A method of health assessment of an electrochemical gas sensor and related apparatus

Abstract

The application discloses a health evaluation method and related equipment of an electrochemical gas sensor, and the method comprises the following steps: obtaining current-time running data of the electrochemical gas sensor and current-time associated electrochemical impedance spectrum data; inputting the current-time running data, the current-time associated electrochemical impedance spectrum data and last-time multi-hidden state health degrees into a prediction model and predicting next-time multi-hidden state health degrees based on a preset constraint condition; the multi-hidden state health degrees comprise catalyst health degrees, diffusion membrane health degrees and electrolyte health degrees; the constraint condition comprises a monotone non-increasing constraint condition of the health degrees and / or a decay rate constraint condition; and calculating a comprehensive health evaluation result of the next time according to the next-time multi-hidden state health degrees, a preset weight and a score scale transformation function. The application can effectively evaluate the health degrees of the electrochemical gas sensor. The application can be widely applied in the technical field of electrochemical sensors.

Description

Technical Field

[0001] This application relates to the field of electrochemical sensor technology, and in particular to a health assessment method and related equipment for an electrochemical gas sensor. Background Technology

[0002] Electrochemical gas sensors are susceptible to various factors during long-term operation, leading to zero drift, decreased sensitivity, hysteresis, increased noise, and reduced alarm reliability. Because these factors are often coupled, a gradual deviation develops between the sensor output and the actual gas concentration, and this deviation cannot always be eliminated through simple compensation.

[0003] Existing black-box calibration models are typically built upon data from sensors that are not significantly degraded or are in good calibration condition. This involves recording sensor outputs under different temperature, humidity, and standard concentration conditions, and then training the model to obtain the concentration correction relationship. While this method can improve the measurement errors of normal sensors under environmental changes, it is often difficult to promptly determine the reliability of the detection values ​​and the accuracy of the calibration results when the sensor has aged or its components have degraded. In practical applications, degraded sensors are usually calibrated or recalibrated by periodically introducing standard concentration gases. However, this method suffers from long detection cycles, delayed on-site response, and high maintenance costs, making it difficult to assess the sensor's usability in real time. Especially in industrial process control, toxic and hazardous gas detection, and safety monitoring scenarios, if a sensor continues to output seemingly normal but actually significantly deviated detection results in a degraded state, it may lead to missed detections, false alarms, or safety accidents. Therefore, the technical challenge of effectively assessing the health of electrochemical gas sensors needs to be addressed. Summary of the Invention

[0004] The main purpose of this application is to propose a health assessment method and related equipment for electrochemical gas sensors, which aims to effectively assess the health of electrochemical gas sensors.

[0005] To achieve the above objectives, one aspect of this application proposes a health assessment method for an electrochemical gas sensor, the method comprising the following steps: Acquire the current operating data of the electrochemical gas sensor and the associated electrochemical impedance spectroscopy data at the current moment; The current running data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-latent state health of the previous time are input into the prediction model, and the multi-latent state health of the next time is predicted based on preset constraints. The multi-latent state health includes catalyst health, diffusion membrane health, and electrolyte health. The constraints include monotonic non-increasing health constraints and / or decay rate constraints. The comprehensive health assessment result for the next time step is calculated based on the multi-latent health status at the next time step, the preset weights, and the scoring scale transformation function.

[0006] In some embodiments, the initial multi-latent health status is determined by the following method: Acquire the electrochemical impedance spectroscopy data at the initial time, and perform equivalent circuit fitting on the electrochemical impedance spectroscopy data at the initial time; The initial catalyst health, diffusion membrane health, and electrolyte health are determined based on the fitting parameters of the equivalent circuit.

[0007] In some embodiments, the monotonically non-increasing constraint on health status includes: Each health value in the current hidden state health status is less than or equal to the corresponding health value in the previous hidden state health status.

[0008] In some embodiments, the decay rate constraint includes: The rate of decline in catalyst health is greater than the rate of decline in diffusion membrane health. The rate of decay of the diffusion membrane health is greater than the rate of decay of the electrolyte health.

[0009] In some embodiments, the prediction model includes a feature extraction module, a catalyst module, a diffusion membrane module, and an electrolyte module. The step of inputting the current time-based operating data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-latent state health status from the previous time step into the prediction model and predicting the multi-latent state health status at the next time step based on preset constraints includes: The current running data and the associated electrochemical impedance spectroscopy data are input into the feature extraction module to extract the current feature data; The current moment feature data and the previous moment catalyst health status are input into the catalyst module, and the original update value of the catalyst at the next moment is predicted based on the decay rate constraint. The current moment feature data and the previous moment diffusion membrane health status are input into the diffusion membrane module, and the original update value of the diffusion membrane at the next moment is predicted based on the decay rate constraint. The current moment feature data and the previous moment electrolyte health status are input into the electrolyte module, and the original update value of the electrolyte at the next moment is predicted based on the decay rate constraint. The multi-hidden state health at the next time step is determined based on the monotonically non-increasing constraint, the original update value of the catalyst at the next time step, the original update value of the diffusion membrane at the next time step, and the original update value of the electrolyte at the next time step.

[0010] In some embodiments, the method further includes: If the overall health assessment results are within the normal range, and any health status continues to decline, a re-examination or calibration recommendation will be made; If the overall health assessment result is below the normal range and any health level is below the replacement threshold, a maintenance or replacement prompt will be issued.

[0011] To achieve the above objectives, another aspect of this application provides a health assessment device for an electrochemical gas sensor, the device comprising: The data acquisition module is used to acquire the current operating data of the electrochemical gas sensor and the associated electrochemical impedance spectroscopy data at the current moment; The data prediction module is used to input the current running data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-latent health status of the previous time into the prediction model and predict the multi-latent health status of the next time based on preset constraints. The multi-latent health status includes catalyst health status, diffusion membrane health status, and electrolyte health status. The constraints include monotonic non-increasing health status constraints and / or decay rate constraints. The health assessment module is used to calculate the comprehensive health assessment result for the next time step based on the multi-latent health status at the next time step, preset weights, and a scoring scale transformation function.

[0012] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0013] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0014] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0015] To achieve the above objectives, another aspect of this application proposes a health assessment system for an electrochemical gas sensor, the system comprising a sensor, an electrochemical impedance spectroscopy unit, and a processor, wherein... The sensor is used to collect operating data from the electrochemical gas sensor; The electrochemical impedance spectroscopy instrument is used to collect electrochemical impedance spectroscopy data; The processor is used to implement the above-described method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a health assessment method and related equipment for electrochemical gas sensors. This scheme divides the internal degradation state of the electrochemical gas sensor into three latent states: catalyst health, diffusion membrane health, and electrolyte health. Based on the current operating data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-latent state health of the previous time, the multi-latent state health of the next time is predicted through a prediction model and constraints. During the prediction process, monotonically non-increasing constraints that conform to the long-term aging law are applied to each latent state to reduce non-physical health recovery caused by short-term noise or abnormal observations. The degradation rate constraint makes the prediction process more reasonable. Finally, a comprehensive health assessment result is output based on the three latent states, thereby effectively assessing the health of the electrochemical gas sensor and improving the interpretability of the state, the reliability of calibration, and the timeliness of on-site maintenance during the long-term use of the electrochemical gas sensor. Attached Figure Description

[0017] Figure 1 This is a flowchart of a health assessment method for an electrochemical gas sensor provided in an embodiment of this application; Figure 2 This is a flowchart of another health assessment method for an electrochemical gas sensor provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a health assessment device for an electrochemical gas sensor provided in an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0020] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] The health assessment method for electrochemical gas sensors provided in this application relates to the field of computer technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the health assessment method for electrochemical gas sensors, but is not limited to the above forms.

[0023] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0024] See Figure 1 This application provides a health assessment method for an electrochemical gas sensor, the method comprising the following steps: Step 101: Obtain the current operating data of the electrochemical gas sensor and the associated electrochemical impedance spectroscopy data at the current time; Step 102: Input the current running data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-hidden state health of the previous time into the prediction model and predict the multi-hidden state health of the next time based on the preset constraints; the multi-hidden state health includes catalyst health, diffusion membrane health, and electrolyte health; the constraints include monotonic non-increasing health constraints and / or decay rate constraints. Step 103: Calculate the comprehensive health assessment result for the next time step based on the multi-latent health status, preset weights, and scoring scale transformation function.

[0025] Operational data includes, but is not limited to, one or more of the following: sensor raw output, current response, voltage response, temperature, humidity, operating time, sensor factory testing phase, calibration gas response, zero-point response, or historical maintenance records. Electrochemical impedance spectroscopy (EIS) data can be collected according to preset time intervals, cumulative operating time, maintenance cycles, or abnormal triggering conditions. It is not required that EIS data be completely synchronized with every operating sampling point. During the health status prediction process, the EIS data associated with the current moment can be the most recent EIS test result, the EIS test result within the same detection cycle, or the EIS test result closest to the current operating moment.

[0026] The three types of health prediction metrics in this embodiment of the invention can be obtained either by a unified multi-output model or by three separate quantification models. (See reference...) Figure 2 In this case, a combination of shared feature extraction and fractional output is adopted: the front end uses a shared feature extraction process for both operational data and electrochemical impedance spectroscopy data, while the back end generates separate outputs for catalyst health, diffusion membrane health, and electrolyte health. The current operational data and electrochemical impedance spectroscopy data are input into the prediction model. The prediction model predicts the multi-latent state health at the next time step based on the input data and the multi-latent state health at the previous time step. During the prediction process, different process noises, decay rates, and monotonic constraints can be applied to reflect the differences in the degradation processes of the catalyst, diffusion membrane, and electrolyte.

[0027] It should be noted that the above-mentioned health prediction model is not limited to a single mathematical formula, and can be implemented using rule mapping, weighted scoring, threshold segmentation, regression models, filtered observation models, or neural network state heads, etc. The obtained catalyst health, diffusion membrane health, and electrolyte health, after normalization and amplitude limiting, fall into the [0, 1] interval. The closer the value is to 1, the healthier the corresponding component is, and the closer the value is to 0, the more severe the degradation of the corresponding component is.

[0028] The formula for calculating the overall health assessment results is as follows:

[0029] H k For comprehensive health scoring, w cat 、w diff 、w ele The weights are those of the three hidden states: catalyst health, diffusion membrane health, and electrolyte health. 、 、 These are catalyst health, diffusion membrane health, and electrolyte health, respectively. s H This is a rating scale transformation function that converts health values ​​from 0 to 1 into a percentage or grade output. The three components—catalyst health, diffusion membrane health, and electrolyte health—are used to characterize catalyst activity decline, changes in diffusion membrane mass transfer capacity, and changes in electrolyte conductivity or stability, respectively.

[0030] In some embodiments, the initial multi-latent health status is determined by the following method: Step 201: Obtain the electrochemical impedance spectroscopy data at the initial time and perform equivalent circuit fitting on the electrochemical impedance spectroscopy data at the initial time. Step 202: Determine the initial catalyst health, diffusion membrane health, and electrolyte health based on the fitting parameters of the equivalent circuit.

[0031] Equivalent circuit fitting is performed on the periodically acquired EIS impedance spectra to obtain the impedance fitting parameters for the k-th detection cycle. Specifically, the EIS impedance spectrum is obtained by applying a small perturbation AC signal of a preset amplitude to the same sensor. This small perturbation AC signal can be a sinusoidal voltage perturbation or a sinusoidal current perturbation, and the corresponding voltage and current responses of the sensor are sequentially acquired at multiple preset frequency points. For any frequency point in the k-th detection cycle... f m The complex impedance is calculated based on the amplitude ratio and phase difference of the voltage and current responses at that frequency point. Z k (f m ) ,Right now: Z k (f m )=U k (f m ) / I k (f m ) in, U k (f m ) This indicates that the k-th detection period has a frequency of f m Voltage response under the following conditions I k (f m ) This represents the corresponding current response. (Based on complex impedance) Z k (f m ) The real part, imaginary part, magnitude, and phase angle of the impedance can be obtained. The complex impedance data obtained at multiple frequency points are combined to form the EIS impedance spectrum for the k-th detection period.

[0032] Equivalent circuit fitting refers to optimizing the measured EIS impedance spectrum using an equivalent circuit model that includes ohmic resistance, interface charge transfer branches, and diffusion or non-ideal interface branches. By adjusting the parameters to be estimated in the model, the error between the impedance spectrum calculated by the model and the measured EIS impedance spectrum is minimized, thus obtaining the impedance fitting parameters for the k-th detection cycle. Impedance fitting parameters include, but are not limited to, those mentioned above. R s,k 、R ct,k 、N k 、P k 、 Low-frequency diffusion impedance parameters, Warburg diffusion coefficient, impedance magnitude at a fixed frequency, phase at a fixed frequency, and slope in the low-frequency region, etc. Among these, R s,k The ohmic resistance represents the resistance during the k-th detection cycle and is used to characterize the ohmic pathway inside the sensor, the conductivity of the electrolyte, or changes in contact resistance. R ct,k The charge transfer resistance represents the charge transfer resistance during the k-th detection cycle, used to characterize the changes in charge transfer capability and catalytic reaction activity at the electrode interface; N k and P k These represent the fitting parameters related to the diffusion process, membrane mass transfer process, or non-ideal interface process during the k-th detection cycle. These impedance fitting parameters can be used directly as electrochemical health characteristics, or they can be normalized or calculated relative to the initial health point, factory calibration point, stable samples from the same batch, or historical stability windows to form an electrochemical feature vector for health estimation. Z EIS,k .

[0033] Z EIS,k The observable electrochemical characteristics obtained from the EIS impedance spectrum and its fitting parameters during the k-th detection period represent the three hidden state health vectors. x k =[h cat,k ，h diff,k ，h ele,k ] T It indicates the health status of three degraded components inside the sensor: catalyst, diffusion membrane, and electrolyte. Z EIS,k It is not the final healthy state itself, but is used to estimate or update the health vector x of the three hidden states. k The basis for observation.

[0034] Based on preset rules or mapping relationships obtained through training, the catalyst health, diffusion membrane health, and electrolyte health are calculated respectively. Among these, catalyst health is mainly based on... R ct,k The health of the diffusion film is determined by factors such as the increase in low-frequency diffusion impedance, changes in charge transfer-related fitting parameters, decrease in response sensitivity, or attenuation of response current; the health of the diffusion film is mainly determined by the increase in low-frequency diffusion impedance, N k or P k The electrolyte health is determined by changes in frequency, low-frequency phase changes, response hysteresis, prolonged response time, or prolonged recovery time; electrolyte health is mainly based on R... s,k The increase in EIS, changes in the ohmic path, OCV (Open Circuit Voltage) drift, zero-point drift, or decrease in long-term baseline stability are all factors that determine this. OCV can be used to reflect electrode equilibrium state, reference electrode drift, or long-term potential drift; IT (It curve, current-time curve) can be used to reflect current response stability, response decay, or changes in mass transfer processes; calibration gas response data can be used to obtain operational performance characteristics such as sensitivity, response time, recovery time, steady-state response value, and zero-point drift. The above EIS, OCV, IT, and calibration gas response data are aligned using the same sensor number, detection time, detection batch, or cumulative runtime to provide more electrochemical and operational characteristics.

[0035] In some embodiments, the monotonically non-increasing constraint on health status includes: Step 301: Each health value in the current hidden state health value is less than or equal to the corresponding health value in the previous hidden state health value.

[0036] The state vector for health is as follows:

[0037] in, h cat,k 、h diff,k 、h ele,k These represent the health status of the catalyst, diffusion membrane, and electrolyte at time k, respectively, with the superscript T indicating transposition.

[0038] The state vector range and monotonically non-increasing constraints for health status are as follows:

[0039]

[0040] The formula for monotonic projection is as follows:

[0041] i represents the hidden state category, where i∈{cat,diff,ele} corresponds to the catalyst, diffusion membrane, and electrolyte, respectively. h i,k + This represents the health status after updating and projecting at time k. h i,k-1 + This represents the posterior health status at time k-1. h i,k The value ranges from 0 to 1, with a larger value indicating a higher level of health. The superscript + indicates the health status after posterior update or monotonic projection. raw This represents the original update value before monotonic projection. clip The function represents the limiting function, used to restrict the health status within a preset range; min indicates taking the smaller value, used to achieve monotonically non-increasing projection. The monotonically non-increasing constraint means that the long-term aging health status should not experience a non-physical rebound due to short-term noise.

[0042] In some embodiments, the decay rate constraint includes: Step 401: The rate of decline in catalyst health is greater than the rate of decline in diffusion membrane health; Step 402: The rate of decay of the diffusion membrane health is greater than the rate of decay of the electrolyte health.

[0043] The formula for the decay rate constraint is as follows:

[0044] q cat 、q diff 、q ele The terms represent the process noise or permissible variation intensity for catalyst health, diffusion membrane health, and electrolyte health, respectively. The aforementioned degradation rate constraints indicate that, in the examples, catalyst health is allowed to change faster, followed by diffusion membrane health, while electrolyte health changes relatively slowly.

[0045] In some embodiments, the prediction model includes a feature extraction module, a catalyst module, a diffusion membrane module, and an electrolyte module. It inputs current runtime data, associated electrochemical impedance spectroscopy data, and the multi-latent state health status from the previous time step into the prediction model and predicts the multi-latent state health status at the next time step based on preset constraints, including: Step 501: Input the current running data and the associated electrochemical impedance spectroscopy data at the current time into the feature extraction module to extract the feature data at the current time; Step 502: Input the current moment feature data and the previous moment catalyst health status into the catalyst module and predict the next moment original update value of the catalyst based on the decay rate constraint. Step 503: Input the current feature data and the previous diffusion membrane health status into the diffusion membrane module and predict the original update value of the diffusion membrane at the next moment based on the decay rate constraint. Step 504: Input the current feature data and the electrolyte health status of the previous time into the electrolyte module and predict the original updated value of the electrolyte at the next time based on the decay rate constraint. Step 505: Determine the multi-hidden state health at the next time step based on the monotonically non-increasing constraint, the original update value of the catalyst at the next time step, the original update value of the diffusion membrane at the next time step, and the original update value of the electrolyte at the next time step.

[0046] Based on the health status of the three hidden states at the previous time step, the current running data, the current EIS features, and optional auxiliary data, the three hidden states at the current time step are predicted and updated to obtain the original updated values. This recursive prediction update can be implemented by constrained filtering, recursive least squares, state-space models, or other recursive optimization methods.

[0047] The specific prediction update process is as follows: based on the posterior health status at the previous moment... x k-1 + Starting from the data points of runtime, temperature, humidity, sensor output changes, and the EIS characteristics of the most recent or current period, the current health status is predicted. x k - Then, based on the current observation vector y k The difference between the observed and predicted values ​​is used to update the three hidden states, yielding the original updated values ​​before applying monotonic constraints. h i,k raw When EIS is collected periodically while operational data is collected continuously, matching can be performed using the most recent EIS features, EIS features from the same detection period, stage labels, or time decay weights. When a certain auxiliary data is missing, a data quality mask is used to reduce its weight or the corresponding observation is skipped. This preserves the role of EIS as a necessary electrochemical input while avoiding the requirement for EIS to be completely synchronized with each operational sampling point. The output of the predictive updater includes not only the three hidden states themselves but also the observation residuals, update gain, state uncertainty, and changes in each hidden state. These intermediate quantities are used to determine whether the current health status update mainly comes from EIS health evidence, operational output drift, environmental disturbances, or historical degradation trends.

[0048] Apply a monotonically decaying constraint: Apply a monotonically non-increasing constraint to any hidden state, ensuring that the current health state is no higher than the previous health state. After obtaining the original update value, first limit it to the [0,1] interval, then compare it with the previous posterior health state and take the smaller value, thereby avoiding non-physical health recovery caused by short-term noise or abnormal observations.

[0049] In some embodiments, the method further includes: Step 601: If the overall health assessment results are within the normal range, and any health status continues to decline, determine the recommendation for re-examination or calibration; Step 602: If the overall health assessment result is below the normal range and any health level is below the replacement threshold, a maintenance or replacement prompt is issued.

[0050] A comprehensive health score is calculated based on three latent states, and the output includes calibration results, health level, re-inspection recommendations, maintenance reminders, or replacement reminders, combined with the thresholds of the three latent states, their changing trends, or historical health curves. The comprehensive health score can be obtained by weighting the catalyst health, diffusion membrane health, and electrolyte health according to their respective weights, which can be determined based on the sensor type, application scenario, or calibration data. The output results are determined by first calculating the comprehensive health score. H k Then check them separately. h cat,k 、 h diff,k 、h ele,k Whether it falls below a preset threshold, and the health level is determined by combining the rate of decline over multiple consecutive cycles. For example, when H k When the sensor is in a high health range and none of the three hidden states have triggered the threshold, the output is normal or continues monitoring. When a hidden state continues to decline but the overall score remains in the middle range, a re-examination or calibration suggestion is output. When the overall score is low or any key hidden state is below the replacement threshold, a maintenance or replacement prompt is output. The above thresholds and levels can be adjusted according to the sensor type and safety level. The calibration results can be used to adjust the concentration calibration model, sensitivity coefficient, zero-point drift compensation, or confidence level using the health score. The maintenance prompt is an auxiliary output based on the health status and is not equivalent to a mandatory alarm based on a single numerical threshold.

[0051] See Figure 3 This application provides a health assessment device for an electrochemical gas sensor, the device comprising: The data acquisition module is used to acquire the current operating data of the electrochemical gas sensor and the associated electrochemical impedance spectroscopy data at the current moment; The data prediction module is used to input the current running data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-latent health status of the previous time into the prediction model and predict the multi-latent health status of the next time based on preset constraints. The multi-latent health status includes catalyst health status, diffusion membrane health status, and electrolyte health status. The constraints include monotonic non-increasing health status constraints and / or decay rate constraints. The health assessment module is used to calculate the comprehensive health assessment result for the next time step based on the multi-latent health status, preset weights, and scoring scale transformation function.

[0052] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0053] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0054] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0055] Please see Figure 4 , Figure 4 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 401 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 402 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 402 and is called and executed by the processor 401 using the methods described in the embodiments of this application. Input / output interface 403 is used to implement information input and output; The communication interface 404 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 405 transmits information between various components of the device (e.g., processor 401, memory 402, input / output interface 403, and communication interface 404); The processor 401, memory 402, input / output interface 403 and communication interface 404 are connected to each other within the device via bus 405.

[0056] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0057] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0058] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0059] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0060] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0061] This application also provides a health assessment system for an electrochemical gas sensor. The system includes a sensor, an electrochemical impedance spectroscopy unit, and a processor. Sensors are used to collect operational data from electrochemical gas sensors. An electrochemical impedance spectroscopy (EIS) meter is used to collect electrochemical impedance spectroscopy data. A processor is used to implement the methods described above.

[0062] The embodiments of this application include at least the following beneficial effects: This application provides a health assessment method and related equipment for electrochemical gas sensors. This scheme divides the internal degradation state of the electrochemical gas sensor into three latent states: catalyst health, diffusion membrane health, and electrolyte health. Based on the current operating data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-latent state health of the previous time, the multi-latent state health of the next time is predicted through a prediction model and constraints. During the prediction process, monotonically non-increasing constraints that conform to the long-term aging law are applied to each latent state to reduce non-physical health recovery caused by short-term noise or abnormal observations. The degradation rate constraint makes the prediction process more reasonable. Finally, a comprehensive health assessment result is output based on the three latent states, thereby effectively assessing the health of the electrochemical gas sensor and improving the interpretability of the state, the reliability of calibration, and the timeliness of on-site maintenance during the long-term use of the electrochemical gas sensor.

[0063] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0064] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0065] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0066] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0067] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0068] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above 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 system, 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; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0070] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] Furthermore, the functional units in the various embodiments of this application 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.

[0072] 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 computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A health assessment method for an electrochemical gas sensor, characterized in that, The method includes the following steps: Acquire the current operating data of the electrochemical gas sensor and the associated electrochemical impedance spectroscopy data at the current moment; The current running data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-latent state health of the previous time are input into the prediction model, and the multi-latent state health of the next time is predicted based on preset constraints. The multi-latent state health includes catalyst health, diffusion membrane health, and electrolyte health. The constraints include monotonic non-increasing health constraints and / or decay rate constraints. The comprehensive health assessment result for the next time step is calculated based on the multi-latent health status at the next time step, the preset weights, and the scoring scale transformation function.

2. The method according to claim 1, characterized in that, The initial multi-latent health status is determined by the following method: Acquire the electrochemical impedance spectroscopy data at the initial time, and perform equivalent circuit fitting on the electrochemical impedance spectroscopy data at the initial time; The initial catalyst health, diffusion membrane health, and electrolyte health are determined based on the fitting parameters of the equivalent circuit.

3. The method according to claim 1, characterized in that, The monotonically non-increasing constraints on the health status include: Each health value in the current hidden state health status is less than or equal to the corresponding health value in the previous hidden state health status.

4. The method according to claim 1, characterized in that, The decay rate constraint includes: The rate of decline in catalyst health is greater than the rate of decline in diffusion membrane health. The rate of decay of the diffusion membrane health is greater than the rate of decay of the electrolyte health.

5. The method according to claim 1, characterized in that, The prediction model includes a feature extraction module, a catalyst module, a diffusion membrane module, and an electrolyte module. The step of inputting the current operating data, the associated electrochemical impedance spectroscopy data, and the multi-latent state health status from the previous time step into the prediction model and predicting the multi-latent state health status at the next time step based on preset constraints includes: The current running data and the associated electrochemical impedance spectroscopy data are input into the feature extraction module to extract the current feature data; The current moment feature data and the previous moment catalyst health status are input into the catalyst module, and the original update value of the catalyst at the next moment is predicted based on the decay rate constraint. The current moment feature data and the previous moment diffusion membrane health status are input into the diffusion membrane module, and the original update value of the diffusion membrane at the next moment is predicted based on the decay rate constraint. The current moment feature data and the previous moment electrolyte health status are input into the electrolyte module, and the original update value of the electrolyte at the next moment is predicted based on the decay rate constraint. The multi-hidden state health at the next time step is determined based on the monotonically non-increasing constraint, the original update value of the catalyst at the next time step, the original update value of the diffusion membrane at the next time step, and the original update value of the electrolyte at the next time step.

6. The method according to claim 1, characterized in that, The method further includes: If the overall health assessment results are within the normal range, and any health status continues to decline, a re-examination or calibration recommendation will be made; If the overall health assessment result is below the normal range and any health level is below the replacement threshold, a maintenance or replacement prompt will be issued.

7. A health assessment device for an electrochemical gas sensor, characterized in that, The device includes: The data acquisition module is used to acquire the current operating data of the electrochemical gas sensor and the associated electrochemical impedance spectroscopy data at the current moment; The data prediction module is used to input the current running data, the electrochemical impedance spectroscopy data associated with the current time, and the multi-latent health status of the previous time into the prediction model and predict the multi-latent health status of the next time based on preset constraints. The multi-latent health status includes catalyst health status, diffusion membrane health status, and electrolyte health status. The constraints include monotonic non-increasing health status constraints and / or decay rate constraints. The health assessment module is used to calculate the comprehensive health assessment result for the next time step based on the multi-latent health status at the next time step, preset weights, and a scoring scale transformation function.

8. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method as described in any one of claims 1-6.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

10. A health assessment system for an electrochemical gas sensor, characterized in that, The system includes sensors, an electrochemical impedance spectroscopy meter, and a processor, wherein, The sensor is used to collect operating data from the electrochemical gas sensor; The electrochemical impedance spectroscopy instrument is used to collect electrochemical impedance spectroscopy data; The processor is configured to implement the method as described in any one of claims 1-6.

Images