Textile production process fault monitoring method and system

By installing tension, visual and sound sensors in the textile machine, the tension and operating status of yarns are monitored in real time, and the problem that the existing technology cannot monitor physical faults of the textile machine is solved, and the stability and production efficiency of the textile process are improved. .

CN119000152AInactive Publication Date: 2024-11-22QIDONG FENGMING TEXTILE CO LTD

Patent Information

Application Number
CN202411483894.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-23
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art cannot effectively monitor physical faults in textile machines, such as yarn breakage, resulting in interruption of textile processes and high waste rates.

Method used

Install tension sensors, cameras and sound sensors in the spinning channel of the textile machine to collect and analyze the tension, image and sound data of the yarn in real time, determine the fault through a comprehensive evaluation mechanism and trigger an alarm.

Benefits of technology

It realizes fault monitoring at the physical level of textile machines, timely identify yarn breaks and other abnormalities, reduces production interruptions and waste rates, and ensures the stability of the textile process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119000152A_ABST
    Figure CN119000152A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of data processing, and discloses a textile production process fault monitoring method and system, the monitoring system is obtained by monitoring method modularization, and the monitoring system is composed of a sensor module, a data acquisition module, a monitoring and analysis module, a fault identification and report module and a data recording and analysis module. The modules of the monitoring system are in data intercommunication. The tension sensor monitors the tension of the yarn in the pay-off channel of the textile machine in real time, the system rapidly detects the abnormal tension of the yarn by recording and comparing the normal range of the tension, the visual monitoring module analyzes a real-time image through the image processing technology and compares the real-time image with a reference image, and the real-time image is obtained. If the difference degree of the real-time images exceeds a set threshold value, the system can warn an operator about possible problems, and the beneficial effects that the textile machine is subjected to physical monitoring, and faults caused by defense line breakage are effectively avoided are achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to a method and system for monitoring faults in a textile production process. Background Art

[0002] In the prior art, the monitoring and fault analysis of the textile production process are mainly carried out by manually formulating data anomaly rules in advance; or collecting a large amount of data generated in the production process, and manually marking these data as abnormal data, and then training them through neural networks to discover abnormal data in daily production processes and report them to relevant personnel.

[0003] After searching, it was found that the publication number of CN 117171670 A is a method, device and system for monitoring faults in the textile production process. The method compares each value in the time series of the monitoring parameter with the normal value to obtain the fluctuation degree of the monitoring parameter; uses the hierarchical analysis method to obtain the priority of the monitoring parameter, and obtains the fault degree of the monitoring parameter in combination with the fluctuation degree; obtains the first correlation coefficient between any two monitoring parameters through correlation analysis, and obtains the second correlation coefficient between the two monitoring parameters according to the probability that any two monitoring parameters are abnormal at the same time; obtains the fault value of the monitoring parameter; when the fault value of the monitoring parameter is greater than the preset first threshold value, the production equipment corresponding to the monitoring parameter is repaired. The present invention can timely identify abnormal equipment based on real-time textile data.

[0004] Although the above-mentioned technical scheme achieves the effect of monitoring faults through the hierarchical analysis method, textiles are composed of multiple warp axes, weft axes and shuttles in a textile machine, and the defense lines are woven through the program control of the textile machine. Even if a single defense line breaks, the textile machine will not have fluctuating parameters because it only involves physical line shortage. Therefore, the above-mentioned technical scheme cannot monitor process faults. Correspondingly, there are also consistency problems in the line transmission link in the textile process, that is, faults caused by physical breaks cannot be monitored by the above-mentioned system. Summary of the invention

[0005] Technical issues solved: In view of the deficiencies in the prior art, the present invention provides a method and system for monitoring faults in a textile production process, which has the advantages of physically monitoring the textile machine to effectively avoid faults caused by broken defense lines, and can uniformly monitor the broken threads of the textile machine, thereby solving the problems of the above-mentioned technologies.

[0006] Technical solution: To achieve the above object, the present invention provides the following technical solution: a method for monitoring faults in a textile production process, the detection method comprising the following steps: Step 1: Sensor installation: Install a tension sensor in the spinning channel of the textile machine, install a camera for visual monitoring, and install a sound sensor to capture the sound of spinning; Step 2, data collection: real-time collection of yarn tension data in the pay-off channel, recording of the normal range, collection of image data in the pay-off channel at a frequency of once per minute and storage as a reference image, recording of sound samples under normal operating conditions, and establishment of a sound database; Step 3: Monitoring and analysis: real-time monitoring of tension sensor data, comparing it with the set threshold, if the tension drops beyond the set threshold, record it as abnormal, use image processing technology to analyze the real-time image, check whether the yarn is normal, set the image recognition algorithm, compare the current image with the reference image, capture the sound signal in real time, and compare it with the normal sound, if there is an abnormal sound feature, record it as a fault signal; Step 4: Fault identification and reporting: Set up a comprehensive evaluation mechanism to summarize the tension, visual and sound monitoring results. If any monitoring data shows an abnormality, the system will immediately determine it as a fault. Once a fault is identified, an alarm will be triggered; Step 5. Data recording and feedback: Record the time, type and handling results of each fault for subsequent analysis. Analyze the fault records once a week to find out the potential fault mode and frequency.

[0007] A textile production process fault monitoring system, characterized in that the monitoring system is obtained by modularizing the monitoring method, the monitoring system is composed of a sensor module, a data acquisition module, a monitoring and analysis module, a fault identification and reporting module and a data recording and analysis module, and the data between the modules of the monitoring system are interoperable; The sensor module is used to monitor the tension, visual and sound signals in the pay-off channel of the textile machine in real time; The data acquisition module is used to collect data generated by the sensor module in real time; The monitoring and analysis module uses the data collected by the sensor module to perform real-time monitoring and anomaly detection; The fault identification and reporting module is used to perform fault determination and alarm processing according to the output of the monitoring and analysis module; The data recording and analysis module is used to record and analyze the specific circumstances under which the failure occurred, optimize the monitoring system and prevent future failures.

[0008] Preferably, the sensor module tension test expression is: Assume that the tension value output by the tension sensor is ,in Indicates time; When the tension exceeds the normal range, it indicates that the yarn is in an abnormal state.

[0009] Preferably, the sensor module visual test expression is: The image data at the current moment is , the reference image is ; Define the difference between images As a distance or difference measure between the live image and the reference image: By setting the threshold ,when It may indicate abnormal visual monitoring.

[0010] Preferably, the sensor module sound test expression is: The sound signal captured by the sound sensor is expressed as ,in It's time The sound signal when

[0011] When the sound signal exceeds the normal range, it means that the sound monitoring has detected an abnormal situation.

[0012] Preferably, the data acquisition module expression is: The data acquisition process is described as real-time recording of tension data: Image data acquisition expression: Image data is collected periodically, and the reference image is : Sound data collection expression: Recording of sound data to establish a sound database: .

[0013] Preferably, the comprehensive evaluation mechanism in the fault identification and reporting module is expressed as: Assume that the abnormal result output by the monitoring and analysis module is ,in Indicates time; in Represents a set of monitoring data. If any monitoring data is abnormal, is true.

[0014] Preferably, the fault alarm triggering expression in the fault identification and reporting module is: The alarm triggering logic is based on status.

[0015] Preferably, the alarm information expression is: When an alarm occurs, the specific information of the fault can be recorded: time , Fault type and processing results ; .

[0016] Preferably, the fault record expression in the data recording and analysis module is: When a fault occurs, record the time of the fault , Fault type , the measures taken ; The analysis function expression in the data recording and analysis module is: Frequency calculation: have Fault records, of which Yes Type The number of failures, then the type The failure frequency is estimated to be: Probability distribution fitting: Failures follow a Poisson distribution, so the type In time Internal The probability of failure is expressed as: in Yes Type The average failure rate is estimated from historical data.

[0017] Compared with the prior art, the present invention provides a method and system for monitoring faults in a textile production process, which has the following beneficial effects: 1. The present invention monitors the tension of the yarn in the pay-off channel of the textile machine in real time through the tension sensor. By recording and comparing the normal range of tension, the system quickly detects abnormal yarn tension. The visual monitoring module uses image processing technology to analyze the real-time image and compares it with the reference image. If the difference of the real-time image exceeds the set threshold, the system will alert the operator of possible problems, including yarn dislocation and abnormal textile structure. The sound sensor captures the sound signal when the yarn is running and compares it with the normal sound sample. The appearance of abnormal sound characteristics promptly indicates possible fault conditions, including yarn winding and abnormal friction of mechanical parts. When any monitoring data indicates an abnormality, the monitoring system immediately triggers an alarm and records the specific time, type and processing result of the fault. Instant feedback and recording help operators to quickly respond to and repair problems, reduce production interruptions and scrap rates, and achieve the beneficial effect of physically monitoring the textile machine and effectively avoiding faults caused by broken defense lines.

[0018] 2. The present invention can monitor the tension changes of yarns in real time through the tension sensor. Since the breakage of textile machine threads is usually accompanied by the occurrence of abnormal tension, the system can timely detect the potential risk of yarn breakage by comparing the real-time tension data with the set normal range. The sound signal captured by the sound sensor can reflect the abnormal situation in the operation of the yarn, such as the abnormal friction sound of yarn winding or mechanical parts. These abnormal sounds are often a precursor to the impending breakage of the yarn. The system can issue an alarm in time according to the characteristics of the sound signal to help prevent the occurrence of breakage. When any monitoring data indicates that there is a risk of breakage of the textile machine, the monitoring system will immediately trigger the alarm mechanism. The system records the time, type and processing result of the fault, achieving the beneficial effect of being able to uniformly monitor the breakage of textile machine threads. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0020] 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.

[0021] See also Figure 1 , a method for monitoring faults in a textile production process, the detection method comprising the following steps: Step 1: Sensor installation: Install a tension sensor in the spinning channel of the textile machine, install a camera for visual monitoring, and install a sound sensor to capture the sound of spinning; Step 2, data collection: real-time collection of yarn tension data in the pay-off channel, recording of the normal range, collection of image data in the pay-off channel at a frequency of once per minute and storage as a reference image, recording of sound samples under normal operating conditions, and establishment of a sound database; Step 3: Monitoring and analysis: real-time monitoring of tension sensor data, comparing it with the set threshold, if the tension drops beyond the set threshold, record it as abnormal, use image processing technology to analyze the real-time image, check whether the yarn is normal, set the image recognition algorithm, compare the current image with the reference image, capture the sound signal in real time, and compare it with the normal sound, if there is an abnormal sound feature, record it as a fault signal; Step 4: Fault identification and reporting: Set up a comprehensive evaluation mechanism to summarize the tension, visual and sound monitoring results. If any monitoring data shows an abnormality, the system will immediately determine it as a fault. Once a fault is identified, an alarm will be triggered; Step 5. Data recording and feedback: Record the time, type and handling results of each fault for subsequent analysis. Analyze the fault records once a week to find out the potential fault mode and frequency.

[0022] A textile production process fault monitoring system, characterized in that the monitoring system is obtained by modularizing the monitoring method, the monitoring system is composed of a sensor module, a data acquisition module, a monitoring and analysis module, a fault identification and reporting module and a data recording and analysis module, and the data between the modules of the monitoring system are interoperable; The sensor module is used to monitor the tension, visual and sound signals in the pay-off channel of the textile machine in real time; The data acquisition module is used to collect data generated by the sensor module in real time; The monitoring and analysis module uses the data collected by the sensor module to perform real-time monitoring and anomaly detection; The fault identification and reporting module is used to perform fault determination and alarm processing according to the output of the monitoring and analysis module; The data recording and analysis module is used to record and analyze the specific circumstances under which a fault occurs, optimize the monitoring system and prevent future faults.

[0023] Preferably, the sensor module tension test expression is: Assume that the tension value output by the tension sensor is ,in Indicates time; When the tension exceeds the normal range, it indicates that the yarn is in an abnormal state.

[0024] The sensor can monitor the changes in yarn tension in the textile machine's pay-off channel in real time. By continuously recording the tension value and comparing it with the preset normal range, the system can instantly detect any tension abnormalities, including tension values ​​that are too high or too low. This is one of the key signals before the textile machine's thread breaks.

[0025] Preferably, the sensor module visual test expression is: The image data at the current moment is , the reference image is ; Define the difference between images As a distance or difference measure between the live image and the reference image: By setting the threshold ,when It may indicate abnormal visual monitoring.

[0026] The system can acquire and analyze the image data generated by the textile machine in real time, and calculate the difference between the real-time image and the reference image by comparing it with the preset reference image. This real-time and sensitivity enables the system to detect problems such as yarn position deviation and textile structure abnormalities in a timely manner, providing early warnings for operators.

[0027] Preferably, the sensor module sound test expression is: The sound signal captured by the sound sensor is expressed as ,in It's time The sound signal when

[0028] When the sound signal exceeds the normal range, it means that the sound monitoring has detected an abnormal situation.

[0029] Preferably, the data acquisition module expression is: The data acquisition process is described as real-time recording of tension data: Image data acquisition expression: Image data is collected periodically, and the reference image is : Sound data collection expression: Recording of sound data to establish a sound database: .

[0030] Preferably, the comprehensive evaluation mechanism in the fault identification and reporting module is expressed as: Assume that the abnormal result output by the monitoring and analysis module is ,in Indicates time; in Represents a set of monitoring data. If any monitoring data is abnormal, is true.

[0031] Preferably, the fault alarm triggering expression in the fault identification and reporting module is: The alarm triggering logic is based on status.

[0032] Fault alarm is based on the status of real-time monitoring data. If the conditions are met, the alarm will be triggered immediately, ensuring that measures can be taken quickly when problems occur to avoid or minimize production interruptions and losses.

[0033] Preferably, the alarm information expression is: When an alarm occurs, the specific information of the fault can be recorded: time , Fault type and processing results ; .

[0034] The alarm information records the specific time when the fault occurred. , Fault type and the measures taken by operators ,This recording method completely reflects the entire process of the failure event, which is helpful for ,subsequent analysis and optimization of the production process.

[0035] Preferably, the fault record expression in the data recording and analysis module is: When a fault occurs, record the time of the fault , Fault type , the measures taken ; The analysis function expression in the data recording and analysis module is: Frequency calculation: have Fault records, of which Yes Type The number of failures, then the type The failure frequency is estimated to be: Probability distribution fitting: Failures follow a Poisson distribution, so the type In time Internal The probability of failure is expressed as: in Yes Type The average failure rate is estimated from historical data.

[0036] The specific time when each failure occurred is recorded , Fault type and measures taken ,This integrity ensures a detailed record of the failure event and provides an accurate data basis for ,subsequent analysis and improvement.

[0037] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring faults in a textile production process, characterized in that: The detection method consists of the following steps: Step 1: Sensor installation: Install a tension sensor in the spinning channel of the textile machine, install a camera for visual monitoring, and install a sound sensor to capture the sound of spinning; Step 2, data collection: real-time collection of yarn tension data in the pay-off channel, recording of the normal range, collection of image data in the pay-off channel at a frequency of once per minute and storage as a reference image, recording of sound samples under normal operating conditions, and establishment of a sound database; Step 3: Monitoring and analysis: real-time monitoring of tension sensor data, comparing it with the set threshold, if the tension drops beyond the set threshold, record it as abnormal, use image processing technology to analyze the real-time image, check whether the yarn is normal, set the image recognition algorithm, compare the current image with the reference image, capture the sound signal in real time, and compare it with the normal sound, if there is an abnormal sound feature, record it as a fault signal; Step 4: Fault identification and reporting: Set up a comprehensive evaluation mechanism to summarize the tension, visual and sound monitoring results. If any monitoring data shows an abnormality, the system will immediately determine it as a fault. Once a fault is identified, an alarm will be triggered; Step 5. Data recording and feedback: Record the time, type and handling results of each fault for subsequent analysis. Analyze the fault records once a week to find out the potential fault mode and frequency.

2. A textile production process fault monitoring system according to claim 1, characterized in that: The monitoring system is obtained by modularizing the monitoring method. The monitoring system consists of a sensor module, a data acquisition module, a monitoring and analysis module, a fault identification and reporting module, and a data recording and analysis module. The modules of the monitoring system are interoperable with each other. The sensor module is used to monitor the tension, visual and sound signals in the pay-off channel of the textile machine in real time; The data acquisition module is used to collect data generated by the sensor module in real time; The monitoring and analysis module uses the data collected by the sensor module to perform real-time monitoring and anomaly detection; The fault identification and reporting module is used to perform fault determination and alarm processing according to the output of the monitoring and analysis module; The data recording and analysis module is used to record and analyze the specific circumstances under which the failure occurred, optimize the monitoring system and prevent future failures.

3. A textile production process fault monitoring system according to claim 2, characterized in that: The sensor module tension test expression is: Assume that the tension value output by the tension sensor is ,in Indicates time; When the tension exceeds the normal range, it indicates that the yarn is in an abnormal state.

4. A textile production process fault monitoring system according to claim 2, characterized in that: The sensor module visual test expression is: The image data at the current moment is , the reference image is ; Define the difference between images As a distance or difference measure between the live image and the reference image: By setting the threshold ,when It may indicate abnormal visual monitoring.

5. A textile production process fault monitoring system according to claim 2, characterized in that: The sensor module sound test expression is: The sound signal captured by the sound sensor is expressed as ,in It's time The sound signal when When the sound signal exceeds the normal range, it means that the sound monitoring has detected an abnormal situation.

6. A textile production process fault monitoring system according to claim 2, characterized in that: The data acquisition module expression is: The data acquisition process is described as real-time recording of tension data: Image data acquisition expression: Image data is collected periodically, and the reference image is : Sound data collection expression: Recording of sound data to establish a sound database: 。 7. A textile production process fault monitoring system according to claim 2, characterized in that: The comprehensive evaluation mechanism in the fault identification and reporting module is expressed as: Assume that the abnormal result output by the monitoring and analysis module is ,in Indicates time; in Represents a set of monitoring data. If any monitoring data is abnormal, is true.

8. A textile production process fault monitoring system according to claim 2, characterized in that: The fault alarm triggering expression in the fault identification and reporting module is: The alarm triggering logic is based on status.

9. A textile production process fault monitoring system according to claim 2, characterized in that: The alarm information expression is: When an alarm occurs, the specific information of the fault can be recorded: time , Fault type and processing results ; 。 10. A textile production process fault monitoring system according to claim 2, characterized in that: The fault record expression in the data recording and analysis module is: When a fault occurs, record the time of the fault , Fault type , the measures taken ; The analysis function expression in the data recording and analysis module is: Frequency calculation: have Fault records, of which Yes Type The number of failures, then the type The failure frequency is estimated to be: Probability distribution fitting: Failures follow a Poisson distribution, so the type In time Internal The probability of failure is expressed as: in Yes Type The average failure rate is estimated from historical data.

Citation Information

Patent Citations

  • Textile production process fault monitoring method, device and system

    CN117171670A

  • Ring spinning broken yarn detection method and system based on image analysis

    CN117779255A

  • Air jet loom data monitoring method, product, equipment and medium

    CN118348923A

  • Clothing intelligent equipment fault intelligent monitoring system

    CN118410389A

Cited By

  • Yarn motion state monitoring method and system

    CN119309628A