An intelligent detection and analysis system for spinning and picking failure risks

Abstract

The present invention relates to the technical field of spinning and cotton plucking fault risk detection, and specifically to a spinning and cotton plucking fault risk intelligent detection and analysis system, comprising a data acquisition module, a server, a cotton knot state analysis module, a pathological state analysis module, a bag discharge state analysis module, an influence factor analysis module, an equipment operation analysis module, a fault risk analysis module and a display terminal; the present invention obtains corresponding influence indexes by analyzing and processing cotton knot state information, pathological state information and bag discharge state information in the spinning and cotton plucking process, and obtains influence factor coefficients by comprehensive analysis of the influence indexes, and monitors and analyzes the equipment operation state information at the same time, and then combines the influence factor coefficients to evaluate the equipment operation state, accurately determine the fault risk of the spinning and cotton plucking equipment, and give the fault risk level, so that the enterprise can take preventive measures in time to ensure the continuous and stable operation of the production line, thereby improving production efficiency and product quality.

Description

Technical Field

[0001] The invention relates to the technical field of spinning and plucking fault risk detection, and in particular to a spinning and plucking fault risk intelligent detection and analysis system. Background Art

[0002] In the textile industry, the spinning and plucking process is the cornerstone of the spinning process. It is responsible for finely loosening and evenly mixing natural fiber raw materials such as cotton, laying a solid quality foundation for subsequent spinning operations. However, despite the significant progress made in modern textile technology, the spinning and plucking process still faces many challenges, especially the instability of raw cotton quality has a huge impact on the stability of the plucking equipment, which has not been fully valued and solved.

[0003] At present, although there are some fault risk detection systems on the market that monitor the electrical parameters of cotton plucking machines, most of these systems focus on the physical operating status of the equipment and ignore the direct impact of the core variable of raw cotton quality on the stability of cotton plucking equipment. Specifically, the dense cotton knots, mildew pollution and inconsistent bale arrangement in the raw cotton have become important sources of failure risks for cotton plucking machines. Excessive cotton knots not only increase the difficulty of opening the cotton plucking machine, but also cause a sharp increase in mechanical load and accelerate the wear and aging of components. Moldy raw cotton may carry harmful microorganisms or chemicals, which not only damages the fiber quality, but also poses a potential threat to the safe operation of the equipment. The inconsistent bale arrangement height further aggravates the uneven distribution of fiber materials during the grasping process, increasing the difficulty of operating the cotton plucking machine and load fluctuations.

[0004] These problems will directly increase the risk of equipment failure during the plucking process, which will not only seriously affect the continuous and stable operation of the spinning production line, but may also lead to a decline in the quality of the final spinning products due to substandard raw material quality, causing immeasurable economic losses and damage to the brand reputation of the company;

[0005] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0006] The purpose of the present invention is to solve the problem that most of the current detection of spinning and cotton picking fault risks focuses on the physical operating status of the equipment, but ignores the direct impact of the core variable of raw cotton quality on the stability of the cotton picking equipment, and proposes an intelligent detection and analysis system for spinning and cotton picking fault risks.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] An intelligent detection and analysis system for spinning and plucking fault risks, comprising:

[0009] The data acquisition module is used to collect the nep status information, lesion status information, bag arrangement status information and equipment operation status information during the spinning and plucking process, and send them to the nep status analysis module, lesion status analysis module, bag arrangement status analysis module and equipment operation analysis module respectively through the server;

[0010] The nep state analysis module is used to receive the nep state information in the spinning and plucking process, analyze and process the nep state in the spinning and plucking process accordingly, obtain the nep state influence index, and send it to the influence factor analysis module;

[0011] The pathological state analysis module is used to receive the pathological state information in the spinning and plucking process, analyze and process the pathological state in the spinning and plucking process accordingly, obtain the pathological state influence index, and send it to the influence factor analysis module;

[0012] The package discharging state analysis module is used to receive the package discharging state information in the spinning and plucking process, analyze and process the package discharging state in the spinning and plucking process accordingly, obtain the package discharging state influence index, and send it to the influence factor analysis module;

[0013] The influencing factor analysis module is used to receive the influence index of the nep state, the influence index of the lesion state and the influence index of the packing state, and analyze the influence factor coefficient of the spinning and plucking equipment based on the influencing factor coefficient to obtain the influence factor coefficient;

[0014] The equipment operation analysis module is used to receive and analyze the equipment operation status information in the spinning and plucking process, obtain the first operation evaluation index, the second operation evaluation index and the third operation evaluation index of the equipment, and then retrieve the influencing factor coefficient, and analyze and process the equipment operation status in the spinning and plucking process accordingly to obtain the equipment operation status evaluation coefficient;

[0015] The fault risk analysis module is used to receive the equipment operation status assessment coefficient, and based on it, determine and analyze the fault risk of the equipment in the spinning and plucking process, and obtain the fault risk level of the equipment in the spinning and plucking process.

[0016] Furthermore, the cotton nep state is analyzed and processed, and the specific analysis is as follows:

[0017] The cotton nep value in the spinning and plucking process within a period of time is monitored in real time, and the cotton nep value at the initial monitoring time point in the spinning and plucking process within a period of time is used as the initial cotton nep value in the spinning and plucking process within a period of time. The cotton nep value is solved as follows: by obtaining the area of ​​the cotton plucking execution area of ​​the cotton plucking machine, and dividing the area of ​​the cotton plucking execution area of ​​the cotton plucking machine into a number of sub-areas according to equal areas, thereby obtaining each sub-area of ​​the cotton plucking execution area of ​​the cotton plucking machine, obtaining the number of cotton neps in each sub-area of ​​the cotton plucking execution area of ​​the cotton plucking machine, and calculating the average thereof, to obtain the average number of cotton neps in the cotton plucking execution area of ​​the cotton plucking machine, as the cotton nep value in the spinning and plucking process within a period of time, and the cotton nep value and the initial cotton nep value in the spinning and plucking process within a period of time are calibrated as Mzund respectively i and Mzund c ;

[0018] According to the formula: , get the cotton nep state influence index YX δ1 , where i represents each monitoring time point within a period of time, and i=1, 2, 3…n, n is a positive integer greater than zero, Mzund * It is represented by the normal cotton nep value in the spinning and plucking process stored in the system library, and a1, a2 and a3 respectively represent the correction factors of the initial cotton nep change degree, the target cotton nep change degree and the normal cotton nep change degree.

[0019] Furthermore, the pathological state is analyzed and processed, and the specific analysis is as follows:

[0020] By acquiring the raw cotton images in the spinning and plucking process within a period of time, each raw cotton image in the spinning and plucking process is obtained, and detection points are arranged for the raw cotton images, and the grayscale value of each detection point is extracted from each raw cotton image, and the grayscale value of each detection point in each raw cotton image is matched and analyzed with the reference grayscale area of ​​the preset lesion corresponding image. If the grayscale value of a certain detection point is within the preset reference grayscale interval of the lesion corresponding image, the detection point is preliminarily marked as a suspected lesion point, and then the spectrum of the suspected lesion point is collected by a spectrum analyzer to obtain the spectrum of the suspected lesion point, and then the spectrum of the suspected lesion point is compared with the stored lesion spectrum, and the overlap between the two is calculated. If the overlap is greater than a preset overlap threshold, the suspected lesion point is marked as a lesion point, and the lesion points in each raw cotton image are integrated to obtain the lesion area in each raw cotton image, and the lesion area in each raw cotton image is compared and analyzed with a preset lesion area threshold. If the lesion area in a raw cotton image is greater than or equal to the preset lesion area threshold, the raw cotton image is marked as a monitoring image;

[0021] The monitoring images are sorted in order of acquisition time to obtain a monitoring image set. At the same time, the monitoring images in the monitoring image set are marked as monitoring points, thereby obtaining each monitoring point, extracting the lesion area of ​​each monitoring point, and calibrating it as Bbing j , according to the formula: , and obtain the disease state impact index YX δ2 , where j represents the number of each monitoring point, and j=1, 2, 3…m, m represents the total number of monitoring point numbers, and a4 represents the correction factor for the degree of lesion change.

[0022] Furthermore, the packet arrangement status is analyzed and processed, and the specific analysis is as follows:

[0023] By obtaining the distance between the cotton plucking machine beater and the raw cotton bale during the spinning and plucking process over a period of time, the plucking distance value during the spinning and plucking process over a period of time is obtained and calibrated as Pzxin i ;

[0024] The standard row grab distance value in the spinning and plucking process is extracted from the storage library as the reference row grab distance value in the spinning and plucking process for a period of time, and it is calibrated as Pzxin * ;

[0025] According to the formula: , get the impact index YX of the package status δ3 , where e represents a natural constant greater than zero, PZG i Indicates the change rate of row-grab distance at each monitoring time point within a period of time, PZG * represents the change rate of reference row grab distance, a5, a6, and λ all represent the set correction factors.

[0026] Furthermore, the impact factor coefficient is analyzed, and the specific analysis is as follows:

[0027] The values ​​of the influence index of cotton nep state, the influence index of lesion state and the influence index of bale discharge state are extracted and normalized to obtain the influence factor coefficient, which is recorded as YXZ.

[0028] Furthermore, the equipment operation status information is analyzed and processed, and the specific analysis is as follows:

[0029] By obtaining the vibration signal and sound signal of each structural component of the equipment corresponding to the spinning and plucking process within a period of time, and generating the vibration waveform and sound waveform of each structural component of the equipment corresponding to the spinning and plucking process within a period of time through specific software; at the same time, extracting the reference vibration waveform and reference sound waveform of each structural component of the equipment corresponding to the system repository, respectively, overlapping and comparing the vibration waveform and sound waveform of each structural component of the equipment corresponding to the spinning and plucking process within a period of time with the reference vibration waveform and reference sound waveform of each structural component of the equipment, the vibration overlap waveform length and the sound overlap waveform length of each structural component of the equipment corresponding to the spinning and plucking process within a period of time are obtained, and the numerical values ​​are taken for analysis to obtain the first operation evaluation index θ1 of the equipment;

[0030] By obtaining the damage parameters of each structural component of the equipment during the spinning and plucking process within a period of time, and extracting the maximum damage area, maximum damage depth and maximum damage quantity from them, as the damage surface value, damage depth value and damage value of each structural component of the equipment during the spinning and plucking process within a period of time, taking their values ​​for analysis, the second operation evaluation index θ2 of the equipment is obtained;

[0031] By obtaining the temperature of each structural component of the equipment corresponding to each monitoring time point in the spinning and cotton plucking process within a period of time, and averaging the temperature of each structural component of the equipment corresponding to each monitoring time point in the spinning and cotton plucking process within a period of time, the average temperature value of each structural component of the equipment corresponding to the spinning and cotton plucking process within a period of time is obtained, and the average temperature value of each structural component of the equipment corresponding to the equipment is compared and analyzed with the preset reference comparison interval. If the average temperature value of a structural component corresponding to the equipment is outside the preset reference comparison interval, the structural component corresponding to the equipment is judged to be in an abnormal state. Otherwise, the structural component corresponding to the equipment is judged to be in a normal state. The number of times the equipment is judged to be in an abnormal state and the total number of judgments in the spinning and cotton plucking process within a period of time are counted, and the values ​​are taken for analysis to obtain the third operation evaluation index θ3 of the equipment.

[0032] Furthermore, the equipment operation status is analyzed and processed, and the specific analysis is as follows:

[0033] The value of the influencing factor coefficient YXZ is retrieved, and the values ​​of the first operation evaluation index θ1, the second operation evaluation index θ2 and the third operation evaluation index θ3 of the equipment are extracted and normalized according to the formula: , the equipment operation status evaluation coefficient Gsnmg is obtained, where η1, η2 and η3 represent the weight coefficients of the first operation evaluation index, the second operation evaluation index and the third operation evaluation index respectively.

[0034] Furthermore, the failure risk of the equipment is determined and analyzed, and the specific analysis is as follows:

[0035] Setting a device operation status assessment threshold, comparing and analyzing the device operation status assessment coefficient with the device operation status assessment threshold, if the device operation status assessment coefficient is greater than or equal to the device operation status assessment threshold, an abnormal trend signal is generated, and if the device operation status assessment coefficient is less than the device operation status assessment threshold, a normal trend signal is generated;

[0036] If an abnormal trend signal is captured, the equipment operation status assessment coefficient is subtracted from the equipment operation status assessment threshold to obtain the equipment failure risk value, and it is matched with the failure risk level corresponding to the set failure risk value of each equipment, thereby obtaining the failure risk level of the equipment in the spinning and plucking process.

[0037] Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects:

[0038] 1. The present invention collects a variety of key information in the spinning and plucking process in real time and comprehensively, and the information is transmitted to the corresponding analysis modules through the server, thereby realizing real-time, accurate and efficient data collection, and providing a strong data basis for subsequent data analysis and fault risk determination;

[0039] 2. The present invention analyzes and processes the nep state information, pathological state information and bag discharge state information in the spinning and plucking process respectively to obtain the nep state influence index, pathological state influence index and bag discharge state influence index. These influence indexes respectively reflect the influence of the nep state, pathological state and bag discharge state on the spinning and plucking equipment in the spinning and plucking process. The three influence indexes are combined to perform influence factor coefficient analysis, thereby achieving a more comprehensive understanding of the influence factors in the spinning and plucking process and avoiding the limitation of a single evaluation coefficient. This comprehensive evaluation method helps to timely and accurately reflect the comprehensive influence of various factors in the current spinning and plucking process on the equipment operation status and fault risk, and provides strong support for subsequent fault risk analysis;

[0040] 3. The present invention monitors and analyzes the equipment operating status information in the spinning and plucking process, and then combines the influencing factor coefficient to evaluate the equipment operating status, accurately determine the failure risk of the spinning and plucking equipment, and give a failure risk level. This helps enterprises to take preventive measures in time, reduce downtime and defective rate caused by equipment failure, and ensure the continuous and stable operation of the production line, thereby improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 It is the overall module block diagram of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] like Figure 1 As shown, a spinning and plucking fault risk intelligent detection and analysis system includes: a data acquisition module, a server, a cotton nep state analysis module, a pathological state analysis module, a bag arrangement state analysis module, an influencing factor analysis module, an equipment operation analysis module, a fault risk analysis module and a display terminal;

[0045] The data acquisition module is used to collect the nep status information, lesion status information, bag arrangement status information and equipment operation status information during the spinning and plucking process, and send them to the nep status analysis module, lesion status analysis module, bag arrangement status analysis module and equipment operation analysis module respectively through the server;

[0046] When the nep status analysis module receives the nep status information in the spinning and plucking process, it analyzes and processes the nep status in the spinning and plucking process accordingly. The specific analysis process is as follows:

[0047] The cotton nep value in the spinning and plucking process within a period of time is monitored in real time, and the cotton nep value at the initial monitoring time point in the spinning and plucking process within a period of time is used as the initial cotton nep value in the spinning and plucking process within a period of time. The cotton nep value is solved as follows: by obtaining the area of ​​the cotton plucking execution area of ​​the cotton plucking machine, and dividing the area of ​​the cotton plucking execution area of ​​the cotton plucking machine into a number of sub-areas according to equal areas, thereby obtaining each sub-area of ​​the cotton plucking execution area of ​​the cotton plucking machine, obtaining the number of cotton neps in each sub-area of ​​the cotton plucking execution area of ​​the cotton plucking machine, and calculating the average thereof, to obtain the average number of cotton neps in the cotton plucking execution area of ​​the cotton plucking machine as the cotton nep value in the spinning and plucking process within a period of time; the cotton nep value and the initial cotton nep value in the spinning and plucking process within a period of time are calibrated as Mzundi and Mzund c ;

[0048] According to the formula: , get the cotton nep state influence index YX δ1 , where i represents each monitoring time point within a period of time, and i=1, 2, 3…n, n is a positive integer greater than zero, Mzund * It is represented by the normal nep value in the spinning and plucking process stored in the system repository, a1, a2 and a3 respectively represent the correction factors of the initial nep change degree, the target nep change degree and the normal nep change degree, wherein the initial nep change degree is the nep change degree of the nep value at each monitoring time point compared with the initial nep value, the target nep change degree is the nep change degree of the nep value at each monitoring time point compared with the nep value at the previous monitoring time point, and the normal nep change degree is the nep change degree of the nep value at each monitoring time point compared with its corresponding normal nep value;

[0049] The obtained nep state impact index is sent to the impact factor analysis module;

[0050] When the pathological state analysis module receives the pathological state information in the spinning and plucking process, it analyzes and processes the pathological state in the spinning and plucking process accordingly. The specific analysis process is as follows:

[0051] By acquiring the raw cotton images in the spinning and plucking process within a period of time, each raw cotton image in the spinning and plucking process is obtained, and detection points are arranged for the raw cotton images, and the grayscale value of each detection point is extracted from each raw cotton image, and the grayscale value of each detection point in each raw cotton image is matched and analyzed with the reference grayscale area of ​​the preset lesion corresponding image. If the grayscale value of a certain detection point is within the preset reference grayscale interval of the lesion corresponding image, the detection point is preliminarily marked as a suspected lesion point, and then the spectrum of the suspected lesion point is collected by a spectrum analyzer to obtain the spectrum of the suspected lesion point, and then the spectrum of the suspected lesion point is compared with the stored lesion spectrum, and the overlap between the two is calculated. If the overlap is greater than a preset overlap threshold, the suspected lesion point is marked as a lesion point, and the lesion points in each raw cotton image are integrated to obtain the lesion area in each raw cotton image, and the lesion area in each raw cotton image is compared and analyzed with a preset lesion area threshold. If the lesion area in a raw cotton image is greater than or equal to the preset lesion area threshold, the raw cotton image is marked as a monitoring image;

[0052] The monitoring images are sorted in order of acquisition time to obtain a monitoring image set. At the same time, the monitoring images in the monitoring image set are marked as monitoring points, thereby obtaining each monitoring point, extracting the lesion area of ​​each monitoring point, and calibrating it as Bbing j , according to the formula: , and obtain the disease state impact index YX δ2 , where j represents the number of each monitoring point, and j=1, 2, 3…m, m represents the total number of monitoring point numbers, and a4 represents the correction factor of the degree of lesion change;

[0053] The obtained lesion status impact index is sent to the impact factor analysis module;

[0054] When the package discharging state analysis module receives the package discharging state information in the spinning and plucking process, it analyzes and processes the package discharging state in the spinning and plucking process accordingly. The specific analysis process is as follows:

[0055] By obtaining the distance between the cotton plucking machine beater and the raw cotton bale during the spinning and plucking process over a period of time, the plucking distance value during the spinning and plucking process over a period of time is obtained and calibrated as Pzxin i ;

[0056] The standard row grab distance value in the spinning and plucking process is extracted from the storage library as the reference row grab distance value in the spinning and plucking process for a period of time, and it is calibrated as Pzxin * ;

[0057] According to the formula: , get the impact index YX of the package status δ3 , where e represents a natural constant greater than zero, PZG i Indicates the change rate of row-grab distance at each monitoring time point within a period of time, PZG * represents the change rate of reference row grab distance, a5, a6, and λ all represent the set correction factors;

[0058] The obtained packet displacing status impact index is sent to the impact factor analysis module;

[0059] When the influencing factor analysis module receives the influence index of the nep state, the influence index of the lesion state and the influence index of the packing state, it analyzes the influence factor coefficient of the spinning and plucking equipment accordingly. The specific analysis process is as follows:

[0060] Extraction of cotton neps state influence index YX δ1 , Pathological status impact index YX δ2 And the impact index of the packaging status YX δ3 The value of is normalized according to the formula: , the influence factor coefficient YXZ is obtained, where β1, β2 and β3 represent the weight coefficients of the influence index of cotton knot state, the influence index of pathological state and the influence index of bale arrangement state respectively, and β1>β2>β3. The weight coefficient is used to balance the weight of each data in the formula calculation, so as to promote the accuracy of the calculation result;

[0061] When the equipment operation analysis module receives the equipment operation status information in the spinning and plucking process, it analyzes and processes the equipment operation status in the spinning and plucking process accordingly. The specific analysis process is as follows:

[0062] By obtaining the vibration signals and sound signals of each structural component of the equipment corresponding to the spinning and plucking process within a period of time, and generating the vibration waveform and sound waveform of each structural component of the equipment corresponding to the spinning and plucking process within a period of time through specific software; at the same time, extracting the reference vibration waveform and reference sound waveform of each structural component of the equipment from the system repository, respectively, the vibration waveform and sound waveform of each structural component of the equipment corresponding to the spinning and plucking process within a period of time are overlapped and compared with the reference vibration waveform and reference sound waveform of each structural component of the equipment, and the vibration overlap waveform length and sound overlap waveform length of each structural component of the equipment corresponding to the spinning and plucking process within a period of time are obtained, and they are calibrated as ZDb respectively. z and SYb z ; z represents the number of each structural component of the equipment, and z=1, 2, 3…q, q represents the total number of the structural component numbers corresponding to the equipment, according to the formula: , the first operation evaluation index θ1 of the equipment is obtained, where p1 and p2 both represent the set weight coefficients;

[0063] By obtaining the damage parameters of each structural component of the equipment during the spinning and plucking process over a period of time, the damage parameters include damage area, damage depth and damage quantity;

[0064] The maximum damage area, maximum damage depth and maximum damage quantity are extracted from the damage parameters of each structural component of the equipment during the spinning and plucking process within a period of time as the damage surface value, damage depth value and damage value of each structural component of the equipment during the spinning and plucking process within a period of time, and they are calibrated as SS1 respectively. z SS2 z and SS3 z , according to the formula: , the second operation evaluation index θ2 of the equipment is obtained, wherein p3, p4, and p5 all represent the set weight coefficients;

[0065] By obtaining the temperature of each monitoring time point of each structural component of the equipment corresponding to the spinning and plucking process within a period of time, and averaging the temperature of each monitoring time point of each structural component of the equipment corresponding to the spinning and plucking process within a period of time, the average temperature value of each structural component of the equipment corresponding to the spinning and plucking process within a period of time is obtained, and the average temperature value of each structural component of the equipment corresponding to the equipment is compared and analyzed with the preset reference comparison interval. If the average temperature value of a structural component corresponding to the equipment is outside the preset reference comparison interval, the structural component corresponding to the equipment is judged to be in an abnormal state, otherwise, the structural component corresponding to the equipment is judged to be in a normal state. The number of times the equipment is judged to be in an abnormal state and the total number of judgments in the spinning and plucking process within a period of time are counted, and they are calibrated as YCc and ZCc respectively, according to the formula: , the third operation evaluation index θ3 of the equipment is obtained, wherein p6 and p7 both represent the set weight coefficients;

[0066] The value of the influencing factor coefficient YXZ is retrieved, and the values ​​of the first operation evaluation index θ1, the second operation evaluation index θ2 and the third operation evaluation index θ3 of the equipment are extracted and normalized according to the formula: , obtain the equipment operation status evaluation coefficient Gsnmg, where η1, η2 and η3 represent the weight coefficients of the first operation evaluation index, the second operation evaluation index and the third operation evaluation index respectively, and η1>η2>η3;

[0067] The obtained equipment operation status assessment coefficient is sent to a fault risk analysis module;

[0068] When the fault risk analysis module receives the equipment operation status assessment coefficient, it determines and analyzes the fault risk of the equipment in the spinning and plucking process based on it. The specific analysis process is as follows:

[0069] Setting a device operation status assessment threshold, comparing and analyzing the device operation status assessment coefficient with the device operation status assessment threshold, if the device operation status assessment coefficient is greater than or equal to the device operation status assessment threshold, an abnormal trend signal is generated, and if the device operation status assessment coefficient is less than the device operation status assessment threshold, a normal trend signal is generated;

[0070] If an abnormal trend signal is captured, the equipment operation status assessment coefficient is subtracted from the equipment operation status assessment threshold to obtain the equipment failure risk value, and it is matched with the failure risk level corresponding to the set failure risk value of each equipment, thereby obtaining the failure risk level of the equipment in the spinning and plucking process;

[0071] The display terminal provides corresponding display notifications based on the failure risk level of the equipment during the spinning and plucking process.

[0072] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent detection and analysis system for spinning and plucking failure risk, characterized in that: include: The data acquisition module is used to collect the nep status information, lesion status information, bag arrangement status information and equipment operation status information during the spinning and plucking process, and send them to the nep status analysis module, lesion status analysis module, bag arrangement status analysis module and equipment operation analysis module respectively through the server; The nep state analysis module is used to receive the nep state information in the spinning and plucking process, and analyze and process the nep state in the spinning and plucking process accordingly. The specific analysis is as follows: Monitor the cotton neps value in the spinning and plucking process in real time over a period of time, and use the cotton neps value at the initial monitoring time point in the spinning and plucking process as the initial cotton neps value in the spinning and plucking process over a period of time, and calibrate the cotton neps value and the initial cotton neps value in the spinning and plucking process over a period of time as Mzund respectively. i and Mzund c ; According to the formula: , Get the cotton nep state influence index YX δ1 , and sent to the impact factor analysis module; Where i represents each monitoring time point within a period of time, and i = 1, 2, 3...n, n is a positive integer greater than zero, Mzund * It is represented by the normal nep value in the spinning and plucking process stored in the system repository, and a1, a2 and a3 respectively represent the correction factors of the initial nep change degree, the target nep change degree and the normal nep change degree; The pathological state analysis module is used to receive the pathological state information in the spinning and plucking process, and analyze and process the pathological state in the spinning and plucking process accordingly. The specific analysis is as follows: By acquiring the raw cotton images in the spinning and plucking process within a period of time, each raw cotton image in the spinning and plucking process is obtained, and detection points are arranged for them. At the same time, the grayscale value of each detection point is extracted from each raw cotton image, and the grayscale value of each detection point in each raw cotton image is matched and analyzed with the reference grayscale area of ​​the preset lesion corresponding image. If the grayscale value of a certain detection point is within the reference grayscale interval of the preset lesion corresponding image, the detection point is preliminarily marked as a suspected lesion point; Then, the spectrum of the suspected lesion point is collected to obtain the spectrum of the suspected lesion point, and then the spectrum of the suspected lesion point is compared with the stored lesion spectrum to calculate the overlap between the two. If the overlap is greater than a preset overlap threshold, the suspected lesion point is marked as a lesion point. At the same time, the lesion points in each raw cotton image are integrated to obtain the lesion area in each raw cotton image. The lesion area in each raw cotton image is compared and analyzed with a preset lesion area threshold. If the lesion area in a raw cotton image is greater than or equal to the preset lesion area threshold, the raw cotton image is marked as a monitoring image. The monitoring images are sorted in order of acquisition time to obtain a monitoring image set. At the same time, the monitoring images in the monitoring image set are marked as monitoring points, thereby obtaining each monitoring point, extracting the lesion area of ​​each monitoring point, and calibrating it as Bbing j , according to the formula: Get the disease state impact index YX δ2 , and sent to the impact factor analysis module; Wherein, j represents the number of each monitoring point, and j=1, 2, 3…m, m represents the total number of the monitoring point numbers, and a4 represents the correction factor of the degree of lesion change; The package discharging state analysis module is used to receive the package discharging state information in the spinning and plucking process, and analyze and process the package discharging state in the spinning and plucking process accordingly. The specific analysis is as follows: By obtaining the distance between the cotton plucking machine beater and the raw cotton bale during the spinning and plucking process over a period of time, the plucking distance value during the spinning and plucking process over a period of time is obtained and calibrated as Pzxin i ; The standard row grab distance value in the spinning and plucking process is extracted from the storage library as the reference row grab distance value in the spinning and plucking process for a period of time, and it is calibrated as Pzxin * ; According to the formula: Get the impact index YX of the package status δ3 , and sent to the impact factor analysis module; Where e represents a natural constant greater than zero, PZG i Indicates the change rate of row-grab distance at each monitoring time point within a period of time, PZG * represents the change rate of reference row grab distance, a5, a6, and λ all represent the set correction factors; The influencing factor analysis module is used to receive the influence index of the nep state, the influence index of the lesion state and the influence index of the packing state, and analyze the influence factor coefficient of the spinning and plucking equipment based on the influencing factor coefficient to obtain the influence factor coefficient; The equipment operation analysis module is used to receive and analyze the equipment operation status information in the spinning and plucking process, obtain the first operation evaluation index, the second operation evaluation index and the third operation evaluation index of the equipment, and then retrieve the influencing factor coefficient, and analyze and process the equipment operation status in the spinning and plucking process accordingly to obtain the equipment operation status evaluation coefficient; The fault risk analysis module is used to receive the equipment operation status assessment coefficient, and based on it, determine and analyze the fault risk of the equipment in the spinning and plucking process, and obtain the fault risk level of the equipment in the spinning and plucking process.

2. According to claim 1, a spinning and picking failure risk intelligent detection and analysis system is characterized in that: The impact factor coefficient is analyzed, and the specific analysis is as follows: The values ​​of the influence index of cotton nep state, the influence index of lesion state and the influence index of bale discharge state are extracted and normalized to obtain the influence factor coefficient, which is recorded as YXZ.

3. According to claim 2, a spinning and picking failure risk intelligent detection and analysis system is characterized in that: Analyze and process the equipment operation status information. The specific analysis is as follows: By obtaining the vibration signal and sound signal of each structural component of the equipment corresponding to the spinning and plucking process within a period of time, and generating the vibration waveform and sound waveform of each structural component of the equipment corresponding to the spinning and plucking process within a period of time through specific software; at the same time, extracting the reference vibration waveform and reference sound waveform of each structural component of the equipment corresponding to the system repository, respectively, overlapping and comparing the vibration waveform and sound waveform of each structural component of the equipment corresponding to the spinning and plucking process within a period of time with the reference vibration waveform and reference sound waveform of each structural component of the equipment, the vibration overlap waveform length and the sound overlap waveform length of each structural component of the equipment corresponding to the spinning and plucking process within a period of time are obtained, and the numerical values ​​are taken for analysis to obtain the first operation evaluation index θ1 of the equipment; By obtaining the damage parameters of each structural component of the equipment during the spinning and plucking process within a period of time, and extracting the maximum damage area, maximum damage depth and maximum damage quantity from them, as the damage surface value, damage depth value and damage value of each structural component of the equipment during the spinning and plucking process within a period of time, taking their values ​​for analysis, the second operation evaluation index θ2 of the equipment is obtained; By obtaining the temperature of each structural component of the equipment corresponding to each monitoring time point in the spinning and cotton plucking process within a period of time, and averaging the temperature of each structural component of the equipment corresponding to each monitoring time point in the spinning and cotton plucking process within a period of time, the average temperature value of each structural component of the equipment corresponding to the spinning and cotton plucking process within a period of time is obtained, and the average temperature value of each structural component of the equipment corresponding to the equipment is compared and analyzed with the preset reference comparison interval. If the average temperature value of a structural component corresponding to the equipment is outside the preset reference comparison interval, the structural component corresponding to the equipment is judged to be in an abnormal state. Otherwise, the structural component corresponding to the equipment is judged to be in a normal state. The number of times the equipment is judged to be in an abnormal state and the total number of judgments in the spinning and cotton plucking process within a period of time are counted, and the values ​​are taken for analysis to obtain the third operation evaluation index θ3 of the equipment.

4. The intelligent detection and analysis system for spinning and plucking failure risk according to claim 3 is characterized in that: Analyze and process the equipment operation status. The specific analysis is as follows: The value of the influencing factor coefficient YXZ is retrieved, and the values ​​of the first operation evaluation index θ1, the second operation evaluation index θ2 and the third operation evaluation index θ3 of the equipment are extracted and normalized according to the formula: The equipment operation status evaluation coefficient Gsnmg is obtained, wherein η1, η2 and η3 represent weight coefficients of the first operation evaluation index, the second operation evaluation index and the third operation evaluation index respectively.

5. The intelligent detection and analysis system for spinning and plucking failure risk according to claim 1 is characterized in that: The failure risk of the equipment is determined and analyzed. The specific analysis is as follows: Setting a device operation status assessment threshold, comparing and analyzing the device operation status assessment coefficient with the device operation status assessment threshold, if the device operation status assessment coefficient is greater than or equal to the device operation status assessment threshold, an abnormal trend signal is generated, and if the device operation status assessment coefficient is less than the device operation status assessment threshold, a normal trend signal is generated; If an abnormal trend signal is captured, the equipment operation status assessment coefficient is subtracted from the equipment operation status assessment threshold to obtain the equipment failure risk value, and it is matched with the failure risk level corresponding to the set failure risk value of each equipment, thereby obtaining the failure risk level of the equipment in the spinning and plucking process.

Images