Western-style clothes fabric non-ironing treatment adjusting system and method

Abstract

The invention relates to the technical field of textile industry automation, and particularly discloses a suit fabric non-ironing treatment adjusting system and method.The suit fabric non-ironing treatment adjusting system comprises a data acquisition module used for acquiring key parameters in the fabric treatment process in real time; the adaptive decision module is used for receiving the data from the data acquisition module and dynamically optimizing process parameters by combining rule reasoning of fuzzy logic and the autonomous learning ability of a neural network; and the execution control module is used for precisely executing the instruction generated by the self-adaptive decision module. According to the western-style clothes fabric non-ironing processing adjusting system and method, collaborative optimization control over multiple parameters such as humidity, temperature, pressure and flatness is achieved based on the fuzzy neural network and dynamic rule base optimization technology, and compared with single-parameter control, the limitation of single-parameter control is effectively solved; the influence of multiple factors on the non-ironing treatment effect can be comprehensively considered, the comprehensiveness and accuracy of control are improved, and self-adaptive adjustment of the non-ironing process parameters of the suit fabric is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of textile industry automation, and in particular to a system and method for adjusting the non-ironing treatment of suit fabrics. Background Art

[0002] Traditional suit fabrics are prone to wrinkles after wearing and washing, which greatly affects the appearance and comfort, so the non-ironing treatment technology came into being. Non-ironing treatment mainly uses physical or chemical means to change the fiber structure of the fabric, so that the fabric is not easy to wrinkle during daily wear and washing, or the wrinkles can be restored to flatness by themselves, bringing consumers a more convenient and beautiful wearing experience. Non-ironing treatment is inseparable from the dryer, press and spray system. The dryer precisely controls the temperature and time so that the fiber structure of the fabric is fixed under the action of the finishing liquid when it is drying, helping to achieve the non-ironing effect; the press uses pressure and heat to iron the fabric to shape the flatness and stiffness; the spray system is responsible for evenly spraying the non-ironing finishing liquid, and the composition and spraying amount of the finishing liquid are directly related to the non-ironing effect.

[0003] The existing parameter control mode of the ironing-free treatment adjustment system for suit fabrics is single. The traditional process relies on fixed parameters and does not consider dynamic factors such as fabric characteristics and changes in ambient temperature and humidity. For example, under high humidity, the liquid carryover rate of the fabric changes, but the fixed parameters cannot adjust the drying and pressing parameters in time, resulting in substandard flatness or even fiber damage, and insufficient feedback control capabilities. Some existing technologies rely only on single sensor feedback, such as using only temperature sensors to control drying. They lack comprehensive consideration and coupling optimization of multiple parameters, and it is difficult to fully reflect the complex processing status, resulting in unstable processing effects.

[0004] Therefore, a more innovative technical means is urgently needed, such as multi-parameter collaborative optimization algorithm and adaptive learning mechanism, to improve the processing effect of the wrinkle-free process, 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 system and method for adjusting the free-ironing treatment of suit fabrics, which solves the problem that the prior art in the background technology is that the parameter control mode of the free-ironing treatment adjustment system for suit fabrics is single, the traditional process relies on fixed parameters, and does not consider dynamic factors such as fabric characteristics and changes in ambient temperature and humidity.

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

[0007] A non-ironing treatment and adjustment system for suit fabrics, comprising:

[0008] Data acquisition module, used to collect key parameters in the fabric processing process in real time, including fabric liquid carrying rate x 1 , drying temperature x 2, Pressing equipment pressure value x 3 , fabric surface flatness x 4 , the parameter set is X = {x 1 ,x 2 ,x 3 ,x 4};

[0009] Adaptive decision module,Adaptive decision module,Uses fuzzy neural network algorithm to map data into fuzzy language variables,Fuzzy language values ​​are high, medium, and low,Define IF-THEN rules based on expert experience and historical data,Expert rules are initially assigned weights w k = 1.0, using the Apriori algorithm to mine historical data, find out the high-frequency parameter combinations, and generate data-driven rules based on them. The initial weight of the data-driven rules is w k =0.8, using the back propagation algorithm to dynamically adjust the rule weight w k , and the lower limit of expert rule weight w k ≥0.5, and when the conflict rule is triggered, the weight is w k :=w k 0.9 attenuation, using the center of gravity method to calculate the final control parameters, 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 module.

[0011] Preferably, the back propagation algorithm is used to dynamically adjust the rule weight w k When , its objective function is the sum of squares of control errors, and the formula is as follows:

[0012] Where E is the control error, y d is the target flatness, y is the output value;

[0013] The weight gradient calculation formula is:

[0014] The system output y is calculated by the weighted rule trigger strength, and the formula is:

[0015] where μ k is the trigger strength of the kth rule, B k is the control amount corresponding to the kth rule, including drying time adjustment amount and pressure adjustment amount.

[0016] Preferably, the execution control module includes an execution unit, and the execution unit includes:

[0017] A variable frequency dryer is used to adjust the temperature curve according to the drying time T calculated by the adaptive decision module;

[0018] Servo pressing machine, through pressure feedback closed loop control, to achieve precise adjustment of P;

[0019] Intelligent spraying system dynamically adjusts the finishing liquid flow Q.

[0020] 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 pressing equipment, and an optical detection unit for analyzing the surface flatness of the fabric through infrared spectroscopy.

[0021] Preferably, it also includes a data processing module for processing the data collected by the data collection module:

[0022] Outlier repair: data that exceeds the process range or deviates from the mean ±3σ is eliminated through the sliding window statistical method;

[0023] Noise filtering, smoothing the data through a first-order low-pass filter;

[0024] Normalization processing eliminates dimensional differences through Z-score standardization.

[0025] Preferably, it also includes an incremental learning module for generating new rules and eliminating rules;

[0026] New rule generation: When the rule matching degree S = max(μ k )<0.6, generate new rules with initial weight w k =0.6;

[0027] Rule elimination: delete weight w k <0.2 or low triggers the rule.

[0028] Preferably, in step S102, expert experience comes from expert interviews and process manuals, and historical data comes from a historical process database.

[0029] Preferably, it also includes a functional self-check module for real-time monitoring of the status of the sensor unit and the execution unit, triggering an alarm and switching to a backup device when an abnormality occurs.

[0030] Preferably, a quality traceability module is also included, which is used to record the entire process of the wrinkle-free treatment of each batch of suit fabrics, including the source of the fabrics, treatment process parameters, equipment operation data, and operator information.

[0031] The present application also includes an embodiment, specifically a method for adjusting the non-ironing treatment of suit fabrics, and a system for adjusting the non-ironing treatment of suit fabrics, comprising the following steps:

[0032] S1: Use humidity, temperature, pressure sensors and optical detection units to accurately collect fabric liquid rate, drying temperature, pressing pressure and flatness parameters;

[0033] S2: The collected precise data is converted into fuzzy linguistic variables of “high”, “medium” and “low” through the Gaussian distribution membership function;

[0034] S3: Integrate expert experience and historical data to generate rules, use the back propagation algorithm to dynamically optimize weights, combine the rule trigger strength, and calculate the control parameters using the center of gravity method;

[0035] S4: The variable frequency dryer adjusts the temperature curve according to the drying time, the servo press accurately adjusts the pressure through pressure closed loop feedback, and the intelligent spray system dynamically controls the flow of finishing liquid;

[0036] S5: Real-time monitoring of the fabric effect after wrinkle-free treatment, comparison with target flatness and other indicators, feedback of deviations to the decision-making module, and continuous optimization of the processing process.

[0037] Compared with the prior art, the beneficial effects of the present invention include:

[0038] 1. Based on fuzzy neural network and dynamic rule base optimization technology, the coordinated optimization control of multiple parameters such as humidity, temperature, pressure, flatness, etc. is realized. Compared with single parameter control, it effectively solves the limitations of single parameter control, can comprehensively consider the influence of multiple factors on the effect of free-ironing treatment, improves the comprehensiveness and accuracy of control, and realizes the adaptive adjustment of free-ironing process parameters of suit fabrics. It is superior to the existing technology in terms of control accuracy, energy efficiency and multi-material adaptability, and has significant industrial application value. It can not only improve the quality and efficiency of free-ironing treatment of suit fabrics, but also reduce production costs and adapt to the needs of the ever-changing textile industry.

[0039] 2. Through the back propagation algorithm, the rule weights are dynamically optimized according to the actual control error. At the same time, combined with the expert rule protection mechanism, it ensures that the expert experience is not overwhelmed by data noise, and the conflict resolution mechanism effectively handles the rule conflict problem, which significantly improves the robustness and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The disclosure of the present invention is described 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 the present invention. In the accompanying drawings, the same reference numerals are used to refer to the same components. Among them:

[0041] Figure 1 Schematically showing a module flow diagram of a system for adjusting the non-ironing treatment of suit fabrics according to one embodiment of the present invention;

[0042] Figure 2The present invention schematically shows a flow chart of a method for adjusting the wrinkle-free treatment of suit fabrics according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] It is easy to understand that according to the technical solution of the present invention, without changing the essential spirit of the present invention, a person skilled in the art can propose a variety of interchangeable structural modes and implementation modes. Therefore, the following specific implementation modes and drawings are only exemplary descriptions of the technical solution of the present invention, and should not be regarded as the whole of the present invention or as a limitation or restriction to the technical solution of the present invention.

[0044] According to one embodiment of the present invention, Figure 1 The invention shows a system for adjusting the free-ironing treatment of suit fabrics, which mainly includes: a data acquisition module, an adaptive decision module, and an execution control module, wherein the data acquisition module is used to collect key parameters in the fabric processing process in real time, and the data acquisition module includes a sensor unit, which includes a humidity sensor for detecting the liquid carrying rate of the fabric, a temperature sensor for monitoring the drying temperature and the ambient temperature, a pressure sensor for measuring the pressure value of the pressing device, and an optical detection unit for analyzing the surface flatness of the fabric through infrared spectroscopy. The liquid carrying rate of the fabric is measured by x 1 The unit is %, and the accuracy can reach ±2%. The drying temperature is expressed by x 2 Indicated by unit ℃, accuracy ±1.5℃, the pressure value of the pressing equipment is measured by x 3 Indicated in kPa, with an accuracy of ±5kPa, the surface smoothness of the fabric is measured by x 4 Indicates that the rating range is 0-4, the accuracy is ±0.2, and the above parameter set is X={x 1 ,x 2 ,x 3 ,x 4};

[0045] The adaptive decision module is used to receive data from the data acquisition module, combine the rule reasoning of fuzzy logic with the autonomous learning ability of neural network, and dynamically optimize the process parameters. The specific algorithm steps include:

[0046] Step 1: Use the fuzzy neural network algorithm to map the data into fuzzy language variables. The fuzzy language values ​​are high, medium, and low. The membership function uses Gaussian distribution. The specific formula is:

[0047] where c ij It represents the central value of the jth input variable under the i-th rule. This value can be defined by experts based on their rich experience and professional knowledge, or generated by clustering analysis of a large amount of historical data. It represents the typical value of the input variable under a certain fuzzy state; σ ijIt is the standard deviation of the jth input variable under the i-th rule, which is 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. On the contrary, the smaller the standard deviation, the narrower the fuzzy interval and the lower the degree of fuzzification.

[0048] Step 2: Build a rule base, define IF-THEN rules based on expert experience and historical data, and the rule format is "IFx 1 For high ANDx 2 For the drying time of THEN to be reduced by 15%, the expert rule initially assigns a weight of w k =1.0, the accuracy and authority of expert rules are high. The Apriori algorithm is used to mine historical data to find the high-frequency parameter combinations and generate data-driven rules based on them. The initial weight of the data-driven rules is w k =0.8, expert experience comes from expert interviews and process manuals, and historical data comes from historical process databases;

[0049] Step 3: Use the back propagation algorithm to dynamically adjust the rule weight w k , its objective function is the sum of squares of control errors, and the formula is as follows:

[0050] Where E is the control error, y d is the target flatness (set to ≥ level 3.5), and y is the output value;

[0051] The weight gradient calculation formula is:

[0052] This formula is used to calculate the rule weight w k The gradient of the objective function E with respect to the weight w k The derivative number, through this partial derivative to determine the weight w k The update direction and amplitude of -(y d -y) represents the error between the target flatness and the actual flatness, Represents the system output y to weight w k The partial derivative of , multiplying the two together gives the weight w k The gradient of is used to guide the update of weights. The system output y is calculated by the weighted rule triggering strength, and the formula is:

[0053] Where M represents the total number of rules, w k is the weight of the kth rule, μ k is the trigger strength of the kth rule, which reflects the degree to which the kth rule is activated under the current input conditions. kis the control amount corresponding to the kth rule, including drying time adjustment amount, pressure adjustment amount, etc., which is determined according to different rules and process requirements;

[0054] In order to prevent data noise from interfering with expert rules, the lower limit of expert rule weight w is set k ≥0.5, to ensure the stability and reliability of prior knowledge in the rule base. When conflicting rules are triggered, such as when "increase pressure" and "reduce pressure" are triggered at the same time, the weight is adjusted by w k :=w k 0.9 attenuation, weakening the impact of conflicting rules;

[0055] It also includes an incremental learning module, which is used for new rule generation and rule elimination. Specifically, when the matching degree S=max(μ k )<0.6, it indicates that the existing rules cannot adapt well to the new situation. At this time, the system automatically generates new rules and assigns them an initial weight w k =0.6. The generation of new rules enables the system to continuously learn and adapt to new working conditions and data. In order to maintain the simplicity and effectiveness of the rule base, the system will periodically delete the weight w. k Rules with a trigger rate of < 0.2 or too few trigger times may no longer be applicable to the current production situation. Deleting them can improve the system's operating efficiency and decision-making accuracy.

[0056] Step 4: Use the center of gravity method to calculate the final control parameters, including drying time T, pressure P, and finishing liquid spraying amount Q. Taking drying time T as an example, the calculation formula is:

[0057] Where T k is the drying time recommended by the kth rule. Through this formula, the influence of all rules can be comprehensively considered to obtain a more reasonable drying time control value. The same is true for pressure P and finishing liquid spraying amount Q.

[0058] An 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 preferably adopts Midea MH100VH36T or Haier Yunxi 37610kg variable frequency dual-engine heat pump dryer or the variable frequency heat pump dryer in Panasonic Baiyueguang 4.0 washing and drying set. The variable frequency dryer can adjust the temperature curve according to the drying time T calculated by the adaptive decision module, and adopt the PID control algorithm to achieve a temperature error of ≤±2°C, thereby ensuring the stability and consistency of the drying process;

[0059] Servo pressing machine, the servo pressing machine is preferably a dye-2000a microcomputer servo pressure testing machine, which can achieve precise adjustment of P through pressure feedback closed-loop control to ensure that the pressing pressure error is ≤±3kPa, thereby ensuring the pressing effect and quality of the fabric;

[0060] Intelligent spray system: The intelligent spray system preferably adopts ZSPM intelligent terminal water testing device or BT-SW-02 intelligent automatic atomizing spray deodorization equipment to dynamically adjust the finishing liquid flow Q, unit mL / s, so that the flow error is ≤±5%, and accurately control the application amount of finishing liquid to meet the requirements of the non-ironing treatment process.

[0061] Take wool / polyester blended fabric as an example to show the actual operation effect of the system:

[0062] The initial state rule base contains 20 expert rules (each rule weight w = 1.0) and 15 data rules (weight w = 0.8), which form the basis of the system's initial decision;

[0063] Abnormal working conditions: When the ambient humidity changes suddenly, the fabric liquid rate x 1 = 92%, which is beyond the scope of the rule base. Since the liquid carrying rate exceeds the normal range, the system triggers the incremental learning mechanism and generates a new rule "IFx 1 >90% THEN the spraying volume is reduced by 10%”, and the rule is given an initial weight w=0.6.

[0064] After three training sessions under the same working conditions, the system continuously optimized the rule weight, and the rule weight was increased to w=0.75. During this process, the fabric flatness was improved from the initial level 3.1 to level 3.7, meeting the target flatness requirement, which fully demonstrated the system's adaptive ability and optimization effect.

[0065] This solution also includes a data processing module, which is used to process the data collected by the data acquisition module, specifically including outlier repair, eliminating data that exceeds the process range or deviates from the mean ±3σ through the sliding window statistics method; noise filtering, smoothing the data through a first-order low-pass filter; normalization processing, eliminating dimensional differences through Z-score standardization.

[0066] It also includes a functional self-check module, which is used to monitor the status of the sensor unit and the execution unit in real time, trigger an alarm and switch to the backup device when an abnormality occurs.

[0067] It also includes a quality traceability module, which is used to record the entire process of the wrinkle-free treatment of each batch of suit fabrics, including the source of the fabric, processing parameters, equipment operation data, and operator information. When quality problems occur, the link and cause of the problem can be quickly traced back so that targeted improvement measures can be taken. It also helps to control and optimize the quality of the production process.

[0068] This application also includes an embodiment, according to one embodiment of the present invention, Figure 2 It is shown that a method for adjusting the non-ironing treatment of suit fabric is provided. The implementation of the non-ironing treatment adjustment system for suit fabric includes the following steps:

[0069] Step 1: Use humidity, temperature, pressure sensors and optical detection units to accurately collect fabric liquid carryover, drying temperature, pressing pressure and flatness parameters;

[0070] Step 2: Convert the collected precise data into fuzzy language variables of "high", "medium" and "low" through Gaussian distribution membership function;

[0071] Step 3: Integrate expert experience and historical data to generate rules, use the back propagation algorithm to dynamically optimize weights, combine the rule trigger strength, and calculate the control parameters using the center of gravity method;

[0072] Step 4: The variable frequency dryer adjusts the temperature curve according to the drying time, the servo press accurately adjusts the pressure through pressure closed-loop feedback, and the intelligent spray system dynamically controls the flow of the finishing liquid;

[0073] Step 5: Monitor the effect of the fabric after the wrinkle-free treatment in real time, compare the target flatness and other indicators, feed back the deviation to the decision-making module, and continuously optimize the processing process.

[0074] The technical scope of the present invention is not limited to the contents in the above description. Those skilled in the art can make various deformations and modifications to the above embodiments without departing from the technical idea of ​​the present invention, and these deformations and modifications should all fall within the protection scope of the present invention.

Claims

1. A system for adjusting the non-ironing treatment of 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 carrying rate x1, drying temperature x2, pressing equipment pressure value x3, fabric surface flatness x4. The parameter set is X = {x1, x2, x3, x4}; Adaptive decision module,Adaptive decision module,Uses fuzzy neural network algorithm to map data into fuzzy language variables,Fuzzy language values ​​are high, medium, and low,Define IF-THEN rules based on expert experience and historical data,Expert rules are initially assigned weights w k = 1.0, using the Apriori algorithm to mine historical data, find out the high-frequency parameter combinations, and generate data-driven rules based on them. The initial weight of the data-driven rules is w k =0.8, using the back propagation algorithm to dynamically adjust the rule weight w k , and the lower limit of expert rule weight w k ≥0.5, and when the conflict rule is triggered, the weight is w k :=w k 0.9 attenuation, using the center of gravity method to calculate the final control parameters, 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 module.

2. A system for adjusting the non-ironing treatment of suit fabrics according to claim 1, characterized in that: Use the back propagation algorithm to dynamically adjust the rule weight w k When , its objective function is the sum of squares of control errors, and the formula is as follows: Where E is the control error, y d is the target flatness, y is the output value; The weight gradient calculation formula is: The system output y is calculated by the weighted rule trigger strength, and the formula is: where μ k is the trigger strength of the kth rule, B k is the control amount corresponding to the kth rule, including drying time adjustment amount and pressure adjustment amount.

3. The system for adjusting the non-ironing treatment of suit fabrics according to claim 1, characterized in that: The execution control module includes an execution unit, and the execution unit includes: A variable frequency dryer is used to adjust the temperature curve according to the drying time T calculated by the adaptive decision module; Servo pressing machine, through pressure feedback closed loop control, to achieve precise adjustment of P; Intelligent spraying system dynamically adjusts the finishing liquid flow Q.

4. A system for adjusting the non-ironing treatment of suit fabrics 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 pressing equipment, and an optical detection unit for analyzing the surface flatness of the fabric through infrared spectroscopy.

5. The system for adjusting the non-ironing treatment of suit fabrics according to claim 1, characterized in that: It also includes a data processing module for processing the data collected by the data collection module: Outlier repair: data that exceeds the process range or deviates from the mean ±3σ is eliminated through the sliding window statistical method; Noise filtering, smoothing the data through a first-order low-pass filter; Normalization processing eliminates dimensional differences through Z-score standardization.

6. The system for adjusting the non-ironing treatment of suit fabrics according to claim 1, characterized in that: It also includes an incremental learning module for new rule generation and rule elimination; New rule generation: When the rule matching degree S = max(μ k )<0.6, generate new rules with initial weight w k =0.6; Rule elimination: delete weight w k <0.2 or low triggers the rule.

7. The system for adjusting the non-ironing treatment of suit fabrics according to claim 1, characterized in that: In step S102, expert experience comes from expert interviews and process manuals, and historical data comes from a historical process database.

8. The non-ironing treatment adjustment system for suit fabrics according to claim 1, characterized in that: It also includes a functional self-check module for real-time monitoring of the status of the sensor unit and the execution unit, triggering an alarm and switching to backup equipment when an abnormality occurs.

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

10. A method for adjusting the non-ironing treatment of suit fabrics, implemented by using the non-ironing treatment adjustment system for suit fabrics according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1: Use humidity, temperature, pressure sensors and optical detection units to accurately collect fabric liquid rate, drying temperature, pressing pressure and flatness parameters; S2: The collected precise data is converted into "high", "medium" and "low" fuzzy language variables through Gaussian distribution membership function; S3: Integrate expert experience and historical data to generate rules, use the back propagation algorithm to dynamically optimize weights, combine the rule trigger strength, and calculate the control parameters using the center of gravity method; S4: The variable frequency dryer adjusts the temperature curve according to the drying time, the servo press accurately adjusts the pressure through pressure closed loop feedback, and the intelligent spray system dynamically controls the flow of finishing liquid; S5: Real-time monitoring of the fabric effect after wrinkle-free treatment, comparison with target flatness and other indicators, feedback of deviations to the decision-making module, and continuous optimization of the processing process.

Images