A wrinkle-free treatment system and method for suit fabrics

Abstract

This invention relates to the field of textile industrial automation technology, specifically disclosing a wrinkle-free treatment adjustment system and method for suit fabrics. The system includes: a data acquisition module for real-time acquisition of key parameters during fabric processing; an adaptive decision-making module for receiving data from the data acquisition module and dynamically optimizing process parameters by combining fuzzy logic rule reasoning with the autonomous learning capability of neural networks; and an execution control module for precisely executing instructions generated by the adaptive decision-making module. This wrinkle-free treatment adjustment system and method for suit fabrics, based on fuzzy neural networks and dynamic rule base optimization technology, achieves coordinated optimization control of multiple parameters such as humidity, temperature, pressure, and smoothness. Compared with single-parameter control, it effectively solves the limitations of single-parameter control, comprehensively considers the influence of multiple factors on the wrinkle-free treatment effect, improves the comprehensiveness and accuracy of control, and realizes adaptive adjustment of wrinkle-free process parameters for suit fabrics.

Description

Technical Field

[0001] This invention relates to the field of automation technology in the textile industry, and in particular to a wrinkle-free treatment and adjustment system and method for suit fabrics. Background Technology

[0002] Traditional suit fabrics wrinkle easily after wearing and washing, greatly affecting aesthetics and comfort. Therefore, wrinkle-free finishing technology has emerged. Wrinkle-free finishing primarily uses physical or chemical methods to alter the fabric's fiber structure, making the fabric less prone to wrinkling during daily wear and washing, or allowing wrinkles to self-smooth out, providing consumers with a more convenient and aesthetically pleasing wearing experience. Wrinkle-free finishing relies on a dryer, a heat press, and a spray system. The dryer precisely controls temperature and time, allowing the fabric's fiber structure to be fixed under the action of a finishing liquid during drying, contributing to the wrinkle-free effect. The heat press uses pressure and heat to iron the fabric, shaping smoothness and crispness. The spray system is responsible for evenly spraying the wrinkle-free finishing liquid; the composition and amount of the finishing liquid directly affect the wrinkle-free effect.

[0003] Existing wrinkle-free treatment systems for suit fabrics have a single parameter control mode. Traditional processes rely on fixed parameters and do not consider dynamic factors such as fabric characteristics and changes in environmental temperature and humidity. For example, under high humidity, the liquid content of the fabric changes, and fixed parameters cannot adjust the drying and pressing parameters in time, resulting in substandard smoothness or even fiber damage. Furthermore, the feedback control capability is insufficient. Some existing technologies rely on feedback from a single sensor, such as using only a temperature sensor to control drying. They lack comprehensive consideration and coupling optimization of multiple parameters, making it difficult to fully reflect complex processing conditions and resulting in unstable processing effects.

[0004] Therefore, there is an urgent need for a newer technical approach, such as multi-parameter collaborative optimization algorithms and adaptive learning mechanisms, to improve the processing effect of wrinkle-free processes, reduce energy consumption, and enhance the adaptability and stability of the system. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the defects of the prior art. The present invention proposes a wrinkle-free treatment adjustment system and method for suit fabrics, which solves the problems of the prior art in the background art, which has a single parameter control mode for wrinkle-free treatment adjustment system for suit fabrics, relies on fixed parameters in traditional processes, and does not take into account dynamic factors such as fabric characteristics and changes in environmental temperature and humidity.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] A wrinkle-free conditioning system for suit fabrics, comprising:

[0008] The data acquisition module is used to collect key parameters in the fabric processing process in real time. The parameters include fabric liquid retention rate x1, drying temperature x2, pressing equipment pressure value x3, and fabric surface smoothness x4. The parameter set is X={x1,x2,x3,x4}.

[0009] The adaptive decision-making module uses a fuzzy neural network algorithm to map data into fuzzy linguistic variables, with fuzzy linguistic values ​​categorized as high, medium, and low. It defines IF-THEN rules based on expert experience and historical data, assigning weights w to these expert rules initially. k =1.0, using the Apriori algorithm to mine historical data, identify frequently occurring parameter combinations, and generate data-driven rules based on these combinations. The initial weights w of the data-driven rules are... k =0.8, and the rule weights w are dynamically adjusted using the backpropagation algorithm. k And the lower limit of the expert rule weight w k ≥0.5, and when a conflict rule is triggered, the weight is adjusted according to w. k :=w k • 0.9 decay, the final control parameters are calculated using the center of gravity method, including drying time T, pressure P, and finishing liquid spraying amount Q;

[0010] The execution control module is used to accurately execute the instructions generated by the adaptive decision-making module.

[0011] Preferably, the backpropagation algorithm is used to dynamically adjust the rule weights w. k When the objective function is the sum of squared control errors, the formula is as follows:

[0012] Where E is the control error, y d Let y represent the target flatness and y be the output value.

[0013] The formula for calculating the weight gradient is:

[0014]

[0015] Preferably, the execution control module includes an execution unit, the execution unit comprising:

[0016] The variable frequency dryer is used to adjust the temperature curve based on the drying time T calculated by the adaptive decision module.

[0017] Servo heat press machine achieves precise adjustment of P through pressure feedback closed-loop control;

[0018] Intelligent spraying system, dynamically adjusts the flow rate Q of the finishing liquid.

[0019] Preferably, the data acquisition module includes a sensor unit, which includes a humidity sensor for detecting the liquid content of the fabric, a temperature sensor for monitoring the drying temperature, a pressure sensor for measuring the pressure value of the ironing equipment, and an optical detection unit for analyzing the surface smoothness of the fabric through infrared spectroscopy.

[0020] Preferably, it also includes a data processing module for processing the data collected by the data acquisition module:

[0021] Outlier repair involves using a sliding window statistical method to remove data that exceeds the process range or deviates from the mean ±3σ.

[0022] Noise filtering is performed by smoothing the data using a first-order low-pass filter.

[0023] Normalization is performed by eliminating dimensional differences through Z-score standardization.

[0024] Preferably, it also includes an incremental learning module for generating new rules and eliminating existing rules;

[0025] New rule generation: When the rule matching degree S = max(μ) k When ) < 0.6, generate a new rule with initial weight w. k =0.6;

[0026] Rule elimination: Delete weight w k <0.2 or low trigger rule.

[0027] Preferably, in step S102, expert experience comes from expert interviews and process manuals, and historical data comes from historical process databases.

[0028] Preferably, it also includes a function self-test module, which is used to monitor the status of the sensor unit and the execution unit in real time, and trigger an alarm and switch to backup equipment when abnormality occurs.

[0029] Preferably, it also includes a quality traceability module, which is used to record the entire process of wrinkle-free treatment of each batch of suit fabric, including fabric source, treatment process parameters, equipment operation data, and operator information.

[0030] This application also includes an embodiment, specifically a method for adjusting wrinkle-free treatment of suit fabric. The wrinkle-free treatment system for suit fabric is implemented and includes the following steps:

[0031] S1: Utilizing humidity, temperature, pressure sensors and optical detection units, it accurately collects parameters such as fabric liquid retention, drying temperature, pressing pressure and smoothness.

[0032] S2: By using the Gaussian distribution membership function, the collected precise data is transformed into "high", "medium" and "low" fuzzy linguistic variables;

[0033] S3: Integrates expert experience and historical data to generate rules, uses the backpropagation algorithm to dynamically optimize weights, and calculates control parameters by combining the rule triggering strength and the centroid method.

[0034] S4: The variable frequency dryer adjusts the temperature curve according to the drying time, the servo heat press precisely adjusts the pressure through pressure closed-loop feedback, and the intelligent spray system dynamically regulates the flow of finishing liquid.

[0035] S5: Monitor the fabric effect after wrinkle-free treatment in real time, compare it with the target flatness and other indicators, and feed the deviation back to the decision module to continuously optimize the processing.

[0036] Compared with the prior art, the beneficial effects of the present invention include:

[0037] 1. Based on fuzzy neural network and dynamic rule base optimization technology, it realizes the coordinated optimization control of multiple parameters such as humidity, temperature, pressure, and smoothness. Compared with single parameter control, it effectively solves the limitations of single parameter control, can comprehensively consider the influence of multiple factors on the wrinkle-free treatment effect, improves the comprehensiveness and accuracy of control, and realizes the adaptive adjustment of wrinkle-free process parameters for suit fabrics. It is superior to existing technologies in terms of control accuracy, energy efficiency, and multi-material compatibility, and has significant industrial application value. It can not only improve the quality and efficiency of wrinkle-free treatment of suit fabrics, but also reduce production costs and adapt to the ever-evolving needs of the textile industry.

[0038] 2. By using the backpropagation algorithm, the rule weights are dynamically optimized based on the actual control error. At the same time, combined with the expert rule protection mechanism, the expert experience is not overwhelmed by data noise, and the conflict resolution mechanism, the rule conflict problem is effectively handled, which significantly improves the robustness and adaptability of the system. Attached Figure Description

[0039] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings, the same reference numerals are used to refer to the same parts. Wherein:

[0040] Figure 1 The schematic diagram illustrates a module flow chart of a wrinkle-free treatment and adjustment system for suit fabrics according to an embodiment of the present invention.

[0041] Figure 2 The illustration shows a flowchart of a wrinkle-free treatment and adjustment method for suit fabric according to an embodiment of the present invention. Detailed Implementation

[0042] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0043] According to one embodiment of the present invention, Figure 1 The diagram illustrates a wrinkle-free treatment system for suit fabrics, primarily comprising: a data acquisition module, an adaptive decision-making module, and an execution control module. The data acquisition module collects key parameters during the fabric processing in real time. The data acquisition module includes a sensor unit, comprising a humidity sensor for detecting fabric liquid retention, a temperature sensor for monitoring drying temperature and ambient temperature, a pressure sensor for measuring the pressure value of the pressing equipment, and an optical detection unit for analyzing fabric surface smoothness using infrared spectroscopy. Fabric liquid retention is represented by x1 (in %) with an accuracy of ±2%, drying temperature by x2 (in °C) with an accuracy of ±1.5 °C, pressing equipment pressure by x3 (in kPa) with an accuracy of ±5 kPa, and fabric surface smoothness by x4 (rating range 0-4 with an accuracy of ±0.2). The set of these parameters is X = {x1, x2, x3, x4}.

[0044] The adaptive decision-making module receives data from the data acquisition module and dynamically optimizes process parameters by combining fuzzy logic rule-based reasoning with the autonomous learning capability of neural networks. The specific algorithm steps include:

[0045] Step 1: Use a fuzzy neural network algorithm to map the data into fuzzy linguistic variables. The fuzzy linguistic values ​​are high, medium, and low. The membership function adopts a Gaussian distribution, and the specific formula is as follows:

[0046] Where c ij σ represents the central value of the j-th input variable under the i-th rule. This value can be defined by experts based on their extensive experience and professional knowledge, or it can be generated through cluster analysis of a large amount of historical data. It represents the typical value of this input variable under a certain fuzzy state; ij It is the standard deviation of the j-th input variable under the i-th rule, used to control the width of the fuzzy interval. The larger the standard deviation, the wider the fuzzy interval and the higher the degree of fuzzification of the input data. Conversely, the smaller the standard deviation, the narrower the fuzzy interval and the lower the degree of fuzzification.

[0047] Step 2: Rule base construction. Define IF-THEN rules based on expert experience and historical data. The rule format is "IF x1 is high AND x2 is medium THEN, drying time reduced by 15%". Expert rules are assigned weights w initially.k =1.0, indicating high accuracy and authority of expert rules. The Apriori algorithm is used to mine historical data, identifying frequently occurring parameter combinations and generating data-driven rules based on these combinations. The initial weight w of the data-driven rules... k =0.8, expert experience comes from expert interviews and process manuals, and historical data comes from historical process databases;

[0048] Step 3: Dynamically adjust the rule weights w using the backpropagation algorithm. k Its objective function is the sum of squared control errors, and the formula is as follows:

[0049] Where E is the control error, y d y represents the target flatness (set to ≥3.5 level) and the output value.

[0050] The formula for calculating the weight gradient is:

[0051] This formula is used to calculate the rule weight w. k The gradient of the objective function E with respect to the weights w k The derivative is used to determine the weight w. k The update direction and magnitude, where -(y d -y) represents the error between the target flatness and the actual flatness. This indicates that the system output y corresponds to the weight w. k The partial derivatives of the two are multiplied to obtain the weight w. k The gradient is used to guide the updating of weights;

[0052] To prevent data noise from interfering with expert rules, a lower limit w is set for the weight of expert rules. k ≥0.5 ensures the stability and reliability of prior knowledge in the rule base. When conflicting rules are triggered, such as when "increase pressure" and "decrease pressure" are triggered simultaneously, the weights are adjusted according to w. k :=w k • 0.9 decay, weakening the impact of conflict rules;

[0053] It also includes an incremental learning module, which is used for new rule generation and rule elimination. Specifically, when the matching degree S between a new working condition and the existing rule base is S = max(μ k When the weight w < 0.6, it indicates that the existing rules cannot adapt well to the new situation. In this case, the system automatically generates new rules and assigns them initial weights w. k =0.6. The generation of new rules enables the system to continuously learn and adapt to new working conditions and data. To maintain the simplicity and effectiveness of the rule base, the system will periodically delete weights w. kRules with a trigger count of <0.2 or too few times may no longer be suitable for current production conditions. Deleting them can improve the system's operating efficiency and decision-making accuracy.

[0054] Step 4: Calculate the final control parameters using the center of gravity method, including drying time T, pressure P, and finishing liquid spraying amount Q. Taking drying time T as an example, the calculation formula is:

[0055] Where T k The drying time suggested by the kth rule can be determined by taking into account the influence of all rules through this formula, resulting in a more reasonable drying time control value. The same applies to the pressure P and the amount of finishing liquid sprayed Q.

[0056] The execution control module is used to accurately execute the instructions generated by the adaptive decision module. The execution control module includes an execution unit, which includes a variable frequency dryer. The variable frequency dryer is preferably a Midea MH100VH36T or Haier Yunxi 37610kg variable frequency dual-engine heat pump dryer or a variable frequency heat pump dryer from the Panasonic White Moonlight 4.0 washer-dryer set. The variable frequency dryer can adjust the temperature curve according to the drying time T calculated by the adaptive decision module, and adopts a PID control algorithm to achieve a temperature error of ≤±2℃, ensuring the stability and consistency of the drying process.

[0057] Servo pressing machine, preferably the dye-2000a microcomputer servo pressure testing machine, achieves precise adjustment of P through pressure feedback closed-loop control, ensuring that the pressing pressure error is ≤±3kPa, thereby guaranteeing the pressing effect and quality of the fabric;

[0058] The intelligent spray system preferably adopts the ZSPM type intelligent end-point water testing device or the BT-SW-02 intelligent automatic atomizing spray deodorization equipment to dynamically adjust the finishing liquid flow rate Q, in mL / s, so that the flow rate error is ≤±5%, accurately controlling the amount of finishing liquid applied to meet the requirements of the non-ironing process.

[0059] Taking wool / polyester blended fabric as an example, the actual operating effect of the system is demonstrated:

[0060] The initial state rule base contains 20 expert rules (each rule has a weight w = 1.0) and 15 data rules (each rule has a weight w = 0.8). These rules form the basis for the system's initial decisions.

[0061] Abnormal operating condition: When the ambient humidity suddenly changes, the fabric liquid rate x1 = 92%, which exceeds the range originally covered by the rule base. Since the liquid rate is outside the normal range, the system triggers the incremental learning mechanism to generate a new rule "IFx1 > 90% THEN spray volume reduced by 10%", and assigns the rule an initial weight w = 0.6.

[0062] After three training sessions under the same working conditions, the system continuously optimized the rule weights, which were increased to w=0.75. During this process, the fabric smoothness improved from the initial level 3.1 to level 3.7, meeting the target smoothness requirements and fully demonstrating the system's adaptive capability and optimization effect.

[0063] This solution also includes a data processing module, which processes the data collected by the data acquisition module. Specifically, it includes outlier repair by removing data that exceeds the process range or deviates from the mean ±3σ using a sliding window statistical method; noise filtering by smoothing the data using a first-order low-pass filter; and normalization by eliminating dimensional differences through Z-score standardization.

[0064] It also includes a self-testing module, which is used to monitor the status of sensor units and execution units in real time, triggering alarms and switching to backup equipment when abnormalities occur.

[0065] It also includes a quality traceability module, which records the entire process of wrinkle-free treatment of each batch of suit fabric, including fabric source, processing parameters, equipment operation data, and operator information. When quality problems occur, it can quickly trace the link and cause of the problem so that targeted improvement measures can be taken. It also helps to control and optimize the production process.

[0066] This application also includes an embodiment, which combines the present invention with... Figure 2 The illustration shows a method for adjusting wrinkle-free treatment of suit fabric. The implementation of the aforementioned wrinkle-free treatment system for suit fabric includes the following steps:

[0067] Step 1: Using humidity, temperature, pressure sensors and optical detection units, accurately collect parameters such as fabric liquid retention rate, drying temperature, pressing pressure and smoothness.

[0068] Step 2: Transform the collected precise data into "high", "medium", and "low" fuzzy linguistic variables using a Gaussian membership function;

[0069] Step 3: Integrate expert experience and historical data to generate rules, use the backpropagation algorithm to dynamically optimize weights, and combine the rule triggering strength to calculate control parameters using the centroid method;

[0070] Step 4: The variable frequency dryer adjusts the temperature curve according to the drying time, the servo heat press precisely adjusts the pressure through pressure closed-loop feedback, and the intelligent spray system dynamically regulates the flow rate of the finishing liquid.

[0071] Step 5: Monitor the fabric effect after wrinkle-free treatment in real time, compare it with the target flatness and other indicators, and feed the deviation back to the decision module to continuously optimize the processing.

[0072] The technical scope of this invention is not limited to the content described above. Those skilled in the art can make various modifications and variations to the above embodiments without departing from the technical concept of this invention, and all such modifications and variations should fall within the protection scope of this invention.

Claims

1. A wrinkle-free conditioning system for suit fabrics, characterized in that, include: The data acquisition module is used to collect key parameters in the fabric processing process in real time. The parameters include fabric liquid retention rate x1, drying temperature x2, pressing equipment pressure value x3, and fabric surface smoothness x4. The parameter set is X={x1,x2,x3,x4}. The adaptive decision-making module uses a fuzzy neural network algorithm to map data into fuzzy linguistic variables, with fuzzy linguistic values ​​categorized as high, medium, and low. It defines IF-THEN rules based on expert experience and historical data, assigning weights w to these expert rules initially. k =1.0, using the Apriori algorithm to mine historical data, identify frequently occurring parameter combinations, and generate data-driven rules based on these combinations. The initial weights w of the data-driven rules are... k =0.8, and the rule weights w are dynamically adjusted using the backpropagation algorithm. k And the lower limit of the expert rule weight w k ≥0.5, and when a conflict rule is triggered, the weight is adjusted according to w. k :=w k • 0.9 decay, the final control parameters are calculated using the center of gravity method, including drying time T, pressure P, and finishing liquid spraying amount Q; The execution control module is used to accurately execute the instructions generated by the adaptive decision-making module; The backpropagation algorithm is used to dynamically adjust the rule weights w. k When the objective function is the squared control error, the formula is as follows: Where E is the control error, y d y represents the target flatness, and y represents the actual flatness.

2. The wrinkle-free treatment and adjustment system for suit fabrics according to claim 1, characterized in that: The formula for calculating the weight gradient is:

3. The wrinkle-free treatment and adjustment system for suit fabrics according to claim 1, characterized in that: The execution control module includes an execution unit, which includes: The variable frequency dryer is used to adjust the temperature curve based on the drying time T calculated by the adaptive decision module. Servo heat press machine achieves precise adjustment of P through pressure feedback closed-loop control; Intelligent spraying system, dynamically adjusts the amount of finishing liquid sprayed (Q).

4. The wrinkle-free treatment and adjustment system for suit fabric according to claim 3, characterized in that: The data acquisition module includes a sensor unit, which includes a humidity sensor for detecting the liquid content of the fabric, a temperature sensor for monitoring the drying temperature, a pressure sensor for measuring the pressure value of the ironing equipment, and an optical detection unit for analyzing the surface smoothness of the fabric through infrared spectroscopy.

5. The wrinkle-free treatment and adjustment system for suit fabric according to claim 1, characterized in that: It also includes a data processing module, which processes the data collected by the data acquisition module: Outlier repair involves using a sliding window statistical method to remove data that exceeds the process range or deviates from the mean ±3σ. Noise filtering is performed by smoothing the data using a first-order low-pass filter. Normalization is performed by eliminating dimensional differences through Z-score standardization.

6. The wrinkle-free treatment and adjustment system for suit fabric according to claim 1, characterized in that: It also includes an incremental learning module for generating new rules and eliminating existing rules; New rule generation: When the rule matching degree S = max(μ) k When ) < 0.6, generate a new rule with initial weight w. k =0.6; where, μ k Let k be the trigger strength of the k-th rule; Rule elimination: Delete weight w k <0.2 or low trigger rule.

7. The wrinkle-free treatment and adjustment system for suit fabrics according to claim 1, characterized in that: In the wrinkle-free treatment system for suit fabrics, historical data comes from a historical process database.

8. The wrinkle-free treatment and adjustment system for suit fabrics according to claim 4, characterized in that: It also includes a self-testing module for real-time monitoring of the status of sensor units and execution units, triggering alarms and switching to backup equipment when abnormalities occur.

9. The wrinkle-free treatment and adjustment system for suit fabric according to claim 1, characterized in that: It also includes a quality traceability module, which records the entire process of wrinkle-free treatment for each batch of suit fabric, including fabric source, treatment parameters, equipment operation data, and operator information.

10. A method for adjusting wrinkle-free treatment of suit fabric, implemented using the wrinkle-free treatment system for suit fabric as described in any one of claims 1-9, characterized in that, Includes the following steps: S1: Utilizing humidity, temperature, pressure sensors and optical detection units, it accurately collects data on fabric liquid retention, drying temperature, pressing equipment pressure, and fabric surface smoothness. S2: By using the Gaussian distribution membership function, the collected precise data is transformed into "high", "medium", and "low" fuzzy linguistic variables; S3: Integrates expert experience and historical data to generate rules, uses the backpropagation algorithm to dynamically optimize weights, and calculates control parameters by combining the rule triggering strength and the centroid method. S4: The variable frequency dryer adjusts the temperature curve according to the drying time, the servo heat press precisely adjusts the pressure through pressure closed-loop feedback, and the intelligent spraying system dynamically controls the amount of finishing liquid sprayed. S5: Monitor the fabric effect after wrinkle-free treatment in real time, compare it with the target flatness index, and feed the deviation back to the decision module to continuously optimize the processing.

Images