Method and device for controlling consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy, electronic equipment and medium

Abstract

The application discloses a method and device for controlling consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy, electronic equipment and medium, and belongs to the technical field of hydrogen energy storage and material preparation. The method comprises the following steps: obtaining a performance prediction model of a production system, wherein the performance prediction model is constructed based on a time trajectory of historical process parameters of production equipment and an anti-poisoning performance index of a hydrogen storage alloy; based on the performance prediction model, an upper-layer decision controller is constructed with the objective of minimizing the difference of the anti-poisoning performance index of the hydrogen storage alloy produced by multiple production equipment; the time trajectory of the historical process parameters is optimized through the upper-layer decision controller to obtain an optimal time trajectory of process parameters of the production system; and based on the optimal time trajectory, the multiple production equipment is controlled through a lower-layer model prediction controller. The method ensures the consistency of the anti-poisoning performance index of the batch production of the hydrogen storage alloy.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of hydrogen energy storage and material preparation, and particularly relates to a method and device for controlling consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy, an electronic device and a medium. BACKGROUND

[0002] As a green energy, hydrogen energy has the advantages of high efficiency and no carbon emission, and has wide application potential in the fields of transportation, industrial manufacturing and renewable energy storage. Solid-state hydrogen storage alloy, due to its reversible hydrogen absorption and desorption characteristics, has become an important way for hydrogen storage. Compared with gaseous and liquid hydrogen storage technologies, solid-state hydrogen storage has higher safety and larger hydrogen storage density.

[0003] However, the batch preparation process of solid-state hydrogen storage alloy faces the challenge of poor performance consistency. Different batches of hydrogen storage alloy often show significant differences in key performance such as hydrogen absorption and desorption rate, hydrogen storage capacity and cycle life. This performance fluctuation affects the stability and reliability in large-scale applications. Especially, the poisoning effect of impurities (such as oxygen and water vapor) can significantly reduce the hydrogen storage capacity of hydrogen storage alloy and cause material failure. Impurities react with the surface of hydrogen storage alloy to form oxides or hydroxides, thereby hindering the absorption of hydrogen, and thus reducing the hydrogen storage efficiency and cycle life of hydrogen storage alloy.

[0004] Existing technical methods mainly rely on experience and simple process control models, which are difficult to cope with complex multi-physical field coupling problems and process fluctuations in the production process, resulting in difficulty in ensuring consistency in large-scale preparation. In particular, in terms of anti-poisoning ability, existing technologies cannot ensure the stability and anti-impurity ability of hydrogen storage alloy in batch production, and there is a problem of inconsistent anti-poisoning performance in large-scale production process. SUMMARY

[0005] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides a method and device for controlling consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy, an electronic device and a medium, which ensures the consistency of anti-poisoning performance indicators of hydrogen storage alloy in batch production.

[0006] In a first aspect, the present application provides a method for controlling consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy, applied to a production system of hydrogen storage alloy, wherein the production system comprises a plurality of production devices for performing preparation processes of hydrogen storage alloy, and the method comprises:

[0007] obtaining a performance prediction model of the production system, wherein the performance prediction model is constructed based on a time trajectory of historical process parameters of the production devices and anti-poisoning performance indicators of the produced hydrogen storage alloy;

[0008] constructing an upper decision controller based on the performance prediction model, the upper decision controller being configured to minimize a difference between the anti-poisoning performance indexes of the hydrogen storage alloy produced by the plurality of production devices;

[0009] optimizing the time trajectory of the historical process parameters by the upper decision controller to obtain an optimal time trajectory of the process parameters of the preparation process;

[0010] controlling the plurality of production devices by a lower model prediction controller based on the optimal time trajectory.

[0011] According to an embodiment of the present application, the constructing an upper decision controller based on the performance prediction model, the upper decision controller being configured to minimize a difference between the anti-poisoning performance indexes of the hydrogen storage alloy produced by the plurality of production devices, comprises:

[0012] constructing a uniformity function of the production system based on the performance prediction model, the uniformity function being configured to represent the difference between the anti-poisoning performance indexes of the plurality of production devices;

[0013] minimizing the uniformity function based on the constraint conditions of the process parameters to construct the upper decision controller.

[0014] According to an embodiment of the present application, the uniformity function comprises:

[0015]

[0016] wherein F is the uniformity function, representing a variance of the anti-poisoning performance indexes of the hydrogen storage alloy produced by the plurality of production devices, N is a number of production devices in the production system, y i is the anti-poisoning performance index of the hydrogen storage alloy produced by the i-th production device, is an average value of the anti-poisoning performance indexes of the hydrogen storage alloy produced by the N production devices.

[0017] According to an embodiment of the present application, the performance prediction model is:

[0018] y = f(X(t))

[0019] the time trajectory of the historical process parameters is:

[0020] X(t) = [T(t), P(t)] T

[0021] wherein y is the anti-poisoning performance index of the hydrogen storage alloy produced by the production device, X(t) is the time trajectory of the process parameters of the production device, T(t) is a temperature trajectory of the production device, and P(t) is a pressure trajectory of the production device.

[0022] According to one embodiment of the present application, the constructing the upper-level decision controller based on the constraint condition of the process parameters, and minimizing the uniformity function comprises:

[0023]

[0024]

[0025] wherein F is the uniformity function, N is the number of production equipment in the production system, Xi is the historical process parameter of the i-th production equipment, X i (t) is the time trajectory of the process parameter of the i-th production equipment at t moment, Xj is the historical process parameter of the j-th production equipment, X j (t) is the time trajectory of the process parameter of the j-th production equipment at t moment, T i (t) is the temperature trajectory of the i-th production equipment at t moment, T min Tmin is the lower limit value of the temperature of the constraint condition, T max Tmax is the upper limit value of the temperature of the constraint condition, P i (t) is the pressure trajectory of the i-th production equipment at t moment, P min Pmin is the lower limit value of the pressure of the constraint condition, P max Pmax is the upper limit value of the pressure of the constraint condition.

[0026] According to one embodiment of the present application, the controlling the plurality of production equipment by the lower-level model predictive controller based on the optimal time trajectory comprises:

[0027] analyzing the optimal time trajectory by the lower-level model predictive controller to determine the target process parameter of the plurality of production equipment at each moment;

[0028] adjusting the equipment parameters of the plurality of production equipment according to the target process parameter by the lower-level model predictive controller.

[0029] According to one embodiment of the present application, after the controlling the plurality of production equipment by the lower-level model predictive controller based on the optimal time trajectory, the method further comprises:

[0030] collecting real-time process parameters of the production system;

[0031] updating the optimal time trajectory by the real-time process parameters.

[0032] In a second aspect, the present application provides a device for controlling consistency of poison resistance in batch production of solid-state hydrogen storage alloy, applied to a production system of hydrogen storage alloy, wherein the production system comprises a plurality of production devices for performing a preparation process of hydrogen storage alloy, and the device comprises:

[0033] an acquisition module, configured to acquire a performance prediction model of the production system, wherein the performance prediction model is constructed based on a time trajectory of historical process parameters of the production devices and a poison resistance performance index of the hydrogen storage alloy;

[0034] a first processing module, configured to construct an upper-layer decision controller based on the performance prediction model, so as to minimize a difference in the poison resistance performance index of the hydrogen storage alloy produced by the plurality of production devices;

[0035] a second processing module, configured to optimize the time trajectory of the historical process parameters through the upper-layer decision controller, so as to obtain an optimal time trajectory of process parameters of the preparation process;

[0036] a third processing module, configured to control the plurality of production devices through a lower-layer model prediction controller based on the optimal time trajectory.

[0037] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the control method for consistency of poison resistance in batch production of solid-state hydrogen storage alloy according to the first aspect.

[0038] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, having a computer program stored thereon, wherein the computer program is executable by a processor to implement the control method for consistency of poison resistance in batch production of solid-state hydrogen storage alloy according to the first aspect.

[0039] In a fifth aspect, the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction to implement the control method for consistency of poison resistance in batch production of solid-state hydrogen storage alloy according to the first aspect.

[0040] In a sixth aspect, the present application provides a computer program product, comprising a computer program, wherein the computer program is executable by a processor to implement the control method for consistency of poison resistance in batch production of solid-state hydrogen storage alloy according to the first aspect.

[0041] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter.

[0042] The application provides a control method and device for consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy, and an electronic device and a medium.

[0043] (1) The upper decision controller constructed based on the performance prediction model optimizes the time trajectory of the process parameters, so that the optimal time trajectory with the lowest difference in anti-poisoning performance indicators can be obtained, and the lower model prediction controller controls each production equipment according to the optimal time trajectory, thereby improving the stability and anti-impurity ability of the hydrogen storage alloy in batch production, ensuring the consistency of the anti-poisoning performance indicators of the hydrogen storage alloy in batch production, and improving the consistency of the anti-poisoning performance of the solid-state hydrogen storage alloy and ensuring the uniformity and long-term use performance of the hydrogen storage alloy in production.

[0044] (2) The upper decision controller is responsible for the optimization of the time trajectory of the global process parameters, and the time trajectory of the key process parameters such as temperature and pressure is optimized in a long period based on the historical process parameters such as temperature and pressure collected in real time, so that the anti-poisoning performance difference between different production equipments is minimized, the optimal time trajectory of the process parameters is obtained, and the temperature and pressure reference values are provided to the lower model prediction controller, thereby ensuring the consistency of the anti-poisoning performance of the hydrogen storage alloy in large-scale production.

[0045] (3) The MPC controller in the lower model prediction controller adjusts the heating power and the vacuum pump rate of the production equipment to control the temperature and the pressure, and performs fine real-time control in a short period, adjusts the controllable parameters such as temperature and pressure of each production equipment in real time according to the optimal time trajectory of the process parameters such as temperature and pressure generated by the upper decision controller, and compensates the environmental changes and the performance fluctuations of the production equipment in real time, predicts the short-term changes of the process parameters through the state space model, realizes that the process parameters of each production equipment meet the optimal time trajectory, ensures the stability of the anti-poisoning performance of the hydrogen storage alloy in production, and can also ensure the consistency of the anti-poisoning performance of the hydrogen storage alloy in batch production through the feedback mechanism, thereby prolonging the service life and stability of the hydrogen storage alloy and being suitable for large-scale industrial application. BRIEF DESCRIPTION OF DRAWINGS

[0046] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

[0047] Figure 1 is one of the flowcharts of the control method for consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy provided by the embodiments of the present application;

[0048] Figure 2 is the second flowchart of the control method for consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy provided by the embodiments of the present application;

[0049] Figure 3 FIG. 3 is a third schematic diagram of a process of a method for controlling consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy provided by embodiments of the present application;

[0050] Figure 4 FIG. 4 is a schematic diagram of a device for controlling consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy provided by embodiments of the present application;

[0051] Figure 5 FIG. 5 is a schematic diagram of an electronic device provided by embodiments of the present application. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of them. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art belong to the scope of protection of the present application.

[0053] The terms "first", "second", and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally a category, and are not limited to the number of objects, for example, the first object can be one or more. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / ", generally represents a "or" relationship between the front and rear associated objects.

[0054] The solid-state hydrogen storage alloy batch preparation consistency of poison resistance control method, the solid-state hydrogen storage alloy batch preparation consistency of poison resistance control device, the electronic device and the readable storage medium provided by the embodiments of the present application will be described in detail below in combination with the drawings, through specific embodiments and application scenarios.

[0055] The solid-state hydrogen storage alloy batch preparation consistency of poison resistance control method can be applied to a terminal, and can be executed by hardware or software in the terminal.

[0056] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or a tablet computer having a touch-sensitive surface (e.g., a touchscreen display and / or a touchpad). It should also be understood that in some embodiments, the terminal can not be a portable communication device, but a desktop computer having a touch-sensitive surface (e.g., a touchscreen display and / or a touchpad).

[0057] In the following embodiments, a terminal including a display and a touch-sensitive surface is described. However, it is understood that the terminal can include one or more other physical user interface devices such as physical keyboards, mice, and joysticks.

[0058] The method for controlling consistency of poison resistance performance in batch preparation of solid-state hydrogen storage alloy provided by the embodiments of the present application can be executed by an electronic device or a functional module or functional entity of the electronic device that can realize the method for controlling consistency of poison resistance performance in batch preparation of solid-state hydrogen storage alloy. The electronic device mentioned in the embodiments of the present application includes but is not limited to a mobile phone, a tablet computer, a computer, a camera, a wearable device, and the like. The method for controlling consistency of poison resistance performance in batch preparation of solid-state hydrogen storage alloy provided by the embodiments of the present application will be described below by taking an electronic device as an example.

[0059] The method is applied to a production system of hydrogen storage alloy, and the production system includes a plurality of production devices that execute a preparation process of the hydrogen storage alloy.

[0060] The plurality of production devices are used to prepare the hydrogen storage alloy in batches, and in this case, the control of consistency of poison resistance performance in preparation needs to be ensured.

[0061] In the production system, each production device executes the same process pipeline for preparing the hydrogen storage alloy.

[0062] As shown in Figure 1 The method for controlling consistency of poison resistance performance in batch preparation of solid-state hydrogen storage alloy includes steps 110 to 130.

[0063] In step 110, a performance prediction model of the production system is acquired, and the performance prediction model is constructed based on a time trajectory of historical process parameters of the production devices and a poison resistance performance index of the production of the hydrogen storage alloy.

[0064] The time trajectory of the historical process parameters is collected in the process of preparing the hydrogen storage alloy by the plurality of production devices, and can include information such as temperature and pressure of the production devices at a plurality of continuous time points in the preparation process that affects the poison resistance performance of the hydrogen storage alloy.

[0065] The poison resistance performance index can be represented as a hydrogen absorption and release cycle efficiency of the hydrogen storage alloy, and is collected for the hydrogen storage alloy produced by the production devices.

[0066] It can be understood that the performance prediction model includes a mapping relationship between the time trajectory of the historical process parameters and the poison resistance performance index, and can be used to predict the poison resistance performance index of the hydrogen storage alloy produced by each production device.

[0067] For example, the process parameters are input into the performance prediction model, and a predicted anti-poisoning performance index output by the performance prediction model can be obtained.

[0068] In this step, a performance prediction model of the production system is constructed according to a data set composed of historical process parameters of the plurality of production devices and the anti-poisoning performance indexes of the production.

[0069] Step 120, based on the performance prediction model, an upper-level decision controller is constructed with the objective of minimizing the difference of the anti-poisoning performance indexes of the plurality of production devices in producing the hydrogen storage alloy.

[0070] The performance prediction model is used to calculate the anti-poisoning performance index corresponding to the process parameter according to the input process parameter.

[0071] In this step, the upper-level decision controller is constructed with the objective of minimizing the difference of the anti-poisoning performance indexes of the plurality of production devices by the prediction ability of the performance prediction model on the anti-poisoning performance indexes of the production devices in producing the hydrogen storage alloy.

[0072] Step 130, the time trajectory of the historical process parameters is optimized by the upper-level decision controller to obtain an optimal time trajectory of the process parameters of the preparation process.

[0073] The optimal time trajectory is used to indicate the production of the hydrogen storage alloy by each production device to improve the consistency of the anti-poisoning performance indexes of the hydrogen storage alloy produced by each production device.

[0074] In this step, the difference between the anti-poisoning performance indexes of the plurality of production devices in producing the hydrogen storage alloy is evaluated by the upper-level decision controller, and the time trajectory of the process parameter corresponding to the minimized difference is optimized by an optimization algorithm such as genetic algorithm or particle swarm optimization to obtain an optimal time trajectory of the entire cycle of producing the hydrogen storage alloy.

[0075] Step 140, based on the optimal time trajectory, the plurality of production devices are controlled by a lower-level model predictive controller.

[0076] In this step, the lower-level model predictive controller controls the running state of each production device in the production system according to the process parameter corresponding to each time in the optimal time trajectory to affect the process parameter of the production device.

[0077] According to the method for controlling consistency of anti-poisoning performance in batch production of solid-state hydrogen storage alloy provided in the embodiment, the upper decision controller constructed based on the performance prediction model is used to optimize the time trajectory of historical process parameters, so that the optimal time trajectory with the lowest difference in anti-poisoning performance index can be obtained, and the lower model prediction controller is used to control each production equipment according to the optimal time trajectory, thereby improving the stability and anti-impurity ability of the hydrogen storage alloy in batch production, ensuring the consistency of the anti-poisoning performance index of the hydrogen storage alloy in batch production, and improving the consistency of the anti-poisoning performance of the solid-state hydrogen storage alloy and ensuring the uniformity and long-term use performance of the hydrogen storage alloy in production.

[0078] In some embodiments, the upper decision controller is constructed based on the performance prediction model, with the objective of minimizing the difference in anti-poisoning performance index of the hydrogen storage alloy produced by the plurality of production equipment, including:

[0079] The uniformity function of the production system is constructed based on the performance prediction model, and the uniformity function is used to represent the difference in anti-poisoning performance index of the plurality of production equipment.

[0080] The minimum value of the uniformity function is calculated based on the constraint condition of the process parameters, and the upper decision controller is constructed.

[0081] The uniformity function is used to represent the difference in anti-poisoning performance index of the plurality of production equipment.

[0082] The constraint condition of the process parameters is an important mechanism to ensure that the production process of the hydrogen storage alloy is operated within the safe, efficient and quality standard range.

[0083] The objective of the upper decision controller is to minimize the uniformity function and optimize under the given process parameter constraint condition, and an optimization algorithm such as genetic algorithm, particle swarm optimization (PSO) or other optimization algorithm is used to solve the optimization problem.

[0084] In this embodiment, the upper decision controller can be effectively constructed to realize the uniformization of the anti-poisoning performance of the plurality of equipment in the production system, and improve the overall production efficiency and product quality.

[0085] In some embodiments, the performance prediction model is:

[0086] y=f(X(t))

[0087] The time trajectory of the historical process parameters is:

[0088] X(t)=[T(t),P(t)] T

[0089] wherein y is the resistance to poisoning performance index of the hydrogen storage alloy produced by the production equipment, X(t) is the time trajectory of the historical process parameters of the production equipment, T(t) is the temperature trajectory of the production equipment, and P(t) is the pressure trajectory of the production equipment.

[0090] In this embodiment, during the preparation of the hydrogen storage alloy, the production system collects key process parameters (temperature, pressure, etc.) of the production equipment through the process monitoring module, which have an important influence on the resistance to poisoning performance of the hydrogen storage alloy. The process monitoring module continuously records the changes of these process parameters and stores them in association with the final resistance to poisoning performance of the hydrogen storage alloy, forming a large number of time trajectories of historical process parameters.

[0091] The resistance to poisoning performance is defined as the hydrogen absorption and desorption cycle efficiency y. Through machine learning method, the historical process parameters are analyzed offline to establish a nonlinear relationship y = f(X(t)) between the hydrogen absorption and desorption cycle efficiency (resistance to poisoning performance index) y and the time trajectory X(t) = [T(t), P(t)] of the historical process parameters (such as temperature, pressure, etc.). T Wherein T(t) and P(t) represent the temperature trajectory and the pressure trajectory, respectively. This model can predict the resistance to poisoning performance of the hydrogen storage alloy under different process conditions.

[0092] On this basis, the historical process parameters are analyzed by using machine learning algorithm to train a nonlinear model between the time trajectory of the temperature, pressure and other process parameters and the resistance to poisoning performance. The nonlinear model is defined as y = f(X(t)) as the performance prediction model.

[0093] In this embodiment, the performance prediction model can accurately predict the contribution of different process parameters to the resistance to poisoning performance of the produced hydrogen storage alloy by learning the influence of different combinations of process parameters on the resistance to poisoning performance index. The performance prediction model is the basis of process optimization and is used to predict the change of the resistance to poisoning performance of the hydrogen storage alloy under different process parameters.

[0094] In some embodiments, the uniformity function comprises:

[0095]

[0096] Wherein F is the uniformity function representing the variance of the resistance to poisoning performance index of the hydrogen storage alloy produced by the plurality of production equipment, N is the number of production equipment in the production system, y i is the resistance to poisoning performance index of the hydrogen storage alloy produced by the i-th production equipment, is the average value of the resistance to poisoning performance index of the hydrogen storage alloy produced by the N production equipment.

[0097] Where F is smaller means better uniformity.

[0098] In this embodiment, the objective of the upper decision controller is to ensure the uniformity of the resistance to poisoning performance of the hydrogen storage alloy produced by each production equipment on the macro time scale of the whole production process of the hydrogen storage alloy.

[0099] To ensure the consistency of production, the objective of the upper decision controller is to minimize the variance of the resistance to poisoning performance index, i.e.

[0100]

[0101] Where y i is the resistance to poisoning performance index, i.e. hydrogen absorption and desorption cycle efficiency, of the hydrogen storage alloy produced by the i-th production equipment; is the average of the hydrogen absorption and desorption cycle efficiency of the hydrogen storage alloy produced by all production equipment. F represents the variance of the resistance to poisoning performance of the hydrogen storage alloy produced by all production equipment. T i (t) and P i (t) represent the temperature and pressure of the production equipment i at time t, respectively. T max , T min , P max and P min represent the upper and lower limits of T i (t) and P i (t), respectively.

[0102] In the optimization process, the upper decision controller will optimize the uniformity of y i by adjusting the time trajectory X i of the process parameters of each production equipment, so as to make it as close to 0 as possible.

[0103] The nonlinear model (performance prediction model) y = f(X(t)) established by machine learning can associate the time trajectory X i (t) of the process parameters with the resistance to poisoning performance y i .

[0104] Therefore, the variance function can be rewritten as a function of the time trajectory of the process parameters:

[0105]

[0106] In the actual optimization problem, the time trajectory X i (t) of the process parameters needs to satisfy the following constraint conditions:

[0107] The temperature, pressure and other parameters of each production equipment must be within a certain operable range, and the constraint conditions are constructed as follows:

[0108]

[0109] wherein T i (t) and P i (t) represent the temperature trajectory and pressure trajectory of the i-th production equipment at time t, respectively, T max , T min , P max and P min represent the lower and upper bounds of T i (t) and P i (t), respectively.

[0110] In some embodiments, the constructing the upper-level decision controller based on the constraint conditions of the process parameters and minimizing the uniformity function comprises:

[0111]

[0112] wherein F is the uniformity function, N is the number of production equipment in the production system, is the time trajectory of the historical process parameters of the i-th production equipment, X i (t) is the optimal time trajectory of the process parameters of the i-th production equipment at time t, is the historical process parameters of the j-th production equipment, X j (t) is the optimal time trajectory of the process parameters of the j-th production equipment at time t, T i (t) is the temperature trajectory of the i-th production equipment at time t, T min is the lower temperature limit value of the constraint condition, T max is the upper temperature limit value of the constraint condition, P i (t) is the pressure trajectory of the i-th production equipment at time t, P min is the lower pressure limit value of the constraint condition, P max is the upper pressure limit value of the constraint condition.

[0113] based on the historical process parameters collected in real time during the process of preparing hydrogen storage alloy The particle swarm optimization algorithm is used to solve the above optimization problem, and the optimal time trajectory X i (t) (such as temperature, pressure, etc.) of the future process parameters of each production equipment is calculated, so that the variance F of the poison resistance performance is minimized, and the hydrogen storage alloys produced by all production equipment are consistent in poison resistance performance.

[0114] It should be noted that during the production process, the upper-level decision controller is responsible for global optimization, adopts long-period control, and based on the historical process parameters collected during the preparation process and the predicted change of poison resistance performance through the performance prediction model, the optimal time trajectory of the future process parameters is constructed.

[0115] In this embodiment, controlling the multiple production devices based on the optimal time trajectory using a lower-level model predictive controller includes:

[0116] The lower-level model predictive controller analyzes the optimal time trajectory to determine the target process parameters of the multiple production devices at each moment;

[0117] The lower-level model predictive controller adjusts the equipment parameters of the multiple production devices based on the target process parameters.

[0118] Understandably, the lower-level model predictive controller is responsible for short-cycle real-time control of each production device at a micro-timescale to ensure the accurate execution of the time trajectory of process parameters.

[0119] The lower-level model predictive controller adjusts the process parameters based on the optimal time trajectory of the process parameters provided by the upper-level decision controller to cope with possible process fluctuations and external disturbances in the short period of time, and to ensure that the actual operating parameters of each production equipment always follow the optimal time trajectory provided by the upper-level decision controller.

[0120] Specifically, the lower-level model predictive controller performs short-cycle real-time control of each production device within a hydrogen storage alloy preparation cycle, ensuring that the optimal time trajectory of process parameters is accurately executed. The state-space expression of the lower-level model predictive controller is defined as follows:

[0121] X i (t+1)=AX i (t)+Bu i (t)+D (6)

[0122] Y i (t)=EX i (t) (7)

[0123] Among them, X i (t+1) is the optimal time trajectory of the process parameters of the i-th production equipment at time t+1, represented as a state vector, including the temperature trajectory T of production equipment i at time t+1. i (t+1) and pressure trajectory P i (t+1), X i (t) is the optimal time trajectory of the process parameters of the i-th production equipment at time t, represented as a state vector, including the temperature trajectory T of production equipment i at time t. i (t) and pressure trajectory P i (t), u i (t) is the control input of the lower-level model predictive controller to production equipment i at time t, including heating power P. i，h(t) and the vacuum pump rate P i，v (t), Y i (t) is the controlled output, i.e. the temperature T measured at time t by the i-th production device i (t) and the pressure P i (t) is the vector X i (t) = [T i (t), P i (t)] r The coefficient matrices A, B, D and E of the state equation are respectively:

[0124]

[0125] where Δt is the time step; k T represents the decay coefficient of temperature, reflecting the heat loss; m is the mass of the object; c p is the specific heat capacity; k P is the pressure decay coefficient; b P is the vacuum pump efficiency constant; d T and d P are the disturbance terms of temperature and pressure respectively.

[0126] The lower model predictive controller tracks the optimal time trajectory of the process parameters given by the upper decision controller by minimizing the control error, and the MPC tracking problem is described as follows:

[0127]

[0128] where R Y (t+k) is the reference trajectory of temperature and pressure. W Y represents the weight matrix, indicating the weighted coefficients of the output error of temperature and pressure, determining the priority of tracking error; Y(t+k) and X(t+k) represent the state vector and output vector at time t+k respectively.

[0129] X max , X min , u max and u min are respectively:

[0130]

[0131] wherein, and are the upper and lower limits of the heating power P h (t) and the vacuum pump rate P v (t) respectively.

[0132] In this embodiment, the lower-layer model predictive controller predicts short-term changes in process parameters through a state-space model, dynamically adjusts key parameters such as temperature and pressure according to the optimal time trajectory, and compensates for deviations caused by environmental changes or fluctuations in production equipment performance in real time. Through this fine control, the production process is adjusted in real time. The lower-layer model predictive controller can ensure the consistency of process parameters of each production equipment in batch production, and minimize the impact of fluctuations in the production process on the resistance to poisoning performance, thereby overcoming the consistency problem in the prior art and improving the long-term use reliability of the hydrogen storage alloy.

[0133] In some embodiments, after the lower-layer model predictive controller controls the plurality of production equipment based on the optimal time trajectory, the method further comprises:

[0134] Collecting real-time process parameters for the production system;

[0135] Updating the optimal time trajectory based on the real-time process parameters.

[0136] In actual implementation, during the entire preparation process of the hydrogen storage alloy, the process monitoring module continuously collects real-time process parameters, and uses a data feedback mechanism to feed back the real-time process parameters to the upper-layer decision controller to update the time trajectory of the process parameters. This feedback mechanism continuously optimizes the process parameters in future batches, thereby continuously improving the consistency of batch production.

[0137] The lower-layer model predictive controller continuously adjusts according to the optimal time trajectory, while the upper-layer decision controller uses real-time process parameters for periodic global feedback optimization to update the optimal time trajectory and provide a more accurate process optimization scheme in future production batches.

[0138] In this embodiment, the time trajectory of the process parameters can be dynamically adjusted based on the real-time collected process parameters to ensure the consistency of the resistance to poisoning performance.

[0139] As shown in Figure 2 A double-layer controller is constructed based on a double-layer control framework, including an upper-layer decision controller and a lower-layer model predictive controller. Through the synergistic effect of the upper-layer and lower-layer control systems, real-time collection, optimization, and control of key process parameters of the hydrogen storage alloy in production are performed. The production system can achieve multi-scale control from a macroscopic to a microscopic level, improve the consistency of the resistance to poisoning performance of the hydrogen storage alloy produced by different production equipment, improve the stability of batch production, and is suitable for large-scale industrial production.

[0140] The lower-layer model predictive controller includes N model predictive control (MPC) controllers, and each MPC controller corresponds to one production equipment.

[0141] The upper decision controller reduces the process parameter deviation between production equipment by optimizing the time trajectory of process parameters in a long period, ensuring global consistency; the lower model predictive controller compensates for disturbances in the short term by real-time control in a short period, maintaining the accurate execution of process parameters. The combination of the two achieves multi-scale control from macro to micro, ensuring that the poison resistance performance of multi-batch hydrogen storage alloy can meet the design requirements.

[0142] In this embodiment, by optimizing the nonlinear relationship between process parameters (temperature, pressure, etc.) and poison resistance performance, combined with a double-layer control system, the consistency of poison resistance performance in batch production of hydrogen storage alloy is achieved, and the long-term service life and performance stability of the material are improved.

[0143] The upper decision controller is responsible for the optimization of the time trajectory of global process parameters. By using real-time collected historical process parameters such as temperature and pressure, the time trajectory of key process parameters such as temperature and pressure is optimized in a long period to minimize the difference in poison resistance performance between different production equipment, obtain the optimal time trajectory of process parameters, and provide temperature and pressure reference values to the lower model predictive controller, ensuring the consistency of the poison resistance performance of hydrogen storage alloy in mass production;

[0144] The MPC controller in the lower model predictive controller adjusts the heating power and vacuum pump rate of the production equipment to control the temperature and pressure, and performs fine real-time control in a short period. According to the optimal time trajectory of process parameters such as temperature and pressure generated by the upper decision controller, the temperature, pressure and other controllable parameters of each production equipment are dynamically adjusted in real time, and environmental changes and production equipment performance fluctuations are compensated in real time. The state space model predicts the short-term changes of process parameters, so that the process parameters of each production equipment meet the optimal time trajectory, ensuring the stability of the poison resistance performance of hydrogen storage alloy in production. Through the feedback mechanism, the consistency of the poison resistance performance of hydrogen storage alloy in batch production is ensured, the long-term service life and stability of the hydrogen storage alloy are improved, and it is suitable for large-scale industrial applications.

[0145] As shown in Figure 3 , the time trajectory of historical process parameters is collected during the preparation of hydrogen storage alloy in multiple production equipment, and a performance prediction model is established by using machine learning method to establish the nonlinear relationship between process parameters and poison resistance performance;

[0146] Based on the performance prediction model, an upper decision controller is constructed to minimize the difference in poison resistance performance indicators of hydrogen storage alloy produced by the multiple production equipment;

[0147] The upper-level decision controller evaluates the differences between the anti-poisoning performance indicators of the multiple production devices producing the hydrogen storage alloy, and optimizes the time trajectory of the process parameters corresponding to the minimum difference by using an optimization algorithm such as a genetic algorithm or a particle swarm optimization, to obtain the optimal time trajectory of the entire production cycle of the hydrogen storage alloy.

[0148] The lower-level model predictive controller controls the operating state of each production device in the production system according to the process parameters corresponding to each time point in the optimal time trajectory, to affect the process parameters of the production devices and realize the synergistic effect of global optimization and local fine control.

[0149] During the entire preparation process of the hydrogen storage alloy, the process monitoring module continuously collects real-time process parameters, and uses a data feedback mechanism to feed back the real-time process parameters to the upper-level decision controller to update the time trajectory of the process parameters. This feedback mechanism continuously optimizes the process parameters in future batches, thereby continuously improving the consistency of batch production.

[0150] In this embodiment, the consistency of the anti-poisoning performance of the solid-state hydrogen storage alloy in large-scale production is improved by optimizing the process parameters, especially the improvement in the anti-poisoning ability of the hydrogen storage alloy to impurities such as oxygen (O2) and water vapor (H2O). By combining material engineering and automation control technology, the performance stability and consistency of the hydrogen storage alloy in batch production are ensured through an advanced control strategy, which is suitable for batch production of hydrogen energy materials and improves the anti-poisoning performance.

[0151] The control method for the consistency of the anti-poisoning performance in batch preparation of the solid-state hydrogen storage alloy provided in the embodiments of the present application can be executed by a control device for the consistency of the anti-poisoning performance in batch preparation of the solid-state hydrogen storage alloy. In the embodiments of the present application, the control method for the consistency of the anti-poisoning performance in batch preparation of the solid-state hydrogen storage alloy is executed by a control device for the consistency of the anti-poisoning performance in batch preparation of the solid-state hydrogen storage alloy, which is used as an example to illustrate the control device for the consistency of the anti-poisoning performance in batch preparation of the solid-state hydrogen storage alloy provided in the embodiments of the present application.

[0152] The embodiments of the present application also provide a control device for the consistency of the anti-poisoning performance in batch preparation of a solid-state hydrogen storage alloy.

[0153] As shown in Figure 4 The control device for the consistency of the anti-poisoning performance in batch preparation of the solid-state hydrogen storage alloy is applied to a production system of the hydrogen storage alloy, and the production system includes multiple production devices that execute a preparation process of the hydrogen storage alloy. The device includes an acquisition module 410, a first processing module 420, a second processing module 430, and a third processing module 440.

[0154] The acquisition module 410 is configured to acquire a performance prediction model of the production system, where the performance prediction model is constructed based on a time trajectory of historical process parameters of the production equipment and an anti-poisoning performance index of the hydrogen storage alloy.

[0155] The first processing module 420 is configured to construct an upper-layer decision controller based on the performance prediction model, so as to minimize the difference of the anti-poisoning performance indexes of the hydrogen storage alloy produced by the plurality of production equipment.

[0156] The second processing module 430 is configured to optimize the time trajectory of the historical process parameters by using the upper-layer decision controller, so as to obtain an optimal time trajectory of the process parameters of the preparation process.

[0157] The third processing module 440 is configured to control the plurality of production equipment by using a lower-layer model prediction controller based on the optimal time trajectory.

[0158] The control device for consistency of anti-poisoning performance in batch production of solid hydrogen storage alloy provided in the embodiments of the present application can optimize the time trajectory of the historical process parameters by using the upper-layer decision controller constructed based on the performance prediction model, so as to obtain an optimal time trajectory with the lowest difference of the anti-poisoning performance indexes. The lower-layer model prediction controller is used to control each production equipment according to the optimal time trajectory, so as to improve the stability and anti-impurity capability of the hydrogen storage alloy in batch production, ensure the consistency of the anti-poisoning performance indexes in batch production of the hydrogen storage alloy, improve the consistency of the anti-poisoning performance of the solid hydrogen storage alloy, and ensure the uniformity and long-term use performance of the hydrogen storage alloy in production.

[0159] The control device for consistency of anti-poisoning performance in batch production of solid hydrogen storage alloy in the embodiments of the present application can be an electronic device or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices except the terminal. For example, the electronic device can be a mobile phone, a tablet computer, an Ultra-Mobile Personal Computer (UMPC), a netbook, a Personal Computer (PC), or the like, and the embodiments of the present application are not limited thereto.

[0160] The control device for consistency of anti-poisoning performance in batch production of solid hydrogen storage alloy in the embodiments of the present application can be a device with an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, and the embodiments of the present application are not limited thereto.

[0161] The control device for consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy provided by the embodiments of the present application can realize each process of the control method for consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy of the above embodiments, and thus repeated description is omitted here.

[0162] In some embodiments, as shown in Figure 5 The embodiments of the present application also provide an electronic device 500, including a processor 501, a memory 502, and a computer program stored in the memory 502 and capable of running on the processor 501, which realizes each process of the control method for consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy of the above embodiments when the program is executed by the processor 501, and can achieve the same technical effects, and thus repeated description is omitted here.

[0163] It should be noted that the electronic device in the embodiments of the present application includes the mobile electronic device and the non-mobile electronic device described above.

[0164] The embodiments of the present application also provide a non-transitory computer readable storage medium, which stores a computer program, which realizes each process of the control method for consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy of the above embodiments when the computer program is executed by a processor, and can achieve the same technical effects, and thus repeated description is omitted here.

[0165] The processor is the processor in the electronic device in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, etc.

[0166] The embodiments of the present application also provide a computer program product, including a computer program, which realizes the control method for consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy when the computer program is executed by a processor.

[0167] The processor is the processor in the electronic device in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, etc.

[0168] The embodiments of the present application also provide a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, the processor is used to run a program or an instruction, and realizes each process of the control method for consistency of poison resistance in batch preparation of solid-state hydrogen storage alloy of the above embodiments, and can achieve the same technical effects, and thus repeated description is omitted here.

[0169] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-level chip, a system chip, a chip system, or a system-on-chip, etc.

[0170] It should be noted that in this document, the terms "comprise", "comprising", or any other variant thereof are intended to cover a non-exclusive inclusion, such that processes, methods, articles, or apparatuses that comprise a list of elements are not limited to those elements, but can also include other elements not expressly listed, or inherent to such processes, methods, articles, or apparatuses. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element. In addition, it should be pointed out that the scope of the methods and apparatuses in the embodiments of the present application is not limited to the order of performing the functions as shown or discussed, but can also include performing the functions in a substantially simultaneous manner or in reverse order, for example, the described method can be performed in an order different from that described, and various steps can also be added, omitted, or combined. In addition, the features described with reference to certain examples can be combined in other examples.

[0171] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a plurality of instructions for making a terminal (which can be a mobile phone, computer, server, or network equipment, etc.) execute the solid-state hydrogen storage alloy batch preparation method for controlling the consistency of the anti-poisoning performance.

[0172] In the description of the present application, "first feature" and "second feature" can include one or more of the features.

[0173] In the description of the present application, "a plurality of" means two or more.

[0174] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the above-mentioned specific embodiments, the above-mentioned specific embodiments are only illustrative, not restrictive, and those skilled in the art can make many forms under the inspiration of the present application without departing from the scope of the present application and the scope protected by the claims.

[0175] In the description of the application, reference has been made to descriptive terms such as "one embodiment", "some embodiments", "an embodiment", "example", "specific example" or "some examples" etc. Such terminology means that a particular feature, structure, material or characteristic being described is included in at least one embodiment or example of the application. The illustrative appearances of such terminology in various places in the specification does not necessarily refer to the same embodiment or example. Moreover, it is appreciated that the specific features, structures, materials or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0176] Although embodiments of this application have been shown and described, it is to be understood that various modifications, substitutions, combinations, and variations can be made therein without departing from the spirit and scope of the application, which is defined by the appended claims and their equivalents.

Claims

1. A method for controlling the consistency of poison resistance in the batch production of solid-state hydrogen storage alloys, characterized by, The application is applied to a production system of hydrogen storage alloy, the production system comprises a plurality of production devices for performing a preparation process of hydrogen storage alloy, and the method comprises the following steps: An performance prediction model of the production system is acquired, the performance prediction model is constructed based on a time trajectory of historical process parameters of the production device and an anti-poisoning performance index of the production of hydrogen storage alloy; An upper decision controller is constructed based on the performance prediction model, aiming to minimize the difference of the anti-poisoning performance index of the production of hydrogen storage alloy by the plurality of production devices; The time trajectory of the historical process parameters is optimized by the upper decision controller to obtain an optimal time trajectory of process parameters of the preparation process; The plurality of production devices are controlled by a lower model prediction controller based on the optimal time trajectory; The upper decision controller is constructed based on the performance prediction model, aiming to minimize the difference of the anti-poisoning performance index of the production of hydrogen storage alloy by the plurality of production devices, comprising: A uniformity function of the production system is constructed based on the performance prediction model, the uniformity function is used to represent the difference of the anti-poisoning performance index of the plurality of production devices; The uniformity function is minimized based on the constraint condition of the process parameters to construct the upper decision controller; The performance prediction model is: ； Wherein, F is the uniformity function, F represents the variance of the anti-poisoning performance index of the hydrogen storage alloy produced by the plurality of production equipment, N is the number of production equipment in the production system, y i is the first i The anti-poisoning performance index of the hydrogen storage alloy produced by the production equipment, is the average value of the anti-poisoning performance index of the hydrogen storage alloy produced by N production equipment. The time trajectory of the historical process parameters is: ； The uniformity function is minimized based on the constraint condition of the process parameters to construct the upper decision controller, comprising: ； wherein, an index of resistance to poisoning of the hydrogen storage alloy produced by the production plant, a time trajectory of a process parameter of the production plant, a temperature trajectory of the production plant, a pressure trajectory of the production plant.

2. The method according to claim 1, wherein the method is characterized by, The optimal time trajectory is analyzed by the lower model prediction controller to determine the target process parameters of the plurality of production devices at each time; ； ； wherein F is the uniformity function, N is the number of production equipment in the production system, is the historical process parameter of the i-th production equipment, is the time trajectory of the process parameter of the i-th production equipment at time t, is the historical process parameter of the j-th production equipment, is the time trajectory of the process parameter of the j-th production equipment at time t, is the temperature trajectory of the i-th production equipment at time t, is the lower limit value of temperature of the constraint condition, is the upper limit value of temperature of the constraint condition, is the pressure trajectory of the i-th production equipment at time t, is the lower limit value of pressure of the constraint condition, is the upper limit value of pressure of the constraint condition.

3. The method according to claim 1, wherein the method is characterized by, The device parameters of the plurality of production devices are adjusted by the lower model prediction controller according to the target process parameters. After the plurality of production devices are controlled by the lower model prediction controller based on the optimal time trajectory, the method further comprises: Real-time process parameters are collected for the production system; 4. The method according to any one of claims 1 to 3, wherein the method is characterized by, The optimal time trajectory is updated by the real-time process parameters. The application is applied to a production system of hydrogen storage alloy, the production system comprises a plurality of production devices for performing a preparation process of hydrogen storage alloy, and the device comprises: An acquisition module is configured to acquire an performance prediction model of the production system, the performance prediction model is constructed based on a time trajectory of historical process parameters of the production device and an anti-poisoning performance index of the production of hydrogen storage alloy; 5. A control device for the consistency of anti-poisoning performance in the batch preparation of solid hydrogen storage alloys, characterized in that, A first processing module is configured to construct an upper decision controller based on the performance prediction model, aiming to minimize the difference of the anti-poisoning performance index of the production of hydrogen storage alloy by the plurality of production devices; A second processing module is configured to optimize the time trajectory of the historical process parameters by the upper decision controller to obtain an optimal time trajectory of process parameters of the preparation process; A third processing module is configured to control the plurality of production devices by a lower model prediction controller based on the optimal time trajectory. ​ ​ The performance prediction model is used to construct an upper-level decision controller, which aims to minimize the difference of the anti-poisoning performance indexes of the hydrogen storage alloy produced by the plurality of production devices, including: Based on the performance prediction model, a uniformity function of the production system is constructed, which is used to represent the difference of the anti-poisoning performance indexes of the plurality of production devices; Based on the constraint conditions of the process parameters, the minimum value of the uniformity function is calculated to construct the upper-level decision controller; The uniformity function includes: ； Wherein, F is the uniformity function, F represents the variance of the anti-poisoning performance index of the hydrogen storage alloy produced by the plurality of production equipment, N is the number of production equipment in the production system, y i is the first i The anti-poisoning performance index of the hydrogen storage alloy produced by the production equipment in the kitchen, is the average value of the anti-poisoning performance index of the hydrogen storage alloy produced by N production equipment. The performance prediction model is: ； The time trajectory of the historical process parameters is: ； wherein, an index of resistance to poisoning of the hydrogen storage alloy produced by the production plant, a time trajectory of a process parameter of the production plant, a temperature trajectory of the production plant, a pressure trajectory of the production plant.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the control method for consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy according to any one of claims 1-4.

7. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the control method for consistency of anti-poisoning performance in batch preparation of solid-state hydrogen storage alloy according to any one of claims 1-4.

Images