Optimization method of leather collagen chemical modification process

Abstract

The invention discloses an optimization method of a leather collagen chemical modification process. The optimization method comprises the following steps: S1, constructing a leather collagen chemical modification process optimization mathematical model; s2, carrying out optimization solution on a leather collagen chemical modification process; and S3, carrying out reliability evaluation on a solving result in the step S2. The method disclosed by the invention has the beneficial effects that manual intervention in the optimization process of the leather collagen chemical modification process can be reduced, so that the accuracy and the reliability of the optimization result of the leather collagen chemical modification process are improved, and fine management of the leather collagen chemical modification process is facilitated; and the extensive production mode of a leather enterprise is favorably converted into a saving production mode, so that the high-quality sustainable development of the leather industry is realized.

Description

Technical Field

[0001] This invention relates to the field of leather production technology, and in particular to an optimized method for the chemical modification process of leather collagen. Background Technology

[0003] The leather industry is a vital sector of my country's national economy, a pillar industry of light industry with international competitiveness, and holds a pivotal position in the manufacturing sector. In leather processing, tanning is the most critical step, a qualitative change process in which tanning agents chemically modify leather collagen, imparting high thermal stability, excellent mechanical strength, and superior sensory properties. However, current tanning process optimization relies on the traditional "experience + trial and error" R&D model. This localized and static optimization approach suffers from inaccurate dosage of leather chemicals, low absorption rates, and low precision control of process parameters. This leads to increased emissions (CH4 emissions from anaerobic wastewater treatment and emissions from carbonate usage), increased carbon emissions from net purchased electricity and heat, excessive use of leather chemicals, heavy wastewater pollution loads, and significant energy and resource waste. Furthermore, under new development trends and requirements, the standard system and digital process mechanism models for leather production are relatively weak, and the actual production process involves numerous process variables. Traditional leather industry knowledge systems and technologies are insufficient to meet the needs of leather process modeling analysis and precise process optimization in complex production environments. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide an optimized method for the chemical modification process of skin collagen.

[0005] The objective of this invention is achieved through the following technical solution: an optimized method for chemical modification of skin collagen, comprising the following steps:

[0006] S1: Construct a mathematical model for optimizing the chemical modification process of skin collagen;

[0007] S2: Optimization solution for the chemical modification process of skin collagen;

[0008] S3: Evaluate the reliability of the solution results in step S2.

[0009] Preferably, in step S1, the mathematical model for optimizing the skin collagen chemical modification process consists of constraints, decision variables, and an objective function;

[0010] The expression for the objective function is:

[0011] ;

[0012] in, Provides heating power to the heater to the reaction temperature of the skin collagen chemical modification process. The motor provides the power for the drum to rotate. This refers to the tanning process time;

[0013] Decision variables include tanning agent dosage, time, initial pH, temperature, and rotation speed;

[0014] The steps for determining the functional expression of the constraints are as follows:

[0015] S11: Read the stored dataset of skin collagen chemical modification process using the pandas module in the PyCharm programming platform;

[0016] S12: Call the splitting algorithm in the scikit-learn library to split the dataset into a model training set and a model test set according to the 8:2 splitting principle;

[0017] S13: The model training set is used as the modeling dataset. The mathematical model is constructed by calling the multiple linear regression algorithm, multinomial regression algorithm, support vector machine regression algorithm and backpropagation artificial neural network algorithm in the scikit-learn library respectively.

[0018] S14: The model test set serves as the model evaluation dataset. The model evaluation metrics, such as the coefficient of determination, mean squared error, and mean absolute error, as well as the data fitting plot toolkit from the scikit-learn library, are used to evaluate the predictive performance of the mathematical model.

[0019] Preferably, step S2 further includes the following step:

[0020] S21: Save the constructed mathematical model Python code using the joblib module in the SciPy toolkit;

[0021] S22: Load the saved mathematical model as a function of constraints into the Python code of the intelligent optimization algorithm to solve the optimization model of the chemical modification process of skin collagen, and convert the objective function as the fitness function in the intelligent optimization algorithm into Python code;

[0022] S23: Python code programming for solving the optimization model of skin collagen chemical modification process using intelligent optimization algorithm.

[0023] Preferably, in step S3, the reliability evaluation of the solution result is optimized based on the intelligent optimization algorithm.

[0024] The present invention has the following advantages: The method disclosed in this invention can reduce human intervention in the optimization process of leather collagen chemical modification, thereby improving the accuracy and reliability of the optimization results of leather collagen chemical modification process, which helps to realize the refined management of leather collagen chemical modification process, and facilitates the transformation of leather enterprises from extensive production mode to economical production mode, thereby realizing the high-quality and sustainable development of the leather industry. Attached Figure Description

[0025] Figure 1 A schematic diagram of the optimized process flow for chemical modification of skin collagen;

[0026] Figure 2 A schematic diagram illustrating the process of determining the functional expression for constraints;

[0027] Figure 3 This is a schematic diagram of the optimization solution process for the chemical modification of skin collagen. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0029] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0030] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other.

[0031] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0032] In the description of this invention, it should be noted that skin collagen includes, but is not limited to, one of porcine skin collagen, sheepskin collagen, and bovine skin collagen.

[0033] In the description of this invention, it should also be noted that the chemical modification process of skin collagen includes, but is not limited to, one of the following processes: chrome tanning, vegetable tanning, and aldehyde tanning.

[0034] In this embodiment, as Figure 1 As shown, an optimized method for the chemical modification process of skin collagen includes the following steps:

[0035] S1: Construct a mathematical model for optimizing the chemical modification process of skin collagen;

[0036] S2: Optimization solution for the chemical modification process of skin collagen;

[0037] S3: Evaluate the reliability of the solution results in step S2. The method disclosed in this invention can reduce human intervention in the optimization process of leather collagen chemical modification, thereby improving the accuracy and reliability of the optimization results. This helps to achieve refined management of the leather collagen chemical modification process, facilitates the transformation of leather enterprises from an extensive production model to an economical production model, and thus achieves high-quality and sustainable development of the leather industry.

[0038] Furthermore, in step S1, the mathematical model for optimizing the chemical modification process of skin collagen consists of constraints, decision variables, and an objective function;

[0039] The expression for the objective function is:

[0040] ;

[0041] in, The heating power provided to the heater to achieve the reaction temperature during the collagen chemical modification process is measured by a smart meter based on the actual reaction temperature, transfer volume, and heating time. The motor power that provides the drum rotation is measured by a smart meter based on the actual speed, load, and rotation time. The tanning process time is used as the objective function. Specifically, this invention aims to address the energy waste and increased carbon emissions associated with the chemical modification of skin collagen. Therefore, minimizing the overall energy consumption of the skin collagen chemical modification process is selected as the objective function. According to the national standard "General Rules for Calculating Overall Energy Consumption" (GB / T 2589-2020), the formula for calculating the overall energy consumption of the skin collagen chemical modification process is as follows:

[0042] ;

[0043] in, The total energy consumption for the chemical modification process of skin collagen is expressed in kilograms of standard coal (kgce). Electricity consumption, measured in kW. . h, This is the standard coal equivalent coefficient for electricity, expressed in kgce / (kW). . h), This refers to water consumption, measured in tons (t). This is the standard coal equivalent coefficient for water, expressed in kgce / t. According to the appendix of the national standard "General Rules for Calculation of Comprehensive Energy Consumption" (GB / T 2589-2020), the standard coal equivalent coefficient for electricity is 0.1229 kgce / (kW). . h), the standard coal equivalent of water is 0.257 kgce / t, therefore the expression for the objective function is obtained. .

[0044] The decision variables are the chemical modification process parameters of hide collagen, including but not limited to tanning agent dosage, time, initial pH, temperature, and rotation speed. Specifically, taking the chrome tanning process as an example, the chrome tanning process includes two relatively independent stages: the penetration of chrome tanning agents and their binding with hide collagen fibers. In the initial stage of tanning, the penetration of chrome tanning agents into hide collagen fibers is dominant, while in the final stage, the binding of chrome tanning agents with hide collagen fibers is dominant. The properties of wet blue hides during the chrome tanning process are highly correlated with the process parameters, and the objective function is linearly correlated with the process parameter time. Therefore, the initial pH and time are selected as the decision variables for the chrome tanning process optimization model for the chrome tanning penetration process and the chrome tanning binding process. That is, the pH value of the pickling solution in the chrome tanning penetration process is in the range of 2.8~3.0, and the penetration time is in the range of 0~160 min; the pH value after alkali removal in the chrome tanning binding process is in the range of 3.8~4.1, and the binding time is in the range of 0~155 min.

[0045] To achieve the optimal process parameters in the leather collagen chemical modification process optimization model under the constraints of energy conservation and carbon reduction goals, the constraints in the model must be transformed into correlation functions of process parameters. The mathematical model between leather performance and process parameters is constructed using machine learning algorithms, such as... Figure 2 As shown, the steps for determining the functional expression of the constraints are as follows:

[0046] S11: Read the stored dataset of skin collagen chemical modification process using the pandas module in the PyCharm programming platform;

[0047] S12: Call the splitting algorithm in the scikit-learn library to split the dataset into a model training set and a model test set according to the 8:2 splitting principle;

[0048] S13: The model training set is used as the modeling dataset. The mathematical model is constructed by calling the multiple linear regression algorithm, multinomial regression algorithm, support vector machine regression algorithm and backpropagation artificial neural network algorithm in the scikit-learn library respectively.

[0049] S14: The model test set serves as the model evaluation dataset. The model evaluation metrics (coefficient of determination, mean squared error, and mean absolute error) and data fitting plot toolkit from the scikit-learn library are used to evaluate the predictive performance of the mathematical model. In this embodiment, the machine learning algorithm includes, but is not limited to, one of the following: multiple linear regression, random forest regression, multinomial regression, support vector machine regression, and backpropagation artificial neural network.

[0050] Furthermore, such as Figure 3 As shown, step S2 also includes the following steps:

[0051] S21: Save the constructed mathematical model Python code using the joblib module in the SciPy toolkit;

[0052] S22: Load the saved mathematical model as a function of constraints into the Python code of the intelligent optimization algorithm to solve the optimization model of the chemical modification process of skin collagen, and convert the objective function as the fitness function in the intelligent optimization algorithm into Python code;

[0053] S23: Python code programming for solving the optimization model of the chemical modification process of leather collagen using an intelligent optimization algorithm. Specifically, the process of solving the optimization model of the chrome tanning and penetration process based on a genetic algorithm is as follows: First, the mathematical model Python code of the relationship between the performance of wet blue leather and process parameters in the chrome tanning and penetration process is saved using the joblib module in the SciPy toolkit; then, the saved mathematical model is loaded as a function of constraints into the Python code of the genetic algorithm for solving the optimization model of the chrome tanning and penetration process, and the objective function is converted into Python code as the fitness function in the genetic algorithm; finally, the Python code programming for solving the optimization model of the chrome tanning and penetration process using the genetic algorithm is performed according to the genetic algorithm process, where the maximum number of iterations is 100, the population size is 50, the crossover probability is 0.8, and the mutation probability is 0.05. The process of solving the optimization model for the chrome tanning process based on a genetic algorithm is as follows: First, the mathematical model Python code relating the properties of wet blue leather and process parameters in the chrome tanning process is saved using the joblib module in the SciPy toolkit. Then, the saved mathematical model is loaded as a constraint function into the Python code for solving the optimization model of the chrome tanning process using the genetic algorithm, and the objective function is converted into Python code as the fitness function in the genetic algorithm. Finally, the Python code for solving the optimization model of the chrome tanning process using the genetic algorithm is programmed according to the genetic algorithm flow, with a maximum of 100 iterations, a population size of 50, a crossover probability of 0.8, and a mutation probability of 0.05. In this embodiment, the intelligent optimization algorithm includes, but is not limited to, one of the following: genetic algorithm, ant colony optimization algorithm, and particle swarm optimization algorithm.

[0054] In this embodiment, step S3 involves evaluating the reliability of the optimization results based on the intelligent optimization algorithm. Specifically, the reliability evaluation process for the optimization results of the chrome tanning and infiltration process based on the genetic algorithm is as follows: Using a field emission scanning microscope at an accelerating voltage of 5.00 kV, the morphology of the entire longitudinal section of the leather pieces prepared by the optimized chrome tanning and infiltration process and those prepared by the conventional chrome tanning and infiltration process is observed. The distribution of Cr elements on the sample surface is analyzed using an attached energy dispersive X-ray spectrometer. By comparing the uniformity of chrome tanning agent distribution in the leather pieces prepared by the two processes, the reliability of the optimization results of the chrome tanning and infiltration process based on the genetic algorithm is evaluated. The reliability evaluation process for the optimization results of the chrome tanning and bonding process based on the genetic algorithm is as follows: Differential scanning calorimetry is used to determine the thermal denaturation temperatures of the wet blue leather prepared by the optimized chrome tanning and bonding process and the wet blue leather prepared by the conventional chrome tanning and infiltration process. The temperature corresponding to the peak value of the endothermic curve is recorded as the thermal denaturation temperature of the sample. By comparing the thermal denaturation temperatures of the wet blue leather prepared by the two processes, the reliability of the optimization results of the chrome tanning and bonding process based on the genetic algorithm is evaluated.

[0055] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An optimized method for the chemical modification process of skin collagen, characterized in that: Includes the following steps: S1: Construct a mathematical model for optimizing the chemical modification process of skin collagen; S2: Optimization solution for the chemical modification process of skin collagen; S3: Evaluate the reliability of the solution results in step S2.

2. The optimized method for the chemical modification process of skin collagen according to claim 1, characterized in that: In step S1, the mathematical model for optimizing the chemical modification process of skin collagen consists of constraints, decision variables, and an objective function. The expression for the objective function is: ； in, Provides heating power to the heater to the reaction temperature of the skin collagen chemical modification process. The motor provides the power for the drum to rotate. This refers to the tanning process time; Decision variables include tanning agent dosage, time, initial pH, temperature, and rotation speed; The steps for determining the functional expression of the constraints are as follows: S11: Read the stored dataset of skin collagen chemical modification process using the pandas module in the PyCharm programming platform; S12: Call the splitting algorithm in the scikit-learn library to split the dataset into a model training set and a model test set according to the 8:2 splitting principle; S13: The model training set is used as the modeling dataset. The mathematical model is constructed by calling the multiple linear regression algorithm, multinomial regression algorithm, support vector machine regression algorithm and backpropagation artificial neural network algorithm in the scikit-learn library respectively. S14: The model test set serves as the model evaluation dataset. The model evaluation metrics, such as the coefficient of determination, mean squared error, and mean absolute error, as well as the data fitting plot toolkit from the scikit-learn library, are used to evaluate the predictive performance of the mathematical model.

3. The optimized method for the chemical modification process of skin collagen according to claim 2, characterized in that: Step S2 further includes the following steps: S21: Save the constructed mathematical model Python code using the joblib module in the SciPy toolkit; S22: Load the saved mathematical model as a function of constraints into the Python code of the intelligent optimization algorithm to solve the optimization model of the chemical modification process of skin collagen, and convert the objective function as the fitness function in the intelligent optimization algorithm into Python code; S23: Python code programming for solving the optimization model of skin collagen chemical modification process using intelligent optimization algorithm.

4. The optimized method for the chemical modification process of skin collagen according to claim 3, characterized in that: In step S3, the reliability evaluation of the solution result is optimized based on the intelligent optimization algorithm.

Images