An online monitoring system for a mineral processing vibrating screen

Abstract

The application discloses an online monitoring system for a mineral processing vibrating screen, relates to the technical field of mineral processing, and solves the technical problem of low monitoring efficiency and accuracy of the vibrating screen caused by fixed abnormality judgment criteria of the vibrating screen; a plurality of screen plate working data and a standard maximum amplitude range are acquired, a plurality of amplitude data of the screen plate are acquired in real time, an adjustment factor is generated according to the screen plate working data, an adjusted maximum amplitude range is generated according to the adjustment factor and the standard maximum amplitude range, and a pre-warning signal is generated according to the amplitude data and the adjusted maximum amplitude range; a screen plate image is acquired in real time, an abnormality coefficient is generated according to the screen plate image, and an alarm signal is generated according to the abnormality coefficient; alarm is performed according to the pre-warning signal and the alarm signal; the adjusted maximum amplitude range is generated according to the adjustment factor and the standard maximum amplitude range, the judgment criteria for the abnormality of the vibrating screen are dynamically adjusted, and the monitoring efficiency and the monitoring accuracy of the vibrating screen are improved.

Description

Technical Field

[0001] This application belongs to the field of mineral processing technology, specifically an online monitoring system for a mineral processing vibrating screen. Background Technology

[0002] In mineral processing, vibrating screens are key equipment used for grading and screening ores. However, traditional monitoring methods rely on periodic manual inspections, which are not only inefficient but also make it difficult to detect potential faults in a timely manner, leading to reduced production efficiency and increased risk of equipment damage. Therefore, developing a system capable of monitoring the operating status of vibrating screens in real time is of great significance for improving mineral processing efficiency and reducing maintenance costs.

[0003] The prior art (patent application CN111001566A) discloses a vibrating screen condition monitoring device and a vibrating screen, including: a control module, a data acquisition module, a wireless transmission module, and an alarm module; the data acquisition module is used to acquire analog parameter information during the operation of the vibrating screen, convert the analog parameter information into digital parameter information, and send the digital parameter information to the control module through the wireless transmission module; the control module is used to obtain the screen box amplitude, lateral sway, vibration direction angle, and vibration frequency of the vibrating screen based on the digital parameter information; the control module is also used to determine whether the vibrating screen has malfunctioned based on the screen box amplitude, lateral sway, vibration direction angle, and vibration frequency; if an malfunction occurs, the control module sends an alarm command to the alarm module to cause the alarm module to issue an alarm prompt.

[0004] The above scheme uses a fixed standard for judging whether a vibrating screen has malfunctioned. However, in actual operation, the vibrating screen and its related components may experience aging and wear, which can affect the degree to which malfunctions occur. This results in low monitoring efficiency and accuracy for the vibrating screen, so there is still room for improvement in the monitoring system for the vibrating screen. Summary of the Invention

[0005] This application aims to at least solve one of the technical problems existing in the prior art. To this end, this application proposes an online monitoring system for a mineral processing vibrating screen to solve the technical problem that existing vibrating screen monitoring devices do not consider the impact of vibrating screen wear and aging on vibrating screen abnormalities, resulting in low monitoring efficiency and low accuracy of abnormality early warning. This application solves the above-mentioned problems by acquiring several screen plate working data and standard maximum amplitude range, as well as acquiring multiple amplitude data of the screen plate in real time, generating an adjustment factor based on the screen plate working data, generating an adjusted maximum amplitude range based on the adjustment factor and standard maximum amplitude range, and generating an early warning signal based on the amplitude data and adjusted maximum amplitude range.

[0006] To achieve the above objectives, the first aspect of this application provides an online monitoring system for a mineral processing vibrating screen, comprising: a data acquisition module, a data processing module, an early warning module, and a database;

[0007] Data acquisition module: Acquires multiple amplitude data and images of the sieve plate in real time through data acquisition equipment;

[0008] Data processing module: acquires several sieve plate working data and standard maximum amplitude range from the database it connects to; generates an adjustment factor based on the sieve plate working data, and generates an adjusted maximum amplitude range based on the adjustment factor and the standard maximum amplitude range; acquires several amplitude data, and generates an early warning signal based on the amplitude data and the adjusted maximum amplitude range; and,

[0009] The sieve plate image is preprocessed to obtain a preprocessed image; the preprocessed image is input into an anomaly detection model to obtain anomaly coefficients; the anomaly detection model is trained based on an artificial intelligence model; an alarm signal is generated based on the anomaly coefficients.

[0010] Early warning module: acquires early warning signals and alarm signals, and issues an alarm based on the early warning signals and alarm signals.

[0011] This application acquires several screen plate working data and standard maximum amplitude range; generates an adjustment factor based on the screen plate working data, and generates an adjusted maximum amplitude range based on the adjustment factor and the standard maximum amplitude range; acquires multiple amplitude data of the screen plate in real time, and generates an early warning signal based on the amplitude data and the adjusted maximum amplitude range; acquires screen plate images in real time; generates an anomaly coefficient based on the screen plate images; generates an alarm signal based on the anomaly coefficient; and triggers an alarm based on the early warning signal and the alarm signal. The method in this application—generating an adjustment factor based on the screen plate working data and generating an adjusted maximum amplitude range based on the adjustment factor and the standard maximum amplitude range—dynamically adjusts the judgment criteria for abnormalities in the vibrating screen, thereby improving the monitoring efficiency and accuracy of the vibrating screen.

[0012] Further, the adjustment factor is generated based on the sieve plate operating data, including:

[0013] Extract the usage time Ti and total amount of screened material Pi from the screen plate's working data;

[0014] The adjustment factor TY is calculated using the formula TY=exp(-∑(α1×(Ti / T0)^β+α2×(Pi / P0)^β)), where T0 is the standard working time; P0 is the standard sieve weight; α1 and α2 are weighting coefficients; β is the exponential coefficient, and β∈(0,1); i is the number of the sieve plate working data, and i=1,2,…,n; n is the total number of sieve plate working data.

[0015] Further, the adjusted maximum amplitude range is generated based on the adjustment factor and the standard maximum amplitude range, including:

[0016] Extract the upper limit of the standard maximum amplitude ZS and the lower limit of the standard maximum amplitude ZX from the standard maximum amplitude range;

[0017] The upper limit of the maximum amplitude adjustment TS is calculated using the formula TS=(γ1+TY)×ZS;

[0018] The lower limit of the maximum amplitude TX is calculated using the formula TX=(γ2+TY)×ZX; where γ1 and γ2 are error factors.

[0019] The adjustment of the upper limit of the maximum amplitude and the adjustment of the lower limit of the maximum amplitude are combined into the adjustment of the maximum amplitude range.

[0020] Furthermore, the warning signal is generated based on amplitude data and by adjusting the maximum amplitude range, including:

[0021] When all amplitude data are within the adjusted maximum amplitude range, a sieve plate warning signal is generated based on each amplitude data; otherwise, a sieve plate detachment warning signal is generated; the warning signals include a sieve plate warning signal and a sieve plate detachment warning signal.

[0022] Furthermore, the generation of the sieve plate early warning signal based on each amplitude data includes:

[0023] The maximum and minimum values ​​in the amplitude data are selected, and the difference between them is calculated and compared with the adjustment difference threshold TCY. The adjustment difference threshold TCY is calculated using the formula TCY = (γ + TY) × CY, where γ is the error factor and CY is the original difference threshold. When the difference is greater than the adjustment difference threshold, a sieve plate warning signal is generated; otherwise, the variance of each amplitude data is obtained, and it is determined whether the variance is greater than the variance threshold. If yes, a sieve plate warning signal is generated; otherwise, no warning signal is generated.

[0024] Further, the sieve plate image is preprocessed to obtain the preprocessed image, including the following steps:

[0025] Step 1: Convert the sieve plate image to grayscale to obtain a grayscale image;

[0026] Step 2: Denoise the grayscale image to obtain a denoised image; the denoised image is processed by a Gaussian filtering algorithm to remove noise from the image and improve image quality;

[0027] Step 3: Perform image enhancement processing on the denoised image to obtain the preprocessed image.

[0028] This application performs grayscale processing on a sieve plate image to obtain a grayscale image; performs denoising processing on the grayscale image to obtain a denoised image; removes noise from the denoised image using a Gaussian filtering algorithm; and performs image enhancement processing on the denoised image to obtain a preprocessed image. The grayscale processing, denoising processing, and image enhancement processing in this application can enhance the feature expression ability of the image and improve the recognition efficiency and accuracy of abnormal sieve plate images.

[0029] Furthermore, the anomaly detection model is trained based on an artificial intelligence model, and includes the following steps:

[0030] Step 1: Obtain several historical sieve plate images and their corresponding anomaly coefficients from the database;

[0031] Step 2: Preprocess the historical sieve plate images to obtain preprocessed images;

[0032] Step 3: Integrate the preprocessed image and the anomaly coefficients into several training data sets;

[0033] Step 4: Train the artificial intelligence model using training data to obtain the anomaly detection model; the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0034] Further, generating the alarm signal based on the anomaly coefficient includes:

[0035] Determine whether the anomaly coefficient is greater than the anomaly threshold one;

[0036] If yes, then when the abnormal coefficient is greater than the abnormal threshold two, a sieve plate detachment alarm signal is generated; otherwise, a sieve plate offset alarm signal is generated.

[0037] No, then no alarm signal will be generated;

[0038] Among them, the first abnormal threshold is less than the second abnormal threshold; the alarm signals include the screen plate falling off alarm signal and the screen plate offset alarm signal.

[0039] Furthermore, the alarm activation based on warning signals and alarm signals includes:

[0040] Acquire current warning and alarm signals; the warning and alarm signals include: screen plate warning signal, screen plate detachment warning signal, screen plate detachment alarm signal and screen plate offset alarm signal; when a warning signal occurs, display a vibrating screen warning prompt on the display; when an alarm signal occurs, stop the operation of the vibrating screen, shut down the related machines, and flash alarm lights on the display and around the vibrating screen to provide a warning.

[0041] Compared with the prior art, the beneficial effects of this application are:

[0042] 1. This application acquires several screen plate working data and standard maximum amplitude range; generates adjustment factors based on the screen plate working data, and generates an adjusted maximum amplitude range based on the adjustment factors and standard maximum amplitude range; acquires multiple amplitude data of the screen plate in real time, and generates an early warning signal based on the amplitude data and adjusted maximum amplitude range; acquires screen plate images in real time; generates an anomaly coefficient based on the screen plate images; generates an alarm signal based on the anomaly coefficient; and triggers an alarm based on the early warning signal and alarm signal. The method in this application, which generates adjustment factors based on screen plate working data and adjusts the maximum amplitude range based on the adjustment factors and standard maximum amplitude range, dynamically adjusts the judgment criteria for abnormalities in the vibrating screen, improving the monitoring efficiency and accuracy of the vibrating screen. This avoids the problem in existing vibrating screen monitoring devices that do not consider the impact of wear and aging on vibrating screen anomalies, resulting in low monitoring efficiency and low accuracy of anomaly early warning.

[0043] 2. This application performs grayscale processing on the sieve plate image to obtain a grayscale image; performs denoising processing on the grayscale image to obtain a denoised image; removes noise from the denoised image using a Gaussian filtering algorithm; and performs image enhancement processing on the denoised image to obtain a preprocessed image. The grayscale processing, denoising processing, and image enhancement processing in this application can enhance the feature expression ability of the image and improve the recognition efficiency and accuracy of abnormal sieve plate images. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of the online monitoring system for the mineral processing vibrating screen of this application.

[0046] Figure 2 This is a schematic diagram of the online monitoring method for mineral processing vibrating screens according to this application;

[0047] Figure 3 This is a flowchart illustrating the generation process of the early warning signal in this application;

[0048] Figure 4 This is a flowchart of the alarm signal generation process in this application. Detailed Implementation

[0049] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0050] Please see Figures 1-2 The first aspect of this application provides an online monitoring system for a mineral processing vibrating screen, comprising: a data acquisition module, a data processing module, an early warning module, and a database;

[0051] Data acquisition module: Real-time acquisition of multiple amplitude data and images of the sieve plate through data acquisition equipment; the data acquisition equipment includes vibration sensors and cameras; the vibration sensors collect amplitude data of the sieve plate, including key parameters such as vibration amplitude and vibration frequency; the images of the sieve plate collected by the camera are pictures of the sieve plate taken by the camera;

[0052] Data processing module: It acquires several screen plate working data and standard maximum amplitude range from a connected database; generates an adjustment factor based on the screen plate working data; generates an adjusted maximum amplitude range based on the adjustment factor and the standard maximum amplitude range; acquires several amplitude data; generates an early warning signal based on the amplitude data and the adjusted maximum amplitude range; preprocesses the screen plate image to obtain a preprocessed image; inputs the preprocessed image into an anomaly detection model to obtain an anomaly coefficient; the anomaly detection model is trained based on an artificial intelligence model; and generates an alarm signal based on the anomaly coefficient. The standard maximum amplitude range is the maximum vibration amplitude of the screen plate set manually, generally set to the range of 4 mm to 6 mm. The adjustment factor is used to adjust the standard maximum amplitude range based on the aging and wear of the vibrating screen and its related components. The adjusted maximum amplitude range is a new maximum amplitude range set when the maximum amplitude of the vibrating screen and its related components fails to reach the standard maximum amplitude due to aging and wear, and is obtained by adjusting the standard maximum amplitude using the adjustment factor.

[0053] Early warning module: acquires early warning signals and alarm signals, and issues an alarm based on the early warning signals and alarm signals.

[0054] In this embodiment, several screen plate working data and standard maximum amplitude range are acquired; an adjustment factor is generated based on the screen plate working data, and an adjusted maximum amplitude range is generated based on the adjustment factor and the standard maximum amplitude range; multiple amplitude data of the screen plate are acquired in real time, and an early warning signal is generated based on the amplitude data and the adjusted maximum amplitude range; screen plate images are acquired in real time; an anomaly coefficient is generated based on the screen plate images; an alarm signal is generated based on the anomaly coefficient; and an alarm is triggered based on the early warning signal and the alarm signal. In this embodiment, the adjustment factor is generated based on the screen plate working data, and the adjusted maximum amplitude range is generated based on the adjustment factor and the standard maximum amplitude range, dynamically adjusting the judgment criteria for abnormalities in the vibrating screen, thereby improving the monitoring efficiency and accuracy of the vibrating screen.

[0055] Adjustment factors are generated based on the sieve plate operating data, including:

[0056] Extract the usage time Ti and total amount of screened material Pi from the screen plate's working data;

[0057] The adjustment factor TY is calculated using the formula TY=exp(-∑(α1×(Ti / T0)^β+α2×(Pi / P0)^β)). Where T0 is the standard working time, empirically set to 1 day; P0 is the standard screen weight, empirically set to 1 ton; α1 and α2 are weighting coefficients, empirically set; β is the exponential coefficient, empirically set, and β∈(0,1); i is the number of the screen plate working data, and i=1,2,…,n; n is the total number of screen plate working data. As the usage time of the vibrating screen increases or the total weight of the screened material increases, these factors affect… Wear and tear on the vibrating screen and its related components has a significant impact, causing the maximum amplitude range of the vibrating screen to fall short of the standard maximum amplitude range. Therefore, an adjustment factor is needed to adjust the standard maximum amplitude range of the vibrating screen. The longer the vibrating screen is used, the greater the wear on the screen plate, and the smaller the adjustment factor becomes. The greater the total weight of the material being screened, the greater the wear on the screen plate, and the smaller the adjustment factor becomes. When the vibrating screen has not been used, its usage time and total weight of the material being screened are both 0. At this time, the adjustment factor is 1, and the maximum amplitude range is adjusted to be consistent with the standard maximum amplitude range.

[0058] The adjusted maximum amplitude range is generated based on the adjustment factor and the standard maximum amplitude range, including:

[0059] Extract the upper limit of the standard maximum amplitude ZS and the lower limit of the standard maximum amplitude ZX from the standard maximum amplitude range;

[0060] The upper limit of the maximum amplitude adjustment TS is calculated using the formula TS=(γ1+TY)×ZS;

[0061] The lower limit of the maximum amplitude TX is calculated using the formula TX=(γ2+TY)×ZX; where γ1 and γ2 are error factors; γ1 and γ2 are set based on experience.

[0062] The adjustment of the upper limit of maximum amplitude and the adjustment of the lower limit of maximum amplitude are combined into the adjustment of the maximum amplitude range.

[0063] In this embodiment, the upper limit of the standard maximum amplitude ZS in the standard maximum amplitude range is 6 mm and the lower limit of the standard maximum amplitude ZX is 4 mm. The calculated current adjustment factor TY is 0.89, and γ1 and γ2 are 0.01. Therefore, the upper limit of the adjusted maximum amplitude TS in the current adjusted maximum amplitude range is TS = (γ1 + TY) × ZS = (0.01 + 0.89) × 6 = 5.4 mm, and the lower limit of the adjusted maximum amplitude TX = (γ2 + TY) × ZX = (0.01 + 0.89) × 4 = 3.6 mm. Thus, the adjusted maximum amplitude range is [3.6, 5.4], in millimeters.

[0064] Early warning signals are generated based on amplitude data and adjustments to the maximum amplitude range, including:

[0065] When all amplitude data are within the adjusted maximum amplitude range, a sieve plate warning signal is generated based on each amplitude data; otherwise, a sieve plate detachment warning signal is generated. The warning signals include a sieve plate warning signal and a sieve plate detachment warning signal.

[0066] The screen plate warning signal is a signal generated when the current vibration amplitude of the screen plate does not reach the warning limit for screen plate detachment, but there is a difference from the normal vibration amplitude. The screen plate detachment warning signal is a signal generated when the current screen plate may detach.

[0067] Please see Figure 3 Based on the amplitude data, a sieve plate early warning signal is generated, including:

[0068] The maximum and minimum values ​​in the amplitude data are selected, and the difference between them is calculated and compared with the adjustment difference threshold TCY. The adjustment difference threshold TCY is calculated using the formula TCY = (γ + TY) × CY, where γ is the error factor and CY is the original difference threshold. When the difference is greater than the adjustment difference threshold, a sieve plate warning signal is generated; otherwise, the variance of each amplitude data is obtained, and it is determined whether the variance is greater than the variance threshold. If yes, a sieve plate warning signal is generated; otherwise, no warning signal is generated.

[0069] In this embodiment, the amplitude data of two sieve plates were obtained. The amplitude data of one of the sieve plates are {4.0, 4.4, 3.8, 5.5, 3.5, 5.1, 3.6}. The current maximum amplitude range is [3.6, 5.4]. There are two amplitude data, 3.5 and 5.5, which are not within the maximum amplitude range. At this time, a sieve plate detachment warning signal is generated.

[0070] The amplitude data of another sieve plate are {4.0, 4.4, 3.8, 5.3, 3.7, 5.1, 3.6}. The current maximum amplitude range is [3.6, 5.4]. The current adjustment factor is TY = 0.89, γ = 0.01. The current amplitude data are all within the maximum amplitude range. At this time, the maximum value of the current amplitude data, 5.3, and the minimum value, 3.6, are selected. The original difference threshold CY = 1.5, and the adjustment difference threshold TCY = (0.89 + 0.01) × 1.5 = 1.35. The difference between the maximum and minimum values ​​is 1.7 > TCY = 1.35. Therefore, a sieve plate warning signal is generated. If there is a difference less than or equal to the adjustment difference threshold, the judgment steps are the same as described.

[0071] The sieve plate image is preprocessed to obtain a preprocessed image, including the following steps:

[0072] Step 1: Convert the sieve plate image to grayscale to obtain a grayscale image; this step simplifies subsequent processing steps and reduces computational complexity.

[0073] Step 2: Denoise the grayscale image to obtain a denoised image; the denoised image is then processed using a Gaussian filtering algorithm to remove noise and improve image quality.

[0074] Step 3: Perform image enhancement processing on the denoised image to obtain a preprocessed image; the preprocessed image is adjusted by contrast enhancement or brightness enhancement methods to highlight key features in the image.

[0075] In this embodiment, the sieve plate image is converted to grayscale to obtain a grayscale image; the grayscale image is then denoised to obtain a denoised image; the denoised image is further denoised using a Gaussian filtering algorithm to remove noise; and the denoised image is then enhanced to obtain a preprocessed image. The grayscale conversion, denoising, and image enhancement processes in this embodiment can enhance the feature representation capability of the image and improve the recognition efficiency and accuracy of abnormal sieve plate images.

[0076] The anomaly detection model is trained based on an artificial intelligence model and includes the following steps:

[0077] Step 1: Obtain several historical sieve plate images and their corresponding anomaly coefficients from the database; historical sieve plate images refer to sieve plate images taken in the past in the database, and anomaly coefficients refer to an anomaly situation corresponding to a historical sieve plate image with an anomaly.

[0078] Step 2: Preprocess the historical sieve plate images to obtain preprocessed images;

[0079] Step 3: Integrate the preprocessed images and anomaly coefficients into several training data sets;

[0080] Step 4: Train the artificial intelligence model using training data to obtain the anomaly detection model; the artificial intelligence model includes the BP neural network model and the RBF neural network model.

[0081] An alarm signal is generated based on the anomaly coefficient, including:

[0082] Please see Figure 4 Determine whether the abnormal coefficient is greater than the abnormal threshold one;

[0083] If yes, then when the abnormal coefficient is greater than the abnormal threshold two, a sieve plate detachment alarm signal is generated; otherwise, a sieve plate offset alarm signal is generated.

[0084] No, then no alarm signal will be generated;

[0085] Among them, the abnormal threshold one is less than the abnormal threshold two; the alarm signals include the sieve plate detachment alarm signal and the sieve plate offset alarm signal; the sieve plate detachment alarm signal is a signal generated when the currently detected sieve plate may detach; the sieve plate offset alarm signal is a signal generated when there is an offset between the currently detected sieve plate image and the normal sieve plate image, but it has not reached the sieve plate detachment alarm signal limit.

[0086] In this embodiment, the first abnormal threshold is set to 0.2 and the second abnormal threshold is set to 0.5. If the current sieve plate image is input into the abnormal detection model and the output abnormal coefficient is 0.6, the abnormal coefficient is greater than the first abnormal threshold and the abnormal coefficient is greater than the second abnormal threshold, and a sieve plate detachment alarm signal is generated. If the current sieve plate image is input into the abnormal detection model and the output abnormal coefficient is 0.3, the abnormal coefficient is greater than the first abnormal threshold and the abnormal coefficient is less than the second abnormal threshold, it is determined that the sieve plate has shifted and the shift amount is small, and a sieve plate shift alarm signal is generated.

[0087] An alarm is triggered based on warning signals and alarm signals, including:

[0088] When a warning signal is detected, a warning message for the vibrating screen will be displayed on the monitor.

[0089] When an alarm signal is detected, the vibrating screen should be stopped, all related machines should be shut down, and alarm lights should flash on the display and around the vibrating screen to alert relevant personnel to inspect and maintain the corresponding equipment.

[0090] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0091] The working principle of this application is as follows: This application acquires several screen plate working data and standard maximum amplitude range; generates an adjustment factor based on the screen plate working data, and generates an adjusted maximum amplitude range based on the adjustment factor and the standard maximum amplitude range; acquires multiple amplitude data of the screen plate in real time, and generates an early warning signal based on the amplitude data and the adjusted maximum amplitude range; acquires screen plate images in real time; generates an anomaly coefficient based on the screen plate images; generates an alarm signal based on the anomaly coefficient; and triggers an alarm based on the early warning signal and the alarm signal. The method of generating an adjustment factor based on the screen plate working data and generating an adjusted maximum amplitude range based on the adjustment factor and the standard maximum amplitude range dynamically adjusts the judgment criteria for abnormalities in the vibrating screen, improving the monitoring efficiency and accuracy of the vibrating screen and avoiding the problem of low monitoring efficiency and accuracy caused by fixed judgment criteria for vibrating screen anomalies.

[0092] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. An online monitoring system for a mineral processing vibrating screen, comprising: The system comprises a data acquisition module, a data processing module, an early warning module, and a database; its features include: Data acquisition module: Acquires multiple amplitude data and images of the sieve plate in real time through data acquisition equipment; Data processing module: acquires several sieve plate operating data and standard maximum amplitude range from a connected database; generates an adjustment factor based on the sieve plate operating data; generates an adjusted maximum amplitude range based on the adjustment factor and the standard maximum amplitude range; generates an early warning signal based on the amplitude data and the adjusted maximum amplitude range; and, The sieve plate image is preprocessed to obtain a preprocessed image; the preprocessed image is input into an anomaly detection model to obtain anomaly coefficients; the anomaly detection model is trained based on an artificial intelligence model; an alarm signal is generated based on the anomaly coefficients. Early warning module: acquires early warning signals and alarm signals, and issues an alarm based on the early warning signals and alarm signals; The adjustment factor is generated based on the sieve plate operating data, including: Extract the usage time Ti and total amount of screened material Pi from the screen plate's working data; The adjustment factor TY is calculated using the formula TY=exp(-∑(α1×(Ti / T0)^β+α2×(Pi / P0)^β)), where T0 is the standard working time; P0 is the standard sieve weight; α1 and α2 are weighting coefficients; β is the exponential coefficient, and β∈(0,1); i is the number of the sieve plate working data, and i=1,2,…,n; n is the total number of sieve plate working data. The adjusted maximum amplitude range is generated based on the adjustment factor and the standard maximum amplitude range, including: Extract the upper limit of the standard maximum amplitude ZS and the lower limit of the standard maximum amplitude ZX from the standard maximum amplitude range; The upper limit of the maximum amplitude adjustment TS is calculated using the formula TS=(γ1+TY)×ZS; The lower limit of the maximum amplitude TX is calculated using the formula TX=(γ2+TY)×ZX; where γ1 and γ2 are error factors. The adjustment of the upper limit and lower limit of the maximum amplitude are combined into the adjustment of the maximum amplitude range; Early warning signals are generated based on amplitude data and adjustments to the maximum amplitude range, including: When all amplitude data are within the adjusted maximum amplitude range, a sieve plate warning signal is generated based on each amplitude data; otherwise, a sieve plate detachment warning signal is generated; the warning signals include a sieve plate warning signal and a sieve plate detachment warning signal.

2. The online monitoring system for a mineral processing vibrating screen according to claim 1, characterized in that, The generation of the sieve plate early warning signal based on each amplitude data includes: The maximum and minimum values ​​in the amplitude data are selected, the difference between them is calculated, and compared with the adjustment difference threshold TCY. The adjustment difference threshold TCY is calculated by the formula TCY=(γ+TY)×CY, where γ is the error factor and CY is the original difference threshold. When the difference is greater than the adjustment difference threshold, a sieve plate warning signal is generated; otherwise, the variance of each amplitude data is obtained, and it is determined whether the variance is greater than the variance threshold; if yes, a sieve plate warning signal is generated; otherwise, no warning signal is generated.

3. The online monitoring system for a mineral processing vibrating screen according to claim 1, characterized in that, Preprocessing the sieve plate image to obtain the preprocessed image includes the following steps: Step 1: Convert the sieve plate image to grayscale to obtain a grayscale image; Step 2: Denoise the grayscale image to obtain a denoised image; the denoised image is then processed using a Gaussian filtering algorithm to remove noise from the image. Step 3: Perform image enhancement processing on the denoised image to obtain the preprocessed image.

4. The online monitoring system for a mineral processing vibrating screen according to claim 1, characterized in that, The anomaly detection model is trained based on an artificial intelligence model and includes the following steps: Step 1: Obtain several historical sieve plate images and their corresponding anomaly coefficients from the database; Step 2: Preprocess the historical sieve plate images to obtain preprocessed images; Step 3: Integrate the preprocessed image and the anomaly coefficients into several training data sets; Step 4: Train the artificial intelligence model using training data to obtain the anomaly detection model; the artificial intelligence model includes a BP neural network model and an RBF neural network model.

5. The online monitoring system for a mineral processing vibrating screen according to claim 1, characterized in that, The alarm signal is generated based on the anomaly coefficient, including: Determine whether the anomaly coefficient is greater than the anomaly threshold one; If yes, then when the abnormal coefficient is greater than the abnormal threshold two, a sieve plate detachment alarm signal is generated; otherwise, a sieve plate offset alarm signal is generated. No, no alarm signal is generated; wherein, the first abnormal threshold is less than the second abnormal threshold; the alarm signals include a sieve plate detachment alarm signal and a sieve plate offset alarm signal.

Images