Data-driven roller screen operation state intelligent monitoring method

Abstract

The present application relates to the technical field of mechanical component failure prediction, in particular to a method for intelligent monitoring of the operating 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 each time interval, and the fluctuation degree of the rotating speed value in the time interval, the actual jam possibility is obtained. According to the difference between the actual jam possibility of each screen shaft in each time interval and the actual jam possibility of the adjacent screen shaft at the same time, the difference between the rotating speed values, and the difference between the change trends of the actual jam possibilities of the adjacent screen shafts in the time interval, the jam degree is obtained. According to the difference between the change trends of the actual jam possibilities of the screen shafts located before and after each screen shaft, the jam degree is adjusted, the jam failure probability is obtained, and the jam failure screen shaft of the roller screen at each time is determined. The jam failure probability can more comprehensively reflect the working state of the screen shaft, and effectively improve the accuracy of the jam failure judgment of the screen shaft.

Description

Technical Field

[0001] This invention relates to the field of mechanical component failure prediction technology, and specifically to a data-driven intelligent monitoring method for the operating status of a roller screen. Background Technology

[0002] Roller screens, as important screening equipment, are widely used in mining, coal, and power industries. During operation, unexpected malfunctions such as screen shaft jamming, bearing damage, screen breakage, and motor failure can cause unexpected shutdowns. Screen shaft jamming is a common malfunction that severely impacts production continuity and safety. Therefore, it is necessary to monitor the operating status of roller screens to identify the screen shafts experiencing jamming.

[0003] Existing methods monitor the rotational speed of each screen shaft in real time. When the rotational speed of a screen shaft is lower than a set threshold for a certain period of time, it is determined that the screen shaft is jammed. However, because the screen shafts at different positions and angles are subjected to different pressures, and the material fed into the feed inlet is difficult to control, the rotational speed of the screen shaft is difficult to reflect the actual jamming situation. As a result, the accuracy of judging the screen shaft with jamming fault by the rotational speed of the screen shaft is low. Summary of the Invention

[0004] To address the technical problem of low accuracy in identifying screen shafts with jamming faults due to the inability of screen shaft rotation speed to accurately reflect the actual jamming situation, this invention aims to provide a data-driven intelligent monitoring method for the operating status of roller screens. The specific technical solution adopted is as follows:

[0005] This invention proposes a data-driven intelligent monitoring method for the operating status of a roller screen, the method comprising:

[0006] Obtain the rotational speed of each screen shaft of the roller screen at each moment during the screening process;

[0007] Based on the position and inclination angle of each screen shaft and the trend of its rotational speed value in the neighborhood time period at each moment, as well as the degree of fluctuation of the rotational speed value in the neighborhood time period, the actual jamming probability of each screen shaft at each moment is obtained.

[0008] Based on the differences in the actual jamming probability and rotational speed of each screen shaft with its neighboring screen shafts at the same time within the neighborhood time period at each time, and the differences in the changing trend of the actual jamming probability of each screen shaft with its neighboring screen shafts at each time within the neighborhood time period at each time, the jamming degree of each screen shaft at each time is obtained.

[0009] Based on the difference in the changing trend of the actual jamming probability of the screen shafts located before and after each screen shaft in the neighborhood time period at each time, the jamming degree of each screen shaft at each time is adjusted, the jamming failure probability of each screen shaft at each time is obtained, and the jamming failure screen shaft of the roller screen at each time is determined.

[0010] Furthermore, obtaining the actual jamming probability of each screen shaft at each moment includes:

[0011] Obtain the standard normal rotational speed value of each screen shaft; take the ratio of the rotational speed value of each screen shaft at each moment to the standard normal rotational speed value as the rotational speed ratio; calculate the mean of the difference between the rotational 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 jamming probability of each screen shaft at each moment.

[0012] Obtain the horizontal angle of the screen shaft and set the position number of the screen shaft; based on the position number of each screen shaft, the horizontal angle and the fluctuation degree of the rotational speed ratio in the neighborhood time period of each time, obtain the jamming correction amplitude of each screen shaft at each time.

[0013] The initial jamming probability is adjusted using the jamming correction amplitude to obtain the actual jamming probability of each screen shaft at each moment.

[0014] Furthermore, obtaining the degree of jamming of each screen shaft at each moment includes:

[0015] The result of negatively mapping the rotational speed ratio of each screen shaft at each moment to the actual jamming probability constitutes a jamming feature vector;

[0016] Based on the difference in the jamming feature vector between each sieve shaft and its adjacent sieve shaft at each time step and the magnitude of the jamming feature vector of each sieve shaft at each time step, the jamming feature difference of each sieve shaft at each time step is obtained.

[0017] For each sieve axis, a linear fit is performed on the actual jamming probability at all times within the neighborhood time period at each time, and the slope of the resulting fitted line is used as the jamming trend value of each sieve axis at each time.

[0018] The degree of jamming of each screen shaft at each time moment is obtained based on the difference in jamming characteristics of each screen shaft within the neighborhood time period at each time moment, and the difference in the jamming trend value of each screen shaft's adjacent screen shafts at each time moment.

[0019] Furthermore, obtaining the jamming failure probability of each screen shaft at each moment includes:

[0020] For the jamming trend values ​​of the screen shafts located before and after each screen shaft at each time moment, a straight line is fitted, and the slope of the fitted straight line is used as the upper screen shaft trend value and lower screen shaft trend value of each screen shaft at each time moment.

[0021] The absolute value of the difference between the sign values ​​of the trend values ​​of the upper and lower screen axes is used as the trend difference degree of each screen axis at each time.

[0022] Determine whether the trend difference is equal to a constant 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 line segment. Use the absolute value of the difference between the jamming trend value of each screen shaft at each time and the slope of the analysis line segment to adjust the jamming degree and obtain the jamming failure probability of each screen shaft at each time. If not, normalize the jamming degree to obtain the jamming failure probability of each screen shaft at each time.

[0023] Furthermore, determining the jammed screen shaft of the roller screen at each moment includes:

[0024] Determine the jamming fault threshold of the roller screen at each time step, and select the screen shaft with a jamming fault probability greater than the jamming fault threshold from all screen shafts of the roller screen at each time step as the jamming screen shaft of the roller screen at each time step.

[0025] Further, adjusting the initial jamming probability using the jamming correction amplitude includes:

[0026] The jamming correction magnitude of each screen shaft at each time step is negatively correlated and normalized. The initial jamming probability is weighted using the processing result, and the weighted result is normalized to obtain the actual jamming probability of each screen shaft at each time step.

[0027] Furthermore, the fluctuation degree of the speed ratio, the position number, and the horizontal angle are all positively correlated with the jamming correction amplitude.

[0028] Furthermore, the closer the screen shaft is to the feed inlet of the roller screen, the smaller its position number.

[0029] Furthermore, obtaining the jamming characteristic difference of each sieve shaft at each time step includes:

[0030] Calculate the mean of the magnitude of the difference between the jamming feature vector of each sieve axis and its adjacent sieve axis at each time step. Multiply the mean by the magnitude of the jamming feature vector of each sieve axis at each time step to obtain the jamming feature difference of each sieve axis at each time step.

[0031] Furthermore, the jamming fault threshold is a classification threshold determined by using Fisher's discriminant method to perform binary classification of the jamming fault probability of all screen shafts of the roller screen at each moment.

[0032] The present invention has the following beneficial effects:

[0033] In this embodiment of the invention, because the pressure on the screen shafts at different positions and inclination angles of the roller screen varies, and the rotational speeds of different screen shafts differ, the rotational speed values ​​are adjusted to reflect the potential for screen shaft jamming by comprehensively considering these factors. This allows the actual probability of jamming to be effectively distinguished from genuine jamming and fluctuations under normal operating conditions. Since material accumulation on a jammed screen shaft can lead to differences in the jamming situation of its adjacent screen shafts, the degree of jamming on each screen shaft is obtained by comprehensively considering the differences in the actual probability of jamming between each screen shaft and its adjacent screen shafts, the differences in rotational speed values, and the differences in the changing trends of the probability of jamming between each screen shaft and its adjacent screen shafts. It can dynamically adapt to complex working conditions and improve the accuracy of screen shaft jamming analysis. The jammed screen shaft has a spatial decay effect on the jamming of surrounding screen shafts. In order to eliminate the misjudgment caused by factors such as the difficulty in controlling the material input at the feed inlet, the degree of jamming of each screen shaft is adjusted by the difference in the change trend of the actual jamming probability of each screen shaft before and after each screen shaft, the jamming failure probability is obtained, and the jammed screen shaft is selected. It makes full use of the spatial decay characteristics between screen shafts, which is more in line with the actual situation, thereby improving the accuracy of screen shaft jamming failure judgment in real-time screening. Attached Figure Description

[0034] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 The flowchart illustrates the steps of a data-driven intelligent monitoring method for the operating status of a roller screen, as provided in one embodiment of the present invention.

[0036] Figure 2 A flowchart illustrating a method for obtaining the actual probability of jamming according to an embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram of a computer device for intelligent monitoring of the operating status of a data-driven roller screen, provided as an embodiment of the present invention. Detailed Implementation

[0038] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a data-driven intelligent monitoring method for the operating status of a roller screen proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0039] Unless otherwise defined, 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 pertains.

[0040] The following description, in conjunction with the accompanying drawings, details a specific scheme for a data-driven intelligent monitoring method for the operating status of a roller screen provided by the present invention.

[0041] Example 1:

[0042] This invention proposes a data-driven intelligent monitoring method for the operating status of roller screens. Please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of a data-driven intelligent monitoring method for the operating status of a roller screen, according to an embodiment of the present invention. The method includes:

[0043] Step S1: Obtain the rotational speed of each screen shaft of the roller screen at each moment during the screening process.

[0044] Each screen shaft of the roller screen is equipped with a Hall effect speed sensor. The feed inlet of the roller screen is usually located at the top of the front end of the equipment. The material is fed into the feed inlet and falls onto the screen surface for screening. The roller screen is started, and material is fed into the feed inlet. The sensors collect the rotational speed value of each screen shaft at each moment during the screening process. Each screen shaft is controlled by an independent geared motor.

[0045] It should be noted that the data acquisition frequency of the sensors on all screen shafts of the roller screen is the same. In one implementation of this invention, the data acquisition frequency of the sensors is set to 10 Hz.

[0046] Step S2: Based on the position and inclination angle of each screen shaft and the trend of its rotational speed value in the neighborhood time period at each moment, as well as the degree of fluctuation of the rotational speed value in the neighborhood time period, obtain the actual jamming probability of each screen shaft at each moment.

[0047] Since the rotational speed of the screen shaft will drop rapidly when the screen shaft is jammed during the operation of the roller screen, if the rotational speed of a certain screen shaft shows a downward trend over a period of time, it can be considered that the screen shaft is very likely to be jammed. Therefore, the trend of the rotational speed of the screen shaft in the neighborhood of each moment can measure the possibility of jamming of the screen shaft at each moment.

[0048] The rotational speed of the screen shaft varies at different locations. Screen shafts closer to the feed inlet directly bear the impact of falling material and initial accumulation, increasing pressure and potentially causing a decrease in rotational speed. This indicates that a decreasing rotational speed closer to the feed inlet is normal, but it increases the likelihood of jamming on a normally functioning screen shaft. The difference between coarse and fine screening is determined by the screening angle. Coarse screening uses a large-angle screen shaft, where material flow is fast and load fluctuations are significant. This results in greater rotational speed fluctuations for screen shafts with larger angles, thus increasing the likelihood of jamming based on rotational speed trends. Fine screening uses a small-angle screen shaft, where material flow is slow and evenly distributed, resulting in more stable rotational speeds. Therefore, a decreasing rotational speed on screen shafts with smaller angles increases the accuracy of identifying jamming. Even with significant rotational speed fluctuations within the screen shaft itself, a normally functioning screen shaft may appear to have a higher likelihood of jamming, although the actual likelihood of jamming is lower. Therefore, by comprehensively considering the three factors of screen shaft position, tilt angle and speed fluctuation, the possibility of screen shaft jamming can be adjusted, so that the actual jamming probability can be effectively distinguished from real jamming and normal operating condition fluctuations, significantly improving the accuracy and reliability of roller screen operation monitoring.

[0049] In one implementation of this invention, the neighborhood time period of each time period is composed of 30 adjacent time periods before each time period, wherein the number of time periods in the neighborhood time period can be set according to the specific situation.

[0050] Step S3: Based on the differences in the actual jamming probability and rotational speed of each screen shaft with its neighboring screen shafts at the same time within the neighborhood time period at each time, and the differences in the changing trends of the actual jamming probability of each screen shaft with its neighboring screen shafts at each time within the neighborhood time period at each time, obtain the jamming degree of each screen shaft at each time.

[0051] When a screen shaft is jammed, a large amount of material accumulates on the jammed shaft, preventing subsequent material input from achieving the same screening efficiency as when no jamming occurs. As material is added, the upstream screen shaft experiences severe accumulation, increasing pressure and decreasing rotational speed, while the downstream screen shaft, lacking subsequent material replenishment, experiences reduced pressure and its rotational speed increases. Therefore, the jamming characteristics of a jammed screen shaft differ from those of adjacent screen shafts, with the upstream screen shaft showing an increasing trend in jamming characteristics and the downstream screen shaft showing a decreasing trend. The likelihood of actual jamming can be assessed by observing the trend of rotational speed changes, but this requires accumulated anomalies to trigger, making it impossible to analyze the initial stage of jamming. Screen shaft rotational speed is a direct physical manifestation of jamming; combining both factors represents the jamming characteristics of the screen shaft, enabling efficient and reliable jamming diagnosis. Therefore, by combining the differences in the actual jamming probability and rotational speed of each screen shaft with the differences in jamming characteristics between it and its adjacent screen shafts, as well as the differences in the changing trends of the jamming probability of each screen shaft with its adjacent screen shafts, the degree of jamming of each screen shaft can be obtained. This allows for dynamic adaptation to complex working conditions and improves the accuracy of screen shaft jamming analysis.

[0052] Step S4: Based on the difference in the changing trend of the actual jamming probability of the screen shafts located before and after each screen shaft in the neighborhood time period at each time, adjust the jamming degree of each screen shaft at each time, obtain the jamming failure probability of each screen shaft at each time, and determine the jamming failure screen shaft of the roller screen at each time.

[0053] The impact of a jammed screen shaft on surrounding screen shafts exhibits spatial decay. Upstream of the jamming location, material accumulation causes the load to increase progressively, leading to a gradual increase in the actual jamming probability of the upstream screen shaft towards the feed inlet. Downstream of the jamming location, material shortage causes the load to decrease progressively, leading to a gradual decrease in the actual jamming probability of the downstream screen shaft towards the discharge outlet. However, during normal material feeding, the jamming characteristics of subsequent screen shafts are affected starting from the first screen shaft, resulting in the same trend in the jamming characteristics of the entire upstream and downstream screen shafts under test. Therefore, to ensure the accuracy of selecting screen shafts with jamming faults, the degree of jamming for each screen shaft is adjusted by analyzing the difference in the trend of the actual jamming probability of each screen shaft before and after it, obtaining the probability of jamming faults for each screen shaft, and then selecting the screen shaft with the jamming fault. The independent geared motor connected to the screen shaft with the jamming fault is shut down to stop the jammed screen shaft and isolate it. At the same time, the screen shaft indicator light alarm of the roller screen is activated to remind the staff to perform maintenance. The remaining screen shafts continue to operate normally and be monitored to ensure that the screening process is not interrupted.

[0054] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the actual probability of jamming is described in [reference needed]. Figure 2 The diagram illustrates a flowchart of a method for obtaining the actual probability of jamming according to an embodiment of the present invention, the method comprising:

[0055] Step S210: Obtain the standard normal rotation speed value of each screen shaft; take the ratio of the rotation speed value of each screen shaft at each moment to the standard normal rotation speed value as the rotation speed ratio; calculate the mean of the difference between the rotation 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 jamming probability of each screen shaft at each moment.

[0056] Different screen shafts have different rotational speeds during normal operation. Analyzing the decrease in rotational speed compared to the normal operating speed yields a speed ratio. A smaller speed ratio indicates a more significant decrease in screen shaft speed, suggesting a higher likelihood of screen shaft jamming. It is known that the rotational speed of a jammed screen shaft exhibits a decreasing trend. The average difference between the speed ratios of adjacent time points within a neighborhood of each time point measures the overall decrease in screen shaft speed over that neighborhood. A larger average value indicates a more significant overall decrease in screen shaft speed over that neighborhood, a higher likelihood of screen shaft jamming at any given time, and a greater initial probability of jamming.

[0057] It should be noted that the Norm function is used for normalization in this embodiment of the invention. Other normalization methods can also be selected, such as function transformation, max-min normalization, etc., and are not limited here. The standard normal rotational speed value is the rotational speed of each screen shaft when the roller screen is running normally without any material being fed in. During material screening, the weight of the material will cause the screen shaft rotational speed to decrease, and the rotational speed ratio ranges from 0 to 1. When calculating the initial jamming probability, the difference in rotational speed ratio between adjacent moments refers to the difference in rotational speed values ​​between the previous moment and the next moment.

[0058] Step S220: Obtain the horizontal angle of the screen shaft and set the position number of the screen shaft; based on the position number of each screen shaft, the horizontal angle and the fluctuation of the rotational speed ratio in the neighborhood time period at each moment, obtain the jamming correction amplitude of each screen shaft at each moment.

[0059] The upstream screen shaft of a roller screen, i.e., the screen shaft near the feed inlet, typically adopts a larger inclination angle to accelerate material flow and achieve coarse screening; the downstream screen shaft adopts a smaller inclination angle to reduce material flow and extend screening time, ensuring fine screening or particle size classification. In this embodiment of the invention, the horizontal angle method includes: establishing a two-dimensional coordinate system with the length direction of the roller screen (i.e., the material flow direction) as the X-axis and the height direction as the Y-axis, with the center point of the first screen shaft as the origin; marking the center points of all screen shafts in the coordinate system; and using 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, representing the inclination angle of the screen shaft relative to the horizontal plane. In this embodiment of the invention, the closer the screen shaft is to the feed inlet of the roller screen, the smaller its position number. The position number is an integer starting from 1.

[0060] It should be noted that screen shafts closer to the feed inlet (i.e., those with smaller position numbers) experience greater pressure, leading to a more significant decrease in rotational speed and thus a higher likelihood of jamming. Similarly, screen shafts with larger inclination angles (i.e., larger horizontal angles) exhibit greater rotational speed fluctuations, further increasing the likelihood of jamming. The standard deviation of the rotational speed ratio across all time intervals within a neighborhood of each screen shaft reflects its rotational speed fluctuation. Standard deviation, variance, range, and interquartile range all reflect the volatility of a set of data. The standard deviation can be replaced with variance, range, or interquartile range. Screen shafts with larger rotational speed fluctuations are more prone to jamming. Therefore, the degree of rotational speed fluctuation, position number, and horizontal angle are all positively correlated with the jamming correction magnitude.

[0061] In one specific implementation of this invention, the Cassette correction magnitude is expressed by the formula:

[0062]

[0063] In the formula, B represents the jamming correction magnitude for each screen shaft at time a; B is the position number for each screen shaft. The horizontal angle of each sieve shaft; Let be the standard deviation of the rotational speed ratio of each sieve axis within the neighborhood time period at time a; sin is the sine function; Norm is the normalization function.

[0064] Step S230: Adjust the initial jamming probability using the jamming correction amplitude, and obtain the actual jamming probability of each screen shaft at each moment.

[0065] It should be noted that the larger the jamming correction amplitude of the screen shaft at each moment, the more significantly the initial jamming probability of the screen shaft is compared to the actual probability of jamming. Therefore, the actual probability of jamming should be smaller, and the actual jamming probability should be lower. The method of adjusting the initial jamming probability using the jamming correction amplitude is as follows: negatively correlate and normalize the jamming correction amplitude of each screen shaft at each moment; use the processing result to weight the initial jamming probability; and normalize the weighted result to obtain the actual jamming probability of each screen shaft at each moment. In this embodiment of the invention, the constant 1 is negatively correlated and normalized by the difference between it and the jamming correction amplitude. The Norm function is used for normalization, but other methods can also be used, which will not be elaborated here.

[0066] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the degree of jamming includes: constructing a jamming feature vector by negatively correlated mapping of the rotational speed ratio of each screen shaft at each moment with the actual jamming probability; obtaining the jamming feature difference of each screen shaft at each moment based on the difference between the jamming feature vectors of each screen shaft and its adjacent screen shafts at each moment and the magnitude of the jamming feature vector of each screen shaft at each moment; performing linear fitting on the actual jamming probability of each screen shaft at all moments in the neighborhood time period of each moment, and using the slope of the obtained fitted line as the jamming trend value of each screen shaft at each moment; obtaining the degree of jamming of each screen shaft at each moment based on the jamming feature difference of each screen shaft in the neighborhood time period of each moment and the difference in the jamming trend value of each screen shaft's adjacent screen shafts at each moment.

[0067] It should be noted that since a smaller speed ratio increases the likelihood of screen shaft jamming, a negative correlation mapping is needed for the speed ratio to analyze the screen shaft jamming characteristics. The speed ratio ranges from 0 to 1. In this embodiment, a negative correlation mapping is achieved by subtracting the speed ratio from a constant 1. In other embodiments, the reciprocal or function transformation can also be used for negative correlation mapping. The jamming feature vector reflects the jamming performance of the screen shaft. The slope of the fitted line of the actual jamming probability of the screen shaft in the neighborhood time period measures the changing trend of the screen shaft's jamming performance. The greater the jamming performance of each screen shaft itself and the greater the difference in jamming performance with its adjacent screen shafts, the higher the degree of jamming of each screen shaft. At the same time, the greater the difference in the changing trends of the jamming performance of two adjacent screen shafts, the greater the likelihood that the changing trends of the jamming performance of the two adjacent screen shafts are opposite. Each screen shaft has a high degree of jamming, and therefore, the higher the probability that the screen shaft is actually jammed. In this embodiment of the invention, the method for obtaining jamming features is as follows: The mean of the magnitudes of the differences between the jamming feature vectors of each sieve axis and its adjacent sieve axes at each time step is calculated. The product of the mean and the magnitude of the jamming feature vector of each sieve axis at each time step is used as the jamming feature difference of each sieve axis at each time step. A two-dimensional coordinate system is established with time as the horizontal axis and actual jamming probability as the vertical axis. The actual jamming probability of each sieve axis at each time step within its neighborhood time period is mapped to the coordinate system to obtain coordinate points. The slope of the straight line obtained by fitting the coordinate points is the jamming trend value.

[0068] In one specific implementation of this invention, the degree of congestion is expressed by the formula:

[0069]

[0070] In the formula, The degree of jamming for each sieve shaft at time a; The jamming trend value of the preceding sieve shaft for each sieve shaft at each time step, with the position number of each sieve shaft being greater than the position number of its preceding sieve shaft. 2 is the jamming trend value of the next adjacent screen axis for each screen axis at each time step, and the position number of each screen axis is less than the position number of its previous adjacent screen axis. The minimum difference in jamming characteristics among all times in the neighborhood time period of each sieve axis at time a; This is an absolute value function. It should be noted that if the minimum value of the jamming characteristic differences among all times in the neighborhood time period of each sieve axis at time a is still relatively large, it indicates that the overall jamming performance of that sieve axis varies significantly throughout the corresponding neighborhood time period, thus each sieve axis exhibits a high degree of jamming. In other embodiments, it is also possible to... Replace it with the mean or median of the differences in jamming characteristics among all times in the neighborhood of each sieve axis at time a, to measure the overall level of jamming performance of the sieve axis in the corresponding neighborhood.

[0071] It should be noted that neither this embodiment nor subsequent embodiments analyze the screen shafts with the largest and smallest position numbers in the roller screen.

[0072] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the jamming failure probability includes: performing linear fitting on the jamming trend values ​​of the screen shafts located before and after each screen shaft at each time moment, and taking the slope of the obtained fitted line as the upper screen shaft trend value and lower screen shaft trend value of each screen shaft at each time moment; taking the absolute value of the difference between the sign values ​​of the upper screen shaft trend value and the lower screen shaft trend value as the trend difference degree of each screen shaft at each time moment; determining whether the trend difference degree is equal to a constant 2, if so, then connecting the jamming trend values ​​of the screen shafts with the largest and smallest position numbers in the roller screen to obtain an analysis line segment, and using the absolute value of the difference between the jamming trend value of each screen shaft at each time moment and the slope of the analysis line segment, adjusting the jamming degree to obtain the jamming failure probability of each screen shaft at each time moment; if not, normalizing the jamming degree to obtain the jamming failure probability of each screen shaft at each time moment.

[0073] It should be noted that the sign values ​​are -1, 0, and 1, with positive numbers having a sign value of 1, negative numbers having a sign value of -1, and zero having a sign value of 0. The jamming trend values ​​of all screen shafts are affected by the global material flow, exhibiting uniform changes such as an increase or decrease in overall load. Jamming disrupts this global consistency, causing local trends to deviate significantly from the global trend. If the trend difference is equal to a constant of 2, it indicates that the jamming trends of the upstream and downstream screen shafts are opposite, belonging to screen shaft speed changes caused by shaft jamming. The slope of the analysis line segment obtained by connecting the jamming trend values ​​of the first and last screen shafts represents the global trend, i.e., the normal change caused by material input. The smaller the difference between the screen shaft jamming trend value and the slope of the analysis line segment, the more consistent the screen shaft trend is with the global trend, indicating that the screen shaft's speed change is a normal change caused by material input factors; conversely, the stronger the impact of jamming on the screen shaft. Therefore, the degree of jamming cannot accurately reflect the degree of jamming on the screen shaft. It is necessary to utilize the difference between the jamming trend value of the screen shaft and the slope of the analysis line segment to increase the perceived degree of jamming, thus increasing the probability of actual jamming. In this embodiment, the method for adjusting the degree of jamming is as follows: the absolute value of the difference between the jamming trend value and the slope of the analysis line segment for each screen shaft at each moment is normalized. The product of the sum of the normalized result and constant 1 with the degree of jamming is then normalized to obtain the probability of jamming failure for each screen shaft at each moment. The Norm function is used for normalization. If the trend difference is not equal to constant 2, it indicates that the jamming trend of the upstream and downstream screen shafts is consistent, belonging to the screen shaft speed change caused by normal material feeding. The degree of jamming on the shaft can directly reflect the true probability of jamming. This embodiment utilizes the spatial correlation and fault locality of the screen shafts of the roller screen to analyze the degree of screen shaft jamming, improving the efficiency and robustness of jammed screen shaft detection.

[0074] In one implementation of this invention, the method for obtaining the analysis line segment is as follows: 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. 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. The line segment obtained by connecting the two coordinate points is the analysis line segment.

[0075] It should be noted that the Norm function is used for normalization in this embodiment of the invention, but other normalization methods can also be selected, such as function transformation, max-min normalization, etc., which are not limited here.

[0076] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the jammed screen shaft includes: determining the jamming anomaly threshold of the roller screen at each time moment, and selecting the screen shaft corresponding to the jamming anomaly threshold from the jamming failure probabilities of all screen shafts of the roller screen at each time moment, and using it as the jammed screen shaft of the roller screen at each time moment. It should be noted that the higher the jamming failure probability of the screen shaft, the greater the probability that it is a jammed screen shaft. In the embodiments of the present invention, the jamming anomaly threshold is the classification threshold determined when performing binary classification of the jamming failure probabilities of all screen shafts of the roller screen at each time moment using the Fisher discriminant method; another embodiment can use the mean of the jamming failure probabilities of all screen shafts at the same time moment as the jamming anomaly threshold at each time moment; other embodiments can set a constant between 0 and 1 according to specific circumstances.

[0077] This invention is now complete.

[0078] Example 2:

[0079] This invention also presents a schematic diagram of a computer device for a data-driven intelligent monitoring system for the operating status of a roller screen. Please refer to [link / reference]. 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. When the processor 502 executes the computer program 503, the computer device can execute any of the aforementioned data-driven intelligent monitoring methods for the operating status of the roller screen.

[0080] Furthermore, this application also protects an apparatus that 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 the data-driven intelligent monitoring method for the operating status of a roller screen provided in this application.

[0081] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0082] When each module is divided according to its function, the device may also include a communication module, a signal analysis module, a complexity analysis module, and a positioning module. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0083] It should be understood that the device provided in this embodiment is used to execute the above-described data-driven intelligent monitoring method for the operating status of a roller screen, and therefore can achieve the same effect as the above-described implementation method.

[0084] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of program code by the workpiece.

[0085] The processing module may be a processor or a controller, which can implement or execute the various exemplary logic blocks, modules, and circuits contained in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0086] Example 3:

[0087] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to realize the data-driven intelligent monitoring method for the operating status of a roller screen provided in the above embodiment.

[0088] Example 4:

[0089] This embodiment also provides a computer program product. When the computer program product is run on a computer, it causes the computer to perform the above-mentioned related steps to realize the data-driven intelligent monitoring method for the operating status of the roller screen provided in the above embodiment.

[0090] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0091] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0092] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0093] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A data-driven intelligent monitoring method for the operating status of a roller screen, characterized in that, The method includes: Obtain the rotational speed of each screen shaft of the roller screen at each moment during the screening process; Based on the position and inclination angle of each screen shaft and the trend of its rotational speed value in the neighborhood time period at each moment, as well as the degree of fluctuation of the rotational speed value in the neighborhood time period, the actual jamming probability of each screen shaft at each moment is obtained. Based on the differences in the actual jamming probability and rotational speed of each screen shaft with its neighboring screen shafts at the same time within the neighborhood time period at each time, and the differences in the changing trend of the actual jamming probability of each screen shaft with its neighboring screen shafts at each time within the neighborhood time period at each time, the jamming degree of each screen shaft at each time is obtained. Based on the difference in the changing trend of the actual jamming probability of the screen shafts located before and after each screen shaft in the neighborhood time period at each time, the jamming degree of each screen shaft at each time is adjusted, the jamming failure probability of each screen shaft at each time is obtained, and the jamming failure screen shaft of the roller screen at each time is determined.

2. The data-driven intelligent monitoring method for the operating status of a roller screen according to claim 1, characterized in that, The process of obtaining the actual jamming probability of each screen shaft at each moment includes: Obtain the standard normal rotational speed value of each screen shaft; take the ratio of the rotational speed value of each screen shaft at each moment to the standard normal rotational speed value as the rotational speed ratio; calculate the mean of the difference between the rotational 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 jamming probability of each screen shaft at each moment. Obtain the horizontal angle of the screen shaft and set the position number of the screen shaft; based on the position number of each screen shaft, the horizontal angle and the fluctuation degree of the rotational speed ratio in the neighborhood time period of each time, obtain the jamming correction amplitude of each screen shaft at each time. The initial jamming probability is adjusted using the jamming correction amplitude to obtain the actual jamming probability of each screen shaft at each moment.

3. The data-driven intelligent monitoring method for the operating status of a roller screen according to claim 2, characterized in that, The process of obtaining the degree of jamming of each screen shaft at each moment includes: The result of negatively mapping the rotational speed ratio of each screen shaft at each moment to the actual jamming probability constitutes a jamming feature vector; Based on the difference in the jamming feature vector between each sieve shaft and its adjacent sieve shaft at each time step and the magnitude of the jamming feature vector of each sieve shaft at each time step, the jamming feature difference of each sieve shaft at each time step is obtained. For each sieve axis, a linear fit is performed on the actual jamming probability at all times within the neighborhood time period at each time, and the slope of the resulting fitted line is used as the jamming trend value of each sieve axis at each time. The degree of jamming of each screen shaft at each time moment is obtained based on the difference in jamming characteristics of each screen shaft within the neighborhood time period at each time moment, and the difference in the jamming trend value of each screen shaft's adjacent screen shafts at each time moment.

4. The data-driven intelligent monitoring method for the operating status of a roller screen according to claim 3, characterized in that, The process of obtaining the jamming failure probability of each screen shaft at each moment includes: For the jamming trend values ​​of the screen shafts located before and after each screen shaft at each time moment, a straight line is fitted, and the slope of the fitted straight line is used as the upper screen shaft trend value and lower screen shaft trend value of each screen shaft at each time moment. The absolute value of the difference between the sign values ​​of the trend values ​​of the upper and lower screen axes is used as the trend difference degree of each screen axis at each time. Determine whether the trend difference is equal to a constant 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 line segment. Use the absolute value of the difference between the jamming trend value of each screen shaft at each time and the slope of the analysis line segment to adjust the jamming degree and obtain the jamming failure probability of each screen shaft at each time. If not, normalize the jamming degree to obtain the jamming failure probability of each screen shaft at each time.

5. The data-driven intelligent monitoring method for the operating status of a roller screen according to claim 1, characterized in that, The determination of the jammed screen shaft of the roller screen at each moment includes: Determine the jamming fault threshold of the roller screen at each time step, and select the screen shaft with a jamming fault probability greater than the jamming fault threshold from all screen shafts of the roller screen at each time step as the jamming screen shaft of the roller screen at each time step.

6. The data-driven intelligent monitoring method for the operating status of a roller screen according to claim 2, characterized in that, The adjustment of the initial jamming probability using the jamming correction magnitude includes: The jamming correction magnitude of each screen shaft at each time step is negatively correlated and normalized. The initial jamming probability is weighted using the processing result, and the weighted result is normalized to obtain the actual jamming probability of each screen shaft at each time step.

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

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

9. The data-driven intelligent monitoring method for the operating status of a roller screen according to claim 3, characterized in that, The acquisition of the jamming feature differences of each sieve shaft at each time step includes: Calculate the mean of the magnitude of the difference between the jamming feature vector of each sieve axis and its adjacent sieve axis at each time step. Multiply the mean by the magnitude of the jamming feature vector of each sieve axis at each time step to obtain the jamming feature difference of each sieve axis at each time step.

10. The data-driven intelligent monitoring method for the operating status of a roller screen according to claim 5, characterized in that, The jamming fault threshold is a classification threshold determined by using Fisher's discriminant method to perform binary classification of the jamming fault probability of all screen shafts of the roller screen at each moment.

Images