Roller screen running state intelligent monitoring method based on data driving

Abstract

The invention relates to the technical field of fault prediction of mechanical parts, in particular to an intelligent monitoring method for the running state of a roller screen based on data driving. According to the position and the inclination angle of the screen shaft, the change trend of the rotating speed value of the screen shaft in the neighborhood time period of each moment and the fluctuation degree of the rotating speed value in the neighborhood time period, the actual blockage possibility degree is obtained; according to the actual blocking possibility degree difference and the rotating speed value difference of each screen shaft and the adjacent screen shaft at the same moment in the neighborhood time period of each moment and the difference of the change trend of the actual blocking possibility degree of the adjacent screen shafts in the neighborhood time period, the blocking degree is obtained; and according to the difference of the change trend of the actual blockage possibility degrees of the screen shafts located before and after each screen shaft, the blockage degree is adjusted, the blockage fault probability is obtained, and the blockage fault screen shaft of the roller screen at each moment is determined. The jamming fault probability can more comprehensively reflect the working state of the screen shaft, and the accuracy of judgment of the jamming fault of the screen shaft is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical component failure prediction, and in particular to a data-driven intelligent monitoring method for the operating status of a roller screen. Background Art

[0002] Roller screens are an important type of screening equipment, widely used in the mining, coal, and power industries. During operation, roller screens can experience unexpected downtime due to unexpected failures, such as screen shaft jams, bearing damage, screen mesh breakage, and motor failure. Shaft jams are a common fault during roller screen operation, seriously impacting production continuity and safety. Therefore, it's necessary to monitor the operating status of roller screens and identify the jammed screen shaft.

[0003] The existing method monitors the rotation speed of each screen shaft in real time. When the rotation speed of a screen shaft is lower than the set threshold and lasts for a certain period of time, it is determined that the screen shaft is stuck. However, since the screen shafts at different positions and inclinations are subjected to different pressures, and the material released at the feed port is difficult to control, the screen shaft rotation speed is difficult to reflect the actual jam situation, and the accuracy of judging the screen shaft with a jam fault based on the screen shaft rotation speed is low. Summary of the Invention

[0004] In order to solve the technical problem that the screen shaft speed cannot reflect the actual jam situation, resulting in low accuracy in judging the screen shaft with jam fault, the purpose of the present invention is to provide a data-driven intelligent monitoring method for the operation status of the roller screen. The technical solution adopted is as follows: The present invention proposes a data-driven intelligent monitoring method for the operation status of a roller screen, the method comprising: Obtain the rotational speed value of each screen shaft of the roller screen at each moment during the screening process; According to the position and inclination of each screen shaft and the change trend of its speed value in the adjacent time period at each moment, as well as the fluctuation degree of the speed value in the adjacent time period, the actual jam possibility of each screen shaft at each moment is obtained; Obtain the jamming degree of each sieve shaft at each moment based on the difference in the actual jamming probability and the speed value of each sieve shaft in the neighborhood time period at each moment and the difference in the change trend of the actual jamming probability of the adjacent sieve shafts of each sieve shaft in the neighborhood time period at each moment; According to the difference in the changing trends of the actual jamming possibilities of the screen shafts located before and after each screen shaft at the same moment in the neighborhood period at each moment, the jamming degree of each screen shaft at each moment is adjusted, the jamming failure probability of each screen shaft at each moment is obtained, and the jamming failure screen shaft of the roller screen at each moment is determined.

[0005] Furthermore, obtaining the actual jam probability of each screen shaft at each moment includes: Obtaining the standard normal speed value of each sieve shaft; taking the ratio of the speed value of each sieve shaft at each moment to the standard normal speed value as the speed ratio; calculating the mean of the difference between the speed ratios of adjacent moments within the neighborhood time period of each sieve shaft at each moment, and performing normalization processing to obtain the initial jam probability of each sieve shaft at each moment; Obtain the horizontal angle of the screen shaft and set the position number of the screen shaft; obtain the jam correction amplitude of each screen shaft at each moment based on the position number, horizontal angle and fluctuation degree of the speed ratio of each screen shaft in its neighborhood time period at each moment; The initial jam possibility is adjusted using the jam correction amplitude to obtain the actual jam possibility of each screen shaft at each moment.

[0006] Furthermore, obtaining the jamming degree of each screen shaft at each moment includes: A jam feature vector is formed by performing negative correlation mapping on the speed ratio of each screen shaft at each moment and the actual jam possibility; Obtain the jam feature difference of each sieve axis at each moment according to the difference in jam feature vectors between each sieve axis and its adjacent sieve axis at each moment and the modulus of the jam feature vector of each sieve axis at each moment; Performing a straight line fitting on the actual jam probability of each sieve axis at all moments in a neighborhood period at each moment, and using the slope of the obtained fitting line as the jam tendency value of each sieve axis at each moment; The jamming degree of each sieve axis at each moment is obtained based on the jamming feature difference of each sieve axis in the neighborhood time period at each moment and the jamming trend value difference of the adjacent sieve axes of each sieve axis at each moment.

[0007] Furthermore, obtaining the jam failure probability of each screen shaft at each moment includes: Performing linear fitting on the jamming trend values ​​of the sieve axes located before and after each sieve axis at each moment, respectively, and using the slopes of the obtained fitting lines as the upper sieve axis trend value and the lower sieve axis trend value of each sieve axis at each moment; The absolute value of the difference between the sign value of the upper sieve axis trend value and the lower sieve axis trend value is used as the trend difference degree of each sieve axis at each moment; Determine whether the trend difference is equal to a constant of 2. If so, connect the jamming trend values ​​of the screen shafts with the largest and smallest position numbers in the roller screen to obtain an analysis segment. Use the absolute value of the difference between the jamming trend value of each screen shaft at each moment and the slope of the analysis segment to adjust the jamming degree and obtain the jamming failure probability of each screen shaft at each moment. If not, normalize the jamming degree to obtain the jamming failure probability of each screen shaft at each moment.

[0008] Furthermore, the step of determining the jammed screen shaft of the roller screen at each moment includes: Determine the jamming abnormality threshold of the roller screen at each moment, and select the corresponding screen axis greater than the jamming abnormality threshold from the jamming failure probability of all screen axes of the roller screen at each moment as the jamming screen axis of the roller screen at each moment.

[0009] Furthermore, the adjusting the initial jam possibility by using the jam correction amplitude includes: The jam correction amplitude of each screen axis at each moment is negatively correlated and normalized, the initial jam possibility is weighted using the processing result, and the weighted result is normalized to obtain the actual jam possibility of each screen axis at each moment.

[0010] Furthermore, the fluctuation degree of the speed ratio, the position number and the horizontal angle are all positively correlated with the jam correction amplitude.

[0011] Furthermore, the closer the screen shaft is to the feed port of the roller screen, the smaller the position number is.

[0012] Furthermore, obtaining the difference in jamming characteristics of each screen shaft at each moment includes: Calculate the mean of the modulus of the difference between the jam feature vectors of each sieve axis and its adjacent sieve axis at each moment, and take the product of the mean and the modulus of the jam feature vector of each sieve axis at each moment as the jam feature difference of each sieve axis at each moment.

[0013] Furthermore, the jam abnormality threshold is a classification threshold determined by using the Fisher discriminant method to perform a binary classification of the jam failure probability of all screen shafts of the roller screen at each moment.

[0014] The present invention has the following beneficial effects: In the embodiment of the present invention, since the pressure on the screen shafts at different positions and inclinations of the roller screen is different, and the rotational speeds of different screen shafts are different, the above factors are comprehensively adjusted to show the rotational speed value change trend of the screen shaft having the possibility of jamming, so that the actual jamming possibility can effectively distinguish between real jamming and normal operating fluctuations; since the material accumulation of the jammed screen shaft will lead to differences in the jamming conditions of the adjacent screen shafts, the jamming degree of each screen shaft is obtained by comprehensively considering the actual jamming possibility difference and rotational speed value difference of each screen shaft and its adjacent screen shafts, as well as the difference in the changing trend of the jamming possibility of each screen shaft and its adjacent screen shafts. , which can dynamically adapt to complex working conditions and improve the accuracy of screen shaft jam analysis; the jammed screen shaft has a spatial attenuation effect on the surrounding screen shafts. In order to eliminate the misjudgment of normal changes in the screen shaft caused by factors such as the difficulty in controlling the material put into the feed port, the jam degree of each screen shaft is adjusted through the difference in the changing trend of the actual jam possibility of the screen shaft before and after each screen shaft, the jam failure probability is obtained, and the screen shaft with jam failure is selected, which makes full use of the spatial attenuation characteristics between the screen shafts, is more in line with the actual situation, and thus improves the accuracy of screen shaft jam failure judgment during real-time screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A flowchart of a data-driven intelligent monitoring method for the operation status of a roller screen provided by one embodiment of the present invention; Figure 2 A flow chart of a method for obtaining an actual jam probability provided by one embodiment of the present invention; Figure 3 A schematic diagram of a computer device for a data-driven intelligent monitoring device for the operation status of a roller screen provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effects employed by the present invention to achieve the intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a data-driven intelligent monitoring method for the operation status of a roller screen, including its specific implementation, structure, features, and effects. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following describes in detail a specific scheme of a data-driven intelligent monitoring method for the operation status of a roller screen provided by the present invention in conjunction with the accompanying drawings.

[0020] Example 1: This invention proposes a data-driven intelligent monitoring method for the operation status of roller screens. Figure 1 , which shows a flowchart of a method for intelligently monitoring the operation status of a roller screen based on data driving according to an embodiment of the present invention, the method comprising: Step S1: Obtain the rotational speed value of each screen shaft of the roller screen at each moment during the screening process.

[0021] A Hall-effect speed sensor is installed on each screen shaft of a roller screen. The roller screen's feed port is typically located at the top of the front end of the device. Material is fed through the feed port and falls onto the screen surface for screening. The roller screen is started, material is added through the feed port, and the sensor measures the speed of each screen shaft at every moment during the screening process. Each screen shaft is controlled by an independent reduction motor.

[0022] It should be noted that the data acquisition frequency of the sensors of all screen shafts of the roller screen is the same. In one implementation of the embodiment of the present invention, the data acquisition frequency of the sensors is set to 10 Hz.

[0023] Step S2: Obtain the actual jam possibility of each screen shaft at each moment based on the position and inclination of each screen shaft, the change trend of its speed value in the adjacent time period at each moment, and the fluctuation degree of the speed value in the adjacent time period.

[0024] Since the speed of the stuck screen shaft will drop rapidly when it is stuck during the operation of the roller screen, when the speed of a screen shaft shows a downward trend within a period of time, it can be considered that the screen shaft is very likely to be stuck. Therefore, the changing trend of the speed value of the screen shaft in the adjacent time period at each moment can measure the possibility of the screen shaft being stuck at each moment.

[0025] The rotation speed of the screen shaft at different positions is different. The screen shaft near the feed port directly bears the impact of the falling material and the initial accumulation. The increased pressure on the screen shaft may cause the screen shaft speed to decrease. It is normal for the speed value of the screen shaft closer to the feed port to show a downward trend, but it will increase the possibility of the normally working screen shaft getting stuck. Coarse screening and fine screening are determined by the screening inclination angle. Coarse screening uses a large-angle screen shaft, which has a fast material flow rate and significant load fluctuations. As a result, the speed value of the screen shaft with a larger inclination angle fluctuates more, which in turn increases the possibility of the screen shaft getting stuck through the speed change trend analysis. Fine screening uses a small-angle screen shaft, which has a slow and evenly distributed material flow rate and a relatively stable speed. As a result, when the speed value of the screen shaft with a smaller inclination angle shows a downward trend, the accuracy of the possibility of the screen shaft getting stuck is higher. When the screen shaft itself has large speed fluctuations, it will also cause the normally working screen shaft to show a greater possibility of getting stuck, but the actual possibility of getting stuck is relatively small. Therefore, by comprehensively considering the three factors of the screen shaft's position, inclination and speed fluctuation, the possibility of the screen shaft being stuck is adjusted, so that the actual possibility of sticking can effectively distinguish between real sticking and normal operating fluctuations, and significantly improve the accuracy and reliability of roller screen operation monitoring.

[0026] In one implementation of the embodiment of the present invention, the neighborhood period of each moment is composed of 30 adjacent moments before each moment, wherein the number of moments in the neighborhood period can be set according to specific circumstances.

[0027] Step S3: Obtain the jamming degree of each screen shaft at each moment based on the difference in actual jamming possibility and speed value between each screen shaft and its adjacent screen shaft at the same moment in the neighborhood time period at each moment, as well as the difference in changing trends of the actual jamming possibility of the adjacent screen shafts of each screen shaft in the neighborhood time period at each moment.

[0028] When a screen shaft is stuck, a large amount of material will accumulate on the stuck screen shaft, resulting in the subsequent material input not being able to complete the material screening according to the screening efficiency when there is no jam. As the material is added, the material on the screen shaft upstream of the jam position will be seriously accumulated, the pressure will increase, and the speed will decrease. However, the downstream screen shaft lacks subsequent material replenishment, the pressure will decrease, and the speed will recover. Therefore, the jam characteristics of the jammed screen shaft and the adjacent screen shaft are different, and the jam characteristics of the upstream screen shaft show an increasing trend while the downstream screen shaft shows a decreasing trend. The actual jam possibility is measured by the change trend of the speed value to measure the possibility of the screen shaft jamming. It requires accumulated anomalies to trigger, and it is impossible to analyze the early stage of jamming. The screen shaft speed is the direct physical manifestation of jamming. The combination of the two represents the jam characteristics of the screen shaft to achieve efficient and reliable jam diagnosis. Therefore, by comprehensively considering the actual jamming possibility difference and speed value difference between each screen shaft and its adjacent screen shafts, that is, the jamming characteristic difference, as well as the difference in the changing trend of the jamming possibility of each screen shaft and its adjacent screen shafts, the jamming degree of each screen shaft can be obtained, which can dynamically adapt to complex working conditions and improve the accuracy of screen shaft jamming analysis.

[0029] Step S4: According to the difference in the changing trends of the actual jamming possibilities of the screen shafts located before and after each screen shaft at the same moment in the neighborhood time period at each moment, adjust the jamming degree of each screen shaft at each moment, obtain the jamming failure probability of each screen shaft at each moment, and determine the jamming failure screen shaft of the roller screen at each moment.

[0030] The impact of a stuck screen shaft on the surrounding screen shafts exhibits spatial attenuation. The load upstream of the stuck location increases step by step due to material accumulation, and the actual jam probability of the upstream screen shaft gradually increases toward the feed port. The load downstream of the stuck location decreases step by step due to material shortage, and the actual jam probability of the downstream screen shaft gradually decreases toward the discharge port. During normal material delivery, the jam characteristics of the first screen shaft begin to affect the subsequent screen shafts, causing the jam characteristics of the entire upstream and downstream screen shafts of the tested screen shaft to have the same change trend. Therefore, to ensure the accuracy of selecting the screen shaft with a jamming fault, the jam degree of each screen shaft is adjusted based on the difference in the change trend of the actual jam probability of the screen shafts before and after each screen shaft. The probability of each screen shaft having a jamming fault is then determined, and the jammed screen shaft is selected. The independent reduction motor connected to the jammed screen shaft is turned off to stop the jammed screen shaft and isolate it. At the same time, the screen shaft indicator alarm of the roller screen is turned on to alert the staff for maintenance. The remaining screen shafts continue to operate normally and are monitored to ensure that the screening process is not interrupted.

[0031] Preferably, in some possible implementations of the present invention, the method for obtaining the actual jam probability can be found in Figure 2 , which shows a flow chart of a method for obtaining an actual jam probability provided by an embodiment of the present invention, the method comprising: Step S210: Obtain the standard normal speed value of each screen shaft; take the ratio of the speed value of each screen shaft at each moment to the standard normal speed value as the speed ratio; calculate the average of the difference between the speed ratios of adjacent moments in the neighborhood time period of each screen shaft at each moment, and perform normalization processing to obtain the initial jam possibility of each screen shaft at each moment.

[0032] Different screen shafts have different speed values ​​during normal operation. The speed ratio is obtained by analyzing the degree of decrease in the speed value of the screen shaft compared to the normal operating speed. The smaller the speed ratio, the more obvious the decrease in the speed of the screen shaft, and the greater the possibility of the screen shaft being stuck. It is known that the speed of the screen shaft shows a downward trend when it is stuck. The overall decrease in the speed of the screen shaft in the neighborhood period is measured by the average of the difference in the speed ratios of the screen shaft at adjacent moments in the neighborhood period of each moment. When the average value is larger, it shows that the overall decrease in the speed of the screen shaft in the neighborhood period is more obvious, the possibility of the screen shaft being stuck at each moment is greater, and the initial possibility of jamming is greater.

[0033] It should be noted that, in the embodiments of the present invention, the Norm function is used for normalization processing. Other normalization methods may also be selected, such as function conversion, maximum and minimum normalization, and other normalization methods, which are not limited here. The standard normal speed value is the speed value of each screen shaft when the roller screen has no material added and is operating normally. The weight of the material during screening will reduce the speed of the screen shaft. The speed ratio range is between 0 and 1. When calculating the initial jam probability, the difference in the speed ratios of adjacent moments refers to the difference in the speed values ​​of the previous moment and the next period of time between two adjacent moments.

[0034] Step S220: Obtain the horizontal angle of the screen shaft and set the position number of the screen shaft; obtain the jam correction amplitude of each screen shaft at each moment according to the position number, horizontal angle and fluctuation degree of the speed ratio of each screen shaft in the neighborhood time period at each moment.

[0035] The upstream screen shaft of the roller screen, that is, the screen shaft close to the feed inlet, usually adopts a larger inclination angle to speed up the material flow rate and achieve coarse screening; the downstream screen shaft adopts a smaller inclination angle to reduce the material flow rate to extend the screening time and ensure fine screening or particle size classification. In an embodiment of the present invention, the horizontal angle method includes: along the length direction of the roller screen, that is, the material flow direction is the X-axis, the height direction is the Y-axis, and the center point of the first screen shaft is used as the origin to establish a two-dimensional coordinate system, mark the center points of all screen shafts in the coordinate system, and use the angle between the line segment connecting two adjacent center points and the X-axis as the analysis angle of the previous center point. The analysis angle is the horizontal angle of the screen shaft corresponding to the center point, which represents the inclination angle of the screen shaft relative to the horizontal plane. In an embodiment of the present invention, the closer the screen shaft is to the feed inlet of the roller screen, the smaller the position number. Among them, the position number is an integer starting from 1.

[0036] It should be noted that the closer the screen shaft is to the feed port, that is, the smaller the position number, the greater the pressure on it, resulting in a more obvious drop in speed, which makes the screen shaft more likely to get stuck; the greater the inclination angle, that is, the larger the horizontal angle, the greater the speed fluctuation, which makes the screen shaft more likely to get stuck; the standard deviation of the speed ratio of each screen shaft at all times in the neighborhood period of each moment reflects the degree of fluctuation of the screen shaft's own speed value. The standard deviation, variance, range and interquartile range can all reflect the degree of fluctuation of a set of data. The standard deviation can also be replaced by variance, range or interquartile range. The larger the screen shaft's own speed fluctuation, the more likely it is that the screen shaft will get stuck. Therefore, the degree of fluctuation of the speed ratio, the position number and the horizontal angle are all positively correlated with the jam correction amplitude.

[0037] In a specific implementation of the embodiment of the present invention, the jam correction amplitude is expressed as follows:

[0038] Where, is the jam correction amplitude of each screen axis at the ath moment; B is the position number of each screen axis; is the horizontal angle of each screen axis; is the standard deviation of the speed ratio of each screen axis at all moments in the neighborhood period of moment a; sin is the sine function; Norm is the normalization function.

[0039] Step S230: using the jam correction amplitude to adjust the initial jam probability, and obtain the actual jam probability of each screen shaft at each moment.

[0040] It should be noted that if the jam correction amplitude of the screen shaft at each moment is larger, it indicates that the initial jam possibility of the screen shaft is more obviously larger than the actual jam possibility, then the actual jam possibility of the screen shaft should be smaller, and the actual jam possibility is smaller. The method of adjusting the initial jam possibility using the jam correction amplitude is as follows: the jam correction amplitude of each screen shaft at each moment is negatively correlated and normalized, the initial jam possibility is weighted using the processing result, and the weighted result is normalized to obtain the actual jam possibility of each screen shaft at each moment. In an embodiment of the present invention, a constant 1 is made a difference with the jam correction amplitude to achieve negative correlation and normalization, and the Norm function is selected for normalization. Other methods can also be selected, which will not be repeated here.

[0041] Preferably, in some possible implementation methods of the embodiments of the present invention, the method for obtaining the degree of jamming includes: forming a jam feature vector by performing a negative correlation mapping on the speed ratio of each screen shaft at each moment and the actual jam possibility; obtaining the jam feature difference of each screen shaft at each moment based on the difference in the jam feature vector of each screen shaft and its adjacent screen shaft at each moment and the modulus of the jam feature vector of each screen shaft at each moment; performing a straight line fitting on the actual jam possibility of each screen shaft at all moments in the neighborhood time period of each moment, and taking the slope of the obtained fitting straight line as the jam trend value of each screen shaft at each moment; obtaining the jam degree of each screen shaft at each moment based on the jam feature difference of each screen shaft in the neighborhood time period of each moment and the difference in the jam trend value of the adjacent screen shafts of each screen shaft at each moment.

[0042] It should be noted that, since the smaller the speed ratio, the greater the possibility of the screen shaft being stuck, it is necessary to perform negative correlation mapping on the speed ratio to analyze the screen shaft blocking characteristics; the speed ratio range is between 0 and 1, and the embodiment of the present invention realizes negative correlation mapping by making a difference between the constant 1 and the speed ratio. In other embodiments, negative correlation mapping can also be performed by taking the inverse, function conversion, etc. The blocking characteristic vector reflects the blocking performance of the screen shaft, and the changing trend of the blocking performance of the screen shaft is measured by the slope of the fitting line of the actual blocking possibility of the screen shaft in the neighborhood time period; when the blocking performance of each screen shaft itself is greater and the difference in blocking performance with its adjacent screen shaft is greater, it indicates that each screen shaft has a higher degree of blocking, and at the same time, the greater the difference in the changing trend of the blocking performance of the two adjacent screen shafts of each screen shaft, the greater the possibility that the blocking performance of the two adjacent screen shafts is opposite, and each screen shaft has a higher degree of blocking, and thus the probability of the screen shaft having real blocking is higher. In an embodiment of the present invention, the method for analyzing and obtaining the jam feature is as follows: the mean of the modulus of the difference between the jam feature vectors of each sieve axis and its adjacent sieve axis at each moment is calculated, and the product of the mean and the modulus of the jam feature vector of each sieve axis at each moment is used as the jam feature difference of each sieve axis at each moment. In this case, a two-dimensional coordinate system is established with time as the horizontal axis and the actual jam possibility as the vertical axis, and the actual jam possibility of the sieve axis at all moments in the neighborhood period of each moment is mapped to the coordinate system, and the coordinate points are obtained. The slope of the straight line obtained by fitting the coordinate points is the jam trend value.

[0043] In a specific implementation of the embodiment of the present invention, the jam degree is expressed by the formula:

[0044] Where, is the jamming degree of each screen shaft at the ath moment; The jam tendency value of the adjacent previous screen axis of each screen axis at each moment, and the position number of each screen axis is greater than the position number of its adjacent previous screen axis; 2 is the jam tendency value of the next sieve axis at each moment, and the position number of each sieve axis is smaller than the position number of the previous sieve axis; The minimum value of the jam characteristic difference of each sieve axis at all moments in the neighborhood period of moment a; It should be noted that if the minimum value of the difference in the jamming characteristics of all moments in the neighborhood period of the ath moment of each screen axis is still too large, it indicates that the jamming performance difference of the screen axis in the entire period of the corresponding neighborhood period is relatively large as a whole, and each screen axis has a high jamming degree; in other embodiments, It is replaced by the mean or median of the difference in the jamming characteristics of each sieve axis at all moments in the neighborhood period of the ath moment to measure the overall level of the jamming performance of the sieve axis in the corresponding neighborhood period.

[0045] It should be noted that this embodiment and subsequent embodiments do not analyze the screen shafts with the largest and smallest position numbers in the roller screen.

[0046] Preferably, in some possible implementation methods of the embodiments of the present invention, the method for obtaining the probability of a jam failure includes: performing linear fitting on the jam trend values ​​of the screen axes located before and after each screen axis at each moment, and taking the slopes of the obtained fitting lines as the upper screen axis trend value and the lower screen axis trend value of each screen axis at each moment; taking the absolute value of the difference between the sign values ​​of the upper screen axis trend value and the lower screen axis trend value as the trend difference of each screen axis at each moment; judging whether the trend difference is equal to a constant 2, and if so, connecting the jam trend values ​​of the screen axes with the largest and smallest position numbers in the roller screen to obtain an analysis segment, and using the absolute value of the difference between the jam trend value of each screen axis at each moment and the slope of the analysis segment to adjust the jam degree and obtain the jam failure probability of each screen axis at each moment; if not, normalizing the jam degree to obtain the jam failure probability of each screen axis at each moment.

[0047] It should be noted that the symbol value is -1, 0, 1, the symbol value of a positive number is 1, the symbol value of a negative number is -1, and the symbol value of zero is 0. The jamming trend value of all screen shafts is affected by the global material flow, which is manifested as a uniform change such as an increase or decrease in the overall load, and the jam will destroy the global consistency, causing its local trend to deviate significantly from the global trend. If the trend difference is equal to the constant 2, it indicates that the jamming performance trends of the upstream and downstream screen shafts of each screen shaft are opposite, and the screen shaft speed change is caused by the jamming of the rotating shaft. The slope of the analysis line segment obtained by connecting the jamming trend values ​​of the head and tail screen shafts represents the global trend, that is, the normal change caused by material delivery; when the difference between the jamming trend value of the screen shaft and the slope of the analysis line segment is smaller, the screen shaft trend is more consistent with the global trend, indicating that the screen shaft belongs to the normal speed change caused by the material delivery factor; conversely, the screen shaft is more strongly affected by the jam. Therefore, the degree of jamming cannot accurately reflect the degree of jamming of the screen shaft. It is necessary to increase the degree of jamming of the screen shaft by utilizing the difference between the jamming trend value of the screen shaft and the slope of the analysis line segment, so that the probability of its existence of real jamming is higher. In an embodiment of the present invention, the method for adjusting the degree of jamming is as follows: the absolute value of the difference between the jamming trend value of each screen shaft at each moment and the slope of the analysis line segment is normalized, and the product of the sum of the normalized result and the constant 1 and the degree of jamming is normalized to obtain the jamming failure probability of each screen shaft at each moment, and the Norm function is selected for normalization. If the trend difference is not equal to the constant 2, it shows that the jamming performance trend of the upstream screen shaft and the downstream screen shaft of each screen shaft is consistent, which belongs to the change of screen shaft speed caused by normal material delivery. The jamming degree of the rotating shaft can directly reflect the real jamming probability. This embodiment utilizes the spatial correlation and fault locality of the screen shaft of the roller screen to analyze the jamming degree of the screen shaft, thereby improving the efficiency and robustness of the jammed screen shaft detection.

[0048] In one implementation of an embodiment of the present invention, the method for obtaining the analysis line segment is: a two-dimensional coordinate system is established with the position number of the screen shaft as the horizontal axis and the jamming trend value of the screen shaft as the vertical axis, and the jamming trends of the screen shafts with the largest and smallest position numbers in the roller screen are mapped to the two-dimensional coordinate system to obtain two coordinate points, and the line segment obtained by connecting the two coordinate points is the analysis line segment.

[0049] It should be noted that, in the embodiment of the present invention, the Norm function is used for normalization processing, and other normalization methods may also be selected, such as function conversion, maximum and minimum normalization, etc., which are not limited here.

[0050] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the stuck screen shaft includes: determining the jam abnormality threshold of the roller screen at each moment, and selecting the screen shaft corresponding to the jam abnormality threshold that is greater than the jam abnormality threshold from the jam failure probability of all the screen shafts of the roller screen at each moment as the jammed screen shaft of the roller screen at each moment. It should be noted that the screen shaft with a greater jam failure probability is more likely to be a jammed screen shaft. In the embodiment of the present invention, the jam abnormality threshold is a classification threshold determined when the jam failure probability of all the screen shafts of the roller screen at each moment is binary classified using the Fisher discriminant method; another embodiment can use the mean of the jam failure probability of all the screen shafts at the same moment as the jam abnormality threshold at each moment; other embodiments can set a constant between 0 and 1 according to the specific situation.

[0051] So far, the present invention is completed.

[0052] Example 2: The present invention also proposes a computer device schematic diagram of a data-driven intelligent monitoring device for the operation status of a roller screen, see Figure 3 The computer device includes a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program 503, the computer device can execute any one of the data-driven intelligent monitoring methods for the operating status of the roller screen introduced above.

[0053] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a data-driven intelligent monitoring method for the operating status of a roller screen provided in an embodiment of the present application.

[0054] In this embodiment, the device can be divided into functional modules based on the above-described method examples. For example, each functional module can be mapped to a specific functional module, or two or more functions can be integrated into a single processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used.

[0055] In the case of dividing the modules into modules corresponding to their functions, the device may further include a communication module, a signal analysis module, a complexity analysis module, a positioning module, etc. It should be noted that all relevant contents of the various steps involved in the above method embodiment can be referred to the functional description of the corresponding functional modules and will not be repeated here.

[0056] It should be understood that the device provided in this embodiment is used to execute the above-mentioned data-driven intelligent monitoring method for the operation status of the roller screen, and thus can achieve the same effect as the above-mentioned implementation method.

[0057] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the operation of the device. The storage module may be used to support the device in executing mutual program codes, etc.

[0058] The processing module may be a processor or controller that implements or executes the various exemplary logic blocks, modules, and circuits disclosed herein. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor (DSP) and a microprocessor, and the like. The storage module may be a memory.

[0059] Example 3: This embodiment also provides a computer-readable storage medium, which stores computer program code. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement a data-driven intelligent monitoring method for the operation status of a roller screen provided in the above embodiment.

[0060] Example 4: This embodiment also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the above-mentioned related steps to implement a data-driven intelligent monitoring method for the operating status of a roller screen provided in the above embodiment.

[0061] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0062] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0063] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0064] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A data-driven intelligent monitoring method for roller screen operation status, characterized in that: The method includes: Obtain the rotational speed value of each screen shaft of the roller screen at each moment during the screening process; According to the position and inclination of each screen shaft and the change trend of its speed value in the adjacent time period at each moment, as well as the fluctuation degree of the speed value in the adjacent time period, the actual jam possibility of each screen shaft at each moment is obtained; Obtain the jamming degree of each sieve shaft at each moment based on the difference in the actual jamming probability and the speed value of each sieve shaft in the neighborhood time period at each moment and the difference in the change trend of the actual jamming probability of the adjacent sieve shafts of each sieve shaft in the neighborhood time period at each moment; According to the difference in the changing trends of the actual jamming possibilities of the screen shafts located before and after each screen shaft at the same moment in the neighborhood period at each moment, the jamming degree of each screen shaft at each moment is adjusted, the jamming failure probability of each screen shaft at each moment is obtained, and the jamming failure screen shaft of the roller screen at each moment is determined.

2. The data-driven intelligent monitoring method for the operation status of a roller screen according to claim 1 is characterized in that: The method of obtaining the actual jam probability of each screen shaft at each moment includes: Obtaining the standard normal speed value of each sieve shaft; taking the ratio of the speed value of each sieve shaft at each moment to the standard normal speed value as the speed ratio; calculating the mean of the difference between the speed ratios of adjacent moments within the neighborhood time period of each sieve shaft at each moment, and performing normalization processing to obtain the initial jam probability of each sieve shaft at each moment; Obtain the horizontal angle of the screen shaft and set the position number of the screen shaft; obtain the jam correction amplitude of each screen shaft at each moment based on the position number, horizontal angle and fluctuation degree of the speed ratio of each screen shaft in its neighborhood time period at each moment; The initial jam possibility is adjusted using the jam correction amplitude to obtain the actual jam possibility of each screen shaft at each moment.

3. The data-driven intelligent monitoring method for the operation status of a roller screen according to claim 2, characterized in that: The obtaining of the jamming degree of each screen shaft at each moment comprises: A jam feature vector is formed by performing negative correlation mapping on the speed ratio of each screen shaft at each moment and the actual jam possibility; Obtain the jam feature difference of each sieve axis at each moment according to the difference in jam feature vectors between each sieve axis and its adjacent sieve axis at each moment and the modulus of the jam feature vector of each sieve axis at each moment; Performing a straight line fitting on the actual jam probability of each sieve axis at all moments in a neighborhood period at each moment, and using the slope of the obtained fitting line as the jam tendency value of each sieve axis at each moment; The jamming degree of each sieve axis at each moment is obtained based on the jamming feature difference of each sieve axis in the neighborhood time period at each moment and the jamming trend value difference of the adjacent sieve axes of each sieve axis at each moment.

4. The data-driven intelligent monitoring method for the operation status of a roller screen according to claim 3 is characterized in that: The obtaining of the jam failure probability of each screen shaft at each moment includes: Performing linear fitting on the jamming trend values ​​of the sieve axes located before and after each sieve axis at each moment, respectively, and using the slopes of the obtained fitting lines as the upper sieve axis trend value and the lower sieve axis trend value of each sieve axis at each moment; The absolute value of the difference between the sign values ​​of the upper sieve axis trend value and the lower sieve axis trend value is taken as the trend difference degree of each sieve axis at each moment; Determine whether the trend difference is equal to a constant of 2. If so, connect the jamming trend values ​​of the screen shafts with the largest and smallest position numbers in the roller screen to obtain an analysis segment. Use the absolute value of the difference between the jamming trend value of each screen shaft at each moment and the slope of the analysis segment to adjust the jamming degree and obtain the jamming failure probability of each screen shaft at each moment. If not, normalize the jamming degree to obtain the jamming failure probability of each screen shaft at each moment.

5. The data-driven intelligent monitoring method for roller screen operation status according to claim 1 is characterized in that: The method of determining the jammed fault screen shaft of the roller screen at each moment includes: Determine the jamming abnormality threshold of the roller screen at each moment, and select the corresponding screen axis greater than the jamming abnormality threshold from the jamming failure probability of all screen axes of the roller screen at each moment as the jamming screen axis of the roller screen at each moment.

6. The data-driven intelligent monitoring method for the operation status of a roller screen according to claim 2, characterized in that: The adjusting the initial jam possibility by using the jam correction amplitude includes: The jam correction amplitude of each screen axis at each moment is negatively correlated and normalized, the initial jam possibility is weighted using the processing result, and the weighted result is normalized to obtain the actual jam possibility of each screen axis at each moment.

7. The data-driven intelligent monitoring method for the operation status of a roller screen according to claim 2, characterized in that: The fluctuation degree of the speed ratio, the position number and the horizontal angle are all positively correlated with the jam correction amplitude.

8. The data-driven intelligent monitoring method for roller screen operation status according to claim 2, characterized in that: The closer the screen shaft is to the feed port of the roller screen, the smaller the position number is.

9. The data-driven intelligent monitoring method for roller screen operation status according to claim 3, characterized in that: The obtaining of the jam characteristic difference of each screen shaft at each moment includes: Calculate the mean of the modulus of the difference between the jam feature vectors of each sieve axis and its adjacent sieve axis at each moment, and take the product of the mean and the modulus of the jam feature vector of each sieve axis at each moment as the jam feature difference of each sieve axis at each moment.

10. The data-driven intelligent monitoring method for roller screen operation status according to claim 5, characterized in that: The jam abnormality threshold is a classification threshold determined by using the Fisher discriminant method to perform a binary classification on the jam failure probability of all screen shafts of the roller screen at each moment.

Images