A method for predicting clean coal ash content in flotation process

Abstract

The present invention relates to a method for predicting the ash content of clean coal in a flotation process, which belongs to the technical field of prediction of key indicators in the coal preparation industry, and solves the problem that the existing flotation clean coal ash content cannot be effectively, accurately and quickly detected. The method comprises: real-time data collection, including flotation foam images, tailings images, flotation feed concentration, flotation feed flow rate and flotation liquid level; inputting the real-time collected flotation foam images into a trained main model for prediction of clean coal ash content, and processing to obtain a predicted value of clean coal ash content; normalizing the grayscale characteristic values, flotation feed concentration, flotation feed flow rate and flotation liquid level of the real-time collected tailings images, respectively, and inputting the normalized grayscale characteristic values, flotation feed concentration, flotation feed flow rate and flotation liquid level into a trained clean coal ash content prediction compensation model, and processing to obtain a predicted value of clean coal ash content error; using the predicted value of clean coal ash content error to compensate the predicted value of clean coal ash content, and obtain a predicted result of clean coal ash content.

Description

Technical Field

[0001] The invention relates to the technical field of prediction of key indicators in coal preparation industry, and in particular to a method for predicting ash content of clean coal in a flotation process. Background Art

[0002] China is a major coal producer and consumer. With the proposal of the "dual carbon" goal, the coal industry needs to build an efficient and clean utilization system, and the transformation of coal preparation plants to digitalization, automation and intelligence has become inevitable. Flotation is the most widely used method for fine coal sorting. It mainly uses the difference in hydrophobicity of mineral surfaces to separate fine-grained coal from gangue. It is a very complex physical and chemical process affected by the synergistic effect of multiple variables.

[0003] However, the coal preparation plant has always monitored the ash content of clean coal through the quick ash test, and the quick ash test process takes at least one hour, which has a serious lag in guiding flotation production. Therefore, the flotation process mainly relies on the on-site workers to control based on experience, but this method is highly subjective, has large errors, low efficiency, and will also cause waste of flotation reagents and mineral resources.

[0004] Therefore, how to effectively, accurately and quickly detect the ash content of flotation clean coal is of great significance to the coal preparation plant in reducing reagent consumption and efficiently recovering resources. Summary of the invention

[0005] In view of the above analysis, an embodiment of the present invention aims to provide a method for predicting the ash content of clean coal in a flotation process, so as to solve the problem that the ash content of the existing flotation clean coal cannot be effectively, accurately and quickly detected.

[0006] The present invention discloses a method for predicting the ash content of clean coal in a flotation process, comprising:

[0007] Real-time data collection, including flotation foam images, tailings images, flotation feed concentration, flotation feed flow and flotation liquid level;

[0008] The real-time collected flotation foam image is input into the trained clean coal ash content prediction main model, and the clean coal ash content prediction value is obtained after processing;

[0009] The grayscale characteristic values, flotation feed concentration, flotation feed flow rate and flotation liquid level of the tailings image collected in real time are normalized respectively, and the normalized grayscale characteristic values, flotation feed concentration, flotation feed flow rate and flotation liquid level are input into the trained clean coal ash content prediction compensation model, and the clean coal ash content error prediction value is obtained after processing;

[0010] The clean coal ash content prediction value is compensated by the clean coal ash content error prediction value to obtain a final clean coal ash content prediction result.

[0011] On the basis of the above scheme, the present invention also makes the following improvements:

[0012] Further, the clean coal ash content prediction main model is trained in the following manner:

[0013] Acquire a first sample set, wherein each set of first sample data in the first sample set includes: a flotation froth image and a measured value of clean coal ash content;

[0014] The flotation foam image of the clean coal in each group of first sample data is used as input and the actual measured value of the clean coal ash content is used as a label, the main model for predicting the clean coal ash content is trained, the structure and parameters of the main model for predicting the clean coal ash content are determined, and a trained main model for predicting the clean coal ash content is obtained.

[0015] Further, the clean coal ash content prediction compensation model is trained in the following manner:

[0016] Acquire a second sample set, wherein each set of second sample data in the second sample set includes: a flotation froth image, a tailings image, a flotation feed concentration, a flotation feed flow rate, a flotation liquid level, and a measured value of clean coal ash content;

[0017] Inputting the flotation foam images in each group of second sample data into the trained clean coal ash content prediction main model to obtain the clean coal ash content prediction value;

[0018] Normalizing the grayscale characteristic value, flotation feed concentration, flotation feed flow rate and flotation liquid level of the tailings image in each group of second sample data respectively;

[0019] The normalized grayscale characteristic value, flotation feed concentration, flotation feed flow rate and flotation liquid level corresponding to each group of second sample data are taken as input, and the difference between the corresponding measured value of clean coal ash content and the predicted value of clean coal ash content is taken as a label. The clean coal ash content prediction and compensation model is trained, and the structure and parameters of the clean coal ash content prediction and compensation model are determined to obtain the trained clean coal ash content prediction and compensation model.

[0020] Furthermore, the main model for predicting clean coal ash content is a main model for predicting clean coal ash content based on a convolutional neural network.

[0021] Furthermore, the clean coal ash content prediction and compensation model uses a prediction and compensation model based on a radial basis function neural network.

[0022] Furthermore, the grayscale characteristic values ​​include grayscale mean value, variance, smoothness and energy entropy;

[0023] The grayscale feature value is obtained by performing grayscale histogram extraction on the tailings image.

[0024] Furthermore, the normalization process uses a maximum-minimum normalization method.

[0025] Further, the flotation foam image is acquired by a foam image acquisition system fixed above the flotation foam liquid surface;

[0026] The foam image acquisition system has a built-in CCD industrial camera, and LED light sources are fixed on both sides of the industrial camera at a downward angle of 45 degrees.

[0027] Further, the tailings image is acquired by a tailings image acquisition system;

[0028] The tailings image acquisition system has a built-in CCD industrial camera;

[0029] The tailings image acquisition system is built next to the flotation tailings tank. A real-time flotation tailings sample is pumped into an imaging black box by a pump. The light source in the black box is fixed, and the tailings image is acquired by a CCD camera.

[0030] Further, a concentration meter is used to detect the concentration of the flotation feed in real time at the flotation feed pipeline;

[0031] Use a flow meter to detect the flotation feed flow rate in real time at the flotation feed pipeline;

[0032] Use a float level meter to detect the flotation level in real time.

[0033] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0034] The method for predicting the ash content of clean coal in a flotation process provided by the present invention has the following advantages:

[0035] First, the clean coal ash content prediction value is determined based on the real-time collected flotation foam image, and the clean coal ash content error prediction value is determined based on the real-time collected tailings image, flotation feed concentration, flotation feed flow rate and flotation liquid level. The clean coal ash content prediction value is compensated by the clean coal ash content error prediction value to obtain the final clean coal ash content prediction result, which can realize the effective, accurate and rapid detection of flotation clean coal ash content, so that the coal preparation plant can timely adjust the coal slime flotation according to the prediction result.

[0036] Second, it can realize the real-time online continuous detection of the ash content of the flotation clean coal, and has a certain degree of self-adaptation, and can correct the predicted value according to the production situation. According to the predicted value, the flotation working condition can be adjusted in time, the reagent consumption can be reduced, and the utilization rate of mineral resources can be improved.

[0037] Third, the present invention utilizes a main model for predicting clean coal ash content based on a convolutional neural network and a compensation model for predicting clean coal ash content based on a radial basis function neural network to realize online prediction of flotation clean coal ash content through foam images and tailings images in the flotation production process and other production process parameters. The prediction results are used to guide the regulation of the flotation production process.

[0038] In the present invention, the above-mentioned technical solutions can also be combined with each other to achieve more preferred combination solutions. Other features and advantages of the present invention will be described in the subsequent description, and some advantages can become obvious from the description, or can be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings are only for the purpose of illustrating particular embodiments and are not to be considered limiting of the present invention. Like reference symbols denote like components throughout the drawings.

[0040] Figure 1 A schematic diagram of a clean coal ash content prediction process for a flotation process provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of the training process of the main model for predicting clean coal ash content in the flotation process provided by an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of the training process of a clean coal ash content prediction and compensation model for a flotation process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0044] A specific embodiment of the present invention discloses a method for predicting the ash content of clean coal in a flotation process, the flow chart of which is as follows: Figure 1 As shown, the following steps are included:

[0045] Step S1: real-time data collection, including flotation foam image, tailings image, flotation feed concentration, flotation feed flow rate and flotation liquid level;

[0046] Step S2: input the flotation foam image collected in real time into the trained main model for clean coal ash content prediction, and obtain the clean coal ash content prediction value after processing; in specific implementation, the flotation foam image can be first preprocessed (such as filtering processing), and then the preprocessed flotation foam image can be input into the trained main model for clean coal ash content prediction, so as to remove clutter in the flotation foam image.

[0047] The grayscale eigenvalues, flotation feed concentration, flotation feed flow rate and flotation liquid level of the tailings image collected in real time are normalized respectively, and the normalized grayscale eigenvalues, flotation feed concentration, flotation feed flow rate and flotation liquid level are input into the trained clean coal ash content prediction and compensation model to obtain the clean coal ash content error prediction value after processing; in specific implementation, the tailings image can be first preprocessed (such as filtering processing) and then the grayscale eigenvalue is obtained through grayscale histogram processing.

[0048] Step S3: compensating the clean coal ash content prediction value with the clean coal ash content error prediction value to obtain a final clean coal ash content prediction result.

[0049] The flotation foam image contains rich foam color, foam texture and foam size characteristics, and the above characteristics have a strong correlation with the flotation clean coal, which is specifically reflected in: if the flotation foam is dark black, the foam surface is wrinkled and has more textures, and the number of flotation foams per unit area is large, it means that the current flotation foam carries a large amount of clean coal, and the clean coal ash content is low at this time; on the contrary, if the flotation foam is bright black, the foam surface is smooth and mostly large virtual bubbles, it means that the current foam carries a small amount of clean coal, and at this time, a large amount of flotation clean coal is lost, the tail coal ash content is reduced, and the clean coal ash content is increased. Therefore, the clean coal ash content can be predicted based on the flotation foam image.

[0050] In addition, tailings image, flotation feed concentration, flotation feed flow rate and flotation liquid level also have different degrees of influence on the prediction of clean coal ash content, which is specifically reflected in:

[0051] (1) There are obvious differences in the grayscale characteristics of tailings images with different ash contents: the lower the tailings ash content, the darker the corresponding tailings image, otherwise, the brighter the corresponding tailings image; at the same time, when the feed ash content fluctuates slightly, there is a strong linear correlation between the tailings ash content and the clean coal ash content. The specific formula is as follows:

[0052]

[0053] Among them, Ad Y 、Ad J 、Ad W They represent the ash content of raw coal, clean coal and tailings respectively, and γ J and γ W They represent the flotation clean coal yield and flotation tail coal yield respectively; during the flotation process, the ash content of the flotation raw coal generally does not fluctuate much, while the clean coal yield and tail coal yield can be detected in real time by a belt scale. Therefore, after simplification, the following linear relationship can be obtained:

[0054] Ad J =K×Ad W +B (2)

[0055] From formula (2), it can be seen that there is a correlation between the ash content of tailings and the ash content of clean coal, and this correlation can be evaluated by analyzing the grayscale feature value of the tailings image;

[0056] (2) The flotation feed concentration and flotation feed flow rate reflect the current processing capacity of the flotation system in real time. When the processing capacity is within a reasonable range, the ash content of the clean coal is relatively low; when the processing capacity increases while other conditions remain unchanged, the flotation clean coal will be lost, and the ash content of the flotation clean coal will increase accordingly; when the processing capacity decreases, the gangue minerals will also be brought into the concentrate, and the ash content of the flotation clean coal will also increase;

[0057] (3) The flotation liquid level reflects the current operating conditions of the flotation equipment. A high liquid level will reduce the concentrate grade, while a low liquid level will reduce the amount of foam scraped out and reduce the clean coal recovery rate;

[0058] Based on the above analysis, it can be seen that the clean coal ash compensation value can be evaluated based on the grayscale feature value of the tailings image, the flotation feed concentration, the flotation feed flow rate and the flotation liquid level. Then, the clean coal ash prediction value is compensated with the clean coal ash error prediction value to obtain the final clean coal ash prediction result. Therefore, the clean coal ash prediction result of the flotation process obtained by the above method is highly accurate.

[0059] Preferably, the flotation foam image is acquired by a foam image acquisition system fixed above the flotation foam liquid surface; the foam image acquisition system has a built-in CCD industrial camera, and LED light sources are fixed on both sides of the industrial camera at a downward angle of 45°; to ensure that the flotation foam image is not disturbed by external factors. Preferably, the tailings image is acquired by a tailings image acquisition system; the tailings image acquisition system has a built-in CCD industrial camera; the tailings image acquisition system is built next to the flotation tailings tank, and the real-time flotation tailings sample is pumped into the imaging black box by a pump, the light source in the black box is fixed, and the tailings image is acquired by the CCD camera. The system is in a confined space to ensure that the tailings image is collected without external interference. In addition, a concentration meter is used to detect the flotation feed concentration in real time at the flotation feed pipeline; a flow meter is used to detect the flotation feed flow in real time at the flotation feed pipeline; and a float level meter is used to detect the flotation liquid level in real time.

[0060] Before implementing the above scheme, the training of the main model for clean coal ash content prediction and the compensation model for clean coal ash content prediction must be completed. The specific implementation method is introduced as follows:

[0061] (1) The clean coal ash content prediction main model is trained in the following manner. The training process is as follows: Figure 2 As shown:

[0062] Step A1: obtaining a first sample set, wherein each group of first sample data in the first sample set includes: a flotation froth image and a measured value of clean coal ash content; specifically, the first sample set is obtained by:

[0063] Step A11: collecting a large number of flotation foam images and actual ash content of clean coal at corresponding time;

[0064] Step A12: screening the collected flotation foam images to select flotation foam images with high definition; and preprocessing the screened flotation foam images to remove noise from the flotation foam images;

[0065] Step A13: cropping the preprocessed flotation foam image to obtain a flotation foam image of a suitable size;

[0066] Step A14: each cropped flotation foam image and the actual ash content of the clean coal at the corresponding time are respectively taken as a group of first sample data; all the first sample data are aggregated to form a first sample set.

[0067] Step A2: Take the flotation foam image of the clean coal in each group of first sample data as input and the measured value of the clean coal ash content as a label, train the main model for predicting the clean coal ash content, determine the structure and parameters of the main model for predicting the clean coal ash content, and obtain a trained main model for predicting the clean coal ash content.

[0068] In the process of training the main model for clean coal ash content prediction, the mapping relationship between the foam color, foam texture and foam size characteristics in the flotation foam image and the measured value of clean coal ash content can be established. This mapping relationship is reflected by the structure and parameters of the main model for clean coal ash content prediction. Therefore, in the real-time processing process, the real-time collected flotation foam image can be input into the trained main model for clean coal ash content prediction, and the clean coal ash content prediction value can be obtained after processing.

[0069] Preferably, the main model for clean coal ash content prediction uses a main model for clean coal ash content prediction based on a convolutional neural network. During the training process of the main model for clean coal ash content prediction, the convolutional neural network back-propagates the error obtained by gradient descent, updates the parameters of each layer of the convolutional neural network layer by layer, and finally determines the structure and parameters of the main model for clean coal ash content prediction after multiple rounds of iterative training.

[0070] The main model for clean coal ash prediction based on convolutional neural network can make a preliminary prediction of the clean coal ash content of flotation, but it is unable to obtain high-precision prediction results due to factors such as complex flotation conditions, errors in the image acquisition process, and limited information reflected by the image. At the same time, other influencing factors of flotation clean coal ash content were also analyzed above. Therefore, according to these influencing factors of flotation clean coal ash content, the clean coal ash content prediction compensation model is trained to predict the deviation of the clean coal ash content prediction value of the main model for clean coal ash content prediction.

[0071] (2) The clean coal ash content prediction and compensation model is trained in the following manner: Figure 3 As shown:

[0072] Step B1: obtaining a second sample set, wherein each set of second sample data in the second sample set includes: flotation froth image, tailings image, flotation feed concentration, flotation feed flow, flotation liquid level and measured value of clean coal ash content; specifically, the second sample set is obtained by:

[0073] Step B11: acquiring sampling data at multiple time points, including: flotation foam image, tailings image, flotation feed concentration, flotation feed flow, flotation liquid level and measured value of clean coal ash content;

[0074] Step B12: Screening the sampling data, and only retaining the sampling data with relatively high clarity of flotation foam image and tailings image as candidate sampling data;

[0075] Step B13: cropping the flotation foam image and tailings image in the candidate sampling data to obtain a flotation foam image of a suitable size;

[0076] Step B14: taking each group of cropped candidate sampling data as a group of second sample data; and aggregating all the second sample data to form a second sample set.

[0077] Step B2: inputting the flotation foam images in each group of second sample data into the trained clean coal ash content prediction main model to obtain the clean coal ash content prediction value;

[0078] Step B3: respectively normalizing the grayscale feature value, flotation feed concentration, flotation feed flow rate and flotation liquid level of the tailings image in each group of second sample data;

[0079] Specifically, in this embodiment, the grayscale feature values ​​of the tailings image include grayscale mean, variance, smoothness and energy entropy; the grayscale feature values ​​are obtained by extracting the grayscale histogram of the tailings image. Preferably, the maximum and minimum normalization method is used to normalize the grayscale feature values ​​of the tailings image, the flotation feed concentration, the flotation feed flow rate and the flotation liquid level. After normalization, all data are converted to the [0,1] interval so that each indicator belongs to the same order of magnitude.

[0080] Step B4: Take the normalized grayscale characteristic value, flotation feed concentration, flotation feed flow rate and flotation liquid level corresponding to each group of second sample data as input, and take the difference between the corresponding measured value of clean coal ash content and the predicted value of clean coal ash content as a label, train the clean coal ash content prediction and compensation model, determine the structure and parameters of the clean coal ash content prediction and compensation model, and obtain the trained clean coal ash content prediction and compensation model.

[0081] Preferably, the clean coal ash content prediction and compensation model can be a prediction and compensation model based on radial basis function neural network. During the training process of the clean coal ash content prediction and compensation model, the structure and parameters of the radial basis function neural network can be determined by cross validation and gradient descent amplification.

[0082] In summary, compared with the prior art, the clean coal ash prediction method for a flotation process provided in this embodiment has the following advantages:

[0083] First, the clean coal ash content prediction value is determined based on the real-time collected flotation foam image, and the clean coal ash content error prediction value is determined based on the real-time collected tailings image, flotation feed concentration, flotation feed flow rate and flotation liquid level. The clean coal ash content prediction value is compensated by the clean coal ash content error prediction value to obtain the final clean coal ash content prediction result, which can realize the effective, accurate and rapid detection of flotation clean coal ash content, so that the coal preparation plant can timely adjust the coal slime flotation according to the prediction result.

[0084] Second, it can realize the real-time online continuous detection of the ash content of the flotation clean coal, and has a certain degree of self-adaptation, and can correct the predicted value according to the production situation. According to the predicted value, the flotation working condition can be adjusted in time, the reagent consumption can be reduced, and the utilization rate of mineral resources can be improved.

[0085] Third, the present invention utilizes a main model for predicting clean coal ash content based on a convolutional neural network and a compensation model for predicting clean coal ash content based on a radial basis function neural network to realize online prediction of flotation clean coal ash content through foam images and tailings images in the flotation production process and other production process parameters. The prediction results are used to guide the regulation of the flotation production process.

[0086] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0087] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for predicting clean coal ash content in a flotation process, characterized in that: include: Real-time data collection, including flotation foam images, tailings images, flotation feed concentration, flotation feed flow and flotation liquid level; The real-time collected flotation foam image is input into the trained clean coal ash content prediction main model, and the clean coal ash content prediction value is obtained after processing; The grayscale characteristic values, flotation feed concentration, flotation feed flow rate and flotation liquid level of the tailings image collected in real time are normalized respectively, and the normalized grayscale characteristic values, flotation feed concentration, flotation feed flow rate and flotation liquid level are input into the trained clean coal ash content prediction compensation model, and the clean coal ash content error prediction value is obtained after processing; The clean coal ash content prediction value is compensated by the clean coal ash content error prediction value to obtain a final clean coal ash content prediction result.

2. The method for predicting clean coal ash content in a flotation process according to claim 1, characterized in that: The clean coal ash content prediction main model is trained in the following way: Acquire a first sample set, wherein each set of first sample data in the first sample set includes: a flotation froth image and a measured value of clean coal ash content; The flotation foam image of the clean coal in each group of first sample data is used as input and the actual measured value of the clean coal ash content is used as a label, the main model for predicting the clean coal ash content is trained, the structure and parameters of the main model for predicting the clean coal ash content are determined, and a trained main model for predicting the clean coal ash content is obtained.

3. The method for predicting clean coal ash content in a flotation process according to claim 1, characterized in that: The clean coal ash prediction compensation model is trained in the following way: Acquire a second sample set, wherein each set of second sample data in the second sample set includes: a flotation froth image, a tailings image, a flotation feed concentration, a flotation feed flow rate, a flotation liquid level, and a measured value of clean coal ash content; Inputting the flotation foam images in each group of second sample data into the trained clean coal ash content prediction main model to obtain the clean coal ash content prediction value; Normalizing the grayscale characteristic value, flotation feed concentration, flotation feed flow rate and flotation liquid level of the tailings image in each group of second sample data respectively; The normalized grayscale characteristic value, flotation feed concentration, flotation feed flow rate and flotation liquid level corresponding to each group of second sample data are taken as input, and the difference between the corresponding measured value of clean coal ash content and the predicted value of clean coal ash content is taken as a label. The clean coal ash content prediction and compensation model is trained, and the structure and parameters of the clean coal ash content prediction and compensation model are determined to obtain the trained clean coal ash content prediction and compensation model.

4. The method for predicting clean coal ash content in a flotation process according to any one of claims 1 to 3, characterized in that: The clean coal ash content prediction main model adopts a clean coal ash content prediction main model based on a convolutional neural network.

5. The method for predicting clean coal ash content in a flotation process according to any one of claims 1 to 3, characterized in that: The clean coal ash content prediction and compensation model is a prediction and compensation model based on radial basis function neural network.

6. The method for predicting clean coal ash content in a flotation process according to any one of claims 1 to 3, characterized in that: The grayscale characteristic values ​​include grayscale mean value, variance, smoothness and energy entropy; The grayscale feature value is obtained by performing grayscale histogram extraction on the tailings image.

7. The method for predicting clean coal ash content in a flotation process according to claim 6, characterized in that: The normalization process uses a maximum and minimum value normalization method.

8. The method for predicting clean coal ash content in a flotation process according to any one of claims 1 to 3, characterized in that: The flotation foam image is acquired by a foam image acquisition system fixed above the flotation foam liquid surface; The foam image acquisition system has a built-in CCD industrial camera, and LED light sources are fixed on both sides of the industrial camera at a downward angle of 45 degrees.

9. The method for predicting clean coal ash content in a flotation process according to any one of claims 1 to 3, characterized in that: The tailings image is acquired by a tailings image acquisition system; The tailings image acquisition system has a built-in CCD industrial camera; The tailings image acquisition system is built next to the flotation tailings tank. A real-time flotation tailings sample is pumped into an imaging black box by a pump. The light source in the black box is fixed, and the tailings image is acquired by a CCD camera.

10. The method for predicting clean coal ash content in a flotation process according to any one of claims 1 to 3, characterized in that: Use a concentration meter to detect the flotation feed concentration in real time at the flotation feed pipeline; Use a flow meter to detect the flotation feed flow rate in real time at the flotation feed pipeline; Use a float level meter to detect the flotation level in real time.

Images