Power plant coal stock prediction method and system based on artificial intelligence

Abstract

The invention belongs to the technical field of power plant coal stock prediction, and discloses a power plant coal stock prediction method and system based on artificial intelligence. The method comprises the following steps: constructing an artificial intelligence model based on a cloud data center; acquiring real-time coal stock associated data based on a data acquisition device, and sending the real-time coal stock associated data to a cloud data center; based on the cloud data center, using the coal stock prediction model to predict the coal stock; generating a coal purchasing optimization strategy by using the coal purchasing optimization model; generating a coal purchasing scheme by using the coal purchasing scheme generation model; updating the real-time coal stock associated data; and performing secondary coal stock prediction by using the coal stock prediction model. The problems that in the prior art, manual experience is relied on, the model generalization ability is poor, a dynamic adjustment mechanism is lacked, and a prediction result feedback mechanism is lacked are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power plant coal inventory prediction, and in particular relates to a power plant coal inventory prediction method and system based on artificial intelligence. Background Art

[0002] With the rapid development of my country's economy, the demand for electricity is growing. Thermal power generation is the main form of power generation in my country, and coal is the main fuel for thermal power generation. Its supply and storage are crucial to the stable operation of power plants. Accurately predicting coal inventory is of great significance for power plants to reasonably arrange production plans and reduce inventory costs.

[0003] The existing coal inventory forecasting technology for power plants has the following defects:

[0004] 1) Reliance on manual experience: Traditional coal inventory forecasting methods mainly rely on manual experience, which may lead to deviations and inaccuracies in forecast results, especially in the face of complex and changing market environments and power plant operating conditions;

[0005] 2) Poor model generalization ability: Traditional coal inventory prediction models may perform well on specific data sets, but when faced with new data environments or changes in application scenarios, the model's generalization ability is insufficient and it is difficult to maintain prediction accuracy;

[0006] 3) Lack of dynamic adjustment mechanism: Existing coal inventory forecasting technologies often lack dynamic adjustment mechanisms and cannot respond to market changes and changes in power plant demand in real time, resulting in lag and inadaptability of coal inventory forecasting results;

[0007] 4) Lack of feedback mechanism for forecast results: Existing coal inventory forecasting systems often lack a feedback mechanism for forecast results and are unable to apply forecast results to the optimization of procurement decisions to form a closed-loop intelligent system. Summary of the invention

[0008] In order to solve the problems of existing technologies such as reliance on manual experience, poor model generalization ability, lack of dynamic adjustment mechanism and lack of feedback mechanism for prediction results, the present invention aims to provide a method and system for predicting coal inventory in power plants based on artificial intelligence.

[0009] The technical solution adopted by the present invention is:

[0010] A method for predicting coal inventory in a power plant based on artificial intelligence comprises the following steps:

[0011] Based on the cloud data center, using artificial intelligence algorithms, we build coal inventory prediction models, coal procurement optimization models, and coal procurement plan generation models;

[0012] Based on the data collection device, the real-time coal inventory related data of the current power plant is collected, and the real-time coal inventory related data is sent to the cloud data center;

[0013] Based on the cloud data center, according to the real-time coal inventory related data, the coal inventory prediction model is used to predict the coal inventory and obtain the real-time coal inventory prediction results;

[0014] Based on the cloud data center, according to the real-time coal inventory forecast results, the coal procurement optimization model is used to generate the coal procurement optimization strategy and obtain the real-time coal procurement optimization strategy;

[0015] Based on the cloud data center, according to the real-time coal procurement optimization strategy, the coal procurement plan generation model is used to generate the coal procurement plan and obtain the real-time coal procurement plan;

[0016] Based on the cloud data center, the real-time coal inventory related data is updated according to the real-time coal procurement plan to obtain updated real-time coal inventory related data;

[0017] Based on the cloud data center, according to the updated real-time coal inventory related data, the coal inventory prediction model is used to perform a secondary coal inventory prediction to obtain the updated real-time coal inventory prediction result.

[0018] Furthermore, real-time coal inventory-related data include historical coal purchase volume data, historical coal purchase plans, real-time power plant operation data, real-time climate and environmental data, real-time coal market supply and demand data, real-time alternative energy data, real-time coal inventory data, and real-time power plant transportation data.

[0019] Furthermore, based on the cloud data center, using artificial intelligence algorithms, a coal inventory prediction model, a coal procurement optimization model, and a coal procurement plan generation model are constructed, including the following steps:

[0020] Based on the cloud data center, historical coal stock related data of several historical power plants are collected and preprocessed to obtain several preprocessed historical coal stock related data;

[0021] Performing data dimensionality reduction on a number of pre-processed historical coal stock related data to obtain a principal component set and a number of dimensionality-reduced historical coal stock related data;

[0022] Based on several dimensionality-reduced historical coal stock correlation data, a coal stock prediction model is constructed using a deep learning algorithm, and several historical coal stock prediction results are generated;

[0023] Based on several historical coal inventory forecast results, a reinforcement learning algorithm is used to build a coal procurement optimization model, and several historical coal procurement optimization strategies and several historical coal procurement optimization experiences are generated;

[0024] According to several historical coal procurement optimization strategies, a coal procurement plan generation model is constructed using swarm intelligence optimization algorithm.

[0025] Furthermore, the PCA method is used to perform data dimensionality reduction on a number of pre-processed historical coal stock related data to obtain a principal component set and a number of historical coal stock related data after dimensionality reduction.

[0026] Furthermore, the coal inventory prediction model is constructed based on the RF-Attention-BiLSTM algorithm;

[0027] The coal procurement optimization model is built based on the DQN algorithm;

[0028] The coal procurement plan generation model is built based on the ICPO optimization algorithm.

[0029] Furthermore, based on the cloud data center, according to the real-time coal inventory associated data, using the coal inventory prediction model, the coal inventory prediction is performed to obtain the real-time coal inventory prediction result, including the following steps:

[0030] Based on the cloud data center, the real-time coal inventory related data is preprocessed to obtain the preprocessed real-time coal inventory related data;

[0031] According to the principal component set, the real-time coal inventory related data after preprocessing is subjected to data dimension reduction to obtain the real-time coal inventory related data after dimension reduction;

[0032] The coal inventory prediction model is used to extract M real-time key features of the real-time coal inventory correlation data after dimensionality reduction;

[0033] According to the preset attention weights, M real-time key features are spliced ​​to obtain real-time spliced ​​features;

[0034] According to the real-time splicing characteristics, coal inventory prediction is carried out to obtain real-time coal inventory prediction results.

[0035] Furthermore, based on the cloud data center, according to the real-time coal inventory prediction result, the coal procurement optimization model is used to generate the coal procurement optimization strategy, and the real-time coal procurement optimization strategy is obtained, including the following steps;

[0036] Based on the cloud data center, according to the real-time coal inventory forecast results, the corresponding historical coal procurement optimization experience is retrieved to obtain several matching historical coal procurement optimization experiences;

[0037] According to the real-time coal inventory forecast result and several matching historical coal procurement optimization experiences, the model parameters of the coal procurement optimization model are updated to obtain updated model parameters;

[0038] According to the updated model parameters, the coal procurement optimization model is used to generate a coal procurement optimization strategy to obtain a real-time coal procurement optimization strategy.

[0039] Furthermore, based on the cloud data center, according to the real-time coal procurement optimization strategy, a coal procurement plan generation model is used to generate a coal procurement plan to obtain a real-time coal procurement plan, including the following steps:

[0040] Based on the cloud data center, the coal procurement solution generation model is used to generate initial solutions for the real-time coal procurement optimization strategy, and several real-time initial solutions are obtained;

[0041] According to several real-time initial solutions, the optimal solution is searched in the search space to obtain the real-time optimal solution;

[0042] The real-time optimal solution is analyzed to obtain the real-time coal purchasing plan.

[0043] Further, based on the cloud data center, according to the real-time coal procurement plan, the real-time coal inventory related data is updated to obtain the updated real-time coal inventory related data. The specific method is:

[0044] Based on the cloud data center, the historical coal purchasing plan in the real-time coal inventory associated data is replaced with the real-time coal purchasing plan to obtain updated real-time coal inventory associated data.

[0045] A power plant coal inventory prediction system based on artificial intelligence is used to implement a power plant coal inventory prediction method. The system includes a cloud data center and a plurality of data acquisition devices. The cloud data center is respectively connected to the plurality of data acquisition devices in communication. The plurality of data acquisition devices are arranged in a plurality of power plants in a one-to-one correspondence, and the data acquisition devices are connected to the data servers of the corresponding power plants in communication.

[0046] The cloud data center includes a model building unit, a coal inventory prediction unit, a coal procurement optimization unit, a coal procurement plan generation unit, a data updating unit and a secondary coal inventory prediction unit which are connected in sequence.

[0047] The beneficial effects of the present invention are:

[0048] The present invention discloses a method and system for predicting coal inventory in power plants based on artificial intelligence. The real-time coal inventory correlation data considers the impact of multiple sources of data such as power plant operation, climate environment, original coal procurement plan, coal supply and demand data on the prediction of coal inventory in power plants, so as to provide more comprehensive and accurate input information. The artificial intelligence algorithms of deep learning algorithm, reinforcement learning algorithm and swarm intelligence optimization algorithm are applied to the prediction of coal inventory in power plants, forming an intelligent solution integrating multiple models, which can more comprehensively consider the complexity of coal inventory prediction and procurement decision-making, and provide more accurate and scientific prediction results. The system has the ability of real-time data collection and processing, It can respond to market changes and power plant operating conditions in a timely manner, and improve the timeliness of predictions and decisions. Through the coal inventory prediction model built based on deep learning technology, its powerful feature extraction and pattern recognition capabilities can fully capture the nonlinear relationship between coal procurement volume and a variety of complex factors to achieve high-precision predictions. The coal inventory prediction model based on deep learning technology has a data memory function. When facing new data environments or changes in application scenarios, the model has strong generalization capabilities and can maintain prediction accuracy. The dynamic adjustment mechanism and closed-loop feedback mechanism are adopted to continuously optimize the prediction results and improve the prediction accuracy.

[0049] Other beneficial effects of the present invention will be further described in the specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flowchart of the power plant coal inventory prediction method based on artificial intelligence in the present invention.

[0051] Figure 2 It is a structural block diagram of the power plant coal inventory prediction system based on artificial intelligence in the present invention. DETAILED DESCRIPTION

[0052] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0053] Embodiment 1:

[0054] like Figure 1 As shown, this embodiment provides a method for predicting coal inventory in a power plant based on artificial intelligence, comprising the following steps:

[0055] S1: Based on the cloud data center, using artificial intelligence algorithms, build a coal inventory prediction model, a coal procurement optimization model, and a coal procurement plan generation model, including the following steps:

[0056] S1-1: Based on the cloud data center, historical coal stock related data of several historical power plants are collected and preprocessed to obtain several preprocessed historical coal stock related data;

[0057] The historical coal inventory-related data include the historical coal purchase volume data of the previous purchase cycle, historical coal purchase plans, historical power plant operation data, historical climate and environmental data, historical coal market supply and demand data, historical alternative energy data, historical coal inventory data, and historical power plant transportation data;

[0058] The purchasing trends and cyclical changes in the historical coal purchasing volume data affect the prediction of the next purchasing volume. The historical coal purchasing plan includes the purchasing situation of the previous purchasing cycle, such as purchasing methods, supplier information, transportation plans, etc. The historical power plant operation data includes historical steam pressure and temperature data, historical thermal pipeline efficiency data, historical plant power consumption rate, historical boiler thermal efficiency, historical turbine heat consumption rate and historical unit load and other operating data closely related to the coal consumption of the power plant. The historical climate and environmental data are used to characterize seasonal demand changes. For example, the demand for electricity in summer and winter is different, which affects the consumption of coal stocks, as well as weather factors, such as extreme weather. Events that affect electricity demand and coal purchases. Historical market supply and demand data include historical coal market supply data, i.e., the total amount of coal available in the historical market, which affects purchase strategies, and historical coal market demand data, i.e., the demand for coal in the historical market, which is directly related to purchase volumes. Historical alternative energy data include alternative energy data such as natural gas, oil, and renewable energy, such as purchase volumes and changes in market supply and demand that may affect coal demand. Historical coal inventory data include coal inventory levels at power plants that affect purchase strategies and purchase volumes. Changes in transportation costs from historical power plant transportation data affect purchase decisions. Transportation capacity restrictions may affect coal purchase volumes and timing.

[0059] Through the various indicator data involved in the coal inventory related data, all factors related to coal inventory prediction can be covered, thus improving the comprehensiveness and accuracy of coal inventory prediction;

[0060] For indicator data from different processing systems, preprocessing includes data format conversion, converting heterogeneous indicator data into a data format that can be recognized by the cloud data center, and then cleaning and filtering the data to remove duplicate, erroneous and noisy data to provide data support for subsequent model training;

[0061] S1-2: using the principal component analysis (PCA) method, the data dimension reduction is performed on a number of pre-processed historical coal stock related data to obtain a principal component set and a number of reduced-dimensional historical coal stock related data;

[0062] The principal component set includes coal purchase quantity index, coal purchase plan index, power plant operation index, climate and environment index, market supply and demand index, alternative energy index, coal inventory index and power plant transportation index, which are principal component indexes related to coal inventory forecast. The PCA method transforms the original data into a set of linearly independent representations in each dimension through linear transformation, which is used to remove noise and redundancy in the data, making the data easier to understand and process.

[0063] S1-3: Based on several dimensionality-reduced historical coal stock correlation data, a coal stock prediction model is constructed using a deep learning algorithm, and several historical coal stock prediction results are generated;

[0064] The coal stock prediction model is built based on the Random Forest (RF)-Attention-Bidirectional Long Short-Term Memory (BiLSTM) algorithm, and the coal stock prediction model includes a key feature extraction module built based on the RF algorithm, an attention weight module built based on the Attention mechanism, and a coal stock prediction module built based on the BiLSTM algorithm;

[0065] The key feature extraction module uses the internal Classification And Regression Tree (CART) to screen the key features of the input data and extract several key features related to the data prediction label; the attention weight generation module uses the preset attention weights to realize the splicing of key features and integrate the scattered features; enhance the influence of key features on label prediction, and the coal purchase volume prediction module uses a multi-layer hidden layer structure to explore the potential connection between key features and data prediction labels, train its own network structure through a large number of key features, predict new data features, and realize fast, efficient and accurate prediction of data labels;

[0066] S1-4: Based on several historical coal inventory forecast results, a reinforcement learning algorithm is used to build a coal procurement optimization model, and several historical coal procurement optimization strategies and several historical coal procurement optimization experiences are generated, including the following steps:

[0067] A-1: Generate coal procurement optimization problem as the simulation environment for the Deep Q Network (DQN) algorithm, and build the intelligent agent and experience replay pool;

[0068] A-2: According to each type of coal stock-related state corresponding to the historical coal stock prediction results, the state space of the DQN algorithm is defined, and the parameters of the state space correspond to each coal stock state; the state space includes the current coal stock, predicted coal stock, coal stock consumption rate, coal depletion time prediction and other states;

[0069] A-3: Define the action space of the DQN algorithm according to the actions that need to be output for coal procurement optimization; the action space includes actions such as increasing the purchase volume, setting the purchase cycle, and adding suppliers;

[0070] A-4: Based on the possible impact of each action in the action space, define the reward function of the DQN algorithm to evaluate the quality or impact of the action;

[0071] A-5: Construct the input layer, several hidden layers, and output layer of the deep Q network, connect the input layer to the state space, and connect the output layer to the action space;

[0072] A-6: Based on the state space, action space and reward function, according to several historical coal inventory prediction results, the deep Q network and intelligent agent are optimized and trained to build a coal procurement optimization model, and generate several historical coal procurement optimization experiences;

[0073] A-7: Store some historical coal purchasing optimization experiences into the experience playback pool of the coal purchasing optimization model;

[0074] The coal procurement optimization model is built based on the DQN algorithm, and the coal procurement optimization model includes a deep Q network, an intelligent agent, and an experience replay pool;

[0075] S1-5: Based on several historical coal procurement optimization strategies, a coal procurement plan generation model is constructed using a swarm intelligence optimization algorithm;

[0076] The coal procurement plan generation model is constructed based on the Improved Crested Porcupine Optimizer (ICPO) optimization algorithm, and the coal procurement plan generation model includes an initial solution generation module, an optimal solution search module and a coal procurement plan generation module;

[0077] The initial solution generation module is used to encode the coal procurement plan generation problem according to the historical coal procurement plan in the coal inventory associated data, convert the coal procurement plan into a coding vector, and use the coding vector as the ICPO individual of the ICPO optimization algorithm to initialize and generate several initial solutions. The optimal solution search module is used to set the adaptation function of the ICPO optimization algorithm according to the preset optimization goal, such as minimizing the procurement cost and transportation cost of the coal procurement plan or maximizing the coal inventory, and iterate the optimization in the search space according to several initial solutions, and retain the optimal individual. The coal procurement plan generation module is used to parse the optimal solution corresponding to the final optimal individual and decode it into a coal procurement plan;

[0078] S2: Based on the data collection device, the real-time coal inventory related data of the current power plant is collected from the data server of the power plant, and the real-time coal inventory related data is sent to the cloud data center;

[0079] Real-time coal inventory-related data include historical coal purchase volume data of the previous purchase cycle, historical coal purchase plans, real-time power plant operation data, real-time climate and environmental data, real-time coal market supply and demand data, real-time alternative energy data, real-time coal inventory data, and real-time power plant transportation data;

[0080] S3: Based on the cloud data center, according to the real-time coal inventory correlation data, using the coal inventory prediction model, the coal inventory prediction is performed to obtain the real-time coal inventory prediction result, including the following steps:

[0081] S3-1: Based on the cloud data center, the real-time coal inventory related data is pre-processed by data format conversion, data denoising and normalization to improve data quality and obtain the real-time coal inventory related data after pre-processing;

[0082] S3-2: According to the principal component set, the preprocessed real-time coal inventory related data is subjected to data dimension reduction to obtain the real-time coal inventory related data after dimension reduction;

[0083] S3-3: Using the key feature extraction module of the coal inventory prediction model, extracting M real-time key features of the real-time coal inventory correlation data after dimensionality reduction, including the following steps:

[0084] S3-3-1: Use the RF structure trained in the key feature extraction module to extract the feature contribution of M candidate features in the real-time coal inventory correlation data after dimensionality reduction, where M is the total number of key features;

[0085] The formula is:

[0086]

[0087] In the formula, is the feature contribution of the j'th candidate feature; is the feature contribution of the j'th candidate feature in the cth tree of the random forest; c is the CART tree indicator; j' is the candidate feature indicator; n' is the total number of CARTs;

[0088]

[0089] In the formula, GI m GI l' GI r" is the Gini index of the CART tree node m, node l' and node r" of the random forest; p mk"is the proportion of category k" in CART tree node m; K' is the total number of categories; m, l', r" are node indicators; k" is the category indicator;

[0090] S3-3-2: normalizing the feature contributions of several candidate features to obtain corresponding normalized feature contributions;

[0091] The formula is:

[0092]

[0093] Where VIM j' is the contribution of the feature after normalization; J is the total number of candidate features;

[0094] S3-3-3: Generate feature selection standard values ​​for several candidate features based on the normalized feature contribution;

[0095] The formula is:

[0096]

[0097] In the formula, CFC j' The feature selection standard value for the j'th candidate feature; VIM j* is the normalized feature contribution of the j*th candidate feature; j* is the indicator of the candidate feature;

[0098] S3-3-4: According to the feature selection standard value, the candidate features are sorted in descending order, and the first M candidate features are selected as real-time key features to obtain M real-time key features;

[0099] S3-4: according to the attention weight preset by the attention weight module of the coal inventory prediction model, feature splicing is performed on the M real-time key features to obtain a real-time splicing feature;

[0100] S3-5: According to the real-time splicing features, the coal stock prediction module of the coal stock prediction model is used to perform coal stock prediction to obtain a real-time coal stock prediction result;

[0101] S4: Based on the cloud data center, according to the real-time coal inventory prediction results, using the coal procurement optimization model, a coal procurement optimization strategy is generated to obtain a real-time coal procurement optimization strategy, including the following steps;

[0102] S4-1: Based on the cloud data center, according to the real-time coal inventory forecast results, the corresponding historical coal procurement optimization experience is retrieved from the experience playback pool of the coal procurement optimization model to obtain several matching historical coal procurement optimization experiences;

[0103] S4-2: According to the real-time coal inventory forecast results and some matching historical coal procurement optimization experiences, the model parameters of the coal procurement optimization model are updated to obtain updated model parameters, including the following steps:

[0104] S4-2-1: Based on the real-time coal inventory forecast results, update the state space of the coal procurement optimization model to obtain the updated state space S' = [s'1,...,s' i" ,...,s' I' ], where s' i" is the updated i'th state value, i' is the state indicator, and I' is the total number of state space dimensions;

[0105] S4-2-2: Based on some matching historical coal procurement optimization experiences, the action space of the coal procurement optimization model is updated to obtain the updated action space A' = [a'1, ..., a' j" ,...,a' I ], where a' j" is the updated j-th "action value", j" is the action indicator, and I is the total number of action space dimensions;

[0106] S4-2-3: Use the updated state space and the updated action space as updated model parameters;

[0107] S4-3: Based on the updated model parameters, the coal procurement optimization model is used to generate a coal procurement optimization strategy to obtain a real-time coal procurement optimization strategy, including the following steps:

[0108] S4-3-1: Use the updated state space as the input of the deep Q network and use the agent to generate the Q value of each possible action in the updated action space;

[0109] S4-3-2: Use the reward function to obtain the reward value of each possible action in the updated action space, and update the Q value of the possible action according to the reward value to obtain the updated Q value of each possible action;

[0110] The formula is:

[0111] Q(s' p' ,a' p' )=(1-α")·Q(s p' ,a p' )+α"·(R(s p' ,a p' ,s' p' )+γ·Q max (s p' ,a p' ))

[0112] In the formula, Q(s' p' ,a'p' ) is the updated state value s' p' and the updated action value a' p' The corresponding updated Q value; Q(s p' ,a p' ) is the state value s p' and action value a p' The Q value of the corresponding possible action; α" is the learning rate; Q max (s p' ,a p' ) is the highest possible Q value of the action; p' is the comprehensive indicator; γ is the update parameter;

[0113] S4-3-3: Repeat the above Q-value update steps until the number of iterations reaches the iteration number threshold, and use the greedy strategy to select the possible action with the highest updated Q-value in each iteration as the execution action;

[0114] S4-3-4: Integrate several execution actions to obtain a real-time coal procurement optimization strategy;

[0115] S5: Based on the cloud data center, according to the real-time coal procurement optimization strategy, a coal procurement plan generation model is used to generate a coal procurement plan to obtain a real-time coal procurement plan, including the following steps:

[0116] S5-1: Based on the cloud data center, the initial solution generation module of the coal procurement solution generation model is used to generate initial solutions for the real-time coal procurement optimization strategy, and several real-time initial solutions are obtained, including the following steps:

[0117] S5-1-1: Encode the coal purchasing plan generation problem according to the historical coal purchasing plan in the coal inventory associated data, and convert the coal purchasing plan into a coding vector;

[0118] S5-1-2: Use the encoding vector as the ICPO individual of the ICPO optimization algorithm, initialize it using the Circle chaotic mapping sequence, and generate several real-time initial solutions;

[0119] The formula is:

[0120]

[0121] In the formula, is the initial ICPO individual of the Circle chaos map, i.e. the initial solution; is the randomly generated initial ICPO individual; i' is the ICPO individual indicator;

[0122] S5-2: Based on several real-time initial solutions, the optimal solution search module of the coal procurement plan generation model is used to search for the optimal solution in the search space to obtain the real-time optimal solution, including the following steps:

[0123] S5-2-1: According to the preset optimization goal, i.e., minimizing the cost of the coal procurement plan, setting the fitness function of the ICPO optimization algorithm, and setting the ICPO population parameters and the maximum number of iterations of the ICPO optimization algorithm;

[0124] The formula is:

[0125]

[0126] Where F(x) is the fitness function; R i (x) is the i-th cost of ICPO individual x, including purchase price cost, purchase transportation cost, power generation cost, etc.; i is the cost indicator; W i is the cost weight of the ith item; x is the ICPO individual variable;

[0127] S5-2-2: Introduce a cyclic population reduction mechanism to limit the number of individuals in the ICPO population parameters and obtain updated ICPO population parameters for the next iteration;

[0128] The formula is:

[0129]

[0130] In the formula, S t+1 is the number of individuals in the ICPO population parameter of the t+1th iteration; S t is the number of individuals in the ICPO population parameter of the tth iteration; S min is the minimum number of individuals in the ICPO population parameter; a' is the function evaluation parameter; V is the function evaluation cycle parameter; V max is the maximum function evaluation loop parameter; t is the number of iterations indicator;

[0131] S5-2-3: Calculate the initial fitness value of the initial ICPO individuals in the initial ICPO population according to the fitness function;

[0132] S5-2-4: According to the initial fitness value and the updated ICPO population parameters, the first defense strategy, the second defense strategy, the third defense strategy and the fourth defense strategy are used to update the initial ICPO population to obtain an updated ICPO population;

[0133] The formula for the first defense strategy is:

[0134]

[0135] In the formula, For the updated ICPO individuals within the first defense range; is the initial ICPO individual within the first defense range; τ1 is a random number based on normal distribution; τ2 is a random value in the interval [0,1]; It is the optimal solution within the first defense range; is the vector generated between the true optimal solution within the first defense range and the optimal solution randomly selected from the ICPO population; i' is the ICPO individual indicator; t is the iteration indicator;

[0136] The formula for the second defense strategy is:

[0137]

[0138] In the formula, For the updated ICPO individuals within the second defense range; The initial ICPO individual within the second defense range; is the search upper limit vector of the second defense range; τ3 is a random value in the interval [0,1]; are the r1th and r2th initial ICPO individuals respectively; r1 and r2 are two random integers between [1, S]; is the vector generated between the true optimal solution within the second defense range and the optimal solution randomly selected from the ICPO population;

[0139] The formula for the third defense strategy is:

[0140]

[0141] In the formula, For the updated ICPO individuals within the third defense range; The initial ICPO individual within the third defense range; is the search upper limit vector of the third defense range; are the r2th and r3th initial ICPO individuals respectively; r3 is a random integer between [1, S]; The odor diffusion factor defined for the fitness function; λ t It is a defense factor; Control parameters for search direction;

[0142] The formula for the fourth defense strategy is:

[0143]

[0144] In the formula, For the updated ICPO individuals within the fourth defense range; The initial ICPO individual within the fourth defense range; is the optimal solution within the fourth defense range; τ4 and τ5 are both random values ​​in the interval [0,1]; λt It is a defense factor; Control parameters for search direction; is the average force affecting the search direction; a' is the convergence speed factor;

[0145] S5-2-5: Use the dynamic reverse learning algorithm to perform dynamic reverse learning on the updated ICPO population to generate a dynamic reverse ICPO population;

[0146] The formula is:

[0147]

[0148] In the formula, is the ICPO individual in dynamic reverse direction; γ' is the decreasing inertia coefficient; L max , L min are the maximum and minimum values ​​of the vector space respectively; For the updated ICPO individuals;

[0149] S5-2-6: According to the fitness function, calculate the fitness values ​​of all ICPO individuals in the updated ICPO population and the dynamically reversed ICPO population, take the ICPO individual with the minimum fitness value as the optimal individual, and retain the optimal individual;

[0150] S5-2-7: If the number of iterations of iterative optimization reaches the maximum number of iterations or the fitness value of the optimal individual meets the requirements, the real-time optimal solution corresponding to the optimal individual is output;

[0151] S5-3: using the coal purchasing plan generation module of the coal purchasing plan generation model, the real-time optimal solution is analyzed, that is, the coding vector of the real-time optimal solution is decoded to obtain the real-time coal purchasing plan; the real-time coal purchasing plan includes information such as purchasing method, purchasing cycle, supplier selection, etc.;

[0152] S6: Based on the cloud data center, according to the real-time coal procurement plan, the real-time coal inventory related data is updated to obtain the updated real-time coal inventory related data. The specific method is:

[0153] Based on the cloud data center, the historical coal purchasing plan in the real-time coal inventory associated data is replaced with the real-time coal purchasing plan to obtain updated real-time coal inventory associated data;

[0154] S7: Based on the cloud data center, according to the updated real-time coal inventory related data, a coal inventory prediction model is used to perform a secondary coal inventory prediction to obtain an updated real-time coal inventory prediction result.

[0155] Embodiment 2:

[0156] like Figure 2As shown, this embodiment provides a power plant coal inventory prediction system based on artificial intelligence, which is used to implement a power plant coal inventory prediction method. The system includes a cloud data center and a plurality of data acquisition devices. The cloud data center is respectively connected to the plurality of data acquisition devices for communication. The plurality of data acquisition devices are arranged in a plurality of power plants in a one-to-one correspondence, and the data acquisition devices are connected to the data servers of the corresponding power plants for communication.

[0157] A data collection device, used to collect the real-time coal inventory related data of the current power plant, and send the real-time coal inventory related data to the cloud data center;

[0158] The cloud data center includes a model building unit, a coal inventory prediction unit, a coal procurement optimization unit, a coal procurement plan generation unit, a data updating unit, and a secondary coal inventory prediction unit which are connected in sequence;

[0159] A model building unit, used to build a coal inventory prediction model, a coal procurement optimization model, and a coal procurement plan generation model using an artificial intelligence algorithm;

[0160] A coal stock prediction unit, used to perform coal stock prediction based on real-time coal stock correlation data and using a coal stock prediction model to obtain a real-time coal stock prediction result;

[0161] A coal purchasing optimization unit is used to generate a coal purchasing optimization strategy based on the real-time coal inventory forecast result and the coal purchasing optimization model to obtain a real-time coal purchasing optimization strategy;

[0162] A coal purchasing plan generating unit, used to generate a coal purchasing plan according to a real-time coal purchasing optimization strategy and using a coal purchasing plan generating model to obtain a real-time coal purchasing plan;

[0163] A data updating unit, used for updating the real-time coal inventory related data according to the real-time coal purchasing plan, and obtaining updated real-time coal inventory related data;

[0164] The secondary coal stock prediction unit is used to perform secondary coal stock prediction based on the updated real-time coal stock associated data and use the coal stock prediction model to obtain the updated real-time coal stock prediction result.

[0165] The present invention discloses a method and system for predicting coal inventory in power plants based on artificial intelligence. The real-time coal inventory correlation data considers the impact of multiple sources of data such as power plant operation, climate environment, original coal procurement plan, coal supply and demand data on the prediction of coal inventory in power plants, so as to provide more comprehensive and accurate input information. The artificial intelligence algorithms of deep learning algorithm, reinforcement learning algorithm and swarm intelligence optimization algorithm are applied to the prediction of coal inventory in power plants, forming an intelligent solution integrating multiple models, which can more comprehensively consider the complexity of coal inventory prediction and procurement decision-making, and provide more accurate and scientific prediction results. The system has the ability of real-time data collection and processing, It can respond to market changes and power plant operating conditions in a timely manner, and improve the timeliness of predictions and decisions. Through the coal inventory prediction model built based on deep learning technology, its powerful feature extraction and pattern recognition capabilities can fully capture the nonlinear relationship between coal procurement volume and a variety of complex factors to achieve high-precision predictions. The coal inventory prediction model based on deep learning technology has a data memory function. When facing new data environments or changes in application scenarios, the model has strong generalization capabilities and can maintain prediction accuracy. The dynamic adjustment mechanism and closed-loop feedback mechanism are adopted to continuously optimize the prediction results and improve the prediction accuracy.

[0166] The present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.

Claims

1. A method for predicting coal inventory in power plants based on artificial intelligence, characterized in that: The steps include: Based on the cloud data center, using artificial intelligence algorithms, we build coal inventory prediction models, coal procurement optimization models, and coal procurement plan generation models; Based on the data collection device, the real-time coal inventory related data of the current power plant is collected, and the real-time coal inventory related data is sent to the cloud data center; Based on the cloud data center, according to the real-time coal inventory related data, the coal inventory prediction model is used to predict the coal inventory and obtain the real-time coal inventory prediction results; Based on the cloud data center, according to the real-time coal inventory forecast results, the coal procurement optimization model is used to generate the coal procurement optimization strategy and obtain the real-time coal procurement optimization strategy; Based on the cloud data center, according to the real-time coal procurement optimization strategy, the coal procurement plan generation model is used to generate the coal procurement plan and obtain the real-time coal procurement plan; Based on the cloud data center, the real-time coal inventory related data is updated according to the real-time coal procurement plan to obtain updated real-time coal inventory related data; Based on the cloud data center, according to the updated real-time coal inventory related data, the coal inventory prediction model is used to perform a secondary coal inventory prediction to obtain the updated real-time coal inventory prediction result.

2. The method for predicting coal inventory in a power plant based on artificial intelligence according to claim 1, characterized in that: The real-time coal inventory related data includes historical coal purchase volume data, historical coal purchase plans, real-time power plant operation data, real-time climate and environment data, real-time coal market supply and demand data, real-time alternative energy data, real-time coal inventory data and real-time power plant transportation data.

3. The method for predicting coal inventory in a power plant based on artificial intelligence according to claim 1, characterized in that: Based on the cloud data center, using artificial intelligence algorithms, we build a coal inventory prediction model, a coal procurement optimization model, and a coal procurement plan generation model, including the following steps: Based on the cloud data center, historical coal stock related data of several historical power plants are collected and preprocessed to obtain several preprocessed historical coal stock related data; Performing data dimensionality reduction on a number of pre-processed historical coal stock related data to obtain a principal component set and a number of dimensionality-reduced historical coal stock related data; Based on several dimensionality-reduced historical coal stock correlation data, a coal stock prediction model is constructed using a deep learning algorithm, and several historical coal stock prediction results are generated; Based on several historical coal inventory forecast results, a reinforcement learning algorithm is used to build a coal procurement optimization model, and several historical coal procurement optimization strategies and several historical coal procurement optimization experiences are generated; According to several historical coal procurement optimization strategies, a coal procurement plan generation model is constructed using swarm intelligence optimization algorithm.

4. The method for predicting coal inventory in a power plant based on artificial intelligence according to claim 3 is characterized by: The PCA method is used to reduce the dimension of several pre-processed historical coal stock related data to obtain the principal component set and several reduced-dimensional historical coal stock related data.

5. The method for predicting coal inventory in a power plant based on artificial intelligence according to claim 4 is characterized in that: The coal inventory prediction model is constructed based on the RF-Attention-BiLSTM algorithm; The coal procurement optimization model is constructed based on the DQN algorithm; The coal procurement plan generation model is constructed based on the ICPO optimization algorithm.

6. The method for predicting coal inventory in a power plant based on artificial intelligence according to claim 5, characterized in that: Based on the cloud data center, according to the real-time coal inventory correlation data, the coal inventory prediction model is used to perform coal inventory prediction, and the real-time coal inventory prediction result is obtained, including the following steps: Based on the cloud data center, the real-time coal inventory related data is preprocessed to obtain the preprocessed real-time coal inventory related data; According to the principal component set, the real-time coal inventory related data after preprocessing is subjected to data dimension reduction to obtain the real-time coal inventory related data after dimension reduction; Using the coal inventory prediction model, M real-time key features of the real-time coal inventory correlation data after dimensionality reduction are extracted; According to the preset attention weights, M real-time key features are spliced ​​to obtain real-time spliced ​​features; According to the real-time splicing characteristics, coal inventory prediction is carried out to obtain real-time coal inventory prediction results.

7. The method for predicting coal inventory in a power plant based on artificial intelligence according to claim 5 is characterized by: Based on the cloud data center, according to the real-time coal inventory forecast results, the coal procurement optimization model is used to generate the coal procurement optimization strategy, and the real-time coal procurement optimization strategy is obtained, including the following steps; Based on the cloud data center, according to the real-time coal inventory forecast results, the corresponding historical coal procurement optimization experience is retrieved to obtain several matching historical coal procurement optimization experiences; According to the real-time coal inventory forecast result and several matching historical coal procurement optimization experiences, the model parameters of the coal procurement optimization model are updated to obtain updated model parameters; According to the updated model parameters, the coal procurement optimization model is used to generate a coal procurement optimization strategy to obtain a real-time coal procurement optimization strategy.

8. The method for predicting coal inventory in a power plant based on artificial intelligence according to claim 5, characterized in that: Based on the cloud data center, according to the real-time coal procurement optimization strategy, the coal procurement plan generation model is used to generate a coal procurement plan to obtain a real-time coal procurement plan, including the following steps: Based on the cloud data center, the coal procurement solution generation model is used to generate initial solutions for the real-time coal procurement optimization strategy, and several real-time initial solutions are obtained; According to several real-time initial solutions, the optimal solution is searched in the search space to obtain the real-time optimal solution; The real-time optimal solution is analyzed to obtain the real-time coal purchasing plan.

9. The method for predicting coal inventory in a power plant based on artificial intelligence according to claim 2, characterized in that: Based on the cloud data center, according to the real-time coal procurement plan, the real-time coal inventory related data is updated to obtain the updated real-time coal inventory related data. The specific method is as follows: Based on the cloud data center, the historical coal purchasing plan in the real-time coal inventory associated data is replaced with the real-time coal purchasing plan to obtain updated real-time coal inventory associated data.

10. A power plant coal inventory prediction system based on artificial intelligence, used to implement the power plant coal inventory prediction method according to any one of claims 1 to 9, characterized in that: The system includes a cloud data center and several data acquisition devices, wherein the cloud data center is respectively connected to the several data acquisition devices in communication, and the several data acquisition devices are arranged in a one-to-one correspondence in several power plants, and the data acquisition devices are connected to the data servers of the corresponding power plants in communication; The cloud data center includes a model building unit, a coal inventory prediction unit, a coal procurement optimization unit, a coal procurement plan generation unit, a data updating unit and a secondary coal inventory prediction unit which are connected in sequence.

Images