CN115074776A - Intelligent adaptive control system and method for electrolysis of water for hydrogen production adapting to wide power fluctuations - Google Patents

Abstract

The invention relates to an intelligent self-adaptive control system and method for electrolyzing water for hydrogen production that can adapt to wide power fluctuations. The system includes: an expert experience knowledge base module: used to obtain expected output parameters of an electrolytic cell under the limit of boundary conditions; a feedback compensation module: used It is used to detect the deviation value between the output parameters and boundary conditions of the electrolyzer after operation, and output the expert experience compensation value; electrolyzed water hydrogen production module: used to control the input value of the electrolyzer according to the expert experience compensation value and the output value of the expert experience knowledge base. Stable operation in the presence of power fluctuations. The present invention can obtain the given value of the parameters of the hydrogen production system through the cooperation of various modules under the premise of adapting to wide power fluctuations, so that the electrolyzed water hydrogen production module can operate safely and stably under the influence of the fluctuation of renewable energy, and the hydrogen production efficiency can be improved , the hydrogen produced is of high purity.

Description

Intelligent adaptive control system and method for electrolysis of water for hydrogen production adapting to wide power fluctuations

technical field

The invention relates to the technical field of electrolysis of water for hydrogen production, in particular to an intelligent adaptive control system and method for electrolysis of water for hydrogen production which can adapt to wide power fluctuations.

Background technique

As a clean and low-carbon energy, hydrogen energy has various advantages such as cleanliness, storage and high energy carrier, and is considered to be the most promising secondary energy in the 21st century. one. However, at present, hydrogen production from fossil energy is the mainstream method of hydrogen production, and the purity of the hydrogen produced is low. In order to reduce the harm to human health and the environment caused by the large-scale use of fossil fuels, the state encourages the production of hydrogen from renewable energy. It is green hydrogen with a purity of more than 99.95%. Green hydrogen will be the mainstream in the future.

Among them, in the process of hydrogen production, alkaline water electrolysis is the most promising method for industrial production of green hydrogen. However, due to the uncertainty of renewable energy such as wind and solar power generation, the given power of the electrolyzer will fluctuate greatly. However, it may cause some key parameters in the electrolyzer system to exceed the safe boundary conditions, resulting in serious consequences. For example, if the input power of the electrolyzer system fluctuates in a large range at a certain time, the hydrogen content in the oxygen in the oxygen scrubber will not be within the safe range (below 2%). In order to avoid the danger of explosion, the system will automatically alarm and make the electrolyzer The shutdown of the system further affects the hydrogen production efficiency and the safety of the system. Therefore, it is of great significance of the present application to study the control method of the electrolyzer system adapting to wide power fluctuation, to ensure the continuous and stable operation of the electrolyzer and maximize the hydrogen production under the premise of the safe operation of the system.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide an intelligent self-adaptive control system and method for electrolyzed water for hydrogen production that can adapt to wide power fluctuations. Through the expert experience knowledge base model, the mutual cooperation between the feedback compensation module and the electrolyzed water hydrogen production module enables the electrolyzer to adapt to the Different power fluctuations ensure the safe and stable operation of the electrolyzer and improve the hydrogen production efficiency of the electrolyzer.

For achieving the above object, the present invention provides the following scheme:

An intelligent adaptive control system for electrolysis of water for hydrogen production that adapts to wide power fluctuations, including:

Expert experience knowledge base module: used to obtain the expected output parameters of the electrolyzer under the constraints of the boundary conditions, where the boundary conditions are used to limit the system parameters and ensure the safe operation of the system, and the expected output parameters are used to make the system run The parameters satisfy the set boundary conditions;

Feedback compensation module: used to detect the deviation value between the output parameters of the electrolyzer after operation and the boundary conditions, and output the expert experience compensation value;

Water electrolysis hydrogen production module: used to control the stable operation of the electrolytic cell under the condition of fluctuations in input power according to the expert experience compensation value and the output value of the expert experience knowledge base.

Preferably, the expert experience knowledge base module includes:

Expert experience knowledge base model: used to obtain the current input power of the electrolytic cell and the current measured operating parameter Y _k of the electrolytic cell, under the restriction of the boundary conditions, to obtain the electrolytic cell that satisfies the boundary The expected output parameters under the constraints of the condition.

Preferably, the measured parameters Y _k of the electrolyzer include: system pressure, lye flow rate, temperature of the electrolyzer, liquid level difference between the oxygen separator and the hydrogen separator, the hydrogen content in the oxygen in the oxygen scrubber, the hydrogen scrubber Oxygen content of hydrogen in the vessel.

Preferably, the expert experience knowledge base module further includes a query and matching unit, and the query and matching unit is configured to calculate, based on a multi-attribute similarity algorithm, the current operating characteristic parameters of the electrolytic cell within the boundary conditions that meet the boundary conditions. Query and match the expert's experience knowledge in the knowledge base, and filter out the expected output value in the knowledge base that is closest to the current working condition of the electrolytic cell.

Preferably, the multi-attribute similarity algorithm includes a nearest neighbor algorithm, Euclidean distance and structural similarity, and based on the multi-attribute similarity algorithm, the overall similarity between the current operating parameters of the electrolytic cell and the expert experience knowledge is obtained, Queries and matches are performed based on the similarity.

Preferably, the expert experience knowledge base module further includes an evaluation and correction unit and a storage and addition unit, and the evaluation and correction unit is used to evaluate and correct the reuse result of the expert experience knowledge in the expert experience knowledge base, according to Whether the important parameters during the operation of the electrolytic cell meet the boundary conditions is used to judge whether to correct the expert experience knowledge. If the current important parameters exceed the boundary conditions, the expert experience knowledge needs to be corrected. If the important parameters are all within the boundary conditions, so there is no need to revise the expert experience and knowledge; wherein the important parameters include the hydrogen content in oxygen, the oxygen content in hydrogen, the liquid level difference and the temperature of the lye; the storage and addition unit is used for Add new expert experience knowledge.

Preferably, the feedback compensation module includes:

Expert rule establishment unit: used to set rules according to the deviation between the important parameters outputted after the electrolyzer runs and the boundary value, and experts give the correlation coefficient of parameter compensation for each deviation according to experience and rules; wherein, The rules include: the error between the hydrogen content in the oxygen in the electrolytic cell operation and the boundary value threshold, the error between the oxygen content in the hydrogen in the electrolytic cell operation and the boundary value threshold, the liquid level difference in the electrolytic cell operation and the boundary value threshold value. The error between the boundary value thresholds and the error between the lye temperature and the boundary value thresholds in the operation of the electrolyser;

Inference engine unit: used to infer the corresponding expert experience compensation value by using an exhaustive item-by-item search algorithm through expert empirical rules according to the difference between the important parameters outputted during the operation of the electrolytic cell and the boundary value, and output The expert experience compensation value.

Preferably, the water electrolysis hydrogen production module is used to perform transient PID control on the pressure regulating valve and the pneumatic regulating valve in the electrolytic cell through the combination of fuzzy rules and neural network, so as to ensure the pressure and oxygen of the electrolytic cell at the current moment. Separator and hydrogen separator levels, as well as lye temperature and flow, respond to given values of important parameters.

An intelligent adaptive control method for hydrogen production from electrolyzed water that adapts to wide power fluctuations, including:

Build an expert experience knowledge base model, according to the current input power and measured parameters of the electrolyzer, obtain the expected output parameters of the electrolyzer system under the constraints of boundary conditions, wherein the boundary conditions include: hydrogen content in oxygen, oxygen in hydrogen Content, lye flow, lye temperature and liquid level difference between oxygen separator and hydrogen separator, and the expected output parameters include a given value of system pressure, a given value of lye temperature and a given value of lye flow;

The electrolytic cell system is operated based on the expected output parameters, the deviation value between the output parameters of the electrolytic cell system after operation and the boundary conditions is detected by a feedback compensation model, and an expert experience compensation value is output;

According to the expert experience compensation value and expected output parameters, the pressure regulating valve and the pneumatic regulating valve in the electrolytic cell are controlled by fuzzy rules and neural network for transient PID control, and the important parameters of the output boundary are detected at the same time. The value is monitored and corrected in the feedback compensation model and the expert experience knowledge base model.

The beneficial effects of the present invention are:

The present invention can adaptively control the given parameters (system pressure, lye flow, lye temperature) of the electrolyzer through the intelligent control method on the basis of adapting to the wide power fluctuation of the alkaline electrolyzer caused by the uncertainty of renewable energy power generation. The important parameters of the electrolyzer system (hydrogen content in oxygen, etc.) are kept within a safe range, so that the electrolyzer system can effectively improve the hydrogen production efficiency and the purity of hydrogen produced under the condition of ensuring safe and stable operation of the electrolyzer system.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings required in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some of the present invention. In the embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative labor.

FIG. 1 is a schematic structural diagram of a module of an intelligent self-adaptive control system for electrolysis of water for hydrogen production that adapts to wide power fluctuations according to an embodiment of the present invention;

2 is a broken line diagram of hydrogen content in oxygen under different electrolyzer input power ranges and different system pressures according to the embodiment of the present invention;

3 is a schematic diagram of a safe area of hydrogen content in oxygen under different power ranges and different system pressures according to an embodiment of the present invention;

4 is a broken line diagram of oxygen content in hydrogen under different power ranges and different system pressures according to an embodiment of the present invention;

5 is a schematic diagram of the liquid level difference of the separator under different power ranges and different system pressures according to an embodiment of the present invention;

6 is a schematic diagram of energy consumption and energy efficiency of different power pressures according to an embodiment of the present invention;

FIG. 7 is a flowchart of an intelligent adaptive control method for electrolysis of water for hydrogen production that adapts to wide power fluctuations according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a workflow of an expert experience knowledge base module according to an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In order to make the above objects, features and advantages of the present invention more clearly understood, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.

After the renewable energy is generated, the power is output to the alkaline electrolyzer through the DC microgrid, and the power supplied to the electrolyzer is relatively fluctuating, which may cause the important parameters of the hydrogen production system to exceed the safe operation boundary conditions. E.g:

1) The hydrogen content in the oxygen in the oxygen scrubber exceeds 2%, and once it exceeds 2%, there is a danger of explosion. In addition, the hydrogen produced by alkaline electrolysis of water requires high purity, and the oxygen content in the hydrogen in the hydrogen scrubber is restricted to not exceed 0.5%;

2) If there is a large deviation between the liquid level of the oxygen separator and the liquid level of the hydrogen separator, it may cause the lye to enter the scrubber and be ejected from the vent through the scrubber. If someone passes under the air defense port, alkali burns may occur. In addition, if the liquid level on one side is too low, the gas and lye in the separator may enter the circulating pump at the same time, causing the circulating amount of lye to fluctuate greatly, or even stop rotating. The deviation may continue to increase, and the gas in the separator on one side will enter the separator on the other side, and the hydrogen-oxygen mixing phenomenon will occur in the separation, which will easily explode in the separator and cause serious safety accidents. Therefore, oxygen separation is set up. The liquid level difference with the hydrogen separator cannot exceed 5cm;

3) During the operation of the alkaline electrolytic cell, the temperature of the cell body is mainly controlled by the lye solution. The temperature of the lye solution is required to be controlled at about 65 °C, and the fluctuation should be less than 1.1 °C. The lower the temperature is, because the diaphragm between the cathode and the anode of the electrolytic cell has certain requirements on the temperature, the temperature of the hydrogen tank and oxygen tank should be less than 85 ℃ when the electrolytic cell is running. If the lye flow rate is too low, the temperature of the separator will be caused. Exceeding the boundary temperature will damage the diaphragm between the cathode and anode of the electrolytic cell, causing hydrogen and oxygen on both sides to mix, causing serious consequences.

4) In addition, the flow of lye will also affect the purity of hydrogen and oxygen. If the flow of lye is too large, the gas-liquid mixture produced by electrolysis in the separator will carry more impurity gas, resulting in the oxygen separator and hydrogen separator. The purity of oxygen and hydrogen decreased. In this embodiment, the lye flow rate range is set within 3.0-4.5 m ³ /h.

In addition, if the above-mentioned hydrogen content in oxygen, oxygen content in hydrogen, liquid level difference between oxygen separator and hydrogen separator, lye flow rate, and lye temperature exceed the boundary conditions, it will not only have a serious impact on system safety but also It will lead to the reduction of hydrogen production efficiency and hydrogen production.

Referring to FIG. 1, the present embodiment provides an intelligent adaptive control system for electrolysis of water for hydrogen production that adapts to wide power fluctuations, including:

Expert experience knowledge base module: used to obtain the expected output parameters of the electrolyzer under the constraints of the boundary conditions, wherein the boundary conditions include: hydrogen content in oxygen, oxygen content in hydrogen, lye flow, lye temperature and oxygen separator and the liquid level difference of the hydrogen separator, the expected output parameters include a given value of system pressure, a given value of lye concentration and a given value of lye flow;

Feedback compensation module: used to detect the deviation value between the output parameters of the electrolyzer after operation and the boundary conditions, and output the expert experience compensation value;

Water electrolysis hydrogen production module: used to control the stable operation of the electrolytic cell under the condition of fluctuations in input power according to the expert experience compensation value and the output value of the expert experience knowledge base.

(1) Expert Experience Knowledge Base Model

The expert experience knowledge base model is based on the input power of the current electrolytic cell system, and comprehensively considers the current measured parameters Y _k of the current electrolytic cell system. Under the limit of the boundary condition B _k , according to the expert experience knowledge base model, coordinate the given electrolytic cell The closed-loop given value Z _k of the system under the constraints that satisfy the boundary conditions.

The measured parameters (Y _k ) of the electrolyzer system entered into the expert experience knowledge base are the system pressure, the flow rate of the lye, the temperature of the electrolyzer, the liquid level difference between the oxygen separator and the hydrogen separator, and the oxygen in the oxygen scrubber. Medium hydrogen content, oxygen content in hydrogen in the hydrogen scrubber. Under the constraints of boundary conditions, the expected output parameters of the electrolyzer system are obtained according to the method of combining knowledge base reasoning and mathematical model, which are the given value of system pressure, the given value of lye temperature, and the given value of lye flow.

The steps are as follows:

①Establish the basic knowledge base of electrolyzed water hydrogen production system

Through a large number of experiments, under the condition that the electrolyzer input power in different ranges (20%, 40%, 60%, 80%, 100%), by changing the system pressure, lye temperature, lye flow parameters, the electrolyzer system It can operate stably under the limitation of boundary conditions. The boundary conditions are that the hydrogen content in oxygen in the oxygen scrubber is less than 2% (50% LFL), the oxygen content in hydrogen in the hydrogen scrubber is less than 0.5%, and the oxygen separation The liquid level difference between the liquid level of the device and the hydrogen separator should be within 5cm, the flow rate of the lye should be within 3-4.5m ³ /h, the temperature of the lye should be kept at about 65°C, and the fluctuation range should be kept at 1.1°C. The temperature should be less than 85 ℃ and so on. Figures 2 to 6 are obtained through experiments, respectively, and their representative meanings are introduced in turn below.

Figure 2 shows the change of hydrogen content in oxygen in different ranges of power input to the electrolyzer and by changing the system under different pressures. ), if the hydrogen content in oxygen exceeds the safe range by 2% (50% LFL), by appropriately changing the system pressure, the hydrogen content in oxygen can be brought back to the safe range.

At each power test, the electrolyzer was run continuously for more than two hours to ensure long-term operation of the electrolyzer at this power. For example, when the input power of the electrolyzer is 40% of the rated power, if the system pressure is 1.6Mpa, the hydrogen content in the oxygen in the oxygen scrubber has exceeded 2%. By changing the system pressure to 1.0Mpa, it can be shown in Fig. It can be seen in 2 that the hydrogen concentration in oxygen drops below 2%, and the system returns to the safe range. Therefore, when the hydrogen concentration in oxygen is not within the safe range, the safe and stable operation of the system can be ensured by appropriately changing the pressure in the system. This establishes a safe area for the concentration of hydrogen in oxygen at different input powers of the electrolyzer and at different system pressures.

As shown in Figure 3, when the LFL is 50%, the red area is the area where the hydrogen content in oxygen is within the safe range; when the LFL is 75%, the red and blue areas are the area where the hydrogen content in oxygen is within the safe range; the 3 area is Undetectable area; 4 area is unsafe area; 5 area is temporarily available area.

Figure 4 shows the change of oxygen content in hydrogen in the hydrogen scrubber when the electrolyzer inputs different ranges of power and changes the system pressure. It can be found from Figure 4 that the concentration of oxygen in hydrogen can be well maintained within a safe range , when the input power of the electrolyzer is determined, the oxygen content in the hydrogen in the hydrogen scrubber can be reduced by changing the pressure of the system. In order to improve the concentration of hydrogen produced by the water electrolysis hydrogen production system, when the oxygen content in the hydrogen in the electrolysis cell system exceeds the hydrogen purity requirement (<0.5%), the purpose of adjusting the oxygen content in the hydrogen can be achieved by adjusting the pressure of the system, thereby Improve the purity of hydrogen produced by the system.

Figure 5 shows the change between the liquid level difference between the oxygen separator and the hydrogen separator under different power ranges and different pressures input to the electrolyzer. If it exceeds 0.7cm, the maximum liquid level deviation shown in Figure 5 does not exceed 0.7cm, which meets the requirements. Therefore, it is concluded that the input power of the electrolyzer and the system pressure have no obvious correlation with the liquid level difference of the hydrogen-oxygen separator, so The safe range of hydrogen content in oxygen can be met by adjusting the pressure of the system at different powers. Figure 6 shows the power consumption and energy efficiency of the system under different power and system pressure. With the increase of power, the energy consumption of the stack shows an upward trend and the energy efficiency shows a downward trend; and the change of system pressure has a significant impact on both indicators. There is no apparent effect, thus also illustrating that the safe range of hydrogen in oxygen can be met by adjusting the system pressure.

Table 1-Table 2 shows the changes of oxygen tank temperature and hydrogen tank temperature in the electrolyzer under different lye flow rates and the changes of hydrogen purity and oxygen purity in the separator. It can be seen from Table 1 that the larger the lye flow rate, the more oxygen The lower the bath temperature and the hydrogen bath temperature, and when the lye flow rate is 2.6m ³ /h, the bath temperature has exceeded 85℃, which is not within the safe range of the working temperature of the electrolyzer, which is not conducive to the safe operation of the electrolyzer system; in Table 2 , with the increase of lye flow, the oxygen purity and hydrogen purity in the oxygen separator and hydrogen separator decrease slightly, so the temperature of the electrolyzer and the purity of oxygen and hydrogen can be adjusted by controlling the lye flow. Therefore, the hydrogen content in the oxygen can also be changed by adjusting the lye flow rate under different working power, and it can also be controlled at 2% (50% LFL). In this way, it is not only possible to control the hydrogen content in oxygen by changing the system pressure, but to combine the system pressure and the lye flow to control the power adjustment range.

Table 1

Table 2

Based on this, an original expert experience knowledge base is established according to the experience obtained from a large number of experiments. The expert experience knowledge base can be expressed as follows:

E _k ={T _k ,P _k ,Y _k ,B _k ,Z _k ,S _k }

In the formula, E _k is the Kth expert experience knowledge (K=1, 2, 3, ..., m, m is the quantity of expert experience knowledge); T _k is the storage time of expert experience knowledge E _k , and P _k is The ratio of the input power of the expert experience knowledge E _k to the rated power, Y _k = {y _k1 , y _k2 , y _k3 , y _k4 , y _k5 , y _k6 } is the characteristic of the electrolytic cell system of the expert experience knowledge E _k during operation The parameters, y _k1 , y _k2 ,…, y _k6 respectively represent the system pressure, lye flow rate, electrolyzer temperature, oxygen separator and hydrogen separator liquid level difference under the safe and stable operation of the electrolyzer system in the Kth expert’s experience and knowledge , hydrogen content in oxygen, oxygen content in hydrogen. B _k ={b _k1 ,b _k2 ,b _k3 ,b _k4 ,b _k5 } is the boundary condition of the important parameters of the electrolytic cell system in the expert experience knowledge E _k when the electrolytic cell system runs stably, b _k1 , b _k2 , and b _k5 respectively represent The hydrogen content in the oxygen in the oxygen scrubber is less than 2%, the oxygen content in the hydrogen in the hydrogen scrubber is less than 0.5%, 3m ³ /h ≤ lye flow rate ≤ 4.5m ³ /h, the liquid in the oxygen separator and the hydrogen separator Potential difference <5cm, 63.9℃≤lye temperature≤66.1℃. Z _k = {z _k1 , z _k2 , z _k3 } is the expected value of expert experience and knowledge output, z _k1 , z _k2 , z _k3 are respectively expressed as a given value of system pressure, a given value of lye temperature, and a given lye flow rate value. _Sk is the comprehensive similarity between the current characteristic parameters of the electrolytic cell system and the Kth expert's experience and knowledge. The input and output of an expert's experience knowledge E _k are shown in Table 3.

table 3

Query and match unit:

In this embodiment, the multi-attribute similarity calculation is used to query and match the expert experience knowledge in the knowledge base that meets the safety boundary conditions through the operating characteristic parameters of the current electrolytic cell system, and screen out the knowledge base that is most similar to the current electrolytic cell operating conditions. Expected output value (Figure 8). First, the current situation of the electrolytic cell system is defined as expert experience knowledge En , P _{n is} the power input ratio of the electrolytic cell under the current situation, and Y _n ={y _n1 ,y _n2 ,...,y _n6 } is the current For each parameter value of the electrolytic cell system, first, for the input power attribute of the electrolytic cell, the similarity between the input power and all expert experience knowledge is calculated according to the optimized nearest neighbor algorithm, so as to determine the phase of the current electrolytic cell input power. Expert experience and knowledge in the adjacent power range. The optimized nearest neighbor algorithm is as follows:

The exponential form can make the similarity calculation more accurate, sim(P _i,k ,P _i,n ) represents the similarity between the input power of the expert experience knowledge E _k and the input power of the current situation. Find out expert knowledge of the adjacent range of input power in the current situation. Among them, the characteristic parameters of the electrolytic cell system may be missing or the characteristic attribute value is 0, so the characteristic information is incomplete, which affects the similarity calculation. Therefore, the structural similarity is added to reduce this effect.

Structural similarity only calculates the similarity between the current situation and the attributes whose attribute value is not 0 in the experience knowledge of historical experts, which can effectively avoid the problem of incomplete information. Suppose P={the set of all non-empty attributes of the electrolyzer system in the current situation}, Q ={all non-empty attribute sets in the empirical knowledge Q of historical experts}, the structural similarity S of P and Q is expressed as follows:

Among them, ω _∩ is the sum of the weight values of all attributes in the intersection of sets P and Q, and ω _∪ is the sum of the weight values of all attributes in the union of sets P and Q.

The Euclidean distance formula for the current parameters of the electrolytic cell system and the previous expert experience knowledge is:

Among them, ω _i represents the feature weight value of expert experience knowledge. Through expert experimental experience, it can be concluded that the system pressure characteristics have a great influence on the important parameters of the electrolytic cell system. When the power of the given electrolytic cell is determined, the current system pressure Under certain circumstances, the hydrogen content in the oxygen in the electrolyzer system is not within the safe range, and the hydrogen content in the oxygen can be kept within the safe range by moderately adjusting the system pressure, as shown in Figure 2. Compared with the system pressure, the lye flow and system liquid level have little influence on important parameters. Based on this, according to the degree of influence on the safe operation of the electrolysis system, ω _i is set as: ω _i ={0.9, 0.05, 0.05, 0, 0, 0}.

Combining the nearest neighbor algorithm, Euclidean distance and structural similarity to obtain the overall similarity between the current situation of the electrolyzer and the experience knowledge of historical experts:

Suppose sim _max is the maximum similarity between the current electrolyzer system situation and historical expert experience knowledge, namely:

The comprehensive similarity threshold sim _yz can be set as:

The threshold Y _YZ is given by expert experience, and is set to 0.9 here. Retrieve all the expert experience knowledge of the overall similarity sim (E _n , E _k ≥sim _yz ) from the expert experience knowledge base, and then record the solution {Z _k } of the expert experience knowledge, time T _k and the overall similarity sim (E _n , E _k ), and then arrange them in descending order according to the attribute values of “overall similarity” and “expert experience and knowledge storage time”, and wait for the next processing.

Expert experience and knowledge reuse:

From the matched expert experience knowledge, select the expert experience knowledge with the maximum similarity sim _max and determine its number Num.

If Num=1, it means that there is only one expert experience knowledge with the greatest similarity. Let this expert experience knowledge be E _k , 1≤k≤m, let the next expert experience matching the expert experience knowledge E _k in the expert experience knowledge data table The knowledge is E _h , 1≤h≤m, because the matching expert experience knowledge is retrieved in descending order according to the attribute values of "overall similarity" and "expert experience knowledge storage time", so E _h should be the second largest similarity And store the latest one for expert experience knowledge. Note that the expected output of expert experience knowledge E _h is Z _h , the overall similarity is sim _h , and the expected output of expert experience knowledge E _k is Z _k , then the expected output Z _hk of the description in the current situation is:

If Num>1, it means that there are multiple expert experience knowledges with the same maximum overall similarity, and there are f, assuming that these expert experience knowledge E _i , i=1...f is arranged in descending order of the storage time attribute value of expert experience knowledge as : E ₁ , E ₂ …E _f , Z ₁ , Z ₂ … Z _f are their corresponding expected outputs, then the expected output of the description in the current situation is:

Among them, θ _i is the time weighting coefficient for the reuse of expert experience and knowledge, which satisfies θ ₁ ≥ θ ₂ ≥...≥ θ _l , which can be determined according to specific circumstances or experience.

Evaluation and Correction Unit:

In order to verify the validity of the reuse results of expert experience and knowledge, it is necessary to evaluate and correct expert experience and knowledge. The first step is to evaluate the reuse results. If it is successful, it is not necessary to modify it. Otherwise, it is necessary to modify the expert experience and knowledge to improve the accuracy of the set module. In this embodiment, the evaluation of the expert's experience and knowledge is based on the feedback of its operation effect in the actual environment, and the correction of the expert's experience and knowledge is carried out on the basis of problems in the execution process.

After the electrolyzer system is running, the hydrogen content in oxygen, the oxygen content in hydrogen, the liquid level difference and the temperature of the lye will have a certain hysteresis. Therefore, these four important parameters are detected every one hour, and the values Feedback to the expert experience knowledge base to judge whether the important parameters in the current operating state meet the boundary conditions, and judge whether to modify the expert experience knowledge according to whether the boundary conditions are met. If the current important parameters exceed the boundary conditions, the expert experience knowledge is required. Make corrections, such as the hydrogen content in oxygen in the oxygen scrubber after the electrolyzer system is operating exceeds the limit of 2%, it will affect the system operation, and the expert experience knowledge will be corrected, if the important parameters are all within the boundary conditions, then No revision of expert experience knowledge is required.

Store and add units:

For the case where the new expert experience knowledge is added to the historical expert experience knowledge base, first calculate the overall similarity between the new expert experience knowledge and all the expert experience knowledge stored in the historical expert experience knowledge base, if all the obtained similarities are less than or equal to a certain A given threshold (the threshold is 0.8), new expert experience knowledge is added, and if there is at least one similarity greater than the threshold, it will not be stored.

(2) Feedback compensation model

After the expected output parameters selected from the expert experience knowledge base are given to the electrolyzer, during the operation of the electrolyzer, changes in some parameters may seriously affect the safety of the system. Among them, the four important parameters that have the most impact on system safety are the hydrogen content in oxygen in the oxygen scrubber, the oxygen content in hydrogen in the hydrogen scrubber, the liquid level difference between the oxygen separator and the hydrogen separator, and the temperature of the lye. The hydrogen content in oxygen is strictly required to be below 2%, the oxygen content in hydrogen must be below 0.5%, and the liquid level difference between the oxygen separator and the hydrogen separator cannot exceed 5cm, and the temperature of the lye should be maintained at about 65°C.

In this embodiment, in order to deal with the situation that the important parameters exceed the boundary conditions, a feedback compensation model is added to the intelligent control model. After the electrolytic cell is running, four important parameters are detected every one hour. The feedback compensation model is based on the operation of the electrolytic cell. The deviation between the four important parameters detected later and the boundary conditions is corrected by the set expert rules to the given values of the parameters of the intelligent control system, so that the parameters affecting the safety of the system and the purity of hydrogen production are returned to the safe range.

The feedback compensation model is mainly divided into three parts:

Expert rule building unit:

Experts set rules for the deviations (△e1, △e2, △e3, △e4) between the four important parameters output after the electrolyzer runs and the boundary values through practical experience and a large number of experiments. The rule table is shown in Table 4. Among them, △e1, △e2, △e3, and △e4 are the error between the hydrogen content of the oxygen in the electrolyzer operation and the boundary value of 2%, and the difference between the oxygen content of the hydrogen in the electrolyzer operation and the boundary value of 0.5%, respectively. Error, the error between the liquid level difference in the operation of the electrolyzer and the boundary value of 5cm, the error between the temperature of the lye solution in the operation of the electrolyzer and the boundary value of 65℃ The system pressure compensation value, lye liquid flow compensation value, and lye liquid temperature compensation value k _1,1 ,k _1,2 ,...,k _4,1 ,k _4,2 respectively represent four different deviations, experts according to Based on experience and rules, the correlation coefficients for the compensation of the given parameters of the three electrolyzers are given for each type of deviation.

Table 4

Inference engine unit:

The reasoning engine infers the corresponding expert experience compensation value by using the exhaustive item-by-item search algorithm through expert experience rules according to the difference between the four important parameters output during the operation of the electrolyzer and the boundary value. Output the expert experience compensation value deduced by the inference engine.

Electrolyzed water hydrogen production module:

The given parameters of the electrolyzer system, including the given value of system pressure, the given value of lye temperature, and the given value of lye flow, are corrected by the electrolysis water hydrogen production module according to the expert experience knowledge base model system and the feedback compensation model. The rules and neural network are combined to perform transient PID control on the pressure regulating valve and pneumatic regulating valve in the electrolyzer system to ensure the pressure of the electrolyzer system, the liquid level of the oxygen separator and the hydrogen separator and the temperature of the lye at this time. And the flow rate can respond quickly to tend to the given value of each parameter, which ensures the safe and stable operation of the electrolyzer hydrogen production system under the fluctuation of input power. At the same time, after the electrolyzer is running, because the parameter changes will have hysteresis, the four parameters are detected every one hour, and the detected four parameters are output to the expert experience knowledge base model. The four parameters are oxygen The hydrogen content in the oxygen in the scrubber, the oxygen content in the hydrogen in the hydrogen scrubber, the liquid level difference between the oxygen separator and the hydrogen separator, and the lye temperature. The reason for outputting these four parameters to the expert experience knowledge base model is to judge whether it is within the boundary range. If it is not within the bounds, the expert experience knowledge needs to be corrected.

As shown in Figure 7, this embodiment also provides an intelligent adaptive control method for electrolyzed water for hydrogen production that adapts to wide power fluctuations, including:

The electrolytic water hydrogen production system is based on the expert experience knowledge base model system and the feedback compensation model to correct the given parameters of the electrolytic cell system, and the pressure regulating valve and pneumatic regulating valve in the electrolytic cell system are combined with fuzzy rules and neural networks. Transient PID control, and output four boundary important parameter detection values to the feedback compensation model and the expert experience knowledge base model every hour. The purpose of outputting to the feedback compensation model is to obtain the compensation values of the four important parameters according to the deviation between the four important parameters and the boundary conditions according to the set expert experience rules; the purpose of outputting to the expert experience knowledge base model is to judge the current parameters Check whether the detected value is within the boundary range. If it is within the range, the system is running normally, and expert experience and knowledge do not need to be corrected. If it is not within the bounds, the expert experience knowledge needs to be corrected.

The intelligent self-adaptive control method for hydrogen production by electrolysis of water adapted to wide power fluctuations proposed by the invention can adaptively control the electrolyzer through the intelligent control method on the basis of adapting to the wide power fluctuation of the alkaline electrolyzer caused by the uncertainty of renewable energy power generation Given parameters (system pressure, lye flow, lye temperature), the important parameters of the electrolyzer system (hydrogen content in oxygen, etc.) are kept within a safe range, so that the electrolyzer system can effectively operate under the condition of ensuring safe and stable operation. The hydrogen production efficiency and the produced hydrogen purity of the electrolyzer are improved.

The above-mentioned embodiments are only descriptions of the preferred modes of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, those of ordinary skill in the art can make various Variations and improvements should fall within the protection scope determined by the claims of the present invention.

Claims (9)

1. an intelligent self-adaptive control system for electrolyzed water for hydrogen production that adapts to wide power fluctuations, is characterized in that, comprises: Expert experience knowledge base module: used to obtain the expected output parameters of the electrolyzer under the constraints of the boundary conditions, where the boundary conditions are used to limit the system parameters and ensure the safe operation of the system, and the expected output parameters are used to make the system run The parameters satisfy the set boundary conditions; Feedback compensation module: used to detect the deviation value between the output parameters of the electrolyzer after operation and the boundary conditions, and output the expert experience compensation value; Water electrolysis hydrogen production module: used to control the stable operation of the electrolytic cell under the condition of fluctuations in input power according to the expert experience compensation value and the output value of the expert experience knowledge base. 2. The intelligent self-adaptive control system for electrolysis of water for hydrogen production that adapts to wide power fluctuations according to claim 1, wherein the expert experience knowledge base module comprises: Expert experience knowledge base model: used to obtain the current input power of the electrolytic cell and the current measured operating parameter Y _k of the electrolytic cell, under the restriction of the boundary conditions, to obtain the electrolytic cell that satisfies the boundary The expected output parameters under the constraints of the condition. 3. The intelligent self-adaptive control system for electrolysis of water for hydrogen production that adapts to wide power fluctuations according to claim 2, wherein the measured parameter Y _k of the operation of the electrolyzer comprises: system pressure, lye flow, electrolyzer temperature , the liquid level difference between the oxygen separator and the hydrogen separator, the hydrogen content in the oxygen in the oxygen scrubber, and the oxygen content in the hydrogen in the hydrogen scrubber. 4. The intelligent self-adaptive control system for electrolysis of water for hydrogen production that adapts to wide power fluctuations according to claim 1, wherein the expert experience knowledge base module further comprises a query and matching unit, and the query and matching unit uses Based on the multi-attribute similarity algorithm, the calculation is based on the current operation characteristic parameters of the electrolyzer to query and match the expert experience knowledge in the knowledge base that meets the boundary conditions, and filter out the knowledge base and the current electrolysis. The tank condition is closest to the expected output value. 5. The intelligent adaptive control system for electrolysis of water for hydrogen production adapting to wide power fluctuations according to claim 4, wherein the multi-attribute similarity algorithm comprises a nearest neighbor algorithm, Euclidean distance and structural similarity, based on the The multi-attribute similarity algorithm obtains the overall similarity between the current operating parameters of the electrolytic cell and the expert experience knowledge, and performs query and matching based on the similarity. 6. The intelligent self-adaptive control system for electrolysis of water for hydrogen production that adapts to wide power fluctuations according to claim 1, wherein the expert experience knowledge base module further comprises an evaluation and correction unit and a storage and addition unit, and the The evaluation and correction unit is used to evaluate and correct the reuse result of the expert experience knowledge in the expert experience knowledge base, and judge whether to carry out the evaluation of the expert experience knowledge according to whether the important parameters during the operation of the electrolyzer meet the boundary conditions. Correction, if the current important parameters exceed the boundary conditions, the expert experience knowledge needs to be corrected; if the important parameters are all within the boundary conditions, the expert experience knowledge does not need to be corrected; wherein the important parameters include oxygen Medium hydrogen content, oxygen content in hydrogen, liquid level difference and lye temperature; the storage and addition unit is used to add new expert knowledge. 7. The intelligent self-adaptive control system for electrolysis of water for hydrogen production adapting to wide power fluctuations according to claim 6, wherein the feedback compensation module comprises: Expert rule establishment unit: used to set rules according to the deviation between the important parameters outputted after the electrolyzer runs and the boundary value, and experts give the correlation coefficient of parameter compensation for each deviation according to experience and rules; wherein, The rules include: the error between the hydrogen content in the oxygen in the electrolytic cell operation and the boundary value threshold, the error between the oxygen content in the hydrogen in the electrolytic cell operation and the boundary value threshold, the liquid level difference in the electrolytic cell operation and the boundary value threshold value. The error between the boundary value thresholds and the error between the lye temperature and the boundary value thresholds in the operation of the electrolyser; Inference engine unit: used to infer the corresponding expert experience compensation value by using an exhaustive item-by-item search algorithm through expert empirical rules according to the difference between the important parameters outputted during the operation of the electrolytic cell and the boundary value, and output The expert experience compensation value. 8. The intelligent self-adaptive control system for electrolyzed water for hydrogen production that adapts to wide power fluctuations according to claim 1, wherein the electrolyzed water for hydrogen production module is used for combining fuzzy rules and neural networks to control the electrolysis cells in the electrolyzer. The pressure regulating valve and pneumatic regulating valve perform transient PID control to ensure that the current pressure of the electrolyzer, the liquid level of the oxygen separator and the hydrogen separator, and the temperature and flow of the lye tend to respond to the given values of important parameters. . 9. An intelligent self-adaptive control method for electrolyzed water for hydrogen production that adapts to wide power fluctuations, characterized in that it comprises: Build an expert experience knowledge base model, according to the current input power and measured parameters of the electrolyzer, obtain the expected output parameters of the electrolyzer system under the constraints of boundary conditions, wherein the boundary conditions include: hydrogen content in oxygen, oxygen in hydrogen Content, lye flow, lye temperature and liquid level difference between oxygen separator and hydrogen separator, and the expected output parameters include a given value of system pressure, a given value of lye temperature and a given value of lye flow; The electrolytic cell system is operated based on the expected output parameters, the deviation value between the output parameters of the electrolytic cell system after operation and the boundary conditions is detected by a feedback compensation model, and an expert experience compensation value is output; According to the expert experience compensation value and expected output parameters, the pressure regulating valve and the pneumatic regulating valve in the electrolytic cell are controlled by fuzzy rules and neural network for transient PID control, and the important parameters of the output boundary are detected at the same time. The value is monitored and corrected in the feedback compensation model and the expert experience knowledge base model.

Images