Semi-worsted wool yarn preparation device and method

Abstract

The invention discloses a semi-worsted wool yarn equipment and a working method, which relate to the technical field of the textile industry, and solve the shortcomings of the existing semi-worsted wool yarn equipment and the working method, such as unstable quality, uneven yarn thickness, high yarn twist, low production efficiency and high energy consumption; the equipment comprises a fiber pretreatment device, an automatic fiber supply system, a yarn quality detection module, an intelligent control system, a spinning friction control module, a yarn wet treatment device, an automatic yarn collecting machine, an energy-saving control system and a networked monitoring system; the invention maintains the consistency of the yarn and monitors the yarn quality in real time through the fiber pretreatment device and the yarn quality detection module; dynamically adjusts the yarn twist through the intelligent control system and the spinning friction control module; solves the problem of low production efficiency through the automatic fiber supply system and the automatic yarn collecting machine; and adjusts and optimizes the energy consumption of the equipment through the energy-saving control system.

Description

Technical Field

[0001] The present invention relates to the technical field of textile industry, and more particularly to a semi-worsted wool yarn preparation device and method. Background Art

[0002] Spinning technology has been a key area in the textile industry over the past few decades. As the global textile market develops and changes, people's requirements for yarn quality and production efficiency are getting higher and higher. However, at a certain time, semi-worsted wool yarn equipment and working methods became a major technology in the textile industry.

[0003] In the existing semi-worsted wool yarn equipment and working methods, the spinning process includes coarse spinning, fine spinning and finishing. Coarse spinning refers to the raw fiber that has been cleaned and graded to be coarse spinning, while fine spinning is to stretch, twist, fine spin and finish the coarse spinning to finally obtain the required semi-worsted wool yarn. These equipment usually consists of a spinning machine, a spinning frame, a finishing machine and accessories, and requires skilled operators to operate and monitor.

[0004] However, this prior art has some disadvantages, which limits the quality and production efficiency of semi-worsted wool yarn to a certain extent. First, due to the limitations of equipment and process, the strength and uniformity of the fiber may not be fully guaranteed, resulting in unstable yarn quality, prone to breakage and uneven thickness. Secondly, it is difficult for semi-worsted equipment to accurately control the thickness of the yarn during the spinning process, resulting in inconsistent thickness of the produced yarn, which has a certain impact on the appearance and quality of the fabric. In addition, the semi-worsted equipment cannot completely eliminate the twisting of the yarn during the spinning process, resulting in the yarn being prone to kinking and breaking, reducing production efficiency and fabric quality. At the same time, compared with fully automated worsted equipment, semi-worsted equipment requires more manual operation and time to complete the same amount of yarn production, limiting the improvement of production efficiency; finally, this type of equipment usually requires a lot of mechanical operation and energy supply, resulting in high energy consumption, which may have a certain impact on the environment.

[0005] Therefore, in order to solve the shortcomings of unstable quality, uneven yarn thickness, high yarn twist, low production efficiency and high energy consumption in the existing semi-worsted wool yarn equipment and working method, the present invention discloses a semi-worsted wool yarn equipment and working method. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention discloses a semi-worsted wool yarn equipment and method, which solves the shortcomings of the existing semi-worsted wool yarn equipment and working method, such as unstable quality, uneven yarn thickness, high yarn distortion, low production efficiency and high energy consumption.

[0007] In order to achieve the above technical effects, the present invention adopts the following technical solutions:

[0008] A semi-worsted wool yarn preparation device, comprising:

[0009] A fiber pretreatment device is used to clean, classify and remove impurities from raw fiber; the fiber pretreatment device enhances the stability and wear resistance of wool fiber by an ionization treatment method;

[0010] An automatic fiber feeding system for adjusting the feeding speed and maintaining the consistency of the yarn; the automatic fiber feeding system controls the feeding speed and uniformity of the fiber through sensors and motor control devices;

[0011] A yarn quality detection module, which is used to monitor the yarn quality in real time. The yarn quality detection module realizes automatic monitoring of the yarn quality through a quality detection algorithm based on artificial intelligence;

[0012] An intelligent control system for controlling various parameters in the yarn processing process; the intelligent control system adjusts and optimizes equipment parameters in real time through a yarn optimization control algorithm based on machine learning;

[0013] A spinning friction control module, used for adjusting the twist of the yarn, wherein the spinning friction control module adjusts the twist of the yarn through a yarn twist control mechanism; the yarn twist control mechanism reduces the twist of the yarn during the spinning process through airflow regulation and electromagnetic induction methods;

[0014] A yarn wet treatment device is used to improve the quality and feel of the yarn; the yarn wet treatment device controls the moisture content of the yarn by means of spinning spray;

[0015] An automated yarn collecting machine is used to automatically collect and sort yarns; the automated yarn collecting machine realizes autonomous monitoring, control and collection of yarns through machine vision and mechanical control methods;

[0016] Energy-saving control system, used to adjust and optimize the energy consumption of equipment. The energy-saving control system monitors and adjusts and optimizes the energy consumption of equipment in real time through energy monitoring sensors and rule engines;

[0017] A networked monitoring system is used to realize remote communication of equipment; the networked monitoring system realizes remote monitoring and management of equipment through sensors and wireless communication networks;

[0018] The fiber pretreatment device is arranged at the feed port of the equipment, and the automatic fiber supply system is arranged on the left side of the fiber pretreatment device; the fiber pretreatment device is connected to the automatic fiber supply system through the feed port and the supply mechanism; the yarn wet treatment device is arranged on the left side of the automatic fiber supply system; the intelligent control system is arranged above the yarn wet treatment device; the yarn quality detection module and the spinning friction control module are arranged inside the intelligent control system; the automatic fiber supply system is connected to the spinning friction control module through a sensor and a motor control device; the spinning friction control module is connected to the yarn wet treatment device through the conveyor belt and monitoring sensor of the spinning part; the yarn quality detection module and the spinning friction control module are connected to the intelligent control system through a data transmission line; the automatic yarn collecting machine is located at the discharge port of the equipment.

[0019] As a further technical solution of the present invention, the working steps of the ionization treatment method in a semi-worsted wool yarn equipment are as follows:

[0020] S1. Removing dirt and impurities from the fiber surface by an airflow cleaning method; the airflow cleaning method uses a high-pressure airflow generator to blow and clean the fiber;

[0021] S2. detecting and analyzing the fiber characteristics including at least length and diameter by an optical sensor;

[0022] S3, changing the chemical properties of the fiber surface by an ionizing spray device;

[0023] S4. Enhance the stability and wear resistance of fibers through chemical coatings and textile auxiliaries.

[0024] As a further technical solution of the present invention, the automatic fiber supply system includes a sensor module, a control device module, a motor module and a feeding and conveying module; the sensor module detects the parameters of the fiber in real time through optical sensors, pressure sensors and capacitive sensors and transmits the data to the control device module; the control device module controls the fiber supply speed and uniformity through a programmable logic controller; the motor module includes a drive motor and a transmission device; the drive motor controls the fiber supply speed through a servo motor; the feeding and conveying module includes a fiber reel, a fiber conveying device and a fiber tension adjustment device; the fiber reel realizes the storage and supply of fiber through a fiber winding method; the fiber conveying device realizes the transmission of fiber through a conveyor belt; the fiber tension adjustment monitors the tension change through a tension wheel and a tension sensor and makes adjustments.

[0025] As a further technical solution of the present invention, the quality detection algorithm based on artificial intelligence monitors the change of the uniformity index through the yarn uniformity index calculation formula; the formula expression of the yarn uniformity index calculation formula is:

[0026] (1);

[0027] In formula (1), It indicates the total twist per unit length of the yarn and is used to measure the degree of twist of the yarn; It represents the number of nodes in the yarn and is used to evaluate the structural continuity of the yarn; The coefficient of variation of yarn thickness is used to measure the consistency of yarn thickness; Indicates the percentage of uneven parts in the yarn, used to evaluate the uniformity of the yarn; monitors the change of the strength evaluation value through the yarn strength evaluation formula; the formula expression of the yarn strength evaluation formula is:

[0028] (2)

[0029] In formula (2), It represents the breaking force of the fibers in the yarn and is used to measure the strength of the fibers; c represents the tensile strength of the yarn during stretching and is used to evaluate the tensile properties of the yarn; Indicates the percentage of yarn breakage, which is used to evaluate the degree of yarn breakage; the yarn moisture content measurement formula is used to realize automatic monitoring and control of yarn humidity; the formula expression of the yarn moisture content measurement formula is:

[0030] (3)

[0031] In formula (3), h represents the weight percentage of the yarn in a hydrated state, which is used to measure the moisture content of the yarn; It represents the difference between wet weight and dry weight of yarn and is used to evaluate the moisture content of yarn; Indicates the humidity percentage of the environment in which the yarn is located, and is used to consider the impact of environmental humidity on yarn quality.

[0032] As a further technical solution of the present invention, the working steps of the yarn optimization control algorithm based on machine learning in a semi-worsted wool yarn equipment are as follows:

[0033] R1, data collection and processing;

[0034] The real-time data of various parameters in the yarn processing process are collected through sensors, and the data are pre-processed through filters and normalization methods;

[0035] R2, feature extraction and selection;

[0036] According to the collected data, the spinning characteristic parameters are selected by feature extraction and data mining methods, wherein the spinning characteristic parameters at least include feed speed, feed roller speed, spindle speed, fan speed and spindle tension;

[0037] R3, modeling and training;

[0038] By establishing a yarn quality model, an optimization control strategy for different yarn quality targets is generated; the formula for modeling and training is:

[0039] (4)

[0040] In formula (4), M represents the yarn quality target output; Indicates the yarn feeding speed; Indicates the rotation speed of the wire feeding roller; Indicates the rotation speed of the spindle, represents the speed of the fan; n represents the tension applied by the spindle to the yarn;

[0041] R4. Real-time adjustment and optimization;

[0042] Various parameters in the yarn processing process are input into the yarn quality model through an intelligent control system; the yarn quality model adjusts and optimizes equipment parameters in real time through a spinning control formula; the spinning control formula is expressed as:

[0043] (5)

[0044] In formula (5), T is the control quantity output, which is used to adjust the equipment parameters; represents the error signal, which is used to measure the difference between the yarn quality target and the actual output; Represents the bias, which is used to adjust the position and inclination of the classification hyperplane; , The proportional, integral and differential coefficients of the controller are used to adjust the proportional, integral and differential forces of the control output;

[0045] R5, feedback adjustment and optimization;

[0046] The yarn quality model is continuously adjusted and optimized through a feedback mechanism; the feedback mechanism improves the stability and consistency of the yarn quality by iteratively adjusting the optimization formula; the formula expression of the iteratively adjusted optimization formula is:

[0047] (6)

[0048] In formula (6), R represents the The yarn quality output is the best; Indicates the target yarn quality; Represents the learning rate.

[0049] As a further technical solution of the present invention, the yarn twist control mechanism includes an airflow regulation module and an electromagnetic induction module; the airflow regulation module includes a compressed air supply unit, an airflow transmission unit and an airflow control unit; the compressed air supply unit pressurizes and stores air in the atmosphere through a compressor and an air storage tank, and transports it to the airflow transmission unit through a pipeline; the airflow transmission unit transmits compressed air to the yarn twist control area through an airflow pipeline and a nozzle; the airflow control unit adjusts the intensity and direction of the airflow through an airflow valve; the electromagnetic induction module controls the magnetic field distribution of the yarn through an electromagnetic induction method; the electromagnetic induction method controls the intensity and direction of the electric field by adjusting the current of the electromagnetic inductor.

[0050] As a further technical solution of the present invention, the automatic yarn collecting machine includes a machine vision module, a mechanical control module and a data processing and decision-making module; the machine vision module includes a line scanning unit, an image recognition unit and a tension detection unit; the line scanning unit obtains the position and state information of the yarn through a camera and an image processing method; the image recognition unit recognizes and analyzes the scanned image through a big data analysis method and a knowledge base; the tension detection unit controls the traction force of the yarn through a tension sensor; the mechanical control module includes a robotic arm unit and a conveyor belt unit; according to the feedback information of the visual sensor, the robotic arm unit realizes autonomous collection of the yarn through motion planning and trajectory control methods; the conveyor belt unit transmits the yarn from the spinning machine to the yarn collecting machine through position control and speed adjustment methods; the data processing and decision-making module autonomously monitors, controls and collects the yarn through a rule engine and a control strategy.

[0051] As a further technical solution of the present invention, the energy-saving control system includes a data acquisition and analysis module, a control strategy module and a feedback and adjustment module; the data acquisition and analysis module includes a data acquisition unit and a data analysis unit; the data acquisition unit collects temperature and humidity data through a high-speed data acquisition chip and a data compression method; the data analysis unit processes and analyzes the collected data through a big data analysis method; the control strategy module includes an energy-saving strategy unit and an equipment optimization unit; based on the data analysis results, the energy-saving strategy unit formulates an energy-saving strategy through fuzzy logic control and a knowledge base; the equipment optimization unit automatically adjusts the operating speed and power of the equipment according to real-time data and energy-saving strategies through a variable frequency speed regulation method; the feedback and adjustment module includes a feedback unit and an adjustment unit; the feedback unit receives and transmits real-time status feedback information from the equipment through sensors and a real-time communication network; according to the feedback information, the adjustment unit dynamically adjusts the parameters of the equipment through a rule engine.

[0052] As a further technical solution of the present invention, a working method of a semi-worsted wool yarn equipment comprises the following steps:

[0053] Step 1: fiber pretreatment;

[0054] The stability and wear resistance of wool fibers are enhanced through ionization treatment, which improves the quality and service life of raw materials;

[0055] Step 2: Automatic fiber supply;

[0056] Use sensors and motor controls to control fiber feed speed and uniformity to maintain yarn consistency;

[0057] Step 3: Yarn quality inspection;

[0058] Use AI-based quality detection algorithms to automatically monitor yarn quality, improving production efficiency and product quality;

[0059] Step 4: Intelligent control;

[0060] Use the yarn optimization and control algorithm based on machine learning to adjust and optimize equipment parameters in real time, optimize the production process, and improve product quality;

[0061] Step 5: Spinning friction control;

[0062] The yarn twist degree is adjusted by a yarn twist degree control mechanism, wherein the yarn twist degree control mechanism reduces the yarn twist degree during the spinning process through air flow regulation and electromagnetic induction method, thereby improving the yarn quality;

[0063] Step 6: Wet treatment of yarn;

[0064] Control the moisture of the yarn through the spinning spray system to improve the quality and feel of the yarn;

[0065] Step 7: Automatic yarn collection;

[0066] Through machine vision and mechanical control methods, the yarn can be autonomously monitored, controlled and collected to improve production efficiency and product quality;

[0067] Step 8: Energy saving control;

[0068] Use energy monitoring sensors and intelligent control algorithms to monitor and adjust equipment energy consumption in real time to reduce energy consumption and environmental pollution;

[0069] Step 9: Network monitoring;

[0070] Use sensors and wireless communication networks to achieve remote monitoring and management of equipment, improving production efficiency and management level.

[0071] Positive beneficial effects:

[0072] The present invention solves the problems of unstable yarn quality and uneven yarn thickness in the existing semi-worsted wool yarn equipment and working method by introducing a fiber pretreatment device and a yarn quality detection module. The fiber pretreatment device enhances the stability and wear resistance of wool fibers by an ionization treatment method, can ensure the quality stability of raw fiber, and reduce the influence of fiber impurities. The yarn quality detection module realizes automatic monitoring of yarn quality by a quality detection algorithm based on artificial intelligence, can timely discover yarn quality problems, avoid the production of low-quality yarn, and improve the stability and quality of yarn. By introducing an intelligent control system and a spinning friction control module, the problem of high yarn twist in the existing semi-worsted wool yarn equipment and working method is solved. The intelligent control system adjusts and optimizes equipment parameters in real time by a yarn optimization control algorithm based on machine learning, can reduce the fluctuation of yarn twist and improve the stability of yarn. The spinning friction control module adjusts the yarn twist by a yarn twist control mechanism, can reduce the twist of yarn during spinning, and improve the quality and stability of yarn. The introduction of an automatic fiber supply system and an automated yarn collection machine solves the problem of low production efficiency in existing semi-worsted wool yarn equipment and working methods. The automatic fiber supply system controls the fiber supply speed and uniformity through sensors and motor control devices, which can realize automated production and improve production efficiency. The automated yarn collection machine uses machine vision and mechanical control methods to realize autonomous monitoring, control and collection of yarns, which can greatly reduce manual intervention and improve production efficiency; the energy consumption of the equipment is monitored and adjusted and optimized in real time through the energy-saving control system, solving the problem of high energy consumption in existing semi-worsted wool yarn equipment and working methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A structural diagram of a semi-worsted wool yarn equipment of the present invention;

[0074] Figure 2 Frame diagram of equipment for semi-worsted wool yarn of the present invention

[0075] Figure 3 A flowchart of the steps of a working method of a semi-worsted wool yarn equipment according to the present invention;

[0076] Figure 4 A diagram showing the operation process of a yarn optimization control algorithm based on machine learning in a semi-worsted wool yarn equipment of the present invention;

[0077] Figure 5 This is a working principle diagram of an automatic yarn collecting machine in a semi-worsted wool yarn equipment of the present invention;

[0078] Figure 6It is a working step diagram of an automatic yarn collecting machine in a semi-worsted wool yarn equipment of the present invention;

[0079] In the figure, number 1 is a fiber pretreatment device; number 2 is an automatic fiber supply system; number 3 is an intelligent control system; number 4 is a yarn wet treatment device; number 5 is an automatic yarn collecting machine. DETAILED DESCRIPTION

[0080] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0081] like Figure 1-Figure 6 As shown, a semi-worsted wool yarn preparation device comprises:

[0082] The fiber pretreatment device 1 is used to clean, classify and remove impurities from raw fiber; the fiber pretreatment device 1 enhances the stability and wear resistance of wool fiber by an ionization treatment method;

[0083] An automatic fiber feeding system 2, used to adjust the feeding speed and maintain the consistency of the yarn; the automatic fiber feeding system 2 controls the feeding speed and uniformity of the fiber through sensors and motor control devices;

[0084] A yarn quality detection module, which is used to monitor the yarn quality in real time. The yarn quality detection module realizes automatic monitoring of the yarn quality through a quality detection algorithm based on artificial intelligence;

[0085] An intelligent control system 3 is used to control various parameters in the yarn processing process; the intelligent control system 3 adjusts and optimizes equipment parameters in real time through a yarn optimization control algorithm based on machine learning;

[0086] A spinning friction control module, used for adjusting the twist of the yarn, wherein the spinning friction control module adjusts the twist of the yarn through a yarn twist control mechanism; the yarn twist control mechanism reduces the twist of the yarn during the spinning process through airflow regulation and electromagnetic induction methods;

[0087] The yarn wet treatment device 4 is used to improve the quality and feel of the yarn; the yarn wet treatment device 4 controls the moisture content of the yarn by means of spinning spray;

[0088] An automatic yarn collecting machine 5 is used to automatically collect and sort the yarn; the automatic yarn collecting machine 5 realizes autonomous monitoring, control and collection of the yarn through machine vision and mechanical control methods;

[0089] Energy-saving control system, used to adjust and optimize the energy consumption of equipment. The energy-saving control system monitors and adjusts and optimizes the energy consumption of equipment in real time through energy monitoring sensors and rule engines;

[0090] A networked monitoring system is used to realize remote communication of equipment; the networked monitoring system realizes remote monitoring and management of equipment through sensors and wireless communication networks;

[0091] The fiber pretreatment device 1 is arranged at the feed port of the equipment, and the automatic fiber supply system 2 is arranged on the left side of the fiber pretreatment device 1; the fiber pretreatment device 1 is connected to the automatic fiber supply system 2 through the feed port and the supply mechanism; the yarn wet treatment device 4 is arranged on the left side of the automatic fiber supply system 2; the intelligent control system 3 is arranged above the yarn wet treatment device 4; the yarn quality detection module and the spinning friction control module are arranged inside the intelligent control system 3; the automatic fiber supply system 2 is connected to the spinning friction control module through a sensor and a motor control device; the spinning friction control module is connected to the yarn wet treatment device 4 through the conveyor belt and monitoring sensor of the spinning part; the yarn quality detection module and the spinning friction control module are connected to the intelligent control system 3 through a data transmission line; the automatic yarn collecting machine 5 is located at the discharge port of the equipment.

[0092] In a specific embodiment, the output end of the fiber pretreatment device 1 is connected to the input end of the automatic fiber supply system 2; the output end of the automatic fiber supply system 2 is connected to the input end of the yarn quality detection module; the output end of the yarn quality detection module and the energy-saving control system are connected to the input end of the intelligent control system 3; the output end of the intelligent control system 3 is connected to the input end of the spinning friction control module; the output end of the spinning friction control module is connected to the input end of the yarn wet treatment device 4; the output end of the yarn wet treatment device 4 is connected to the input end of the automatic yarn collecting machine 5; the networked monitoring system is connected to each module through sensors and wireless communication networks.

[0093] In a specific embodiment, the fiber pretreatment device 1 includes a cleaning machine connected to a water supply pipeline, and a cleaning liquid is injected into the cleaning machine through a water pump to clean the raw fiber. The classifier is connected to the cleaning machine to classify the cleaned fibers according to length and quality. The impurity removal device is connected to the classifier to remove impurities in the fibers through a vibrating screen or an airflow separator. The ionization treatment device is connected to the fiber pretreatment device 1 and is used to ionize the wool fibers. The automatic fiber supply system 1 includes: a sensor: installed on the feeding device to monitor the state of fiber supply. The motor control device is connected to the sensor to adjust the fiber supply speed and uniformity according to the feedback signal of the sensor. The feeding device: connected to the fiber pretreatment device 1 to feed the treated fibers into the spinning machine. The yarn quality detection module includes: a sensor: installed at the yarn outlet of the spinning machine to collect relevant data of the yarn. The data processing unit is connected to the sensor to transmit the collected data to the artificial intelligence algorithm for quality analysis and judgment. The artificial intelligence algorithm is connected to the data processing unit to analyze and judge the yarn quality. The intelligent control system 3 includes: a control unit connected to the sensor and the control device of the spinning machine, receiving data from the sensor, and adjusting parameters according to the machine learning algorithm. The parameter adjustment device is connected to the control unit, and the parameters of the equipment are adjusted and optimized in real time by controlling the various parameters of the spinning machine. The spinning friction control module includes: a twist control mechanism is connected to the twisting wheel of the spinning machine, and the twist of the yarn is reduced by airflow adjustment and electromagnetic induction method according to the feedback signal of the sensor. The airflow adjustment device is connected to the twist control mechanism, and is used to adjust the air flow in the spinning machine. The electromagnetic induction device is connected to the twist control mechanism, and the twist of the yarn is controlled by adjusting the electromagnetic induction torque. The yarn wet treatment device 4 includes: a spray device is connected to the spinning machine, and the humidity of the yarn is controlled by spraying. The humidity control device is connected to the spray device, and is used to adjust the humidity in the spinning machine. The automatic yarn collecting machine 5 includes: a machine vision system is installed on the yarn collecting device, and the yarn is monitored and controlled by image recognition technology. The mechanical control device is connected to the machine vision system and is responsible for the collection and arrangement of the yarn. The energy-saving control system includes: Energy monitoring sensors are installed at key parts of the equipment to collect energy consumption data of the equipment. The rule engine is connected to the energy monitoring sensor to analyze and adjust the energy consumption according to the set rules and strategies. The energy consumption adjustment device is connected to the rule engine and is responsible for the actual operation of the equipment energy consumption. The networked monitoring system includes: Sensors are installed at key parts of the equipment to collect the status data of the equipment. The wireless communication network connects all sensors and the monitoring management platform to realize data transmission and communication. The monitoring management platform is connected to the wireless communication network to receive the data transmitted by the sensors to realize remote monitoring and management of the equipment.

[0094] In the above embodiment, the working steps of the ionization treatment method in a semi-worsted wool yarn preparation device are:

[0095] S1. Removing dirt and impurities from the fiber surface by an airflow cleaning method; the airflow cleaning method uses a high-pressure airflow generator to blow and clean the fiber;

[0096] S2. detecting and analyzing the fiber characteristics including at least length and diameter by an optical sensor;

[0097] S3, changing the chemical properties of the fiber surface by an ionizing spray device;

[0098] S4. Enhance the stability and wear resistance of fibers through chemical coatings and textile auxiliaries.

[0099] In a specific embodiment, ionization treatment refers to exposing wool fibers to ionized gas, causing chemical reactions on the surface of the wool fibers through ionization to change the surface properties. Plasma technology is usually used to excite ions in the gas through a high-frequency electric field or a direct current electric field to generate plasma.

[0100] In specific implementation, the working steps of the ionization treatment method are:

[0101] U1. Prepare plasma: Inject gas into the cavity of the ionization treatment device, and excite ions in the gas through a high-frequency electric field or a direct current electric field to form plasma.

[0102] U2. Fiber exposure: The wool fibers to be treated are fed into the ionization treatment device and exposed to plasma. The ions in the plasma interact with the surface of the wool fibers.

[0103] U3. Chemical reaction: The ions in the plasma react with the molecules on the surface of the wool fiber to change the surface structure and properties. These reactions can include cross-linking, oxidation, hydrophobization, etc. to enhance the stability and wear resistance of the fiber.

[0104] In semi-worsted wool yarn equipment, ionization treatment can cause a cross-linking reaction on the surface of wool fibers, making the fibers more stable. This helps to reduce the elongation and shrinkage of the fibers, improve the dimensional stability of the fibers, and reduce fiber breakage and loss during the spinning process. In addition, ionization treatment can change the surface properties of wool fibers, making them more wear-resistant. Through chemical reactions, a substance similar to a hard protective film can be formed to protect the fibers from friction and wear and extend the service life of the fibers. At the same time, ionization treatment can change the hydrophilicity or hydrophobicity of the wool fiber surface, making it easier to dye. This helps to improve the dyeing uniformity and color fastness of the yarn.

[0105] In the above embodiment, the automatic fiber supply system 2 includes a sensor module, a control device module, a motor module and a feeding and conveying module; the sensor module detects the parameters of the fiber in real time through optical sensors, pressure sensors and capacitive sensors and transmits the data to the control device module; the control device module controls the fiber supply speed and uniformity through a programmable logic controller; the motor module includes a drive motor and a transmission device; the drive motor controls the fiber supply speed through a servo motor; the feeding and conveying module includes a fiber reel, a fiber conveying device and a fiber tension adjustment device; the fiber reel realizes the storage and supply of the fiber through a fiber winding method; the fiber conveying device realizes the transmission of the fiber through a conveyor belt; the fiber tension adjustment monitors the tension change through a tension wheel and a tension sensor and makes adjustments.

[0106] In a specific embodiment, the automatic fiber supply system 2 detects parameters such as fiber length, strength and density through the sensor module, and transmits these parameters to the control device module. After receiving the parameters from the sensor module, the control device module calculates the optimal fiber supply speed and quantity through an internal algorithm, and transmits these instructions to the motor module. The motor module controls the operation of the motor in the fiber supply system according to the instructions of the control device module to realize the supply of fibers. The feeding and conveying module is responsible for conveying the fibers to the feed port of the spinning machine.

[0107] In the semi-worsted wool yarn equipment, the automatic fiber supply system 2 can automatically control the fiber supply according to the fiber parameters, reducing the time and cost of manual intervention, while also reducing the probability of error and improving production efficiency. In addition, the automatic fiber supply system 2 adjusts the supply speed and quantity according to the fiber parameters, which can ensure the stability and consistency of the fiber, thereby improving product quality. At the same time, the automatic fiber supply system 2 can accurately control the fiber supply, avoid waste and oversupply, and save the cost of raw materials.

[0108] In the above embodiment, the quality detection algorithm based on artificial intelligence monitors the change of the uniformity index through the yarn uniformity index calculation formula; the formula expression of the yarn uniformity index calculation formula is:

[0109] (1)

[0110] In formula (1), It indicates the total twist per unit length of the yarn and is used to measure the degree of twist of the yarn; It represents the number of nodes in the yarn and is used to evaluate the structural continuity of the yarn; The coefficient of variation of yarn thickness is used to measure the consistency of yarn thickness; Indicates the percentage of uneven parts in the yarn, used to evaluate the uniformity of the yarn; monitors the change of the strength evaluation value through the yarn strength evaluation formula; the formula expression of the yarn strength evaluation formula is:

[0111] (2)

[0112] In formula (2), It represents the breaking force of the fibers in the yarn and is used to measure the strength of the fibers; c represents the tensile strength of the yarn during stretching and is used to evaluate the tensile properties of the yarn; Indicates the percentage of yarn breakage, which is used to evaluate the degree of yarn breakage; the yarn moisture content measurement formula is used to realize automatic monitoring and control of yarn humidity; the formula expression of the yarn moisture content measurement formula is:

[0113] (3)

[0114] In formula (3), h represents the weight percentage of the yarn in a hydrated state, which is used to measure the moisture content of the yarn; It represents the difference between wet weight and dry weight of yarn and is used to evaluate the moisture content of yarn; Indicates the humidity percentage of the environment in which the yarn is located, and is used to consider the impact of environmental humidity on yarn quality.

[0115] In a specific embodiment, the hardware environment of the quality detection algorithm based on artificial intelligence includes: High-performance computing server: used for large-scale data processing and complex algorithm calculation. Image sensor: used to obtain yarn image data. High-resolution camera: used to take yarn images. Image processing chip: used to quickly process and analyze yarn images. Network interface: used for data interaction and communication with other devices and systems.

[0116] In a semi-worsted wool yarn equipment, the operation process of the quality detection algorithm based on artificial intelligence is as follows:

[0117] G1. Image acquisition: Use a high-resolution camera to shoot the yarn and obtain yarn image data.

[0118] G2. Image preprocessing: The collected yarn images are preprocessed, including denoising, contrast enhancement and other operations to improve image quality.

[0119] G3. Feature extraction: Use computer vision technology to extract yarn feature information from images, such as yarn diameter, spinning evenness, yarn twist, etc.

[0120] G4. Data labeling: Use artificial intelligence algorithms to label feature extraction results, associate each feature with the corresponding quality score, and form a training data set.

[0121] G5. Model training: Based on the labeled training data set, the quality detection model is trained using a deep learning algorithm to establish a yarn quality assessment model.

[0122] G6. Yarn quality assessment: The newly collected yarn image is input into the quality detection model, and the yarn quality score is obtained by calculation.

[0123] G7. Judgment and alarm: Determine whether the yarn is qualified based on the quality score. If the yarn quality does not meet the standard, the alarm mechanism will be triggered.

[0124] In a semi-worsted wool yarn equipment, the test data table of the quality detection algorithm based on artificial intelligence is shown in Table 1:

[0125] Table 1 Test data of quality inspection algorithm based on artificial intelligence

[0126]

[0127] In data table 1, the yarn diameter, spinning uniformity and yarn twist of each image are extracted and calculated to obtain the corresponding quality score. According to the quality score, the quality of the yarn can be judged and whether the yarn is qualified can be evaluated. In a semi-worsted wool yarn equipment, the yarn quality characteristics can be learned from a large amount of training data through a deep learning algorithm, thereby improving the detection accuracy. In addition, the automated quality inspection process can achieve fast and accurate yarn evaluation, improve production efficiency and save human resources. Secondly, through automated quality inspection, the cost of manual inspection can be reduced, production efficiency can be improved, and the product defect rate can be reduced. At the same time, the quality inspection algorithm based on artificial intelligence can monitor the yarn quality in real time and alarm in time to remind the operator to make adjustments and repairs. Finally, by collecting and analyzing a large amount of quality inspection data, potential problems in the production process can be discovered, and optimization and improvement can be made to improve product quality and production efficiency.

[0128] In the above embodiment, the working steps of the yarn optimization control algorithm based on machine learning in a semi-worsted wool yarn equipment are:

[0129] R1, data collection and processing;

[0130] The real-time data of various parameters in the yarn processing process are collected through sensors, and the data are pre-processed through filters and normalization methods;

[0131] R2, feature extraction and selection;

[0132] According to the collected data, the spinning characteristic parameters are selected by feature extraction and data mining methods, wherein the spinning characteristic parameters at least include feed speed, feed roller speed, spindle speed, fan speed and spindle tension;

[0133] R3, modeling and training;

[0134] By establishing a yarn quality model, an optimization control strategy for different yarn quality targets is generated; the formula for modeling and training is:

[0135] (4)

[0136] In formula (4), M represents the yarn quality target output; Indicates the yarn feeding speed; Indicates the rotation speed of the wire feeding roller; Indicates the rotation speed of the spindle, represents the speed of the fan; n represents the tension applied by the spindle to the yarn;

[0137] R4. Real-time adjustment and optimization;

[0138] Various parameters in the yarn processing process are input into the yarn quality model through the intelligent control system 3; the yarn quality model adjusts and optimizes the equipment parameters in real time through the spinning control formula; the formula expression of the spinning control formula is:

[0139] (5)

[0140] In formula (5), T is the control quantity output, which is used to adjust the equipment parameters; represents the error signal, which is used to measure the difference between the yarn quality target and the actual output; Represents the bias, which is used to adjust the position and inclination of the classification hyperplane; , The proportional, integral and differential coefficients of the controller are used to adjust the proportional, integral and differential forces of the control output;

[0141] R5, feedback adjustment and optimization;

[0142] The yarn quality model is continuously adjusted and optimized through a feedback mechanism; the feedback mechanism improves the stability and consistency of the yarn quality by iteratively adjusting the optimization formula; the formula expression of the iteratively adjusted optimization formula is:

[0143] (6)

[0144] In formula (6), R represents the The yarn quality output is the best; Indicates the target yarn quality; Represents the learning rate.

[0145] In a specific embodiment, the hardware operating environment of the yarn optimization and control algorithm based on machine learning includes: High-performance computing server: used for large-scale data processing and complex algorithm calculation. Sensor: used for real-time monitoring of various parameters in the yarn production process, such as yarn tension, speed, humidity, etc. Programmable logic controller (PLC): used to control the operation and parameter adjustment of the equipment. Data acquisition card: used to collect sensor data and transmit it to the computing server for processing. Network interface: used for data interaction and communication with other devices and systems.

[0146] In a semi-worsted wool yarn equipment, the operation process of the yarn optimization control algorithm based on machine learning is as follows:

[0147] J1. Data collection: The sensor collects key parameter data of the yarn production process in real time, such as yarn tension, speed, humidity, etc.

[0148] J2. Data preprocessing: Preprocess the collected data, including denoising, outlier processing, data normalization and other operations to improve data quality.

[0149] J3. Feature extraction: Use feature engineering technology to extract key features in the yarn production process from the preprocessed data, such as yarn tension change trend, speed fluctuation, etc.

[0150] J4. Data annotation: Through manual or expert knowledge, the feature extraction results are annotated, and each feature is associated with the corresponding device parameter adjustment to form a training data set.

[0151] J5. Model training: Based on the labeled training data set, use machine learning algorithms (such as supervised learning or reinforcement learning) to train the yarn optimization and control model to establish a model of the relationship between equipment parameters and yarn quality.

[0152] J6. Real-time control: Input the newly collected data from the yarn production process into the yarn optimization control model, and obtain the best equipment parameter adjustment plan through model calculation.

[0153] J7. Equipment parameter adjustment: Send the best equipment parameter adjustment plan to the programmable logic controller (PLC) to adjust the equipment parameters in real time and optimize the yarn production process.

[0154] In a semi-worsted wool yarn equipment, the test data table of the yarn optimization control algorithm based on machine learning is shown in Table 2:

[0155] Table 2 Test data of yarn optimization control algorithm based on machine learning

[0156] In data table 2, the yarn tension, yarn speed and humidity of each data are collected and used to calculate the equipment parameter adjustment plan based on the machine learning yarn optimization control algorithm, and the corresponding yarn quality score is obtained by calculation. According to the yarn quality score, the pros and cons of the equipment parameter adjustment plan can be judged.

[0157] In a semi-worsted wool yarn equipment, the machine learning algorithm can automatically adjust the equipment parameters according to the real-time data in the yarn production process to improve the yarn quality. In addition, based on the real-time monitoring data and machine learning model, the algorithm can optimize the equipment parameters in time to keep the yarn production process in the best state. At the same time, the automated yarn optimization and control algorithm reduces the need for human intervention and reduces the burden on operators. Secondly, by optimizing the equipment parameters, the efficiency and output of yarn production can be improved. In addition, the optimization and control algorithm based on the machine learning model can improve the quality consistency and stability of the yarn. Finally, by collecting and analyzing a large amount of yarn production data, potential problems in the production process can be discovered, and optimization and improvement can be carried out to improve product quality and production efficiency.

[0158] In the above embodiment, the yarn twist control mechanism includes an airflow regulation module and an electromagnetic induction module; the airflow regulation module includes a compressed air supply unit, an airflow transmission unit and an airflow control unit; the compressed air supply unit pressurizes and stores air in the atmosphere through a compressor and an air storage tank, and transports it to the airflow transmission unit through a pipeline; the airflow transmission unit transmits compressed air to the yarn twist control area through an airflow pipeline and a nozzle; the airflow control unit adjusts the intensity and direction of the airflow through an airflow valve; the electromagnetic induction module controls the magnetic field distribution of the yarn through an electromagnetic induction method; the electromagnetic induction method controls the intensity and direction of the electric field by adjusting the current of the electromagnetic inductor.

[0159] In a specific embodiment, the spinning friction control module adjusts the twist of the yarn through a yarn twist control mechanism. The yarn twist control mechanism controls the twist of the yarn by changing the tension and speed of the yarn so that the yarn obtains appropriate twist during the spinning process.

[0160] In a semi-worsted wool yarn preparation device, the working steps of the yarn twist control mechanism are:

[0161] C1. Monitoring yarn status: The spinning friction control module monitors the yarn tension and speed in real time through sensors or other monitoring devices, and transmits them to the yarn twist control mechanism.

[0162] C2. Twist adjustment: The yarn twist control mechanism changes the yarn twist by adjusting the yarn tension and speed according to the yarn tension and speed signals. For example, increasing the tension can increase the yarn twist, while reducing the tension can reduce the yarn twist.

[0163] C3. Feedback control: The yarn twist control mechanism will continuously monitor and adjust the yarn twist to ensure that the yarn maintains proper twist during the spinning process. If the yarn twist is found to be beyond the preset range, the control mechanism will adjust the tension and speed in time to restore the yarn to a normal twist level.

[0164] C4. Process optimization: The spinning friction control module will optimize and adjust the yarn twist control mechanism based on the real-time collected data to improve the production efficiency and quality of the yarn.

[0165] In a semi-worsted wool yarn equipment, the yarn twist control mechanism can adjust the yarn twist according to the yarn tension and speed to ensure that the yarn has appropriate twist during the spinning process. This helps to produce spinning products that meet the requirements and improve the quality stability of the products. In addition, by real-time monitoring and adjusting the yarn twist, the spinning friction control module can optimize the yarn twist control mechanism, thereby improving the production efficiency and quality of the yarn and reducing the loss and scrap rate during the spinning process. Secondly, the automated control capabilities of the spinning friction control module and the yarn twist control mechanism reduce the need for manual intervention and operation, improve the automation level of the equipment, and reduce labor costs and operational risks.

[0166] In the above embodiment, the automatic yarn collecting machine 5 includes a machine vision module, a mechanical control module and a data processing and decision-making module; the machine vision module includes a line scanning unit, an image recognition unit and a tension detection unit; the line scanning unit obtains the position and state information of the yarn through a camera and an image processing method; the image recognition unit recognizes and analyzes the scanned image through a big data analysis method and a knowledge base; the tension detection unit controls the traction force of the yarn through a tension sensor; the mechanical control module includes a robotic arm unit and a conveyor belt unit; according to the feedback information of the visual sensor, the robotic arm unit realizes autonomous collection of the yarn through motion planning and trajectory control methods; the conveyor belt unit transmits the yarn from the spinning machine to the yarn collecting machine through position control and speed adjustment methods; the data processing and decision-making module autonomously monitors, controls and collects the yarn through a rule engine and a control strategy.

[0167] In a specific embodiment, the automatic yarn collecting machine 5 monitors and analyzes the yarn in real time through the machine vision module, and controls the actions of the yarn collecting disc and the yarn collecting knife through the mechanical control module to realize automatic yarn collecting and cutting. The data processing and decision module is responsible for collecting, analyzing and processing the data collected by the machine vision module, and making corresponding decisions according to preset rules and algorithms.

[0168] In a semi-worsted wool yarn equipment, the working steps of the automatic yarn collecting machine 5 are:

[0169] T1. Monitoring yarn status: The machine vision module monitors the yarn in real time, obtains information such as yarn position, diameter, tension, torsion, etc., and transmits it to the data processing and decision-making module.

[0170] T2. Determine yarn abnormality: The data processing and decision module analyzes and processes the data sent by the machine vision module according to the preset rules and algorithms to determine whether the yarn is abnormal. If the yarn is found to be abnormal, a signal will be sent to the mechanical control module to trigger the corresponding control operation.

[0171] T3. Control the action of the yarn receiver: The mechanical control module controls the action of the yarn receiving disc and the yarn receiving knife according to the instructions of the data processing and decision-making module to realize automatic yarn receiving and cutting.

[0172] T4. Send signal: The mechanical control module feeds back the control results to the data processing and decision-making module, and sends signals to other devices at the same time to realize the automated production process.

[0173] In a semi-worsted wool yarn equipment, the automatic yarn collecting machine 5 can automatically monitor and judge the yarn according to the preset rules and algorithms, and realize the automatic yarn collecting and cutting of the yarn. This can greatly improve production efficiency, reduce manual intervention and misoperation, and reduce production costs. In addition, the automatic yarn collecting machine 5 can monitor the yarn state in real time, and judge and control the yarn according to the preset rules and algorithms, so as to avoid affecting the product quality due to yarn abnormalities and improve the product qualification rate and stability. Secondly, the automatic yarn collecting machine 5 can realize the automatic yarn collecting and cutting of the yarn, reduce manual intervention and labor intensity, and improve the safety of the production site.

[0174] In the above embodiment, the energy-saving control system includes a data acquisition and analysis module, a control strategy module and a feedback and adjustment module; the data acquisition and analysis module includes a data acquisition unit and a data analysis unit; the data acquisition unit collects temperature and humidity data through a high-speed data acquisition chip and a data compression method; the data analysis unit processes and analyzes the collected data through a big data analysis method; the control strategy module includes an energy-saving strategy unit and an equipment optimization unit; based on the data analysis results, the energy-saving strategy unit formulates an energy-saving strategy through fuzzy logic control and a knowledge base; the equipment optimization unit automatically adjusts the operating speed and power of the equipment according to real-time data and energy-saving strategies through a variable frequency speed regulation method; the feedback and adjustment module includes a feedback unit and an adjustment unit; the feedback unit receives and transmits real-time status feedback information from the equipment through sensors and a real-time communication network; based on the feedback information, the adjustment unit dynamically adjusts the parameters of the equipment through a rule engine.

[0175] In a specific embodiment, the energy-saving control system monitors and analyzes the energy consumption of the equipment in real time through the data acquisition and analysis module, and then adjusts the working state of the equipment according to the preset strategy of the control strategy module to achieve the purpose of energy saving and emission reduction. The feedback and adjustment module tracks and adjusts the control effect in real time to ensure that the equipment is always in the best working state.

[0176] In a specific embodiment of the semi-worsted wool yarn equipment, the data acquisition and analysis module monitors the energy consumption in real time by installing sensors, meters, energy consumption meters and other equipment, and uploads the data to the data acquisition and analysis module. The module analyzes and processes the data in real time and generates an energy consumption report and analysis results. The control strategy module presets a series of energy-saving and emission-reduction strategies based on the analysis results and the actual situation of the equipment, and uploads them to the control strategy module. The module automatically adjusts the working state of the equipment according to the strategy to achieve the purpose of energy saving and emission reduction. The feedback and adjustment module monitors the operating state and energy consumption of the equipment in real time, and the feedback and adjustment module tracks and adjusts the control effect in real time. If the control effect is found to be poor, the module will adjust the control strategy in time to keep the equipment in the best working state.

[0177] In specific implementation, the energy-saving control system can monitor and analyze the energy consumption of the equipment, and automatically adjust the working status of the equipment through the control strategy module to achieve the purpose of energy saving and emission reduction. This helps to reduce the energy cost of the enterprise, improve production efficiency, and reduce pollution and damage to the environment. In addition, by real-time monitoring and analysis of the operating status of the equipment, the energy-saving control system can find and solve problems in the equipment, thereby improving the operating efficiency and stability of the equipment. This helps to improve product quality and production efficiency and reduce production costs. Secondly, the automated control capability of the energy-saving control system reduces the need for manual intervention and operation, improves the automation level of the equipment, and reduces labor costs and operational risks.

[0178] In the above embodiment, a working method of a semi-worsted wool yarn preparation device comprises the following steps:

[0179] Step 1: fiber pretreatment;

[0180] The stability and wear resistance of wool fibers are enhanced through ionization treatment, which improves the quality and service life of raw materials;

[0181] Step 2: Automatic fiber supply;

[0182] Use sensors and motor controls to control fiber feed speed and uniformity to maintain yarn consistency;

[0183] Step 3: Yarn quality inspection;

[0184] Use AI-based quality detection algorithms to automatically monitor yarn quality, improving production efficiency and product quality;

[0185] Step 4: Intelligent control;

[0186] Use the yarn optimization and control algorithm based on machine learning to adjust and optimize equipment parameters in real time, optimize the production process, and improve product quality;

[0187] Step 5: Spinning friction control;

[0188] The yarn twist degree is adjusted by a yarn twist degree control mechanism, wherein the yarn twist degree control mechanism reduces the yarn twist degree during the spinning process through air flow regulation and electromagnetic induction method, thereby improving the yarn quality;

[0189] Step 6: Wet treatment of yarn;

[0190] Control the moisture of the yarn through the spinning spray system to improve the quality and feel of the yarn;

[0191] Step 7: Automatic yarn collection;

[0192] Through machine vision and mechanical control methods, the yarn can be autonomously monitored, controlled and collected to improve production efficiency and product quality;

[0193] Step 8: Energy saving control;

[0194] Use energy monitoring sensors and intelligent control algorithms to monitor and adjust equipment energy consumption in real time to reduce energy consumption and environmental pollution;

[0195] Step 9: Network monitoring;

[0196] Use sensors and wireless communication networks to achieve remote monitoring and management of equipment, improving production efficiency and management level.

[0197] In a specific embodiment, the stability, consistency and quality of the yarn can be improved through fiber pretreatment, yarn quality detection and intelligent control. Through technical means such as automatic fiber supply, automated yarn collection and network monitoring, production efficiency can be improved, and manual intervention and production costs can be reduced. Through energy-saving control and intelligent optimization algorithms, the energy consumption of equipment can be monitored and adjusted to reduce energy consumption and environmental pollution. Through technical means such as spinning friction control and yarn wet treatment, the consistency and feel of the product can be improved. Through network monitoring and remote management, the equipment status can be monitored in real time, production parameters can be adjusted, and the management level and decision-making efficiency can be improved.

[0198] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that these specific embodiments are only illustrative, and those skilled in the art may omit, replace, and change the details of the above methods and systems in various ways without departing from the principles and essence of the present invention. For example, merging the above method steps so as to perform substantially the same functions in substantially the same manner to achieve substantially the same results is within the scope of the present invention. Therefore, the scope of the present invention is limited only by the appended claims.

Claims

1. A semi-worsted wool yarn preparation device, characterized in that: include: A fiber pretreatment device (1) for cleaning, grading and removing impurities from raw fiber; The fiber pretreatment device (1) enhances the stability and wear resistance of wool fibers by an ionization treatment method; An automatic fiber supply system (2) for adjusting the feeding speed and maintaining the consistency of the yarn; the automatic fiber supply system (2) controls the fiber feeding speed and uniformity through sensors and motor control devices; A yarn quality detection module, which is used to monitor the yarn quality in real time. The yarn quality detection module realizes automatic monitoring of the yarn quality through a quality detection algorithm based on artificial intelligence; An intelligent control system (3) is used to control various parameters in the yarn processing process; the intelligent control system (3) adjusts and optimizes equipment parameters in real time through a yarn optimization control algorithm based on machine learning; A spinning friction control module, used for adjusting the twist of the yarn, wherein the spinning friction control module adjusts the twist of the yarn through a yarn twist control mechanism; the yarn twist control mechanism reduces the twist of the yarn during the spinning process through airflow regulation and electromagnetic induction methods; The yarn wet treatment device (4) is used to improve the quality and feel of the yarn; the yarn wet treatment device (4) controls the moisture content of the yarn by means of spinning spray; An automatic yarn collecting machine (5) is used for automatically collecting and arranging yarns; the automatic yarn collecting machine (5) realizes autonomous monitoring, control and collection of yarns through machine vision and mechanical control methods; Energy-saving control system, used to adjust and optimize the energy consumption of equipment. The energy-saving control system monitors and adjusts and optimizes the energy consumption of equipment in real time through energy monitoring sensors and rule engines; A networked monitoring system is used to realize remote communication of equipment; the networked monitoring system realizes remote monitoring and management of equipment through sensors and wireless communication networks; The fiber pretreatment device (1) is arranged at the feed inlet of the equipment, and the automatic fiber supply system (2) is arranged on the left side of the fiber pretreatment device (1); the fiber pretreatment device (1) is connected to the automatic fiber supply system (2) through the feed inlet and the supply mechanism; the yarn wet treatment device (4) is arranged on the left side of the automatic fiber supply system (2); the intelligent control system (3) is arranged above the yarn wet treatment device (4); the yarn quality detection module and the spinning friction control module are arranged inside the intelligent control system (3); the automatic fiber supply system (2) is connected to the spinning friction control module through a sensor and a motor control device; the spinning friction control module is connected to the yarn wet treatment device (4) through a conveyor belt and a monitoring sensor of the spinning part; the yarn quality detection module and the spinning friction control module are connected to the intelligent control system (3) through a data transmission line; the automatic yarn collecting machine (5) is located at the discharge port of the equipment; The AI-based quality detection algorithm monitors the change of the uniformity index through the yarn uniformity index calculation formula; the formula expression of the yarn uniformity index calculation formula is: （1） In formula (1), It indicates the total twist per unit length of the yarn and is used to measure the degree of twist of the yarn; It represents the number of nodes in the yarn and is used to evaluate the structural continuity of the yarn; The coefficient of variation of yarn thickness is used to measure the consistency of yarn thickness; Indicates the percentage of uneven parts in the yarn, used to evaluate the uniformity of the yarn; monitors the change of the strength evaluation value through the yarn strength evaluation formula; the formula expression of the yarn strength evaluation formula is: （2） In formula (2), It represents the breaking force of the fibers in the yarn and is used to measure the strength of the fibers; c represents the tensile strength of the yarn during stretching and is used to evaluate the tensile properties of the yarn; Indicates the percentage of yarn breakage, used to evaluate the degree of yarn breakage; The yarn moisture content measurement formula is used to realize automatic monitoring and control of the yarn humidity; the formula expression of the yarn moisture content measurement formula is: （3） In formula (3), h represents the weight percentage of the yarn in a hydrated state, which is used to measure the moisture content of the yarn; It represents the difference between wet weight and dry weight of yarn and is used to evaluate the moisture content of yarn; Indicates the humidity percentage of the environment in which the yarn is located, and is used to consider the impact of environmental humidity on yarn quality.

2. A semi-worsted wool yarn preparation device according to claim 1, characterized in that: The working steps of the ionization treatment method in a semi-worsted wool yarn equipment are as follows: S1. Removing dirt and impurities from the fiber surface by an airflow cleaning method; the airflow cleaning method uses a high-pressure airflow generator to blow and clean the fiber; S2. detecting and analyzing the fiber characteristics including at least length and diameter by an optical sensor; S3, changing the chemical properties of the fiber surface by an ionizing spray device; S4. Enhance the stability and wear resistance of fibers through chemical coatings and textile auxiliaries.

3. A semi-worsted wool yarn preparation device according to claim 1, characterized in that: The automatic fiber supply system (2) comprises a sensor module, a control device module, a motor module and a feeding and conveying module; the sensor module detects fiber parameters in real time through optical sensors, pressure sensors and capacitive sensors and transmits data to the control device module; the control device module controls the fiber supply speed and uniformity through a programmable logic controller; the motor module comprises a drive motor and a transmission device; the drive motor controls the fiber supply speed through a servo motor; the feeding and conveying module comprises a fiber reel, a fiber conveying device and a fiber tension adjustment device; the fiber reel realizes fiber storage and supply through a fiber winding method; the fiber conveying device realizes fiber transmission through a conveyor belt; the fiber tension adjustment monitors tension changes through a tension wheel and a tension sensor and makes adjustments.

4. A semi-worsted wool yarn preparation device according to claim 1, characterized in that: The working steps of the yarn optimization control algorithm based on machine learning in a semi-worsted wool yarn equipment are as follows: R1, data collection and processing; The real-time data of various parameters in the yarn processing process are collected through sensors, and the data are pre-processed through filters and normalization methods; R2, feature extraction and selection; According to the collected data, the spinning characteristic parameters are selected by feature extraction and data mining methods, wherein the spinning characteristic parameters at least include feed speed, feed roller speed, spindle speed, fan speed and spindle tension; R3, modeling and training; By establishing a yarn quality model, an optimization control strategy for different yarn quality targets is generated; the formula for modeling and training is as follows: （4） In formula (4), M represents the yarn quality target output; Indicates the yarn feeding speed; Indicates the rotation speed of the wire feeding roller; Indicates the rotation speed of the spindle, represents the speed of the fan; n represents the tension applied by the spindle to the yarn; R4. Real-time adjustment and optimization; Various parameters in the yarn processing process are input into the yarn quality model through the intelligent control system (3); the yarn quality model adjusts and optimizes the equipment parameters in real time through a spinning control formula; the spinning control formula is expressed as: （5） In formula (5), T is the control quantity output, which is used to adjust the equipment parameters; represents the error signal, which is used to measure the difference between the yarn quality target and the actual output; Represents the bias, which is used to adjust the position and inclination of the classification hyperplane; , The proportional, integral and differential coefficients of the controller are used to adjust the proportional, integral and differential forces of the control output; R5, feedback adjustment and optimization; The yarn quality model is continuously adjusted and optimized through a feedback mechanism; the feedback mechanism improves the stability and consistency of the yarn quality by iteratively adjusting the optimization formula; the formula expression of the iteratively adjusted optimization formula is: （6） In formula (6), R represents the The yarn quality output is the best; Indicates the target yarn quality; Represents the learning rate.

5. A semi-worsted wool yarn preparation device according to claim 1, characterized in that: The yarn twist control mechanism includes an airflow regulation module and an electromagnetic induction module; the airflow regulation module includes a compressed air supply unit, an airflow transmission unit and an airflow control unit; the compressed air supply unit pressurizes and stores air in the atmosphere through a compressor and an air storage tank, and transports it to the airflow transmission unit through a pipeline; the airflow transmission unit transmits compressed air to the yarn twist control area through an airflow pipeline and a nozzle; the airflow control unit adjusts the intensity and direction of the airflow through an airflow valve; the electromagnetic induction module controls the magnetic field distribution of the yarn through an electromagnetic induction method; the electromagnetic induction method controls the intensity and direction of the electric field by adjusting the current of the electromagnetic inductor.

6. A semi-worsted wool yarn preparation device according to claim 1, characterized in that: The automatic yarn collecting machine (5) comprises a machine vision module, a mechanical control module and a data processing and decision module; the machine vision module comprises a line scanning unit, an image recognition unit and a tension detection unit; the line scanning unit obtains the position and state information of the yarn through a camera and an image processing method; the image recognition unit recognizes and analyzes the scanned image through a big data analysis method and a knowledge base; the tension detection unit controls the traction force of the yarn through a tension sensor; the mechanical control module comprises a mechanical arm unit and a conveyor belt unit; according to the feedback information of the visual sensor, the mechanical arm unit realizes the autonomous collection of the yarn through motion planning and trajectory control methods; the conveyor belt unit transmits the yarn from the spinning machine to the yarn collecting machine through position control and speed adjustment methods; the data processing and decision module autonomously monitors, controls and collects the yarn through a rule engine and a control strategy.

7. A semi-worsted wool yarn preparation device according to claim 1, characterized in that: The energy-saving control system includes a data acquisition and analysis module, a control strategy module and a feedback and adjustment module; the data acquisition and analysis module includes a data acquisition unit and a data analysis unit; the data acquisition unit collects temperature and humidity data through a high-speed data acquisition chip and a data compression method; the data analysis unit processes and analyzes the collected data through a big data analysis method; the control strategy module includes an energy-saving strategy unit and an equipment optimization unit; Based on the data analysis results, the energy-saving strategy unit formulates energy-saving strategies through fuzzy logic control and knowledge base; the equipment optimization unit automatically adjusts the operating speed and power of the equipment according to real-time data and energy-saving strategies through variable frequency speed regulation method; the feedback and adjustment module includes a feedback unit and an adjustment unit; the feedback unit receives and transmits real-time status feedback information from the equipment through sensors and real-time communication networks; According to the feedback information, the adjustment unit dynamically adjusts the parameters of the device through a rule engine.

8. A method for producing semi-worsted wool yarn, characterized in that: A semi-worsted wool yarn preparation device according to any one of claims 1 to 7 is used, comprising the following steps: Step 1: fiber pretreatment; The stability and wear resistance of wool fibers are enhanced through ionization treatment, which improves the quality and service life of raw materials; Step 2: Automatic fiber supply; Use sensors and motor controls to control fiber feed speed and uniformity to maintain yarn consistency; Step 3: Yarn quality inspection; Use AI-based quality detection algorithms to automatically monitor yarn quality, improving production efficiency and product quality; Step 4: Intelligent control; Use the yarn optimization and control algorithm based on machine learning to adjust and optimize equipment parameters in real time, optimize the production process, and improve product quality; Step 5: Spinning friction control; The yarn twist degree is adjusted by a yarn twist degree control mechanism, wherein the yarn twist degree control mechanism reduces the yarn twist degree during the spinning process through air flow regulation and electromagnetic induction method, thereby improving the yarn quality; Step 6: Wet treatment of yarn; Control the moisture of the yarn through the spinning spray system to improve the quality and feel of the yarn; Step 7: Automatic yarn collection; Through machine vision and mechanical control methods, the yarn can be autonomously monitored, controlled and collected to improve production efficiency and product quality; Step 8: Energy saving control; Use energy monitoring sensors and intelligent control algorithms to monitor and adjust equipment energy consumption in real time to reduce energy consumption and environmental pollution; Step 9: Network monitoring; Use sensors and wireless communication networks to achieve remote monitoring and management of equipment, improving production efficiency and management level.

Images