Intelligent regulation and control system and method for rotating speed of front roller of spinning frame

Abstract

The invention belongs to the technical field of spinning management and control, and discloses a spinning frame front roller rotating speed intelligent regulation and control system and method.The method comprises the steps that data collection is conducted on the production process of a target spinning frame, and corresponding spinning frame information is obtained and stored; the spinning frame information comprises operation data and production data; performing data processing on the obtained information of the spinning frame, and constructing a corresponding multi-objective optimization function based on a data processing result; constructing a corresponding production parameter tuning model based on the obtained target optimization function; performing parameter control on a target spinning frame in combination with the production parameter tuning model; the method is of great significance in improving the production efficiency and the product quality of the spinning frame and reducing the energy consumption and the labor cost.

Description

Technical Field

[0001] The present invention relates to the technical field of spinning control, and more specifically, to an intelligent control system and method for the front roller speed of a spinning frame. Background Art

[0002] With the continuous improvement of the requirements for production efficiency and product quality in the textile industry, the automation and intelligence levels of spinning frames also need to be correspondingly improved; some existing detection and control methods cannot meet the requirements of modern textile production for high precision and high efficiency, and more intelligent and automated systems are needed to achieve real-time monitoring and control; in recent years, with the rapid development of Internet of Things, big data, and artificial intelligence technologies, intelligent control technologies have been gradually applied to the speed control of textile equipment; however, most of the existing intelligent speed control methods only optimize a single speed parameter, ignoring various factors involved in the operation process of the spinning frame, such as energy consumption, output, and quality, and it is difficult to achieve the globally optimal control effect.

[0003] Compared with the prior art, in the traditional spinning process, the speed of the front roller is usually manually adjusted by operators or controlled in a fixed mode; these methods are difficult to adapt to the changes in different yarn varieties and production environments, resulting in problems such as low production efficiency, high energy consumption, and unstable product quality; these problems seriously affect the production efficiency and product quality of the spinning frame. In view of this, the present invention proposes an intelligent control system and method for the front roller speed of a spinning frame to solve the above problems. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art and to achieve the above object, the present invention provides the following technical solutions: An intelligent control method for the front roller speed of a spinning frame, comprising: Step 1: Collect data on the production process of the target spinning frame, obtain the corresponding spinning frame information and store it; the spinning frame information includes operation data and production data; Step 2: Process the obtained spinning frame information and construct a corresponding multi-objective optimization function based on the data processing results; Step 3: Construct a corresponding production parameter optimization model based on the obtained target optimization function; and control the parameters of the target spinning frame in combination with the production parameter optimization model.

[0005] Further, the process of collecting data on the production process of the target spinning frame, obtaining the corresponding spinning frame information and storing it includes: Set up data acquisition nodes, and based on the data acquisition nodes, collect relevant data during the production process of the corresponding spinning frame to obtain the corresponding spinning frame information; the spinning frame information includes spinning operation data, spinning energy consumption data, and spinning production data; Perform data preprocessing on the collected spinning frame information; after the data preprocessing is completed, store the spinning frame information with completed data preprocessing into a pre-constructed information database; wherein, the information database also stores the corresponding spinning transaction information.

[0006] Furthermore, the process of performing data processing on the obtained spinning frame information includes: Construct a two-dimensional rectangular coordinate system with time as the horizontal axis and spinning frame information as the vertical axis, and map the obtained rectangular coordinate system into the corresponding two-dimensional rectangular coordinate system to obtain the corresponding spinning change curve; the spinning change curve includes a spinning operation data curve, a spinning energy consumption data curve, and a spinning production data curve; Perform data sampling on the obtained spinning operation data curve, spinning energy consumption data curve, and spinning production data curve respectively, and construct the corresponding operation matrix, energy consumption matrix, and production matrix based on them; Perform normalization processing on the obtained energy consumption matrix and operation matrix respectively, and perform component extraction on the normalized energy consumption matrix and operation matrix based on the principal component analysis algorithm to obtain the corresponding eigenpairs; Based on the above process of obtaining eigenpairs, and based on randomly sampling the spinning operation data curve and spinning energy consumption data curve to update the operation matrix and eigenmatrix, and repeating the process of extracting eigenpairs, obtain several eigenpairs; construct the corresponding first eigenspace matrix based on the eigenpairs; Based on the above method of obtaining the first eigenspace matrix, obtain the corresponding second eigenspace matrix corresponding to the spinning operation data and the spinning output data; Obtain the collected spinning transaction information, and construct the corresponding spinning profit curve based on it. Furthermore, based on the collection time, perform data fitting on the corresponding spinning profit curve and spinning operation curve to obtain the corresponding operation-profit fitting curve; Furthermore, construct the corresponding multi-objective optimization function based on the operation-profit fitting curve, the first eigenspace matrix, and the second eigenspace matrix.

[0007] Furthermore, the formula for obtaining eigenpairs is: ; in the formula, and respectively represent the eigenvectors corresponding to the inner eigen u a and v a of the a-th eigenpair; ρ a represents the unit eigenvector corresponding to the matrix TM when the a-th eigenpair is extracted; represents the weight vector corresponding to the feature v in the a-th feature pair a ; ; where A and B represent the energy consumption matrix and the operation matrix respectively; θ represents the maximum eigenvalue corresponding to the matrix TM; where TM = A T BB T A; multi-objective optimization function ; G(E1) and G(E2) refer to the linear functions defined by the corresponding first feature space matrix and the second feature space matrix respectively; F(b) is the defined linear function of the corresponding operation-profit fitting curve; E1, E2 and b represent the function independent variables of the linear functions defined by the corresponding first feature space matrix, the second feature space matrix and the operation-profit fitting curve respectively.

[0008] Furthermore, the process of constructing the corresponding production parameter tuning model based on the obtained objective optimization function includes: Defining the network framework of the production parameter tuning model as an improved convolutional neural network for learning the non-linear relationship between the roving operation data and the roving production data in the roving machine information; The basic architecture of the improved convolutional neural network is an input layer, a multi-scale convolutional layer and an output layer; The output layer is used to receive the input training samples and convert the corresponding training samples into one-dimensional data vectors; The multi-scale convolutional layer is composed of a convolutional layer and a pooling layer, and several multi-scale convolutional layers are set in the corresponding improved convolutional neural network; the convolutional layer is used to perform convolutional operations on the one-dimensional data vectors output by the input layer to obtain the output features corresponding to the convolutional layer; the pooling layer is used to perform pooling operations on the output features of the convolutional layer; A fully connected layer is set in the output layer, and the fully connected layer is used to map the output features learned by the improved convolutional neural network into the corresponding sample space, and the result is output by the output layer; Defining the loss function ; where is the total number of training samples input to the production parameter tuning model, z is an index variable used to traverse all training samples, is the output of the production parameter tuning model for the z-th training sample, and Y(z) is the label of the z-th training sample; Initialize the weights in each layer of the improved convolutional neural network based on the multi-objective optimization function. After the initialization is completed, construct a corresponding training data set based on the historical spinning machine information, divide the training samples in the training data set into several training batches, and perform iterative training on the corresponding production parameter tuning model based on them, and record the values of the corresponding loss function. When the loss function no longer decreases or changes within several consecutive training batches, save the model parameters at this time, that is, complete the construction process of the corresponding production parameter tuning model.

[0009] Further, define the formula for the convolution operation as: ; where represents the j-th output feature in the convolutional layer within the -th multi-scale convolutional layer; represents the j-th output feature in the previous layer of the convolutional layer within the multi-scale convolutional layer; (i.e., the output result of the pooling layer within the -th multi-scale convolutional layer); > 0 and is an integer); M j represents the total number of output results of the previous layer of the convolutional layer within the -th multi-scale convolutional layer; represents the weight matrix of the convolutional kernel within the -th convolutional layer; represents the bias term of the convolutional layer; represents the convolution operation, and f() represents the selected activation function; Define the formula for the pooling operation as: ; where represents the downsampling parameter of the i-th output feature in the pooling layer within the -th multi-scale convolutional layer, and H() represents the downsampling function; represents the bias term of the pooling layer; represents the i-th output feature of the pooling layer within the -th multi-scale convolutional layer; , i, and j are all natural numbers, representing the layer indices of the multi-scale convolutional layer and the pooling layer and convolutional layer within the multi-scale convolutional layer respectively.

[0010] Further, the process of initializing the weights in each layer of the improved convolutional neural network includes: Obtain the mean square error of the network performance function within the corresponding improved convolutional neural network, and construct a corresponding fitness function in combination with the obtained multi-objective optimization function ; where MSE represents the mean square error of the network performance function, and represent the function weights of the multi-objective optimization function and the mean square error; Meanwhile, initialize a particle swarm set based on the learning mode of the improved convolutional neural network, and define the number of particles and the spatial dimension corresponding to the respective particle swarm sets; Obtain the initial velocity and initial position of each particle in the corresponding particle swarm, and mark them as Sp and Wp respectively; obtain the fitness value corresponding to the corresponding particle based on the fitness function, and update the initial position and initial velocity of the corresponding particle based on it; Continuously update the initial position and initial velocity of each particle in the corresponding particle swarm based on the fitness function until the pre-set iteration stop condition is satisfied, then obtain the corresponding global optimal solution; map the obtained global optimal solution into the corresponding improved convolutional neural network, and then obtain a new fitness value through the forward feedback output of the improved convolutional neural network, and update the weights of the improved convolutional neural network based on it.

[0011] Further, define the update formula for the initial position as: ; where represents the particle position of particle p at the (k + 1)-th iteration; represents the particle velocity of particle p at the k-th iteration; and represent the individual optimal solution and the global optimal solution at the k-th iteration respectively; r1 and r2 are constants, and both r1 and r2 ∈ [0, 1]; ω represents the adaptive inertia weight; ; where ω max and ω min represent the maximum value and the minimum value of the pre-set inertia weight respectively; k and k max represent the current iteration number and the maximum iteration number respectively; α and ε represent the velocity coefficients, which are fixed constants; c1 and c2 represent the learning factors; where ; where c10, c20 and c12, c22 represent the initial values and the final values of the learning factors c1 and c2 respectively.

[0012] Further, the process of controlling the parameters of the target spinning frame in combination with the production parameter optimization model includes: Based on the information database, obtain the real-time spinning frame information corresponding to the target spinning frame, and input it into the corresponding production parameter optimization model to obtain the corresponding model output result; the model output result is the optimal data after optimizing the target spinning operation data; Feed the obtained model output result back into the control terminal of the corresponding spinning frame; furthermore, the control terminal adjusts the spinning operation parameters of the corresponding spinning frame based on the model output result until the actual operation parameters are the same as the model output result.

[0013] Furthermore, an intelligent control system for the front roller speed of a spinning frame includes: A data acquisition module, configured to collect data on the production process of the target spinning frame, obtain the corresponding spinning frame information and store it; the spinning frame information includes operation data and production data; A data processing module, configured to process the obtained spinning frame information and construct a corresponding multi-objective optimization function based on the data processing result; A data regulation module, configured to construct a corresponding production parameter optimization model based on the obtained target optimization function; and perform parameter control on the target spinning frame in combination with the production parameter optimization model.

[0014] The technical effects and advantages of the intelligent control system and method for the front roller speed of a spinning frame according to the present invention: 1. The multi-objective optimization function constructed based on the data processing result can comprehensively consider multiple factors such as energy consumption, output, and profit, and achieve the optimal configuration of the spinning frame operation parameters; it helps to reduce energy consumption and increase profit while meeting production requirements, achieving a win-win situation for economic and social benefits. 2. The production parameter optimization model constructed using the improved convolutional neural network can learn the non-linear relationship between the spinning operation data and the spinning production data in the spinning frame information, thereby achieving more accurate speed control; it not only has high prediction accuracy and generalization ability, but also can adapt to changes in different production environments and process requirements, improving the flexibility and adaptability of the control. 3. The present invention realizes the intelligent control of the front roller speed of the spinning frame, can automatically adjust the speed according to real-time data and optimization goals, making the operation of the spinning frame more stable and efficient; it not only improves production efficiency and product quality, but also reduces operation difficulty and labor costs, bringing significant economic benefits and competitive advantages to the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of an intelligent control method for the front roller speed of a spinning frame according to the present invention; Figure 2 It is a schematic diagram of an intelligent control system for the front roller speed of a spinning frame according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment 1 Please refer to Figure 1 As shown, a method for intelligent regulation of the front roller speed of a spinning frame in this embodiment includes: Step 1: Collect data on the production process of the target spinning frame, obtain the corresponding spinning frame information and store it; the spinning frame information includes operation data and production data; Step 2: Process the obtained spinning frame information and construct a corresponding multi-objective optimization function based on the data processing results; Step 3: Construct a corresponding production parameter optimization model based on the obtained target optimization function; and control the parameters of the target spinning frame in combination with the production parameter optimization model; It should be further noted that in the specific implementation process, the process of collecting data on the production process of the target spinning frame, obtaining the corresponding spinning frame information and storing it includes: Set data collection nodes, and the data collection nodes are set in the spinning frame equipment and the control terminal of the corresponding spinning frame according to actual needs; collect relevant data in the production process of the corresponding spinning frame based on the data collection nodes to obtain the corresponding spinning frame information; the spinning frame information includes spinning operation data, spinning energy consumption data and spinning production data; Among them, the spinning operation data consists of several spinning operation indicators, and the spinning operation indicators include the front roller speed of the spinning frame, spindle speed and other index data related to the operation of the corresponding spinning frame equipment; the spinning energy consumption data consists of several spinning energy consumption indicators, and the spinning energy consumption indicators include power indicators, voltage indicators and other index data related to the energy consumption of the spinning frame; the spinning production data consists of several spinning production indicators, and the spinning production indicators include output indicators, quality index parameters, etc.; Furthermore, perform data preprocessing on the collected spinning frame information. The data processing includes data cleaning, data conversion and format conversion. Data cleaning is used to eliminate or repair incorrect data and missing data in the corresponding spinning frame information. Data conversion is used to unify the data units in the corresponding spinning frame information. Format conversion is used to standardize the format of the discrete data in the corresponding spinning information and perform normalization processing to facilitate subsequent data processing and analysis; After the data preprocessing is completed, the information of the spinning frame with completed data preprocessing is stored in the pre-constructed information database; wherein, the information database also stores the corresponding spinning transaction information.

[0018] It should be further noted that, in the specific implementation process, the process of processing the obtained spinning frame information and constructing the corresponding multi-objective optimization function based on the data processing results includes: Construct a two-dimensional rectangular coordinate system with time as the horizontal axis and the spinning frame information as the vertical axis, and map the obtained rectangular coordinate system into the corresponding two-dimensional rectangular coordinate system to obtain the corresponding spinning change curve; the spinning change curve includes a spinning operation data curve, a spinning energy consumption data curve, and a spinning production data curve; Furthermore, data sampling is respectively performed on the obtained spinning operation data curve, spinning energy consumption data curve, and spinning production data curve, and the corresponding operation matrix, energy consumption matrix, and production matrix are constructed based on them; wherein, the column vectors of the operation matrix, energy consumption matrix, and production matrix are the respective index data in the corresponding operation data curve, spinning energy consumption data curve, and spinning production data curve; the row vectors are the acquisition values corresponding to the corresponding index data; Taking the energy consumption matrix and the operation matrix as examples, the obtained energy consumption matrix and operation matrix are respectively normalized, and component extraction is performed on the normalized energy consumption matrix and operation matrix based on the principal component analysis algorithm to obtain the corresponding eigenpairs; ; where and respectively represent the eigenvectors corresponding to the eigen u a and v a in the a-th eigenpair; ρ a represents the unit eigenvector corresponding to the matrix TM during the extraction of the a-th eigenpair, and is used to represent the weight vector of the eigen u a ; represents the weight vector corresponding to the eigen v a in the a-th eigenpair; ; where A and B respectively represent the energy consumption matrix and the operation matrix; θ represents the largest eigenvalue corresponding to the matrix TM; wherein, TM = A T BB T A; Based on the above process of obtaining eigenpairs, and by randomly sampling the spinning operation data curve and the spinning energy consumption data curve to update the operation matrix and the eigenmatrix, and repeating the process of extracting eigenpairs, several eigenpairs are obtained; a corresponding first eigenspace matrix is constructed based on the eigenpairs; the first eigenspace matrix retains the original eigenspace data information, realizes the orthogonality of the eigenspace, and maximally retains the mapping relationship between the spinning operation data and the spinning energy consumption data during the spinning process; Based on the above method for obtaining the first feature space matrix, obtain the second feature space matrix corresponding to the corresponding spun yarn running data and the corresponding spun yarn production data; Obtain the collected spun yarn transaction information, and construct the corresponding spun yarn profit curve based on it. Furthermore, based on the collection time, perform data fitting on the corresponding spun yarn profit curve and the spun yarn running curve to obtain the corresponding running-profit fitting curve; Furthermore, construct the corresponding multi-objective optimization function based on the running-profit fitting curve, the first feature space matrix, and the second feature space matrix; ; G(E1) and G(E2) refer to the linear functions defined by the corresponding first feature space matrix and the second feature space matrix respectively; F(b) is the defined linear function of the corresponding running-profit fitting curve; Y is a 3×1 vector containing energy consumption, production, and profit; E1, E2, and b respectively represent the function independent variables of the linear functions defined by the corresponding first feature space matrix, the second feature space matrix, and the running-profit fitting curve; among them, the function independent variables involved in the linear functions all belong to the spun yarn running data.

[0019] It should be further noted that in the specific implementation process, the process of constructing the corresponding production parameter tuning model based on the obtained objective optimization function includes: Define the network framework of the production parameter tuning model as an improved convolutional neural network, which is used to learn the non-linear relationship between the spun yarn running data and the spun yarn production data in the spun yarn machine information; The basic architecture of the improved convolutional neural network is an input layer, a multi-scale convolutional layer, and an output layer; The output layer is used to receive the input training samples and convert the corresponding training samples into one-dimensional data vectors; The multi-scale convolutional layer consists of a convolutional layer and a pooling layer, and several multi-scale convolutional layers are set in the corresponding improved convolutional neural network; the convolutional layer is used to perform convolutional operations on the one-dimensional data vectors output by the input layer to obtain the output features corresponding to the convolutional layer; the pooling layer is used to perform pooling operations on the output features of the convolutional layer to retain the main features and reduce the parameter vectors; and prevent overfitting; A fully connected layer is set in the output layer, and the fully connected layer is used to map the output features learned by the improved convolutional neural network into the corresponding sample space, and the result is output by the output layer; Define the formula for the convolutional operation as: ; In the formula, represents the th output feature in the convolutional layer of the th multi-scale convolutional layer; The output result of the pooling layer within a multi-scale convolutional layer; > 0 and is an integer); M j represents the total number of output results of the previous layer of the convolutional layer within the th multi-scale convolutional layer; represents the th weight matrix of the convolutional kernel within the convolutional layer; represents the bias term of the convolutional layer; represents the convolutional operation, and f() represents the selected activation function; The formula for defining the pooling operation is: ; where, represents the downsampling parameter of the th output feature in the pooling layer within the th multi-scale convolutional layer, and H() represents the downsampling function; represents the bias term of the pooling layer; represents the th output feature of the pooling layer within the

[0020] Define the loss function of the production parameter tuning model ; where, is the total number of training samples input to the production parameter tuning model, z is an index variable used to traverse all training samples, is the output of the production parameter tuning model for the zth training sample, and Y(z) is the label of the zth training sample; Initialize the weights within each layer of the improved convolutional neural network. After the initialization is completed; construct the corresponding training data set based on the historical spinning frame information, divide the training samples in the training data set into several training batches, and perform iterative training on the corresponding production parameter tuning model based on them, and record the values of the corresponding loss function. When the loss function no longer decreases or changes within several consecutive training batches, save the model parameters at this time, that is, complete the construction process of the corresponding production parameter tuning model; It should be further noted that in the specific implementation process, the process of initializing the weights within each layer of the improved convolutional neural network includes: Obtain the mean square error of the network performance function within the corresponding improved convolutional neural network, and construct the corresponding fitness function in combination with the obtained multi-objective optimization function ; where, MSE represents the mean square error of the network performance function, and The function weights representing the multi-objective optimization function and the mean square error; meanwhile, initialize a particle swarm set based on the learning mode of the improved convolutional neural network, and define the number of particles and the spatial dimension corresponding to the corresponding particle swarm set; Furthermore, obtain the initial velocity and initial position of each particle in the corresponding particle swarm, and mark them as Sp and Wp respectively; furthermore, obtain the fitness value corresponding to the corresponding particle based on the fitness function, and update the initial position and initial velocity of the corresponding particle based on it; where Sp ∈ [Vmin, Vmax]; Vmax and Vmin respectively represent the maximum particle velocity and the minimum particle velocity allowed for the corresponding particle; Wp ∈ [Ld, Ud]; Ld and Ud respectively represent the lower bound and the upper bound of the spatial dimension where the corresponding particle is located; Define the update formula for the initial position as: ; In the formula, represents the particle position of particle p at the (k + 1)-th iteration; represents the particle velocity of particle p at the k-th iteration; and respectively represent the individual optimal solution and the global optimal solution at the k-th iteration; r1, r2 are constants, and both r1, r2 ∈ [0, 1]; ω represents the adaptive inertia weight; ; In the formula, ω max and ω min respectively represent the maximum value and the minimum value of the inertia weight set in advance; k and k max respectively represent the current iteration number and the maximum iteration number; α and ε represent the velocity coefficients, which are fixed constants; c1 and c2 represent the learning factors; where, ; In the formula, c10, c20 and c12, c22 respectively represent the initial values and the final values of the learning factors c1 and c2; Furthermore, perform scale update on the initial position and initial velocity of each particle in the corresponding particle swarm based on the fitness function until the preset iteration stop condition is met, then obtain the corresponding global optimal solution; furthermore, map the obtained global optimal solution into the corresponding improved convolutional neural network, and then obtain a new fitness value through the forward feedback output of the improved convolutional neural network, and update the weights of the improved convolutional neural network based on it; where, the iteration stop condition is reaching the maximum iteration number or the individual optimal solution obtained is inferior to the global optimal solution for P1 consecutive times, and P1 is a fixed constant.

[0021] It should be further noted that in the specific implementation process, the process of controlling the parameters of the target spinning frame in combination with the production parameter optimization model includes: Based on the information database, obtain the real-time spinning machine information corresponding to the target spinning machine, and input it into the corresponding production parameter optimization model to obtain the corresponding model output result; the model output result is the optimal data after optimizing the target spinning operation data; Feed back the obtained model output result to the control terminal of the corresponding spinning machine; furthermore, the control terminal adjusts the spinning operation parameters of the corresponding spinning machine based on the model output result until the actual operation parameters are the same as the model output result; Taking the front roller speed of the spinning machine as an example, the control terminal obtains the corresponding optimal front roller speed based on the model output result; The control terminal generates a corresponding control signal and adjusts the front roller speed based on the control signal; at the same time, the real-time speed of the front roller of the current spinning machine is collected in real time, and the deviation is calculated with the optimal front roller speed to obtain the corresponding deviation value, and the corresponding control signal is adjusted based on the deviation value until the real-time speed of the front roller meets the model output result; at the same time, the control terminal obtains the correlation between the corresponding front roller speed and other operation parameters, and based on the correlation, and in combination with the optimal front roller speed, makes proportional parameter adjustments to other operation parameters.

[0022] In the present invention, from data collection, data processing, construction of a multi-objective optimization function, construction of a production parameter optimization model to parameter control, each step is closely linked, which can realize the intelligent control of the front roller speed of the spinning machine, improve the production efficiency and product quality of the spinning machine; and has a broad application prospect, which is of great significance for the intelligent transformation and upgrading of the textile industry.

[0023] Embodiment 2 Please refer to Figure 2 As shown, for the parts not described in detail in this embodiment, refer to the description content of Embodiment 1. Provide an intelligent control system for the front roller speed of a spinning machine, including: A data collection module for collecting data on the production process of the target spinning machine, obtaining the corresponding spinning machine information and storing it; the spinning machine information includes operation data and production data; A data processing module for processing the obtained spinning machine information and constructing a corresponding multi-objective optimization function based on the data processing result; A data regulation module for constructing a corresponding production parameter optimization model based on the obtained target optimization function; and controlling the parameters of the target spinning machine in combination with the production parameter optimization model; Each module is connected by wired and / or wireless means to realize data transmission between modules.

[0024] Embodiment 3 This embodiment discloses an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the operation mode of the above-provided intelligent control system and method for the front roller speed of a flyer frame.

[0025] Since the electronic device introduced in this embodiment is the electronic device adopted for implementing an intelligent control system and method for the front roller speed of a flyer frame in an embodiment of the present application, based on the intelligent control system and method for the front roller speed of a flyer frame introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation manner and various variation forms of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device adopted for an intelligent control system and method for the front roller speed of a flyer frame in the embodiment of the present application, it falls within the scope of protection of the present application.

[0026] The above formulas are all calculated by taking the numerical values after dimensionless. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and threshold selection in the formula are set by those skilled in the art according to the actual situation.

[0027] The above is only the preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. Any technical solution within the idea of the present invention belongs to the protection scope of the present invention. It should be noted that for ordinary technical users in the technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. A method for intelligently controlling the rotation speed of the front roller of a spinning frame, characterized in that: include: Step 1: Collect data on the production process of the target spinning frame, obtain and store corresponding spinning frame information; the spinning frame information includes operation data and production data; Step 2: Process the obtained spinning frame information and construct a corresponding multi-objective optimization function based on the data processing results; Step three: construct a corresponding production parameter tuning model based on the obtained target optimization function; and perform parameter control on the target spinning frame in combination with the production parameter tuning model.

2. The method for intelligently controlling the rotation speed of the front roller of a spinning frame according to claim 1 is characterized in that: The process of collecting data from the production process of the target spinning frame, obtaining corresponding spinning frame information and storing it includes: Setting a data collection node, collecting relevant data in the production process of the corresponding spinning frame based on the data collection node, and obtaining corresponding spinning frame information; the spinning frame information includes spinning operation data, spinning energy consumption data and spinning production data; The collected spinning frame information is subjected to data preprocessing; after the data preprocessing is completed, the spinning frame information after the data preprocessing is stored in a pre-built information database; wherein the information database also stores corresponding spinning transaction information.

3. The method for intelligently controlling the rotation speed of the front roller of a spinning frame according to claim 2 is characterized in that: The process of data processing the obtained spinning frame information includes: A two-dimensional rectangular coordinate system is constructed with time as the horizontal axis and spinning frame information as the vertical axis, and the obtained rectangular coordinate system is mapped into a corresponding two-dimensional rectangular coordinate system to obtain a corresponding spinning change curve; the spinning change curve includes a spinning operation data curve, a spinning energy consumption data curve and a spinning production data curve; The obtained spinning operation data curve, spinning energy consumption data curve and production data curve are sampled respectively, and corresponding operation matrix, energy consumption matrix and production matrix are constructed based on the obtained spinning operation data curve, energy consumption data curve and production data curve; Normalize the obtained energy consumption matrix and operation matrix respectively, and extract components of the normalized energy consumption matrix and operation matrix based on the principal component analysis algorithm to obtain corresponding feature pairs; By randomly sampling the spinning operation data curve and the spinning energy consumption data curve to update the operation matrix and the feature matrix, and repeating the feature pair extraction process to obtain a plurality of feature pairs; constructing a corresponding first feature space matrix based on the feature pairs; Based on the method for obtaining the first characteristic space matrix, a second characteristic space matrix corresponding to the corresponding spinning operation data and the corresponding spinning output data is obtained; Acquire the collected spinning transaction information, and build a corresponding spinning profit curve based on it, and perform data fitting on the corresponding spinning profit curve and the spinning operation curve based on the collection time to obtain a corresponding operation-profit fitting curve; A corresponding multi-objective optimization function is constructed based on the operation-profit fitting curve, the first characteristic space matrix and the second characteristic space matrix.

4. The method for intelligently controlling the rotation speed of the front roller of a spinning frame according to claim 3 is characterized in that: The formula for obtaining feature pairs is: ; In the formula, and Respectively represent the feature u within the a-th feature pair a and v a The corresponding eigenvector; ρ a Represents the unit eigenvector corresponding to the matrix TM when the a-th feature pair is extracted; represents the feature v within the a-th feature pair a The corresponding weight vector; ; In the formula, A and B represent the energy consumption matrix and the operation matrix respectively; θ represents the maximum eigenvalue corresponding to the matrix TM; where TM=A T BB T A; Multi-objective optimization function ; G(E1) and G(E2) refer to the linear functions defined by the corresponding first feature space matrix and the second feature space matrix respectively; F(b) is the defining linear function of the corresponding operation-profit fitting curve; E1, E2 and b respectively represent the functional independent variables of the linear functions defined by the corresponding first feature space matrix, the second feature space matrix and the operation-profit fitting curve.

5. The method for intelligently controlling the rotation speed of the front roller of a spinning frame according to claim 3 is characterized in that: The process of building a corresponding production parameter tuning model based on the obtained target optimization function includes: The network framework of the production parameter tuning model is defined as an improved convolutional neural network; the basic architecture of the improved convolutional neural network is an input layer, a multi-scale convolutional layer and an output layer; The output layer is used to receive input training samples and convert the corresponding training samples into a one-dimensional data vector; The multi-scale convolution layer is composed of a convolution layer and a pooling layer, and a plurality of multi-scale convolution layers are provided in the corresponding improved convolutional neural network; the convolution layer is used to perform a convolution operation on the one-dimensional data vector output by the input layer to obtain the output features corresponding to the corresponding convolution layer; the pooling layer is used to perform a pooling operation on the output features of the convolution layer; A fully connected layer is provided in the output layer, and the fully connected layer is used to map the output features learned by the improved convolutional neural network to the corresponding sample space, and the output layer outputs the results; Defining the loss function ;in, The total number of training samples input to the production parameter tuning model. z is the index variable used to traverse all training samples. Produce the output of the parameter tuning model for the zth training sample, where Y(z) is the label of the zth training sample; Based on the multi-objective optimization function, the weights in each layer of the improved convolutional neural network are initialized and set, and the initialization setting is completed; based on the historical spinning frame information, a corresponding training data set is constructed, and the training samples in the training data set are divided into several training batches, and based on it, the corresponding production parameter tuning model is iteratively trained, and the value of the corresponding loss function is recorded. When the loss function in several consecutive training batches no longer decreases or changes, the model parameters at this time are saved, and the construction process of the corresponding production parameter tuning model is completed.

6. The method for intelligently controlling the rotation speed of the front roller of a spinning frame according to claim 5, characterized in that: The formula defining the convolution operation is: ; In the formula, Indicates The j-th output feature of the convolutional layer in the multi-scale convolutional layer; represents the j-th output feature of the previous convolutional layer in the multi-scale convolutional layer; M j Indicates The total number of output results of the previous convolution layer in a multi-scale convolution layer; Indicates The weight matrix of the convolution kernel in the convolution layer; Represents the bias term of the convolutional layer; represents the convolution operation, and f() represents the selected activation function; The formula that defines the pooling operation is: ; In the formula, Indicates The downsampling parameter of the i-th output feature in the pooling layer in the multi-scale convolutional layer, H() represents the downsampling function; Represents the bias term of the pooling layer; Indicates The i-th output feature of the pooling layer in the multi-scale convolutional layer; , i and j are all natural numbers, representing the layer indexes of the multi-scale convolutional layer and the pooling layer and convolution layer within the multi-scale convolutional layer, respectively.

7. The method for intelligently controlling the rotation speed of the front roller of a spinning frame according to claim 5, characterized in that: The process of initializing the weights in each layer of the improved convolutional neural network includes: Obtain the mean square error of the network performance function in the corresponding improved convolutional neural network, and construct the corresponding fitness function in combination with the obtained multi-objective optimization function ; In the formula, MSE represents the mean square error of the network performance function, and Function weights representing multi-objective optimization functions and mean square error; At the same time, a particle swarm set is initialized based on the learning mode of the improved convolutional neural network, and the number of particles and the spatial dimension corresponding to the corresponding particle swarm set are defined; Obtaining the initial velocity and initial position of each particle in the corresponding particle group, marking them as Sp and Wp respectively; obtaining the fitness value corresponding to the corresponding particle based on the fitness function, and updating the initial position and initial velocity of the corresponding particle based on the fitness value; Based on the fitness function, the initial position and initial velocity of each particle in the corresponding particle group are continuously updated until a preset iteration stop condition is met, thereby obtaining the corresponding global optimal solution; the obtained global optimal solution is mapped to the corresponding improved convolutional neural network, and then a new fitness value is obtained through the positive feedback output of the improved convolutional neural network, and the weights of the improved convolutional neural network are updated based on the new fitness value.

8. The method for intelligently controlling the rotation speed of the front roller of a spinning frame according to claim 7, characterized in that: The update formula that defines the initial position is: ; In the formula, represents the particle position of particle p at the k+1th iteration; represents the particle velocity of particle p at the kth iteration; and They represent the individual optimal solution and the global optimal solution at the kth iteration respectively; r1 and r2 are constants, and both r1 and r2 are ∈ [0,1]; ω represents the adaptive inertia weight; ; In the formula, ω max and ω min Respectively represent the maximum and minimum values ​​of the preset inertia weight; k and k max Respectively represent the current number of iterations and the maximum number of iterations; α and ε represent the speed coefficients, which are fixed constants; c1 and c2 represent learning factors; where ; In the formula, c10, c20 and c12, c22 represent the initial and final values ​​of learning factors c1 and c2 respectively.

9. The method for intelligently controlling the rotation speed of the front roller of a spinning frame according to claim 7, characterized in that: The process of controlling the parameters of the target spinning frame in combination with the production parameter tuning model includes: Based on the information database, real-time spinning frame information corresponding to the target spinning frame is obtained, and the information is input into the corresponding production parameter tuning model to obtain the corresponding model output result; the model output result is the best data after optimizing the target spinning operation data; The obtained model output result is fed back to the control terminal of the corresponding spinning frame; the control terminal adjusts the spinning operation parameters of the corresponding spinning frame based on the model output result until the actual operation parameters are the same as the model output result.

10. A spinning frame front roller speed intelligent control system, which is used to implement a spinning frame front roller speed intelligent control method according to any one of claims 1 to 9, comprising: A data acquisition module is used to collect data on the production process of the target spinning frame, obtain corresponding spinning frame information and store it; The spinning frame information includes operation data and production data; A data processing module is used to process the obtained spinning frame information and construct a corresponding multi-objective optimization function based on the data processing results; The data control module is used to construct a corresponding production parameter tuning model based on the obtained target optimization function; and to control the parameters of the target spinning frame in combination with the production parameter tuning model.

Images