A monitoring system and monitoring method for an alkaline water electrolysis hydrogen production electrolyzer

Abstract

The present invention discloses a monitoring system and a monitoring method for an electrolyzer for producing hydrogen by electrolysis of alkaline water, and relates to the technical field of electrolyzer monitoring, including an intelligent identification module for deploying sampling wires, collecting and analyzing the data of the electrolyzer connected for the first time to identify the electrolyzer model, and configuring system parameters according to the identification results; a grouping monitoring module for grouping the electrolyzer chambers according to the adjusted parameters and monitoring the operating status of each group of electrolyzers; and a data analysis module for analyzing data anomalies based on the monitoring results and executing response measures. The present invention automatically configures system parameters by automatically identifying the electrolyzer models connected to the system, groups the electrolyzer chambers according to different operating states, and performs parallel monitoring and analysis of the abnormalities of each group of data on the grouped electrolyzer chambers and executes response measures. It can respond to changes in the electrolyzer in real time and quickly adjust the operating state of the electrolyzer, thereby improving the pertinence and efficiency of monitoring and the adaptability of the system.

Description

Technical Field

[0001] The invention relates to the technical field of electrolyzer monitoring, and in particular to a monitoring system and a monitoring method of an electrolyzer for producing hydrogen by electrolysis of alkaline water. Background Art

[0002] In the field of hydrogen production by alkaline water electrolysis, the design and implementation of the monitoring system is a key factor in ensuring electrolysis efficiency and equipment safety. With the growing global demand for clean energy, alkaline water electrolysis, as an efficient hydrogen production technology, has attracted widespread attention. This technology produces hydrogen by electrolyzing water and is an important part of renewable energy conversion and storage. However, traditional electrolyzer monitoring systems mostly rely on manual settings and regular inspections. It is impossible to set different system parameters according to different electrolyzer models, and it is difficult to achieve real-time monitoring of complex working conditions of the electrolyzer. It is impossible to respond to changes inside the electrolyzer in real time. There is a lack of effective data processing mechanisms to instantly identify and adjust the operating status of the electrolyzer, resulting in insufficient rapid and accurate responses when faced with reduced electrolysis efficiency or potential safety risks. Summary of the invention

[0003] In view of the problems existing in the monitoring system and monitoring method of the existing alkaline water electrolysis hydrogen production electrolyzer, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that traditional electrolytic cell monitoring systems mostly rely on manual settings and regular inspections, and are unable to set different system parameters according to different electrolytic cell models. It is difficult to achieve real-time monitoring of complex working conditions of the electrolytic cell, and is unable to respond to changes inside the electrolytic cell in real time. There is a lack of effective data processing mechanisms to instantly identify and adjust the operating status of the electrolytic cell, resulting in a response that is not quick or accurate enough when faced with reduced electrolysis efficiency or potential safety risks.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a monitoring system for an alkaline water electrolysis hydrogen production electrolyzer, comprising:

[0006] Intelligent identification module, used to deploy sampling wires, collect and analyze the data of the electrolyzer connected for the first time to identify the electrolyzer model, and configure system parameters based on the identification results;

[0007] A group monitoring module is used to group the electrolytic cell chambers according to the adjusted parameters and monitor the operating status of each group of electrolytic cells;

[0008] Data analysis module, used to analyze data anomalies based on monitoring results and execute response measures;

[0009] The visualization module is used to visualize the real-time data of each electrolytic cell chamber group.

[0010] As a preferred solution of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer described in the present invention, wherein: deploying the sampling wire means connecting one end of the sampling wire to the anode plate and the other end to the cathode plate in each small chamber of the electrolyzer according to the configuration of the electrolyzer, and fixing the wire with an insulating bracket and an insulating clamp, and connecting the output end of the sampling wire to the central database.

[0011] As a preferred solution of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer of the present invention, wherein: collecting and analyzing the electrolyzer data connected for the first time to identify the electrolyzer model and specifications, configuring the system parameters according to the identification results refers to collecting the voltage and current data and operating parameters of electrolyzers of different models from multiple data sources, marking the corresponding electrolyzer model for each data point and standardizing the collected data, and sorting the operating parameters of electrolyzers of different models according to the electrolyzer model to generate an electrolyzer parameter library and store it in a central database;

[0012] The RBF kernel function is used to construct the electrolytic cell classification model, and the candidate value range and initial candidate value of the regularization parameter C and the kernel function parameter γ are set. The RBF kernel function is:

[0013] K(x i , x j )=exp(-γ‖x i -x j ‖ 2 ),

[0014] Where γ is the kernel function parameter, x i and x j are the i-th and j-th data input;

[0015] The standardized electrolytic cell data of different models are used as training sets to train the electrolytic cell classification model, and the optimization objective function of the data electrolytic cell classification model is defined as:

[0016]

[0017] In the formula, a i is the slack variable, w is the normal vector of the decision boundary, b is the bias term of the decision boundary, C is the regularization parameter, n is the number of samples, and y i is the i-th training data label, φ(x i ) is the representation of the feature vector mapped to the high-dimensional space through the RBF kernel function;

[0018] The candidate values ​​of the regularization parameter C and the kernel function parameter γ are combined, each combination is substituted into the electrolytic cell classification model for model training to obtain the optimized objective function output, and the regularization parameter C and the kernel function parameter γ combination of the minimum optimized objective function is selected as the model parameter output to the electrolytic cell classification model;

[0019] Deploy the trained electrolytic cell classification model to the monitoring system, collect the electrolytic cell operation data of the first connection, and input the electrolytic cell operation data into the electrolytic cell classification model after preprocessing to classify the electrolytic cell operation data and generate the electrolytic cell classification result;

[0020] According to the model of the electrolytic cell in the electrolytic cell classification result, the configuration parameters of the corresponding electrolytic cell model are queried from the parameter library in the central database to match the electrolytic cell, and the queried parameters are applied to the monitoring system to adjust the sampling frequency, voltage range and current range.

[0021] As a preferred solution of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer of the present invention, wherein: grouping the electrolyzer cells according to the adjusted parameters means collecting the initial voltage and current data of the electrolyzer cells after the electrolyzer operates according to the adjusted parameters and performing standardization on the collected data;

[0022] Use K-means algorithm to identify natural clusters in the data and divide the electrolyzer cells into N groups;

[0023] Randomly select K data points as initial cluster centers, assign each data point to the nearest cluster center, and calculate the new center point of each cluster:

[0024]

[0025] Where k is the number of clusters, C j is the data point in the i-th cluster, l is the data point, A j It is cluster C j The center point of

[0026] Repeat the steps of assigning and updating until the cluster center no longer changes;

[0027] The grouping results after clustering are updated to the central database, the group number of each cell is obtained from the clustering algorithm, and the group number of each cell and its corresponding electrolytic cell identifier are updated to the central database;

[0028] According to the grouping results, configure independent monitoring channels and data acquisition frequencies for each group, collect data within the past 24 hours of each group, and calculate the average values ​​μ of voltage and current and the standard deviation σ of voltage and current within each time window:

[0029]

[0030] In the formula, v l is a single data point, and m is the total number of data points;

[0031] Set the data stability judgment threshold Q, and compare the calculated standard deviation σ of each group with the judgment threshold Q to judge the data stability.

[0032] If σ≤Q, it means that the data fluctuation of this group is small, the operation is stable, and the frequency of data collection is reduced;

[0033] If σ>Q, it means that the data set fluctuates greatly and the operation is unstable, so the frequency of data collection should be increased.

[0034] As a preferred solution of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer described in the present invention, monitoring the operating status of each group of electrolyzers refers to monitoring the operating data of each electrolyzer chamber group, collecting data of each electrolyzer chamber group according to the calculated data collection frequency of each electrolyzer chamber group, and transmitting the collected data to the data analysis module.

[0035] As a preferred solution of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer of the present invention, wherein: analyzing data abnormalities based on monitoring results and executing response measures refers to receiving the operating data of different electrolyzer chamber groups transmitted, implementing a dynamic control chart for each electrolyzer chamber group according to the standard deviation calculated by the group monitoring module, and setting the control limit of each electrolyzer chamber group as follows:

[0036] UCL=μ+3σ,

[0037] LCL = μ-3σ,

[0038] Where UCL and LCL are the upper control limit and the lower control limit, respectively, μ is the mean value of the electrolytic cell chamber group data, and σ is the standard deviation of the electrolytic cell chamber group data;

[0039] Real-time monitoring of the data points of each electrolytic cell chamber group, regular update of the mean and standard deviation of each electrolytic cell chamber group, and comparison of each data point. If a data point exceeds the control limit three times in a row, the data is automatically marked as abnormal;

[0040] The corresponding electrolytic cell chamber is found according to the group number and electrolytic cell identifier corresponding to the detected abnormal data, and the electrolytic cell chamber is further monitored and analyzed, the data abnormality is recorded, and a notification report is generated and sent to the operator for early warning.

[0041] As a preferred solution of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer described in the present invention, wherein: visually displaying the real-time data of each electrolyzer chamber group means converting the collected electrolyzer chamber group data into analysis charts through professional software for visual centralized display, and collecting the display content in real time during the display process to adjust the data and generate a personalized display mode for storage.

[0042] Another object of the present invention is to provide a method for monitoring an alkaline water electrolysis hydrogen production electrolyzer, comprising:

[0043] Deploy sampling wires on the anode plate and cathode plate of the electrolytic cell chamber, collect and analyze the electrolytic cell data of the initial connection to identify the electrolytic cell model, and configure system parameters based on the identification results;

[0044] The electrolytic cell chambers are grouped according to the adjusted parameters, and the operating status of each group of electrolytic cells is monitored;

[0045] Analyze data anomalies based on monitoring results and implement corresponding measures;

[0046] Visualize the real-time data of each electrolyzer chamber group.

[0047] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer when executing the computer program.

[0048] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer.

[0049] The beneficial effects of the present invention are as follows: the present invention automatically configures system parameters by automatically identifying the model of the electrolytic cell connected to the system, groups the electrolytic cell chambers according to their different operating states, monitors the grouped electrolytic cell chambers in parallel to analyze the abnormal conditions of each group of data and executes response measures, and can respond to changes inside the electrolytic cell in real time and quickly adjust the operating state of the electrolytic cell, thereby improving the pertinence and efficiency of monitoring and the adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0051] Figure 1 Schematic diagram of the structure of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer.

[0052] Figure 2 A schematic flow chart of a monitoring method for an electrolyzer for producing hydrogen by electrolysis of alkaline water. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0056] Example 1

[0057] Reference Figure 1 , which is the first embodiment of the present invention, and which provides a monitoring system for an alkaline water electrolysis hydrogen production electrolyzer, the monitoring system for an alkaline water electrolysis hydrogen production electrolyzer comprising the following modules:

[0058] S1, intelligent identification module, used to deploy sampling wires, collect and analyze the electrolytic cell data of the initial connection to identify the electrolytic cell model, and configure system parameters according to the identification results;

[0059] Specifically, deploying the sampling wire means connecting one end of the sampling wire to the anode plate and the other end to the cathode plate in each chamber of the electrolytic cell according to the configuration of the electrolytic cell, fixing the wire with an insulating bracket and an insulating clamp, and connecting the output end of the sampling wire to the central database.

[0060] By connecting the sampling wires directly to the anode and cathode plates of each chamber, the voltage and current differences can be accurately measured. Acquiring data directly from the source reduces losses and interference during data transmission and ensures the high accuracy of the measurement results. The independent monitoring settings of each chamber enable the operator to grasp the working conditions of each area in real time, identify problem areas in a timely manner, and make targeted adjustments or maintenance. The use of insulating brackets and clamps to fix the wires effectively prevents electrical failures and operational risks.

[0061] Further, collecting and analyzing the data of the electrolytic cells connected for the first time to identify the electrolytic cell model and specifications, and configuring the system parameters according to the identification results means collecting the voltage and current data and operating parameters of electrolytic cells of different models from multiple data sources, marking the corresponding electrolytic cell model for each data point and standardizing the collected data, and arranging the operating parameters of electrolytic cells of different models according to the electrolytic cell models to generate an electrolytic cell parameter library and store it in the central database;

[0062] The RBF kernel function is used to construct the electrolytic cell classification model, and the candidate value range and initial candidate value of the regularization parameter C and the kernel function parameter γ are set. The RBF kernel function is:

[0063] K(x i , x j )=exp(-γ‖x i -x j ‖ 2 ),

[0064] Where γ is the kernel function parameter, x i and x j are the i-th and j-th data input;

[0065] The standardized electrolytic cell data of different models are used as training sets to train the electrolytic cell classification model, and the optimization objective function of the data electrolytic cell classification model is defined as:

[0066]

[0067] In the formula, a i is the slack variable, w is the normal vector of the decision boundary, b is the bias term of the decision boundary, C is the regularization parameter, n is the number of samples, and y i is the i-th training data label, φ(x i ) is the representation of the feature vector mapped to the high-dimensional space through the RBF kernel function;

[0068] The candidate values ​​of the regularization parameter C and the kernel function parameter γ are combined, each combination is substituted into the electrolytic cell classification model for model training to obtain the optimized objective function output, and the regularization parameter C and the kernel function parameter γ combination of the minimum optimized objective function is selected as the model parameter output to the electrolytic cell classification model;

[0069] Deploy the trained electrolytic cell classification model to the monitoring system, collect the electrolytic cell operation data of the first connection, including the voltage and current of the electrolytic cell, and input the electrolytic cell operation data into the electrolytic cell classification model after preprocessing to classify the electrolytic cell operation data and generate the electrolytic cell classification result;

[0070] According to the model of the electrolytic cell in the electrolytic cell classification result, the configuration parameters of the corresponding electrolytic cell model are queried from the parameter library in the central database to match the electrolytic cell, and the queried parameters are applied to the monitoring system to adjust the sampling frequency, voltage range and current range.

[0071] By automatically identifying the electrolytic cell model and specifications, the system can retrieve and apply the most suitable operating parameters from the central database, optimize the monitoring process and improve the electrolysis efficiency, reduce human setting errors, and ensure that the equipment operates under optimal conditions. The SVM using the RBF kernel function not only improves the classification accuracy, but also achieves efficient processing of the electrolytic cell data by optimizing the regularization parameter C and the kernel function parameter γ. The process of selecting the optimal parameter combination ensures that the model achieves the best performance in actual operation through automated grid search. The system can receive new operating data in real time, process and classify it quickly, and immediately adjust the monitoring parameters to keep the monitoring system in the best state at all times, significantly improving the system's adaptability to environmental changes and ensuring the continuity and safety of the electrolysis process.

[0072] S2, a group monitoring module, used to group the electrolytic cell chambers according to the adjusted parameters and monitor the operating status of each group of electrolytic cells;

[0073] Specifically, grouping the electrolytic cell chambers according to the adjusted parameters means collecting initial voltage and current data of the electrolytic cell chambers after the electrolytic cell operates according to the adjusted parameters and performing standardization on the collected data;

[0074] Use K-means algorithm to identify natural clusters in the data and divide the electrolyzer cells into N groups;

[0075] Randomly select K data points as initial cluster centers, assign each data point to the nearest cluster center, and calculate the new center point of each cluster:

[0076]

[0077] Where k is the number of clusters, C j is the data point in the i-th cluster, l is the data point, A j It is cluster C j The center point of

[0078] Repeat the steps of assigning and updating until the cluster center no longer changes;

[0079] The grouping results after clustering are updated to the central database, the group number of each cell is obtained from the clustering algorithm, and the group number of each cell and its corresponding electrolytic cell identifier are updated to the central database;

[0080] According to the grouping results, configure independent monitoring channels and data acquisition frequencies for each group, collect data within the past 24 hours of each group, and calculate the average values ​​μ of voltage and current and the standard deviation σ of voltage and current within each time window:

[0081]

[0082]

[0083] In the formula, v l is a single data point, and m is the total number of data points;

[0084] Set the data stability judgment threshold Q, and compare the calculated standard deviation σ of each group with the judgment threshold Q to judge the data stability.

[0085] If σ≤Q, it means that the data fluctuation of this group is small, the operation is stable, and the frequency of data collection is reduced;

[0086] If σ>Q, it means that the data set fluctuates greatly and the operation is unstable, so the frequency of data collection should be increased.

[0087] Due to the variability of actual application scenarios, the stability judgment threshold is set based on the actual application scenarios and the experience of professionals. By grouping the electrolyzer chambers according to actual working data, the status of each chamber can be monitored more accurately, and the operating parameters can be adjusted in time to prevent excessive monitoring and waste of resources. Based on the data volatility and operating stability of each group, the data acquisition frequency and monitoring strategy are dynamically adjusted, which not only improves the flexibility of monitoring, but also enhances the adaptability of the system. Especially under different operating conditions, by analyzing the average voltage and current and their standard deviation in each time window, the system can judge the stability of each chamber and optimize resource allocation accordingly, such as reducing the monitoring frequency in stable operating chambers and increasing the monitoring frequency in chambers with large fluctuations, thereby effectively utilizing monitoring resources and adjusting the monitoring parameters and sampling frequency in a timely manner to ensure that the electrolyzer operates in the best state, reduce the occurrence of failures, and extend the life of the equipment, thereby improving the efficiency and hydrogen production of the entire electrolysis process.

[0088] Furthermore, monitoring the operating status of each group of electrolytic cells refers to monitoring the operating data of each electrolytic cell chamber group, collecting data of each electrolytic cell chamber group according to the calculated data collection frequency of each electrolytic cell chamber group, and transmitting the collected data to the data analysis module.

[0089] For chamber groups with stable operation, reducing their data collection frequency can significantly reduce the data processing burden and storage requirements. At the same time, more monitoring resources can be allocated to chamber groups with larger fluctuations to ensure that data in critical situations are not missed. By real-time monitoring and analysis of the operating data of each chamber group, the system can promptly detect potential operating problems or efficiency declines, and quickly make adjustments or alarms, thereby ensuring the operating efficiency and safety of the electrolyzer.

[0090] S3, data analysis module, used to analyze data anomalies based on monitoring results and take corresponding measures;

[0091] Specifically, analyzing data anomalies based on monitoring results and executing response measures refers to receiving the operating data of different electrolytic cell chamber groups transmitted, implementing a dynamic control chart for each electrolytic cell chamber group according to the standard deviation calculated by the group monitoring module, and setting the control limit of each electrolytic cell chamber group as:

[0092] UCL=μ+3σ,

[0093] LCL = μ-3σ,

[0094] Where UCL and LCL are the upper control limit and the lower control limit, respectively, μ is the mean value of the electrolytic cell chamber group data, and σ is the standard deviation of the electrolytic cell chamber group data;

[0095] Real-time monitoring of the data points of each electrolytic cell chamber group, regular update of the mean and standard deviation of each electrolytic cell chamber group, and comparison of each data point. If a data point exceeds the control limit three times in a row, the data is automatically marked as abnormal;

[0096] The corresponding electrolytic cell chamber is found according to the group number and electrolytic cell identifier corresponding to the detected abnormal data, and the electrolytic cell chamber is further monitored and analyzed, the data abnormality is recorded, and a notification report is generated and sent to the operator for early warning.

[0097] By continuously monitoring the data of each electrolyzer chamber group and comparing it with the dynamically updated control limits, the system can quickly identify any possible operational abnormalities or equipment failures. This real-time monitoring and immediate response mechanism significantly reduces the risk of production interruptions and safety accidents caused by operational errors or equipment failures. The system can quickly identify and analyze abnormal data to guide operators to adjust electrolysis parameters or take maintenance measures, thereby optimizing the overall operating efficiency of the electrolyzer. By reducing invalid or inefficient electrolysis operations, energy consumption can be saved and hydrogen yield can be increased. By setting strict data stability judgment thresholds and automated monitoring processes, the sensitivity and responsiveness of the electrolyzer monitoring system are improved, potential risks can be discovered in a timely manner and preventive measures can be taken to effectively avoid accidents and ensure the safety of the production process.

[0098] S4, a visualization display module, used to visualize the real-time data of each electrolytic cell chamber group;

[0099] Specifically, visually displaying the real-time data of each electrolytic cell chamber group means converting the collected electrolytic cell chamber group data into analysis charts through professional software for visual centralized display, and collecting display content in real time during the display process to adjust the data and generate a personalized display mode for storage.

[0100] Professional software refers to Microsoft Power BI, which provides rich data integration, data modeling, reporting and dashboard functions. By converting complex data into an easy-to-understand visual format, operators can more quickly identify key information in the data, such as trends, periodicity and anomalies, which is essential for improving operational efficiency and reducing errors. The visual display of real-time data ensures the immediate response capability of the monitoring system, allowing operators to quickly identify and take measures at the early stage of the problem, thereby optimizing the production process and reducing potential downtime. It provides personalized display modes to meet the visual preferences and analysis needs of different operators, which not only improves the user experience, but also enhances the user satisfaction and ease of operation of the monitoring system. Through centralized display and analysis of charts, operators can obtain data-driven support and make more scientific and accurate decisions.

[0101] Example 2

[0102] Reference Figure 2 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a monitoring method for an alkaline water electrolysis hydrogen production electrolyzer, which comprises:

[0103] Deploy sampling wires on the anode plate and cathode plate of the electrolytic cell chamber, collect and analyze the electrolytic cell data of the initial connection to identify the electrolytic cell model, and configure system parameters based on the identification results;

[0104] The electrolytic cell chambers are grouped according to the adjusted parameters, and the operating status of each group of electrolytic cells is monitored;

[0105] Analyze data anomalies based on monitoring results and implement corresponding measures;

[0106] Visualize the real-time data of each electrolyzer chamber group.

[0107] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0108] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0109] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0110] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A monitoring system for an alkaline water electrolysis hydrogen production electrolyzer, characterized in that: include, Intelligent identification module, used to deploy sampling wires, collect and analyze the data of the electrolyzer connected for the first time to identify the electrolyzer model, and configure system parameters based on the identification results; A group monitoring module is used to group the electrolytic cell chambers according to the adjusted parameters and monitor the operating status of each group of electrolytic cells; Data analysis module, used to analyze data anomalies based on monitoring results and execute response measures; A visualization module is used to visualize the real-time data of each electrolytic cell chamber group; Deploying the sampling wires means connecting one end of the sampling wires to the anode plate and the other end to the cathode plate in each cell of the electrolytic cell according to the configuration of the electrolytic cell, fixing the wires with insulating brackets and insulating clamps, and connecting the output end of the sampling wires to the central database; The collecting and analyzing the electrolytic cell data of the initial connection to identify the electrolytic cell model and specifications, and configuring the system parameters according to the identification results refers to collecting the voltage and current data and operating parameters of electrolytic cells of different models from multiple data sources, marking the corresponding electrolytic cell model for each data point and standardizing the collected data, and arranging the operating parameters of electrolytic cells of different models according to the electrolytic cell models to generate an electrolytic cell parameter library and storing it in a central database; The RBF kernel function is used to construct the electrolytic cell classification model, and the candidate value range and initial candidate value of the regularization parameter C and the kernel function parameter γ are set. The RBF kernel function is: K(x i ,x j )=exp(-γ||x i -x j || 2 ), Where γ is the kernel function parameter, x i and x j is the i-th and j-th data input; The standardized electrolytic cell data of different models are used as training sets to train the electrolytic cell classification model, and the optimization objective function of the data electrolytic cell classification model is defined as: In the formula, a i is the slack variable, w is the normal vector of the decision boundary, b is the bias term of the decision boundary, C is the regularization parameter, n is the number of samples, and y i is the i-th training data label, φ(x i ) is the representation of the feature vector mapped to the high-dimensional space through the RBF kernel function; The candidate values ​​of the regularization parameter C and the kernel function parameter γ are combined, each combination is substituted into the electrolytic cell classification model for model training to obtain the optimized objective function output, and the regularization parameter C and the kernel function parameter γ combination of the minimum optimized objective function is selected as the model parameter output to the electrolytic cell classification model; Deploy the trained electrolytic cell classification model to the monitoring system, collect the electrolytic cell operation data of the first connection, and input the electrolytic cell operation data into the electrolytic cell classification model after preprocessing to classify the electrolytic cell operation data and generate the electrolytic cell classification result; According to the model of the electrolytic cell in the electrolytic cell classification result, the configuration parameters of the corresponding electrolytic cell model are queried from the parameter library in the central database to match the electrolytic cell, and the queried parameters are applied to the monitoring system to adjust the sampling frequency, voltage range and current range.

2. The monitoring system for an alkaline water electrolysis hydrogen production electrolyzer according to claim 1, characterized in that: The grouping of the electrolytic cell chambers according to the adjusted parameters refers to collecting initial voltage and current data of the electrolytic cell chambers after the electrolytic cell operates according to the adjusted parameters and performing standardization on the collected data; Use K-means algorithm to identify natural clusters in the data and divide the electrolyzer cells into N groups; Randomly select K data points as initial cluster centers, assign each data point to the nearest cluster center, and calculate the new center point of each cluster: Where k is the number of clusters, C j is the data point in the i-th cluster, l is the data point, A j It is cluster C j The center point of Repeat the steps of assigning and updating until the cluster center no longer changes; The grouping results after clustering are updated to the central database, the group number of each cell is obtained from the clustering algorithm, and the group number of each cell and its corresponding electrolytic cell identifier are updated to the central database; According to the grouping results, configure independent monitoring channels and data acquisition frequencies for each group, collect data within the past 24 hours of each group, and calculate the average values ​​μ of voltage and current and the standard deviation σ of voltage and current within each time window: In the formula, v l is a single data point, and m is the total number of data points; Set the data stability judgment threshold Q, and compare the calculated standard deviation σ of each group with the judgment threshold Q to judge the data stability. If σ≤Q, it means that the data fluctuation of this group is small, the operation is stable, and the frequency of data collection is reduced; If σ>Q, it means that the data set fluctuates greatly and the operation is unstable, so the frequency of data collection should be increased.

3. The monitoring system for an alkaline water electrolysis hydrogen production electrolyzer as claimed in claim 2, characterized in that: Monitoring the operating status of each group of electrolytic cells refers to monitoring the operating data of each electrolytic cell chamber group, collecting data of each electrolytic cell chamber group according to the calculated data collection frequency of each electrolytic cell chamber group, and transmitting the collected data to the data analysis module.

4. The monitoring system for an alkaline water electrolysis hydrogen production electrolyzer as claimed in claim 3, characterized in that: Analyzing data anomalies based on monitoring results and executing response measures refers to receiving the operating data of different electrolytic cell chamber groups transmitted, implementing a dynamic control chart for each electrolytic cell chamber group according to the standard deviation calculated by the group monitoring module, and setting the control limit of each electrolytic cell chamber group to: UCL=μ+3σ, LCL = μ-3σ, Where UCL and LCL are the upper control limit and the lower control limit, respectively, μ is the mean value of the electrolytic cell chamber group data, and σ is the standard deviation of the electrolytic cell chamber group data; Real-time monitoring of the data points of each electrolytic cell chamber group, regular update of the mean and standard deviation of each electrolytic cell chamber group, and comparison of each data point. If a data point exceeds the control limit three times in a row, the data is automatically marked as abnormal; The corresponding electrolytic cell chamber is found according to the group number and electrolytic cell identifier corresponding to the detected abnormal data, and the electrolytic cell chamber is further monitored and analyzed, the data abnormality is recorded, and a notification report is generated and sent to the operator for early warning.

5. The monitoring system for an alkaline water electrolysis hydrogen production electrolyzer as claimed in claim 4, characterized in that: The visual display of the real-time data of each electrolytic cell chamber group refers to converting the collected electrolytic cell chamber group data into analysis charts through professional software for visual centralized display, and collecting display content in real time during the display process to adjust the data and generate a personalized display mode for storage.

6. A method for monitoring an alkaline water electrolysis hydrogen production electrolyzer based on the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer according to any one of claims 1 to 5, characterized in that: include, Deploy sampling wires on the anode plate and cathode plate of the electrolytic cell chamber, collect and analyze the electrolytic cell data of the initial connection to identify the electrolytic cell model, and configure system parameters based on the identification results; The electrolytic cell chambers are grouped according to the adjusted parameters, and the operating status of each group of electrolytic cells is monitored; Analyze data anomalies based on monitoring results and implement corresponding measures; Visualize the real-time data of each electrolyzer chamber group.

7. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that the processor implements the steps of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the monitoring system of the alkaline water electrolysis hydrogen production electrolyzer according to any one of claims 1 to 5 are implemented.

Images