Energy-saving control method and equipment for lining cloth production workshop

Abstract

The invention discloses an energy-saving control method and equipment for a lining cloth production workshop, and belongs to the field of energy-saving control, and the method comprises the steps: reading the attribute information of target lining cloth, and taking the attribute information as a constraint, and carrying out the retrieval to obtain a lining cloth drying record; carrying out drying characteristic analysis, and fitting to construct a lining cloth drying curve; determining an initial water content and a target drying curve; identifying a target drying production line, dividing a target drying curve based on the section number of a drying furnace, and determining a drying target; in order to meet the drying target, stage optimization of drying control parameters is executed, and an optimized drying scheme is generated through integration; and the drying operation of the target wet lining cloth is executed, the drying effect is monitored in real time, and real-time compensation of the drying operation is completed based on the predetermined deviation proofreading decision tree. Through multi-stage drying parameter optimization and introduction of a real-time monitoring and intelligent compensation mechanism, the technical effects of minimizing drying energy consumption and realizing energy-saving and efficient production while ensuring stable quality of a lining cloth product are achieved.

Description

Technical Field

[0001] The invention relates to the field of energy-saving control, and in particular to an energy-saving control method and equipment for a lining cloth production workshop. Background Art

[0002] In the production process of lining cloth, the drying process is the production process to remove moisture from the lining cloth to make it reach the required moisture content. At present, in the lining cloth production workshop, the setting of lining cloth drying parameters mainly depends on the experience of the operator, and it is difficult to achieve the optimal drying effect; at the same time, the existing drying process lacks parameter optimization mechanism for different lining cloth varieties and process requirements, and it is difficult to achieve energy saving and efficiency improvement in the drying process; furthermore, the lining cloth drying production line lacks real-time monitoring and intelligent control means, and it is difficult to compensate for drying deviations in time, resulting in unstable product quality. Therefore, in the existing lining cloth drying production, the reliance on experience in the setting of drying parameters, the lack of parameter optimization, and the lack of real-time intelligent control in the production process lead to energy waste and unstable product quality in the lining cloth production workshop. Summary of the invention

[0003] This application provides an energy-saving control method and equipment for an lining cloth production workshop, aiming to solve the technical problems in the existing lining cloth drying production, such as energy waste and unstable product quality in the lining cloth production workshop due to the reliance on experience in drying parameter setting, lack of parameter optimization, and lack of real-time intelligent regulation of the production process.

[0004] In view of the above problems, the present application provides an energy-saving control method and equipment for a lining cloth production workshop.

[0005] The first aspect disclosed in the present application provides an energy-saving control method for an interlining production workshop, the method comprising: reading attribute information of a target interlining, and retrieving and acquiring interlining drying records with the attribute information as a constraint; performing drying characteristic analysis based on the interlining drying records, and fitting and constructing an interlining drying curve; calling historical processing logs for analysis to determine an initial moisture content, and mapping an interlining drying curve with the initial moisture content and an expected moisture content to determine a target drying curve; identifying a target drying production line, dividing the target drying curve based on the number of drying furnace sections, and determining N stage drying targets, wherein the target drying production line includes N drying furnace sections, and each drying furnace section can be independently controlled, and N is an integer greater than 2; for the purpose of meeting the N stage drying targets, performing stage optimization of drying control parameters, integrating and generating an optimized drying plan, and the optimized drying plan is a plan with the best comprehensive energy consumption; performing a drying operation of the target wet interlining according to the optimized drying plan, and monitoring the drying effect in real time, and completing real-time compensation of the drying operation based on a predetermined deviation proofreading decision tree.

[0006] Another aspect disclosed in the present application provides an energy-saving control device for an interlining production workshop, the device comprising: a record retrieval component for reading the attribute information of a target interlining, and retrieving and acquiring the interlining drying record with the attribute information as a constraint; a drying curve fitting component for performing drying characteristic analysis based on the interlining drying record, and fitting and constructing an interlining drying curve; a drying curve determination component for calling a historical processing log analysis to determine an initial moisture content, and mapping the interlining drying curve with the initial moisture content and the expected moisture content, and determining a target drying curve; a curve division component for identifying a target drying production line, dividing the target drying curve based on the number of drying furnace sections, and determining N stage drying targets, wherein the target drying production line includes N drying furnace sections, and each drying furnace section can be independently controlled, and N is an integer greater than 2; a parameter stage optimization component for performing stage optimization of drying control parameters for the purpose of meeting the N stage drying targets, integrating and generating an optimized drying plan, wherein the optimized drying plan is a plan with the best comprehensive energy consumption; a drying operation execution component for performing a drying operation of a target wet interlining according to the optimized drying plan, and monitoring the drying effect in real time, and completing real-time compensation of the drying operation based on a predetermined deviation proofreading decision tree.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: By reading the attribute information of the target lining cloth and taking the attribute information as a constraint, the lining cloth drying records are retrieved to provide a data basis for the subsequent construction of the drying curve model; the drying characteristics are analyzed based on the lining cloth drying records, and the lining cloth drying curve is constructed by fitting to guide the setting of drying parameters; the historical processing log analysis is called to determine the initial moisture content, and the lining cloth drying curve is mapped with the initial moisture content and the expected moisture content to determine the target drying curve, which provides a basis for the subsequent optimization of the drying process; the target drying production line is identified, the target drying curve is divided according to the number of drying furnace sections, and the N-stage drying targets are determined to provide a basis for the subsequent staged optimization control. Since each drying furnace section can be independently controlled, the drying parameters of each stage can be optimized in a targeted manner; in order to meet the N-stage drying targets, the drying control parameters are executed. The optimal number of stages is searched, and the optimized drying plan is integrated to minimize energy consumption while ensuring the drying effect; the drying operation of the target wet lining is performed according to the optimized drying plan, and the drying effect is monitored in real time. The real-time compensation of the drying operation is completed based on the predetermined deviation proofreading decision tree. The technical solution of ensuring the stable drying quality of the lining cloth through closed-loop feedback control solves the technical problems of energy waste and unstable product quality in the lining cloth production workshop due to the reliance on experience in drying parameter setting, lack of parameter optimization, and lack of real-time intelligent regulation in the production process in the existing lining cloth drying production. The multi-stage drying parameter setting is guided by the data-driven modeling optimization method, and the real-time monitoring and intelligent compensation mechanism is introduced to achieve the technical effect of minimizing drying energy consumption while ensuring the stable quality of the lining cloth product, and realizing energy-saving and efficient production.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flow chart of an energy-saving control method for a lining cloth production workshop is provided for an embodiment of the present application; Figure 2 A structural schematic diagram of an energy-saving control device for a lining cloth production workshop is provided for an embodiment of the present application.

[0010] Explanation of reference numerals: record retrieval component 11 , drying curve fitting component 12 , drying curve determination component 13 , curve division component 14 , parameter stage optimization component 15 , drying operation execution component 16 . DETAILED DESCRIPTION

[0011] The overall idea of ​​the technical solution provided by this application is as follows: The embodiment of the present application provides an energy-saving control method and equipment for an interlining production workshop. By constructing an interlining drying mathematical model, the drying process is divided into multiple stages and optimized in combination with the characteristics of the production line, and a real-time monitoring and intelligent compensation mechanism is introduced to achieve energy saving and efficiency improvement in the drying process while ensuring the quality of the interlining.

[0012] First, the drying curve model of the lining cloth is established by analyzing the historical drying data, and the target drying curve is determined according to the actual process requirements, providing a theoretical basis for the subsequent optimization of drying parameters. Then, the target drying curve is divided into multiple stage targets by comprehensively considering the layout characteristics of the drying furnace of the production line, and the drying control parameters are optimized for each stage to obtain the optimal drying plan with the best energy consumption. Subsequently, the optimized drying plan is strictly implemented in the actual drying operation. At the same time, the preset drying effect is compared through real-time monitoring, and intelligent compensation is implemented according to the deviation situation based on the predetermined deviation proofreading decision tree, and the continuous and stable drying quality of the lining cloth is ensured through closed-loop feedback control.

[0013] This application is based on the actual production process of lining cloth, makes full use of data mining and modeling technology to guide the optimization of drying curve, and balances the relationship between product quality and energy consumption through a control strategy of independent optimization in stages and real-time monitoring of intelligent compensation. While improving the drying efficiency of lining cloth and ensuring the consistency of product quality, it greatly reduces the energy consumption level of the drying process and achieves energy-saving control.

[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0015] Embodiment 1 like Figure 1 As shown, the embodiment of the present application provides an energy-saving control method for a lining cloth production workshop, the method comprising: S1: reading the attribute information of the target lining cloth, and using the attribute information as a constraint, retrieving and obtaining the lining cloth drying record; Specifically, the attribute information of the target interlining includes but is not limited to the material, fabric structure, weight, thickness, etc. of the interlining. This attribute information is obtained through information carriers such as barcodes and RFID tags, or collected in real time through IoT sensors. After obtaining the attribute information of the target interlining, it is used as a constraint condition to retrieve matching or similar interlining drying records in the historical production database. The interlining drying records contain the drying process data of interlinings with similar attributes to the target interlining under different initial moisture contents, expected moisture contents, and drying equipment parameter settings, such as drying time, energy consumption, temperature change curve, etc.

[0016] Through the retrieval of attribute matching constraints, reference drying records with similar characteristics to the target lining fabric can be found quickly and accurately, providing a reliable data basis for subsequent drying characteristic analysis, drying curve fitting and other steps, which helps to improve the accuracy and efficiency of energy-saving optimization.

[0017] S2: Analyze the drying characteristics of the lining cloth based on the drying record, and construct a drying curve of the lining cloth by fitting; Specifically, after obtaining the drying records of the lining cloth that match the properties of the target lining cloth, these recorded data are deeply analyzed and mined to discover the drying characteristics of the lining cloth under different process conditions. For example, analyze the changing trend of the moisture content of the lining cloth with the drying time under different initial moisture content and target moisture content conditions; analyze the influence of different drying temperature, wind speed and other equipment parameters on the drying rate of the lining cloth; analyze the correlation between the attribute parameters such as the thickness and gram weight of the lining cloth and the drying energy consumption; compare and analyze the differences in the drying process of different batches of lining cloth to find the key factors affecting the drying effect. Through the above analysis, the drying characteristics of the lining cloth are fully understood, providing a theoretical basis and data support for the fitting modeling of the drying curve. Subsequently, based on the analysis of the drying characteristics, mathematical statistics, machine learning and other methods are used to comprehensively consider factors such as lining cloth properties, process parameters, energy consumption indicators, etc., to construct the lining cloth drying curve, quantitatively describe the functional relationship between the moisture content of the lining cloth and the drying time and equipment parameters, and provide a decision-making basis for the subsequent optimization of the drying process.

[0018] S3: calling historical processing logs for analysis to determine the initial moisture content, and mapping the lining cloth drying curve with the initial moisture content and the expected moisture content to determine the target drying curve; Specifically, first, sample data similar to the current target lining is screened out from the historical production data as the historical processing log, and the initial moisture content record is extracted from it. Secondly, after removing the outliers from the initial moisture content record, the mode of the moisture content record is taken as the initial moisture content of the current lining. Then, the obtained initial moisture content and the expected moisture content set by the process are substituted into the constructed lining drying curve. Through curve fitting, the target drying curve of the lining moisture content changing with drying time under the given initial moisture content and expected moisture content constraints is obtained, which describes the drying time and process trajectory required for the lining to reach the expected state from the initial state.

[0019] S4: Identify the target drying production line, divide the target drying curve based on the number of drying furnace sections, and determine N stage drying targets, wherein the target drying production line includes N drying furnace sections, and each drying furnace section can be independently controlled, and N is an integer greater than 2; Specifically, according to the target drying curve and equipment conditions, the entire drying process is divided into several control stages, and the target parameters of each stage are determined, laying the foundation for achieving segmented optimization control.

[0020] First, identify the target drying production line where the lining cloth is dried and obtain its key equipment parameters. Taking the tunnel dryer production line as an example, obtain the design and process parameters such as the number of drying furnaces, the length of each furnace section, the temperature and wind speed adjustment range. Then, based on the number of drying furnaces N, the obtained target drying curve is divided into N intervals in the time dimension, and each interval corresponds to a control cycle of a drying furnace. Subsequently, according to the starting and ending moisture content of the target drying curve in each time interval, combined with the furnace length and cloth transmission speed parameters, the moisture content reduction target of each furnace section in each time interval is calculated, and N stage drying targets are obtained, corresponding to N drying furnace sections, so that each drying furnace section can be independently controlled according to the stage drying target.

[0021] S5: for the purpose of meeting the N-stage drying targets, performing stage optimization of drying control parameters, integrating and generating an optimized drying plan, wherein the optimized drying plan is a plan with the best comprehensive energy consumption; Specifically, under the constraints of the determined N-stage drying targets, the optimal control scheme for the entire drying process is formulated by optimizing and solving the drying control parameters of each stage, so as to achieve energy saving and efficiency improvement of lining cloth drying. For example, with the temperature and wind speed of the tunnel dryer as the main control variables, each drying furnace section can independently adjust the temperature and wind speed parameters during its corresponding control period. Based on the moisture content reduction target of each furnace section, a multi-stage optimization control model for the drying process is constructed. The objective function of the multi-stage optimization control model is a comprehensive energy-saving optimization index, which is composed of the weighted sum of three indicators: energy consumption, furnace temperature and lining cloth quality loss of each drying furnace section. By adjusting the weight coefficients of each indicator, the relationship between drying quality and energy saving effect can be balanced. The constraints of the multi-stage optimization control model include that the actual moisture content reduction of each furnace section is equal to the target value, and the furnace temperature and wind speed parameters are within their adjustable range. Under this constraint, the optimization algorithm is used to solve the optimal control parameter sequence of the multi-stage drying process, including the optimal temperature and wind speed setting values ​​of each furnace section, and a complete optimization drying scheme is formed as the scheme with the best comprehensive energy consumption.

[0022] S6: performing a drying operation of the target wet lining cloth according to the optimized drying scheme, monitoring the drying effect in real time, and completing real-time compensation of the drying operation based on a predetermined deviation calibration decision tree.

[0023] Specifically, the optimized drying scheme is applied to the actual lining cloth drying operation, and through real-time monitoring and feedback control, it is ensured that the dynamic performance of the drying process meets the expected goals.

[0024] First, the parameter setting values ​​of each drying furnace section in the optimized drying scheme are sent to the control system of the dryer as the initial parameter configuration. After the lining cloth drying operation starts, the process parameters such as temperature, humidity and moisture content of each drying furnace section are collected in real time, and compared with the stage drying target in the optimized drying scheme to calculate the deviation value of the actual drying effect. For the detected drying effect deviation, a deviation correction decision tree is pre-built to quickly determine the cause of the deviation and give the corresponding compensation control strategy. The judgment conditions of the predetermined deviation correction decision tree include but are not limited to the size, positive and negative signs, duration, and change trend of the deviation value, and the compensation control measures include adjusting the furnace temperature, wind speed, and cloth transmission speed. According to the reasoning results of the predetermined deviation correction decision tree, a dynamic compensation control instruction is generated and sent to the dryer control system for execution. Through closed-loop feedback control, real-time optimization and adjustment of the drying process is achieved, so that the actual drying effect is dynamically consistent with the stage target in the optimized drying scheme. For example, when it is monitored that the moisture content of the cloth in a certain drying furnace section decreases at a rate lower than the optimization target, the predetermined deviation correction decision tree determines that the temperature setting of the furnace section is too low, and thus generates a compensation instruction to increase the temperature of the furnace in that section; or, when the energy consumption level of the entire drying process exceeds the expected value of the optimized drying plan, the predetermined deviation correction decision tree infers that the cloth stays in the furnace for a long time, and thus generates an overall control instruction to increase the cloth transmission speed.

[0025] Through real-time monitoring and feedback control, the execution effect of the optimized drying plan in actual production is guaranteed, the influence of factors such as initial state fluctuation of the lining cloth and equipment characteristic drift is overcome, and the whole energy-saving optimization control of the drying process is achieved.

[0026] Furthermore, the embodiment of the present application also includes: Reading the property information of the target lining cloth, wherein the property information at least includes the lining cloth material, lining cloth thickness, lining cloth density, hygroscopicity, air permeability and heat resistance; Based on the textile big data, taking the attribute information as a constraint condition, the lining cloth drying record is retrieved online, wherein the lining cloth drying record includes a plurality of lining cloth drying data, and each lining cloth drying data includes a plurality of sample drying nodes and a plurality of sample moisture contents; A two-dimensional coordinate system is constructed based on the sample drying nodes and the sample moisture content, and multiple lining cloth drying data are sequentially distributed in the two-dimensional coordinate system to generate multiple initial lining cloth drying curves; The multiple initial lining cloth drying curves are subjected to time normalization processing, and curve fitting of the multiple normalized lining cloth drying curves is performed based on the Bezier curve fitting principle to obtain the lining cloth drying curve.

[0027] In a feasible implementation, first, the attribute information of the target interlining is read. The attribute information includes at least the characteristic parameters of the material, thickness, density, hygroscopicity, air permeability and heat resistance of the interlining. These parameters comprehensively describe the physical and chemical properties of the target interlining and are important factors affecting its drying characteristics. Among them, the interlining material includes natural fibers such as cotton, linen, silk, or chemical fibers such as polyester and nylon. The hygroscopicity and thermal conductivity of different materials vary greatly; the thickness and density of the interlining determine its unit area water content and air permeability; the hygroscopicity and air permeability affect the water absorption rate and water evaporation rate of the interlining; and the heat resistance restricts the maximum temperature of the drying process. Excessive temperature may cause damage or deformation of the interlining material. Textile big data brings together a wide variety of interlining production and processing data in the industry. Through big data mining and association analysis, the intrinsic connection between different interlinings in the drying process can be found. Using the attribute information of the target interlining as a keyword, interlining samples with similar parameters such as material and thickness are retrieved in the textile big data, and the drying process records of these samples in historical production are retrieved to form interlining drying data. The interlining drying record consists of multiple interlining drying data, each of which corresponds to a specific interlining sample. Each interlining drying data contains the measured moisture content of the sample at several drying nodes, forming a discrete data point sequence reflecting the entire drying process, describing the dynamic change characteristics of the moisture content of different interlinings under actual drying conditions.

[0028] Next, a two-dimensional coordinate system with drying nodes as horizontal coordinates and moisture content as vertical coordinates is established to intuitively present the drying process. Then, the sample drying nodes and corresponding sample moisture content in each lining cloth drying data are marked one by one in the two-dimensional coordinate system to generate a scatter plot. Since the lining cloth drying record contains multiple lining cloth drying data, several groups of scattered point distributions will be formed in the same coordinate system. By observing the distribution form and law of the scattered points, the trend and rate of moisture content decrease of different lining cloth samples during the drying process are preliminarily judged. Subsequently, based on the scatter point distribution, each group of discrete sample points is logically connected to generate a series of initial lining cloth drying curves reflecting the continuous change of moisture content. Each initial lining cloth drying curve corresponds to the complete drying process of a lining cloth sample. Multiple initial lining cloth drying curves intuitively show the differences in drying characteristics between different samples. Afterwards, the time dimension of each initial lining cloth drying curve is normalized and uniformly mapped to the interval of [0, 1]. Through linear compression or stretching, the difference in drying time of different lining cloth samples is eliminated, and the dimensionless expression of the drying process is realized. Next, with normalized time as the independent variable and moisture content as the dependent variable, each normalized initial lining cloth drying curve is smoothly fitted using the principle of Bezier curve fitting. Through Bezier curve fitting, while maintaining the morphological characteristics of the initial drying curve, its local fluctuations and singular points are eliminated, and multiple smooth and continuous normalized lining cloth drying curves are obtained. Subsequently, the morphological characteristics of multiple normalized lining cloth drying curves are comprehensively analyzed and compared, and individual curves with obvious abnormalities are eliminated. In combination with the material, thickness and other attribute parameters of the lining cloth, a representative preferred curve is selected as the lining cloth drying curve.

[0029] Starting from the target lining cloth property information, through big data retrieval, visual analysis, data preprocessing and curve fitting, the lining cloth drying curve is obtained, laying the foundation for the subsequent quantitative drying process optimization control.

[0030] Furthermore, the embodiment of the present application also includes: Based on the Bezier curve fitting principle, curve fitting of multiple normalized lining cloth drying curves is performed to obtain an initial fitting curve; Performing similarity analysis on the initial fitting curve and the multiple initial lining cloth drying curves in sequence to determine multiple curve similarity coefficients; Eliminate the initial lining cloth drying curves corresponding to the curve similarity coefficients that do not meet the predetermined similarity threshold, and obtain multiple standard lining cloth drying curves; The plurality of standard lining cloth drying curves are subjected to curve fitting based on the Bezier curve fitting principle to obtain the lining cloth drying curve.

[0031] In a preferred embodiment, first, the discrete points on the normalized lining drying curves are used as the control points of the Bezier curve, and the parametric equation of the Bezier curve is used to generate a smooth and continuous curve as a fitting approximation of the original discrete points. By adjusting the order of the Bezier curve and the weight of the control point, the shape and smoothness of the fitting curve are controlled, and the smooth expression of the drying curve is achieved on the basis of maintaining the distribution characteristics of the original data points, and the initial fitting curve is obtained. Subsequently, the initial fitting curve and each normalized lining drying curve are discretely sampled to obtain two groups of discrete point sequences of equal length, and the curve similarity coefficient between the two groups of discrete point sequences is calculated as a quantitative indicator to measure the degree of similarity of their morphology, and multiple curve similarity coefficients are obtained. Among them, the curve similarity coefficient can be calculated using a variety of mathematical calculation methods, such as Euclidean distance, Manhattan distance, dynamic time warping distance, etc., to characterize the similarity of the two curves in terms of shape, trend, rate of change, etc. from different angles. The value range of the curve similarity coefficient is between [0, 1], and the closer the value is to 1, the higher the similarity of the two curves.

[0032] Subsequently, a predetermined similarity threshold is set, and the calculated curve similarity coefficient is compared with the threshold one by one. For the normalized lining cloth drying curve whose curve similarity coefficient is greater than or equal to the predetermined similarity threshold, it is considered that its morphological fit with the initial fitting curve is good and it is retained as the standard lining cloth drying curve, while for the normalized lining cloth drying curve whose curve similarity coefficient is less than the predetermined similarity threshold, it is regarded as an abnormal sample and is eliminated. Through similarity screening, a set of multiple standard lining cloth drying curves with high similarity and good internal consistency with the initial fitting curve are obtained, providing high-quality data support for the subsequent construction of the lining cloth drying curve. Then, the discrete points on the standard lining cloth drying curve are used as the control points of the Bezier curve, and a smooth and continuous fitting curve is generated by adjusting the curve order and the control point weight as the lining cloth drying curve. Compared with the initial fitting curve, since the standard lining cloth drying curve has undergone similarity screening and individual samples with abnormal morphology have been eliminated, the fitted lining cloth drying curve has higher robustness and representativeness, and can more accurately reflect the law of lining cloth drying.

[0033] Furthermore, the embodiment of the present application also includes: Identify the drying furnace, determine the drying control parameters and parameter rated thresholds, the drying control parameters including drying temperature, drying humidity, drying wind speed and drying air volume; Selecting a first drying furnace, obtaining a first-stage drying target of the first drying furnace, and determining a first drying time based on a rated conveying speed of a drying conveyor belt and a length of the first drying furnace; With the purpose of meeting the first-stage drying target, based on the first drying time and the parameter rated threshold, a stage optimization of the drying control parameters is performed to generate a first optimized drying plan, which is added to the optimized drying plan, wherein the rated threshold of the drying temperature is initially updated using the heat resistance.

[0034] In a feasible implementation, first, by conducting a field survey of the lining cloth production line or consulting the equipment data, the model specifications, structural layout, technical parameters and other information of the drying furnace are obtained, and the drying control parameters that play a leading role in the lining cloth drying process are identified, including drying temperature, drying humidity, drying wind speed and drying air volume. While determining the drying control parameters, it is also necessary to give the rated threshold range of each parameter based on factors such as equipment performance and process requirements. For example, the upper limit of the drying temperature cannot exceed the heat-resistant temperature of the lining cloth material to avoid damage to the physical properties of the lining cloth; and the lower limit of the drying wind speed must ensure uniform heat transfer to avoid insufficient drying of the lining cloth. Subsequently, among the N stage drying targets divided, a drying furnace is selected in turn as the first drying furnace, and the corresponding stage drying target is selected as the first stage drying target, which specifies the moisture content level that the target lining cloth needs to reach after passing through the first drying furnace. According to the design parameters of the lining cloth production line, the rated conveying speed of the drying conveyor belt is obtained, and then combined with the effective drying length of the first drying furnace, the drying time of the lining cloth in the first drying furnace is obtained as the first drying time. Then, in order to meet the drying target of the first stage, based on the first drying time and the rated threshold of the parameters, the optimization algorithm is used to search for the optimal control parameter combination in the parameter space. Through optimization and solution, the process parameter settings that can minimize the moisture content of the lining cloth and improve the drying efficiency under the current constraints are obtained, and the optimized control scheme of the first drying furnace is formed as the first optimized drying scheme. When optimizing the drying temperature, it is necessary to fully consider the heat resistance limit of the lining cloth material. During the optimization process, the upper threshold of the temperature parameter is dynamically corrected so that it does not exceed the highest heat resistance temperature of the lining cloth, thereby improving the drying efficiency while avoiding the adverse effects of high temperature on the quality of the lining cloth. According to the above method, the drying parameters of the remaining drying furnaces in the lining cloth production line are optimized one by one, and finally the optimal control schemes of all drying furnaces in their respective drying stages are obtained, which together constitute a complete optimized drying scheme.

[0035] Through system decomposition from overall optimization of the drying process to local optimization of a single device, and reconstruction based on the optimization of each device to form a global optimal solution, compared with traditional empirical operations, on the premise of meeting product quality requirements, each process parameter is precisely controlled to tap the potential of the equipment to a greater extent, achieving energy saving and efficiency improvement in the drying process.

[0036] Furthermore, the embodiment of the present application also includes: Based on the parameter rating threshold, randomly generating a plurality of drying parameter groups; Through the drying performance analysis channel, the drying performance of the multiple drying parameter groups is evaluated based on the first drying time, and an initial solution that meets the first stage drying target is extracted to obtain multiple standard initial solutions; Performing energy consumption evaluation on the multiple standard initial solutions respectively through an energy consumption evaluation channel, and outputting multiple energy consumption evaluation coefficients, wherein the drying performance analysis channel and the energy consumption evaluation channel are constructed based on a feedforward neural network; Arranging the multiple initial solutions from small to large according to the energy consumption evaluation coefficients to generate an initial solution sequence; Select the first A initial solutions in the initial solution sequence as primary solutions and the last B initial solutions as secondary solutions, where the sum of A and B is the number of initial solutions in the initial solution sequence; Based on A first solutions, B secondary solutions are randomly clustered to generate A solution sets, and within the A solution sets, the first solution is used as the optimal solution, and the secondary solutions in the solution set are adjusted once based on a predetermined quaternary step size to determine A updated solution sets, wherein during the adjustment process, if the secondary solution in the updated solution set does not meet the parameter rated threshold, the secondary solution parameter is not updated; In the A updated solution sets, if there is a secondary solution that meets the first stage drying target and the energy consumption evaluation coefficient is less than the energy consumption evaluation coefficient of the first solution, then the first solution in the updated solution set is updated based on the secondary solution; Continue to iterate and optimize until the preset number of iterations is reached, output the current A updated solution sets, and select the first solution in the optimal updated solution set as the first optimized drying scheme, wherein the optimal updated solution set is the solution set with the smallest total energy consumption evaluation coefficient.

[0037] In a preferred embodiment, first, within the rated threshold range of the determined drying control parameters, random sampling is performed using a random number generation algorithm to obtain a set of numerical combinations of drying temperature, drying humidity, drying wind speed, and drying air volume. Through multiple random samplings, multiple groups of candidate drying parameter groups can be obtained, covering different areas of the drying parameter space, providing initial candidate solutions for subsequent optimization selection. Then, multiple drying parameter groups and the first drying time are substituted into the drying performance analysis channel to obtain the predicted values ​​of the moisture content of the lining cloth corresponding to each parameter group. Subsequently, the predicted values ​​are compared with the first-stage drying target, and the parameter group that can achieve the target moisture content is selected as the initial feasible solution to obtain multiple standard initial solutions. Among them, the drying performance analysis channel is constructed using a feedforward neural network, which is obtained through training with a large amount of historical production data. The drying performance analysis channel takes the drying parameter group and the drying time as input, and outputs the predicted change value of the moisture content of the lining cloth, which can effectively evaluate the drying effect under different parameter combinations. Through the drying performance evaluation, the initial solution that meets the requirements is screened out from the randomly generated candidate solutions, narrowing the scope of the subsequent optimization search and improving the optimization efficiency. Afterwards, the standard initial solution is substituted into the energy consumption evaluation channel to obtain the energy consumption prediction value corresponding to each initial solution, and the energy consumption prediction value is normalized to an energy consumption evaluation coefficient between 0 and 1. The smaller the energy consumption evaluation coefficient, the better the energy consumption performance of the standard initial solution. Among them, the energy consumption evaluation channel is also constructed using a feedforward neural network, which is obtained through training with a large amount of historical energy consumption data. The energy consumption evaluation channel takes the drying parameter group and drying time as input, and outputs the predicted energy consumption, which can effectively evaluate the energy cost of different drying parameter groups. Through energy consumption evaluation, the differences in energy utilization efficiency of standard initial solutions that meet the drying performance requirements are further revealed, providing a basis for judgment for subsequent energy consumption optimization.

[0038] Subsequently, all standard initial solutions are arranged in order from small to large according to the energy consumption evaluation coefficient to form an ordered sequence of initial solutions. The standard initial solutions at the front of the sequence represent parameter combinations with relatively good energy consumption performance under the premise of meeting the drying performance requirements; while the initial solutions at the back of the sequence mean relatively high energy consumption levels and greater optimization potential. By sorting the energy consumption, the standard initial solutions are distinguished from each other, which is convenient for focused search and accelerated convergence of optimization. Then, from the sorted initial solution sequence, the first A solutions are selected as the preferred starting point for optimization search, recorded as the first solution; the last B solutions are selected as auxiliary references for optimization search, recorded as secondary solutions. Among them, A and B are positive integers, and the sum of A and B is equal to the number of initial solutions in the initial solution sequence. By setting the first solution and the secondary solution, multiple reference points are formed in the optimization search process. With the first solution with better energy consumption performance as the center, combined with the secondary solution with suboptimal energy consumption performance, a search strategy that focuses on optimization and takes into account the overall situation is formed. By cross-fusion of the first solution and the secondary solution, the convergence of the optimization algorithm to the global optimal solution can be accelerated.

[0039] Next, the B secondary solutions are assigned to the A primary solutions by random clustering to form A solution sets. Each solution set consists of a primary solution and several secondary solutions, representing a local optimization search space. In each solution set, the primary solution is used as the current optimal drying solution, and the drying parameters in the secondary solution are locally adjusted using a preset four-element step size to generate several adjusted new solutions to form A updated solution sets. The preset four-element step size refers to setting different numerical adjustment steps for different types of drying parameters. For example, for the drying temperature parameter, the temperature adjustment step size is set to 5-10 degrees Celsius according to the heat resistance threshold of the lining cloth; and for the drying wind speed parameter, the wind speed adjustment step size can be set to 10-50 rpm according to the speed regulation range of the fan. When adjusting the parameters of the secondary solution, the secondary solution in the updated solution set is checked. If the secondary solution in the adjusted updated solution set exceeds the parameter rated threshold, the original parameter value should be kept unchanged to ensure that the optimization search is always carried out within the feasible parameter space.

[0040] Afterwards, the constructed drying performance analysis channel and energy consumption evaluation channel are used to evaluate each sub-solution in the updated solution set. If it is found that a sub-solution meets the first-stage drying target and its energy consumption evaluation coefficient is less than the first solution, it means that the sub-solution is better than the first solution. At this time, the sub-solution is used to replace the first solution to complete the update iteration of the first solution in the solution set. By updating the first solution in the solution set, the search focus can be guided to the better solution area, and the dynamic optimization of the local search space can be achieved. After multiple rounds of iterations, the total energy consumption evaluation coefficients of the current A updated solution sets are compared, and the updated solution set with the smallest total energy consumption evaluation coefficient is selected as the optimal updated solution set, and the first solution in the optimal updated solution set is used as the optimal control scheme for the first-stage drying target, that is, the first optimized drying scheme. At this point, the drying parameters of the first drying furnace at the first-stage drying target are systematically optimized under given drying time and process constraints, and energy consumption is minimized while meeting the drying quality requirements, so as to obtain an optimized drying scheme that takes into account both drying performance and optimal energy consumption.

[0041] Furthermore, the embodiment of the present application also includes: Execute the drying operation of the target wet lining cloth according to the optimized drying scheme, and record the drying data of the wet lining cloth; Analyze the drying data of the wet lining cloth to determine the drying fluctuation thresholds of N stages; Selecting a first-stage drying fluctuation threshold, and dividing the first-stage drying fluctuation threshold according to a preset distance to determine a plurality of first-stage drying fluctuation intervals; Based on the stage drying target, drying deviations are calculated for multiple first stage drying fluctuation intervals to determine multiple drying deviation values; To eliminate the plurality of drying deviation values, optimizing the drying control parameters of the drying furnace in the next adjacent stage is performed to determine the optimization parameters of the plurality of adjacent stages; Establishing a first mapping association between the first stage drying fluctuation range and the optimization parameters of the adjacent stages, and constructing a predetermined deviation correction decision tree based on the first mapping association; The drying effect is monitored in real time through a predetermined moisture measurement array, and the real-time compensation of the drying operation is completed based on the predetermined deviation correction decision tree.

[0042] In a feasible implementation, first, according to the generated optimized drying scheme, the actual drying operation is performed on the target wet lining cloth, and various sensors configured on the production line are used to collect various parameter data of the lining cloth drying process in real time, such as temperature, humidity, wind speed, lining cloth moisture content, etc., to form wet lining cloth drying data. The wet lining cloth drying data is divided according to the N stage drying targets, corresponding to the N drying furnace sections in the optimized drying scheme. For each drying stage, the maximum and minimum values ​​of the lining cloth moisture content in its historical production data are calculated as the upper and lower limit thresholds of the moisture content fluctuation under normal drying conditions in this stage, and the N stage drying fluctuation thresholds are determined. By setting the stage drying fluctuation threshold, the normal variation range of the lining cloth moisture content in each drying stage is quantitatively described. Then, the N stage drying fluctuation thresholds are processed in turn, and one stage drying fluctuation threshold is selected each time as the first stage drying fluctuation threshold. On the basis of the first-stage drying fluctuation threshold, the first-stage drying fluctuation threshold is divided into multiple moisture content sub-intervals according to the preset distance, forming multiple first-stage drying fluctuation intervals, so as to realize the hierarchical quantification of the drying process deviation and provide more detailed judgment criteria for subsequent deviation analysis and compensation control.

[0043] Then, for each first-stage drying fluctuation interval, take the midpoint value of the interval as the representative moisture content value of the interval, compare the representative moisture content value with the first-stage drying target, calculate the difference between the two, and obtain the drying deviation value of the interval relative to the first-stage drying target. A positive deviation indicates that the actual moisture content is higher than the first-stage drying target, and a negative deviation indicates that the actual moisture content is lower than the first-stage drying target. The larger the absolute value of the deviation value, the greater the degree of deviation from the target. By calculating the drying deviation values ​​of each interval, multiple drying deviation values ​​are obtained, which quantitatively characterize the severity of the drying process deviating from the expected target under different moisture content fluctuations, and provide a judgment basis for subsequent compensation control measures. Subsequently, with the elimination of the drying deviation of the first stage as the optimization target, and the next adjacent stage of the first drying stage as the optimization object, an optimal search is performed in the control parameter space of the drying furnace in this stage, and a set of optimal control parameters of the adjacent stages corresponding to multiple drying deviation values ​​are obtained, thereby determining multiple adjacent stage optimization parameters. Next, with the first-stage drying fluctuation interval as the independent variable and the corresponding adjacent stage optimization parameters as the dependent variable, an interval-parameter mapping relationship table is established. On the basis of this mapping relationship, a decision tree algorithm is used to construct a predetermined deviation correction decision tree. The predetermined deviation correction decision tree takes the real-time moisture content monitoring value of the first stage drying process as input, locks the drying fluctuation interval where the monitoring value is located, and then outputs the corresponding adjacent stage optimization parameters according to the interval-parameter mapping relationship, thereby realizing the automatic matching of the drying deviation state to the compensation control measures. An online moisture sensor array is arranged in each drying stage of the lining cloth drying production line to collect the wet lining cloth drying data in real time. When the wet lining cloth drying data of the first drying stage is monitored to have a deviation, the corresponding first stage drying fluctuation interval is determined and input into the predetermined deviation correction decision tree China to obtain the adjacent stage optimization parameters for the next adjacent stage. The adjacent stage optimization parameters are sent to the drying furnace of the next adjacent stage, and the temperature, wind speed, etc. of the drying furnace of this stage are dynamically adjusted to realize the rapid compensation of the deviation. Through the feedforward optimization control based on real-time deviation monitoring, the influence of the deviation of the first drying stage on the subsequent stages can be eliminated to the maximum extent, ensuring the quality stability and energy-saving optimization of the entire drying process.

[0044] Furthermore, the embodiment of the present application also includes: Collect moisture sensor monitoring data and drying control data; Performing delay analysis based on the moisture sensor monitoring data and the drying control data to determine the sensor monitoring delay and the drying control delay; A comprehensive control delay is determined based on the sensor monitoring delay and the drying control delay, and control nodes of optimization parameters in adjacent stages are compensated based on the comprehensive control delay.

[0045] In a preferred embodiment, the moisture sensor monitoring data includes the real-time moisture content measurement value of the lining cloth at each drying stage, reflecting the dynamic change of the moisture state of the lining cloth, and is collected and transmitted in real time by moisture sensors arranged at the entrance and exit of the drying furnace. The drying control data includes the equipment operation parameters of each drying stage, such as the drying furnace temperature, fan frequency, cloth transmission speed, etc., reflecting the real-time working condition and control state of the drying furnace, and is collected and transmitted in real time by temperature sensors, speed sensors, etc. arranged on the drying equipment. Through the real-time collection of moisture sensor monitoring data and drying control data, the material state information and equipment operation state information of the lining cloth drying process can be comprehensively and dynamically grasped, providing a data basis for compensation control.

[0046] Subsequently, the moisture sensor monitoring data is timestamped and cleaned, and the measured values ​​of the moisture content of the lining cloth and the corresponding sampling moments are extracted to form a complete moisture content time series. The statistical characteristics of the moisture content time series are analyzed, and the mathematical relationship between the moisture content change and the actual moisture state change is established. The inherent delay of the moisture sensor measurement loop is estimated, which is recorded as the sensor monitoring delay. Similarly, the drying control data is timestamped and cleaned, and the operating parameters of each device and the corresponding sampling moments are extracted to form the device state time series. The correlation between the device state time series and the action response of the actual actuator is analyzed, and the mathematical relationship between the device state change and the actual control effect is established. The inherent delay of the drying control execution loop is quantitatively estimated, which is recorded as the drying control delay. Through the time series correlation analysis, the measurement and control delay characteristics of the lining cloth drying production line control system are objectively evaluated, and the time lag between moisture state perception and control command execution is quantified, providing a time scale basis for subsequent dynamic compensation control.

[0047] After that, the sensor monitoring delay and the drying control delay are summed to obtain the total delay from the occurrence of moisture content deviation to the actual effectiveness of drying compensation measures, which is the comprehensive control delay, reflecting the overall response speed of the control system to moisture deviation disturbances. After obtaining the comprehensive control delay, the delay is used as the time scale to perform forward compensation on the time axis for each adjacent stage optimization parameter in the constructed predetermined deviation correction decision tree, forming a dynamic feedforward control sequence to achieve compensation for the control nodes of the adjacent stage optimization parameters.

[0048] Through comprehensive control delay analysis and compensation, the inherent information lag effect in the drying production process is overcome, so that the compensation control can respond to the dynamic changes of moisture deviation in a timely and accurate manner, minimize the impact of the deviation on the drying quality of the lining cloth, and improve the control accuracy and dynamic performance of the drying production line.

[0049] In summary, the energy-saving control method for a lining cloth production workshop provided in the embodiment of the present application has the following technical effects: The attribute information of the target interlining is read, and the interlining drying records are retrieved with the attribute information as a constraint, providing data support and case reference for the construction of the interlining drying curve model, laying the foundation for data-driven optimization. Drying characteristics are analyzed based on the interlining drying records, and the interlining drying curve is constructed by fitting, revealing the intrinsic connection between the interlining properties and the drying characteristics, forming a theoretical tool to guide the setting of drying parameters, and providing a decision-making basis for the subsequent optimization of the drying process. The initial moisture content is determined by calling the historical processing log analysis, and the interlining drying curve is mapped with the initial moisture content and the expected moisture content to determine the target drying curve, providing optimization targets and constraints for staged drying control. The target drying production line is identified, the target drying curve is divided based on the number of drying furnace sections, and the N-stage drying targets are determined, fully considering the impact of the equipment layout on the drying process, and laying the foundation for the subsequent independent optimization control in stages, improving the pertinence and operability of drying parameter optimization. With the purpose of meeting the N-stage drying targets, the stage optimization of the drying control parameters is performed, and the optimized drying plan is integrated to generate the optimized drying plan, which is the most energy-efficient plan, while meeting the quality targets of each stage and minimizing the overall energy consumption, achieving the purpose of energy saving and efficiency improvement. The target wet lining cloth is dried according to the optimized drying plan, and the drying effect is monitored in real time. The real-time compensation of the drying operation is completed based on the predetermined deviation proofreading decision tree. The drying effect deviation is eliminated in time through closed-loop feedback control, ensuring the continuous stability of the lining cloth product quality. The multi-stage drying parameter setting is guided by the data-driven modeling optimization method, and the real-time monitoring and intelligent compensation mechanism are introduced to minimize the drying energy consumption while ensuring the stability of the lining cloth product quality, thus achieving energy-saving and efficient production.

[0050] Embodiment 2 Based on the same inventive concept as the energy-saving control method for a lining cloth production workshop in the aforementioned embodiment, Figure 2 As shown, the embodiment of the present application provides an energy-saving control device for a lining cloth production workshop, the device comprising: A record retrieval component 11 is used to read the attribute information of the target lining cloth, and retrieve and obtain the lining cloth drying record based on the attribute information as a constraint; A drying curve fitting component 12 is used to analyze the drying characteristics based on the lining cloth drying record and to fit and construct a lining cloth drying curve; A drying curve determination component 13 is used to call historical processing logs for analysis to determine the initial moisture content, and map the lining cloth drying curve with the initial moisture content and the expected moisture content to determine the target drying curve; The curve division component 14 is used to identify the target drying production line, divide the target drying curve based on the number of drying furnace sections, and determine N stage drying targets, wherein the target drying production line includes N drying furnace sections, and each drying furnace section can be independently controlled, and N is an integer greater than 2; The parameter stage optimization component 15 is used to perform stage optimization of drying control parameters for the purpose of meeting the N stage drying targets, and integrate and generate an optimized drying plan, wherein the optimized drying plan is a plan with the best comprehensive energy consumption; The drying operation execution component 16 is used to execute the drying operation of the target wet lining cloth according to the optimized drying scheme, monitor the drying effect in real time, and complete the real-time compensation of the drying operation based on the predetermined deviation calibration decision tree.

[0051] Furthermore, the drying curve fitting component 12 includes the following execution steps: Reading the property information of the target lining cloth, wherein the property information at least includes the lining cloth material, lining cloth thickness, lining cloth density, hygroscopicity, air permeability and heat resistance; Based on the textile big data, taking the attribute information as a constraint condition, the lining cloth drying record is retrieved online, wherein the lining cloth drying record includes a plurality of lining cloth drying data, and each lining cloth drying data includes a plurality of sample drying nodes and a plurality of sample moisture contents; A two-dimensional coordinate system is constructed based on the sample drying nodes and the sample moisture content, and multiple lining cloth drying data are sequentially distributed in the two-dimensional coordinate system to generate multiple initial lining cloth drying curves; The multiple initial lining cloth drying curves are subjected to time normalization processing, and curve fitting of the multiple normalized lining cloth drying curves is performed based on the Bezier curve fitting principle to obtain the lining cloth drying curve.

[0052] Furthermore, the drying curve fitting component 12 also includes the following execution steps: Based on the Bezier curve fitting principle, curve fitting of multiple normalized lining cloth drying curves is performed to obtain an initial fitting curve; Performing similarity analysis on the initial fitting curve and the multiple initial lining cloth drying curves in sequence to determine multiple curve similarity coefficients; Eliminate the initial lining cloth drying curves corresponding to the curve similarity coefficients that do not meet the predetermined similarity threshold, and obtain multiple standard lining cloth drying curves; The plurality of standard lining cloth drying curves are subjected to curve fitting based on the Bezier curve fitting principle to obtain the lining cloth drying curve.

[0053] Furthermore, the parameter phase optimization component 15 includes the following execution steps: Identify the drying furnace, determine the drying control parameters and parameter rated thresholds, the drying control parameters including drying temperature, drying humidity, drying wind speed and drying air volume; Selecting a first drying furnace, obtaining a first-stage drying target of the first drying furnace, and determining a first drying time based on a rated conveying speed of a drying conveyor belt and a length of the first drying furnace; With the purpose of meeting the first-stage drying target, based on the first drying time and the parameter rated threshold, a stage optimization of the drying control parameters is performed to generate a first optimized drying plan, which is added to the optimized drying plan, wherein the rated threshold of the drying temperature is initially updated using the heat resistance.

[0054] Furthermore, the parameter phase optimization component 15 also includes the following execution steps: Based on the parameter rating threshold, randomly generating a plurality of drying parameter groups; Through the drying performance analysis channel, the drying performance of the multiple drying parameter groups is evaluated based on the first drying time, and an initial solution that meets the first stage drying target is extracted to obtain multiple standard initial solutions; Performing energy consumption evaluation on the multiple standard initial solutions respectively through an energy consumption evaluation channel, and outputting multiple energy consumption evaluation coefficients, wherein the drying performance analysis channel and the energy consumption evaluation channel are constructed based on a feedforward neural network; Arranging the multiple initial solutions from small to large according to the energy consumption evaluation coefficients to generate an initial solution sequence; Select the first A initial solutions in the initial solution sequence as primary solutions and the last B initial solutions as secondary solutions, where the sum of A and B is the number of initial solutions in the initial solution sequence; Based on A first solutions, B secondary solutions are randomly clustered to generate A solution sets, and within the A solution sets, the first solution is used as the optimal solution, and the secondary solutions in the solution set are adjusted once based on a predetermined quaternary step size to determine A updated solution sets, wherein during the adjustment process, if the secondary solution in the updated solution set does not meet the parameter rated threshold, the secondary solution parameter is not updated; In the A updated solution sets, if there is a secondary solution that meets the first stage drying target and the energy consumption evaluation coefficient is less than the energy consumption evaluation coefficient of the first solution, then the first solution in the updated solution set is updated based on the secondary solution; Continue to iterate and optimize until the preset number of iterations is reached, output the current A updated solution sets, and select the first solution in the optimal updated solution set as the first optimized drying scheme, wherein the optimal updated solution set is the solution set with the smallest total energy consumption evaluation coefficient.

[0055] Furthermore, the drying operation execution component 16 includes the following execution steps: Execute the drying operation of the target wet lining cloth according to the optimized drying scheme, and record the drying data of the wet lining cloth; Analyze the drying data of the wet lining cloth to determine the drying fluctuation thresholds of N stages; Selecting a first-stage drying fluctuation threshold, and dividing the first-stage drying fluctuation threshold according to a preset distance to determine a plurality of first-stage drying fluctuation intervals; Based on the stage drying target, drying deviations are calculated for multiple first stage drying fluctuation intervals to determine multiple drying deviation values; To eliminate the plurality of drying deviation values, optimizing the drying control parameters of the drying furnace in the next adjacent stage is performed to determine the optimization parameters of the plurality of adjacent stages; Establishing a first mapping association between the first stage drying fluctuation range and the optimization parameters of the adjacent stages, and constructing a predetermined deviation correction decision tree based on the first mapping association; The drying effect is monitored in real time through a predetermined moisture measurement array, and the real-time compensation of the drying operation is completed based on the predetermined deviation correction decision tree.

[0056] Furthermore, the drying operation execution component 16 also includes the following execution steps: Collect moisture sensor monitoring data and drying control data; Performing delay analysis based on the moisture sensor monitoring data and the drying control data to determine the sensor monitoring delay and the drying control delay; A comprehensive control delay is determined based on the sensor monitoring delay and the drying control delay, and control nodes of optimization parameters in adjacent stages are compensated based on the comprehensive control delay.

[0057] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0058] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An energy-saving control method for a lining cloth production workshop, characterized in that: The method comprises: Reading the attribute information of the target lining cloth, and using the attribute information as a constraint, retrieving and acquiring the lining cloth drying record; Perform drying characteristic analysis based on the lining cloth drying record, and construct a lining cloth drying curve by fitting; Calling historical processing logs for analysis to determine the initial moisture content, and mapping the lining cloth drying curve with the initial moisture content and the expected moisture content to determine the target drying curve; Identify the target drying production line, divide the target drying curve based on the number of drying furnace sections, and determine N stage drying targets, wherein the target drying production line includes N drying furnace sections, and each drying furnace section can be independently controlled, and N is an integer greater than 2; To meet the N-stage drying targets, the drying control parameters are optimized in stages, and an optimized drying plan is generated through integration, wherein the optimized drying plan is a plan with the best comprehensive energy consumption; The drying operation of the target wet lining cloth is performed according to the optimized drying scheme, and the drying effect is monitored in real time, and the real-time compensation of the drying operation is completed based on the predetermined deviation correction decision tree.

2. The method according to claim 1, characterized in that: Based on the lining cloth drying record, a drying characteristic analysis is performed and a lining cloth drying curve is constructed by fitting, including: Reading the property information of the target lining cloth, wherein the property information at least includes the lining cloth material, lining cloth thickness, lining cloth density, hygroscopicity, air permeability and heat resistance; Based on the textile big data, taking the attribute information as a constraint condition, the lining cloth drying record is retrieved online, wherein the lining cloth drying record includes a plurality of lining cloth drying data, and each lining cloth drying data includes a plurality of sample drying nodes and a plurality of sample moisture contents; A two-dimensional coordinate system is constructed based on the sample drying nodes and the sample moisture content, and multiple lining cloth drying data are sequentially distributed in the two-dimensional coordinate system to generate multiple initial lining cloth drying curves; The multiple initial lining cloth drying curves are subjected to time normalization processing, and curve fitting of the multiple normalized lining cloth drying curves is performed based on the Bezier curve fitting principle to obtain the lining cloth drying curve.

3. The method according to claim 2, characterized in that The lining cloth drying curve is obtained, and the process also includes: Based on the Bezier curve fitting principle, curve fitting of multiple normalized lining cloth drying curves is performed to obtain an initial fitting curve; Performing similarity analysis on the initial fitting curve and the multiple initial lining cloth drying curves in sequence to determine multiple curve similarity coefficients; Eliminate the initial lining cloth drying curves corresponding to the curve similarity coefficients that do not meet the predetermined similarity threshold, and obtain multiple standard lining cloth drying curves; The plurality of standard lining cloth drying curves are subjected to curve fitting based on the Bezier curve fitting principle to obtain the lining cloth drying curve.

4. The method according to claim 2, characterized in that: In order to meet the N-stage drying targets, the drying control parameters are optimized in stages, and an optimized drying plan is generated by integration, including: Identify the drying furnace, determine the drying control parameters and parameter rated thresholds, the drying control parameters including drying temperature, drying humidity, drying wind speed and drying air volume; Selecting a first drying furnace, obtaining a first-stage drying target of the first drying furnace, and determining a first drying time based on a rated conveying speed of a drying conveyor belt and a length of the first drying furnace; With the purpose of meeting the first-stage drying target, based on the first drying time and the parameter rated threshold, a stage optimization of the drying control parameters is performed to generate a first optimized drying plan, which is added to the optimized drying plan, wherein the rated threshold of the drying temperature is initially updated using the heat resistance.

5. The method according to claim 4, characterized in that Generate a first optimized drying plan, including: Based on the parameter rating threshold, randomly generating a plurality of drying parameter groups; Through the drying performance analysis channel, the drying performance of the multiple drying parameter groups is evaluated based on the first drying time, and an initial solution that meets the first stage drying target is extracted to obtain multiple standard initial solutions; Performing energy consumption evaluation on the multiple standard initial solutions respectively through an energy consumption evaluation channel, and outputting multiple energy consumption evaluation coefficients, wherein the drying performance analysis channel and the energy consumption evaluation channel are constructed based on a feedforward neural network; Arranging the multiple initial solutions from small to large according to the energy consumption evaluation coefficients to generate an initial solution sequence; Select the first A initial solutions in the initial solution sequence as primary solutions and the last B initial solutions as secondary solutions, where the sum of A and B is the number of initial solutions in the initial solution sequence; Based on A first solutions, B secondary solutions are randomly clustered to generate A solution sets, and within the A solution sets, the first solution is used as the optimal solution, and the secondary solutions in the solution set are adjusted once based on a predetermined quaternary step size to determine A updated solution sets, wherein during the adjustment process, if the secondary solution in the updated solution set does not meet the parameter rated threshold, the secondary solution parameter is not updated; In the A updated solution sets, if there is a secondary solution that meets the first stage drying target and the energy consumption evaluation coefficient is less than the energy consumption evaluation coefficient of the first solution, then the first solution in the updated solution set is updated based on the secondary solution; Continue to iterate and optimize until the preset number of iterations is reached, output the current A updated solution sets, and select the first solution in the optimal updated solution set as the first optimized drying scheme, wherein the optimal updated solution set is the solution set with the smallest total energy consumption evaluation coefficient.

6. The method according to claim 1, characterized in that The target wet lining cloth is dried according to the optimized drying scheme, and the drying effect is monitored in real time. The real-time compensation of the drying operation is completed based on the predetermined deviation proofreading decision tree, including: Execute the drying operation of the target wet lining cloth according to the optimized drying scheme, and record the drying data of the wet lining cloth; Analyze the drying data of the wet lining cloth to determine the drying fluctuation thresholds of N stages; Selecting a first-stage drying fluctuation threshold, and dividing the first-stage drying fluctuation threshold according to a preset distance to determine a plurality of first-stage drying fluctuation intervals; Based on the stage drying target, drying deviations are calculated for multiple first stage drying fluctuation intervals to determine multiple drying deviation values; To eliminate the plurality of drying deviation values, optimizing the drying control parameters of the drying furnace in the next adjacent stage is performed to determine the optimization parameters of the plurality of adjacent stages; Establishing a first mapping association between the first stage drying fluctuation range and the optimization parameters of the adjacent stages, and constructing a predetermined deviation correction decision tree based on the first mapping association; The drying effect is monitored in real time through a predetermined moisture measurement array, and the real-time compensation of the drying operation is completed based on the predetermined deviation correction decision tree.

7. The method according to claim 6, characterized in that The real-time compensation of the drying operation is completed based on the predetermined deviation correction decision tree, including: Collect moisture sensor monitoring data and drying control data; Performing delay analysis based on the moisture sensor monitoring data and the drying control data to determine the sensor monitoring delay and the drying control delay; A comprehensive control delay is determined based on the sensor monitoring delay and the drying control delay, and control nodes of optimization parameters in adjacent stages are compensated based on the comprehensive control delay.

8. Energy-saving control equipment for lining cloth production workshop, characterized in that: The energy-saving control method for a lining cloth production workshop according to any one of claims 1 to 7 is used to implement the device comprising: A record retrieval component, the record retrieval component is used to read the attribute information of the target lining cloth, and retrieve and obtain the lining cloth drying record based on the attribute information as a constraint; A drying curve fitting component, the drying curve fitting component is used to perform drying characteristic analysis based on the lining cloth drying record, and to fit and construct a lining cloth drying curve; A drying curve determination component, the drying curve determination component is used to call the historical processing log analysis to determine the initial moisture content, and map the lining cloth drying curve with the initial moisture content and the expected moisture content to determine the target drying curve; A curve division component, the curve division component is used to identify a target drying production line, divide the target drying curve based on the number of drying furnace sections, and determine N stage drying targets, wherein the target drying production line includes N drying furnace sections, and each drying furnace section can be independently controlled, and N is an integer greater than 2; A parameter stage optimization component, wherein the parameter stage optimization component is used to perform stage optimization of drying control parameters for the purpose of meeting the N stage drying targets, and integrate and generate an optimized drying plan, wherein the optimized drying plan is a plan with the best comprehensive energy consumption; A drying operation execution component is used to execute the drying operation of the target wet lining cloth according to the optimized drying scheme, monitor the drying effect in real time, and complete the real-time compensation of the drying operation based on the predetermined deviation proofreading decision tree.

Images