Method for measuring aluminum liquid fluctuation, two levels and electrolyte temperature of aluminum electrolytic cell

Abstract

The embodiment of the present disclosure provides a kind of aluminum electrolytic cell molten aluminum fluctuation, two level and electrolyte temperature measurement method, belong to the field of computing technology, specifically include: by target yolo-v5 model identification target aluminum electrolytic cell flame hole in picture, obtain in pixel coordinate system flame hole center point coordinate and the vertex coordinate of anchor frame;According to the vertex coordinate of anchor frame, judge whether the opening degree of flame hole is normal;With flame hole center point coordinate as target, drive measuring rod inserts into flame hole mouth;According to the time when measuring rod enters different interface according to different stress;According to the time when measuring rod enters different interface, calculate the electrolyte level data and molten aluminum level data of target aluminum electrolytic cell;After measuring rod touches bottom and stays reach preset time, measure the electrolyte temperature data in target aluminum electrolytic cell;According to moment data, calculate the molten aluminum fluctuation of target aluminum electrolytic cell in preset period.The scheme of the present disclosure improves the measurement accuracy and adaptability of aluminum electrolytic cell.

Description

Technical Field

[0001] This disclosure relates to the field of computational technology, and in particular to a method for measuring aluminum liquid fluctuation, two levels, and electrolyte temperature in an aluminum electrolysis cell. Background Technology

[0002] Currently, aluminum is the world's largest-produced non-ferrous metal and an indispensable basic raw material for promoting national economic construction, defense science and technology industries, and the development of strategic emerging industries. It is widely used in construction, power, packaging, transportation, aerospace, and other fields. As a crucial production equipment in the molten salt electrolysis process, the aluminum electrolytic cell's good condition is fundamental to maintaining normal electrolytic aluminum production and directly affects the production efficiency and economic benefits of the electrolytic aluminum plant. However, due to the complexity of the aluminum electrolytic cell's condition and the limitations of current technology, it is difficult to control the aluminum electrolytic cell in a dynamic thermal equilibrium during actual electrolytic aluminum production. This often results in red-hot furnaces and leaks, causing not only huge economic losses to enterprises but also potentially leading to serious accidents such as fires and explosions, and even injuries or fatalities to on-site personnel. Therefore, to avoid such accidents, effective monitoring of the aluminum melt fluctuations, the two levels (heat level and electrolyte temperature) of the electrolytic cell is essential. However, most existing measurement methods rely on manual measurement combined with empirical formulas, which places high demands on the operators' skills, and the measurement results are often singular and not precise enough.

[0003] It is evident that there is an urgent need for a method that provides high accuracy and adaptability for measuring the fluctuations, two levels, and electrolyte temperature of molten aluminum in aluminum electrolysis cells. Summary of the Invention

[0004] In view of this, the present disclosure provides a method for measuring the fluctuation of aluminum liquid in an aluminum electrolysis cell, the two levels, and the electrolyte temperature, which at least partially solves the problems of poor measurement accuracy and adaptability in the prior art.

[0005] In a first aspect, embodiments of this disclosure provide a method for measuring aluminum melt fluctuation, two levels, and electrolyte temperature in an aluminum electrolysis cell, including:

[0006] Step 1: Control the inspection equipment to take a picture of the fire eye of the target aluminum electrolytic cell, and identify the fire eye of the target aluminum electrolytic cell in the fire eye picture through the target YOLO-V5 model to obtain the coordinates of the center point of the fire eye and the vertex coordinates of the anchor box in the pixel coordinate system.

[0007] Step 2: Determine whether the opening degree of the fire eye is normal based on the vertex coordinates of the anchor frame. If yes, proceed to Step 3; otherwise, return to Step 1 and measure the next aluminum electrolysis cell.

[0008] Step 3: Using the principle of binocular vision, the coordinates of the center point of the fire eye and the vertex coordinates of the anchor box in the pixel coordinate system are converted into coordinates in the world coordinate system. With the coordinates of the center point of the fire eye as the target, the measuring rod is driven to insert into the fire eye opening.

[0009] Step 4: During the process of inserting the measuring rod into the fire hole, record the moment when the measuring rod enters different interfaces according to the different forces applied.

[0010] Step 5: Calculate the electrolyte level data and aluminum liquid level data of the target aluminum electrolysis cell based on the time when the measuring rod enters different interfaces;

[0011] Step 6: After the measuring rod touches the bottom and remains there for a preset time, measure the electrolyte temperature data in the target aluminum electrolysis cell;

[0012] Step 7: During the preset time period when the measuring rod touches the bottom and stays there, collect torque data in real time and calculate the fluctuation of aluminum liquid in the target aluminum electrolysis cell during the preset time period based on the torque data.

[0013] According to a specific implementation of this disclosure, before step 1, the method further includes:

[0014] Randomly sample video frame images from the pre-captured Huoyan video dataset and annotate them with anchor boxes;

[0015] A preset number of images are used as the training set for the initial YOLO-V5 model, and the remaining images are used as the test set for the initial YOLO-V5 model.

[0016] The initial YOLO-V5 model was trained using the k-means clustering method to obtain the target YOLO-V5 model.

[0017] According to a specific implementation of an embodiment of this disclosure, step 2 specifically includes:

[0018] Step 2.1: Calculate the anchor frame size based on the vertex coordinates of the anchor frame;

[0019] Step 2.2: Determine whether the anchor frame size is greater than the threshold. If yes, the opening degree of the fire eye is normal. If no, the opening degree of the fire eye is abnormal.

[0020] According to a specific implementation of an embodiment of this disclosure, step 3 specifically includes:

[0021] Step 3.1, let [u, v, 1] T Let [x] be the coordinates of the center point of the fire eye in the pixel coordinate system. w y w , z w ,1] TLet the coordinates of the center point of the fire-eye system be in the world coordinate system. Then, for the left and right cameras of the inspection equipment, there are respectively...

[0022]

[0023]

[0024] Step 3.2, based on the above two equations, we obtain...

[0025]

[0026]

[0027]

[0028]

[0029] Wherein, the matrix and For camera matrix;

[0030] Step 3.3: Solve for X, Y, and Z using the least squares method to obtain the coordinates of the center point of the fire eye and the vertices of the anchor frame in the world coordinate system.

[0031] According to a specific implementation of an embodiment of this disclosure, step 3 further includes:

[0032] The coordinates of the vertex of the anchor frame in the world coordinate system are used as the boundary for the movement of the measuring rod.

[0033] According to a specific implementation of an embodiment of this disclosure, step 4 specifically includes:

[0034] When the measuring rod moves from the air to the electrolyte liquid surface, it is subjected to the force of the electrolyte liquid flow. The force on the measuring rod increases, and the time t1 when it moves to this interface is obtained.

[0035] When the measuring rod enters the molten aluminum from the electrolyte liquid, the electromagnetic force is significantly greater than that of the electrolyte liquid. At this time, the force on the measuring rod increases, and the time t2 when it moves to this interface is obtained.

[0036] After the measuring rod is driven to the bottom, record the moment t3 when the motor power increases.

[0037] According to a specific implementation of an embodiment of this disclosure, step 5 specifically includes:

[0038] Step 5.1: Calculate the displacement x1 between times t1 and t2 as the electrolyte level based on the number of pulses generated by the control element between times t1 and t2;

[0039] Step 5.2: Calculate the displacement x2 between times t2 and t3 as the aluminum liquid level based on the number of pulses generated by the control element between times t2 and t3.

[0040] According to a specific implementation of an embodiment of this disclosure, step 5.1 specifically includes:

[0041] Assuming a fixed subdivision number, n L If the screw pitch is L and the number of pulses between times t1 and t2 is n1, then x1 = n1 / n L *L.

[0042] According to a specific implementation of an embodiment of this disclosure, step 5.2 specifically includes:

[0043] Assuming a fixed subdivision number, n L If the screw pitch is L and the number of pulses between times t2 and t3 is n2, then x2 = n2 / n L *L.

[0044] According to a specific implementation of an embodiment of this disclosure, step 7 specifically includes:

[0045] Let the x-axis represent the direction from side A to side B of the aluminum electrolysis cell, and the y-axis be the vertical direction. Assume the force at the contact point a between the measuring rod and the slider is F. 1x and F 1y The force at point b, the contact point between the measuring rod and the tank shell, is F. 2x and F 2y The turning point of the measuring rod is point d, and the angle between the turning part of the measuring rod and the horizontal direction is θ.

[0046] Measure the center of mass c of the measuring rod and the total weight m of the measuring rod, and calculate the distance L between points a, b, c, and d accordingly. ac L bc L cd ;

[0047] Assume the force F acting on the measuring rod in the target aluminum electrolysis cell is... 3x and F 3y For the entire measuring rod, F in the y-axis direction 1y +F 2y +F 3y -mg=0, therefore F 3y The value;

[0048] For torque equilibrium at the center of mass, F 1y *L ac +F 2y *L bc +F 3y *x n=0, X1 is obtained at the peak of the fluctuation, and X2 is obtained at the trough of the fluctuation. Calculate the aluminum liquid fluctuation h = (x1 - L) / (x1 - L) cd )*tanθ-(x2-l cd )*tanθ.

[0049] The aluminum electrolysis cell aluminum liquid fluctuation, two-level measurement, and electrolyte temperature measurement scheme in this embodiment includes: Step 1, controlling the inspection equipment to capture a picture of the target aluminum electrolysis cell, and identifying the target aluminum electrolysis cell's fire eye in the fire eye image using the target YOLO-V5 model, and obtaining the coordinates of the fire eye's center point and the vertex coordinates of the anchor frame in the pixel coordinate system; Step 2, judging whether the opening degree of the fire eye is normal based on the vertex coordinates of the anchor frame. If yes, proceed to Step 3; if no, return to Step 1 and measure the next aluminum electrolysis cell; Step 3, using the principle of binocular vision, reconstructing the fire eye's center point coordinates and the anchor frame's vertex coordinates in the pixel coordinate system. The coordinates are converted to coordinates in the world coordinate system. Using the center point of the fire eye as the target, the measuring rod is driven to insert into the fire eye opening. Step 4: During the process of driving the measuring rod to insert into the fire eye opening, the time when the measuring rod enters different interfaces is recorded according to the different forces. Step 5: Calculate the electrolyte level data and aluminum liquid level data of the target aluminum electrolysis cell based on the time when the measuring rod enters different interfaces. Step 6: After the measuring rod touches the bottom and stays for a preset time, measure the electrolyte temperature data in the target aluminum electrolysis cell. Step 7: During the preset time period when the measuring rod touches the bottom and stays, collect torque data in real time and calculate the aluminum liquid fluctuation of the target aluminum electrolysis cell within the preset time period based on the torque data.

[0050] The beneficial effects of this disclosed embodiment are as follows: Through the solution of this disclosure, the YOLO-V5 model is used to accurately identify the "fire eye" and the coordinates of the center point of the fire eye and the vertex coordinates of the anchor frame in the pixel coordinate system are converted into coordinates in the world coordinate system based on the principle of binocular vision to control the insertion of the measuring rod. The timing of the measuring rod entering different interfaces is recorded according to the force, and the electrolyte level data and aluminum liquid level data of the target aluminum electrolytic cell are calculated accordingly. At the same time, the electrolyte temperature data in the target aluminum electrolytic cell are measured after the bottom is reached. During the preset time period when the measuring rod touches the bottom and stays, the torque data is collected in real time and the aluminum liquid fluctuation of the target aluminum electrolytic cell is calculated based on the torque data. Multiple data are measured in one insertion process, which improves the measurement accuracy and adaptability of the aluminum electrolytic cell. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A schematic flowchart illustrating a method for measuring aluminum liquid fluctuation, two levels, and electrolyte temperature in an aluminum electrolysis cell, provided in an embodiment of this disclosure.

[0053] Figure 2 This is a schematic diagram of the force on the measuring rod during the calculation process of aluminum liquid fluctuation, which is part of a method for measuring aluminum liquid fluctuation, two levels, and electrolyte temperature in an aluminum electrolysis cell provided in this embodiment of the disclosure. Detailed Implementation

[0054] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0055] The following specific examples illustrate the implementation of this disclosure. Those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0056] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0057] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this disclosure. The drawings only show the components related to this disclosure and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0058] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0059] This disclosure provides a method for measuring aluminum liquid fluctuation, two levels, and electrolyte temperature in an aluminum electrolysis cell. This method can be applied to the monitoring process of aluminum electrolysis in industrial production scenarios.

[0060] See Figure 1 This is a schematic flowchart illustrating a method for measuring aluminum melt fluctuation, two levels, and electrolyte temperature in an aluminum electrolysis cell, provided by an embodiment of this disclosure. Figure 1 As shown, the method mainly includes the following steps:

[0061] Step 1: Control the inspection equipment to take a picture of the fire eye of the target aluminum electrolytic cell, and identify the fire eye of the target aluminum electrolytic cell in the fire eye picture through the target YOLO-V5 model to obtain the coordinates of the center point of the fire eye and the vertex coordinates of the anchor box in the pixel coordinate system.

[0062] Optionally, before step 1, the method further includes:

[0063] Randomly sample video frame images from the pre-captured Huoyan video dataset and annotate them with anchor boxes;

[0064] A preset number of images are used as the training set for the initial YOLO-V5 model, and the remaining images are used as the test set for the initial YOLO-V5 model.

[0065] The initial YOLO-V5 model was trained using the k-means clustering method to obtain the target YOLO-V5 model.

[0066] In practical implementation, the inspection equipment may include a robot chassis, a screw lifting device, and a push rod detection device. The screw lifting device is fixed to the chassis and drives the push rod detection device to move up and down via a motor. The push rod detection device includes a housing, a lead screw and slider structure inside the housing driven by a motor, a force signal measuring rod and a temperature measuring rod, as well as electronic components such as a binocular camera, thermocouples, force sensors, power sensors, a microcontroller, and a signal processor required for measuring and processing signals. All measuring rods are made of steel, and the temperature measuring rod is a threaded tubular structure. Thermocouples are embedded in the measuring rods via threaded connections, with the thermocouple probes extending outside the measuring rods to ensure full contact with the electrolyte solution. The force sensors are two-dimensional force sensors to obtain the force distribution on a two-dimensional plane. All motors in the device are servo motors, with speed adjusted by controlling the pulse frequency.

[0067] Before detecting the target aluminum electrolytic cell, video frame images from a pre-captured "Fire Eye" video dataset can be randomly sampled and anchored. Then, 90% of the image data is used as the training set for the YOLO-V5 model, and the remaining 10% is used as the test set. K-means clustering is used to obtain more reasonable anchored boxes, thereby training the target YOLO-V5 model. When detecting the target aluminum electrolytic cell, the inspection equipment can be controlled to capture "Fire Eye" images of the target aluminum electrolytic cell. The target YOLO-V5 model can then identify the "Fire Eye" of the target aluminum electrolytic cell in the "Fire Eye" images, and obtain the coordinates of the center point of the "Fire Eye" and the vertex coordinates of the anchored boxes in the pixel coordinate system.

[0068] Step 2: Determine whether the opening degree of the fire eye is normal based on the vertex coordinates of the anchor frame. If yes, proceed to Step 3; otherwise, return to Step 1 and measure the next aluminum electrolysis cell.

[0069] Furthermore, step 2 specifically includes:

[0070] Step 2.1: Calculate the anchor frame size based on the vertex coordinates of the anchor frame;

[0071] Step 2.2: Determine whether the anchor frame size is greater than the threshold. If yes, the opening degree of the fire eye is normal. If no, the opening degree of the fire eye is abnormal.

[0072] In practice, the size of the anchor frame can be calculated using the vertex coordinates. The size of the anchor frame is then used to determine the degree of flame opening. This is compared to a pre-set opening threshold that meets the detection requirements to determine the flame opening status. If the anchor frame size is smaller than the required size for measurement, the flame opening is marked as abnormal and recorded, and the next aluminum electrolysis cell is inspected.

[0073] Step 3: Using the principle of binocular vision, the coordinates of the center point of the fire eye and the vertex coordinates of the anchor box in the pixel coordinate system are converted into coordinates in the world coordinate system. With the coordinates of the center point of the fire eye as the target, the measuring rod is driven to insert into the fire eye opening.

[0074] Based on the above embodiments, step 3 specifically includes:

[0075] Step 3.1, let [u, v, 1] T Let [x] be the coordinates of the center point of the fire eye in the pixel coordinate system. w y w , z w ,1] T Let the coordinates of the center point of the fire-eye system be in the world coordinate system. Then, for the left and right cameras of the inspection equipment, there are respectively...

[0076]

[0077]

[0078] Step 3.2, based on the above two equations, we obtain...

[0079]

[0080]

[0081]

[0082]

[0083] Wherein, the matrix and For camera matrix;

[0084] Step 3.3: Solve for X, Y, and Z using the least squares method to obtain the coordinates of the center point of the fire eye and the vertices of the anchor frame in the world coordinate system.

[0085] Furthermore, step 3 also includes:

[0086] The coordinates of the vertex of the anchor frame in the world coordinate system are used as the boundary for the movement of the measuring rod.

[0087] In practical implementation, the coordinates of the eye center and the anchor frame vertices in the pixel coordinate system are converted to coordinates in the world coordinate system using the principle of binocular vision. The measuring rod is inserted into the eye opening with the eye center coordinates as the target. The coordinates of the anchor frame vertices in the world coordinate system are used as the boundary to prevent the measuring rod from hitting the wall. Specifically, [u, v, 1] can be set. T Let [x] be the coordinates of the center point of the fire eye in the pixel coordinate system. w y w , z w ,1] T Let the coordinates of the center point of the fire-eye system be in the world coordinate system. Then, for the left and right cameras of the inspection equipment, there are respectively...

[0088]

[0089] Then, based on the above two equations, we obtain...

[0090]

[0091]

[0092]

[0093]

[0094] Wherein, the matrix and For camera matrix;

[0095] Then, the least squares method is used to solve for X, Y, and Z, and the coordinates of the center point of the fire eye and the vertex of the anchor frame in the world coordinate system are obtained.

[0096] Step 4: During the process of inserting the measuring rod into the fire hole, record the moment when the measuring rod enters different interfaces according to the different forces applied.

[0097] Based on the above embodiments, step 4 specifically includes:

[0098] When the measuring rod moves from the air to the electrolyte liquid surface, it is subjected to the force of the electrolyte liquid flow. The force on the measuring rod increases, and the time t1 when it moves to this interface is obtained.

[0099] When the measuring rod enters the molten aluminum from the electrolyte liquid, the electromagnetic force is significantly greater than that of the electrolyte liquid. At this time, the force on the measuring rod increases, and the time t2 when it moves to this interface is obtained.

[0100] After the measuring rod is driven to the bottom, record the moment t3 when the motor power increases.

[0101] In practice, during the insertion of the measuring rod into the flame port, as the measuring rod moves from the air to the electrolyte surface, it experiences the force of the flowing electrolyte, causing the force on the measuring rod to increase. The force sensor determines the time t1 when the measuring rod reaches this interface. When the measuring rod enters the molten aluminum from the electrolyte, the molten aluminum is in a single-phase flow region, and the electromagnetic force is significantly greater than that of the electrolyte. At this time, the force on the measuring rod increases, and the force sensor determines the time t2 when the measuring rod reaches this interface. After the measuring rod is driven to the bottom, the power meter in the control circuit detects the increase in motor power, and the time t3 is recorded.

[0102] Step 5: Calculate the electrolyte level data and aluminum liquid level data of the target aluminum electrolysis cell based on the time when the measuring rod enters different interfaces;

[0103] Based on the above embodiments, step 5 specifically includes:

[0104] Step 5.1: Calculate the displacement x1 between times t1 and t2 as the electrolyte level based on the number of pulses generated by the control element between times t1 and t2;

[0105] Step 5.2: Calculate the displacement x2 between times t2 and t3 as the aluminum liquid level based on the number of pulses generated by the control element between times t2 and t3.

[0106] Furthermore, step 5.1 specifically includes:

[0107] Assuming a fixed subdivision number, nL If the screw pitch is L and the number of pulses between times t1 and t2 is n1, then x1 = n1 / n L *L.

[0108] Furthermore, step 5.2 specifically includes:

[0109] Assuming a fixed subdivision number, n L If the screw pitch is L and the number of pulses between times t2 and t3 is n2, then x2 = n2 / n L *L.

[0110] In practical implementation, the displacement x1 between t1 and t2, and the displacement x2 between t2 and t3 are calculated by the number of pulses generated by the control element between times t1, t2, and t3 during the driving process. That is, the electrolyte level is x1, and the aluminum liquid level is x2. Assuming a fixed subdivision number, n... L One pulse counts per revolution, and the screw pitch is L. The number of pulses between times t1 and t2 is n1. The number of pulses between times t2 and t3 is n2. Therefore, x1 = n1 / n L *L, similarly, x2=n2 / n L *L. This yields the two horizontal data points for the aluminum electrolysis cell.

[0111] Step 6: After the measuring rod touches the bottom and remains there for a preset time, measure the electrolyte temperature data in the target aluminum electrolysis cell;

[0112] For example, considering that the temperature detected when the measuring rod first enters the electrolyte may have errors, the surface thermocouple can measure and output a signal to the back end after the device pauses for about one minute after touching the bottom, calculate the electrolyte temperature data of the aluminum electrolysis cell and store it in the back end.

[0113] Step 7: During the preset time period when the measuring rod touches the bottom and stays there, collect torque data in real time and calculate the fluctuation of aluminum liquid in the target aluminum electrolysis cell during the preset time period based on the torque data.

[0114] Based on the above embodiments, step 7 specifically includes:

[0115] Let the x-axis represent the direction from side A to side B of the aluminum electrolysis cell, and the y-axis be the vertical direction. Assume the force at the contact point a between the measuring rod and the slider is F. 1x and F 1y The force at point b, the contact point between the measuring rod and the tank shell, is F. 2x and F 2y The turning point of the measuring rod is point d, and the angle between the turning part of the measuring rod and the horizontal direction is θ.

[0116] Measure the center of mass c of the measuring rod and the total weight m of the measuring rod, and calculate the distance L between points a, b, c, and d accordingly.ac L bc L cd ;

[0117] Assume the force F acting on the measuring rod in the target aluminum electrolysis cell is... 3x and F 3y For the entire measuring rod, F in the y-axis direction 1y +F 2y +F 3y -mg=0, therefore F 3y The value;

[0118] For torque equilibrium at the center of mass, F 1y *L ac +F 2y *L bc +F 3y *x n =0, X1 is obtained at the peak of the fluctuation, and X2 is obtained at the trough of the fluctuation. Calculate the aluminum liquid fluctuation h = (x1 - L) / (x1 - L) cd )*tanθ-(x2-l cd )*tanθ.

[0119] In practical implementation, considering the fluctuations in the molten aluminum during the pause, the height of the molten aluminum changes, resulting in a change in the lever arm. To balance the changing torque caused by the fluctuations in the molten aluminum, the force applied to the fixed end of the measuring rod changes. The force sensor reads this force change and outputs it as an electrical signal to the back end, then... Figure 2 As shown, the x-axis is defined as the direction from side A to side B of the aluminum electrolysis cell, and the y-axis is the vertical direction. Assume the force at point a, the contact point between the measuring rod and the slider, is F. 1x and F 1y The force at point b, the contact point between the measuring rod and the tank shell, is F. 2x and F 2y The turning point of the measuring rod is point d, and the angle between the turning part of the measuring rod and the horizontal direction is θ. Before installing the measuring rod, the center of mass c and the total weight m of the measuring rod are measured in advance. Therefore, the distance L between points a, b, c, and d can be determined. ac L bc L cd The force F acting on the measuring rod in the aluminum electrolysis cell is... 3x and F 3y For the entire measuring rod, F in the y-axis direction 1y +F 2y +F 3y -mg=0, from which we can derive F 3y The value of F. For the center of mass, where the torque is balanced, F... 1y *L ac +F 2y *L bc +F 3y *xn =0. X1 is obtained at the peak of the fluctuation, and X2 is obtained at the trough of the fluctuation. Fluctuation value h = (x1 - L) cd )*tanθ-(x2-l cd )*tanθ.

[0120] The method for measuring aluminum liquid fluctuation, two levels, and electrolyte temperature in an aluminum electrolysis cell provided in this embodiment accurately identifies the "fire eye" using a YOLOv5 model and converts the coordinates of the fire eye's center point and the vertex coordinates of the anchor frame in the pixel coordinate system to coordinates in the world coordinate system to control the insertion of the measuring rod. It records the moment the measuring rod enters different interfaces based on the force applied, and calculates the electrolyte level and aluminum liquid level data of the target aluminum electrolysis cell accordingly. Simultaneously, it measures the electrolyte temperature data within the target aluminum electrolysis cell after bottoming out. During the preset time period when the measuring rod bottoms out and remains stationary, it collects torque data in real time and calculates the aluminum liquid fluctuation within the target aluminum electrolysis cell during the preset time period based on the torque data. By measuring multiple data points in a single insertion process, it improves the measurement accuracy and adaptability of the aluminum electrolysis cell.

[0121] The units described in the embodiments of this disclosure can be implemented in software or in hardware.

[0122] It should be understood that the various parts of this disclosure can be implemented in hardware, software, firmware, or a combination thereof.

[0123] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method of measuring aluminium liquid fluctuations, two levels and electrolyte temperature in an aluminium reduction cell, characterised by, The method comprises the following steps: Step 1, controlling the inspection equipment to shoot a picture of the fire hole of the target aluminum electrolysis cell, and identifying the target aluminum electrolysis cell fire hole in the fire hole picture through a target yolo-v5 model to obtain the coordinates of the fire hole center point and the coordinates of the top point of the anchor frame in the pixel coordinate system; Step 2, judging whether the opening degree of the fire hole is normal according to the coordinates of the top point of the anchor frame, if yes, entering step 3, if no, returning to step 1 to measure the next aluminum electrolysis cell; Step 3, converting the coordinates of the fire hole center point and the top point of the anchor frame in the pixel coordinate system into coordinates in the world coordinate system through the principle of binocular vision, and driving the measuring rod to insert into the fire hole opening with the fire hole center point as the target; Step 4, recording the time when the measuring rod enters different interfaces according to different forces during the driving of the measuring rod into the fire hole opening; Step 5, calculating the electrolyte level data and the aluminum liquid level data of the target aluminum electrolysis cell according to the time when the measuring rod enters different interfaces; Step 6, measuring the electrolyte temperature data in the target aluminum electrolysis cell after the measuring rod touches the bottom and stays for a preset time; Step 7, collecting torque data in real time and calculating the aluminum liquid fluctuation of the target aluminum electrolysis cell in the preset period according to the torque data during the preset period when the measuring rod touches the bottom and stays; The step 7 specifically comprises: The x axis is set as the aluminum electrolytic cell A side to the B side, the y axis is the vertical direction, the force at the contact point a between the measuring rod and the sliding block is F 1x and F 1y , the force at the contact point b between the measuring rod and the cell shell is F 2x and F 2y , the turning point of the measuring rod is point d, and the angle between the turning part of the measuring rod and the horizontal direction is ; The center of mass c of the measuring rod and the total weight m of the measuring rod are measured, and the distance L between points a, b, c, d is calculated therefrom ac , L bc , L cd ; Assume that the force on the measuring rod in the target aluminium electrolysis cell is F 3x and F 3y , in the y-axis direction for the entire measuring rod , the value of F 3y is derived; For the balance of the moment of the center of mass point, At the peak of the fluctuation, X1 is obtained, at the trough of the fluctuation, X2 is obtained, the fluctuation of the molten aluminum is calculated .

2. The method of claim 1, wherein Before the step of the step 1, the method further comprises: Randomly sampling video frame images in a pre-shot fire hole video data set and labeling anchor frames; Taking a preset number of picture data as a training set of an initial yolo-v5 model, and taking the remaining picture data as a test set of the initial yolo-v5 model; Training the initial yolo-v5 model by using a k-means clustering method to obtain a target yolo-v5 model.

3. The method of claim 1, wherein The step 2 specifically comprises: Step 2.1, calculating the anchor frame size according to the coordinates of the top point of the anchor frame; Step 2.2, judging whether the anchor frame size is greater than a threshold value, if yes, determining that the opening degree of the fire hole is normal, if no, determining that the opening degree of the fire hole is abnormal.

4. The method of claim 1, wherein The step 3 specifically comprises: Step 3.1, set [u, v, 1] T is the coordinate of the fire-eye center point in the pixel coordinate system, [x w , y w , z w , 1] T is the coordinate of the fire-eye center point in the world coordinate system, then for the left and right cameras of the inspection device respectively = ； = ； Step 3.2, converting the above two formulas to obtain + = -u1 ； + = -v1 ； + = -u2 ； + = -v2 ； wherein, where matrix and is the camera matrix; Step 3.3, solving X, Y and Z by using the least square method to obtain the coordinates of the fire hole center point and the top point of the anchor frame in the world coordinate system.

5. The method of claim 1, wherein The step 3 further comprises: Taking the coordinates of the top point of the anchor frame in the world coordinate system as the moving boundary of the measuring rod.

6. The method of claim 1, wherein The step 4 specifically comprises: When the measuring rod moves from air to electrolyte liquid surface, the measuring rod is subjected to the action force of electrolyte liquid flow, the force on the measuring rod becomes larger, and the time t1 when the measuring rod moves to this interface is obtained; When the measuring rod moves from the electrolyte liquid to the aluminum liquid, the electromagnetic force is obviously greater than the electrolyte liquid, at this time the force on the measuring rod becomes larger, and the time t2 when the measuring rod moves to this interface is obtained; After the measuring rod is driven to the bottom, the time t3 when the motor power increases is recorded.

7. The method of claim 6, wherein The step 5 specifically comprises: Step 5.1, calculating the displacement x1 between the times t1 and t2 as the electrolyte level according to the pulse number generated by the control element between the times t1 and t2. Step 5.2, calculating the displacement x2 between the instants t2 and t3 as the level of the aluminium bath as a function of the number of pulses generated by the control element between the instants t2 and t3.

8. The method of claim 7, wherein , said step 5.1 specifically comprising: Assume that a fixed number of divisions, n L is set, and that the screw pitch is L, and the number of pulses between times t1 and t2 is n1, then .

9. The method of claim 7, wherein , said step 5.2 specifically comprising: Assume that a fixed number of divisions, n L is set, and the number of pulses per revolution of the screw is L, and the number of pulses between times t2 and t3 is n2 .

Images