Textile equipment fault diagnosis method and system

Abstract

The invention provides a textile equipment fault diagnosis method and system, and belongs to the technical field of data processing, and the method comprises the steps: determining a fabric quality monitoring result based on fabric quality monitoring data; in response to the fact that the fabric quality monitoring result does not contain defect classification information, monitoring operation data of the textile equipment based on a first period; in response to defect classification information contained in the fabric quality monitoring result, determining a first device based on the defect classification information, adjusting a first period corresponding to the first device to obtain a second period, and monitoring operation data of the textile devices based on the first period or the second period corresponding to each textile device; the first period is greater than the second period; and carrying out fault diagnosis on the textile equipment based on the operation data. According to the textile equipment fault diagnosis method and system provided by the invention, the calculated amount of the fault diagnosis process can be reduced.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of data processing, and more particularly, relates to a method and system for fault diagnosis of textile equipment. Background Art

[0002] Textile equipment is various equipment used in the textile process to process natural fibers or chemical fibers into textiles, such as sizing machines, spinning frames, winding machines, etc. With the development of the textile industry towards intelligence and digitization, the requirements for the reliability and stability of equipment are getting higher and higher. As an important support for intelligent production, fault diagnosis technology can realize real-time monitoring and remote diagnosis of textile equipment, and improve the intelligent management level of equipment.

[0003] Existing methods for fault diagnosis of textile equipment usually rely on fault diagnosis models. Inputting the operation data of textile equipment into the fault diagnosis model can obtain the fault diagnosis result. During the operation of textile equipment, a large amount of data is generated, resulting in a large amount of calculation in the fault diagnosis process. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a method and system for fault diagnosis of textile equipment to reduce the amount of calculation in the fault diagnosis process.

[0005] In the first aspect of the embodiments of the present disclosure, a method for fault diagnosis of textile equipment is provided, including: Determining a fabric quality monitoring result based on fabric quality monitoring data; In response to the fabric quality monitoring result not including defect classification information, monitoring the operation data of the textile equipment based on a first period; In response to the fabric quality monitoring result including defect classification information, determining a first device based on the defect classification information, adjusting the first period corresponding to the first device to obtain a second period, and monitoring the operation data of the textile equipment based on the first period or the second period corresponding to each textile equipment; the first period is greater than the second period; Performing fault diagnosis of the textile equipment based on the operation data.

[0006] In the second aspect of the embodiments of the present disclosure, a system for fault diagnosis of textile equipment is provided, including: A first calculation module for determining a fabric quality monitoring result based on fabric quality monitoring data; A first monitoring module for monitoring the operation data of the textile equipment based on a first period in response to the fabric quality monitoring result not including defect classification information; The second monitoring module is configured to, in response to the fabric quality monitoring result including defect classification information, determine a first device based on the defect classification information, adjust a first period corresponding to the first device to obtain a second period, and monitor the operation data of the textile devices based on the first period or the second period corresponding to each textile device; the first period is greater than the second period; The fault diagnosis module is configured to perform fault diagnosis on the textile devices based on the operation data.

[0007] In a third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned textile device fault diagnosis method are implemented.

[0008] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned textile device fault diagnosis method are implemented.

[0009] The beneficial effects of the textile device fault diagnosis method and system provided by the embodiments of the present disclosure are as follows: In the embodiments of the present disclosure, considering that the operating conditions of textile devices are often reflected in the fabric quality, if the fabric quality monitoring result shows no defects, it indicates that the textile devices are currently in a normal operating state. At this time, a relatively large first period can be used to monitor the operation data of the textile devices for routine equipment status checks to ensure their stable operation; if the fabric quality monitoring result shows defects, it indicates that the textile devices may have faults, and it is necessary to reduce the monitoring period of the textile devices. At the same time, considering that different defects may be caused by different equipment faults, therefore, in this embodiment, a first device with a fault is determined based on the defect classification information, and the monitoring period of the first device is reduced, while the monitoring periods of other devices remain unchanged.

[0010] Based on the fabric quality monitoring result, this embodiment automatically adjusts the monitoring period of the textile devices, which can minimize the calculation amount in the fault diagnosis process while ensuring the fault diagnosis effect. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1Schematic flowchart of a textile equipment fault diagnosis method provided by an embodiment of the present disclosure; Figure 2 Block diagram of the structure of a textile equipment fault diagnosis system provided by an embodiment of the present disclosure; Figure 3 Schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0013] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0014] To make the purpose, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0015] Please refer to Figure 1 , Figure 1 Schematic flowchart of a textile equipment fault diagnosis method provided by an embodiment of the present disclosure. The method includes: S101: Determine the fabric quality monitoring result based on the fabric quality monitoring data.

[0016] In this embodiment, the fabric quality monitoring data may include fabric images and fabric performance data. Among them, the fabric images can be collected by a machine vision system, and the fabric performance data includes the yarn tension detected by a tension sensor, the warp and weft density of the fabric detected by a density sensor, and the pH value, formaldehyde content, etc. detected by a chemical property sensor. The above data are collected in real time during the production process.

[0017] By analyzing the fabric quality monitoring data, the fabric quality monitoring result can be obtained. Among them, by analyzing the fabric images, it can be determined whether there are defects on the fabric and the types of defects; by comparing the fabric performance data with the corresponding numerical ranges, it can be determined whether the performance meets the standards. For example, by comparing the tension data with the normal tension range, it can be determined whether the tension is normal.

[0018] S102: In response to the fabric quality monitoring result not including defect classification information, monitor the operation data of the textile equipment based on the first period.

[0019] In this embodiment, the operation data of the textile equipment refers to the speed, temperature, vibration data, sound data, etc. monitored during the operation of the textile equipment. The operation data can reflect the working state and operation characteristics of the equipment. Therefore, based on the operation data of the textile equipment, abnormal conditions of the textile equipment can be detected in a timely manner.

[0020] If the fabric quality monitoring result does not contain defect classification information, it indicates that the fabric has no obvious defects, that is, the fabric quality meets the standard, and the current production state is good. At this time, a relatively large first period can be used to monitor the operation data of the textile equipment for routine equipment status inspection to ensure its stable operation and maintain a good production state.

[0021] S103: In response to the fabric quality monitoring result containing defect classification information, determine the first equipment based on the defect classification information, adjust the first period corresponding to the first equipment to obtain a second period, and monitor the operation data of the textile equipment based on the first period or the second period corresponding to each textile equipment; the first period is greater than the second period.

[0022] In this embodiment, if the fabric quality monitoring result contains defect classification information, it indicates that the textile equipment may have a fault, and different defects may be caused by different equipment faults. For example, fabric warp breakage may be related to faults in the warp system of the warping machine, sizing machine or loom; fabric weft skew may be a problem with the weft insertion system or coiling system of the loom. Therefore, by analyzing the defect classification information, the first equipment that may have a fault can be quickly located.

[0023] On this basis, the first period corresponding to the first equipment can be adjusted by setting a first proportionality coefficient between 0 and 1 to obtain a second period, and the operation data of the first equipment can be monitored based on the second period, that is, the monitoring period of the first equipment is reduced to capture equipment abnormalities in a timely manner. For other equipment outside the first equipment, its monitoring period can be maintained as the first period.

[0024] S104: Perform fault diagnosis on the textile equipment based on the operation data.

[0025] In this embodiment, features that can effectively characterize the operation state of the equipment can be extracted from the historical operation data of the textile equipment. For example, for vibration data, various features such as vibration amplitude, frequency, and phase can be extracted. Then, based on machine learning classification algorithms such as support vector machines, decision trees, random forests, neural networks, etc., the extracted features are trained and classified to establish a fault diagnosis model. On this basis, the operation data of the textile equipment is input into the fault diagnosis model, and a fault diagnosis result can be obtained.

[0026] As can be seen from the above, considering that the operating conditions of textile equipment are often reflected in the fabric quality, if the fabric quality monitoring result shows no defects, it indicates that the textile equipment is currently in normal operation. At this time, a relatively large first period can be used to monitor the operating data of the textile equipment for routine equipment status inspection to ensure its stable operation; if the fabric quality monitoring result shows defects, it indicates that the textile equipment may have a fault, and it is necessary to reduce the monitoring period of the textile equipment. At the same time, considering that different defects may be caused by different equipment faults, therefore, in this embodiment, the first equipment with a fault is determined based on the defect classification information, and the monitoring period of the first equipment is reduced, while the monitoring periods of other equipment remain unchanged.

[0027] In this embodiment, the monitoring period of the textile equipment is automatically adjusted based on the fabric quality monitoring result, which can minimize the calculation amount in the fault diagnosis process while ensuring the fault diagnosis effect.

[0028] In an embodiment of the present disclosure, the fabric quality monitoring data includes fabric images. Determining the fabric quality monitoring result based on the fabric quality monitoring data includes: Identifying the fabric image and determining the fabric quality monitoring result based on the image recognition result.

[0029] In this embodiment, the color, shape, and texture features in the fabric image can be extracted first, and then the decision tree algorithm can be used to construct branches according to different values of the features, and finally the classification of defects can be realized to determine whether there are defects such as broken warp, broken weft, oil stains, and weft skew.

[0030] In an embodiment of the present disclosure, before identifying the fabric image, the textile equipment fault diagnosis method further includes: Calculating the gray standard deviation of the fabric image; If the gray standard deviation of the fabric image is greater than the first threshold, correct the gray level of the fabric image.

[0031] In this embodiment, considering that the working environment of the textile equipment is complex, uneven illumination will cause brightness differences on the fabric surface, which may be misjudged as defects. To solve the above problems, in this application, before identifying the fabric image, the gray standard deviation of the fabric image is calculated first. If the gray standard deviation is greater than the first threshold, it indicates that the degree of dispersion of the pixel gray values in the fabric image is relatively high, and there is a problem of uneven illumination. At this time, it is necessary to correct the gray level of the fabric image. Among them, the first threshold is a preset constant, and those skilled in the art can flexibly design the specific value of the first threshold according to actual needs.

[0032] Specifically, the fabric image can be subjected to histogram equalization processing. By adjusting the gray distribution of the image, the histogram of the image can be made as uniform as possible to achieve gray correction of the fabric image and reduce the influence of uneven illumination.

[0033] As can be seen from the above, before recognizing the fabric image in this embodiment, the gray level of the image is corrected to make the gray level distribution of the image uniform, so that features such as defects can be presented more clearly, facilitating the recognition algorithm to accurately extract features, and further improving the recognition accuracy of defects such as broken warp, broken weft, and oil stains.

[0034] In an embodiment of the present disclosure, correcting the gray level of the fabric image includes: For each first pixel point of the fabric image, count the proportion of second pixel points within the neighborhood range of the first pixel point; the first pixel point is any pixel point, and the second pixel point is a pixel point whose corresponding gray level value is less than the gray level value of the first pixel point; Determine the correction coefficient of the first pixel point based on the proportion of the second pixel points; Correct the gray level value of the first pixel point based on the correction coefficient.

[0035] In this embodiment, a specific implementation manner for correcting the gray level of the fabric image is given. For each pixel point in the image (taking the first pixel point as an example), starting from the column where the first pixel point is located, expand n pixels to the left and right sides respectively, and count the number of pixels whose pixel values are less than the gray level value of the first pixel point within this range (that is, the number of second pixel points). At the same time, starting from the row where the first pixel point is located, expand m pixels upward and downward respectively, and count the number of pixels whose pixel values are less than the gray level value of the first pixel point within this range (that is, the number of second pixel points). The pixel points in the column direction and the row direction form the neighborhood range of the first pixel point. Add the number of second pixel points within the neighborhood range to obtain the total number of second pixel points, and then calculate the proportion of the total number of second pixel points to the total number of pixels within the neighborhood range to obtain the correction coefficient.

[0036] The correction coefficient reflects the relative gray level of the first pixel point within its neighborhood. If the gray level value of a pixel point is significantly higher than most of its surrounding pixels, it indicates that the pixel point is at a relatively high gray level position within its neighborhood, and the correction coefficient will be relatively large, indicating that this point may be affected by factors such as illumination and its gray level value is too high, and a relatively large adjustment is required.

[0037] Specifically, (1 - correction coefficient) can be used as the second proportional coefficient, and the gray level value of the first pixel point is multiplied by the second proportional coefficient to obtain the adjusted gray level value. If the correction coefficient is large, the second proportional coefficient is small, indicating that the gray level value of the first pixel point needs to be reduced to a large extent to make it closer to the gray level of the surrounding pixels; on the contrary, if the correction coefficient is small, the second proportional coefficient is large, and the adjustment range of the gray level value of the first pixel point is small because the difference between the gray level value of this point and the surrounding pixels is small and no large adjustment is required.

[0038] Through the above process, the pixel gray values of the fabric image are adjusted according to the characteristics of the gray distribution, making the pixel values at corresponding positions closer to the same gray level.

[0039] It can be concluded from the above that this embodiment corrects the gray values based on the actual gray situation of the fabric image, rather than treating all gray values indifferently as in histogram equalization. Therefore, when processing images with a low noise level, the method of this embodiment is not likely to over-stretch or enhance the gray values of the noise, thereby reducing the impact of noise on the image quality.

[0040] In an embodiment of the present disclosure, the textile equipment fault diagnosis method further includes: Determining the number of columns n based on the gray standard deviation of the fabric image; wherein, the gray standard deviation of the fabric image is positively correlated with the number of columns n; Determining the number of rows m based on the number of columns n and the aspect ratio of the fabric image; Determining the neighborhood range of the first pixel point based on the number of columns n and the number of rows m.

[0041] In this embodiment, when determining the number of columns n and the number of rows m corresponding to the neighborhood range of the first pixel point, considering that when the gray standard deviation of the fabric image is large, it indicates that the illumination non-uniformity of the fabric image is relatively serious, and there are large areas of light and dark differences. At this time, setting larger values of m and n can perform gray-scale statistics and comparison within a larger neighborhood range, thereby more comprehensively considering the influence of illumination changes and correcting the pixel gray values to achieve overall gray-scale balance.

[0042] Specifically, a third proportionality coefficient greater than zero can be preset, and the product of the gray standard deviation of the fabric image and the third proportionality coefficient is used as the normalized value of the number of columns n, and the specific value of the number of columns n is obtained by multiplying the normalized value of the number of columns n by the width of the fabric image.

[0043] At the same time, considering that for images with different aspect ratios, the information distribution in the row and column directions is different. In order to make the setting of the neighborhood range in the row and column directions more in line with the shape characteristics of the image, in this embodiment, based on determining the number of columns n based on the gray standard deviation of the fabric image, the number of columns n is divided by the aspect ratio of the fabric image to obtain the number of rows m.

[0044] It can be concluded from the above that this embodiment dynamically adjusts the neighborhood range according to the illumination non-uniformity and aspect ratio of different fabric images, making the neighborhood range closely match the actual shape and information distribution of the fabric image, which is beneficial to improving the correction effect of the image gray scale.

[0045] In an embodiment of the present disclosure, fault diagnosis of textile equipment based on operation data includes: If the textile equipment belongs to the first type of equipment, analyze the operation data of the textile equipment based on the multivariate statistical analysis model to obtain the fault diagnosis result of the textile equipment; the first type of equipment is the equipment in which the corresponding multiple operation data are coupled with each other. If the textile equipment belongs to the second type of equipment, analyze the operation data of the textile equipment based on the deep learning model to obtain the fault diagnosis result of the textile equipment; the second type of equipment is the equipment in which the corresponding multiple operation data include multi-source heterogeneous data. If the textile equipment belongs to the third type of equipment, analyze the operation data of the textile equipment based on the physical model to obtain the fault diagnosis result of the textile equipment; the third type of equipment is the equipment in which the proportion of process parameters in the corresponding operation data is greater than the second threshold.

[0046] In this embodiment, the first type of equipment (i.e., the equipment in which multiple operation data are coupled with each other) may include equipment such as blow-room equipment and sizing machines. The operation process of this type of equipment involves multiple interrelated parameters, such as the cotton flow rate, opening degree, and carding intensity of the blow-room equipment, and the slurry concentration, temperature, and sizing rate of the sizing machine. The complex relationships between these parameters will affect the overall operation status of the equipment and the product quality.

[0047] Therefore, for the first type of equipment, a data-driven multivariate statistical analysis model can be used to analyze the operation data of the textile equipment. The multivariate statistical analysis model includes methods such as principal component analysis (PCA) and partial least squares (PLS). The data can be processed and analyzed through the above methods to calculate the correlation and statistical characteristics between each variable. By comparing with the data characteristics in the normal operation state, if it is found that the distribution, correlation, etc. of the data have changed significantly, it can be judged that the equipment may have a fault.

[0048] The second type of equipment (i.e., the equipment in which the corresponding multiple operation data include multi-source heterogeneous data) may include spinning frames, winding machines, automatic reeling machines, etc. During the operation of the above equipment, it is necessary to sense and process information in multiple dimensions, such as mechanical vibration, electrical signals, and yarn quality parameters. The deep learning model can effectively fuse these multi-source heterogeneous data, extract more comprehensive and representative features, and improve the accuracy and reliability of fault diagnosis.

[0049] Therefore, for the second type of equipment, the operation data of the textile equipment can be analyzed based on the deep learning model. The deep learning model (such as convolutional neural network, recurrent neural network, etc.) can automatically learn valuable features from complex data without the need for complex feature engineering by humans.

[0050] The third type of equipment (i.e., equipment in which the proportion of process parameters in the operation data is greater than the second threshold) may include dyeing machines, steaming machines, setting machines, etc. The working principles of the above-mentioned equipment are mainly based on specific physical processes, such as the thermodynamic and hydrodynamic processes of dyeing machines, the wet heat transfer process of steaming machines, the heat setting process of setting machines, etc. These physical processes play a decisive role in the operation of the equipment and the product quality. Therefore, the operation state of the equipment can be described and analyzed by establishing a physical model. Among them, the second threshold is a preset constant, and those skilled in the art can set the specific value of the second threshold according to the characteristics of the equipment and historical operation data.

[0051] The physical model is a mathematical model established based on the physical principles and working mechanisms of the equipment. For the third type of equipment, since the proportion of process parameters in the operation data is relatively large, these process parameters are closely related to the physical characteristics and working processes of the equipment. By establishing a physical model, the operation state and performance of the equipment can be accurately described. For example, for a dyeing machine, a model based on physical principles such as heat conduction and chemical reactions can be established to describe the influence of process parameters such as temperature, time, and dye concentration on the dyeing effect during the dyeing process.

[0052] It can be concluded from the above that in this embodiment, different methods are used to construct a fault diagnosis model for different types of textile equipment, which can give full play to the advantages of various methods and capture fault information in the equipment operation data more accurately.

[0053] In an embodiment of the present disclosure, the fault diagnosis result of the textile equipment includes the fault type and the corresponding confidence level. The textile equipment fault diagnosis method further includes: Search for the first mapping relationship based on the fault type to obtain the risk level corresponding to the fault type; Sort multiple fault types based on the risk level corresponding to the fault type and the confidence level, and output the sorting result.

[0054] In this embodiment, in addition to outputting the fault type, the fault diagnosis model can also output the corresponding confidence level. The confidence level reflects the reliability of the fault diagnosis result. If the confidence level corresponding to a certain fault type is low, it indicates that the fault characteristics are not obvious, and it can be further detected and verified before processing to avoid resource waste caused by misjudgment; if the confidence level corresponding to a certain fault type is high, it indicates that the diagnosis result is highly credible, and targeted maintenance work can be carried out immediately based on the diagnosis result. Therefore, the order of fault repair can be determined according to the confidence level corresponding to the fault type.

[0055] At the same time, considering that the risk levels corresponding to each fault type are different, in order to ensure that faults with high risk levels are processed first, this embodiment comprehensively considers the confidence level and risk level to sort multiple fault types, and the staff can determine the order of fault repair based on the sorting result.

[0056] Specifically, based on a large amount of historical data, expert experience, and industry standards in advance, a first mapping relationship between fault types and risk levels can be established. The first mapping relationship can be in the form of a table or a data structure stored in a database. For example, a broken yarn fault corresponds to a low risk level because it is relatively easy to repair and has a small impact on production; while the damage of key mechanical components may correspond to a high risk level because this may cause the equipment to stop for a long time, seriously affecting the production schedule and product quality.

[0057] From the above, it can be concluded that in this embodiment, by comprehensively considering the risk level and confidence level to sort the fault types, faults with a high risk level and a high confidence level can be processed preferentially.

[0058] In an embodiment of the present disclosure, sorting multiple fault types based on the risk level and confidence level corresponding to the fault types includes: Determining a first sorting number of the fault type based on the risk level corresponding to the fault type; For fault types with the same first sorting number, determining a second sorting number of the fault type based on the confidence level corresponding to the fault type; Sorting the fault types based on the second sorting number and the second sorting number.

[0059] In this embodiment, first, overall sorting of each fault type is performed according to the first sorting number, which can ensure that high-risk faults are ranked at the top; for fault types with the same first sorting number, refined sorting is then performed according to the second sorting number. The above sorting method fully considers both the severity of the faults and the reliability of the diagnostic results, making the sorting results more in line with the actual needs of textile equipment.

[0060] In an embodiment of the present disclosure, the fabric quality monitoring data includes fabric performance data, and determining the fabric quality monitoring result based on the fabric quality monitoring data includes: Comparing the fabric performance data with the corresponding numerical range to determine the fabric quality monitoring result.

[0061] In this embodiment, the fabric performance data includes yarn tension, fabric warp and weft density, and pH value, formaldehyde content, etc. detected by chemical performance sensors. Comparing the fabric performance data obtained by real-time detection with the preset numerical range one by one can obtain the corresponding fabric quality monitoring result. Taking the tensile strength as an example, if the data is between the set minimum value and maximum value, it is determined that the fabric is qualified in this performance; if the color fastness test result is equal to or higher than the standard value, it indicates that the color fastness meets the standard. As long as one piece of performance data exceeds or does not reach the corresponding numerical range, it indicates that there are quality defects in this aspect of the fabric, and the corresponding defect classification information can be output.

[0062] It can be concluded from the above that in this embodiment, the corresponding evaluation method is determined based on the characteristics of different performance data, and the fabric quality monitoring result is obtained, making the interpretability of the fabric quality monitoring result stronger.

[0063] Corresponding to the textile equipment fault diagnosis method in the above embodiment, Figure 2 is a structural block diagram of a textile equipment fault diagnosis system provided by an embodiment of the present disclosure. For ease of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 The textile equipment fault diagnosis system 20 includes: a first calculation module 21, a first monitoring module 22, a second monitoring module 23, and a fault diagnosis module 24. Among them, the first calculation module 21 is used to determine the fabric quality monitoring result based on the fabric quality monitoring data; The first monitoring module 22 is used to monitor the operation data of the textile equipment based on the first period in response to the fact that the fabric quality monitoring result does not include defect classification information; The second monitoring module 23 is used to determine the first device based on the defect classification information in response to the fact that the fabric quality monitoring result includes defect classification information, adjust the first period corresponding to the first device to obtain the second period, and monitor the operation data of the textile equipment based on the first period or the second period corresponding to each textile equipment; the first period is greater than the second period; The fault diagnosis module 24 is used to perform fault diagnosis on the textile equipment based on the operation data.

[0064] In an embodiment of the present disclosure, the fabric quality monitoring data includes a fabric image, and the first calculation module 21 is specifically used for: Identify the fabric image and determine the fabric quality monitoring result based on the image recognition result.

[0065] In an embodiment of the present disclosure, before identifying the fabric image, the first calculation module 21 is specifically further used for: Calculate the gray standard deviation of the fabric image; If the gray standard deviation of the fabric image is greater than the first threshold, correct the gray level of the fabric image.

[0066] In an embodiment of the present disclosure, the first calculation module 21 is specifically further used for: For each first pixel point of the fabric image, count the proportion of second pixel points within the neighborhood range of the first pixel point; the first pixel point is any pixel point, and the second pixel point is a pixel point with a gray value less than the gray value of the first pixel point; Determine the correction coefficient of the first pixel point based on the proportion of the second pixel points; Correct the gray value of the first pixel point based on the correction coefficient.

[0067] In one embodiment of the present disclosure, the fault diagnosis module 24 is specifically configured to: If the textile equipment belongs to the first type of equipment, analyze the operation data of the textile equipment based on a multivariate statistical analysis model to obtain a fault diagnosis result of the textile equipment; the first type of equipment is equipment in which multiple corresponding operation data are coupled with each other; If the textile equipment belongs to the second type of equipment, analyze the operation data of the textile equipment based on a deep learning model to obtain a fault diagnosis result of the textile equipment; the second type of equipment is equipment in which multiple corresponding operation data include multi-source heterogeneous data; If the textile equipment belongs to the third type of equipment, analyze the operation data of the textile equipment based on a physical model to obtain a fault diagnosis result of the textile equipment; the third type of equipment is equipment in which the proportion of process parameters in the corresponding operation data is greater than a second threshold.

[0068] In one embodiment of the present disclosure, the fault diagnosis result of the textile equipment includes a fault type and a corresponding confidence level. The fault diagnosis module 24 is further specifically configured to: Search for a first mapping relationship based on the fault type to obtain a risk level corresponding to the fault type; Sort multiple fault types based on the risk level corresponding to the fault type and the confidence level, and output a sorting result.

[0069] In one embodiment of the present disclosure, the fabric quality monitoring data includes fabric performance data. The first calculation module 21 is specifically configured to: Compare the fabric performance data with a corresponding numerical range to determine a fabric quality monitoring result.

[0070] See Figure 3 , Figure 3 which is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 3 shown, the electronic device 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 the functions of the modules 21 to 24 shown.

[0071] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0072] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0073] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0074] In specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may implement the implementation manners described in the first embodiment and the second embodiment of the textile equipment fault diagnosis method provided by the embodiments of the present disclosure, and may also implement the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated herein.

[0075] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0076] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0077] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0078] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0079] In several embodiments provided by the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between each other can be an indirect coupling or communication connection through some interfaces or units, or can also be an electrical, mechanical or other form of connection.

[0080] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.

[0081] In addition, in each embodiment of the present disclosure, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0082] The above are only the specific implementation manners of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A textile equipment fault diagnosis method, characterized in that: include: determining fabric quality monitoring results based on the fabric quality monitoring data; In response to the fabric quality monitoring result not including defect classification information, monitoring operation data of the textile equipment based on the first cycle; In response to the fabric quality monitoring result containing defect classification information, a first device is determined based on the defect classification information, a first cycle corresponding to the first device is adjusted to obtain a second cycle, and operation data of the textile device is monitored based on the first cycle or the second cycle corresponding to each textile device; the first cycle is greater than the second cycle; Fault diagnosis of the textile equipment is performed based on the operating data.

2. The textile equipment fault diagnosis method according to claim 1, characterized in that: The fabric quality monitoring data includes a fabric image, and determining the fabric quality monitoring result based on the fabric quality monitoring data includes: The fabric image is recognized, and the fabric quality monitoring result is determined based on the image recognition result.

3. The textile equipment fault diagnosis method according to claim 2, characterized in that: Before identifying the fabric image, the textile equipment fault diagnosis method further includes: Calculating the grayscale standard deviation of the fabric image; If the grayscale standard deviation of the fabric image is greater than a first threshold, the grayscale of the fabric image is corrected.

4. The textile equipment fault diagnosis method according to claim 3, characterized in that: The grayscale correction of the fabric image comprises: For each first pixel point of the fabric image, the proportion of second pixels within the neighborhood of the first pixel point is counted; the first pixel point is any pixel point, and the second pixel point is a pixel point whose corresponding grayscale value is less than the grayscale value of the first pixel point; Determine a correction coefficient of the first pixel based on the proportion of the second pixel; The grayscale value of the first pixel is corrected based on the correction coefficient.

5. The textile equipment fault diagnosis method according to claim 1, characterized in that: The fault diagnosis of the textile equipment based on the operation data comprises: If the textile equipment belongs to the first type of equipment, the operation data of the textile equipment is analyzed based on a multivariate statistical analysis model to obtain a fault diagnosis result of the textile equipment; the first type of equipment is a device whose corresponding multiple operation data are coupled to each other; If the textile equipment belongs to the second type of equipment, the operating data of the textile equipment is analyzed based on the deep learning model to obtain a fault diagnosis result of the textile equipment; the second type of equipment is a device whose corresponding multiple operating data contain multi-source heterogeneous data; If the textile equipment belongs to the third category of equipment, the operating data of the textile equipment is analyzed based on the physical model to obtain a fault diagnosis result of the textile equipment; the third category of equipment is equipment in which the proportion of process parameters in the corresponding operating data is greater than a second threshold.

6. The textile equipment fault diagnosis method according to claim 5, characterized in that: The fault diagnosis result of the textile equipment includes a fault type and a corresponding confidence level, and the textile equipment fault diagnosis method further includes: Searching a first mapping relationship based on the fault type to obtain a risk level corresponding to the fault type; The plurality of fault types are sorted based on the risk levels and confidence levels corresponding to the fault types, and the sorting result is output.

7. The textile equipment fault diagnosis method according to claim 1, characterized in that: The fabric quality monitoring data includes fabric performance data, and the fabric quality monitoring result is determined based on the fabric quality monitoring data, including: Compare the fabric performance data with the corresponding value range to determine the fabric quality monitoring results.

8. A textile equipment fault diagnosis system, characterized in that: include: A first calculation module, used to determine a fabric quality monitoring result based on the fabric quality monitoring data; A first monitoring module, configured to monitor the operation data of the textile equipment based on a first cycle in response to the fabric quality monitoring result not including defect classification information; A second monitoring module is configured to, in response to the defect classification information included in the fabric quality monitoring result, determine the first device based on the defect classification information, adjust the first cycle corresponding to the first device to obtain the second cycle, and monitor the operation data of the textile device based on the first cycle or the second cycle corresponding to each textile device; the first cycle is greater than the second cycle; A fault diagnosis module is used to perform fault diagnosis of the textile equipment based on the operation data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images