Method for assessing the performance recovery of an electrolysis system after pulsing operation

Abstract

This invention discloses a method for evaluating the performance recovery of an electrolysis system after a pulsing operation. The method includes the following steps: Step 1: Collecting electrolysis system performance data for a baseline period before pulsing, the pulsing period, and the recovery evaluation period after pulsing; Step 2: Preprocessing the collected data; Step 3: Based on the preprocessed data from Step 2, fitting a natural decay trend within the baseline period before pulsing and extrapolating to obtain a non-interventional prediction curve; Step 4: Calculating four evaluation indicators within the recovery evaluation period after pulsing: recovery amount, recovery stability, improvement in decay slope, and recovery sustainability. The evaluation results can be used for selecting / recommending pulsing parameter combinations to achieve performance recovery and lifespan extension under energy consumption constraints.

Description

Technical Field

[0001] This invention belongs to the field of electrochemical device operation optimization and performance evaluation technology, specifically relating to a method for evaluating the performance recovery of an electrolysis system after a Pulsing operation. Background Technology

[0002] During long-term operation, electrolysis systems often exhibit increased cell voltage, higher energy consumption per unit of hydrogen production, greater fluctuations, and accelerated degradation rates due to factors such as membrane electrode assembly aging, catalyst layer contamination / coverage, changes in gas-liquid mass transfer states, localized drying, or bubble coverage. To mitigate these degradations, engineering practices often employ a pulsing strategy. This involves temporarily altering current density, duration, frequency, and operating parameters such as gas / liquid flow rate and pressure to allow the reactor to temporarily "rest," thereby reducing cell voltage or improving stability for a certain period.

[0003] Current technologies for judging the effectiveness of Pulsing are mostly based on:

[0004] Directly observe whether the indicator curves fall back before and after the pulsing;

[0005] Compare the average or lowest indicators before and after the intervention;

[0006] Use experience to set certain "rebound levels" as effective standards.

[0007] However, existing technologies still have the following major drawbacks:

[0008] (1) The evaluation bias caused by the inability to separate the "natural decay trend"

[0009] Electrolysis system performance exhibits a natural degradation trend over time. Existing methods only compare mean / instantaneous values ​​before and after pulsing, without establishing a "prediction baseline without intervention," which can easily lead to misjudging natural degradation as strategy ineffectiveness or misjudging random fluctuations as recovery.

[0010] (2) Unable to generate quantized outputs that can be used for parameter selection / closed-loop optimization

[0011] In engineering, it is necessary to select the optimal combination of pulsing parameters (load reduction magnitude, duration, frequency, and associated flow / pressure, etc.) to achieve maximum recovery and extend lifespan with minimal hydrogen production loss or energy consumption. Existing methods cannot provide comparable quantitative indicators (such as recovery amount, sustainability, and improvement in decay slope), making it difficult to conduct cross-strategy comparisons and parameter optimization.

[0012] (3) Lack of an integrated evaluation system for “recovery magnitude - stability - decline rate”

[0013] Different pulsing strategies may have varying impacts on the magnitude of recovery, volatility suppression, and reduction of the rate of decline. Existing methods lack a unified framework for simultaneously and quantitatively evaluating these three types of effects, leading to operational optimization relying on empirical trial and error. Summary of the Invention

[0014] The purpose of this invention is to address the difficulty in accurately and quantitatively assessing the effectiveness of pulsing strategies in electrolysis systems. It provides a method for evaluating the performance recovery of electrolysis systems after pulsing. This method can evaluate the following outputs under conditions of noise, slow decay, and operating fluctuations: the actual recovery amount brought by pulsing (stripping natural decay), the stability and duration of the recovery, and the improvement of the decay rate slope by pulsing. The evaluation results can be used for screening / recommending pulsing parameter combinations to achieve performance recovery and lifespan extension under energy consumption constraints.

[0015] This invention is achieved through the following technical solution:

[0016] A method for evaluating the performance recovery of an electrolysis system after a pulsing operation includes the following steps:

[0017] Step 1: Collect performance data of the electrolysis system during the baseline period before Pulsing, the Pulsing period, and the recovery evaluation period after Pulsing;

[0018] Step 2: Preprocess the collected data;

[0019] Step 3: Based on the data preprocessed in Step 2, fit the natural decay trend within the baseline period before Pulsing and extrapolate to obtain the intervention-free prediction curve;

[0020] Step 4: During the recovery assessment period after Pulsing, calculate four types of assessment indicators: recovery amount, recovery stability, improvement in decline slope, and recovery sustainability.

[0021] For the recovery amount, the deviation data between the actual value and the predicted value obtained from the no-intervention prediction curve is calculated during the recovery assessment period to quantitatively characterize the performance recovery of the system by Pulsing.

[0022] To assess the recovery stability, the mean and standard deviation of the electrolysis system performance data are calculated during the baseline period and the recovery assessment period, respectively. Then, the fluctuation reduction rate is calculated to represent the recovery stability.

[0023] Regarding the improvement of the degradation slope, the natural degradation slope of the baseline period and the natural degradation slope of the recovery evaluation period are fitted to the data after the preprocessing in step 2; then the degradation slope improvement ratio between the two is calculated to represent the improvement of the system's performance degradation by Pulsing.

[0024] To ensure persistence of recovery, a recovery threshold is set. Performance data during the recovery assessment period after Pulsing that is greater than the recovery threshold The continuous time length is defined as the recovery duration, and the magnitude of this recovery duration is used to measure the persistence of Pulsing recovery.

[0025] In the above technical solution, the performance data of the electrolysis system collected in step 1 includes at least: cell voltage, current, temperature, pressure, hydrogen production flow rate, and start and end timestamps of the Pulsing event.

[0026] In the above technical solution, in step 1, the windows for the baseline period before Pulsing, the window for the Pulsing period, and the window for the recovery evaluation period after Pulsing are divided according to the start and end timestamps of the Pulsing event and the set baseline window length and recovery evaluation window length.

[0027] In the above technical solution, data preprocessing includes: timestamp alignment, outlier removal, filtering / moving average, and other processing methods.

[0028] In the above technical solution, the intervention-free prediction curve is obtained by linear regression trend fitting.

[0029] In the above technical solution, the intervention-free prediction curve can be obtained by exponential smoothing fitting, polynomial fitting, or ARIMA or LSTM prediction models.

[0030] In the above technical solution, based on the obtained deviation data, the following indicators are extracted to quantitatively evaluate the system's performance recovery: maximum recovery amount, average recovery amount, and equivalent total recovery amount.

[0031] Another aspect of the present invention provides an optimal recommendation method for Pulsing parameter combinations: for different Pulsing parameter combinations, repeat steps 1-4 above to form an evaluation index set; then, perform a comprehensive score on each Pulsing parameter combination and output the parameter combination with the highest score as the recommended Pulsing strategy.

[0032] Another aspect of the invention provides a system for implementing the method for evaluating the performance recovery of an electrolysis system after a Pulsing operation and the method for optimal recommendation of Pulsing parameter combinations, the system comprising:

[0033] Data acquisition module: used to collect performance data of the electrolysis system during the baseline period before Pulsing, the Pulsing period, and the recovery evaluation period after Pulsing;

[0034] Preprocessing module: Used to preprocess the collected data;

[0035] Baseline prediction module: used to fit the natural decay trend within the baseline period before Pulsing and extrapolate to obtain an intervention-free prediction curve;

[0036] Assessment Calculation Module: Used to calculate four types of assessment indicators during the recovery assessment period after pulsing: recovery amount, recovery stability, improvement in decline slope, and recovery sustainability.

[0037] Strategy scoring and recommendation module: This module is used to comprehensively score each group of Pulsing parameter combinations and outputs the parameter combination with the highest score as the recommended Pulsing strategy.

[0038] Another aspect of the present invention provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the methods described above.

[0039] Another aspect of the present invention provides a computer program product comprising computer-executable instructions which, when executed, are used to implement the method described above.

[0040] The advantages and beneficial effects of this invention are as follows:

[0041] 1) By stripping away the natural decay trend, we can achieve quantitative analysis of true recovery.

[0042] This invention quantifies the performance recovery of a system by constructing a non-interventional prediction baseline during the pre-pulsing baseline period and calculating the deviation data between the actual values ​​and the predicted values ​​obtained from the non-interventional prediction curve during the recovery assessment period. This eliminates reliance on empirical observation in the assessment, avoids misjudging natural degradation or random fluctuations as pulsing effects, and thus solves the evaluation bias problem of existing technologies.

[0043] 2) Output engineering indicators that can be used for running optimization / closed-loop control.

[0044] The present invention outputs the integral area of ​​the deviation (i.e., the equivalent total recovery). Volatility reduction rate Improvement ratio of the decline slope and recovery duration Quantitative indicators that can be directly used by the control system are used to compare and rank different combinations of Pulsing parameters, solving the problem that existing technologies cannot guide parameter selection.

[0045] 3) Unify the recovery magnitude, stability, and lifetime-related degradation rate into a single framework.

[0046] This invention simultaneously covers recovery amount, recovery stability, degradation improvement and recovery sustainability, forming a scalable multi-index evaluation system that can be used to compare different electrolysis systems, different operating conditions and different pulsing strategies, solving the problem of the lack of a systematic evaluation framework in the existing technology;

[0047] 4) Achieve optimal Pulsing screening under energy consumption cost constraints

[0048] By introducing (Additional energy consumption or hydrogen production loss) is included in the score, enabling the selection of the Pulsing strategy with the greatest recovery effect, longest duration and smallest degradation slope under the condition of meeting hydrogen production / energy consumption constraints, thereby improving overall energy efficiency and extending the life of key components. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart illustrating the implementation of the evaluation method of the present invention.

[0051] Figure 2 This is a schematic diagram illustrating the changes in performance indicators of an electrolysis system during pulsing.

[0052] Figure 3 This diagram illustrates the combination of performance index changes during the pulsing of an electrolysis system and predictions using non-interventional prediction curves. Detailed Implementation

[0053] To enable those skilled in the art to better understand the present invention, the technical solution of the present invention will be further described below with reference to specific embodiments.

[0054] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the invention for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0055] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0056] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0057] In existing technologies, it is difficult to accurately and quantitatively determine the effect of the Pulsing strategy during the operation of an electrolysis system. Therefore, this embodiment provides a method for evaluating the performance recovery of an electrolysis system after Pulsing. This method can evaluate the following outputs under conditions of noise, slow decay, and operating fluctuations: the actual recovery amount brought by Pulsing (stripping natural decay), the stability and duration of the recovery, and the slope improvement of the decay rate by Pulsing. The evaluation results can be used for screening / recommending Pulsing parameter combinations to achieve performance recovery and lifespan extension under energy consumption constraints.

[0058] Specifically, the method provided by this invention for evaluating the performance recovery of an electrolysis system after a pulsing operation is described in the appendix. Figure 1 This includes the following steps:

[0059] Step 1: Collect performance data of the electrolysis system during the baseline period before Pulsing, the Pulsing period, and the recovery evaluation period after Pulsing.

[0060] As a preferred embodiment, the collected performance data of the electrolysis system shall include at least the following performance data: cell voltage U, current I, temperature T, pressure P, and hydrogen production flow rate F (or equivalent hydrogen production signal).

[0061] Furthermore, based on the start and end timestamps of the Pulsing event, as well as the set baseline window length and recovery assessment window length, the windows are divided into the baseline window before Pulsing, the Pulsing window, and the recovery assessment window after Pulsing.

[0062] For example, let the Pulsing start timestamp be... The Pulsing end timestamp is ,but:

[0063] ①The window for the base period before Pulsing is: ;

[0064] ②The window for the Pulsing period is: ;

[0065] ③The window for recovery assessment after pulsing is: ;

[0066] in, The window length for the baseline period. To restore the assessment window length, and It can be set according to engineering experience (e.g., 30~120 minutes) and can be adjusted according to the sampling frequency.

[0067] Step 2: Preprocess the collected data.

[0068] As a preferred embodiment, the data preprocessing includes timestamp alignment, outlier removal, filtering / moving average, and other processing methods. This results in a processed data sequence. .

[0069] Step 3: Based on the data preprocessed in Step 2, fit the natural decay trend within the baseline period before Pulsing and extrapolate to obtain the intervention-free prediction curve. This intervention-free prediction curve is used to represent the baseline that "if Pulsing is not performed, the performance of the electrolysis system will continue to change according to natural decay".

[0070] As a preferred embodiment, the intervention-free prediction curve can be obtained by linear regression trend fitting, and is expressed as: . This indicates that the performance data of the electrolysis system, which continues to change according to natural decay, is not being processed using Pulsing. a and b The coefficients are the fitted values, and t represents time.

[0071] Furthermore, the intervention-free prediction curve can also be obtained using methods such as exponential smoothing fitting, polynomial fitting, or ARIMA, LSTM prediction models, etc.

[0072] Step 4: During the recovery assessment period following pulsing, calculate four types of assessment indicators: recovery amount, recovery stability, improvement in the decline slope, and recovery sustainability. These are detailed below.

[0073] ①Recovery Assessment

[0074] See appendix Figure 2 This is a schematic diagram illustrating the changes in performance indicators of an electrolysis system during pulsing. Figure 2The green box indicates the implementation period of Pulsing, and the red box indicates the performance recovery period after Pulsing.

[0075] See appendix Figure 3 This is a schematic diagram combining the performance index changes of the electrolysis system during pulsing with the prediction curves without intervention. Figure 3 The blue line represents the actual performance value, and the red line represents the predicted value obtained based on the no-intervention prediction curve.

[0076] During the recovery assessment period, calculate the deviation between the actual value and the predicted value obtained from the no-intervention prediction curve: Based on the obtained deviation data, the following indicators can be further extracted to quantitatively evaluate the performance recovery of the system by the Pulsing strategy:

[0077] Maximum recovery amount: ;

[0078] Average recovery amount: ;

[0079] The area of ​​the deviation integral (i.e., the total equivalent recovery): ;

[0080] when or Furthermore, when the threshold is exceeded, it indicates that Pulsing brings quantifiable performance recovery.

[0081] ②Restoration Stability Assessment

[0082] The statistical characteristics of the mean and standard deviation of the electrolysis system performance data were calculated during the baseline period and the recovery assessment period, respectively, and then the fluctuation reduction rate was calculated: ;

[0083] In the formula, The average of the performance data for the baseline period. To restore the mean of the performance data during the evaluation period, The standard deviation of the performance data for the baseline period. The standard deviation of the performance data during the recovery evaluation period.

[0084] Furthermore, t-tests / variance tests can be used to determine the significance of differences.

[0085] ③: Assessment of improvement in degradation slope (improvement in degradation slope is related to the lifespan of the electrolysis system)

[0086] First, the natural decay slope of the baseline period is obtained by fitting the data after preprocessing in step 2. And the natural decline slope of the recovery assessment period obtained by fitting. (Linear fitting or sliding window local fitting can be used).

[0087] Then, calculate the improvement ratio of the decline slope between the two: Improvement ratio through this decline slope , to represent the improvement of system performance degradation caused by Pulsing.

[0088] when This indicates that Pulsing can slow down system performance degradation; when This indicates that the recession has been reversed (a recovery trend has emerged).

[0089] ④: Resumption of ongoing assessment

[0090] Set recovery threshold (e.g., 5 mV or 1% of the predicted value), when the condition is met The continuous time length is defined as the recovery duration. Through this recovery duration This is used to measure the sustainability of recovery from the Pulsing strategy.

[0091] After the above steps, the performance recovery of the electrolysis system after the Pulsing operation can be evaluated (including the amount of recovery, recovery stability, improvement in the rate of decline, and the sustainability of recovery).

[0092] Furthermore, based on the above steps, this invention also provides a method for optimal recommendation of Pulsing parameter combinations:

[0093] Repeat steps 1-4 above for different combinations of pulsing parameters (load reduction magnitude, duration, frequency, associated flow / pressure, etc.) to form an evaluation index set. Preferably, the evaluation index set includes... Data such as...

[0094] Then, a comprehensive score is calculated for each combination of Pulsing parameters. For example, the comprehensive score formula can be expressed as: In the formula, Additional energy consumption or hydrogen production loss caused by Pulsing (which can be obtained by integrating hydrogen production flow rate and electrical power). , , , , , These are the weighting coefficients.

[0095] The parameter combination with the highest output score is used as the recommended Pulsing strategy.

[0096] The present invention also provides a system for implementing the method for evaluating the performance recovery of an electrolysis system after Pulsing operation and the method for optimal recommendation of Pulsing parameter combinations. The system includes:

[0097] Data acquisition module: used to collect performance data of the electrolysis system during the baseline period before Pulsing, the Pulsing period, and the recovery evaluation period after Pulsing;

[0098] Preprocessing module: Used to preprocess the collected data;

[0099] Baseline prediction module: used to fit the natural decay trend within the baseline period before Pulsing and extrapolate to obtain an intervention-free prediction curve;

[0100] Assessment Calculation Module: Used to calculate four types of assessment indicators during the recovery assessment period after pulsing: recovery amount, recovery stability, improvement in decline slope, and recovery sustainability.

[0101] Strategy scoring and recommendation module: This module is used to comprehensively score each group of Pulsing parameter combinations and outputs the parameter combination with the highest score as the recommended Pulsing strategy.

[0102] The present invention also provides a computer-readable storage medium carrying one or more programs that, when executed, implement the method according to embodiments of the present invention.

[0103] According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples may include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), and portable compact disk read-only memory (CD-ROM). ROM, optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0104] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of the present invention. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the methods provided in the embodiments of the present invention.

[0105] According to embodiments of the present invention, program code for executing the computer programs provided in the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0106] The embodiments of the present invention have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of the invention. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of the invention, and all such substitutions and modifications should fall within the scope of the invention.

Claims

1. A method for assessing the performance recovery of an electrolysis system after a pulsing operation, characterized in that, Includes the following steps: Step 1: Collect performance data of the electrolysis system during the baseline period before Pulsing, the Pulsing period, and the recovery evaluation period after Pulsing; Step 2: Preprocess the collected data; Step 3: Based on the data preprocessed in Step 2, fit the natural decay trend within the baseline period before Pulsing and extrapolate to obtain the intervention-free prediction curve; Step 4: During the recovery assessment period after Pulsing, calculate four types of assessment indicators: recovery amount, recovery stability, improvement in decline slope, and recovery sustainability. For the recovery amount, the deviation data between the actual value and the predicted value obtained from the no-intervention prediction curve is calculated during the recovery assessment period to quantitatively characterize the performance recovery of the system by Pulsing. To assess the recovery stability, the mean and standard deviation of the electrolysis system performance data are calculated during the baseline period and the recovery assessment period, respectively. Then, the fluctuation reduction rate is calculated to represent the recovery stability. Regarding the improvement of the degradation slope, the natural degradation slope of the baseline period and the natural degradation slope of the recovery evaluation period are fitted to the data after the preprocessing in step 2; then the degradation slope improvement ratio between the two is calculated to represent the improvement of the system's performance degradation by Pulsing. To ensure persistence of recovery, a recovery threshold is set. Performance data during the recovery assessment period after Pulsing that is greater than the recovery threshold The continuous time length is defined as the recovery duration, and the magnitude of this recovery duration is used to measure the persistence of Pulsing recovery.

2. The method for assessing the performance recovery of an electrolysis system after pulsing operation according to claim 1, characterized in that: In step 1, the performance data of the electrolysis system collected includes at least the cell voltage, current, temperature, pressure, and hydrogen production flow rate of the electrolysis system.

3. The method for assessing the performance recovery of an electrolysis system after pulsing operation according to claim 1, characterized in that: In step 1, the windows for the baseline period before Pulsing, the window for the Pulsing period, and the window for the recovery evaluation period after Pulsing are divided according to the start and end timestamps of the Pulsing event and the set baseline window length and recovery evaluation window length.

4. The method for assessing the performance recovery of an electrolytic system after pulsing operation according to claim 1, characterized in that: Data preprocessing includes: timestamp alignment, outlier removal, and filtering / moving average.

5. The method for assessing the performance recovery of an electrolytic system after pulsing operation according to claim 1, characterized in that: The intervention-free prediction curve was obtained by fitting a linear regression trend.

6. The method for assessing the performance recovery of an electrolytic system after pulsing operation according to claim 1, characterized in that: The intervention-free prediction curve can be obtained using exponential smoothing fitting, polynomial fitting, or ARIMA / LSTM prediction models.

7. The method for assessing the performance recovery of an electrolysis system after pulsing operation according to claim 1, characterized in that: Based on the obtained deviation data, the following indicators are extracted to quantitatively evaluate the system's performance recovery: maximum recovery amount, average recovery amount, and equivalent total recovery amount.

8. A method for Pulsing parameter combination optimal recommendation, characterized in that: For different combinations of Pulsing parameters, the method described in claim 1 is used to obtain an evaluation index set; then, each combination of Pulsing parameters is comprehensively scored, and the parameter combination with the highest score is output as the recommended Pulsing strategy.

9. A recommendation system for implementing the Pulsing parameter combination optimal recommendation method of claim 8, characterized in that, The recommendation system includes: Data acquisition module: used to collect performance data of the electrolysis system during the baseline period before Pulsing, the Pulsing period, and the recovery evaluation period after Pulsing; Preprocessing module: Used to preprocess the collected data; Baseline prediction module: used to fit the natural decay trend within the baseline period before Pulsing and extrapolate to obtain an intervention-free prediction curve; Assessment Calculation Module: Used to calculate recovery amount, recovery stability, improvement in decline slope, and recovery sustainability during the recovery assessment period after Pulsing; Policy scoring and recommendation module: used to give a comprehensive score to each set of Pulsing parameter combination, and output the parameter combination with the highest score as the recommended Pulsing policy.

10. A computer program product, characterised in that, The computer program product comprises computer-executable instructions which, when executed, implement the method of claim 1.

Images