Lyocell fiber production and manufacturing cost prediction method and application

Abstract

The invention relates to the technical field of intelligent manufacturing and cost management, in particular to a Lyocell fiber production and manufacturing cost prediction method and application. Collecting data in the Lyocell fiber production and manufacturing process; performing data preprocessing on the data; constructing a predicted total model; extracting three technological parameter groups from the data after data preprocessing, inputting the technological parameter groups into a predicted total model, and outputting to obtain a raw material consumption predicted value, an energy consumption predicted value and an equipment maintenance predicted value; setting initial weight distribution of the predicted total models, calculating mean square errors of the three models in each total model, and introducing Gaussian process regression to obtain weights of the three models in each total model; calculating an equipment maintenance predicted value, a raw material consumption predicted value and an energy consumption predicted value after weighted fusion; solving the predicted total production and manufacturing cost; according to the invention, an enterprise is assisted to realize refined cost management in the Lyocell fiber production and manufacturing process.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing and cost management, and in particular to a method and application for predicting the production cost of lyocell fibers. Background Art

[0002] Lyocell fiber was launched in the mid-1990s with natural plant fiber as raw material. It is hailed as the most valuable product in the history of artificial fibers in the past half century, and has many excellent properties of both natural and synthetic fibers. Lyocell is a green fiber made of cellulose. There is no chemical reaction in the production process and the solvents used are non-toxic. Lyocell fiber is a new type of textile and clothing fabric that emerged in Europe and the United States in the mid-to-late 1990s. It not only has the comfort, good hand feel, and easy dyeing characteristics of natural fiber cotton, but also has environmental advantages that traditional viscose fiber does not have. Compared with viscose fiber, Lyocell fiber is more environmentally friendly in the production process. Viscose fiber will release harmful gases such as carbon disulfide and hydrogen sulfide during the production process, which pollutes the environment and has been gradually eliminated in developed countries.

[0003] In the production and manufacturing of lyocell fibers, raw material costs, energy consumption costs and equipment maintenance costs are key factors affecting the company's profit margin and market competitiveness. The sum of raw material costs, energy consumption costs and equipment maintenance costs is the company's total production and manufacturing cost in lyocell fiber production and manufacturing. The raw material cost fluctuations, energy consumption cost fluctuations and equipment maintenance costs caused by the raw material consumption involved in the raw material cost lead to excessive fluctuations in the process consumption cost. If the total production and manufacturing cost cannot be accurately predicted, and because the process consumption cost fluctuates too much, the environmental protection costs in the process consumption cost, such as recycling costs, cannot be confirmed, making it impossible for the company to carry out refined management of the costs involved in the entire process production and manufacturing.

[0004] In the prior art, the production cost prediction methods of lyocell fiber are mostly based on traditional empirical formulas or static analysis of a single cost module, which have the following limitations: 1. Insufficient prediction accuracy of raw material cost: The main raw materials for Lyocell fiber production are cellulose materials such as dissolving pulp, and their prices are significantly affected by the supply and demand relationship in the international market and policy regulation. Existing methods usually use the historical price average for prediction, which does not fully consider the dynamic fluctuations of the raw material supply chain and the impact of process optimization on raw material utilization, resulting in large prediction deviations.

[0005] 2. Imperfect energy cost modeling: Lyocell fiber production requires solvent spinning under high temperature and high pressure conditions, which consumes a relatively high proportion of energy. Existing energy consumption forecasts mostly rely on equipment rated power or fixed unit energy consumption coefficients, and lack forecast analysis based on specific process parameters, making it difficult to accurately reflect energy consumption fluctuations in actual production.

[0006] 3. Equipment maintenance costs have not been systematically quantified: The maintenance costs of Lyocell fiber production line equipment are closely related to the degree of equipment aging, failure rate and preventive maintenance strategies. Traditional methods usually adopt regular maintenance plans or simple statistical models based on fault records, and fail to combine real-time operating data for prediction, resulting in delayed or redundant maintenance cost estimates.

[0007] Therefore, companies are in urgent need of a method that can predict the production and manufacturing costs of Lyocell fibers, provide a scientific basis for process optimization and resource scheduling, and assist companies in conducting refined cost management during the production and manufacturing of Lyocell fibers.

[0008] For example, a Chinese patent with publication number CN117788037A and publication date 2024.01.02 is named "A method for multi-value chain cost prediction of electricity cost". Its specific technical solution is as follows: The invention uses network data mining technology to collect various cost data of power equipment manufacturing enterprises in multiple value chains, and construct an influencing factor library under the multi-value chain collaboration of power equipment manufacturing enterprises; the Pearson correlation coefficient and gray correlation method are used to analyze and screen the influencing factors of the influencing factor library, and indicators with a high correlation with cost prediction are selected as the main influencing factors for the prediction model analysis, and the firefly perturbation and sparrow search algorithm combination algorithm are used to optimize the BP neural network model to construct a FA-SSA-BP cost intelligent prediction model that can combine multi-value chain data collaboration such as product production, sales, supply, and services.

[0009] The above patent uses BP neural network and sparrow algorithm to perform model prediction optimization, so as to output the final prediction result of the cost of power equipment manufacturing enterprises. However, the coefficient optimization method of weight in the above patent is too single, and the method of the above patent cannot be applied to process the parameters of the cost of the Lyocell fiber production and manufacturing process, and predict the cost involved in the Lyocell fiber production and manufacturing process. Summary of the invention

[0010] In order to solve the problems existing in the above-mentioned prior art, the present application provides a method for predicting the production and manufacturing cost of lyocell fiber by fusing algorithm models and optimizing the model fusion weights, thereby realizing an accurate prediction of the production and manufacturing cost of lyocell fiber and providing a method and application for predicting the production and manufacturing cost of lyocell fiber.

[0011] In order to achieve the above technical effects, the technical solution of this application is as follows: In a first aspect, a method for predicting the production cost of lyocell fiber comprises the following specific steps: Step 1: Collect historical raw material data, energy consumption data and equipment maintenance data in the production and manufacturing process of Lyocell fibers; raw material data include wood pulp parameter data, NMMO solution parameter data and chemical additive parameter data; energy consumption data include temperature data, pressure data and flow data; equipment maintenance data include equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history; Step 2: Preprocess raw material data, energy consumption data, and equipment maintenance data; Step 3: Build and train the overall model for raw material consumption prediction, the overall model for energy consumption prediction, and the overall model for equipment maintenance prediction; Step 4: Input the process parameter group 1, process parameter group 2 and process parameter group 3 in the current lyocell fiber production process into the three total models in step 3 respectively, and obtain three raw material consumption prediction values, three energy consumption prediction values ​​and three equipment maintenance prediction values; Step 5: Set the initial weight distribution of the total model for raw material consumption prediction, the total model for energy consumption prediction, and the total model for equipment maintenance prediction, and calculate the mean square error of the three models within each total model. Then update the Beta distribution parameters of the total model based on the mean square error. At the same time, introduce Gaussian process regression to calculate the uncertainty of the three models within each total model, and then update the Beta distribution parameters again based on the uncertainty. Then, based on the updated Beta distribution parameters combined with variational Bayesian inference, calculate the fusion weights of the three models within each total model. Step 6: According to the fusion weights of the three types of prediction values ​​in step 4 and the three models within the corresponding total model, the final prediction value after weighted fusion is calculated; Step 7: Based on the final forecast value, combined with raw material prices, energy consumption prices and equipment maintenance prices, the predicted total production and manufacturing cost is obtained.

[0012] Furthermore, in the step three, the overall model for raw material consumption prediction, the overall model for energy consumption prediction and the overall model for equipment maintenance prediction are constructed and trained based on random forest, support vector machine and long short-term memory network; in the step four, process parameter group 1 is the raw material data in the current lyocell fiber production process, process parameter group 2 is the energy consumption data in the current lyocell fiber production process and the equipment operation time in the equipment maintenance data, and process parameter group 3 is the equipment maintenance data in the current lyocell fiber production process; the specific method of step four is: inputting process parameter group 1 into the overall model output of raw material consumption prediction to obtain three raw material consumption prediction values, inputting process parameter group 2 into the overall model output of energy consumption prediction to obtain three energy consumption prediction values, and inputting process parameter group 3 into the overall model output of equipment maintenance prediction to obtain three equipment maintenance prediction values; the three types of prediction values ​​in step six include three raw material consumption prediction values, three energy consumption prediction values ​​and three equipment maintenance prediction values; the final prediction The values ​​include the final raw material consumption forecast value, the final energy consumption forecast value and the final equipment maintenance forecast value; the specific method of step six is: the three raw material consumption forecast values ​​are calculated according to the fusion weights of the three models within the total model of raw material consumption forecast to obtain the final raw material consumption forecast value after weighted fusion; the three energy consumption forecast values ​​are calculated according to the fusion weights of the three models within the total model of energy consumption forecast to obtain the final energy consumption forecast value after weighted fusion; the three equipment maintenance forecast values ​​are calculated according to the fusion weights of the three models within the total model of equipment maintenance forecast to obtain the final equipment maintenance forecast value after weighted fusion; the specific method of step seven is: according to the final raw material consumption forecast value, the final energy consumption forecast value and the final equipment maintenance forecast value, combined with the raw material price, energy consumption price and equipment maintenance price, the raw material forecast cost, energy consumption forecast cost and equipment maintenance forecast cost are obtained, so as to obtain the predicted total production and manufacturing cost.

[0013] Furthermore, the wood pulp parameter data in step one include wood pulp viscosity, wood pulp polymerization degree and wood pulp methyl fiber content; the NMMO solution parameter data include NMMO solution concentration; the chemical additive parameter data include propylene glycol content and hydroxylamine content; the raw material data also include raw material purchase price data, raw material inventory data and raw material consumption data; the energy consumption data also includes equipment operation time; the temperature data includes dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature and ambient temperature; the pressure data includes solvent delivery pressure, vacuum pressure and ambient air pressure; the flow data includes NMMO solvent flow, water consumption and steam consumption.

[0014] Furthermore, the viscosity of wood pulp, degree of polymerization of wood pulp and methyl cellulose content of wood pulp are monitored and collected in real time through online viscometers and optical measuring instruments; the concentration of NMMO solution is collected by liquid phase concentration detection sensors; the propylene glycol content and hydroxylamine content are detected and collected by chemical sensors; the purchase price data of raw materials, the inventory data of raw materials and the consumption data of raw materials are collected through the enterprise resource planning system and synchronized with the external market database.

[0015] Furthermore, the dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature and ambient temperature are measured by PT100 platinum resistance temperature sensor or thermocouple; the solvent delivery pressure, vacuum pressure and ambient air pressure are collected by MEMS piezoresistive pressure sensor; NMMO solvent flow, water consumption and steam consumption are collected by electromagnetic flowmeter and ultrasonic flowmeter, and the accumulated flow value is calculated in combination with PLC; the reactor temperature, insulation water system temperature, insulation water system pressure, spinning wind system temperature and spinning wind system pressure are collected by SCADA system.

[0016] Furthermore, equipment operation time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history are recorded and collected through the MES system.

[0017] Furthermore, the specific method steps for data preprocessing of raw material data, energy consumption data and equipment maintenance data are as follows: Step a: Perform outlier detection on time series data, numerical data, and non-normal distribution data in raw material data, energy consumption data, and equipment maintenance data, and remove outliers. Finally, perform missing value processing and duplicate data removal. Step b: normalizing raw material data, energy consumption data and equipment maintenance data; Step c: Use Pearson correlation analysis and principal component analysis to extract key features of raw material data, energy consumption data, and equipment maintenance data; Step d: Use K-means cluster analysis and information entropy screening methods to conduct final screening of raw material data, energy consumption data, and equipment maintenance data.

[0018] Furthermore, the specific method of performing outlier detection on numerical data in step a is: using the 3σ principle to detect outliers, for each data point f i , calculate the mean μ and standard deviation σ of the original data, if it satisfies: ; It is judged as abnormal data and is removed; where, is the ith data point.

[0019] Furthermore, the specific method of performing outlier detection on non-normal distribution data in step a is: using the interquartile range method to detect outliers, calculating the first quartile Q1 and the third quartile Q3, and setting the abnormal range as follows: ; ; Data outside this range are considered outliers and are removed; where IQR means interquartile range.

[0020] Furthermore, the specific method for handling missing values ​​is as follows: time series data is filled using linear interpolation; if the missing ratio of numerical data is less than 20%, k-nearest neighbor interpolation is used to fill it; if the missing ratio of non-normal distribution data is less than 20%, k-nearest neighbor interpolation is used to fill it; if the missing ratio of non-normal distribution data is more than 20%, the non-normal distribution data is excluded.

[0021] Furthermore, the time series data includes inventory data of raw materials, consumption data of raw materials, dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature, ambient temperature, solvent delivery pressure, vacuum pressure, insulation water system pressure, spinning wind system pressure, ambient air pressure, NMMO solvent flow rate, water consumption, steam consumption, equipment operating time and number of failures.

[0022] Furthermore, the numerical data include wood pulp viscosity, wood pulp polymerization degree, wood pulp methyl fiber content, NMMO solution concentration, propylene glycol content, hydroxylamine content, raw material purchase price data, maintenance cost and equipment failure rate; the non-normal distribution data include raw material purchase price data, raw material inventory data, raw material consumption data, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history.

[0023] Furthermore, the raw material data, energy consumption data and equipment maintenance data are normalized by Min-Max normalization. The specific formula is as follows: ; In the formula, x is the original data value; x min is the minimum value of the original data; x max is the maximum value of the original data; For data with abnormal distribution, Z-score standardization is used: ; In the formula, μ is the mean of the original data; σ is the standard deviation, is the data value after Z-score standardization, xis the original data value.

[0024] Furthermore, the specific method steps for extracting key features of raw material data, energy consumption data and equipment maintenance data using Pearson correlation analysis and principal component analysis in step c are as follows: Step a1: Calculate the Pearson correlation coefficient between features. The specific formula is as follows: ; When |r|>0.8, the two features are determined to be highly correlated and one of them is removed; where r is the Pearson correlation coefficient, h i is the i-th observation value of variable h, y i is the ith observation value of variable y, is the mean of variable h, μ y is the mean of variable y; Step b1: Perform principal component analysis to reduce the dimension. First, construct a standardized data matrix X with a dimension of m×n, where m is the number of samples and n is the number of features. Then calculate the covariance matrix , the specific calculation formula is as follows: ; Where, X T is the transposed matrix of the standardized data matrix X; Step c1: Solve the covariance matrix The eigenvalues ​​and eigenvectors of , and sort them from large to small according to the eigenvalues, and calculate the cumulative contribution rate; select the first k eigenvectors with cumulative contribution rates exceeding 95% to form a dimensionality reduction projection matrix W, and obtain projection data through the dimensionality reduction projection matrix W, and finally reduce the data dimension after principal component analysis from n dimensions to k dimensions; the specific formula for obtaining the projection data is as follows: ; Where W is the dimension reduction projection matrix, and X′ is the feature data after dimension reduction.

[0025] Furthermore, the specific steps of using K-means cluster analysis and information entropy screening methods to finally screen raw material data, energy consumption data, and equipment maintenance data are as follows: Step a2: Use K-means cluster analysis, first initialize, set the number of clusters k=5, select k random samples as the initial cluster centers, and then calculate the Euclidean distance from the sample to the cluster center. The specific formula is as follows: ; In the formula, The meaning of is expressed as the Euclidean distance between the sample point s and the cluster center c; is the i-th data sample, is the new cluster center of the i-th cluster, and n is the n-dimensional space; Step b2: Reassign clusters, calculate the distance between each sample point and all cluster centers, and assign the sample point to the nearest cluster; Step c2: Update the cluster center. First, calculate the new cluster center and continue to iterate until convergence. When the cluster center change is less than the set threshold, stop the iteration. The specific calculation formula for calculating the new cluster center is: ; In the formula, is the new cluster center of the ith cluster, Cluster C i The number of internal sample points, s is the data sample point; Step d2: Filter out representative data, calculate the average distance from each cluster to the cluster center, and select 10% of the data around the cluster center in each cluster as training samples; Step e2: Through information entropy screening, further evaluate the information content of each cluster and calculate the information entropy of each cluster , the specific formula is as follows: ; In the formula, Cluster The probability of category j in ; is the number of categories within the cluster; Step f2: Filter the cluster with the highest information entropy, calculate the information entropy values ​​of all clusters, and select the top 50% clusters with the highest information entropy. Among the selected clusters, retain the samples around the center of the cluster and remove outliers to form the final training data set.

[0026] Furthermore, in the step three, the total model for raw material consumption prediction, the total model for energy consumption prediction and the total model for equipment maintenance prediction constructed and trained based on random forest, support vector machine and long short-term memory network are specifically as follows: the total model for raw material consumption prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first raw material consumption prediction model constructed based on random forest, a second raw material consumption prediction model constructed based on support vector machine and a third raw material consumption prediction model constructed based on long short-term memory network; the total model for energy consumption prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first energy consumption prediction model constructed based on random forest, a second energy consumption prediction model constructed based on support vector machine and a third energy consumption prediction model constructed based on long short-term memory network; the total model for equipment maintenance prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first equipment maintenance prediction model constructed based on random forest, a second equipment maintenance prediction model constructed based on support vector machine and a third equipment maintenance prediction model constructed based on long short-term memory network.

[0027] Furthermore, the specific method steps for constructing the first raw material consumption prediction model, the first energy consumption prediction model and the first equipment maintenance prediction model based on random forest are as follows: Step a3: constructing a first raw material consumption prediction model based on random forest; the specific construction method of the first raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, training to obtain the first raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b3: constructing a first energy consumption prediction model based on random forest; the specific construction method of the first energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of the training set, and taking power consumption, water consumption and steam consumption as output features, training to obtain the first energy consumption prediction model; Step c3: Construct a first equipment maintenance prediction model based on random forest; the specific construction method of the first equipment maintenance prediction model is: use equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use equipment failure rate and maintenance times as output features, and train to obtain the first equipment maintenance prediction model.

[0028] Furthermore, the specific method steps for constructing the second raw material consumption prediction model, the second energy consumption prediction model and the second equipment maintenance prediction model based on the support vector machine are as follows: Step a4: constructing a second raw material consumption prediction model based on a support vector machine; the specific construction method of the second raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, and training to obtain the second raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b4: constructing a second energy consumption prediction model based on a support vector machine; the specific construction method of the second energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of a training set, and taking power consumption, water consumption and steam consumption as output features, and training to obtain the second energy consumption prediction model; Step c4: Construct a second equipment maintenance prediction model based on support vector machine; the specific construction method of the second equipment maintenance prediction model is: use equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use equipment failure rate and maintenance times as output features, and train to obtain the second equipment maintenance prediction model.

[0029] Furthermore, the specific method steps for constructing the third raw material consumption prediction model, the third energy consumption prediction model and the third equipment maintenance prediction model based on the long short-term memory network are as follows: Step a5: constructing a third raw material consumption prediction model based on the long short-term memory network; the specific construction method of the third raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, and training to obtain the third raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b5: constructing a third energy consumption prediction model based on the long short-term memory network; the specific construction method of the third energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of the training set, and taking power consumption, water consumption and steam consumption as output features, training to obtain the third energy consumption prediction model; Step c5: construct a third equipment maintenance prediction model based on the long short-term memory network; the specific construction method of the third equipment maintenance prediction model is: use the equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use the equipment failure rate and maintenance number as output features, and train to obtain the third equipment maintenance prediction model.

[0030] Furthermore, in step 5, the initial weight distribution of the total model for raw material consumption prediction, the total model for energy consumption prediction, and the total model for equipment maintenance prediction is set, and the mean square error of the three models within each total model is calculated, and then Gaussian process regression is introduced to calculate the uncertainty of the three models within each total model. Finally, the fusion weights of the three models within each total model are obtained according to the variational Bayesian inference calculation. Specifically, it is assumed that the weights of the three models within each total model obey the Beta distribution: ; In the formula, The weight coefficients of the three models within the total model for raw material consumption prediction, the weight coefficients of the three models within the total model for energy consumption prediction, or the weight coefficients of the three models within the total model for equipment maintenance prediction, and Set as initial parameters, generally: ; In the formula, is a positive number, ensuring that the weights are evenly distributed in the initial state; The prediction errors of the three models within the total model for raw material consumption prediction, the prediction errors of the three models within the total model for energy consumption prediction, or the prediction errors of the three models within the total model for equipment maintenance prediction are evaluated by calculating the mean square error of the three models within the total model for raw material consumption prediction, the mean square error of the three models within the total model for energy consumption prediction, or the mean square error of the three models within the total model for equipment maintenance prediction. The specific calculation formula is as follows: ; ; ; In the formula, represents a mean square error of the first raw material consumption prediction model, the first energy consumption prediction model, or the first equipment maintenance prediction model based on random forest; represents a mean square error of a second raw material consumption prediction model, a second energy consumption prediction model, or a second equipment maintenance prediction model based on a support vector machine; represents the mean square error of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network; N represents the total number of training samples; Represents the true value of the i-th sample; represents the predicted value of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model based on random forest for the i-th sample; represents the predicted value of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model based on the support vector machine for the i-th sample; represents the predicted value of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network for the i-th sample; Then update the Beta distribution parameters according to the mean square error: ; ; In the formula, It represents a distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction. represents another distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; represents the mean square error of the total model for raw material consumption prediction, the mean square error of the total model for energy consumption prediction, or the mean square error of the total model for equipment maintenance prediction; Gaussian process regression is introduced to calculate the uncertainty of each model. The specific formula is as follows: ; In the formula, It means the uncertainty of the model; N is the total number of training samples; It is expressed as the prediction variance of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction on all samples. The specific solution formula is as follows: ; In the formula, represents the predicted value of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction for the i-th sample; It represents the average prediction value of the total model for raw material consumption prediction, the total model for energy consumption prediction or the total model for equipment maintenance prediction on all samples; Then introduce uncertainty into the Beta distribution update: ; ; In the formula, represents a distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction after update; Another distribution parameter representing an updated fusion weight calculation of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; Finally, the final weights are calculated using variational Bayesian inference: ; In the formula, The model weight after the t+1th iteration of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; Represents the contribution of actual data; Then, the fusion weights of the three models within each model are obtained: ; ; ; In the formula, The meaning of is the weight coefficient of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; Meaning is the weight coefficient of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; The meaning is the weight coefficient of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; Meaning is another distribution parameter in the fusion weight calculation of the updated first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; Meaning is another distribution parameter in the fusion weight calculation of the updated second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; Meaning is another distribution parameter in the calculation of the fusion weight of the updated third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; It means the sum of the predicted output values ​​of all training samples of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model based on random forest; The meaning is the sum of the predicted output values ​​of all training samples of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model based on the support vector machine; It means the sum of the predicted output values ​​of all training samples of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network.

[0031] Furthermore, the process parameter group 1 includes wood pulp viscosity, wood pulp polymerization degree, wood pulp methyl fiber content, NMMO solution concentration, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data; the raw material consumption forecast value includes wood pulp consumption, NMMO solution consumption and chemical additive consumption; the chemical additive consumption includes propylene glycol consumption and hydroxylamine consumption; the process parameter group 2 includes temperature data, pressure data, flow data and equipment operating time; the energy consumption forecast value includes electricity consumption, water consumption and steam consumption; the process parameter group 3 includes equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history; the equipment maintenance forecast value includes equipment failure rate and equipment maintenance number.

[0032] Furthermore, the specific formulas for calculating the final weighted fusion of the predicted value of raw material consumption, the final predicted value of energy consumption, and the final predicted value of equipment maintenance are as follows: ; In the formula, Indicates the final raw material consumption forecast value, the final energy consumption forecast value or the final equipment maintenance forecast value; when represents the raw material consumption prediction value of the first raw material consumption prediction model based on random forest, represents the raw material consumption prediction value of the second raw material consumption prediction model based on support vector machine, When represents the raw material consumption forecast value of the third raw material consumption forecast model based on the long short-term memory network, then represents the weight coefficient of the first raw material consumption prediction model, represents the weight coefficient of the second raw material consumption forecast model and represents the weight coefficient of the third raw material consumption forecast model; when represents the energy consumption prediction value of the first energy consumption prediction model based on random forest, represents the energy consumption prediction value of the second energy consumption prediction model based on the support vector machine, When represents the energy consumption prediction value of the third energy consumption prediction model based on the long short-term memory network, then represents the weight coefficient of the first energy consumption prediction model, represents the weight coefficient of the second energy consumption prediction model and represents the weight coefficient of the third energy consumption prediction model; when represents the equipment maintenance prediction value of the first equipment maintenance prediction model based on random forest, represents the equipment maintenance prediction value of the second equipment maintenance prediction model based on support vector machine, When represents the equipment maintenance prediction value of the third equipment maintenance prediction model based on the long short-term memory network, then represents the weight coefficient of the first equipment maintenance prediction model, represents the weight coefficient and Represents the weight coefficient of the third equipment maintenance prediction model.

[0033] The specific calculation formula for the predicted total production cost obtained in step 7 is as follows: ; In the formula, Meaning is the predicted total production and manufacturing cost, Meaning is the cost of raw materials, Meaning is energy consumption cost, It means equipment maintenance cost.

[0034] Furthermore, the calculation formula of the raw material cost is as follows: ; In the formula, is the final wood pulp consumption, is the price of wood pulp, is the final NMMO solution consumption, is the price of NMMO solution, is the final propylene glycol consumption, is the price of propylene glycol, is the final hydroxylamine consumption, is the price of hydroxylamine.

[0035] Furthermore, the calculation formula of the energy consumption cost is as follows: ; In the formula, is the final power consumption, For the price of electricity, is the final water consumption, For the price of water, is the final steam consumption, For the price of steam.

[0036] Furthermore, the specific calculation formula of the equipment maintenance cost is as follows: ; In the formula, is the fixed maintenance cost of the equipment, is the final number of failures, is the cost of repairing a single failure.

[0037] In a second aspect, a method for predicting the production cost of lyocell fibers is applied, which is suitable for predicting the production cost of lyocell fibers.

[0038] According to the above technical solution, the beneficial effects of this application are as follows: 1. The method adopted in the present invention optimizes the weight coefficient, first accurately predicts the raw material consumption, energy consumption and equipment maintenance, and then accurately calculates the predicted total production and manufacturing cost through the obtained accurate prediction value, thereby providing a scientific basis for Lyocell process optimization and resource scheduling, and assisting enterprises to realize refined cost management in the production and manufacturing process of Lyocell fibers.

[0039] 2. The method adopted in the present invention is based on random forest, support vector machine and long short-term memory network to construct and train the overall model of raw material consumption prediction, the overall model of energy consumption prediction and the overall model of equipment maintenance prediction, and then the three raw material consumption prediction values, three energy consumption prediction values ​​and three equipment maintenance prediction values ​​are obtained respectively by weighted fusion to accurately obtain the final raw material consumption prediction value, the final energy consumption prediction value and the final equipment maintenance prediction value, thereby improving the accuracy of the final predicted total production and manufacturing cost.

[0040] 3. The method of the present invention combines variational Bayesian inference, Gaussian process regression and Beta distribution update to optimize the model fusion weight calculation, adapt it to different data distributions, and improve the stability and accuracy of the final prediction.

[0041] 4. The method of the present invention adopts the introduction of Gaussian process regression to calculate the uncertainty of the three models within each total model, and incorporates it into the weight update rule, thereby achieving the technical effect of reducing the weight of the high uncertainty model and improving the prediction stability.

[0042] 5. Compared with the traditional Beta distribution update, the Beta distribution update adopted by the method of the present invention adopts variational inference, which realizes the dynamic association of the parameter update of the Beta distribution with the data error and uncertainty, and achieves the technical effect of improving the speed and adaptability of weight adjustment.

[0043] 6. The method adopted in the present invention obtains the fusion weights of the three models within each total model through variational Bayesian inference calculation, realizes dynamic optimization of model weights, ensures that the weight calculation is not only based on error distribution, but also can adapt to different data characteristics, and improves the technical effect of prediction accuracy.

[0044] 7. The method adopted in the present invention obtains the predicted total production and manufacturing cost. By obtaining the predicted total production and manufacturing cost, the process consumption cost involved in the production and manufacturing process of lyocell fiber is determined. The relevant staff can specifically determine the recovery cost involved in the process consumption cost, so as to carry out refined management of the costs involved in the entire process production and manufacturing.

[0045] 8. The method adopted in the present invention obtains the predicted total production and manufacturing cost, which is helpful to guide the enterprise to carry out future production and sales, effectively reduces the cost of the enterprise in production and manufacturing, and increases the profit of the enterprise in future sales. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a structural block diagram of the present invention.

[0047] Figure 2 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0049] Example 1 A method for predicting the production cost of lyocell fiber comprises the following specific steps: Step 1: Collect historical raw material data, energy consumption data and equipment maintenance data in the production and manufacturing process of Lyocell fibers; raw material data include wood pulp parameter data, NMMO solution parameter data and chemical additive parameter data; energy consumption data include temperature data, pressure data and flow data; equipment maintenance data include equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history; Step 2: Preprocess the raw material data, energy consumption data and equipment maintenance data; data preprocessing is a mature technology in this field, the purpose of which is to remove outliers in the data and process missing values; Step 3: construct and train a total model for raw material consumption prediction, a total model for energy consumption prediction, and a total model for equipment maintenance prediction based on random forest, support vector machine, and long short-term memory network; random forest, support vector machine, and long short-term memory network are all existing technologies in this field; Step 4: Input the raw material data in the current lyocell fiber production process as process parameter group 1 into the total model output of raw material consumption prediction to obtain three raw material consumption prediction values, input the energy consumption data and the equipment operation time in the equipment maintenance data into the total model output of energy consumption prediction as process parameter group 2 to obtain three energy consumption prediction values, and input the equipment maintenance data into the total model output of equipment maintenance prediction as process parameter group 3 to obtain three equipment maintenance prediction values; Step 5: Set the initial weight distribution of the total model for raw material consumption prediction, the total model for energy consumption prediction, and the total model for equipment maintenance prediction, and calculate the mean square error of the three models within each total model. Then update the Beta distribution parameters based on the mean square error. At the same time, introduce Gaussian process regression to calculate the uncertainty of the three models within each total model, and then update the Beta distribution parameters again based on the uncertainty. According to the updated Beta distribution parameters combined with variational Bayesian inference calculation, the fusion weights of the three models within each total model are obtained respectively. Step 6: The three raw material consumption prediction values ​​obtained are calculated according to the fusion weights of the three models within the total model of raw material consumption prediction to obtain the final raw material consumption prediction value after weighted fusion; the three energy consumption prediction values ​​obtained are calculated according to the fusion weights of the three models within the total model of energy consumption prediction to obtain the final energy consumption prediction value after weighted fusion; the three equipment maintenance prediction values ​​obtained are calculated according to the fusion weights of the three models within the total model of equipment maintenance prediction to obtain the final equipment maintenance prediction value after weighted fusion; Step 7: Based on the final raw material consumption forecast value, the final energy consumption forecast value and the final equipment maintenance forecast value, combined with the raw material price, energy consumption price and equipment maintenance price, the raw material forecast cost, energy consumption forecast cost and equipment maintenance forecast cost are calculated to obtain the predicted total production and manufacturing cost; the predicted total production and manufacturing cost is the sum of the raw material forecast cost, energy consumption forecast cost and equipment maintenance forecast cost.

[0050] Example 2 A method for predicting the production cost of lyocell fiber comprises the following specific steps: Step 1: Collect historical raw material data, energy consumption data and equipment maintenance data in the production and manufacturing process of Lyocell fibers; raw material data include wood pulp parameter data, NMMO solution parameter data and chemical additive parameter data; energy consumption data include temperature data, pressure data and flow data; equipment maintenance data include equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history; Step 2: Preprocess raw material data, energy consumption data, and equipment maintenance data; Step 3: Build and train the overall model for raw material consumption prediction, the overall model for energy consumption prediction, and the overall model for equipment maintenance prediction based on random forest, support vector machine, and long short-term memory network; Step 4: Input the raw material data in the current lyocell fiber production process as process parameter group 1 into the total model output of raw material consumption prediction to obtain three raw material consumption prediction values, input the energy consumption data and the equipment operation time in the equipment maintenance data into the total model output of energy consumption prediction as process parameter group 2 to obtain three energy consumption prediction values, and input the equipment maintenance data into the total model output of equipment maintenance prediction as process parameter group 3 to obtain three equipment maintenance prediction values; Step 5: Set the initial weight distribution of the total model for raw material consumption prediction, the total model for energy consumption prediction, and the total model for equipment maintenance prediction, and calculate the mean square error of the three models within each total model. Then update the Beta distribution parameters based on the mean square error. At the same time, introduce Gaussian process regression to calculate the uncertainty of the three models within each total model, and then update the Beta distribution parameters again based on the uncertainty. According to the updated Beta distribution parameters combined with variational Bayesian inference calculation, the fusion weights of the three models within each total model are obtained respectively. Step 6: The three raw material consumption prediction values ​​obtained are calculated according to the fusion weights of the three models within the total model of raw material consumption prediction to obtain the final raw material consumption prediction value after weighted fusion; the three energy consumption prediction values ​​obtained are calculated according to the fusion weights of the three models within the total model of energy consumption prediction to obtain the final energy consumption prediction value after weighted fusion; the three equipment maintenance prediction values ​​obtained are calculated according to the fusion weights of the three models within the total model of equipment maintenance prediction to obtain the final equipment maintenance prediction value after weighted fusion; Step 7: Based on the final raw material consumption forecast value, the final energy consumption forecast value and the final equipment maintenance forecast value, combined with the raw material price, energy consumption price and equipment maintenance price, the raw material forecast cost, energy consumption forecast cost and equipment maintenance forecast cost are obtained to obtain the predicted total production cost.

[0051] In step one, the wood pulp parameter data include wood pulp viscosity, wood pulp polymerization degree and wood pulp methyl fiber content; the NMMO solution parameter data include NMMO solution concentration; the chemical additive parameter data include propylene glycol content and hydroxylamine content; the raw material data also include raw material purchase price data, raw material inventory data and raw material consumption data; the energy consumption data also includes equipment operation time; the temperature data includes dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature and ambient temperature; the pressure data includes solvent delivery pressure, vacuum pressure and ambient air pressure; the flow data includes NMMO solvent flow, water consumption and steam consumption.

[0052] The viscosity of wood pulp, degree of polymerization of wood pulp and methyl cellulose content of wood pulp are monitored and collected in real time through online viscometers and optical measuring instruments; the concentration of NMMO solution is collected through liquid phase concentration detection sensors; the propylene glycol content and hydroxylamine content are detected and collected by chemical sensors; the purchase price data of raw materials, the inventory data of raw materials and the consumption data of raw materials are collected through the enterprise resource planning system and synchronized with the external market database.

[0053] The dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature and ambient temperature are measured by PT100 platinum resistance temperature sensor or thermocouple; the solvent delivery pressure, vacuum pressure and ambient air pressure are collected by MEMS piezoresistive pressure sensor; NMMO solvent flow, water consumption and steam consumption are collected by electromagnetic flowmeter and ultrasonic flowmeter, and the accumulated flow value is calculated in combination with PLC; the reactor temperature, insulation water system temperature, insulation water system pressure, spinning wind system temperature and spinning wind system pressure are collected by SCADA system.

[0054] Equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history are recorded and collected through the MES system.

[0055] Example 3 Based on Example 2, the specific method steps for data preprocessing of raw material data, energy consumption data and equipment maintenance data are as follows: Step a: Perform outlier detection on time series data, numerical data, and non-normal distribution data in raw material data, energy consumption data, and equipment maintenance data, and remove outliers. Finally, perform missing value processing and duplicate data removal. Step b: normalizing raw material data, energy consumption data and equipment maintenance data; Step c: Use Pearson correlation analysis and principal component analysis to extract key features of raw material data, energy consumption data, and equipment maintenance data; Step d: Use K-means cluster analysis and information entropy screening methods to conduct final screening of raw material data, energy consumption data, and equipment maintenance data.

[0056] The specific method of outlier detection for numerical data in step a is: use the 3σ principle to detect outliers, for each data point f i , calculate the mean μ and standard deviation σ of the original data, if it satisfies: ; It is judged as abnormal data and is removed; is the ith data point.

[0057] For outliers in non-normal distribution, Z-score standardization is used to make them meet the standard normal distribution. The specific method of outlier detection for non-normal distribution data in step a is: the interquartile range method is used to detect outliers, and the first quartile Q1 and the third quartile Q3 are calculated. The set abnormal range is as follows: ; ; Data outside this range are considered outliers and are removed; where IQR means interquartile range.

[0058] The specific method for handling missing values ​​is as follows: time series data is filled using linear interpolation; if the missing ratio of numerical data is less than 20%, k-nearest neighbor interpolation is used to fill it; if the missing ratio of non-normal distribution data is less than 20%, k-nearest neighbor interpolation is used to fill it; if the missing ratio of non-normal distribution data is more than 20%, the non-normal distribution data is excluded.

[0059] The time series data include inventory data of raw materials, consumption data of raw materials, dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature, ambient temperature, solvent delivery pressure, vacuum pressure, insulation water system pressure, spinning wind system pressure, ambient air pressure, NMMO solvent flow, water consumption, steam consumption, equipment operating time and number of failures.

[0060] Numerical data include wood pulp viscosity, wood pulp polymerization degree, wood pulp methyl fiber content, NMMO solution concentration, propylene glycol content, hydroxylamine content, raw material purchase price data, maintenance cost and equipment failure rate; non-normal distribution data include raw material purchase price data, raw material inventory data, raw material consumption data, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history.

[0061] Min-Max normalization is used to normalize raw material data, energy consumption data, and equipment maintenance data. The specific formula is as follows: ; In the formula, x is the original data value; x min is the minimum value of the original data; x max is the maximum value of the original data; For data with abnormal distribution, Z-score standardization is used: ; In the formula, μ is the mean of the original data; σ is the standard deviation, is the data value after Z-score standardization, x is the original data value.

[0062] In step c, the specific method steps for extracting key features of raw material data, energy consumption data and equipment maintenance data using Pearson correlation analysis and principal component analysis are as follows: Step a1: Calculate the relevant features between the same category data and different category data, analyze the linear correlation between variables, and then screen redundant features, calculate the Pearson correlation coefficient between features, and specifically calculate the Pearson correlation coefficient between the following features: Within the raw material data, analyze the correlation between wood pulp viscosity, wood pulp polymerization degree, and wood pulp methyl fiber content to determine their linear dependence in the data set; at the same time, analyze the correlation between NMMO solution concentration, propylene glycol content, and hydroxylamine content to evaluate the impact of chemical additives on the production process; in addition, it is necessary to calculate the correlation between raw material inventory data, raw material consumption data, and raw material purchase price data to analyze the impact of inventory management on costs.

[0063] Within the energy consumption data, the correlation between temperature data is calculated to determine the temperature control relationship in different production stages. At the same time, the interaction between pressure data is analyzed to optimize the pressure regulation mechanism; in addition, the correlation between flow data is calculated to optimize solvent and energy consumption strategies.

[0064] Within the equipment maintenance data, calculate the correlation between equipment operating time, number of failures, and equipment failure rate to evaluate the impact of equipment aging on failure rate; at the same time, analyze the relationship between maintenance cost and equipment operating time and number of failures to optimize maintenance budget and repair plan; in addition, conduct correlation analysis of cross-category features, for example: calculate the correlation between raw material consumption data and energy consumption data to evaluate the relationship between raw material consumption and energy use. Calculate the correlation between equipment operating time and energy consumption data to analyze the impact of equipment operating status on energy consumption; finally, calculate the correlation between maintenance cost and energy consumption data to optimize equipment maintenance strategy and energy consumption management; The specific calculation formula is as follows: ; When |r|>0.8, the two features are determined to be highly correlated and one of them is removed; where r is the Pearson correlation coefficient, h i is the i-th observation value of variable h, y i is the ith observation value of variable y, is the mean of variable h, μ y is the mean of variable y; Step b1: Perform principal component analysis to reduce the dimension. First, construct a standardized data matrix X with a dimension of m×n, where m is the number of samples and n is the number of features. Then calculate the covariance matrix , the specific calculation formula is as follows: ; Where, X T is the transposed matrix of the standardized data matrix X; Step c1: Solve the covariance matrix The eigenvalues ​​and eigenvectors of The eigenvalues ​​λ1, λ2, ..., λn of are sorted from large to small according to the eigenvalues, and the cumulative contribution rate is calculated; the first k eigenvectors with cumulative contribution rates exceeding 95% are selected to form a dimensionality reduction projection matrix W, and the projection data is obtained through the dimensionality reduction projection matrix W, and finally the data dimension after dimensionality reduction by principal component analysis is reduced from n dimensions to k dimensions; the reason for selecting 95% as the cumulative contribution rate threshold is that a good balance can be achieved between information retention and dimensionality reduction effect. If the cumulative contribution rate is too low, it may lead to the loss of important information and affect the accuracy of data analysis; if it is too high, the effect of dimensionality reduction is limited and the computational complexity cannot be effectively reduced; therefore, 95% is used as an empirical threshold to ensure that most of the information is retained, while significantly reducing the data dimension and improving the generalization ability and computational efficiency of the model; then, the original data is linearly transformed through the dimensionality reduction projection matrix W to obtain the projection data, and finally the data dimension after dimensionality reduction by principal component analysis is reduced from n The dimension is reduced to k Dimension; the specific formula for obtaining the projection data is as follows: ; Where W is the dimension reduction projection matrix, and X′ is the feature data after dimension reduction.

[0065] K-means cluster analysis and information entropy screening methods were used to conduct final screening of raw material data, energy consumption data, and equipment maintenance data to extract key features and remove redundant data, thereby improving the calculation efficiency and prediction accuracy of the model. In terms of raw material data, wood pulp viscosity, wood pulp polymerization degree, wood pulp methyl fiber content, NMMO solution concentration, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data, and raw material consumption data were screened to determine which raw material parameters have the greatest impact on production costs and energy consumption. In terms of energy consumption data, Dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature, ambient temperature, solvent delivery pressure, vacuum pressure, insulation water system pressure, spinning wind system pressure, ambient air pressure, NMMO solvent flow, water consumption and steam consumption were screened to extract key energy consumption characteristics and optimize energy utilization efficiency; in terms of equipment maintenance data, equipment operating time, maintenance cost, number of failures and equipment failure rate were screened to analyze the impact of equipment status on production efficiency and maintenance cost. The specific method steps for optimizing the final screening of maintenance strategies are as follows: Step a2: Use K-means cluster analysis, first initialize, set the number of clusters k=5, select k random samples as the initial cluster centers, and then calculate the Euclidean distance from the sample to the cluster center. The specific formula is as follows: ; In the formula, The meaning of is expressed as the Euclidean distance between the sample point s and the cluster center c, which measures the similarity between the data point and the cluster center. The smaller the distance, the closer the data point is to the cluster center. is the i-th data sample, is the new cluster center of the i-th cluster, and n is the n-dimensional space; Step b2: Reassign clusters, calculate the distance between each sample point and all cluster centers, and assign the sample point to the nearest cluster; Step c2: Update the cluster center. First, calculate the new cluster center and continue to iterate until convergence. When the cluster center change is less than the set threshold, stop the iteration. The specific calculation formula for calculating the new cluster center is: ; In the formula, is the new cluster center of the ith cluster, Cluster C i The number of internal sample points, s is the data sample point; Step d2: Filter out representative data, calculate the average distance from each cluster to the cluster center, and select 10% of the data around the cluster center in each cluster as training samples; Step e2: Although the most representative samples have been selected through the intra-cluster distance in step d2, the importance and information content of different clusters may still vary greatly; some clusters may contain too much redundant information, while some clusters may contribute more to the data distribution; therefore, it is necessary to further evaluate the information content of each cluster through information entropy screening and calculate the information entropy of each cluster. , the specific formula is as follows: ; In the formula, Cluster The probability of category j in ; is the number of categories within the cluster; Step f2: Filter the cluster with the highest information entropy, calculate the information entropy values ​​of all clusters, and select the top 50% clusters with the highest information entropy. Among the selected clusters, retain the samples around the center of the cluster and remove outliers to form the final training data set.

[0066] Example 4 Based on Example 3, in step three, the total model for raw material consumption prediction, the total model for energy consumption prediction and the total model for equipment maintenance prediction are constructed and trained based on random forest, support vector machine and long short-term memory network. Specifically, the total model for raw material consumption prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first raw material consumption prediction model constructed based on random forest, a second raw material consumption prediction model constructed based on support vector machine and a third raw material consumption prediction model constructed based on long short-term memory network; the total model for energy consumption prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first energy consumption prediction model constructed based on random forest, a second energy consumption prediction model constructed based on support vector machine and a third energy consumption prediction model constructed based on long short-term memory network; the total model for equipment maintenance prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first equipment maintenance prediction model constructed based on random forest, a second equipment maintenance prediction model constructed based on support vector machine and a third equipment maintenance prediction model constructed based on long short-term memory network.

[0067] The specific method steps for constructing the first raw material consumption prediction model, the first energy consumption prediction model and the first equipment maintenance prediction model based on random forest are as follows: Step a3: constructing a first raw material consumption prediction model based on random forest; the specific construction method of the first raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, training to obtain the first raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b3: constructing a first energy consumption prediction model based on random forest; the specific construction method of the first energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of the training set, and taking power consumption, water consumption and steam consumption as output features, training to obtain the first energy consumption prediction model; Step c3: Construct a first equipment maintenance prediction model based on random forest; the specific construction method of the first equipment maintenance prediction model is: use equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use equipment failure rate and maintenance times as output features, and train to obtain the first equipment maintenance prediction model.

[0068] During the training process, in order to prevent overfitting and underfitting, the random forest model is composed of 100 decision trees based on experience, and the maximum depth of each tree is set to 15 to prevent overfitting; in the training stage, the Bootstrap sampling method is first used to randomly extract subsamples from the training data set, that is, m samples are randomly extracted with replacement from the original data set as the training data set for each tree, and each sample may be extracted multiple times or not selected, thus forming multiple different data subsets; the main purpose of doing this is to improve the generalization ability of the model, reduce overfitting, and enhance the stability of the model; in addition, when each decision tree splits a node, it randomly selects some features for decision-making to ensure the diversity of the model, further reduce the dependence on a single feature, and improve the overall prediction effect.

[0069] For regression tasks, such as raw material consumption prediction, energy consumption prediction, or equipment maintenance prediction, the mean square error (MSE) is used as the loss function to minimize the error between the predicted value and the true value. The calculation formula is as follows: ; in, is the true value, is the predicted value, N is the number of samples; for classification tasks (such as equipment failure prediction), the Gini index is used As a feature splitting criterion to measure the impurity of the data, the calculation formula is as follows: ; in, p i For the category in the current node k The sample proportion of k is the total number of categories.

[0070] After training, the test data set is used for prediction. The final output of the random forest is calculated by integrating multiple decision trees to obtain the final prediction value. is the weighted average of all decision trees: ; in, T is the number of decision trees, For the t The predicted value of the tree.

[0071] The training and construction process based on random forest is a mature technology in this field. The innovation of this part lies in the matching of input data features with output features, so as to obtain a predictable model through training and finally obtain the predicted value.

[0072] The specific method steps for constructing the second raw material consumption prediction model, the second energy consumption prediction model and the second equipment maintenance prediction model based on the support vector machine are as follows: Step a4: constructing a second raw material consumption prediction model based on a support vector machine; the specific construction method of the second raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, and training to obtain the second raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b4: constructing a second energy consumption prediction model based on a support vector machine; the specific construction method of the second energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of a training set, and taking power consumption, water consumption and steam consumption as output features, and training to obtain the second energy consumption prediction model; Step c4: Construct a second equipment maintenance prediction model based on support vector machine; the specific construction method of the second equipment maintenance prediction model is: use equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use equipment failure rate and maintenance times as output features, and train to obtain the second equipment maintenance prediction model.

[0073] During the training process, the optimization goal of support vector regression is to minimize the ε-insensitive loss function, that is, to ensure the generalization ability of the model through the combination of regularization terms and error penalty terms. Its objective function is as follows: ; middle, w1 is the model weight vector, b is the bias term, N is the number of samples, is the regularization parameter (the optimization range is set to [0.1, 100]), which is used to control the balance between error and model complexity; is a slack variable, is another slack variable to handle the error tolerance interval ε Samples of ε is the error tolerance interval (the optimization range is set to [0.01,1]), that is, when the error is less than ε No loss is included.

[0074] In order to enhance the model's learning ability for nonlinear data, the present invention uses a radial basis kernel function for high-dimensional mapping, and its calculation formula is as follows: ; in, is the kernel parameter, which controls the influence range of data mapping to high-dimensional space. The optimization range is set to [10 −3 ,10], and select the optimal value through cross-validation; is the input data point, is the center point of the radial basis kernel function.

[0075] At the same time, cross validation is used to optimize hyperparameters , γ and ε to ensure the optimal model configuration; secondly, the model is optimized using stochastic gradient descent, and the maximum number of iterations is set to 1000 to ensure that the model converges within a reasonable computing time. The update formula is: ; in, For the t+ The weight of 1 round of iteration, η is the learning rate, is the gradient of the loss function; finally, the model predicts using the trained weight parameters w2 and the bias term b Make predictions: ; in, is the eigenvector after kernel mapping, is the final predicted value, weight parameter w2 The transpose of .

[0076] The training and construction process based on support vector machines is a mature technology in this field. The innovation of this part lies in the matching of input data features with output features, so as to obtain a predictable model through training and finally obtain the predicted value.

[0077] The specific method steps for constructing the third raw material consumption prediction model, the third energy consumption prediction model and the third equipment maintenance prediction model based on the long short-term memory network are as follows: Step a5: constructing a third raw material consumption prediction model based on the long short-term memory network; the specific construction method of the third raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, and training to obtain the third raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b5: constructing a third energy consumption prediction model based on the long short-term memory network; the specific construction method of the third energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of the training set, and taking power consumption, water consumption and steam consumption as output features, training to obtain the third energy consumption prediction model; Step c5: construct a third equipment maintenance prediction model based on the long short-term memory network; the specific construction method of the third equipment maintenance prediction model is: use the equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use the equipment failure rate and maintenance number as output features, and train to obtain the third equipment maintenance prediction model.

[0078] During the training process, LSTM inputs the training data into the model for training. The LSTM model structure includes LSTM layer, fully connected layer, optimizer and loss function. The LSTM layer contains 64 LSTM units and uses Tanh activation function to enhance nonlinear expression ability; the fully connected layer includes two layers of neural network, which are composed of 128 neurons and 64 neurons respectively, and uses ReLU activation function for nonlinear transformation to improve the model fitting ability.

[0079] During the optimization process, LSTM uses the Adam optimizer, and its parameters are updated as follows: ; ; Among them, m t represents the exponential moving average g of the first-order moment estimate in the Adam optimizer t is the gradient, v t represents an unbiased estimate of the second-order moment; and is the momentum parameter, which makes the model converge faster in the high-dimensional optimization space. The loss function uses the mean square error MSE, and the calculation formula is as follows: ; in, is the true value, is the predicted value, N is the number of samples, and the mean square error is used to measure the error between the predicted value and the true value; During the training process, each batch contains 32 samples (Batch Size=32); forward propagation is used to calculate the output, and the LSTM processes the input data sequentially through the time steps, and finally the prediction value is calculated by the fully connected layer: ; in, W1 and W 2 is the weight matrix of the fully connected layer, b1 and b2 are bias terms, and h is the hidden state vector of the LSTM layer. Then the loss function is calculated, and the gradient is calculated by back propagation. Adam is used for optimization, and the maximum number of training iterations is set to 200 to ensure training convergence. The training and construction process based on the long short-term memory network is a mature technology in this field. The innovation of this part lies in the matching of input data features with output features, so as to obtain a predictable model through training and finally obtain the predicted value.

[0080] Example 5 Based on Example 4, in step 5, the initial weight distribution of the total model for raw material consumption prediction, the total model for energy consumption prediction, and the total model for equipment maintenance prediction is set, and the mean square error of the three models within each total model is calculated, and then Gaussian process regression is introduced to calculate the uncertainty of the three models within each total model. Finally, the fusion weights of the three models within each total model are obtained according to the variational Bayesian inference calculation. Specifically, it is assumed that the weights of the three models within each total model obey the Beta distribution: ; In the formula, The weight coefficients of the three models within the total model for raw material consumption prediction, the weight coefficients of the three models within the total model for energy consumption prediction, or the weight coefficients of the three models within the total model for equipment maintenance prediction, and Set as initial parameters, generally: ; In the formula, is a positive number, ensuring that the weights are evenly distributed in the initial state; The prediction errors of the three models within the total model for raw material consumption prediction, the prediction errors of the three models within the total model for energy consumption prediction, or the prediction errors of the three models within the total model for equipment maintenance prediction are evaluated by calculating the mean square error of the three models within the total model for raw material consumption prediction, the mean square error of the three models within the total model for energy consumption prediction, or the mean square error of the three models within the total model for equipment maintenance prediction. The specific calculation formula is as follows: ; ; ; In the formula, represents a mean square error of the first raw material consumption prediction model, the first energy consumption prediction model, or the first equipment maintenance prediction model based on random forest; represents a mean square error of a second raw material consumption prediction model, a second energy consumption prediction model, or a second equipment maintenance prediction model based on a support vector machine; represents the mean square error of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network; N represents the total number of training samples; Represents the true value of the i-th sample; represents the predicted value of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model based on random forest for the i-th sample; represents the predicted value of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model based on the support vector machine for the i-th sample; represents the predicted value of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network for the i-th sample; Then update the Beta distribution parameters according to the mean square error: ; ; In the formula, It represents a distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction. represents another distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; represents the mean square error of the total model for raw material consumption prediction, the mean square error of the total model for energy consumption prediction, or the mean square error of the total model for equipment maintenance prediction; Gaussian process regression is introduced to calculate the uncertainty of each model. The specific formula is as follows: ; In the formula, It means the uncertainty of the model, which is used to measure the uncertainty of the total model of raw material consumption prediction, the total model of energy consumption prediction and the total model of equipment maintenance prediction on all samples; N is the total number of training samples; It is expressed as the prediction variance of the total model for raw material consumption prediction, the total model for energy consumption prediction or the total model for equipment maintenance prediction on all samples. This variance is calculated based on Gaussian process regression and indicates the degree of uncertainty of the model output under the same input conditions. If the variance of the model prediction value on different training sets is large, it means that the confidence of the model in this input area is low. The specific solution formula is as follows: ; In the formula, represents the predicted value of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction for the i-th sample; It represents the average prediction value of the total model for raw material consumption prediction, the total model for energy consumption prediction or the total model for equipment maintenance prediction on all samples; Then introduce uncertainty into the Beta distribution update: ; ; In the formula, represents a distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction after update; represents another distribution parameter in the updated fusion weight calculation of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; these distribution parameters are updated at each iteration to reflect the uncertainty of the model; Finally, the final weights are calculated using variational Bayesian inference: ; In the formula, The model weight after the t+1th iteration of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; Represents the contribution of actual data; Then, the fusion weights of the three models within each model are obtained: ; ; ; In the formula, The meaning of is the weight coefficient of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; Meaning is the weight coefficient of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; The meaning is the weight coefficient of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; Meaning is another distribution parameter in the fusion weight calculation of the updated first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; Meaning is another distribution parameter in the fusion weight calculation of the updated second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; Meaning is another distribution parameter in the calculation of the fusion weight of the updated third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; It means the sum of the predicted output values ​​of all training samples of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model based on random forest; The meaning is the sum of the predicted output values ​​of all training samples of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model based on the support vector machine; It means the sum of the predicted output values ​​of all training samples of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network.

[0081] Process parameter group 1 includes wood pulp viscosity, wood pulp polymerization degree, wood pulp methyl fiber content, NMMO solution concentration, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data; the physical properties and chemical composition of wood pulp determine its solubility in the production process, the NMMO solution concentration and chemical additive content affect the stability of the solvent system, and the raw material inventory data and raw material purchase price data reflect the impact of the supply chain on consumption. By comprehensively considering these factors, the model can accurately predict the consumption of raw materials in the production process and provide decision support for raw material procurement and inventory management; the raw material consumption forecast value includes wood pulp consumption, NMMO solution consumption and chemical additive consumption; the chemical additive consumption includes propylene glycol consumption and hydroxylamine consumption; process parameter group 2 includes temperature data, pressure data, flow data and equipment operation time; the energy consumption forecast value includes electricity consumption, water consumption and steam consumption. steam consumption; temperature data and pressure data reflect the load status of the energy system, flow data is directly related to energy consumption, and equipment operation time determines the total energy consumption of the entire production cycle; based on these input characteristics, the model can effectively predict electricity consumption, water consumption and steam consumption, thereby optimizing energy management and improving production efficiency; process parameter group 3 includes equipment operation time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history; the equipment maintenance prediction value includes equipment failure rate and equipment maintenance number; equipment operation time and number of failures directly reflect the use status of the equipment, maintenance cost and maintenance history provide past maintenance conditions and repair frequency, and equipment vibration data is an important indicator of equipment health status, which can warn of possible mechanical failures in advance. Through these input characteristics, the model can accurately predict the equipment failure rate and equipment maintenance number, thereby optimizing equipment maintenance plans, reducing unexpected downtime, and improving production stability.

[0082] The specific formulas for calculating the final weighted fusion forecast value of raw material consumption, the final energy consumption forecast value, and the final equipment maintenance forecast value are as follows: ; In the formula, Indicates the final raw material consumption forecast value, the final energy consumption forecast value or the final equipment maintenance forecast value; when represents the raw material consumption prediction value of the first raw material consumption prediction model based on random forest, represents the raw material consumption prediction value of the second raw material consumption prediction model based on support vector machine, When represents the raw material consumption forecast value of the third raw material consumption forecast model based on the long short-term memory network, then represents the weight coefficient of the first raw material consumption prediction model, represents the weight coefficient of the second raw material consumption forecast model and represents the weight coefficient of the third raw material consumption forecast model; when represents the energy consumption prediction value of the first energy consumption prediction model based on random forest, represents the energy consumption prediction value of the second energy consumption prediction model based on the support vector machine, When represents the energy consumption prediction value of the third energy consumption prediction model based on the long short-term memory network, then represents the weight coefficient of the first energy consumption prediction model, represents the weight coefficient of the second energy consumption prediction model and represents the weight coefficient of the third energy consumption prediction model; when represents the equipment maintenance prediction value of the first equipment maintenance prediction model based on random forest, represents the equipment maintenance prediction value of the second equipment maintenance prediction model based on support vector machine, When represents the equipment maintenance prediction value of the third equipment maintenance prediction model based on the long short-term memory network, then represents the weight coefficient of the first equipment maintenance prediction model, represents the weight coefficient and Represents the weight coefficient of the third equipment maintenance prediction model.

[0083] Example 6 Based on Example 5, the specific calculation formula for the predicted total production cost obtained in step 7 is as follows: ; In the formula, Meaning is the predicted total production and manufacturing cost, Meaning is the cost of raw materials, Meaning is energy consumption cost, It means equipment maintenance cost.

[0084] The calculation formula for raw material cost is as follows: ; In the formula, is the final wood pulp consumption, is the price of wood pulp, is the final NMMO solution consumption, is the price of NMMO solution, is the final propylene glycol consumption, is the price of propylene glycol, is the final hydroxylamine consumption, is the price of hydroxylamine.

[0085] The calculation formula for energy consumption cost is as follows: ; In the formula, is the final power consumption, For the price of electricity, is the final water consumption, For the price of water, is the final steam consumption, For the price of steam.

[0086] Furthermore, the specific calculation formula of the equipment maintenance cost is as follows:

[0087] The specific calculation formula for equipment maintenance cost is as follows: ; In the formula, is the fixed maintenance cost of the equipment, is the final number of failures, is the cost of repairing a single failure.

[0088] Example 7 like Figure 1 As shown, process parameter group 1 is input into a first raw material consumption prediction model constructed based on random forest, a second raw material consumption prediction model constructed based on support vector machine, and a third raw material consumption prediction model constructed based on long short-term memory network, thereby obtaining three raw material consumption prediction values, and the three raw material consumption prediction values ​​are weightedly fused to obtain a final raw material consumption prediction value; process parameter group 2 is input into a first energy consumption prediction model constructed based on random forest, a second energy consumption prediction model constructed based on support vector machine, and a third energy consumption prediction model constructed based on long short-term memory network, thereby obtaining three energy consumption prediction values, and the three energy consumption prediction values ​​are weightedly fused to obtain a final energy consumption prediction value. The process parameter group 3 is input into the first equipment maintenance prediction model constructed based on random forest, the second equipment maintenance prediction model constructed based on support vector machine and the third equipment maintenance prediction model constructed based on long short-term memory network, so as to obtain three equipment maintenance prediction values, and the three equipment maintenance prediction values ​​are weightedly fused to obtain the final equipment maintenance prediction value; the final equipment maintenance prediction value, the final energy consumption prediction value and the final raw material consumption prediction value are combined with the raw material price, energy consumption price and equipment maintenance price to obtain the raw material prediction cost, energy consumption prediction cost and equipment maintenance prediction cost; finally, the raw material prediction cost, energy consumption prediction cost and equipment maintenance prediction cost are added together to obtain the predicted total production and manufacturing cost.

[0089] Example 8 like Figure 2 As shown, the process of the method of the present invention is as follows: first, data collection and preprocessing are performed; after data cleaning, data normalization, principal component analysis and clustering information processing, the data is used for model construction and training; the model construction and training method is based on random forest trees, support vector machines and long short-term memory networks; predictions are made according to the constructed model, and the predicted values ​​are weighted and fused to obtain the final predicted values; the predicted total production cost is obtained based on the final predicted values ​​combined with the price.

[0090] Example 9 Based on Example 6, an application of a method for predicting the production cost of lyocell fibers is suitable for predicting the cost of producing lyocell fibers.

[0091] The above description is a detailed description of the preferred feasible embodiment of the present application, but the embodiment is not intended to limit the patent application scope of the present application. All equivalent changes or modified changes made under the technical spirit suggested by the present application should fall within the patent scope covered by the present application.

Claims

1. A method for predicting the production cost of lyocell fiber, characterized in that: The specific steps include: Step 1: Collect historical raw material data, energy consumption data and equipment maintenance data in the production and manufacturing process of Lyocell fibers; raw material data include wood pulp parameter data, NMMO solution parameter data and chemical additive parameter data; energy consumption data include temperature data, pressure data and flow data; equipment maintenance data include equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history; Step 2: Preprocess raw material data, energy consumption data, and equipment maintenance data; Step 3: Build and train the overall model for raw material consumption prediction, the overall model for energy consumption prediction, and the overall model for equipment maintenance prediction; Step 4: Input the process parameter group 1, process parameter group 2 and process parameter group 3 in the current lyocell fiber production process into the three total models in step 3 respectively, and obtain three raw material consumption prediction values, three energy consumption prediction values ​​and three equipment maintenance prediction values; Step 5: Set the initial weight distribution of the total model for raw material consumption prediction, the total model for energy consumption prediction, and the total model for equipment maintenance prediction, and calculate the mean square error of the three models within each total model. Then update the Beta distribution parameters of the total model based on the mean square error. At the same time, introduce Gaussian process regression to calculate the uncertainty of the three models within each total model, and then update the Beta distribution parameters again based on the uncertainty. Then, based on the updated Beta distribution parameters combined with variational Bayesian inference, calculate the fusion weights of the three models within each total model. Step 6: According to the fusion weights of the three types of prediction values ​​in step 4 and the three models in the corresponding total model, the final prediction value after weighted fusion is calculated; Step 7: Based on the final forecast value, combined with raw material prices, energy consumption prices and equipment maintenance prices, the predicted total production and manufacturing cost is obtained.

2. A method for predicting the production cost of lyocell fiber according to claim 1, characterized in that: In the step 3, the overall model for raw material consumption prediction, the overall model for energy consumption prediction and the overall model for equipment maintenance prediction are constructed and trained based on random forest, support vector machine and long short-term memory network; in the step 4, process parameter group 1 is the raw material data in the current lyocell fiber production process, process parameter group 2 is the energy consumption data in the current lyocell fiber production process and the equipment operation time in the equipment maintenance data, and process parameter group 3 is the equipment maintenance data in the current lyocell fiber production process; the specific method of step 4 is: inputting process parameter group 1 into the overall model output of raw material consumption prediction to obtain three raw material consumption prediction values, inputting process parameter group 2 into the overall model output of energy consumption prediction to obtain three energy consumption prediction values, and inputting process parameter group 3 into the overall model output of equipment maintenance prediction to obtain three equipment maintenance prediction values; The three types of prediction values ​​in step 6 include three raw material consumption prediction values, three energy consumption prediction values ​​and three equipment maintenance prediction values; the final prediction value includes the final raw material consumption prediction value, the final energy consumption prediction value and the final equipment maintenance prediction value; the specific method of step 6 is: the three raw material consumption prediction values ​​are obtained, according to the fusion weights of the three models within the total model of raw material consumption prediction, to calculate the final raw material consumption prediction value after weighted fusion; The three energy consumption prediction values ​​obtained are calculated according to the fusion weights of the three models within the total model of energy consumption prediction to obtain the final energy consumption prediction value after weighted fusion; The three equipment maintenance prediction values ​​obtained are calculated according to the fusion weights of the three models within the total model of the equipment maintenance prediction to obtain the final equipment maintenance prediction value after weighted fusion; the specific method of the step seven is: according to the final raw material consumption prediction value, the final energy consumption prediction value and the final equipment maintenance prediction value, combined with the raw material price, energy consumption price and equipment maintenance price, the raw material prediction cost, energy consumption prediction cost and equipment maintenance prediction cost are obtained, thereby obtaining the predicted total production and manufacturing cost.

3. A method for predicting the production cost of lyocell fiber according to claim 1, characterized in that: The wood pulp parameter data in step one include wood pulp viscosity, wood pulp polymerization degree and wood pulp methyl fiber content; the NMMO solution parameter data include NMMO solution concentration; the chemical additive parameter data include propylene glycol content and hydroxylamine content; the raw material data also include raw material purchase price data, raw material inventory data and raw material consumption data; the energy consumption data also includes equipment operation time; the temperature data includes dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature and ambient temperature; the pressure data includes solvent delivery pressure, vacuum pressure and ambient air pressure; the flow data includes NMMO solvent flow, water consumption and steam consumption.

4. A method for predicting the production cost of lyocell fiber according to claim 3, characterized in that: The viscosity of wood pulp, degree of polymerization of wood pulp and methyl cellulose content of wood pulp are monitored and collected in real time through online viscometers and optical measuring instruments; the concentration of NMMO solution is collected through liquid phase concentration detection sensors; the propylene glycol content and hydroxylamine content are detected and collected by chemical sensors; the purchase price data of raw materials, the inventory data of raw materials and the consumption data of raw materials are collected through the enterprise resource planning system and synchronized with the external market database.

5. The method for predicting the production cost of lyocell fiber according to claim 3, characterized in that: The dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature and ambient temperature are measured by PT100 platinum resistance temperature sensor or thermocouple; the solvent delivery pressure, vacuum pressure and ambient air pressure are collected by MEMS piezoresistive pressure sensor; NMMO solvent flow, water consumption and steam consumption are collected by electromagnetic flowmeter and ultrasonic flowmeter, and the accumulated flow value is calculated in combination with PLC; the reactor temperature, insulation water system temperature, insulation water system pressure, spinning wind system temperature and spinning wind system pressure are collected by SCADA system.

6. The method for predicting the production cost of lyocell fiber according to claim 1, characterized in that: Equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history are recorded and collected through the MES system.

7. The method for predicting the production cost of lyocell fiber according to claim 1, characterized in that: The specific steps for data preprocessing of raw material data, energy consumption data and equipment maintenance data are as follows: Step a: Perform outlier detection on time series data, numerical data, and non-normal distribution data in raw material data, energy consumption data, and equipment maintenance data, and remove outliers. Finally, perform missing value processing and duplicate data removal. Step b: normalizing raw material data, energy consumption data and equipment maintenance data; Step c: Use Pearson correlation analysis and principal component analysis to extract key features of raw material data, energy consumption data, and equipment maintenance data; Step d: Use K-means cluster analysis and information entropy screening methods to conduct final screening of raw material data, energy consumption data, and equipment maintenance data.

8. The method for predicting the production cost of lyocell fiber according to claim 7, characterized in that: The specific method of performing outlier detection on numerical data in step a is: using the 3σ principle to detect outliers, for each data point f i , calculate the mean μ and standard deviation σ of the original data, if it satisfies: ； It is judged as abnormal data and is removed; where, is the ith data point.

9. The method for predicting the production cost of lyocell fiber according to claim 7, characterized in that: The specific method of performing outlier detection on non-normal distribution data in step a is: using the interquartile range method to detect outliers, calculating the first quartile Q1 and the third quartile Q3, and setting the outlier range as follows: ； ； Data outside this range are considered outliers and are removed; where IQR means interquartile range.

10. The method for predicting the production cost of lyocell fiber according to claim 7, characterized in that: The specific method for handling missing values ​​is as follows: time series data is filled using linear interpolation; if the missing ratio of numerical data is less than 20%, k-nearest neighbor interpolation is used to fill it; if the missing ratio of non-normal distribution data is less than 20%, k-nearest neighbor interpolation is used to fill it; if the missing ratio of non-normal distribution data is more than 20%, the non-normal distribution data is excluded.

11. A method for predicting the production cost of lyocell fiber according to claim 10, characterized in that: The time series data include inventory data of raw materials, consumption data of raw materials, dissolution temperature, reactor temperature, insulation water system temperature, spinning wind system temperature, coagulation bath temperature, ambient temperature, solvent delivery pressure, vacuum pressure, insulation water system pressure, spinning wind system pressure, ambient air pressure, NMMO solvent flow, water consumption, steam consumption, equipment operating time and number of failures.

12. The method for predicting the production cost of lyocell fiber according to claim 10, characterized in that: The numerical data include wood pulp viscosity, wood pulp polymerization degree, wood pulp methyl fiber content, NMMO solution concentration, propylene glycol content, hydroxylamine content, raw material purchase price data, maintenance cost and equipment failure rate; the non-normal distribution data include raw material purchase price data, raw material inventory data, raw material consumption data, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history.

13. The method for predicting the production cost of lyocell fiber according to claim 7, characterized in that: Min-Max normalization is used to normalize raw material data, energy consumption data, and equipment maintenance data. The specific formula is as follows: ； In the formula, x is the original data value; x min is the minimum value of the original data; x max is the maximum value of the original data; For data with abnormal distribution, Z-score standardization is used: ； In the formula, μ is the mean of the original data; σ is the standard deviation, is the data value after Z-score standardization, x is the original data value.

14. The method for predicting the production cost of lyocell fiber according to claim 7, characterized in that: The specific method steps for extracting key features of raw material data, energy consumption data and equipment maintenance data using Pearson correlation analysis and principal component analysis in step c are as follows: Step a1: Calculate the Pearson correlation coefficient between features. The specific formula is as follows: ； When |r|>0.8, the two features are determined to be highly correlated and one of them is removed; where r is the Pearson correlation coefficient, h i is the i-th observation value of variable h, y i is the ith observation value of variable y, is the mean of variable h, μ y is the mean of variable y; Step b1: Perform principal component analysis to reduce the dimension. First, construct a standardized data matrix X with a dimension of m×n, where m is the number of samples and n is the number of features. Then calculate the covariance matrix , the specific calculation formula is as follows: ； In the formula, X T is the transposed matrix of the standardized data matrix X; Step c1: Solve the covariance matrix The eigenvalues ​​and eigenvectors of , and sort them from large to small according to the eigenvalues, and calculate the cumulative contribution rate; select the first k eigenvectors with cumulative contribution rates exceeding 95% to form a dimensionality reduction projection matrix W, and obtain projection data through the dimensionality reduction projection matrix W, and finally reduce the data dimension after principal component analysis from n dimensions to k dimensions; the specific formula for obtaining the projection data is as follows: ； Where W is the dimension reduction projection matrix, and X′ is the feature data after dimension reduction.

15. The method for predicting the production cost of lyocell fiber according to claim 7, characterized in that: The specific steps for final screening of raw material data, energy consumption data and equipment maintenance data using K-means cluster analysis and information entropy screening methods are as follows: Step a2: Use K-means cluster analysis, first initialize, set the number of clusters k=5, select k random samples as the initial cluster centers, and then calculate the Euclidean distance from the sample to the cluster center. The specific formula is as follows: ； In the formula, The meaning of is expressed as the Euclidean distance between the sample point s and the cluster center c; is the i-th data sample, is the new cluster center of the i-th cluster, and n is the n-dimensional space; Step b2: Reassign clusters, calculate the distance between each sample point and all cluster centers, and assign the sample point to the nearest cluster; Step c2: Update the cluster center. First, calculate the new cluster center and continue to iterate until convergence. When the cluster center change is less than the set threshold, stop the iteration. The specific calculation formula for calculating the new cluster center is: ； In the formula, is the new cluster center of the ith cluster, Cluster C i The number of internal sample points, s is the data sample point; Step d2: Filter out representative data, calculate the average distance from each cluster to the cluster center, and select 10% of the data around the cluster center in each cluster as training samples; Step e2: Through information entropy screening, further evaluate the information content of each cluster and calculate the information entropy of each cluster , the specific formula is as follows: ； In the formula, Cluster The probability of category j in ; is the number of categories within the cluster; Step f2: Filter the cluster with the highest information entropy, calculate the information entropy values ​​of all clusters, and select the top 50% clusters with the highest information entropy. Among the selected clusters, retain the samples around the center of the cluster and remove outliers to form the final training data set.

16. The method for predicting the production cost of lyocell fiber according to claim 2, characterized in that: The overall model for raw material consumption prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first raw material consumption prediction model constructed based on random forest, a second raw material consumption prediction model constructed based on support vector machine and a third raw material consumption prediction model constructed based on long short-term memory network; the overall model for energy consumption prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first energy consumption prediction model constructed based on random forest, a second energy consumption prediction model constructed based on support vector machine and a third energy consumption prediction model constructed based on long short-term memory network; the overall model for equipment maintenance prediction constructed and trained based on random forest, support vector machine and long short-term memory network includes a first equipment maintenance prediction model constructed based on random forest, a second equipment maintenance prediction model constructed based on support vector machine and a third equipment maintenance prediction model constructed based on long short-term memory network.

17. A method for predicting the production cost of lyocell fiber according to claim 16, characterized in that: The specific method steps for constructing the first raw material consumption prediction model, the first energy consumption prediction model and the first equipment maintenance prediction model based on random forest are as follows: Step a3: constructing a first raw material consumption prediction model based on random forest; the specific construction method of the first raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, training to obtain the first raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b3: constructing a first energy consumption prediction model based on random forest; the specific construction method of the first energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of the training set, and taking power consumption, water consumption and steam consumption as output features, training to obtain the first energy consumption prediction model; Step c3: Construct a first equipment maintenance prediction model based on random forest; the specific construction method of the first equipment maintenance prediction model is: use equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use equipment failure rate and maintenance times as output features, and train to obtain the first equipment maintenance prediction model.

18. The method for predicting the production cost of lyocell fiber according to claim 16, characterized in that: The specific method steps for constructing the second raw material consumption prediction model, the second energy consumption prediction model and the second equipment maintenance prediction model based on the support vector machine are as follows: Step a4: constructing a second raw material consumption prediction model based on a support vector machine; the specific construction method of the second raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, and training to obtain the second raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b4: constructing a second energy consumption prediction model based on a support vector machine; the specific construction method of the second energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of a training set, and taking power consumption, water consumption and steam consumption as output features, and training to obtain the second energy consumption prediction model; Step c4: Construct a second equipment maintenance prediction model based on support vector machine; the specific construction method of the second equipment maintenance prediction model is: use equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use equipment failure rate and maintenance times as output features, and train to obtain the second equipment maintenance prediction model.

19. The method for predicting the production cost of lyocell fiber according to claim 16, characterized in that: The specific method steps for constructing the third raw material consumption prediction model, the third energy consumption prediction model and the third equipment maintenance prediction model based on the long short-term memory network are as follows: Step a5: constructing a third raw material consumption prediction model based on the long short-term memory network; the specific construction method of the third raw material consumption prediction model is: using wood pulp viscosity, wood pulp polymerization degree, NMMO solution concentration, wood pulp methyl fiber content, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data as input features of the training set, and using wood pulp consumption, NMMO solution consumption and chemical additive consumption as output features of the training set, and training to obtain the third raw material consumption prediction model; the consumption of the chemical additives includes propylene glycol consumption and hydroxylamine consumption; Step b5: constructing a third energy consumption prediction model based on the long short-term memory network; the specific construction method of the third energy consumption prediction model is: taking temperature data, pressure data, flow data and equipment operation time as input features of the training set, and taking power consumption, water consumption and steam consumption as output features, training to obtain the third energy consumption prediction model; Step c5: construct a third equipment maintenance prediction model based on the long short-term memory network; the specific construction method of the third equipment maintenance prediction model is: use the equipment operating time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history as input features of the training set, and use the equipment failure rate and maintenance number as output features, and train to obtain the third equipment maintenance prediction model.

20. The method for predicting the production cost of lyocell fiber according to claim 1, characterized in that: In the step 5, the initial weight distribution of the total model for raw material consumption prediction, the total model for energy consumption prediction and the total model for equipment maintenance prediction is set, and the mean square error of the three models within each total model is calculated, and then Gaussian process regression is introduced to calculate the uncertainty of the three models within each total model. Finally, the fusion weights of the three models within each total model are obtained according to the variational Bayesian inference calculation. Specifically, it is assumed that the weights of the three models within each total model obey the Beta distribution: ； In the formula, The weight coefficients of the three models within the total model for raw material consumption prediction, the weight coefficients of the three models within the total model for energy consumption prediction, or the weight coefficients of the three models within the total model for equipment maintenance prediction, and Set as initial parameters, generally: ； In the formula, is a positive number, ensuring that the weights are evenly distributed in the initial state; The prediction errors of the three models within the total model for raw material consumption prediction, the prediction errors of the three models within the total model for energy consumption prediction, or the prediction errors of the three models within the total model for equipment maintenance prediction are evaluated by calculating the mean square error of the three models within the total model for raw material consumption prediction, the mean square error of the three models within the total model for energy consumption prediction, or the mean square error of the three models within the total model for equipment maintenance prediction. The specific calculation formula is as follows: ； ； ； In the formula, represents a mean square error of the first raw material consumption prediction model, the first energy consumption prediction model, or the first equipment maintenance prediction model based on random forest; represents a mean square error of a second raw material consumption prediction model, a second energy consumption prediction model, or a second equipment maintenance prediction model based on a support vector machine; represents the mean square error of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network; N represents the total number of training samples; Represents the true value of the i-th sample; represents the predicted value of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model based on random forest for the i-th sample; represents the predicted value of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model based on the support vector machine for the i-th sample; represents the predicted value of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network for the i-th sample; Then update the Beta distribution parameters according to the mean square error: ； ； In the formula, It represents a distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction. represents another distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; represents the mean square error of the total model for raw material consumption prediction, the mean square error of the total model for energy consumption prediction, or the mean square error of the total model for equipment maintenance prediction; Gaussian process regression is introduced to calculate the uncertainty of each model. The specific formula is as follows: ； In the formula, It means the uncertainty of the model; N is the total number of training samples; It is expressed as the prediction variance of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction on all samples. The specific solution formula is as follows: ； In the formula, represents the predicted value of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction for the i-th sample; It represents the average prediction value of the total model for raw material consumption prediction, the total model for energy consumption prediction or the total model for equipment maintenance prediction on all samples; Then introduce uncertainty into the Beta distribution update: ； ； In the formula, represents a distribution parameter in the calculation of the fusion weight of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction after update; Another distribution parameter representing an updated fusion weight calculation of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; Finally, the final weights are calculated using variational Bayesian inference: ； In the formula, The model weight after the t+1th iteration of the total model for raw material consumption prediction, the total model for energy consumption prediction, or the total model for equipment maintenance prediction; Represents the contribution of actual data; Then, the fusion weights of the three models within each model are obtained: ； ； ； In the formula, The meaning of is the weight coefficient of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; Meaning is the weight coefficient of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; The meaning is the weight coefficient of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; It means a distribution parameter in the fusion weight calculation of the updated third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; Meaning is another distribution parameter in the fusion weight calculation of the updated first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model; Meaning is another distribution parameter in the fusion weight calculation of the updated second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model; Meaning is another distribution parameter in the calculation of the fusion weight of the updated third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model; It means the sum of the predicted output values ​​of all training samples of the first raw material consumption prediction model, the first energy consumption prediction model or the first equipment maintenance prediction model based on random forest; The meaning is the sum of the predicted output values ​​of all training samples of the second raw material consumption prediction model, the second energy consumption prediction model or the second equipment maintenance prediction model based on the support vector machine; It means the sum of the predicted output values ​​of all training samples of the third raw material consumption prediction model, the third energy consumption prediction model or the third equipment maintenance prediction model based on the long short-term memory network.

21. The method for predicting the production cost of lyocell fiber according to claim 2, characterized in that: The process parameter group 1 includes wood pulp viscosity, wood pulp polymerization degree, wood pulp methyl fiber content, NMMO solution concentration, propylene glycol content, hydroxylamine content, raw material purchase price data, raw material inventory data and raw material consumption data; the raw material consumption forecast value includes wood pulp consumption, NMMO solution consumption and chemical additive consumption; the chemical additive consumption includes propylene glycol consumption and hydroxylamine consumption; the process parameter group 2 includes temperature data, pressure data, flow data and equipment operation time; the energy consumption forecast value includes electricity consumption, water consumption and steam consumption; the process parameter group 3 includes equipment operation time, maintenance cost, number of failures, equipment failure rate, equipment vibration data and equipment maintenance history; the equipment maintenance forecast value includes equipment failure rate and equipment maintenance number.

22. The method for predicting the production cost of lyocell fiber according to claim 2, characterized in that: The specific formulas for calculating the final weighted fusion forecast value of raw material consumption, the final energy consumption forecast value, and the final equipment maintenance forecast value are as follows: ； In the formula, Indicates the final raw material consumption forecast value, the final energy consumption forecast value or the final equipment maintenance forecast value; when represents the raw material consumption prediction value of the first raw material consumption prediction model based on random forest, represents the raw material consumption prediction value of the second raw material consumption prediction model based on support vector machine, When represents the raw material consumption forecast value of the third raw material consumption forecast model based on the long short-term memory network, then represents the weight coefficient of the first raw material consumption prediction model, represents the weight coefficient and represents the weight coefficient of the third raw material consumption forecast model; when represents the energy consumption prediction value of the first energy consumption prediction model based on random forest, represents the energy consumption prediction value of the second energy consumption prediction model based on the support vector machine, When represents the energy consumption prediction value of the third energy consumption prediction model based on the long short-term memory network, represents the weight coefficient of the first energy consumption prediction model, represents the weight coefficient of the second energy consumption prediction model and represents the weight coefficient of the third energy consumption prediction model; when represents the equipment maintenance prediction value of the first equipment maintenance prediction model based on random forest, represents the equipment maintenance prediction value of the second equipment maintenance prediction model based on support vector machine, When represents the equipment maintenance prediction value of the third equipment maintenance prediction model based on the long short-term memory network, then represents the weight coefficient of the first equipment maintenance prediction model, represents the weight coefficient and Represents the weight coefficient of the third equipment maintenance prediction model.

23. The method for predicting the production cost of lyocell fiber according to claim 1, characterized in that: The specific calculation formula for the predicted total production cost obtained in step 7 is as follows: ； In the formula, Meaning is the predicted total production and manufacturing cost, Meaning: raw material cost, Meaning is energy consumption cost, It means equipment maintenance cost.

24. A method for predicting the production cost of lyocell fiber according to claim 23, characterized in that: The calculation formula of the raw material cost is as follows: ； In the formula, is the final wood pulp consumption, is the price of wood pulp, is the final NMMO solution consumption, is the price of NMMO solution, is the final propylene glycol consumption, is the price of propylene glycol, is the final hydroxylamine consumption, is the price of hydroxylamine.

25. The method for predicting the production cost of lyocell fiber according to claim 23, characterized in that: The calculation formula of the energy consumption cost is as follows: ； In the formula, is the final power consumption, For the price of electricity, is the final water consumption, For the price of water, is the final steam consumption, For the price of steam.

26. A method for predicting the production cost of lyocell fiber according to claim 23, characterized in that: The specific calculation formula of the equipment maintenance cost is as follows: ； In the formula, is the fixed maintenance cost of the equipment, is the final number of failures, is the cost of repairing a single failure.

27. An application of a method for predicting the production cost of lyocell fiber, characterized in that: The method for predicting the production cost of lyocell fibers as described in any one of claims 1 to 26 is suitable for predicting the cost of producing lyocell fibers.

Images