Displacement control system and method for anode rod of electrolytic cell

Abstract

The invention belongs to the technical field of electrolytic bath anode carbon block replacement, and provides a displacement control system and method for an electrolytic bath anode guide rod, the displacement control system comprises a data acquisition module, a feature matching module and a movement control module, the data acquisition module is configured to synchronously move along with a crown block and acquire workshop environment data and workshop point cloud data, and the feature matching module is configured to identify target features from the corrected workshop point cloud data; and the mobile control module is configured to construct an environment map, generate a plurality of paths in the environment map for the crown block to move, and calculate the path with the minimum cost in the paths as a planned path. According to the technical scheme of the invention, the target features can be identified only from the point cloud data, and the optimal path is calculated from the plurality of paths generated through path planning; the carbon block replacement efficiency is improved, and meanwhile the operation safety is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrolytic cell anode carbon block replacement, and particularly relates to a displacement control system and method for an electrolytic cell anode guide rod. BACKGROUND

[0002] In the process of aluminum electrolysis production, the anode guide rod is used to fix the anode carbon block at a specified position in the electrolytic cell to ensure the stable progress of the electrolysis reaction. The traditional displacement and positioning operation of the anode guide rod usually relies on manual cooperation with the crown block for handling and installation. The operator needs to visually judge the positional relationship between the guide rod and the fixing buckle of the electrolytic cell, and manually adjust the position of the crown block to make the guide rod inserted into the buckle to realize fixation. However, in the high temperature, high dust and strong electromagnetic interference environment of the electrolysis workshop, the accuracy of manual visual measurement is severely limited. Especially in the anode carbon block replacement or maintenance operation, due to the limited operation field of view, the buckle shielding and the change of environmental light, the alignment accuracy of the guide rod and the buckle is difficult to guarantee, and the insertion deviation or multiple adjustment is prone to occur, which not only prolongs the operation time, increases the energy consumption and labor intensity, but also may cause damage to the guide rod, the buckle and the carbon block, and even causes safety accidents.

[0003] Some existing technologies introduce a multi-sensor fusion method such as a camera and a laser range finder for auxiliary positioning, and send the positioning information to the crown block to make the carbon block in the automatic replacement operation according to the positioning information. However, the multi-sensor system has a high cost and complex installation and maintenance, and in the high temperature and high dust concentration workshop environment, the imaging quality and service life of the optical sensor are easily affected, resulting in insufficient reliability of the positioning system. In addition, the crown block can only move along a single route during movement, and cannot achieve the effect of adaptive adjustment of the path, thereby reducing the operation efficiency and increasing the danger of the operation.

[0004] Therefore, the present application is proposed. SUMMARY

[0005] In order to solve the problems that the multi-sensor fusion positioning technology is greatly affected by environmental factors, and the moving path of the crown block is single, the present application provides a displacement control system and method for an electrolytic cell anode guide rod.

[0006] The application provides a displacement control system for an anode guide rod of an electrolytic cell, which comprises a data acquisition module, a feature matching module and a movement control module.

[0007] In the embodiment of the application, the path planning module comprises an environment modeling unit, a cost evaluation unit and a path generation unit.

[0008] The environment modeling unit is configured to construct a three-dimensional space of 2*2*2 meters at the fixed buckle feature, and to scatter the three-dimensional space into regular grids with a grid interval distance of 0.02*0.02*0.02 meters, so that each grid contains (x, y, z) coordinates and an obstacle state.

[0009] The cost evaluation unit is configured to calculate the total cost f(n) of each grid by using the following formula:

[0010] f(n) = g(n) + h(n)

[0011] wherein g(n) is the cumulative cost from the starting point to the current node n, and h(n) is the heuristic cost from the current node to the target node g.

[0012] The path generation unit is configured to calculate the path with the minimum total cost in all nodes as the planning path when the crane drives the anode guide rod into the environment map.

[0013] In the embodiment of the application, the cumulative cost g(n) is calculated according to the movement distance between nodes, the cost of linear adjacent nodes is d = 1, and the cost of diagonal adjacent nodes is

[0014] The heuristic cost h(n) is calculated by using the following formula:

[0015] h(n) = w1*d(n, goal) + w2*obsCost(n)

[0016] Wherein, d(n, goal) is the three-dimensional Euclidean distance from the current node n to the target node g, and the calculation formula is:

[0017]

[0018] obsCost(n) is the obstacle risk cost of the current node, and w1 and w2 are weight coefficients for adjusting the trade-off between distance and safety.

[0019] In the embodiment of the present application, the obstacle risk cost obsCost(n) is calculated according to the shortest distance from the current node to the nearest obstacle, and when the distance is less than the safety threshold, the obstacle risk cost increases in inverse proportion to the distance; when the distance is greater than the safety threshold, the obstacle risk cost is zero.

[0020] In the embodiment of the present application, the data acquisition module includes a temperature sensor, a dust concentration sensor, an optical intensity sensor, and an interference analysis unit,

[0021] The temperature sensor is configured to collect temperature information in the workshop in real time.

[0022] The dust concentration sensor is configured to collect dust concentration information in the workshop in real time.

[0023] The interference analysis unit is configured to compare the temperature information collected by the temperature sensor with the preset temperature to calculate the refraction distortion caused by hot air disturbance, and compare the dust concentration information collected by the dust concentration sensor with the preset dust concentration to calculate the scattering loss or noise points caused by dust particles.

[0024] In the embodiment of the present application, the data acquisition module includes a laser radar and a feature correction unit,

[0025] The laser radar is configured to collect workshop point cloud data containing electrolytic cells and anode guide rods in the workshop.

[0026] The feature correction unit is configured to correct the workshop point cloud data collected by the laser radar based on the calculation result of the feature correction unit.

[0027] In the embodiment of the present application, the feature matching module includes a local recognition unit and a global recognition unit,

[0028] The local recognition unit is configured to identify the local features of the electrolytic cell in the corrected workshop point cloud data based on the pre-stored feature data of the electrolytic cell.

[0029] The global recognition unit is configured to cluster the corrected workshop point cloud data to identify the electrolytic cell features in combination with the local features of the electrolytic cell and the pre-stored feature data of the electrolytic cell.

[0030] In the embodiment of the present application, the local recognition unit is further configured to recognize the local feature of the anode guide rod in the corrected workshop point cloud data based on the pre-stored feature data of the anode guide rod, and calculate the anode guide rod feature in combination with the preset guide rod parameters.

[0031] In the embodiment of the present application, the feature matching module comprises a feature completion unit,

[0032] The local recognition unit is further configured to recognize the local feature of the fixed buckle in the corrected workshop point cloud data based on the pre-stored feature data of the fixed buckle.

[0033] The feature completion unit is further configured to complete the missing part in the local feature of the fixed buckle in combination with the pre-stored feature data of the anode guide rod feature and the fixed buckle, so as to calculate the fixed buckle feature.

[0034] To solve the problems in the prior art, the present application further provides a displacement control method for an anode guide rod of an electrolytic cell, which is applied to the displacement control system and comprises the following steps:

[0035] S1: The data acquisition module moves synchronously with the crown block and acquires the workshop environment data and the workshop point cloud data containing the electrolytic cell and the anode guide rod, and corrects the workshop point cloud data based on the workshop environment data;

[0036] S2: The feature matching module compares the corrected workshop point cloud data with the pre-stored feature data to identify the target feature;

[0037] S3: The movement control module constructs an environment map of a preset size space at the target feature, generates a plurality of movement paths reaching the target feature in the environment map, calculates the movement path with the minimum cost as the planned path of the anode guide rod when the anode guide rod is driven by the crown block to enter the environment map, and controls the crown block to drive the anode guide rod to move along the planned path.

[0038] Compared with the prior art, the present application has the following advantages:

[0039] By moving synchronously with the crown block and acquiring the workshop point cloud data and the workshop environment data through the data acquisition module, and correcting the workshop point cloud data through the workshop environment data, the influence of high temperature, high dust and other factors in the workshop on the accuracy of the workshop point cloud data is avoided, thereby improving the identification accuracy of the target feature by the subsequent feature recognition module, without the need to equip additional cameras, laser range finders and other devices to collect data, reducing the operation cost, facilitating installation and maintenance, and being not affected by the high temperature and high dust factors in the workshop.

[0040] The pre-stored feature data is called to compare the corrected workshop point cloud data with the pre-stored feature data, and then the target feature is recognized from the corrected workshop point cloud data, so that the recognition success rate of the target feature in the complex environment of the workshop and the operation continuity are improved.

[0041] By generating an environment map at the fixed buckle position and generating a plurality of moving paths in the environment map, a path with minimum cost is calculated as a planning path based on safety factors and distance factors, to control the crown to drive the guide rod to move along the planning path, so that the clamp on the anode guide rod can accurately clamp the anode carbon block, and the anode guide rod can be accurately plugged with the fixed buckle on the electrolytic cell, thereby improving the replacement efficiency and safety of the anode carbon block.

[0042] Other features and advantages of the embodiments of the present application will be described in the subsequent specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0044] Figure 1 The module architecture diagram of the shift control system provided by the embodiments of the present application;

[0045] Figure 2 The workshop point cloud data diagram collected by the shift control system provided by the embodiments of the present application;

[0046] Figure 3 The step flowchart of the shift control method provided by the embodiments of the present application.

[0047] Explanation of reference signs:

[0048] 1, shift control system; 11, data acquisition module; 12, feature matching module; 13, movement control module. DETAILED DESCRIPTION

[0049] The terms "second direction", "first direction", "third direction", "inner", "outer" and the like appearing below indicate the description of the orientation or positional relationship, and if there is no special description, it is understood as the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0050] In addition, where a limitation of "first", "second", etc. appears, such terminology is used merely as a label, and is not intended to signify relative importance or implicitly characterize one component as superior to another component, or to infer that a feature necessarily requires two or more components. A limitation of "first", "second", etc. can explicitly or implicitly include at least one of the features so limited. Where the term "plurality" appears, the general meaning is at least two, such as two, three, etc., unless otherwise specifically limited.

[0051] In this application, unless otherwise clearly indicated and limited, the terms "mounting", "connecting", "connecting", "fixing" and the like should be interpreted broadly. For example, it can be fixed connection, or detachable connection, or integrated; it can be mechanical connection, or electrical connection, it can be direct connection, or indirect connection through intermediate medium, or internal communication of two elements, or interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in this application can be understood according to the specific circumstances.

[0052] In the description of the present application, the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the different embodiments or examples described in the present application and the features of the different embodiments or examples without contradiction.

[0053] Reference Figure 1 and Figure 2The present application provides a displacement control system 1 for an anode guide rod of an electrolytic cell, which comprises a data acquisition module 11, a feature matching module 12 and a movement control module 13. The data acquisition module 11 is configured to move synchronously with the crown block and acquire workshop environment data and workshop point cloud data containing the electrolytic cell and the anode guide rod, and correct the workshop point cloud data based on the workshop environment data. The feature matching module 12 is configured to compare the corrected workshop point cloud data with pre-stored feature data to identify target features. The movement control module 13 is configured to construct an environment map of a preset size at the target features and generate a plurality of movement paths to the target features in the environment map. When the crown block drives the anode guide rod into the environment map, the movement path with the minimum cost is calculated as the planned path of the anode guide rod and the crown block is controlled to move along the planned path. The target features include anode guide rod features, electrolytic cell features and fixed buckle features around the electrolytic cell.

[0054] The data acquisition module 11 is installed on the crown block and moves synchronously with the crown block, so that the data acquisition module 11 can acquire workshop point cloud data containing the electrolytic cell and the anode guide rod during anode carbon block replacement operation, while acquiring workshop environment data. The accuracy of the workshop point cloud data is corrected by the workshop environment data to avoid the influence of high temperature and high dust in the workshop on the accuracy of the workshop point cloud data, thereby improving the recognition accuracy of the target features by the subsequent feature recognition module.

[0055] When identifying the target features, the feature matching module 12 calls the pre-stored feature data to compare the corrected workshop point cloud data with the pre-stored feature data, and then identifies the target features from the corrected workshop point cloud data, thereby improving the recognition success rate and operation continuity of the target features in the complex environment of the workshop.

[0056] Before controlling the crown block to drive the anode guide rod to move, the movement control module 13 first generates an environment map according to the identified fixed buckle position and generates a plurality of movement paths in the environment map. The movement path with the minimum cost is calculated as the planned path based on safety factors and distance factors to control the crown block to drive the guide rod along the planned path, so that the clamp on the anode guide rod can accurately clamp the anode carbon block, and the anode guide rod can accurately plug into the fixed buckle on the electrolytic cell, thereby improving the replacement efficiency and safety of the anode carbon block.

[0057] In the embodiment of the present application, the path planning module comprises an environment modeling unit, a cost evaluation unit and a path generation unit; the environment modeling unit is configured to construct a 2*2*2-meter three-dimensional space at the fixed buckle feature, and disperse the space into regular grids with a grid interval distance of 0.02*0.02*0.02 meters, so that each grid contains (x, y, z) coordinates and obstacle state; the cost evaluation unit is configured to calculate the total cost f(n) of each grid by using the following formula:

[0058] f(n) = g(n) + h(n)

[0059] wherein g(n) is the cumulative cost from the starting point to the current node n, and h(n) is the heuristic cost from the current node to the target node g; the path generation unit is configured to calculate the path with the minimum total cost among all nodes as the planning path when the crane drives the anode guide rod into the environment map.

[0060] The environment modeling unit constructs a 2*2*2-meter three-dimensional space at the position of the fixed buckle feature, and disperses the space into regular grids, so that each grid unit contains x, y, z coordinates and obstacle state, so that the crane increases the moving speed before the crane drives the anode guide rod and the anode carbon block into the three-dimensional space to improve the work efficiency, and controls the crane to reduce the moving speed when the anode guide rod enters the three-dimensional space, and moves in the three-dimensional space according to the planning path to improve the work efficiency and safety.

[0061] The cost evaluation unit calculates the cost of each passable node grid to calculate all movable paths in the three-dimensional space and the corresponding cost, so that the path generation unit takes the path with the minimum cost as the planning path, that is, when the crane drives the anode guide rod into the environment map, the path with the minimum total cost among all nodes is calculated as the planning path, so that the crane moves in a shorter moving distance and a safer moving path, thereby improving the efficiency and safety of the anode carbon block replacement work.

[0062] In the embodiment of the present application, the cumulative cost g(n) is calculated according to the moving distance between nodes, the cost of linear adjacent nodes is d = 1, and the cost of diagonal adjacent nodes is

[0063] The heuristic cost h(n) is calculated by using the following formula:

[0064] h(n) = w1*d(n, goal) + w2*obsCost(n)

[0065] wherein d(n, goal) is the three-dimensional Euclidean distance from the current node n to the target node g, and the calculation formula is:

[0066]

[0067] obsCost(n) is the obstacle risk cost of the current node, w1 and w2 are weight coefficients used to adjust the trade-off between distance and safety.

[0068] By introducing direction-related movement costs into g(n), the actual lengths of different paths can be more realistically reflected. By superimposing obstacle risk costs into h(n), path planning not only pursues the shortest distance but also actively avoids high-risk areas, improving safety.

[0069] In an embodiment of the present invention, the obstacle risk cost obsCost(n) is calculated based on the shortest distance from the current node to the nearest obstacle. When the distance is less than a safety threshold, the obstacle risk cost increases according to the inverse of the distance. When the distance is greater than the safety threshold, the obstacle risk cost is zero. That is, the closer the distance between the anode guide rod and the obstacle, the faster the risk cost increases, so that the algorithm quickly increases the path cost when approaching the obstacle, prompting avoidance. Conversely, when the anode guide rod is outside the safety range, the risk cost is reset to zero, avoiding overly conservative path planning and ensuring travel efficiency.

[0070] In an embodiment of the present invention, the data acquisition module includes a temperature sensor, a dust concentration sensor, an optical intensity sensor and an interference analysis unit. The temperature sensor is configured to: collect temperature information in the workshop in real time to obtain real-time quantitative data of thermal disturbance intensity, providing a basis for the correction of workshop point cloud data; the dust concentration sensor is configured to: collect dust concentration information in the workshop in real time to evaluate the degree of influence of particulate matter in the workshop on lidar ranging in real time; the interference analysis unit is configured to: compare the temperature information collected by the temperature sensor with the preset temperature to calculate the refraction distortion caused by hot air disturbance; compare the dust concentration information collected by the dust concentration sensor with the preset dust concentration to calculate the scattering missing or noise points caused by dust particles, improve the anti-interference ability of the workshop point cloud data, ensure the original accuracy of the workshop point cloud data, and lay the foundation for subsequent feature recognition.

[0071] In one example, the temperature information collected by the temperature sensor is T(t), the dust concentration information collected by the dust concentration sensor is D(t), and the collected light intensity is I(t). When calculating the refractive distortion, the temperature difference ΔT = T(t) - T ref To estimate the refraction angle shift Δθ caused by the change in air density, the refraction angle shift Δθ can be calculated using the following approximate advance model:

[0072] Δθ≈k T ΔT,

[0073] Among them, k Tis an empirical coefficient, and a specific value can be selected by calibration in the field.

[0074] When calculating the dust noise interference, based on D(t) and the return intensity I of the laser radar return , the point cloud loss probability p loss and the noise point ratio p nosse are estimated.

[0075]

[0076] σ D , σ I is an empirical coefficient, and a specific value can be obtained by calibration. Typically, the value range is generally 0.01-0.1.

[0077] In the embodiment of the present application, the data acquisition module includes a laser radar and a feature correction unit, the laser radar is configured to acquire workshop point cloud data containing electrolytic cells and anode guide rods in the workshop, so that the feature recognition module identifies target features of electrolytic cell features and anode guide rod features from the workshop point cloud data; the feature correction unit is configured to correct the workshop point cloud data collected by the laser radar based on the calculation result of the feature correction unit, so as to improve the identification accuracy of the target features by the feature recognition module.

[0078] In the embodiment of the present application, the feature correction unit corrects the workshop point cloud data based on the preset thermal disturbance correction coefficient and the detected workshop temperature information when correcting the workshop point cloud data, so as to compensate for the distance distortion caused by the change of air refractive index of the laser radar in the high temperature environment, and correct the noise points of the workshop point cloud data by selecting different intensity filtering algorithms based on the dust concentration. When the dust concentration is higher than the set threshold, the intensity of the filtering algorithm is increased to remove the noise points caused by the reflection of dust particles, so as to avoid too many noise points affecting the detection accuracy of the target features by the laser radar.

[0079] In the embodiment of the present application, the feature matching module includes a local recognition unit and a global recognition unit, the local recognition unit is configured to identify the local features of the electrolytic cell in the corrected workshop point cloud data based on the pre-stored feature data of the electrolytic cell; and the global recognition unit is configured to cluster the corrected workshop point cloud data by combining the local features of the electrolytic cell and the pre-stored feature data of the electrolytic cell to identify the electrolytic cell features.

[0080] The local recognition unit compares the modified plant point cloud data with the pre-stored feature data of the electrolytic cell to quickly identify the local feature of the electrolytic cell from the modified plant point cloud data, thereby improving the recognition speed of the local feature of the electrolytic cell, and then further identifies the local feature of the electrolytic cell by using the global feature recognition module, so as to cluster the point cloud corresponding to the feature of the electrolytic cell in the plant point cloud data and identify the feature of the electrolytic cell, thereby facilitating subsequent identification of the fixed buckle feature based on the feature of the electrolytic cell.

[0081] In the embodiment of the present application, the local recognition unit is further configured to identify the local feature of the anode guide rod in the modified plant point cloud data based on the pre-stored feature data of the anode guide rod, and calculate the anode guide rod feature in combination with the pre-set guide rod parameters.

[0082] In the identification of the anode guide rod feature, only the local feature recognition unit is used to identify the local feature of the anode guide rod from the plant point cloud data, and then the anode guide rod feature can be calculated based on the pre-set guide rod parameters, for example, when the cylindrical surface feature of the anode guide rod is identified, the anode guide rod feature can be calculated by using the pre-set guide rod diameter parameter and length parameter, thereby eliminating the need to use the global feature recognition unit to identify the anode guide rod feature, and improving the recognition speed and accuracy of the anode guide rod feature.

[0083] In the embodiment of the present application, the feature matching module includes a feature completion unit, and the local recognition unit is further configured to identify the local feature of the fixed buckle in the modified plant point cloud data based on the pre-stored feature data of the fixed buckle; and the feature completion unit is further configured to complete the missing part in the local feature of the fixed buckle in combination with the pre-stored feature data of the anode guide rod and the fixed buckle, so as to calculate the fixed buckle feature.

[0084] In the identification of the fixed buckle feature, only the local feature recognition unit is used to identify the local feature of the fixed buckle from the plant point cloud data based on the pre-stored feature data of the fixed buckle around the feature of the electrolytic cell, and then the feature completion unit is used to complete the actual part of the fixed buckle in combination with the anode guide rod feature and the pre-stored feature of the fixed buckle based on the local feature of the fixed buckle, thereby identifying the fixed buckle feature, and improving the recognition speed and accuracy of the fixed buckle.

[0085] Reference Figure 3 To solve the problems in the prior art, the present application further provides a displacement control method for an anode guide rod of an electrolytic cell, which is applied to the displacement control system, and the displacement control method comprises the following steps:

[0086] S1: The data acquisition module moves synchronously with the crown block and acquires plant environment data and plant point cloud data containing the electrolytic cell and the anode guide rod, and modifies the plant point cloud data based on the plant environment data;

[0087] S2: The feature matching module compares the corrected workshop point cloud data with the pre-stored feature data to identify the target feature.

[0088] S3: The movement control module constructs an environment map of a preset size space at the target feature, and generates a plurality of movement paths to the target feature in the environment map. When the overhead crane drives the anode guide rod into the environment map, the movement path with the minimum cost is calculated as the planned path of the anode guide rod, and the overhead crane is controlled to drive the anode guide rod to move along the planned path.

[0089] When the anode carbon block replacement operation is performed, the overhead crane is first controlled to move, so that the data acquisition module moves synchronously with the overhead crane, so that the data acquisition module can acquire the workshop point cloud data containing the electrolytic cell and the anode guide rod when the anode carbon block replacement operation is performed. At the same time, the workshop environment data is acquired, and the workshop point cloud data is corrected through the workshop environment data to avoid the influence of high temperature, high dust and other factors in the workshop on the accuracy of the workshop point cloud data, thereby improving the recognition accuracy of the target feature by the subsequent feature recognition module.

[0090] When the feature matching module identifies the target feature, the pre-stored feature data is called to compare the corrected workshop point cloud data with the pre-stored feature data, and then the target feature is identified from the corrected workshop point cloud data, thereby improving the recognition success rate and operation continuity of the target feature in the complex environment of the workshop.

[0091] Before the movement control module controls the overhead crane to drive the anode guide rod to move, the environment map is first generated according to the identified fixed buckle position, and a plurality of movement paths are generated in the environment map. The movement path with the minimum cost is calculated as the planned path based on safety factors and distance factors to control the overhead crane to drive the guide rod to move along the planned path, so that the clamp on the anode guide rod can accurately clamp the anode carbon block, and the anode guide rod can accurately plug with the fixed buckle on the electrolytic cell, thereby improving the replacement efficiency and safety of the anode carbon block.

[0092] The technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by the present description, as long as such a combination does not contradict.

[0093] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still adjust the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part or all of the technical features; and these adjustments or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A displacement control system for an anode guide rod of an electrolytic cell, characterized in that: The shift control system includes a data acquisition module, a feature matching module and a movement control module. The data acquisition module is configured to: move synchronously with the overhead crane and collect workshop environment data and workshop point cloud data including the electrolytic cell and the anode guide rod, and modify the workshop point cloud data based on the workshop environment data; The feature matching module is configured to: compare the corrected workshop point cloud data with pre-stored feature data to identify target features; The movement control module is configured to: construct an environment map of a preset size space at the target feature, and generate a plurality of movement paths to the target feature in the environment map; when the overhead crane drives the anode guide rod into the environment map, calculate the path with the lowest cost among the movement paths as the planned path for the anode guide rod, and control the overhead crane to drive the anode guide rod to move along the planned path; The target features include anode guide rod features, electrolytic cell features, and fixed buckle features located around the electrolytic cell.

2. The shift control system according to claim 1, characterized in that: The path planning module includes an environment modeling unit, a cost evaluation unit and a path generation unit; The environment modeling unit is configured to: construct a 2×2×2 meter three-dimensional space at the fixed snap feature, and discretize it into a regular grid with a grid spacing of 0.02×0.02×0.02 meters, so that each grid contains (x, y, z) coordinates and obstacle status; The cost evaluation unit is configured to calculate the total cost f(n) of each grid using the following formula: f(n)=g(n)+h(n) Among them, g(n) is the cumulative cost from the starting point to the current node n, and h(n) is the heuristic cost from the current node to the target node g; The path generation unit is configured to: when the overhead travelling vehicle drives the anode guide rod into the environment map, calculate the path with the minimum total cost among all nodes as the planned path.

3. The shift control system according to claim 2, characterized in that: The cumulative cost g(n) is calculated based on the moving distance between nodes. The cost of linearly adjacent nodes is d=1, and the cost of diagonally adjacent nodes is The heuristic cost h(n) is calculated using the following formula: h(n)=w1×d(n,goal)+w2×obsCost(n) Where d(n, goal) is the three-dimensional Euclidean distance from the current node n to the target node g, and the calculation formula is: obsCost(n) is the obstacle risk cost of the current node, w1 and w2 are weight coefficients used to adjust the trade-off between distance and safety.

4. The shift control system according to claim 3, characterized in that: The obstacle risk cost obsCost(n) is calculated based on the shortest distance from the current node to the nearest obstacle. When the distance is less than the safety threshold, the obstacle risk cost increases by the inverse of the distance. When the distance is greater than the safety threshold, the obstacle risk cost is zero.

5. The shift control system according to claim 1, characterized in that: The data acquisition module includes a temperature sensor, a dust concentration sensor, an optical intensity sensor and an interference analysis unit. The temperature sensor is configured to: collect temperature information in the workshop in real time; The dust concentration sensor is configured to: collect dust concentration information in the workshop in real time; The interference analysis unit is configured to: compare the temperature information collected by the temperature sensor with a preset temperature to calculate the refraction distortion caused by hot air disturbance; compare the dust concentration information collected by the dust concentration sensor with a preset dust concentration to calculate the scattering loss or noise points caused by dust particles.

6. The shift control system according to claim 5, characterized in that: The data acquisition module includes a laser radar and a feature correction unit, The laser radar is configured to: collect point cloud data of the workshop including the electrolytic cell and the anode guide rod in the workshop; The feature correction unit is configured to correct the workshop point cloud data collected by the laser radar based on the calculation result of the feature correction unit.

7. The shift control system according to claim 1, characterized in that: The feature matching module includes a local recognition unit and a global recognition unit. The local recognition unit is configured to: recognize local features of the electrolytic cell in the corrected workshop point cloud data based on pre-stored feature data of the electrolytic cell; The global recognition unit is configured to cluster the corrected workshop point cloud data in combination with the local features of the electrolytic cell and pre-stored feature data of the electrolytic cell to identify the features of the electrolytic cell.

8. The shift control system according to claim 7, characterized in that: The local recognition unit is further configured to: recognize local features of the anode guide rod in the corrected workshop point cloud data based on pre-stored feature data of the anode guide rod, and calculate the anode guide rod features in combination with preset guide rod parameters.

9. The shift control system according to claim 8, characterized in that: The feature matching module includes a feature completion unit, The local recognition unit is further configured to: recognize local features of the fixing buckle in the corrected workshop point cloud data based on pre-stored feature data of the fixing buckle; The feature completion unit is further configured to complete missing parts in the local features of the fixing buckle by combining the features of the anode guide rod and pre-stored feature data of the fixing buckle to calculate the features of the fixing buckle.

10. A method for controlling the displacement of an anode guide rod of an electrolytic cell, applied to the displacement control system according to any one of claims 1 to 9, characterized in that: The shift control method comprises: The data acquisition module moves synchronously with the overhead crane and collects workshop environmental data and workshop point cloud data including electrolytic cells and anode guide rods, and corrects the workshop point cloud data based on the workshop environmental data; The feature matching module compares the corrected workshop point cloud data with the pre-stored feature data to identify the target features; The mobile control module constructs an environmental map of a preset size space at the target feature and generates several moving paths to the target feature in the environmental map. When the overhead crane drives the anode guide rod into the environmental map, the one with the lowest cost in the moving path is calculated as the planned path for the anode guide rod and the overhead crane is controlled to drive the anode guide rod to move along the planned path.

Images