Visual assistance method and equipment for bag overturning and discharging centrifugal machine and medium

Abstract

The invention discloses a visual assistance method, equipment and medium for a bag turning and discharging centrifugal machine, relates to the technical field of industrial intelligent detection, and solves the problems that when a current bag turning centrifugal machine conducts centrifugal operation, a method for detecting the thickness of a filter cake is single and has errors, and an evaluation index for evaluating the centrifugal effect of the bag turning centrifugal machine is single. The method comprises the following steps: randomly sampling a detection material, and then processing a to-be-tested material obtained by sampling; performing centrifugal operation on the to-be-tested material by the bag-turning centrifugal machine, and detecting the maximum thickness of a filter cake on the surface of filter cloth in the bag-turning centrifugal machine in real time; obtaining a filtrate and a filter cake after the material to be tested is centrifuged, and calculating a filtrate qualification index of the filtrate and a filter cake qualification index of the filter cake; the centrifugal effect of the bag-turning centrifugal machine is judged based on the filtrate qualification index and the filter cake qualification index, the bag-turning centrifugal machine is improved according to the centrifugal effect, and intelligent analysis of the working process of the bag-turning centrifugal machine is achieved based on the visual assistance technology.

Description

Technical Field

[0001] The invention belongs to the technical field of industrial intelligent detection, and in particular relates to a visual assistance method, equipment and medium for a bag-turning unloading centrifuge. Background Art

[0002] The bag turning centrifuge is a centrifugal device used for solid-liquid separation. It mainly generates centrifugal force through the high-speed rotating drum, so that the solid particles in the suspension form a filter cake on the filter cloth, and the filtrate is discharged through the filter cloth. The characteristic of this equipment is that it has a "bag turning" function, that is, after the separation process is completed, the filter bag is turned over by reversal or mechanical device, so that the filter cake on the filter cloth falls off, thereby realizing automatic unloading. This design improves the efficiency of solid-liquid separation and reduces manual intervention. It is widely used in solid-liquid separation processes in chemical, pharmaceutical, food and other industries.

[0003] In the prior art, when a bag centrifuge is performing centrifugal operation, a thickness sensor is usually used to detect the thickness of the filter cake. The method for detecting the thickness of the filter cake is single and has errors. In addition, the centrifugal effect of the bag centrifuge is currently evaluated only by the solid content of the filtrate and the moisture content of the filter cake. The evaluation index is single, which leads to errors in evaluating the centrifugal effect of the bag centrifuge. To this end, the present invention provides a visual assistance method, device and medium for a bag-turning unloading centrifuge. Summary of the invention

[0004] The purpose of the present invention is to provide a visual assistance method, device and medium for a bag-turning unloading centrifuge to solve the problems raised in the above-mentioned background technology.

[0005] The technical problems to be solved by the present invention are: How to realize intelligent analysis of centrifugal operation of bag centrifuge based on visual assisted technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A visual assistance method for bag-turning unloading centrifuge, the method comprising: Step S1, randomly sampling the test materials, and then processing the sampled materials to be tested; Step S2, the bag centrifuge performs centrifugal operation on the material to be tested, and detects the maximum thickness of the filter cake on the filter cloth surface in the bag centrifuge in real time; Step S3, obtaining the filtrate and filter cake after the material to be tested is centrifuged, and calculating the filtrate qualification index of the filtrate and the filter cake qualification index of the filter cake; Step S4, judging the centrifugal effect of the bag inverting centrifuge based on the filtrate qualification index and the filter cake qualification index, and improving the bag inverting centrifuge according to the centrifugal effect.

[0007] Furthermore, the step S1 includes the following sub-steps: Step S11, stirring the test materials of the same production batch for a preset stirring time, and then randomly sampling from the uniformly stirred test materials; Step S12, when the weight of the test material is less than or equal to the preset weight threshold, randomly selecting a first fixed weight ratio of the test material as the material to be tested; Step S13, when the weight of the test material is greater than the preset weight threshold, randomly select a second fixed weight ratio of the test material as the material to be tested; wherein the first fixed weight ratio is greater than the second fixed weight ratio.

[0008] Furthermore, the step S2 includes the following sub-steps: Step S21, inputting the material to be tested into the storage tank, and then setting the feeding mode of the bag centrifuge to continuous feeding; Step S22, setting the corresponding rotation speed of the drum in the bag turning centrifuge to the first rotation speed, inputting the material to be tested into the bag turning centrifuge at a uniform speed, and setting the rotation speed of the drum to the second rotation speed when the feed port of the bag turning centrifuge detects that the material to be tested enters; Step S23, detecting the maximum thickness of the filter cake on the surface of the filter cloth in the bag-turning centrifuge.

[0009] Furthermore, the step S23 includes the following sub-steps: Step S2301, obtaining a static image of the filter cake on the filter cloth surface, and converting the static image of the filter cake on the filter cloth surface into a static grayscale image, and then performing denoising on the static grayscale image, specifically: The R value, G value and B value of all pixels in the static image of the filter cake are obtained, and the gray value i corresponding to each pixel is calculated by the formula Y=0.3R+0.59G+0.11B; Step S2302, taking any gray value as a gray threshold, and counting the number of first pixel points corresponding to the gray values ​​less than the gray threshold, and the number of second pixel points corresponding to the gray values ​​greater than or equal to the gray threshold in the static gray image; Step S2303, the pixel points corresponding to the grayscale values ​​less than the grayscale threshold in the static grayscale image are recorded as background pixel points, and the background image is composed of all the background pixel points; at the same time, the pixel points corresponding to the grayscale values ​​greater than or equal to the grayscale threshold in the static grayscale image are recorded as foreground pixel points, and the foreground image is composed of all the foreground pixel points; Among them, the background pixel points are the pixel points in the non-filter cake range in the static grayscale image, and the foreground pixel points are the pixel points in the filter cake range in the static grayscale image; Step S2303, obtain the total number of pixels XSZ in the static grayscale image of the filter cake and the number of pixels H(i) with grayscale value i, and calculate the probability P(i) that any pixel has a grayscale value i by the formula, which is as follows: P(i) = H(i) / XSZ; Step S2304, the background average grayscale value BPH of the background image is calculated by the formula, and the specific formula is as follows: ; Then the grayscale variance BJF(t) of the background image is calculated by the formula, which is as follows: .

[0010] Furthermore, the step S23 further includes the following sub-steps: Step S2305, the foreground average gray value QPH of the foreground image is calculated by the formula, and the specific formula is as follows: ; Then the grayscale variance QJF(t) of the foreground image is calculated by the formula, which is as follows: ; Step S2306, the inter-class variance LJF(t) of the static grayscale image is calculated by the formula, and the specific formula is as follows: LJF(t)=BJX(t)×BJF²(t)+QJX(t)×QJF²(t); Step S2307, after removing the selected grayscale value, the grayscale threshold t is increased from zero to t = [0, 255], and the grayscale threshold that maximizes the inter-class variance is calculated, and the corresponding grayscale threshold is used as the optimal threshold for binarizing the static grayscale image, and the static grayscale image is binarized according to the optimal threshold to obtain a binary image of the filter cake; Step S2308, analyzing the binary image of the filter cake to obtain edge pixel points of the filter cake, and connecting the edge pixel points of the filter cake one by one to obtain the filter cake outline; Step S2309, draw a vertical line from any pixel point of the top contour of the filter cake contour to the bottom contour, calculate the number of pixel points intersecting with the vertical line, traverse to obtain the vertical line with the maximum number of pixel points, and record the pixel point corresponding to the top contour as the thickest point of the filter cake; Step S2310, obtaining a proportionality coefficient between the static image and the actual size of the filter cake, and calculating the maximum thickness corresponding to the thickest point of the filter cake through the proportionality coefficient.

[0011] Furthermore, the step S3 includes the following sub-steps: Step S31, when the maximum thickness of the filter cake reaches the first thickness threshold, the storage tank stops feeding, and if the liquid outlet of the bag turning centrifuge is still outputting filtrate, the drum maintains the second rotation speed until there is no filtrate output from the liquid outlet, or the maximum thickness of the filter cake reaches the second thickness threshold, the liquid outlet is closed, and the filtrate of the material to be tested is obtained at the same time; wherein the second thickness threshold is greater than the first thickness threshold, and the first thickness threshold is greater than zero; Step S32, setting the rotation speed of the drum to the third rotation speed, turning the filter bag over at the same time, and setting the bag turning rotation time; wherein the second rotation speed is greater than the first rotation speed, and the first rotation speed is greater than the third rotation speed; the third rotation speed is used to discharge the filter cake; Step S33, when the rotation time of the drum reaches the bag turning rotation time, the drum stops rotating and closes the discharge port to obtain the filter cake of the material to be tested; Step S34, detecting the real-time moisture content SHS, real-time impurity content SZL and real-time weight SZL of the filter cake corresponding to the material to be tested; Then, the moisture content threshold, impurity content threshold and weight threshold of the filter cake corresponding to the material to be tested are obtained; wherein the moisture content threshold, impurity content threshold and weight threshold are ideal data obtained under ideal conditions for materials with the same weight as the material to be tested; Step S35: If any one of the following occurs: the real-time moisture content is greater than the moisture content threshold, the real-time impurity content is greater than the impurity content threshold, or the real-time weight is greater than the weight threshold, no operation is performed.

[0012] Furthermore, the step S3 also includes the following sub-steps: Step S36: If the real-time moisture content is less than or equal to the moisture content threshold, the real-time impurity content is less than or equal to the impurity content threshold, and the real-time weight is less than or equal to the weight threshold, the filter cake qualification index BHZ is calculated by the formula, and the specific formula is as follows: BHZ=1 / [(SHS / BHS)×w1+(SZL / BZL)×w2+(SZL / BZL)×w3], where w1, w2 and w3 are weight coefficients with fixed values, and w1>w2>w3, BHS is the standard value of real-time moisture content, BZL is the standard value of real-time impurity content, BZL is the standard value of real-time weight, and the standard value is 1; Step S37, detecting the real-time solid content GTH and real-time transmittance TGD of the filtrate corresponding to the material to be tested, and then obtaining the solid content threshold BGTH and transmittance threshold BTGD of the filtrate; Step S38, if the real-time solid content is greater than the solid content threshold or the real-time transmittance is less than the transmittance threshold, no operation is performed; Step S39, if the real-time solid content is less than or equal to the solid content threshold, and the real-time transmittance is greater than or equal to the transmittance threshold, the filtrate qualification index YHZ is calculated by the formula YHZ=v1×(TGD / BTGD) / v2×(GTH / BGTH); wherein v1 and v2 are weight coefficients of fixed values, and v1>v2, BTGD is the standard value of the transmittance threshold, BGTH is the standard value of the solid content threshold, and the standard value is 1.

[0013] Furthermore, the step S4 includes the following sub-steps: Step S41, if the filtrate qualification index is greater than the filtrate qualification index threshold, proceed to step S42; If the filtrate qualified index is less than or equal to the filtrate qualified index threshold, the test material is randomly sampled again, and step S22 is repeated. When the feed port of the bag turning centrifuge detects that the test material enters, the rotation speed of the drum is gradually increased upward with the second rotation speed as the initial speed, until the filtrate qualified index obtained by subsequent detection is greater than the filtrate qualified index threshold, and the corresponding rotation speed is used as the standard rotation speed; Step S42, when the filter cake qualification index is greater than the filter cake qualification index threshold, the centrifugal effect of the bag turning centrifuge is determined to be excellent, and no operation is performed; When the test score of the bag centrifuge is less than or equal to the score threshold, proceed to the next step; Step S43, reducing the rotation speed of the drum in the bag-turning centrifuge to zero, and detecting the number of holes on the surface of the filter cloth; Step S44, if the number of holes on the filter cloth surface is greater than the number threshold, no operation is performed; If the number of holes on the filter cloth surface is less than or equal to the number threshold, increase the rotation time of the drum and detect the number of holes on the filter cloth surface at fixed intervals until the number of holes on the filter cloth surface is greater than the number threshold. The drum stops rotating and records the corresponding bag turning rotation time as the standard bag turning rotation time.

[0014] In a second aspect, a computer device is provided, the computer device comprising: A memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, the method described is implemented.

[0015] In a third aspect, a computer-readable storage medium stores a computer program, which implements the method described above when executed by a processor.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention first randomly samples the test material, and then processes the sampled test material. After the processing is completed, the test material is centrifuged by a bag centrifuge, so as to detect the maximum thickness of the filter cake on the surface of the filter cloth in the bag centrifuge in real time; 2. The present invention obtains the filtrate and filter cake after the material to be tested is centrifuged, and calculates the filtrate qualification index of the filtrate and the filter cake qualification index of the filter cake. The visual technology combines the filtrate qualification index and the filter cake qualification index to judge the centrifugal effect of the bag inverting centrifuge, and improves the bag inverting centrifuge according to the centrifugal effect. The present invention realizes intelligent analysis of the working process of the bag inverting centrifuge based on visual auxiliary technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 is the overall system block diagram of the present invention; Figure 2 It is a side view of the bag inverting centrifuge in the present invention; Figure 3 This is an example diagram of the thickest point of the filter cake in the present invention; Figure 4 It is a schematic diagram of the structure of the computer device in the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1: Please refer to Figure 1-Figure 3 As shown, the technical solution provided by the present invention is: a visual assistance method for bag-turning unloading centrifuge, which is suitable for centrifugal operation of materials in a solid-liquid coexisting state through a bag-turning centrifuge, and analyzes whether the centrifugal effect of the bag-turning centrifuge on the material reaches the expected value. The method is specifically as follows: Step S1, randomly sampling the test materials, and then processing the sampled materials to be tested; In this embodiment, step S1 includes the following sub-steps: Step S11, stirring the test materials of the same production batch for a preset stirring time, and then randomly sampling from the uniformly stirred test materials; Step S12, when the weight of the test material is less than or equal to the preset weight threshold, randomly selecting a first fixed weight ratio of the test material as the material to be tested; Step S13, when the weight of the test material is greater than the preset weight threshold, randomly select a second fixed weight ratio of the test material as the material to be tested; wherein the first fixed weight ratio is greater than the second fixed weight ratio; In practice, when the weight of the test material is less than or equal to the preset weight threshold, 10% of the weight of the test material can be randomly selected as the material to be tested; when the weight of the test material is greater than the preset weight threshold, 5% of the weight of the test material can be randomly selected as the material to be tested.

[0021] Step S2, the bag centrifuge performs centrifugal operation on the material to be tested, and detects the maximum thickness of the filter cake on the filter cloth surface in the bag centrifuge in real time; In this embodiment, the bag centrifuge consists of a storage tank, a drum, a filter cloth, a transparent observation window, a filter bag, a liquid outlet and a material outlet. The storage tank is used to store the material to be tested, and a drum is arranged inside the storage tank; the drum rotates at high speed to provide centrifugal force to achieve solid-liquid separation of the material to be tested; the filter cloth is used to intercept solid particles in the material to be tested and form a filter cake on the surface of the filter cloth; the transparent observation window is used for the camera to capture a static image of the filter cake on the surface of the filter cloth; the filter bag is used to fix the filter cloth; the liquid outlet is used to output the filtrate generated after the material to be tested is centrifuged; the material outlet is used to output the filter cake generated after the material to be tested is centrifuged; In this embodiment, step S2 includes the following sub-steps: Step S21, inputting the material to be tested into the storage tank, and then setting the feeding mode of the bag centrifuge to continuous feeding; wherein the feeding mode includes continuous feeding, intermittent feeding, etc.; Step S22, setting the corresponding rotation speed of the drum in the bag turning centrifuge to the first rotation speed, inputting the material to be tested into the bag turning centrifuge at a uniform speed, and setting the rotation speed of the drum to the second rotation speed when the feed port of the bag turning centrifuge detects that the material to be tested enters; Specifically, when the rotation speed of the drum is the first rotation speed, it is used to input the material to be tested into the bag turning centrifuge; when the rotation speed of the drum is the second rotation speed, it is used to centrifuge the material to be tested; Step S23, detecting the maximum thickness of the filter cake on the surface of the filter cloth in the bag-turning centrifuge; Wherein, a transparent observation window is installed on the side wall of the bag turning centrifuge, and a camera is placed outside the transparent observation window of the bag turning centrifuge, and the camera is used to take a static image of the filter cake in the bag turning centrifuge; In this embodiment, step S23 includes the following sub-steps: Step S2301, obtaining a static image of the filter cake on the surface of the filter cloth, converting the static image of the filter cake on the surface of the filter cloth into a static grayscale image, and then performing denoising on the static grayscale image; The conversion process is as follows: obtaining the R value, G value and B value of all pixels in the static image of the filter cake, and calculating the gray value i corresponding to each pixel through the formula Y=0.3R+0.59G+0.11B; Specifically, the static grayscale image of the filter cake is denoised using Gaussian filtering, which is an existing technology; Step S2302, taking any gray value as a gray threshold t, t=[0, 255], and counting the number of first pixel points corresponding to the gray values ​​less than the gray threshold in the static gray image, and the number of second pixel points corresponding to the gray values ​​greater than or equal to the gray threshold; Step S2303, the pixel points corresponding to the grayscale values ​​less than the grayscale threshold in the static grayscale image are recorded as background pixel points, and the background image is composed of all the background pixel points; at the same time, the pixel points corresponding to the grayscale values ​​greater than or equal to the grayscale threshold in the static grayscale image are recorded as foreground pixel points, and the foreground image is composed of all the foreground pixel points; Among them, the background pixel points are the pixel points in the non-filter cake range in the static grayscale image, and the foreground pixel points are the pixel points in the filter cake range in the static grayscale image; Step S2303, obtain the total number of pixels XSZ in the static grayscale image of the filter cake and the number of pixels H(i) with grayscale value i, and calculate the probability P(i) that any pixel has a grayscale value i by the formula, which is as follows: P(i) = H(i) / XSZ; Step S2304, the background average grayscale value BPH of the background image is calculated by the formula, and the specific formula is as follows: ; Then the grayscale variance BJF(t) of the background image is calculated by the formula, which is as follows: ; Step S2305, the foreground average gray value QPH of the foreground image is calculated by the formula, and the specific formula is as follows: ; Then the grayscale variance QJF(t) of the foreground image is calculated by the formula, which is as follows: ; Step S2306, the inter-class variance LJF(t) of the static grayscale image is calculated by the formula, and the specific formula is as follows: LJF(t)=BJX(t)×BJF²(t)+QJX(t)×QJF²(t); Among them, the larger the inter-class variance of the static grayscale image is, the more obvious the distinction between the grayscale image representing the filter cake range and the grayscale image representing the non-filter cake range is; Step S2307, after removing the selected grayscale value, the grayscale threshold t is increased from zero to t = [0, 255], and the grayscale threshold that maximizes the inter-class variance is calculated, and the corresponding grayscale threshold is used as the optimal threshold for binarizing the static grayscale image, and the static grayscale image is binarized according to the optimal threshold to obtain a binary image of the filter cake; Step S2308, analyzing the binary image of the filter cake to obtain edge pixel points of the filter cake, and connecting the edge pixel points of the filter cake one by one to obtain the filter cake outline; Specifically, edge pixels of the filter cake are obtained by contour detection, and contour detection includes Sobel operator, Prewitt operator or Canny edge detection, etc., which are existing technologies; Step S2309, as Figure 3 As shown, a vertical line is drawn from any pixel point of the top contour of the filter cake contour to the bottom contour, the number of pixel points intersecting with the vertical line is calculated, and the vertical line with the maximum number of pixel points is traversed to obtain the vertical line, and the pixel point corresponding to the top contour is recorded as the thickest point of the filter cake; In this embodiment, the top contour is the surface contour of the filter cake, and the bottom contour is the surface of the filter cloth; Step S2310, obtaining a proportionality coefficient between the static image and the actual size of the filter cake, and calculating the maximum thickness corresponding to the thickest point of the filter cake through the proportionality coefficient.

[0022] Step S3, obtaining the filtrate and filter cake after the material to be tested is centrifuged, and calculating the filtrate qualification index of the filtrate and the filter cake qualification index of the filter cake; In this embodiment, step S3 includes the following sub-steps: Step S31, when the maximum thickness of the filter cake reaches the first thickness threshold, the storage tank stops feeding, and if the liquid outlet of the bag turning centrifuge is still outputting filtrate, the drum maintains the second rotation speed until there is no filtrate output from the liquid outlet, or the maximum thickness of the filter cake reaches the second thickness threshold, the liquid outlet is closed, and the filtrate of the material to be tested is obtained at the same time; wherein the second thickness threshold is greater than the first thickness threshold, and the first thickness threshold is greater than zero; Step S32, setting the rotation speed of the drum to a third rotation speed, performing a bag turning operation on the filter bag, and setting a bag turning rotation time; Specifically, the second rotation speed is greater than the first rotation speed, and the first rotation speed is greater than the third rotation speed; the third rotation speed is used to discharge the filter cake; It should be specifically stated that the filter cloth is a component of the filter bag. The filter cloth is used to filter the solid matter in the material to be tested, and the filter bag is used to wrap the filter cloth. The filter bag is turned over to remove the filter cake on the surface of the filter cloth. Step S33, when the rotation time of the drum reaches the bag turning rotation time, the drum stops rotating and closes the discharge port to obtain the filter cake of the material to be tested; Step S34, detecting the real-time moisture content SHS, real-time impurity content SZL and real-time weight SZL of the filter cake corresponding to the material to be tested; Then, the moisture content threshold, impurity content threshold and weight threshold of the filter cake corresponding to the material to be tested are obtained; wherein the moisture content threshold, impurity content threshold and weight threshold are ideal data obtained under ideal conditions for materials with the same weight as the material to be tested; Step S35, if any one of the following occurs: the real-time moisture content is greater than the moisture content threshold, the real-time impurity content is greater than the impurity content threshold, or the real-time weight is greater than the weight threshold, no operation is performed; Step S36: If the real-time moisture content is less than or equal to the moisture content threshold, the real-time impurity content is less than or equal to the impurity content threshold, and the real-time weight is less than or equal to the weight threshold, the filter cake qualification index BHZ is calculated by the formula, and the specific formula is as follows: BHZ=1 / [(SHS / BHS)×w1+(SZL / BZL)×w2+(SZL / BZL)×w3], where w1, w2 and w3 are weight coefficients with fixed values, and w1>w2>w3, BHS is the standard value of real-time moisture content, BZL is the standard value of real-time impurity content, BZL is the standard value of real-time weight, and the standard value is 1. The standard value is used to remove the dimension of each parameter in the formula; Specifically, the filter cake qualification index is used to reflect the separation of solids in the tested material by the bag-turning centrifuge; Step S37, detecting the real-time solid content GTH and real-time transmittance TGD of the filtrate corresponding to the material to be tested, and then obtaining the solid content threshold BGTH and transmittance threshold BTGD of the filtrate; wherein the standard solid content and standard transmittance are also ideal data obtained under ideal conditions for materials of the same weight as the material to be tested; Step S38, if the real-time solid content is greater than the solid content threshold or the real-time transmittance is less than the transmittance threshold, no operation is performed; Step S39: If the real-time solid content is less than or equal to the solid content threshold, and the real-time transmittance is greater than or equal to the transmittance threshold, the filtrate qualification index YHZ is calculated by the formula, and the specific formula is as follows: YHZ=v1×(TGD / BTGD) / v2×(GTH / BGTH), where v1 and v2 are weight coefficients with fixed values, and v1>v2, BTGD is the standard value of the transmittance threshold, BGTH is the standard value of the solid content threshold, and the standard value is 1. The standard value is used to remove the dimension of each parameter in the formula; Among them, the filtrate qualification index is used to reflect the separation of liquid in the test material by the bag centrifuge.

[0023] Step S4, judging the centrifugal effect of the bag inverting centrifuge based on the filtrate qualification index and the filter cake qualification index, and improving the bag inverting centrifuge according to the centrifugal effect; In this embodiment, step S4 includes the following sub-steps: Step S41, if the filtrate qualification index is greater than the filtrate qualification index threshold, proceed to step S42; If the filtrate qualified index is less than or equal to the filtrate qualified index threshold, the test material is randomly sampled again, and step S22 is repeated. When the feed port of the bag turning centrifuge detects that the test material enters, the rotation speed of the drum is gradually increased upward with the second rotation speed as the initial speed, until the filtrate qualified index obtained by subsequent detection is greater than the filtrate qualified index threshold, and the corresponding rotation speed is used as the standard rotation speed; Step S42, when the filter cake qualification index is greater than the filter cake qualification index threshold, the centrifugal effect of the bag turning centrifuge is determined to be excellent, and no operation is performed; When the test score of the bag centrifuge is less than or equal to the score threshold, proceed to the next step; Step S43, reducing the rotation speed of the drum in the bag-turning centrifuge to zero, and detecting the number of holes on the surface of the filter cloth; Specifically, the number of holes on the filter cloth surface is detected by using visual technology, which specifically includes edge detection algorithm, deep learning image segmentation technology and stereo vision technology. This embodiment uses edge detection algorithm as a method for detecting the number of holes on the filter cloth surface, and the edge detection algorithm is an existing technology. It should be specifically noted that there are tiny holes on the surface of the filter cloth, which are used to discharge the filtrate and block the solid matter in the material to be tested. When the filter cake is not completely discharged, the remaining filter cake blocks the holes on the surface of the filter cloth, resulting in a decrease in the number of holes on the surface of the filter cloth; Step S44, if the number of holes on the filter cloth surface is greater than the number threshold, no operation is performed; If the number of holes on the filter cloth surface is less than or equal to the number threshold, increase the rotation time of the drum and detect the number of holes on the filter cloth surface at fixed intervals until the number of holes on the filter cloth surface is greater than the number threshold. The drum stops rotating and records the corresponding bag turning rotation time as the standard bag turning rotation time.

[0024] In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.

[0025] Embodiment 2: Figure 4 The following is a schematic diagram of the structure of a computer device, such as Figure 4 As shown, the computer device may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute a visual aid method for a bag-turning centrifuge, the method comprising: randomly sampling the test material, and then processing the sampled test material; the bag-turning centrifuge performs centrifugal operation on the test material, and detects the maximum thickness of the filter cake on the filter cloth surface of the bag-turning centrifuge in real time; obtains the filtrate and filter cake of the test material after the centrifugal operation, and calculates the filtrate qualification index of the filtrate and the filter cake qualification index of the filter cake; judges the centrifugal effect of the bag-turning centrifuge based on the filtrate qualification index and the filter cake qualification index, and improves the bag-turning centrifuge according to the centrifugal effect.

[0026] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0027] Embodiment three, the present application also provides a computer program product, the computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by the computer, the computer can execute a visual assistance method for a bag-turning unloading centrifuge provided by the above methods, the method including: randomly sampling the test material, and then processing the sampled test material; the bag-turning centrifuge performs centrifugal operation on the test material, and real-time detects the maximum thickness of the filter cake on the surface of the filter cloth in the bag-turning centrifuge; obtains the filtrate and filter cake of the test material after the centrifugal operation, and calculates the filtrate qualification index of the filtrate and the filter cake qualification index of the filter cake; judges the centrifugal effect of the bag-turning centrifuge based on the filtrate qualification index and the filter cake qualification index, and improves the bag-turning centrifuge according to the centrifugal effect.

[0028] In the fourth embodiment, the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the visual assistance method for a bag-turning unloading centrifuge provided above, the method comprising: randomly sampling the test material, and then processing the sampled test material; centrifuging the test material with the bag-turning centrifuge, and detecting the maximum thickness of the filter cake on the surface of the filter cloth in the bag-turning centrifuge in real time; obtaining the filtrate and filter cake of the test material after the centrifugal operation, and calculating the filtrate qualification index of the filtrate and the filter cake qualification index of the filter cake; judging the centrifugal effect of the bag-turning centrifuge based on the filtrate qualification index and the filter cake qualification index, and improving the bag-turning centrifuge according to the centrifugal effect.

[0029] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0030] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0031] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A visual assistance method for bag unloading centrifuge, characterized in that: Methods include: Step S1, randomly sampling the test materials, and then processing the sampled materials to be tested; Step S2, the bag centrifuge performs centrifugal operation on the material to be tested, and detects the maximum thickness of the filter cake on the filter cloth surface in the bag centrifuge in real time; Step S3, obtaining the filtrate and filter cake after the material to be tested is centrifuged, and calculating the filtrate qualification index of the filtrate and the filter cake qualification index of the filter cake; Step S4, judging the centrifugal effect of the bag inverting centrifuge based on the filtrate qualification index and the filter cake qualification index, and improving the bag inverting centrifuge according to the centrifugal effect.

2. A visual assistance method for bag unloading centrifuge according to claim 1, characterized in that: The step S1 includes the following sub-steps: Step S11, stirring the test materials of the same production batch for a preset stirring time, and then randomly sampling from the uniformly stirred test materials; Step S12, when the weight of the test material is less than or equal to the preset weight threshold, randomly selecting a first fixed weight ratio of the test material as the material to be tested; Step S13, when the weight of the test material is greater than the preset weight threshold, randomly select a second fixed weight ratio of the test material as the material to be tested; wherein the first fixed weight ratio is greater than the second fixed weight ratio.

3. A visual assistance method for bag unloading centrifuge according to claim 1, characterized in that: The step S2 includes the following sub-steps: Step S21, inputting the material to be tested into the storage tank, and then setting the feeding mode of the bag centrifuge to continuous feeding; Step S22, setting the corresponding rotation speed of the drum in the bag turning centrifuge to the first rotation speed, inputting the material to be tested into the bag turning centrifuge at a uniform speed, and setting the rotation speed of the drum to the second rotation speed when the feed port of the bag turning centrifuge detects that the material to be tested enters; Step S23, detecting the maximum thickness of the filter cake on the surface of the filter cloth in the bag-turning centrifuge.

4. A visual assistance method for bag unloading centrifuge according to claim 3, characterized in that: The step S23 includes the following sub-steps: Step S2301, obtaining a static image of the filter cake on the filter cloth surface, and converting the static image of the filter cake on the filter cloth surface into a static grayscale image, and then performing denoising on the static grayscale image, specifically: The R value, G value and B value of all pixels in the static image of the filter cake are obtained, and the gray value i corresponding to each pixel is calculated by the formula Y=0.3R+0.59G+0.11B; Step S2302, taking any gray value as a gray threshold, and counting the number of first pixel points corresponding to the gray values ​​less than the gray threshold, and the number of second pixel points corresponding to the gray values ​​greater than or equal to the gray threshold in the static gray image; Step S2303, the pixel points corresponding to the grayscale values ​​less than the grayscale threshold in the static grayscale image are recorded as background pixel points, and the background image is composed of all the background pixel points; at the same time, the pixel points corresponding to the grayscale values ​​greater than or equal to the grayscale threshold in the static grayscale image are recorded as foreground pixel points, and the foreground image is composed of all the foreground pixel points; Among them, the background pixel points are the pixel points in the non-filter cake range in the static grayscale image, and the foreground pixel points are the pixel points in the filter cake range in the static grayscale image; Step S2303, obtain the total number of pixels XSZ in the static grayscale image of the filter cake and the number of pixels H(i) with grayscale value i, and calculate the probability P(i) that any pixel has a grayscale value i by the formula, which is as follows: P(i) = H(i) / XSZ; Step S2304, the background average grayscale value BPH of the background image is calculated by the formula, and the specific formula is as follows: ； Then the grayscale variance BJF(t) of the background image is calculated by the formula, which is as follows: 。 5. A visual assistance method for bag unloading centrifuge according to claim 4, characterized in that: The step S23 further includes the following sub-steps: Step S2305, the foreground average gray value QPH of the foreground image is calculated by the formula, and the specific formula is as follows: ； Then the grayscale variance QJF(t) of the foreground image is calculated by the formula, which is as follows: ； Step S2306, the inter-class variance LJF(t) of the static grayscale image is calculated by the formula, and the specific formula is as follows: LJF(t)=BJX(t)×BJF²(t)+QJX(t)×QJF²(t); Step S2307, after removing the selected grayscale value, the grayscale threshold t is increased from zero to t = [0, 255], and the grayscale threshold that maximizes the inter-class variance is calculated, and the corresponding grayscale threshold is used as the optimal threshold for binarizing the static grayscale image, and the static grayscale image is binarized according to the optimal threshold to obtain a binary image of the filter cake; Step S2308, analyzing the binary image of the filter cake to obtain edge pixel points of the filter cake, and connecting the edge pixel points of the filter cake one by one to obtain the filter cake outline; Step S2309, draw a vertical line from any pixel point of the top contour of the filter cake contour to the bottom contour, calculate the number of pixel points intersecting with the vertical line, traverse to obtain the vertical line with the maximum number of pixel points, and record the pixel point corresponding to the top contour as the thickest point of the filter cake; Step S2310, obtaining a proportionality coefficient between the static image and the actual size of the filter cake, and calculating the maximum thickness corresponding to the thickest point of the filter cake through the proportionality coefficient.

6. A visual assistance method for bag unloading centrifuge according to claim 3, characterized in that: The step S3 includes the following sub-steps: Step S31, when the maximum thickness of the filter cake reaches the first thickness threshold, the storage tank stops feeding, and if the liquid outlet of the bag turning centrifuge is still outputting filtrate, the drum maintains the second rotation speed until there is no filtrate output from the liquid outlet, or the maximum thickness of the filter cake reaches the second thickness threshold, the liquid outlet is closed, and the filtrate of the material to be tested is obtained at the same time; wherein the second thickness threshold is greater than the first thickness threshold, and the first thickness threshold is greater than zero; Step S32, setting the rotation speed of the drum to the third rotation speed, turning the filter bag over at the same time, and setting the bag turning rotation time; wherein the second rotation speed is greater than the first rotation speed, and the first rotation speed is greater than the third rotation speed; the third rotation speed is used to discharge the filter cake; Step S33, when the rotation time of the drum reaches the bag turning rotation time, the drum stops rotating and closes the discharge port to obtain the filter cake of the material to be tested; Step S34, detecting the real-time moisture content SHS, real-time impurity content SZL and real-time weight SZL of the filter cake corresponding to the material to be tested; Then, the moisture content threshold, impurity content threshold and weight threshold of the filter cake corresponding to the material to be tested are obtained; wherein the moisture content threshold, impurity content threshold and weight threshold are ideal data obtained under ideal conditions for materials with the same weight as the material to be tested; Step S35: If any one of the following occurs: the real-time moisture content is greater than the moisture content threshold, the real-time impurity content is greater than the impurity content threshold, or the real-time weight is greater than the weight threshold, no operation is performed.

7. A visual assistance method for bag unloading centrifuge according to claim 6, characterized in that: The step S3 also includes the following sub-steps: Step S36: If the real-time moisture content is less than or equal to the moisture content threshold, the real-time impurity content is less than or equal to the impurity content threshold, and the real-time weight is less than or equal to the weight threshold, the filter cake qualification index BHZ is calculated by the formula, and the specific formula is as follows: BHZ=1 / [(SHS / BHS)×w1+(SZL / BZL)×w2+(SZL / BZL)×w3], where w1, w2 and w3 are weight coefficients with fixed values, and w1>w2>w3, BHS is the standard value of real-time moisture content, BZL is the standard value of real-time impurity content, BZL is the standard value of real-time weight, and the standard value is 1; Step S37, detecting the real-time solid content GTH and real-time transmittance TGD of the filtrate corresponding to the material to be tested, and then obtaining the solid content threshold BGTH and transmittance threshold BTGD of the filtrate; Step S38, if the real-time solid content is greater than the solid content threshold or the real-time transmittance is less than the transmittance threshold, no operation is performed; Step S39, if the real-time solid content is less than or equal to the solid content threshold, and the real-time transmittance is greater than or equal to the transmittance threshold, the filtrate qualification index YHZ is calculated by the formula YHZ=v1×(TGD / BTGD) / v2×(GTH / BGTH); wherein v1 and v2 are weight coefficients of fixed values, and v1>v2, BTGD is the standard value of the transmittance threshold, BGTH is the standard value of the solid content threshold, and the standard value is 1.

8. A visual assistance method for bag unloading centrifuge according to claim 7, characterized in that: The step S4 includes the following sub-steps: Step S41, if the filtrate qualification index is greater than the filtrate qualification index threshold, proceed to step S42; If the filtrate qualified index is less than or equal to the filtrate qualified index threshold, the test material is randomly sampled again, and step S22 is repeated. When the feed port of the bag turning centrifuge detects that the test material enters, the rotation speed of the drum is gradually increased upward with the second rotation speed as the initial speed, until the filtrate qualified index obtained by subsequent detection is greater than the filtrate qualified index threshold, and the corresponding rotation speed is used as the standard rotation speed; Step S42, when the filter cake qualification index is greater than the filter cake qualification index threshold, the centrifugal effect of the bag turning centrifuge is determined to be excellent, and no operation is performed; When the test score of the bag centrifuge is less than or equal to the score threshold, proceed to the next step; Step S43, reducing the rotation speed of the drum in the bag-turning centrifuge to zero, and detecting the number of holes on the surface of the filter cloth; Step S44, if the number of holes on the filter cloth surface is greater than the number threshold, no operation is performed; If the number of holes on the filter cloth surface is less than or equal to the number threshold, increase the rotation time of the drum and detect the number of holes on the filter cloth surface at fixed intervals until the number of holes on the filter cloth surface is greater than the number threshold. The drum stops rotating and records the corresponding bag turning rotation time as the standard bag turning rotation time.

9. A computer device, characterized in that: The computer device comprises: A memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, the method described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images