Lithium hydroxide production environment assessment method and system

Abstract

The embodiments of the present disclosure disclose a lithium hydroxide production environment evaluation method and system. The evaluation method comprises: establishing a basic neural network model; constructing an adaptive curve grey wolf optimization algorithm; optimizing and training the basic neural network model based on the adaptive curve grey wolf optimization algorithm to obtain a trained basic neural network model; and obtaining lithium hydroxide production environment evaluation information based on lithium hydroxide production environment information and the trained basic neural network model. The method can improve the efficiency and accuracy of lithium hydroxide production environment evaluation, and provides strong support for environmental protection and sustainable development.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of environmental risk assessment, in particular to a lithium hydroxide production environment assessment method and system. BACKGROUND

[0002] In recent years, with the increasing demand for lithium hydroxide, people have begun to pay more attention to the impact of its production process on the environment. Traditional environmental impact assessment methods usually rely on experimental data and empirical judgments, and these methods are inefficient and have limited accuracy.

[0003] To solve this problem, neural networks and grey wolf optimization (GWO) algorithms are introduced in the prior art to assess environmental impact, however, the standard GWO algorithm is prone to local optimization when dealing with complex problems, which affects its optimization effect; at the same time, the neural network model has the problems of low training efficiency and insufficient generalization ability, which leads to long training time of the neural network model in practical application, i.e. low evaluation efficiency, and cannot guarantee the accuracy of the evaluation results. SUMMARY

[0004] Therefore, the embodiments of the present disclosure provide a lithium hydroxide production environment assessment method and system, which can solve the problems of low environmental assessment efficiency and poor accuracy in the prior art.

[0005] In a first aspect, the embodiments of the present disclosure provide a lithium hydroxide production environment assessment method, comprising:

[0006] establishing a basic neural network model;

[0007] constructing an adaptive curve grey wolf optimization algorithm;

[0008] optimizing and training the basic neural network model based on the adaptive curve grey wolf optimization algorithm to obtain a trained basic neural network model;

[0009] obtaining lithium hydroxide production environment assessment information based on lithium hydroxide production environment information and the trained basic neural network model.

[0010] Optionally, the establishing a basic neural network model comprises:

[0011] determining a network structure; the network structure comprises the number of neural network layers and the number of neurons in each layer;

[0012] preprocessing input data;

[0013] determining a loss function and an evaluation index.

[0014] Optionally, the input data is data related to lithium hydroxide production; the preprocessing includes normalization and denoising.

[0015] The loss function comprises a mean square error function.

[0016] The evaluation index comprises accuracy.

[0017] Optionally, the adaptive curve grey wolf optimization algorithm comprises:

[0018] determining an initial grey wolf optimization algorithm;

[0019] based on a preset strategy, adaptively adjusting the initial grey wolf optimization algorithm to obtain the adaptive curve grey wolf optimization algorithm.

[0020] Optionally, the preset strategy comprises a first strategy and a second strategy:

[0021] The first strategy comprises introducing a randomly generated new individual into the initial grey wolf optimization algorithm.

[0022] The second strategy comprises dividing the population after introducing the new individual into several subgroups for searching in different regions.

[0023] Optionally, the introduction of the randomly generated new individual comprises:

[0024] determining a strategy for randomly generating a new individual; the strategy comprises an initialization individual strategy and an introduction frequency strategy;

[0025] fusing the new individual into the population of the initial grey wolf optimization algorithm.

[0026] Optionally, the dividing of the population after introducing the new individual into several subgroups for searching in different regions comprises:

[0027] dividing the entire population into several subgroups according to the characteristics of the grey wolf individual;

[0028] Alternatively, the entire population is divided into several subgroups based on different search strategies;

[0029] The characteristics of the grey wolf individual comprise position or fitness.

[0030] The search strategy comprises an exploration strategy and a development strategy.

[0031] Optionally, the adaptive curve grey wolf optimization algorithm further comprises fusing a sigmoid function optimization search strategy.

[0032] Optionally, the optimization and training of the basic neural network model based on the adaptive curve grey wolf optimization algorithm to obtain the trained basic neural network model comprises:

[0033] encoding the weight and bias parameters of the basic neural network model as the position of the grey wolf.

[0034] In each iteration of the round-by-round iteration, the position of each grey wolf is updated according to the adaptive curve grey wolf optimization algorithm;

[0035] According to the actual iteration progress, the proportion of exploring new areas and refining the current optimal solution is dynamically adjusted;

[0036] For the current position of each grey wolf, evaluation is performed through a preset fitness function, and after each iteration, the position of the grey wolf with the highest fitness is selected as the new parameters of the neural network;

[0037] When a preset number of iterations is reached or the fitness meets a preset threshold, the optimization process is ended, and the trained basic neural network model is obtained.

[0038] In a second aspect, the embodiments of the present disclosure further provide a lithium hydroxide production environment evaluation system, comprising:

[0039] A first construction module configured to establish a basic neural network model;

[0040] A second construction module configured to construct an adaptive curve grey wolf optimization algorithm;

[0041] An optimization module configured to optimize and train the basic neural network model based on the adaptive curve grey wolf optimization algorithm, and obtain a trained basic neural network model;

[0042] An output module configured to obtain lithium hydroxide production environment evaluation information based on lithium hydroxide production environment information and the trained basic neural network model.

[0043] In a third aspect, the embodiments of the present disclosure further provide an electronic device, which adopts the following technical solution:

[0044] The electronic device comprises:

[0045] at least one processor; and

[0046] a memory in communication with the at least one processor; wherein

[0047] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the lithium hydroxide production environment evaluation method described above.

[0048] In a fourth aspect, the embodiments of the present disclosure further provide a computer readable storage medium storing computer instructions for causing a computer to perform the lithium hydroxide production environment evaluation method described above.

[0049] The lithium hydroxide production environment evaluation method disclosed in the application can accurately analyze and process complex data required for environmental impact evaluation by establishing a basic neural network model, thereby improving the accuracy and reliability of the evaluation; the self-adaptive curve grey wolf optimization algorithm can solve the problem that the standard GWO algorithm is prone to local optimization, and can effectively improve the efficiency of the optimization process and the quality of the results; the self-adaptive curve grey wolf optimization algorithm can better adjust and optimize the parameters of the neural network model, thereby improving the training effect and generalization ability; based on the lithium hydroxide production environment information and the trained basic neural network model, accurate lithium hydroxide production environment evaluation information can be obtained, which can help decision makers and relevant stakeholders better understand and evaluate the impact of the lithium hydroxide production process on the environment, so as to take corresponding measures for environmental protection and sustainable development.

[0050] The technical solution aims to improve the accuracy and efficiency of environmental impact evaluation in the lithium hydroxide production process. Traditional environmental impact evaluation methods have the problems of low efficiency and limited accuracy. Therefore, we propose to integrate the adaptive curve grey wolf optimization (ACGWO) algorithm into the neural network back propagation method to optimize the learning process of the neural network and improve the generalization ability and accuracy of the model. Compared with the traditional grey wolf optimization algorithm, the ACGWO algorithm enhances the adaptive ability and population diversity of the algorithm by introducing the sigmoid function, effectively avoiding the problem of premature convergence.

[0051] The above description is only a summary of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, the contents of the specification can be implemented, and in order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and those skilled in the art can obtain other drawings according to these drawings without creating any creative labor.

[0053] Figure 1 The flowchart of the lithium hydroxide production environment evaluation method provided by the embodiments of the present disclosure is shown.

[0054] Figure 2 The flowchart of the method for establishing a basic neural network model provided by the embodiments of the present disclosure is shown.

[0055] Figure 3 A flowchart of a construction method of an adaptive curve grey wolf optimization algorithm provided by an embodiment of the present disclosure is shown.

[0056] Figure 4 A principle block diagram of a lithium hydroxide production environment evaluation system provided by an embodiment of the present disclosure is shown.

[0057] Figure 5 A structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0058] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0059] It should be apparent that the following describes embodiments of this disclosure by way of specific examples, and that one of ordinary skill in the art will readily understand other advantages and benefits of the present disclosure from this disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, and are not all the embodiments. The present disclosure can also be implemented or applied by other different specific embodiments, and the details in the specification can be modified or changed based on different views and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by one of ordinary skill in the art without creative labor are within the scope of protection of the present disclosure.

[0060] It should be noted that the various aspects of the embodiments described below are within the scope of the appended claims. It should be apparent that the aspects described herein can be embodied in a wide variety of forms and that any specific structure and / or function described herein is merely illustrative. Based on the teachings herein one skilled in the art should appreciate that an aspect described herein can be implemented independently of any other aspects and that two or more of these aspects can be combined in various ways. For example, an apparatus can be implemented or a method can be practiced using any number of the aspects described herein. In addition, such an apparatus can be implemented or such a method can be practiced using other structure and / or functionality in addition to or other than one or more of the aspects described herein.

[0061] It should also be noted that the drawings included in the following embodiments are only to illustrate the basic concept of the present disclosure in a schematic manner, and only show the components related to the present disclosure in the drawings, not drawn according to the number, shape and size of the components when actually implemented, and the shape, number and proportion of each component when actually implemented can be arbitrarily changed, and the layout pattern of the components can also be more complex.

[0062] Also in the following description, specific details are provided to facilitate thorough understanding of examples. However, one skilled in the relevant art will appreciate that the described aspects can be practiced without these specific details.

[0063] Referring to Figure 1 The first aspect of the present application discloses a lithium hydroxide production environment evaluation method, which comprises the following steps:

[0064] S100, a basic neural network model is established.

[0065] S200, an adaptive curve grey wolf optimization algorithm is constructed.

[0066] S300, the basic neural network model is optimized and trained based on the adaptive curve grey wolf optimization algorithm, and a trained basic neural network model is obtained.

[0067] S400, lithium hydroxide production environment evaluation information is obtained based on lithium hydroxide production environment information and the trained basic neural network model.

[0068] The lithium hydroxide production environment evaluation method disclosed in the present application can accurately analyze and process complex data required for environmental impact evaluation by establishing a basic neural network model, which can improve the accuracy and reliability of the evaluation. By constructing an adaptive curve grey wolf optimization algorithm, the problem of the standard GWO algorithm easily falling into local optimum can be solved, and the efficiency of the optimization process and the quality of the results can be effectively improved. By using the adaptive curve grey wolf optimization algorithm to optimize and train the basic neural network model, the parameters of the neural network model can be better adjusted and optimized, thereby improving the training effect and generalization ability. Based on the lithium hydroxide production environment information and the trained basic neural network model, accurate lithium hydroxide production environment evaluation information can be obtained, which can help decision makers and relevant stakeholders better understand and evaluate the impact of the lithium hydroxide production process on the environment, so as to take appropriate measures for environmental protection and sustainable development.

[0069] Referring to Figure 2 The method for establishing the basic neural network model comprises the following steps:

[0070] S110, the network structure is determined; the network structure includes the number of neural network layers and the number of neurons in each layer. By reasonably determining the network structure, the model's expression ability and performance can be improved to adapt to specific lithium hydroxide production environment evaluation tasks.

[0071] S120, the input data is preprocessed.

[0072] In this embodiment, the input data is related to the production of lithium hydroxide; preprocessing includes normalization, denoising and other processing methods to ensure the accuracy and consistency of the data. Through preprocessing, the noise and redundant information of the data can be reduced, and the training effect and stability of the model can be improved.

[0073] S130, determine the loss function and evaluation index.

[0074] In this embodiment, the loss function includes a mean square error function; the evaluation index includes accuracy.

[0075] In this embodiment, the mean square error function is used as the loss function, which can effectively measure the error between the model prediction result and the actual value. At the same time, the accuracy as the evaluation index can effectively evaluate the performance and accuracy of the model; by determining the loss function and the evaluation index, the model can be effectively trained and evaluated to optimize the prediction result of the model.

[0076] Further, in this embodiment, the network structure is preferably a multi-layer perceptron (MLP), which is a feedforward artificial neural network model composed of multiple layers of nodes, each layer is fully connected to the next layer. In MLP, each node corresponds to a neuron containing a nonlinear activation function. MLP contains at least three layers of nodes: input layer, one or more hidden layers, and output layer; due to the presence of one or more hidden layers, MLP can learn nonlinear models of data.

[0077] Specifically, the number of nodes in the input layer depends on the dimensionality of the feature data. For example, if our dataset is a set of 64 features, the input layer will have 64 neurons.

[0078] The hidden layer is the core of MLP and can contain one or more layers. In this example, we use two hidden layers, each with 32 neurons, which can process complex patterns of input data through nonlinear activation functions such as ReLU or Sigmoid.

[0079] The number of nodes in the output layer depends on the desired output. For example, in a classification problem, if we predict 10 different classes, the output layer will have 10 neurons, each representing a class.

[0080] Structural diagram: input layer (64 neurons) -> hidden layer 1 (32 neurons) -> hidden layer 2 (32 neurons) -> output layer (10 neurons).

[0081] All neurons between each layer are fully connected. This means that each neuron in the input layer is connected to all neurons of the hidden layer 1, each neuron of the hidden layer 1 is connected to all neurons of the hidden layer 2, and so on, until the output layer.

[0082] With reference to Figure 3 The method for constructing the adaptive curve grey wolf optimization algorithm comprises the following steps:

[0083] In S210, an initial grey wolf optimization algorithm is determined.

[0084] In S220, the initial grey wolf optimization algorithm is adaptively adjusted based on a preset strategy to obtain an adaptive curve grey wolf optimization algorithm.

[0085] The method constructs a new algorithm, which has better optimization ability and robustness. Specifically, it can dynamically adjust according to task requirements, which helps to overcome the problem that the standard grey wolf optimization algorithm is prone to fall into local optimum when dealing with complex problems, thereby improving the optimization effect and the quality of the results. Such a method can better adapt to complex optimization problems in lithium hydroxide production environment evaluation and provide more reliable support for practical applications.

[0086] Grey Wolf Optimizer (GWO) is a swarm intelligence optimization algorithm that simulates the social hierarchy and hunting behavior of grey wolves. In the GWO algorithm, the grey wolf population is divided into four roles: Alpha (leader), Beta (deputy leader), Delta (adviser), and Omega (Omega). The entire optimization process simulates the social structure and hunting strategy of grey wolves, including tracking, surrounding, and attacking prey. Each wolf in the algorithm represents a potential solution, and the position of the prey represents the optimal solution.

[0087] The adaptive curve grey wolf optimization algorithm constructed through this embodiment can effectively explore the solution space and has strong global search ability by simulating the social hierarchy and hunting strategy of grey wolves. When dealing with complex multi-peak problems, it will not converge to a local optimal solution too early. The population diversity will not decrease with the iteration, which will not affect the search ability of the algorithm, and it also has adaptability to specific problems.

[0088] Further, the adaptive curve grey wolf optimization algorithm includes adaptive parameter adjustment, which dynamically adjusts key parameters in the algorithm, such as the position update coefficient of the grey wolf, to achieve different exploration and exploitation capabilities at different stages of the algorithm. In the early stage of search, the exploration ability is increased to avoid premature convergence; in the later stage of search, the exploitation ability is improved to fine-tune the solution.

[0089] Specifically, the preset strategy includes a first strategy and a second strategy: the first strategy includes introducing a randomly generated new individual in the initial grey wolf optimization algorithm; and the second strategy includes dividing the population after introducing the new individual into a plurality of subpopulations to search in different regions.

[0090] Through the preset strategy, the limitations in the standard GWO algorithm, such as premature convergence and insufficient population diversity, can be overcome; specifically, by introducing a randomly generated new individual, the diversity of the population will not decrease as the number of iterations increases, so the search process will not be trapped in a local region, and a wider solution space can be effectively explored.

[0091] The method for introducing the new individual includes the following steps:

[0092] A10, determining a strategy for randomly generating a new individual.

[0093] The strategy includes an initialization individual strategy and an introduction frequency strategy.

[0094] A20, fusing the new individual into the population of the initial grey wolf optimization algorithm. The specific fusion method includes random insertion, replacing the worst individual, etc. After fusing the new individual, the size of the population will increase, thereby increasing the exploration ability and diversity of the search space.

[0095] Further, if necessary, the population size can be adjusted to maintain effective management of computing resources.

[0096] Introducing a new individual can provide more search space and diversity, and help avoid getting stuck in a local optimum. By introducing a randomly generated new individual, the algorithm can be more exploratory, increasing the search probability for the global optimal solution, which can improve the effectiveness and performance of the optimization algorithm and provide more abundant solutions for lithium hydroxide production environment evaluation and other problems.

[0097] The initialization individual strategy includes generating a certain number of random individuals at the beginning of each iteration. The positions of these individuals (representing a point in the solution space) can be randomly determined in the entire solution space by a random number generator.

[0098] The introduction frequency strategy includes setting an appropriate frequency to determine how often to introduce a new random individual; the frequency can be based on the number of iterations or other performance indicators.

[0099] Further, the population after introducing the new individual is divided into a plurality of subpopulations to search in different regions, specifically including:

[0100] The entire population is divided into a plurality of subpopulations according to the characteristics of the grey wolf individuals;

[0101] Or, the entire population is divided into several sub-populations based on different search strategies;

[0102] The grey wolf individual features include position or fitness;

[0103] The search strategies include exploration strategy and exploitation strategy.

[0104] In this embodiment, by dividing the population into multiple sub-populations and distributing them in different areas for searching, the diversity of the search can be enhanced, each sub-population can explore in its area to better explore the problem solution space and reduce the possibility of falling into a local optimal solution; each sub-population can search according to the grey wolf individual features or different search strategies. Dividing the sub-population according to the grey wolf individual features can make the individual search in the most suitable position, and dividing the sub-population based on different search strategies can use multiple search methods at the same time to speed up the search convergence speed; by dividing the entire population into several sub-populations and making the sub-populations search in different areas, the global search ability of the algorithm can be increased, each sub-population can use the exploration strategy to constantly find new solutions, and further optimize the obtained solutions through the exploitation strategy. This can effectively improve the global search potential of the algorithm and help to find better solutions.

[0105] Therefore, dividing the population after introducing new individuals into several sub-populations for searching can better utilize the diversity and search ability of the population and improve the effect of the grey wolf optimization algorithm. Such grouping search strategy has great potential and application prospect in the optimization of complex problems such as lithium hydroxide production environment evaluation.

[0106] Searching in different areas includes allocating search areas and independent running, wherein allocating search areas allocates different search areas or different search tasks to each sub-population; independent running lets each sub-population independently run in its designated area to execute the search task.

[0107] Further, it also includes information exchange and fusion, specifically including: regular exchange of information, i.e. regularly exchanging information between sub-populations, such as sharing the best solution found or search experience; final solution fusion, at the end of the algorithm, collecting the optimal solutions from all sub-populations and fusing these solutions through a certain strategy to obtain the final optimal solution.

[0108] Through these strategies, the population diversity of the ACGWO algorithm (adaptive curve grey wolf optimization algorithm) can be significantly increased, the exploration ability and adaptability of the algorithm can be improved, and thus the overall optimization performance can be improved.

[0109] In this application, the adaptive curve grey wolf optimization algorithm further includes: fusing a sigmoid function optimization search strategy.

[0110] Application of Sigmoid Function: Utilize the characteristics of the sigmoid function to adjust the search behavior of the gray wolves. The sigmoid function can map any value within the search space to a fixed range (e.g., 0 to 1), thereby controlling the search step size and direction, increasing the flexibility and adaptability of the search process.

[0111] Dynamic Weight Distribution: Dynamically adjust the contribution weight of each gray wolf to the final solution through the sigmoid function, enabling the algorithm to more effectively balance the exploration and exploitation process.

[0112] To dynamically adjust the contribution weight of each gray wolf to the final solution through the sigmoid function, effectively balancing the exploration and exploitation process, we can adopt the following steps:

[0113] B10, Understand the characteristics of the sigmoid function: The sigmoid function is a typical logistic function, defined as: It can map input values to the range of (0, 1).

[0114] Function characteristics: When the input value is very small or very large, the function output approaches 0 or 1. This means that under extreme conditions, the function output changes little, which helps stabilize the exploration and exploitation behavior of the algorithm.

[0115] B20, Design weight adjustment strategy.

[0116] Gray wolf position and weight: In the gray wolf optimization algorithm, the position of each gray wolf can be regarded as a potential solution. We can process the position of each gray wolf with the Sigmoid function to obtain a weight value between 0 and 1.

[0117] Dynamic weight distribution: According to the output of the Sigmoid function, dynamically adjust the contribution of each gray wolf to the final solution. The higher the weight, the greater the impact on the final solution.

[0118] B30, Balance exploration and exploitation.

[0119] Exploration phase: In the early stages of the algorithm, to promote more extensive search, increase the range of values input into the Sigmoid function, so that the weights of most gray wolves are more uniform, thereby promoting exploration.

[0120] Exploitation phase: As the algorithm progresses, gradually reduce the range of input values, so that the weights are more concentrated on some well-performing gray wolves, which helps fine-tune the solution and promote exploitation.

[0121] B40, Implement the weight adjustment mechanism.

[0122] Weight update formula: Define an update formula, for example, the weight ω i = σ(f(x i )), where x i is the position of the i-th gray wolf, f(x i ) is a function adjusted according to the number of iterations, used to control the input range of the Sigmoid function.

[0123] Iterative update: In each iteration, update the weight of each gray wolf according to the current iteration number and the position of the gray wolf.

[0124] B50, test and evaluation.

[0125] Test algorithm: Test the ACGWO algorithm using the Sigmoid function to adjust the weight on different optimization problems.

[0126] Performance evaluation: Compare the performance of the algorithm before and after adjustment in terms of exploration and development ability, to ensure that the new strategy can effectively balance the two aspects.

[0127] Through the above steps, the ACGWO algorithm can adjust the weight of the gray wolf in different stages to adapt to different exploration and development needs, thereby improving the overall optimization efficiency and effect.

[0128] Further, the present application also includes testing and verification, specifically, a series of experiments are designed to test the effectiveness of the adaptive strategy, these experiments can be carried out on different types of optimization problems, such as multi-peak function optimization, constrained optimization problem, etc.; compare the performance of the adaptive strategy on various problems and the performance of the standard GWO algorithm, the indicators include the quality of the solution, the convergence speed, the stability of the algorithm, etc.

[0129] Through these steps, we can design a strengthened version of the GWO algorithm that can maintain the original advantages and overcome its limitations, and this adaptive strategy is expected to significantly improve the performance of the algorithm in complex optimization problems.

[0130] Further, based on the adaptive curve gray wolf optimization algorithm, the basic neural network model is optimized and trained to obtain a trained basic neural network model, specifically including:

[0131] S410, encode the weight and bias parameters of the basic neural network model as the position of the gray wolf.

[0132] In this step, the weight and bias parameters of the neural network model are encoded as position information in the gray wolf optimization algorithm, so that each gray wolf represents a solution in the parameter space of the neural network model.

[0133] Before the iteration begins, set the number of iterations: determine the total number of iterations of the optimization loop. This number should be based on the complexity of the problem and the computing resources. Set the initial population: initialize the grey wolf population before the optimization begins; each grey wolf represents a set of parameters for the neural network.

[0134] S420, in each iteration of the round iteration, update the position of each grey wolf according to the adaptive curve grey wolf optimization algorithm.

[0135] Update its position information in each iteration to achieve global search and optimization of the neural network model parameter space.

[0136] S430, according to the actual iteration progress, dynamically adjust the proportion of exploring new areas and refining the current optimal solution.

[0137] According to the actual optimization process, dynamically adjust the exploration and development ratio of the algorithm to balance global exploration and local optimization.

[0138] S440, for the current position of each grey wolf, evaluate it through the preset fitness function, and after each iteration, select the position of the grey wolf with the highest fitness as the new parameters of the neural network.

[0139] Evaluate each grey wolf position through the fitness function, and select the global optimal position to update the neural network model parameters.

[0140] S450, when the preset number of iterations is reached or the fitness meets the preset threshold, end the optimization process, that is, obtain the trained basic neural network model. In this embodiment, the adaptive curve grey wolf optimization algorithm can realize global search, which helps to find the global optimal solution in the neural network model parameter space and improve the generalization ability and prediction performance of the model; the diversity and robustness of the grey wolf optimization algorithm help to avoid falling into local optimal solution and improve the robustness of the neural network model; by dynamically adjusting the exploration and development ratio, the algorithm can adjust the search strategy in real time according to the complexity of the problem and the optimization progress, better adapt to different optimization tasks; the grey wolf optimization algorithm can automatically adjust the parameters of the neural network model, reducing the complexity of manual parameter tuning.

[0141] Therefore, the combination of adaptive curve grey wolf optimization algorithm for neural network model training can fully exert the advantages of the algorithm, improve the performance of the model, and obtain better application effect in the field of lithium hydroxide production environment evaluation.

[0142] Further, it also includes iteration update, specifically, after completing all steps of the current iteration, end the current loop.

[0143] Enter the next iteration: if the predetermined number of iterations has not been reached or the early termination condition is met, continue the next round of iteration.

[0144] Through the above steps, the parameters of the neural network will be effectively optimized under the guidance of the ACGWO algorithm to improve the performance of the model in the environmental impact assessment of lithium hydroxide production.

[0145] After each iteration, the position of the grey wolf with the highest fitness is selected as the new parameters of the neural network.

[0146] The performance of the neural network during optimization is regularly assessed to monitor the reduction of error and improvement of prediction ability.

[0147] Through this series of steps, the ACGWO algorithm can effectively optimize the parameters of the neural network, improving the training efficiency and accuracy of the model in the environmental impact assessment of lithium hydroxide production.

[0148] Further, cross-validation is also included to assess the generalization ability of the model on different datasets. Through experiments, the performance differences between ACGWO and traditional optimization methods (such as gradient descent) in environmental impact assessment are compared.

[0149] In the embodiments, the optimized model is applied to assess the environmental impact of lithium hydroxide production; the results of the model assessment are analyzed to verify its reliability and effectiveness; and the application prospects and potential value of the model in the actual production environment are explored.

[0150] The following will be described in conjunction with specific embodiments.

[0151] Example 1: Application of ACGWO-optimized neural network in wastewater treatment assessment of lithium hydroxide production

[0152] Step 1: Collect relevant data on wastewater treatment in lithium hydroxide production.

[0153] Step 2: Adjust the parameters of the neural network using the ACGWO optimization algorithm to improve the prediction accuracy of the model on wastewater treatment effectiveness.

[0154] Example 2: Application of ACGWO-optimized neural network in energy consumption assessment of lithium hydroxide production

[0155] Step 1: Collect energy consumption data from the lithium hydroxide production process.

[0156] Step 2: Apply the ACGWO-optimized neural network model to predict and assess energy consumption in the production process.

[0157] Example 3: Application of ACGWO-optimized neural network in environmental pollutant emission assessment of lithium hydroxide production

[0158] Step 1: Collect pollutant emission data from the lithium hydroxide production process.

[0159] Step 2: Accurate assessment of pollutant emissions using the neural network model optimized by ACGWO.

[0160] Referring Figure 4 The second aspect of the present application discloses a lithium hydroxide production environment evaluation system, comprising:

[0161] A first construction module configured to establish a basic neural network model;

[0162] A second construction module configured to construct an adaptive curve grey wolf optimization algorithm;

[0163] An optimization module configured to optimize and train the basic neural network model based on the adaptive curve grey wolf optimization algorithm to obtain a trained basic neural network model;

[0164] An output module configured to obtain lithium hydroxide production environment evaluation information based on lithium hydroxide production environment information and the trained basic neural network model.

[0165] The electronic device according to the embodiments of the present disclosure includes a memory and a processor. The memory is configured to store non-transitory computer readable instructions. Specifically, the memory can include one or more computer program products, which can include various forms of computer readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM), cache memory, and / or the like. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, and / or the like.

[0166] The processor can be a central processing unit (CPU) or other forms of processing units having data processing and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions. In an embodiment of the present disclosure, the processor is configured to execute the computer readable instructions stored in the memory, so that the electronic device performs all or part of the steps of the lithium hydroxide production environment evaluation method according to the embodiments of the present disclosure.

[0167] Those skilled in the art should understand that, in order to solve the technical problem of how to obtain a good user experience effect, the present embodiment can also include well-known structures such as communication bus, interface, etc., which should also be included in the protection scope of the present disclosure.

[0168] As Figure 5 A structural schematic diagram of an electronic device according to an embodiment of the present disclosure is provided. It shows a structural schematic diagram suitable for implementing the electronic device in the embodiments of the present disclosure. Figure 5 The electronic device shown is only an example and should not impose any limitation on the functions and use range of the embodiments of the present disclosure.

[0169] like Figure 5 As shown, an electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) or a program loaded from a storage device into random access memory (RAM). The RAM also stores various programs and data required for the operation of the electronic device. The processor, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0170] Typically, the following devices can be connected to the I / O interface: input devices, such as sensors or visual information acquisition devices; output devices, such as displays; storage devices, such as magnetic tapes or hard drives; and communication devices. Communication devices allow electronic devices to communicate wirelessly or wiredly with other devices (such as edge computing devices) to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0171] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processor, all or part of the steps of the lithium hydroxide production environment assessment method of embodiments of this disclosure are performed.

[0172] For a detailed description of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0173] A computer-readable storage medium according to embodiments of the present disclosure stores non-transitory computer-readable instructions. When these non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the lithium hydroxide production environment assessment methods described in the foregoing embodiments of the present disclosure are performed.

[0174] The aforementioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or portable hard drive), media with built-in rewritable non-volatile memory (e.g., memory card), and media with built-in ROM (e.g., ROM cartridge).

[0175] The detailed description of the embodiments hereinabove with reference to the drawings is merely used to illustrate the basic or important part of the present disclosure. It should not be considered as limitation of the present disclosure. Accordingly, the protection scope of the present disclosure should not be limited by the detailed description hereinabove.

[0176] The above describes the basic principles of the present disclosure in combination with specific embodiments. It should be noted that the advantages, benefits, effects and the like mentioned in the present disclosure are merely examples and are not limiting. These advantages, benefits, effects and the like should not be considered as necessary for each embodiment of the present disclosure. In addition, the specific details of the above disclosure are merely for the purpose of illustration and understanding, and are not limiting. The above details do not limit the present disclosure to be necessarily implemented with the above specific details.

[0177] In the present disclosure, the relationship terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. The block diagrams of the devices, apparatuses, equipment, systems involved in the present disclosure are only illustrative examples and are not intended to require or imply the connection, arrangement, configuration as shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner. The words such as "include", "contain", "have" and the like are open-ended words, which mean "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0178] In addition, as used herein, "or" used in the list of items "at least one of the items" indicates a disjunctive list, such that, for example, a list of "at least one of A, B, or C" means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). In addition, the word "exemplary" does not mean that the described example is preferred or better than other examples.

[0179] It should also be noted that in the systems and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present disclosure.

[0180] Various changes, modifications, and alterations to the techniques described herein can be made without departing from the teachings of the attached claims. Moreover, the scope of the claims should not be limited to the particular aspects described herein, but should be given the broadest interpretation available to them under the law. All patents, patent applications, and publications identified are expressly incorporated herein by reference for the purpose of describing and disclosing, for example, the methodologies described in such publications that might be used in connection with the technology described herein. These publications are provided solely for their disclosure prior to the filing date of the present application. Nothing in this regard should be construed as a representation by the inventor and / or the assignee that the inventors and / or the assignee has made or maintains any dedication to the public of the patentable matter in the publications other than the inventor and / or assignee's own intellectual property. No admission is made that any portion of the patent literature can be prior art. The claims should not be limited to the specific aspects and embodiments described herein but should be given the broadest possible interpretation available to them under the circumstances.

[0181] The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0182] The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. The above description has been presented for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although various example aspects and embodiments have been discussed above, those of skill in the art will recognize certain modifications, permutations, additions, and sub-combinations thereof.

Claims

1. A method for assessing the environmental impact of lithium hydroxide production, characterized in that, include: Establish a basic neural network model; Construct an adaptive curve gray wolf optimization algorithm; The basic neural network model is optimized and trained based on the adaptive curve gray wolf optimization algorithm to obtain the trained basic neural network model. Based on the lithium hydroxide production environment information and the trained basic neural network model, lithium hydroxide production environment assessment information is obtained; the lithium hydroxide production environment information includes one or more of the following: lithium hydroxide production wastewater treatment data, lithium hydroxide production process energy consumption data, and lithium hydroxide production process pollutant emission data; the lithium hydroxide production environment assessment information includes one or more of the following: lithium hydroxide production wastewater treatment effect assessment information, lithium hydroxide production process energy consumption assessment information, and lithium hydroxide production process pollutant emission assessment information. The construction of the adaptive curve gray wolf optimization algorithm includes: determining an initial gray wolf optimization algorithm; and adaptively adjusting the initial gray wolf optimization algorithm based on a preset strategy to obtain the adaptive curve gray wolf optimization algorithm. The preset strategy includes a first strategy and a second strategy: the first strategy includes introducing randomly generated new individuals into the initial gray wolf optimization algorithm; the second strategy includes dividing the population after introducing new individuals into several subgroups for searching in different regions. The optimization training of the basic neural network model based on the adaptive curve gray wolf optimization algorithm to obtain the trained basic neural network model includes: encoding the weights and bias parameters of the basic neural network model as the positions of gray wolves; updating the position of each gray wolf according to the adaptive curve gray wolf optimization algorithm in each iteration; dynamically adjusting the ratio of exploring new regions to refining the current optimal solution according to the actual iteration progress; evaluating the current position of each gray wolf through a preset fitness function, and selecting the gray wolf position with the highest fitness as the new parameter of the neural network after each iteration; and ending the optimization process when the preset number of iterations is reached or the fitness meets a preset threshold, thus obtaining the trained basic neural network model.

2. The method for assessing the environmental impact of lithium hydroxide production according to claim 1, characterized in that, The establishment of the basic neural network model includes: Determine the network structure; the network structure includes the number of neural network layers and the number of neurons in each layer; Preprocess the input data; Determine the loss function and evaluation metrics.

3. The method for assessing the production environment of lithium hydroxide according to claim 2, characterized in that, The input data is data related to lithium hydroxide production; The preprocessing includes normalization and noise reduction; The loss function includes the mean squared error function; The evaluation metrics include accuracy.

4. The method for assessing the environmental impact of lithium hydroxide production according to claim 1, characterized in that, The introduction of randomly generated new individuals includes: Determine a strategy for randomly generating new individuals; the strategy includes an individual initialization strategy and a frequency introduction strategy; The new individuals are then merged into the population of the initial gray wolf optimization algorithm.

5. The method for assessing the environmental impact of lithium hydroxide production according to claim 4, characterized in that, The process of dividing the population after introducing new individuals into several subgroups for searching in different regions includes: The entire population was divided into several subgroups based on the individual characteristics of gray wolves; Alternatively, the entire population can be divided into several subgroups based on different search strategies; The individual characteristics of the gray wolf include location or fitness; The search strategy includes exploration strategy and development strategy.

6. The method for assessing the environmental impact of lithium hydroxide production according to claim 5, characterized in that, The adaptive curve gray wolf optimization algorithm also includes: a search strategy that incorporates the sigmoid function.

7. A lithium hydroxide production environment assessment system, characterized in that, include: The first building module is configured to establish a basic neural network model; The second building module is configured to build the adaptive curve gray wolf optimization algorithm; The optimization module is configured to optimize and train the basic neural network model based on the adaptive curve gray wolf optimization algorithm to obtain the trained basic neural network model. The output module is configured to obtain lithium hydroxide production environment assessment information based on lithium hydroxide production environment information and the trained basic neural network model; the lithium hydroxide production environment information includes one or more of the following: lithium hydroxide production wastewater treatment data, lithium hydroxide production process energy consumption data, and lithium hydroxide production process pollutant emission data; the lithium hydroxide production environment assessment information includes one or more of the following: lithium hydroxide production wastewater treatment effect assessment information, lithium hydroxide production process energy consumption assessment information, and lithium hydroxide production process pollutant emission assessment information. The construction of the adaptive curve gray wolf optimization algorithm includes: determining an initial gray wolf optimization algorithm; and adaptively adjusting the initial gray wolf optimization algorithm based on a preset strategy to obtain the adaptive curve gray wolf optimization algorithm. The preset strategy includes a first strategy and a second strategy: the first strategy includes introducing randomly generated new individuals into the initial gray wolf optimization algorithm; the second strategy includes dividing the population after introducing new individuals into several subgroups for searching in different regions. The optimization training of the basic neural network model based on the adaptive curve gray wolf optimization algorithm to obtain the trained basic neural network model includes: encoding the weights and bias parameters of the basic neural network model as the positions of gray wolves; updating the position of each gray wolf according to the adaptive curve gray wolf optimization algorithm in each iteration; dynamically adjusting the ratio of exploring new regions to refining the current optimal solution according to the actual iteration progress; evaluating the current position of each gray wolf through a preset fitness function, and selecting the gray wolf position with the highest fitness as the new parameter of the neural network after each iteration; and ending the optimization process when the preset number of iterations is reached or the fitness meets a preset threshold, thus obtaining the trained basic neural network model.

Images