodiment, before testing the preset reference fuel cell stack based on the third preset environmental data, it is necessary to perform an air tightness test and an insulation test on the preset reference fuel cell stack to ensure that the air tightness and insulation of the fuel cell stack meet the requirements.

[0064] In step S503, the second actual operation data and the third preset environment data are input into a preset simulation model, and the simulation model is calibrated to obtain a target simulation model of a preset reference fuel cell stack.

[0065] In a specific embodiment, the above-mentioned inputting the second actual operation data and the third preset environmental data into the preset simulation model, calibrating the simulation model, and obtaining the target simulation model of the preset reference fuel cell stack may include: inputting the second actual operation data and the third preset environmental data into the simulation model, driving the joint inversion of multi-physical field parameters: correcting the electrochemical polarization equation and heat transfer model based on the voltage / temperature field data, using the environmental disturbance characteristics to constrain the membrane water transport and activation energy parameters, and generating a high-fidelity target simulation model that reproduces the dynamic characteristics of the preset reference fuel cell stack under all working conditions.

[0066] In step S505 , a preset aging operation is performed on a preset reference fuel cell stack to obtain an aged reference fuel cell stack.

[0067] In step S507 , an aging-related indicator of the aging reference fuel cell stack and third actual operation data under fourth preset environmental data within a third preset time period are obtained.

[0068] In step S509, the preset correlation index, the aging correlation index, the second actual operation data, the third actual operation data, the third preset environment data and the fourth preset environment data are input into the preset aging analysis model, and the preset aging analysis model is calibrated to obtain the target aging analysis model of the preset reference fuel cell stack.

[0069] In a specific embodiment, the above-mentioned inputting of the preset correlation indicators, aging correlation indicators, second actual operation data, third actual operation data, third preset environmental data and fourth preset environmental data into the preset aging analysis model, calibrating the preset aging analysis model, and obtaining the target aging analysis model of the preset reference fuel cell can include: inputting the baseline performance of the preset reference fuel cell in a brand new state (preset correlation indicators + second actual operation data), material and performance degradation evidence after the preset aging operation (aging correlation indicators + third actual operation data), and environmental data in the new and old states (third preset environmental data, fourth preset environmental data) into the preset aging analysis model, driving the model to decouple the contribution weights of key failure modes such as membrane dehydration cracking, catalyst poisoning, and interface corrosion, and accurately analyzing the proportion of acceleration factors of environmental stresses such as temperature mutation, impurity concentration, and humidity cycle on the degradation rate, and finally establishing a target aging analysis model that can quantify the main controlling factors of aging of the preset reference fuel cell and its environmental sensitivity.

[0070] In step S511 , the target simulation model and the target aging analysis model are coupled to obtain a preset universal analysis model.

[0071] In a specific embodiment, the above-mentioned coupling of the target simulation model and the target aging analysis model to obtain the preset general analysis model may include: dynamically injecting key parameters output by the target aging analysis model into the physical field equations of the target simulation model, and simultaneously establishing an environmental sensitivity coefficient transmission channel; when the simulation model calculates the transient response, triggering the aging model in real time to correct the degradation trajectory, forming a closed-loop interactive system between the operating status and the aging process, and finally generating the preset general analysis model.

[0072] In the above embodiment, the target simulation model is calibrated based on the actual operating data of the preset reference fuel cell in the second preset time period and the third preset environmental data to accurately characterize its dynamic electrothermal response characteristics under complex working conditions; the target aging analysis model uses the key aging indicators of the preset reference fuel cell after the preset aging operation and the operating data under the fourth preset environmental data to deeply reveal the performance degradation law of the fuel cell and the sensitivity to environmental disturbances; finally, the preset general analysis model formed by coupling the two types of models can realize full life cycle performance mapping from a new state to an aged state, and has the ability to simultaneously analyze the operating state and aging process in any environmental scenario and the generalized prediction accuracy across working conditions.

[0073] In a specific embodiment, Figure 6 As shown, the target simulation model and the target aging analysis model are coupled to obtain a preset general analysis model including: In step S601 , the target simulation model and the target aging analysis model are coupled to obtain an initial general analysis model.

[0074] In a specific embodiment, the target simulation model and the target aging analysis model are coupled to obtain the initial general analysis model. For details, see step S511 above, where the target simulation model and the target aging analysis model are coupled to obtain the preset general analysis model, which will not be described in detail here.

[0075] In step S603, the preset correlation index and the fifth preset environmental data are input into the initial general analysis model, and a performance analysis is performed on the basis of the aging analysis of the preset reference stack to obtain second initial analysis data of the preset reference stack.

[0076] In a specific embodiment, the specific details of the second initial analysis data can refer to the first initial analysis data, which will not be repeated here.

[0077] In a specific embodiment, the preset correlation indicators and the fifth preset environmental data are input into the initial general analysis model, and a performance analysis is performed on the basis of an aging analysis of the preset reference fuel cell to obtain the second initial analysis data of the preset reference fuel cell. For the specific details, please refer to the above step S107, and the target correlation indicators and the first preset environmental data are input into the exclusive performance analysis model. Based on the aging analysis of the target detection fuel cell, a performance analysis is performed to obtain the target performance analysis data of the target detection fuel cell, which will not be repeated here.

[0078] In step S605 , fourth actual operating data of a preset reference fuel cell stack under fifth preset environmental data within a fourth preset time period is obtained.

[0079] In step S607 , the initial universal analysis model is calibrated based on the second initial analysis data and the fourth actual operation data to obtain a preset universal analysis model.

[0080] In a specific embodiment, the above-mentioned calibration of the initial universal analysis model based on the second initial analysis data and the fourth actual operation data to obtain the preset universal analysis model may include: decoupling three types of errors, namely transient response, aging accumulation, and environmental sensitivity, based on a deep comparison between the second initial analysis data (model prediction) and the fourth actual operation data (entity response); driving the electrochemical dynamic parameters of the target simulation model and the decay rate equation of the target aging analysis model to collaboratively reconstruct, and through multiple rounds of feedback iteration, making the model output and the entity operation fingerprint strongly converge, and finally generating the preset universal analysis model.

[0081] In the above embodiment, an initial general analysis model is generated based on the coupling of the target simulation model and the target aging analysis model, and the aging-performance joint analysis of the preset reference fuel cell stack is realized by inputting the preset correlation indicators and the fifth preset environmental data, and the second initial analysis data is output; then, the fourth actual operation data under the fifth preset environmental data in the fourth preset time period is combined for precise benchmarking, so as to obtain the preset general analysis model, so that the model further enhances the dynamic response fitting accuracy and life state migration trajectory fidelity of complex environmental conditions on the basis of retaining the aging-performance coupling mechanism, so that the final preset general analysis model has a unified decision-making benchmark with the dual capabilities of aging analysis factor analysis and transient condition mapping.

[0082] Figure 7 FIG. 1 is a block diagram of a performance analysis device according to an exemplary embodiment. Figure 7 , the device comprises: The correlation index acquisition module 710 is used to obtain a preset correlation index of a preset reference stack and a target correlation index of a target detection stack; The standard indicator acquisition module 720 is used to input the preset correlation indicator and the target correlation indicator into the preset indicator conversion module, perform indicator standardization conversion on the target correlation indicator based on the preset correlation indicator, and obtain the standard indicator of the target detection stack; A dedicated performance analysis model acquisition module 730 is configured to input the standard indicators and the preset general model parameters of the preset general analysis model into a preset parameter update module, and update the preset general model parameters in the preset general analysis model based on the standard indicators to obtain a dedicated performance analysis model for the target detection stack, where the preset general analysis model is obtained based on a preset reference stack; The target performance analysis data acquisition module 740 is used to input the target related indicators and the first preset environmental data into the exclusive performance analysis model, perform performance analysis on the basis of aging analysis of the target detection stack, and obtain target performance analysis data of the target detection stack.

[0083] In an optional embodiment, the dedicated performance analysis model acquisition module 730 includes: An initial performance analysis model acquisition unit is used to input the standard indicators and preset general model parameters into the preset parameter update module, and update the preset general model parameters in the preset general analysis model based on the standard indicators to obtain an initial performance analysis model of the target detection stack; A first initial analysis data acquisition unit is configured to input the target-related index and the second preset environmental data into an initial performance analysis model, perform a performance analysis on the target detection stack based on an aging analysis, and obtain first initial analysis data of the target detection stack; A first actual operation data acquisition unit is used to acquire first actual operation data of the target detection stack under second preset environmental data within a first preset time period; A performance deviation data acquisition unit is used to determine, based on the first initial analysis data and the first actual operation data, performance deviation data corresponding to each of multiple preset performance dimensions of the target detection stack; The exclusive performance analysis model acquisition unit is used to update the target model parameters in the initial performance analysis model based on the performance deviation data when the performance deviation data is greater than a preset threshold, so as to obtain the exclusive performance analysis model.

[0084] In an optional embodiment, the above device further includes: A parameter priority information acquisition module is used to input parameter association data and standard indicators corresponding to multiple preset initial model parameters in the initial performance analysis model into a first preset parameter learning module for parameter priority analysis and processing, thereby obtaining parameter priority information for the target detection stack; The above-mentioned exclusive performance analysis model acquisition unit includes: A parameter identifier to be updated obtaining subunit, configured to determine the parameter identifier to be updated based on the parameter priority information; The first model acquisition subunit is used to update the target model parameters in the initial performance analysis model based on the performance deviation data and the identifier of the parameter to be updated, so as to obtain the exclusive performance analysis model.

[0085] In an optional embodiment, the above device further includes: An update data acquisition module is used to obtain historical operating data of a preset reference fuel cell stack and parameter update data of a preset general analysis model; A parameter update rule acquisition module is used to input standard indicators, historical operating data and parameter update data into the second preset parameter learning module for update rule analysis and processing to obtain parameter update rules for the target detection stack; The first model acquisition subunit includes: The second model acquisition subunit is used to update the target model parameters in the initial performance analysis model based on the performance deviation data, the identifier of the parameter to be updated and the parameter update rule to obtain the exclusive performance analysis model.

[0086] In an optional embodiment, the above device further includes: The indicator update module is used to update at least one indicator of the target detection stack based on the target performance analysis data to extend the service life of the target detection stack.

[0087] In an optional embodiment, the above-mentioned preset general analysis model is obtained using the following modules: A second actual operation data acquisition module is used to acquire second actual operation data of a preset reference fuel cell stack under third preset environmental data within a second preset time period; a target simulation model acquisition module, configured to input the second actual operation data and the third preset environment data into a preset simulation model, calibrate the simulation model, and obtain a target simulation model of a preset reference fuel cell stack; An aging reference stack acquisition module is used to perform a preset aging operation on a preset reference stack to obtain an aging reference stack; a third actual operation data acquisition module, configured to acquire an aging-related indicator of an aging reference fuel cell stack and third actual operation data under fourth preset environmental data within a third preset time period; a target aging analysis model acquisition module, configured to input a preset correlation index, an aging correlation index, second actual operation data, third actual operation data, third preset environment data, and fourth preset environment data into a preset aging analysis model, calibrate the preset aging analysis model, and obtain a target aging analysis model for a preset reference stack; The preset universal analysis model acquisition module is used to couple the target simulation model and the target aging analysis model to obtain the preset universal analysis model.

[0088] In an optional embodiment, the preset general analysis model acquisition module includes: An initial general analysis model acquisition subunit is used to couple the target simulation model and the target aging analysis model to obtain an initial general analysis model; a second initial analysis data acquisition subunit, configured to input the preset correlation index and the fifth preset environmental data into the initial general analysis model, perform a performance analysis on the basis of an aging analysis of a preset reference stack, and obtain second initial analysis data of the preset reference stack; a fourth actual operation data acquisition subunit, configured to acquire fourth actual operation data of a preset reference fuel cell stack under fifth preset environmental data within a fourth preset time period; The preset universal analysis model acquisition subunit is used to calibrate the initial universal analysis model based on the second initial analysis data and the fourth actual operation data to obtain the preset universal analysis model.

[0089] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0090] Figure 8 is a block diagram of an electronic device for performance analysis according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a performance analysis method is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0091] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, an electronic device is further provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the performance analysis method in the embodiment of the present disclosure.

[0092] In an exemplary embodiment, a computer-readable storage medium is further provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the performance analysis method in the embodiment of the present disclosure.

[0093] In an exemplary embodiment, a computer program product including instructions is further provided. When the computer program product is run on a computer, the computer is caused to execute the performance analysis method in the embodiment of the present disclosure.

[0094] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, which can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0095] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0096] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A performance analysis method, characterized in that: include: Obtaining a preset correlation index of a preset reference stack and a target correlation index of a target detection stack; Inputting the preset correlation index and the target correlation index into a preset index conversion module, performing index standardization conversion on the target correlation index based on the preset correlation index to obtain a standard index of the target detection stack; Inputting the standard indicator and the preset general model parameters of the preset general analysis model into a preset parameter updating module, and updating the preset general model parameters in the preset general analysis model based on the standard indicator to obtain a dedicated performance analysis model for the target detection stack, wherein the preset general analysis model is obtained based on the preset reference stack; The target-related index and the first preset environmental data are input into the exclusive performance analysis model, and performance analysis is performed on the basis of aging analysis of the target detection stack to obtain target performance analysis data of the target detection stack.

2. The method according to claim 1, characterized in that The step of inputting the standard indicator and the preset general model parameters of the preset general analysis model into a preset parameter updating module, and updating the preset general model parameters in the preset general analysis model based on the standard indicator to obtain a dedicated performance analysis model for the target detection stack includes: Inputting the standard index and the preset general model parameters into the preset parameter updating module, and updating the preset general model parameters in the preset general analysis model based on the standard index to obtain an initial performance analysis model of the target detection stack; Inputting the target-related index and the second preset environmental data into the initial performance analysis model, and performing a performance analysis on the target detection stack based on an aging analysis to obtain first initial analysis data of the target detection stack; Acquire first actual operating data of the target detection stack under the second preset environmental data within a first preset time period; Determining, based on the first initial analysis data and the first actual operation data, performance deviation data corresponding to each of multiple preset performance dimensions of the target detection stack; When the performance deviation data is greater than a preset threshold, target model parameters in the initial performance analysis model are updated based on the performance deviation data to obtain the exclusive performance analysis model.

3. The method according to claim 2, characterized in that The method further comprises: Inputting parameter association data corresponding to each of a plurality of preset initial model parameters in the initial performance analysis model and the standard indicator into a first preset parameter learning module for parameter priority analysis processing to obtain parameter priority information for the target detection stack, wherein the parameter priority information represents the degree of influence of each of the plurality of preset initial model parameters on the performance analysis capability of the initial performance analysis model, wherein the plurality of preset initial model parameters include the target model parameter; The updating of target model parameters in the initial performance analysis model based on the performance deviation data to obtain the exclusive performance analysis model includes: Determining an identifier of a parameter to be updated based on the parameter priority information; Based on the performance deviation data and the identifier of the parameter to be updated, the target model parameters in the initial performance analysis model are updated to obtain the exclusive performance analysis model.

4. The method according to claim 3, characterized in that The method further comprises: Acquiring historical operating data of the preset reference fuel cell stack and parameter update data of the preset universal analysis model; Inputting the standard indicator, the historical operating data, and the parameter update data into a second preset parameter learning module for update rule analysis and processing to obtain a parameter update rule for the target detection stack, wherein the parameter update rule represents a corresponding relationship between the performance deviation data and the parameter update operation; The updating of the target model parameters in the initial performance analysis model based on the performance deviation data and the identifier of the parameter to be updated to obtain the exclusive performance analysis model includes: Based on the performance deviation data, the identifier of the parameter to be updated and the parameter updating rule, the target model parameters in the initial performance analysis model are updated to obtain the exclusive performance analysis model.

5. The method according to claim 1, characterized in that: The method further comprises: Based on the target performance analysis data, at least one indicator of the target detection stack is updated to extend the service life of the target detection stack, and the target-related indicators include the at least one indicator.

6. The method according to claim 1, characterized in that The preset general analysis model is obtained in the following way: Acquiring second actual operating data of the preset reference fuel cell stack under third preset environmental data within a second preset time period; Inputting the second actual operation data and the third preset environment data into a preset simulation model, calibrating the simulation model, and obtaining a target simulation model of the preset reference fuel cell stack; performing a preset aging operation on the preset reference fuel cell stack to obtain an aged reference fuel cell stack; Acquiring an aging-related indicator of the aging reference fuel cell stack and third actual operating data under fourth preset environmental data within a third preset time period; inputting the preset correlation index, the aging correlation index, the second actual operation data, the third actual operation data, the third preset environment data, and the fourth preset environment data into a preset aging analysis model, calibrating the preset aging analysis model, and obtaining a target aging analysis model for the preset reference fuel cell stack; The target simulation model and the target aging analysis model are coupled to obtain the preset universal analysis model.

7. The method according to claim 6, characterized in that The coupling of the target simulation model and the target aging analysis model to obtain the preset universal analysis model includes: coupling the target simulation model and the target aging analysis model to obtain an initial general analysis model; Inputting the preset correlation index and the fifth preset environmental data into the initial general analysis model, and performing a performance analysis on the preset reference fuel cell stack based on an aging analysis to obtain second initial analysis data of the preset reference fuel cell stack; Acquiring fourth actual operating data of the preset reference fuel cell stack under the fifth preset environmental data within a fourth preset time period; The initial universal analysis model is calibrated based on the second initial analysis data and the fourth actual operation data to obtain the preset universal analysis model.

8. A performance analysis device, characterized in that: include: A correlation index acquisition module, used to obtain a preset correlation index of a preset reference stack and a target correlation index of a target detection stack; a standard indicator acquisition module, configured to input the preset correlation indicator and the target correlation indicator into a preset indicator conversion module, perform indicator standardization conversion on the target correlation indicator based on the preset correlation indicator, and obtain a standard indicator for the target detection stack; a dedicated performance analysis model acquisition module, configured to input the standard indicator and the preset general model parameters of the preset general analysis model into a preset parameter updating module, and update the preset general model parameters in the preset general analysis model based on the standard indicator to obtain a dedicated performance analysis model for the target detection stack, wherein the preset general analysis model is obtained based on the preset reference stack; The target performance analysis data acquisition module is used to input the target related indicators and the first preset environmental data into the exclusive performance analysis model, perform performance analysis on the basis of aging analysis of the target detection stack, and obtain target performance analysis data of the target detection stack.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the performance analysis method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the performance analysis method according to any one of claims 1 to 7.

Images