Intelligent diagnosis method for textile equipment failure

Abstract

The application discloses a kind of textile equipment fault intelligent diagnosis methods, it is related to textile equipment fault diagnosis technical field, comprising the following steps: according to the working characteristics and historical data of spinning frame spindle, set an initial monitoring frequency, ensure that the basic running condition of spinning frame spindle is covered;In monitoring period T, the running data of spinning frame spindle is collected in real time, after abnormal analysis processing is carried out to running data, establish abnormal monitoring mechanism through the data after abnormal analysis processing.The application sets initial monitoring frequency, collects and analyzes running data, establishes abnormal monitoring mechanism, carries out intelligent diagnosis to spinning frame spindle, generates hidden trouble occurrence coefficient according to the vibration amplitude ratio and strain rate data of different frequency bands, and divides hidden danger into high, medium and low risk, takes different monitoring frequency, effectively solves data excess and false alarm problem, ensures diagnostic accuracy, improves diagnostic accuracy and efficiency, reduces maintenance cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of textile equipment fault diagnosis, and particularly relates to a textile equipment fault intelligent diagnosis method. BACKGROUND

[0002] Textile equipment refers to mechanical equipment used in spinning, weaving and subsequent processing of textile processes, including key components such as spindles and rollers of spinning machines, shuttles and harnesses of looms, and mangle and steaming box in dyeing and finishing equipment. These devices realize efficient production and processing from raw material fibers to finished fabrics through the comprehensive operation of mechanical, electronic and control systems.

[0003] Textile equipment fault intelligent diagnosis is a system that uses advanced technical means to automatically detect and analyze faults that occur during the operation of textile equipment. By integrating sensors, data acquisition devices and artificial intelligence algorithms, the system can monitor the running state of the equipment in real time, collect relevant data and analyze it, so as to identify abnormal conditions of the equipment in time and give corresponding fault diagnosis and maintenance suggestions. This intelligent diagnosis system can greatly improve the maintenance efficiency of textile equipment, reduce downtime and improve the overall production efficiency of the production line.

[0004] The most core component of textile equipment is the spindle of the spinning machine. The spindle plays a key role in the spinning process, which twists the fiber bundle into yarn through high-speed rotation, and determines the evenness and strength of the yarn. Its precise design and manufacturing quality directly affect the spinning efficiency and yarn quality, and is an indispensable key component in textile production.

[0005] The prior art has the following disadvantages:

[0006] When the prior art performs intelligent fault diagnosis on the spindle of the spinning machine, it usually uses a fixed monitoring frequency to monitor the spindle of the spinning machine in real time. When the monitoring frequency is set too high, a large amount of data will be generated during the normal operation of the spindle of the spinning machine. These data need to be stored and processed, which occupies a large amount of storage space and computing resources. Moreover, the high-frequency collected data is easily affected by environmental noise and transient fluctuations, resulting in a high false alarm rate, which increases unnecessary maintenance workload and cost. When the monitoring frequency is set too low, if the spindle of the spinning machine has running abnormalities, the low-frequency collected data samples are insufficient, which may not fully reflect the running state of the equipment, resulting in a decrease in diagnosis accuracy and difficulty in accurately identifying fault patterns.

[0007] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0008] The application aims to provide a spinning machine spindle running state intelligent sensing method, which establishes an abnormal monitoring mechanism by setting an initial monitoring frequency and collecting running data in a monitoring period, and performing abnormal analysis and processing, realizes the intelligent sensing of the spinning machine spindle running state, and comprehensively considers the vibration amplitude ratio information and strain rate data information of different frequency bands to generate a hidden fault occurrence coefficient, compares and analyzes the hidden fault occurrence coefficient, divides the abnormal running hidden danger into high risk, general risk and low risk, and takes different monitoring frequency strategies for targeted monitoring, effectively solves the data overload and false alarm problem caused by high-frequency monitoring, and still guarantees the diagnosis accuracy under low-frequency monitoring, dynamically adjusts the monitoring frequency, improves the accuracy and efficiency of fault diagnosis, and reduces the maintenance cost, to solve the problems in the above background art.

[0009] To achieve the above-mentioned purpose, the application provides the following technical scheme: a spinning machine spindle running state intelligent sensing method, comprising the following steps:

[0010] According to the working characteristics and historical data of the spinning machine spindle, an initial monitoring frequency is set to ensure that the basic running state of the spinning machine spindle is covered;

[0011] In a monitoring period T, the running data of the spinning machine spindle is collected in real time, the running data is subjected to abnormal analysis and processing, and an abnormal monitoring mechanism is established through the data after abnormal analysis and processing to intelligently sense the abnormal running hidden danger of the spinning machine spindle;

[0012] When the abnormal running of the spinning machine spindle is sensed, the abnormal running hidden danger of the spinning machine spindle is divided into high-risk running hidden danger, general-risk running hidden danger and low-risk running hidden danger;

[0013] For the low-risk running hidden danger, the running state of the spinning machine spindle is continuously monitored based on the initial monitoring frequency, for the general-risk running hidden danger, the monitoring frequency is increased for medium-density data acquisition to observe the development of potential problems, and for the high-risk running hidden danger, the monitoring frequency is increased for high-density data acquisition to ensure that more detailed fault information is captured.

[0014] Preferably, the running data of the spinning machine spindle includes vibration amplitude ratio information and strain rate data information of different frequency bands, the vibration amplitude ratio information and strain rate data information of different frequency bands are subjected to abnormal analysis and processing, and a frequency band vibration amplitude ratio increment index and a strain rate rising gradient index are generated, an abnormal monitoring mechanism is established through the frequency band vibration amplitude ratio increment index and the strain rate rising gradient index to generate a hidden fault occurrence coefficient, and the abnormal running hidden danger of the spinning machine spindle is intelligently sensed.

[0015] Preferably, the invisible fault occurrence coefficient generated in the monitoring period T when the spinning machine spindle is running is compared and analyzed with the preset invisible fault occurrence coefficient reference threshold value, if the invisible fault occurrence coefficient is greater than or equal to the invisible fault occurrence coefficient reference threshold value, a hidden danger signal is generated, and if the invisible fault occurrence coefficient is less than the invisible fault occurrence coefficient reference threshold value, an efficient signal is generated.

[0016] Preferably, when the spinning machine spindle running generates a hidden danger signal, the invisible fault occurrence coefficient is compared and analyzed with the first reference threshold value and the second reference threshold value, wherein the first reference threshold value is less than the second reference threshold value, and the invisible fault occurrence coefficient reference threshold value is less than the first reference threshold value, the abnormal running hidden danger of the spinning machine spindle is divided into high-risk running hidden danger, general-risk running hidden danger and low-risk running hidden danger, and the specific division steps are as follows:

[0017] If the invisible fault occurrence coefficient is greater than or equal to the invisible fault occurrence coefficient reference threshold value and less than the first reference threshold value, the abnormal running hidden danger of the spinning machine spindle is divided into low-risk running hidden danger;

[0018] If the invisible fault occurrence coefficient is greater than or equal to the first reference threshold value and less than the second reference threshold value, the abnormal running hidden danger of the spinning machine spindle is divided into general-risk running hidden danger;

[0019] If the invisible fault occurrence coefficient is greater than or equal to the second reference threshold value, the abnormal running hidden danger of the spinning machine spindle is divided into high-risk running hidden danger.

[0020] Preferably, for the general-risk running hidden danger, the monitoring frequency is improved to carry out medium-density data acquisition, and the specific steps are as follows:

[0021] The invisible fault occurrence coefficient under the general-risk running hidden danger is obtained, and the actual monitoring frequency under the general-risk running hidden danger is regulated based on the invisible fault occurrence coefficient, the first reference threshold value, the second reference threshold value and the initial monitoring frequency, and the regulation formula is: F x1 The actual monitoring frequency under the general-risk running hidden danger is represented, f0 represents the initial monitoring frequency, Fault ξ The invisible fault occurrence coefficient under the general-risk running hidden danger is represented, θ1 represents the first reference threshold value, and θ2 represents the second reference threshold value.

[0022] Preferably, for the high-risk running hidden danger, the monitoring frequency is improved to carry out high-density data acquisition, and the specific steps are as follows:

[0023] The invisible fault occurrence coefficient under the high-risk running hidden danger is obtained, and the actual monitoring frequency under the high-risk running hidden danger is regulated based on the invisible fault occurrence coefficient, the second reference threshold value and the initial monitoring frequency, and the regulation formula is: Fx2 represents the actual monitoring frequency under high-risk operation hidden danger, f0 represents the initial monitoring frequency, Fault ξ represents the hidden failure occurrence coefficient under high-risk operation hidden danger, q is an adjustment coefficient.

[0024] Preferably, after the abnormal analysis processing of the obtained vibration amplitude ratio information of different frequency bands, the step of generating the frequency band vibration amplitude ratio increment index is as follows:

[0025] In the monitoring period T, real-time collection of vibration signal data of different frequency bands of the spinning reel is performed, the vibration signal is divided into a plurality of time windows, and the length of each time window is Δt, wherein Δt satisfies T=m·Δt, and m is the total number of time windows.

[0026] Fast Fourier transform is performed on the signal in each time window, and the value of the frequency domain signal at the kth frequency component index is calculated, and the calculation expression is: Wherein, X k represents the value of the frequency domain signal at the kth frequency component index, x n represents the vibration signal of the nth sampling point in the time window, N represents the total number of sampling points in the time window, k represents the frequency component index, and j represents the imaginary unit.

[0027] The value X k of the frequency domain signal at the kth frequency component index is divided into several frequency bands, the vibration amplitude of each frequency band is calculated, and the calculation expression is: Wherein, A i represents the vibration amplitude of the ith frequency band, F i represents the frequency component index set contained in the ith frequency band, and |X k | represents the amplitude of the frequency domain signal at the kth frequency component index.

[0028] The vibration amplitude ratio of adjacent frequency bands is calculated, and the calculation expression is: In the formula, R i，i+1 represents the vibration amplitude ratio of the ith frequency band to the ith+1 frequency band, A i+1 represents the vibration amplitude of the ith+1 frequency band.

[0029] Abnormal analysis is performed on the obtained frequency band vibration amplitude ratio, the frequency band vibration amplitude ratio is compared and analyzed with the pre-set frequency band vibration amplitude ratio reference threshold, the abnormal points are identified, and the abnormal points are marked as R' i，i+1 , then: R' i，i+1 ={R i，i+1 |R i，i+1 >θ}, wherein θ represents the frequency band vibration amplitude ratio reference threshold.

[0030] For the abnormal point, the change amount of the vibration amplitude ratio of the same frequency band in the adjacent time window is calculated, and the expression for calculation is: ΔR' i，i+1 (t)=R' i，i+1 (t)-R' i，i+1 (t-1), wherein ΔR' i，i+1 (t) represents the frequency band vibration amplitude ratio increment of the abnormal point at time t, R' i，i+1 (t) represents the frequency band vibration amplitude ratio of the abnormal point at time t, R' i，i+1 (t-1) represents the frequency band vibration amplitude ratio of the abnormal point at time t-1.

[0031] The frequency band vibration amplitude ratio increment index is calculated, and the expression for calculation is: wherein Vb A represents the frequency band vibration amplitude ratio increment index, w i represents the weight factor of the i-th frequency band, and M represents the total number of frequency bands.

[0032] Preferably, after the abnormal analysis and processing of the obtained strain rate data information, the steps of generating the strain rate rising gradient index are as follows:

[0033] In the monitoring period T, a fixed time interval Δt' is set for data acquisition, and a strain rate data sequence is obtained wherein u is the index of the acquisition time, u=1, 2, …, y,

[0034] The strain rate change rate in each time interval Δt' is calculated, and the expression for calculation is: wherein represents the strain rate change amount in the u-th time interval;

[0035] The strain rate change amount is compared and analyzed with the pre-set strain rate change amount reference threshold value, and the abnormal strain rate change point is identified, specifically: wherein λ represents the index set of all time intervals identified as abnormal, and μ represents the strain rate change amount reference threshold value;

[0036] The strain rate rising gradient index is calculated, and the expression for calculation is: wherein G v represents the strain rate rising gradient index, and |λ| represents the number of elements in the set λ, that is, the number of abnormal strain rate change points identified.

[0037] In the above technical solution, the technical effects and advantages provided by the present application are as follows:

[0038] The application establishes an abnormal monitoring mechanism by setting an initial monitoring frequency and collecting operation data in a monitoring period, performing abnormal analysis processing, realizing intelligent perception of the running state of the spinning machine spindle, the method comprehensively considers vibration amplitude ratio information and strain rate data information of different frequency bands, generates a hidden fault occurrence coefficient, compares and analyzes the hidden fault occurrence coefficient, divides the abnormal operation hidden danger into high risk, general risk and low risk, and respectively takes different monitoring frequency strategies for targeted monitoring, effectively solves the problems of data excess and false alarm caused by high-frequency monitoring, and still guarantees the diagnosis accuracy under low-frequency monitoring, through dynamic adjustment of the monitoring frequency, the accuracy and efficiency of fault diagnosis are improved, and the maintenance cost is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art according to these drawings.

[0040] Figure 1 The method flow chart of the intelligent fault diagnosis method of the textile equipment. DETAILED DESCRIPTION

[0041] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these example implementations are provided so that this disclosure will be thorough and complete, and will fully convey the inventive aspects of the example implementations to those skilled in the art. Like reference numerals may refer to like elements throughout the description of the figures.

[0042] The present application provides an intelligent fault diagnosis method for textile equipment as shown in Figure 1 The present application provides an intelligent fault diagnosis method for textile equipment as shown in

[0043] According to the working characteristics and historical data of the spinning machine spindle, an initial monitoring frequency is set to ensure that the basic operation of the spinning machine spindle is covered;

[0044] When formulating the monitoring strategy of the spinning machine spindle, first, the working characteristics of the spinning machine spindle need to be understood in depth, including the speed, load, vibration mode and temperature change and other key parameters. These characteristics determine the normal running state and potential failure mode of the spindle. At the same time, by analyzing the historical operation data of the spindle, including long-term monitoring records and past fault data, common fault types and occurrence rules can be identified. Based on this information, an initial monitoring frequency is determined to balance between data collection and resource consumption.

[0045] The selection of the initial monitoring frequency needs to balance the comprehensiveness of data acquisition and the efficiency of system resource use, both to capture potential fault signals in time and to ensure the safe operation of the equipment, and to avoid data redundancy, increased processing burden and waste of storage resources due to excessively high frequency.

[0046] In the monitoring period T, the running data of the spinning machine spindle is collected in real time, and after abnormal analysis and processing of the running data, an abnormal monitoring mechanism is established through the data after abnormal analysis and processing to intelligently perceive the abnormal running hidden danger of the spinning machine spindle.

[0047] The monitoring duration in the monitoring period T remains equal. The effect of keeping the monitoring duration equal in the monitoring window is to ensure that the collected data is consistent and comparable, thereby improving the accuracy and reliability of abnormal analysis. By monitoring in the same time window, the influence of data fluctuations and environmental interference can be effectively reduced, enabling the abnormal detection algorithm to more accurately identify the abnormal running mode and hidden danger of the spinning machine spindle, and thus realize intelligent fault warning and diagnosis. This consistent monitoring duration also helps to establish a more robust abnormal monitoring mechanism to ensure the monitoring effect of the equipment under different running states;

[0048] The running data of the spinning machine spindle includes vibration amplitude ratio information and strain rate data information of different frequency bands. After abnormal analysis and processing of the obtained vibration amplitude ratio information and strain rate data information of different frequency bands, frequency band vibration amplitude ratio increment indexes and strain rate rising gradient indexes are generated, and an abnormal monitoring mechanism is established through the frequency band vibration amplitude ratio increment indexes and strain rate rising gradient indexes to generate a hidden fault occurrence coefficient, and the abnormal running hidden danger of the spinning machine spindle is intelligently perceived.

[0049] In the monitoring period T, the vibration amplitude ratio of the spinning machine spindle in the frequency band has a larger increment, which usually indicates that the spinning machine spindle has hidden problems of abnormal operation. The significant increase in the vibration amplitude ratio means that the vibration intensity of the spindle in certain frequency bands is much higher than the normal level, which may be caused by various mechanical problems such as imbalance, poor shaft alignment, bearing failure or poor gear engagement, etc. These problems can cause significant changes in the vibration characteristics of the spindle, thereby increasing the increment of the vibration amplitude ratio. Specifically, imbalance can cause the spindle to produce larger vibrations at its rotational frequency, while poor shaft alignment can cause an increase in the multiple frequency vibrations. Bearing failure can produce characteristic vibration signals at high frequencies, and gear engagement problems can exhibit abnormal vibration amplitudes at the gear engagement frequency and its harmonic frequencies. These abnormal changes in vibration characteristics not only affect the normal operation of the spinning machine spindle, but also can accelerate the wear and damage of mechanical parts, leading to frequent equipment failures and even safety hazards. Therefore, monitoring the increment of the vibration amplitude ratio in the frequency band can be an important indicator for early detection of abnormal operation of the spinning machine spindle. By identifying and addressing these hidden problems in a timely manner, serious failures can be effectively prevented.

[0050] After abnormal analysis and processing of the acquired vibration amplitude ratio information in different frequency bands, the step of generating the frequency band vibration amplitude ratio increment index is as follows:

[0051] In the monitoring period T, the vibration signal data of the spinning machine spindle in different frequency bands is collected in real time, and the vibration signal is divided into multiple time windows, each time window has a length of Δt, where Δt satisfies T = m Δt, m is the total number of time windows;

[0052] The vibration signal data of the spinning machine spindle refers to the mechanical vibration information generated by the equipment during operation. These data are usually represented in the form of acceleration, speed or displacement. The acquisition of vibration signal data can be achieved in various ways, including the installation of high-precision measurement devices such as accelerometers, speed sensors or displacement sensors. These sensors can be installed at key positions of the spinning machine spindle and transmit signals to the data acquisition system through cables or wireless means for real-time monitoring and recording. The signals collected by the sensors are converted into digital signals, which can be used for further frequency domain analysis and fault diagnosis.

[0053] The signals in each time window are subjected to Fast Fourier Transform (FFT) to calculate the value of the frequency domain signal at the kth frequency component index, and the expression is: where X k represents the value of the frequency domain signal at the kth frequency component index, x n represents the vibration signal at the nth sampling point in the time window, N represents the total number of sampling points in the time window, k represents the frequency component index, and j represents the imaginary unit;

[0054] X(k) represents the value of the frequency domain signal at the kth frequency component index k The frequency domain signal is divided into several frequency bands, and the vibration amplitude of each frequency band is calculated, and the expression is: Wherein, A i represents the vibration amplitude of the i-th frequency band, F i represents the frequency component index set contained in the i-th frequency band, |X k | represents the amplitude of the frequency domain signal at the kth frequency component index;

[0055] The vibration amplitude ratio of adjacent frequency bands is calculated, and the expression is: Wherein, R i，i+1 represents the vibration amplitude ratio of the i-th frequency band and the i+1-th frequency band, A i+1 represents the vibration amplitude of the i+1-th frequency band;

[0056] The obtained frequency band vibration amplitude ratio is analyzed for abnormalities, and the frequency band vibration amplitude ratio is compared and analyzed with the pre-set frequency band vibration amplitude ratio reference threshold, and the abnormal points are identified and marked as R' i，i+1 , then: R' i，i+1 ={R i，i+1 |R i，i+1 >θ}, wherein θ represents the frequency band vibration amplitude ratio reference threshold;

[0057] For abnormal points, the change amount of the same frequency band vibration amplitude ratio in the adjacent time window is calculated, and the expression is: ΔR' i，i+1 (t) = R' i，i+1 (t) - R' i，i+1 (t-1), wherein ΔR' i，i+1 (t) represents the frequency band vibration amplitude ratio increment of the abnormal point at time t, R' i，i+1 (t) represents the frequency band vibration amplitude ratio of the abnormal point at time t, and R' i，i+1 (t-1) represents the frequency band vibration amplitude ratio of the abnormal point at time t-1.

[0058] The frequency band vibration amplitude ratio increment index is calculated, and the expression is: Wherein, Vb A represents the frequency band vibration amplitude ratio increment index, w i represents the weight factor of the i-th frequency band, which is set according to the importance or sensitivity of the frequency band, and M represents the total number of frequency bands.

[0059] From the frequency band vibration amplitude ratio increment index, it can be seen that in the monitoring period T, the greater the performance value of the frequency band vibration amplitude ratio increment index generated by the spindle running of the spinning machine, the greater the hidden danger of the abnormal state of the spindle running of the spinning machine, and vice versa.

[0060] If the strain rate rise gradient of the spinning spindle is large within the monitoring period T, it usually indicates that the spinning spindle has potential problems of abnormal operation. The strain rate rise gradient reflects the change of the material deformation rate, and when the strain rate rises significantly, it may indicate that the spinning spindle is subjected to excessive stress or strain, which is usually related to mechanical failure, material fatigue, poor lubrication, etc. Abnormal increase in the strain rate rise gradient will lead to accelerated wear and structural damage of the spindle components, thereby affecting the operation stability and service life of the equipment. Specifically, a large strain rate rise gradient can be caused by various reasons. For example, mechanical imbalance or misalignment can cause periodic stress changes in the spindle during operation, thereby increasing the strain rate. Wear and insufficient lubrication of bearings or gears can also increase friction, causing the strain rate to rise. In addition, fatigue cracks and aging phenomena of the material itself can also cause the strain rate to increase. Therefore, a large strain rate rise gradient is an important early warning signal that the spinning spindle may have potential failures.

[0061] After abnormal analysis and processing of the obtained strain rate data information, the strain rate rise gradient index is generated as follows:

[0062] Within the monitoring period T, set a fixed time interval Δt' for data collection, and obtain the strain rate data sequence where u is the index of the collection time, u = 1, 2, …, y,

[0063] Strain gauges are commonly used strain measurement tools that can directly measure the strain rate of the spinning spindle. Strain gauges are installed at key positions of the spinning spindle, usually in areas where stress is concentrated. Strain gauges are made of thin metal foil, and when the spindle deforms, the resistance value of the metal foil changes. The resistance change is converted into a voltage signal by a Wheatstone bridge circuit, and the voltage signal is collected and processed by a data acquisition system to monitor the strain signal in real time, and the strain rate data is calculated.

[0064] The strain rate change rate in each time interval Δt' is calculated, and the calculation expression is: where represents the strain rate change in the u-th time interval;

[0065] The strain rate change is compared and analyzed with the pre-set strain rate change reference threshold to identify abnormal strain rate change points, specifically: where λ represents the index set of all time intervals identified as abnormal, and μ represents the strain rate change reference threshold;

[0066] The strain rate rising gradient index is calculated, and the expression is: In the formula, G v represents the strain rate rising gradient index, and |λ| represents the number of elements in the set λ, that is, the number of abnormal strain rate change points identified.

[0067] According to the strain rate rising gradient index, the greater the performance value of the strain rate rising gradient index generated by the spinning machine spindle during the monitoring period T, the greater the hidden danger of the abnormal spinning machine spindle running state, and vice versa.

[0068] The frequency band vibration amplitude ratio increment index Vb A and the strain rate rising gradient index G v are obtained. ξ The hidden fault occurrence coefficient Fault

[0069] The specific implementation of the above weighted summation is not limited here, and any weighted summation method that can comprehensively analyze the frequency band vibration amplitude ratio increment index Vb A and the strain rate rising gradient index G v can be used. In order to realize the technical scheme of the present application, a specific implementation method is provided.

[0070] The calculation formula of the hidden fault occurrence coefficient Fault ξ is: In the formula, α and β are respectively preset proportion coefficients of the frequency band vibration amplitude ratio increment index Vb A and the strain rate rising gradient index G v , and both α and β are greater than 0.

[0071] According to the hidden fault occurrence coefficient, the greater the performance value of the frequency band vibration amplitude ratio increment index generated by the spinning machine spindle during the monitoring period T, the greater the performance value of the strain rate rising gradient index generated by the spinning machine spindle during the monitoring period T, that is, the greater the performance value of the hidden fault occurrence coefficient generated by the spinning machine spindle during the monitoring period T. The greater the hidden danger of the abnormal spinning machine spindle running state, and vice versa.

[0072] The invisible fault occurrence coefficient generated in the monitoring period T when the spinning machine spindle is running is compared and analyzed with the preset invisible fault occurrence coefficient reference threshold value, if the invisible fault occurrence coefficient is greater than or equal to the invisible fault occurrence coefficient reference threshold value, a hidden danger signal is generated, indicating that there is an abnormal hidden danger in the running state of the spinning machine spindle when the spinning machine spindle is running, if the invisible fault occurrence coefficient is less than the invisible fault occurrence coefficient reference threshold value, a high efficiency signal is generated, indicating that the spinning machine spindle can realize efficient operation.

[0073] When the abnormal operation of the spinning machine spindle is perceived, the abnormal operation hidden danger of the spinning machine spindle is divided into high-risk operation hidden danger, general-risk operation hidden danger and low-risk operation hidden danger.

[0074] When the spinning machine spindle generates a hidden danger signal, the invisible fault occurrence coefficient is compared and analyzed with the first reference threshold value and the second reference threshold value, wherein the first reference threshold value is less than the second reference threshold value, and the invisible fault occurrence coefficient reference threshold value is less than the first reference threshold value, the abnormal operation hidden danger of the spinning machine spindle is divided into high-risk operation hidden danger, general-risk operation hidden danger and low-risk operation hidden danger, and the specific division steps are as follows:

[0075] If the invisible fault occurrence coefficient is greater than or equal to the invisible fault occurrence coefficient reference threshold value and less than the first reference threshold value, the abnormal operation hidden danger of the spinning machine spindle is divided into low-risk operation hidden danger.

[0076] If the invisible fault occurrence coefficient is greater than or equal to the first reference threshold value and less than the second reference threshold value, the abnormal operation hidden danger of the spinning machine spindle is divided into general-risk operation hidden danger.

[0077] If the invisible fault occurrence coefficient is greater than or equal to the second reference threshold value, the abnormal operation hidden danger of the spinning machine spindle is divided into high-risk operation hidden danger.

[0078] For low-risk operation hidden danger, the running state of the spinning machine spindle is continuously monitored based on the initial monitoring frequency, for general-risk operation hidden danger, the monitoring frequency is improved for medium-density data acquisition, and the development of potential problems is observed, for high-risk operation hidden danger, the monitoring frequency is improved for high-density data acquisition, to ensure that more detailed fault information is captured.

[0079] For low-risk operational hazards, the system continues to monitor the operational status of the spinning machine spindles based on the initial monitoring frequency. This means that when the analysis of the operational data of the spinning machine spindles shows potential but low-risk abnormalities, the system will continue to monitor in real-time at the set initial monitoring frequency (i.e., the basic data collection frequency). The purpose of this is to continuously focus on the operational status of the equipment while maintaining resource efficiency, ensuring that any further changes or potential problems can be captured in a timely manner. This strategy balances the comprehensiveness of monitoring and the effective use of resources, avoiding unnecessary storage and computational burden due to frequent data collection, while providing sufficient monitoring strength to ensure the safe operation of the equipment.

[0080] For general-risk operational hazards, the monitoring frequency is increased for medium-density data collection, with the following specific steps:

[0081] The coefficient of hidden failure occurrence under general-risk operational hazards is obtained, and the actual monitoring frequency under general-risk operational hazards is regulated based on the coefficient of hidden failure occurrence, the first reference threshold, the second reference threshold, and the initial monitoring frequency, with the regulation formula being: F x1 Factual monitoring frequency under general-risk operational hazards, f0 represents the initial monitoring frequency, Fault ξ 'Coefficient of hidden failure occurrence under general-risk operational hazards, θ1 represents the first reference threshold, and θ2 represents the second reference threshold.

[0082] For high-risk operational hazards, the monitoring frequency is increased for high-density data collection, with the following specific steps:

[0083] The coefficient of hidden failure occurrence under high-risk operational hazards is obtained, and the actual monitoring frequency under high-risk operational hazards is regulated based on the coefficient of hidden failure occurrence, the second reference threshold, and the initial monitoring frequency, with the regulation formula being: F x2 Factual monitoring frequency under high-risk operational hazards, f0 represents the initial monitoring frequency, Fault ξ "Coefficient of hidden failure occurrence under high-risk operational hazards, q is an adjustment coefficient, with a value range greater than 1, used to significantly increase the monitoring frequency.

[0084] The application establishes an abnormal monitoring mechanism by setting an initial monitoring frequency and collecting operation data in a monitoring period, performing abnormal analysis processing, realizing intelligent perception of the running state of the spindle of the spinning machine, comprehensively considering the vibration amplitude ratio information and strain rate data information of different frequency bands, generating a hidden fault occurrence coefficient, dividing the abnormal operation hidden danger into high risk, general risk and low risk through comparison and analysis of the hidden fault occurrence coefficient, and taking different monitoring frequency strategies for targeted monitoring, effectively solving the problem of data overload and false alarm caused by high-frequency monitoring, while still ensuring the diagnosis accuracy under low-frequency monitoring, improving the accuracy and efficiency of fault diagnosis by dynamically adjusting the monitoring frequency, and reducing the maintenance cost.

[0085] The above formulas are dimensionless values calculated, the formulas are obtained by collecting a large amount of data to simulate a formula of the latest real situation, and the preset parameters and threshold values in the formula are set by a person skilled in the art according to the actual situation.

[0086] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like containing one or more available medium sets. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0087] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0089] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only one, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0090] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0091] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0092] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the essential part or part of the technical solutions that make contributions to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0093] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0094] Finally, the above merely provides the preferred embodiments of the present application, but is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for intelligent diagnosis of faults in textile equipment, characterized in that, The method comprises the following steps: According to the working characteristics and historical data of the spinning machine spindle, an initial monitoring frequency is set to ensure the basic operation of the spinning machine spindle; In the monitoring period T, the running data of the spinning machine spindle is collected in real time, and the abnormal analysis processing is performed on the running data to establish an abnormal monitoring mechanism through the abnormal analysis processing data to intelligently perceive the abnormal running hidden danger of the spinning machine spindle; When the abnormal running of the spinning machine spindle is perceived, the abnormal running hidden danger of the spinning machine spindle is divided into high-risk running hidden danger, general-risk running hidden danger and low-risk running hidden danger; For the low-risk running hidden danger, the running state of the spinning machine spindle is continuously monitored in real time based on the initial monitoring frequency, for the general-risk running hidden danger, the monitoring frequency is improved for medium-density data acquisition, and the development of potential problems is observed, and for the high-risk running hidden danger, the monitoring frequency is improved for high-density data acquisition to ensure that more detailed fault information is captured; For the general-risk running hidden danger, the monitoring frequency is improved for medium-density data acquisition, and the specific steps are as follows: The hidden failure occurrence coefficient under the general risk operation hidden danger is obtained, and the actual monitoring frequency under the general risk operation hidden danger is regulated based on the hidden failure occurrence coefficient, the first reference threshold, the second reference threshold and the initial monitoring frequency, and the regulation formula is: , represents the actual monitoring frequency under the general risk operation hidden danger, represents the initial monitoring frequency, represents the hidden failure occurrence coefficient under the general risk operation hidden danger, represents the first reference threshold, represents the second reference threshold. For the high-risk running hidden danger, the monitoring frequency is improved for high-density data acquisition, and the specific steps are as follows: An actual monitoring frequency under the high-risk operation hidden danger is regulated based on the invisible failure occurrence coefficient, the second reference threshold and the initial monitoring frequency, and a regulation formula is as follows: , An actual monitoring frequency under the high-risk operation hidden danger is represented by q, The initial monitoring frequency is represented by q0, The invisible failure occurrence coefficient under the high-risk operation hidden danger is represented by q1, and q is an adjustment coefficient.

2. The method according to claim 1, wherein The running data of the spinning machine spindle includes vibration amplitude ratio information and strain rate data information of different frequency bands, and after the vibration amplitude ratio information and strain rate data information of different frequency bands are acquired, frequency band vibration amplitude ratio increment index and strain rate rising gradient index are generated, and an abnormal monitoring mechanism is established through the frequency band vibration amplitude ratio increment index and the strain rate rising gradient index to generate a hidden fault occurrence coefficient, and the abnormal running hidden danger of the spinning machine spindle is intelligently perceived.

3. The method according to claim 2, wherein The hidden fault occurrence coefficient generated in the monitoring period T when the spinning machine spindle runs is compared and analyzed with the pre-set hidden fault occurrence coefficient reference threshold value, if the hidden fault occurrence coefficient is greater than or equal to the hidden fault occurrence coefficient reference threshold value, a hidden danger signal is generated, and if the hidden fault occurrence coefficient is less than the hidden fault occurrence coefficient reference threshold value, an efficient signal is generated.

4. The method according to claim 3, wherein, When the spinning machine spindle generates a hidden danger signal, the hidden fault occurrence coefficient is compared and analyzed with the first reference threshold value and the second reference threshold value, wherein the first reference threshold value is less than the second reference threshold value, and the hidden fault occurrence coefficient reference threshold value is less than the first reference threshold value, the abnormal running hidden danger of the spinning machine spindle is divided into high-risk running hidden danger, general-risk running hidden danger and low-risk running hidden danger, and the specific division steps are as follows: If the hidden fault occurrence coefficient is greater than or equal to the hidden fault occurrence coefficient reference threshold value and less than the first reference threshold value, the abnormal running hidden danger of the spinning machine spindle is divided into low-risk running hidden danger; If the hidden fault occurrence coefficient is greater than or equal to the first reference threshold value and less than the second reference threshold value, the abnormal running hidden danger of the spinning machine spindle is divided into general-risk running hidden danger; If the hidden fault occurrence coefficient is greater than or equal to the second reference threshold value, the abnormal running hidden danger of the spinning machine spindle is divided into high-risk running hidden danger.

5. The method according to claim 2, wherein, After the abnormal analysis and processing of the acquired vibration amplitude ratio information of different frequency bands, the steps of generating the frequency band vibration amplitude ratio increment index are as follows: In the monitoring period T, the vibration signal data of different frequency bands of the spinning machine spindle are collected in real time, the vibration signal is divided into a plurality of time windows, and the length of each time window is wherein satisfies m is the total number of time windows. The signal in each time window is subjected to a fast Fourier transform, and the value of the frequency domain signal at the kth frequency component index is calculated, and the expression for calculation is: wherein, represents the value of the frequency domain signal at the kth frequency component index, represents the vibration signal of the nth sampling point in the time window, N represents the total number of sampling points in the time window, k represents the frequency component index, and j represents the imaginary unit. the value of the frequency domain signal at the kth frequency component index The frequency domain signal is divided into several frequency bands, and the vibration amplitude of each frequency band is calculated, and the expression is: wherein, represents the vibration amplitude of the ith frequency band, represents the set of frequency component indexes contained in the ith frequency band, represents the amplitude of the frequency domain signal at the kth frequency component index; The vibration amplitude ratio of adjacent frequency bands is calculated, and the expression is: , wherein, represents the vibration amplitude ratio of the i-th frequency band and the i+1-th frequency band, represents the vibration amplitude of the i+1-th frequency band. The acquired frequency band vibration amplitude ratio is subjected to abnormality analysis, the frequency band vibration amplitude ratio is compared and analyzed with a preset frequency band vibration amplitude ratio reference threshold value, an abnormal point is identified, and the abnormal point is marked as Then: wherein, represents the frequency band vibration amplitude ratio reference threshold value. For the abnormal point, the change of the vibration amplitude ratio of the same frequency band in the adjacent time window is calculated, and the expression is: , wherein, represents the frequency band vibration amplitude ratio increment of the abnormal point at time t, represents the frequency band vibration amplitude ratio of the abnormal point at time t, represents the frequency band vibration amplitude ratio of the abnormal point at time t-1. The frequency band vibration amplitude ratio increment index is calculated, and the expression is: , wherein, represents the frequency band vibration amplitude ratio increment index, represents the weight factor of the i-th frequency band, and M represents the total number of frequency bands.

6. The method according to claim 2, wherein After the abnormal analysis and processing of the acquired strain rate data information, the steps of generating the strain rate rising gradient index are as follows: In the monitoring period T, set a fixed time interval Carrying out data acquisition, obtaining strain rate data sequence Wherein u is the index of the acquisition time, u=1, 2, …, y, ; The rate of change of strain rate in each time interval is calculated, the expression for which is: where represents the amount of change in the rate of strain in the u-th time interval; The strain rate change amount is compared with a preset strain rate change amount reference threshold value, and an abnormal strain rate change point is identified, specifically as follows: wherein, represents a set of all time interval indexes identified as abnormal, represents a strain rate change amount reference threshold value; A strain rate rise gradient index is calculated, and the expression for the calculation is: wherein represents the strain rate rise gradient index, represents the number of elements in the set , that is, the number of abnormal strain rate change points identified.

Images