Intelligent feeding system for rare earth metal electrolysis and use method of intelligent feeding system

Abstract

The invention relates to the technical field of rare earth electrolysis, and discloses an intelligent feeding system for rare earth metal electrolysis and a using method thereof.The intelligent feeding system comprises an intelligent feeding algorithm module, a controller and a rare earth discharging machine, and the controller is used for receiving parameters output by the intelligent feeding algorithm module; the controller is further used for sending a discharging instruction to the rare earth discharging machine. And the intelligent feeding algorithm module comprises an electrolysis process data acquisition module, an electrolytic bath state evaluation module, an electrolysis parameter prediction module and an electrolysis prediction parameter optimization module. According to the method, the state of the electrolytic cell is accurately evaluated through the intelligent feeding algorithm module, the process parameters are accurately predicted on the basis of the state, finally, the electrolytic process parameters are optimized by combining the cell state judgment result and the electrolytic process parameter prediction result, and the optimal solution parameters are output. And the controller responds and issues an instruction to control the blanking rate of the rare earth blanking machine, so that the content of rare earth elements in the molten electrolyte is effectively controlled.

Description

Technical Field

[0001] The present invention relates to the technical field of rare earth electrolysis, and specifically to an intelligent feeding system for rare earth metal electrolysis and its usage method. Background Art

[0002] Rare earth is the general term for the lanthanide elements (15 metals with atomic numbers 57 - 71) in the periodic table of chemical elements and two elements, scandium and yttrium, in the same group as them, and altogether includes 17 metal components with similar chemical properties. Due to their unique optoelectromagnetic properties and catalytic activities, these elements have now become key materials in modern industry: During the process of electrolyzing praseodymium-neodymium oxide molten salt to produce metallic neodymium, there are numerous complex physical and electrochemical processes inside the electrolytic cell, mainly including oxidation-reduction and electrochemical reactions; among them, the electrolysis temperature is one of the key factors determining the performance of the electrolytic cell, and the electrolysis temperature is closely related to the feeding amount of rare earth oxides and the concentration of rare earth oxides. To effectively exert the performance of the electrolytic cell, it is not only necessary to control the feeding amount of rare earth oxides, but also to adjust the feeding rate of rare earth oxides in real time to ensure effective control of the rare earth element content in the molten electrolyte, so as to ensure that the electrolytic cell remains in a stable state.

[0003] Chinese Patent Publication No.: CN113604842A, discloses an intelligent feeding system for rare earth metal electrolysis and its usage method, which includes a material tank, a quantitative feeding tank I, a mixing tank, a vacuum feeding device, a temporary storage tank, and a quantitative feeding tank II arranged in sequence, and transparent material pipes are connected between each device; it also includes a clogging removal device and a control system; the clogging removal device includes a support plate, a track, a photoelectric sensor, and a moving vibration device; the support plate and the track are arranged along the transparent material pipe; a photoelectric sensor is arranged outside the transparent material pipe; the moving vibration device is movably arranged on the track; a stirring rod I and a stirring rod II are arranged in the mixing tank; the stirring rod I and the stirring rod II are respectively connected to a stirring motor I and a stirring motor II, and speed sensors are both provided; weight sensors are arranged in the quantitative feeding tank I and the quantitative feeding tank II.

[0004] Although the above device can achieve the function of automatically quantitative feeding during the rare earth metal electrolysis process, it cannot control the feeding rate of rare earth oxides in real time to adjust the temperature of the electrolytic cell when the temperature of the electrolytic cell rises or drops too fast. Therefore, there is an urgent need in the market for an intelligent feeding system for rare earth metal electrolysis and its usage method to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent feeding system for rare earth metal electrolysis and its usage method to solve the problem proposed in the above background art that although the current intelligent feeding system can achieve the function of automatically quantitative feeding during the rare earth metal electrolysis process, it cannot control the feeding rate of rare earth oxides in real time to adjust the temperature of the electrolytic cell when the temperature of the electrolytic cell rises or drops too fast.

[0006] To achieve the above object, the present invention provides the following technical solution: An intelligent feeding system for rare earth metal electrolysis, comprising an intelligent feeding algorithm module, a controller, and a rare earth feeder. The controller is used to receive the parameters output by the intelligent feeding algorithm module, and the controller is also used to send a feeding instruction to the rare earth feeder; The intelligent feeding algorithm module includes an electrolysis process data acquisition module, an electrolytic cell state evaluation module, an electrolysis parameter prediction module, and an electrolysis prediction parameter optimization module; Among them, the electrolysis prediction parameter optimization module is used to calculate and output the optimal feeding rate parameter with the output parameters of the electrolytic cell state evaluation module and the electrolysis parameter prediction module as constraint conditions when the electrolytic cell state is in a steady state. The electrolysis process data acquisition module is used to obtain the rare earth oxide feeding rate parameter, oxide concentration parameter, electrolytic cell voltage parameter, electrolysis temperature parameter, and electrolysis current parameter through sensors; After the intelligent feeding algorithm module obtains the rare earth electrolysis process parameters through the electrolysis process data acquisition module, under the condition of ensuring that the electrolytic cell state is stable, it calculates the optimal feeding rate parameter and transmits it to the controller, and the controller issues an instruction to adjust the feeding rate of the feeder.

[0007] As a further preferred embodiment of this technical solution: The electrolytic cell state evaluation module is used to classify and discriminate the cell state according to the process parameters obtained by the electrolysis process data acquisition module. The electrolytic cell state evaluation module includes an electrolysis process data receiving unit, an electrolytic cell state preset evaluation classification unit, and an electrolytic cell state determination output unit; Among them, the rare earth oxide feeding rate parameter, oxide concentration parameter, electrolytic cell voltage parameter, electrolysis temperature parameter, and electrolysis current parameter are classified by the electrolysis process data acquisition module as input variables of the electrolytic cell state evaluation module , and the electrolysis process data receiving unit is used to receive the input variables and transmit them to the electrolytic cell state preset evaluation classification unit. The electrolytic cell state preset evaluation classification unit classifies and determines the input variables , and the electrolytic cell state determination output unit outputs the discrimination result of the electrolytic cell state .

[0008] As a further preferred embodiment of this technical solution: The electrolysis parameter prediction module is used to predict the process parameters in the rare earth electrolysis process according to the time series characteristics of the electrolysis data. The electrolysis parameter prediction module includes an electrolysis process data receiving unit, a process data feature extraction unit, and an electrolysis data prediction unit; Among them, the rare earth oxide feeding rate parameter, the oxide concentration parameter, the electrolytic cell voltage parameter, the electrolytic temperature parameter, and the electrolytic current parameter are classified by the electrolysis process data acquisition module as input variables of the electrolysis parameter prediction module , the input variables are received by the electrolysis process data receiving unit and transmitted to the process data feature extraction unit. The process data feature extraction unit is used to extract the feature information between the process parameter data during electrolysis and retain the time series feature of the data. The electrolysis data prediction unit is used to receive the data processed by the process data feature extraction unit, and the electrolysis data prediction unit outputs the predicted electrolysis process parameters after operating with the goal of optimal current efficiency.

[0009] As a further preference of the present technical solution: the electrolysis prediction parameter optimization module is used to construct an objective optimization function based on the determination result of the electrolytic cell state evaluation module and the optimal solution of the electrolysis parameter prediction module. The electrolysis prediction parameter optimization module includes an algorithm optimization unit. The algorithm optimization unit performs an optimization search based on multiple groups of output parameters of the objective optimization function and the high mutual dependence between the output parameters, and then outputs the optimal solution process parameters; Among them, the formula of the objective optimization function is: (1) In its formula (1), is a function of the electrolysis data prediction unit, K is a constant, and C is the discrimination result output by the electrolytic cell state determination output unit , F(x) is in the interval (0, 1), Ω is the feasible solution space, and is the input variable of the electrolytic cell state evaluation module and the electrolysis parameter prediction module.

[0010] As a further preference of the present technical solution: the algorithm optimization unit outputs the optimal solution process parameters, and the controller reads the optimal solution process parameters output by the algorithm optimization unit and responds to output a mapping parameter instruction to control the feeding rate of the rare earth feeder.

[0011] As a further preference of the present technical solution: the rare earth feeder includes a weighing and feeding unit and a feeding speed regulating unit, and the weighing and feeding unit is connected to the feeding speed regulating unit.

[0012] As a further preference of the present technical solution: the feeding speed regulating unit includes a feeding chute. After the weighing and feeding unit quantitatively weighs and feeds the rare earth oxide into the feeding speed regulating unit, the rotation speed of the feeding chute in the feeding speed regulating unit controls the feeding rate of the rare earth oxide.

[0013] As a further preference of this technical solution: The weighing and feeding unit includes a quantitative feeding tank, a tank support frame, and a feeding baffle. The quantitative feeding tank is embedded in the tank support frame. At the four corners of the upper end of the quantitative feeding tank, weight sensors are connected. The weight sensors are used to weigh the rare earth oxides in the quantitative feeding tank. The weight sensors are threadedly connected to the tank support frame. A feeding slot is opened at the lower part of the quantitative feeding tank. The feeding baffle is used to control the opening and closing of the feeding slot. The tank support frame is fixedly connected to the feeding speed regulation unit.

[0014] As a further preference of this technical solution: The feeding speed regulation unit further includes a temporary storage tank, a feeding speed regulation fixing frame, and a feeding speed regulation driving member. The inside of the temporary storage tank is provided with a storage tank inner cavity. The storage tank inner cavity is a conical cylinder structure. The feeding speed regulation fixing frame is connected to the temporary storage tank. Both ends of the feeding chute are connected with connecting shafts. The connecting shafts and the feeding chute are rotatably connected in the feeding speed regulation fixing frame. The feeding chute is arranged at the lower end of the storage tank inner cavity. One end of one group of connecting shafts far away from the feeding chute is fixedly connected to the output end of the feeding speed regulation driving member. And the feeding speed regulation driving member is bolted to the feeding speed regulation fixing frame. The tank support frame is fixedly connected to the temporary storage tank.

[0015] As a further preference of this technical solution: The feeding method includes: A1: Obtain electrolysis process data, where the electrolysis process data includes rare earth oxide feeding rate parameters, oxide concentration parameters, electrolytic cell voltage parameters, electrolysis temperature parameters, and electrolysis current parameters; A2: Perform algorithm optimization based on the electrolysis process data obtained in A1, and output optimal solution parameters. The optimal solution parameters are the process parameters output after the intelligent feeding algorithm module performs optimization. A3: Respond to the optimal solution parameters, and output a mapping parameter instruction to control the rotation speed of the feeding speed regulation driving member of the rare earth feeder.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. In the present invention, the intelligent feeding algorithm module first accurately evaluates the state of the electrolytic cell, and based on this, accurately predicts the process parameters under the condition of the best current efficiency. Finally, combining the evaluation result of the cell state and the prediction result of the electrolysis process parameters, the electrolysis process parameters are optimized, and the optimal solution parameters are output. The controller responds and issues an instruction to control the feeding rate of the rare earth feeder. Thus, it overcomes the problem that the existing rare earth feeding system cannot control the feeding rate of rare earth oxide in real time when the temperature of the electrolytic cell rises or drops too fast, and ensures that the electrolytic cell remains in a stable state during the rare earth electrolysis process. At the same time, it can also achieve the goal of energy conservation and consumption reduction in the rare earth electrolysis industry, thereby improving the economic benefits of rare earth electrolysis enterprises; 2. In the present invention, the intelligent feeding algorithm module constructs an objective optimization function based on the determination result of the electrolytic cell state evaluation module and the optimal solution of the electrolysis parameter prediction module. Its algorithm optimization unit performs an optimization search on the output parameters of the objective optimization function and the high mutual dependence between the output parameters, and then outputs the optimal solution process parameters, enabling the intelligent feeding system to not only take into account the state of the electrolytic cell but also ensure the current efficiency. 3. In the present invention, the weighing and feeding unit has an automatic quantitative feeding function, and the inner cavity of the quantitative feeding tank is of a conical cylinder structure, effectively preventing the occurrence of material accumulation at the bottom of the quantitative feeding tank. The inner cavity of the storage tank in the temporary storage tank also has the same structure and the same function, and the feeding chute is arranged at the bottom end of the inner cavity of the storage tank, further ensuring the smooth feeding of rare earth oxides. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic structural diagram of an intelligent feeding system and its usage method for rare earth metal electrolysis according to the present invention; Figure 2 is a flowchart of the operation of the intelligent algorithm module in an intelligent feeding system and its usage method for rare earth metal electrolysis according to the present invention; Figure 3 is a flowchart of the operation of the electrolytic cell state evaluation module in an intelligent feeding system and its usage method for rare earth metal electrolysis according to the present invention; Figure 4 is a flowchart of the operation of the electrolysis parameter prediction module in an intelligent feeding system and its usage method for rare earth metal electrolysis according to the present invention; Figure 5 is a flowchart of the operation of the electrolysis prediction parameter optimization module in an intelligent feeding system and its usage method for rare earth metal electrolysis according to the present invention; Figure 6 is a schematic three-dimensional structure diagram of a rare earth feeder in an intelligent feeding system and its usage method for rare earth metal electrolysis according to the present invention Figure 1 ; Figure 7 is a front view of a rare earth feeder in an intelligent feeding system and its usage method for rare earth metal electrolysis according to the present invention; Figure 8 is Figure 7 a schematic cross-sectional structure diagram taken along line A-A in Figure 9 is Figure 8 a schematic enlarged structure diagram at position B in Figure 10 is a schematic three-dimensional structure diagram of a rare earth feeder in an intelligent feeding system and its usage method for rare earth metal electrolysis according to the present invention Figure 2 ; Figure 11 is Figure 10Enlarged schematic diagram at position C in the figure.

[0018] In the figure: 10, weighing and feeding unit; 101, quantitative feeding tank; 102, weight sensor; 103, tank support frame; 104, feeding baffle; 105, baffle drive; 20, feeding speed regulation unit; 201, temporary storage tank; 202, inner cavity of the storage tank; 203, feeding speed regulation fixing frame; 204, feeding chute; 205, connecting shaft; 206, feeding speed regulation drive; 30, transparent material pipe. Specific embodiments

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention.

[0021] Embodiment As mentioned in the background art, in order to control the problem of the feeding amount of rare earth oxides, in the related art, a method of providing a weight sensor in a quantitative feeding tank is adopted.

[0022] Specifically, a rare earth metal electrolysis intelligent feeding system and its use method include a material tank, a quantitative feeding tank I, a mixing tank, a vacuum feeding device, a temporary storage tank, and a quantitative feeding tank II arranged in sequence, and transparent material pipes are connected between each device; it also includes a clogging removal device and a control system; the clogging removal device includes a support plate, a track, a photoelectric sensor, and a moving vibration device; the support plate and the track are arranged along the transparent material pipe; a photoelectric sensor is arranged outside the transparent material pipe; the moving vibration device is movably arranged on the track; a stirring rod I and a stirring rod II are arranged in the mixing tank; the stirring rod I and the stirring rod II are respectively connected to a stirring motor I and a stirring motor II, and speed sensors are provided; weight sensors are provided in the quantitative feeding tank I and the quantitative feeding tank II.

[0023] However, although the above device can achieve the function of automatically quantitative feeding during the electrolysis of rare earth metals, it cannot control the feeding rate of rare earth oxides in real time when the temperature of the electrolytic cell rises or drops too fast, so it cannot effectively adjust the temperature of the electrolytic cell in real time.

[0024] To solve the problem of controlling the temperature of the electrolytic cell by controlling the feeding rate of rare earth oxides in real time when the temperature of the electrolytic cell rises or falls too fast, an intelligent feeding system for rare earth metal electrolysis and its usage method are designed in the embodiments of the present application. As Figures 1 - 11 shown, it includes an intelligent feeding algorithm module, a controller, and a rare earth feeder. The controller is used to receive the parameters output by the intelligent feeding algorithm module, and the controller is also used to send a feeding instruction to the rare earth feeder; As Figure 2 shown, the intelligent feeding algorithm module includes an electrolysis process data acquisition module, an electrolytic cell state evaluation module, an electrolysis parameter prediction module, and an electrolysis prediction parameter optimization module; As Figure 5 shown, among them, the electrolysis prediction parameter optimization module is used to calculate and output the optimal feeding rate parameter with the output parameters of the electrolytic cell state evaluation module and the electrolysis parameter prediction module as constraint conditions when the electrolytic cell state is in a steady state. The electrolysis process data acquisition module is used to obtain the rare earth oxide feeding rate parameter, oxide concentration parameter, electrolytic cell voltage parameter, electrolysis temperature parameter, and electrolysis current parameter through sensors; Optionally, the sensors include a rotational speed sensor, a high-temperature resistant probe, a temperature sensor, a voltage sensor, a current sensor, etc.

[0025] After the intelligent feeding algorithm module obtains the rare earth electrolysis process parameters through the electrolysis process data acquisition module, under the condition of ensuring that the electrolytic cell state is stable, it calculates the optimal feeding rate parameter and transmits it to the controller, and the controller issues an instruction to adjust the feeding rate of the feeder.

[0026] In this way, the intelligent feeding algorithm module can first accurately evaluate the electrolytic cell state, and based on this, accurately predict the process parameters under the condition of better current efficiency. Finally, combining the electrolytic cell state evaluation result and the electrolysis process parameter prediction result, optimize the electrolysis process parameters, output the optimal solution parameters, and the controller responds to the optimal solution parameters and issues an instruction to control the feeding rate of the rare earth feeder.

[0027] Moreover, the intelligent feeding algorithm module constructs an objective optimization function with the determination result of the electrolytic cell state evaluation module and the optimal solution of the electrolysis parameter prediction module as the goal. Its algorithm optimization unit optimizes and searches the output parameters of the objective optimization function and the high mutual dependence between the output parameters, and then outputs the optimal solution process parameters, so that the intelligent feeding system not only takes into account the electrolytic cell state but also ensures the current efficiency.

[0028] In addition, the weighing and feeding unit 10 has an automatic quantitative feeding function, and the inner cavity of the quantitative feeding tank 101 is of a conical cylinder structure, effectively preventing the occurrence of material accumulation at the bottom of the quantitative feeding tank 101. The inner cavity 202 of the storage tank in the temporary storage tank 201 also has the same structure and the same function, and the feeding chute 204 is arranged at the bottom end of the inner cavity 202 of the storage tank, further ensuring the smooth feeding of rare earth oxides.

[0029] The intelligent feeding system for rare earth metal electrolysis and its usage method in the embodiments of the present application can be applied in the process of electrolyzing molten salt of praseodymium-neodymium oxide to produce metallic neodymium. Specifically, rare earth oxides are not limited to lanthanum, cerium, praseodymium, neodymium, etc.

[0030] In this embodiment, as Figure 3 shown, the electrolytic cell state evaluation module is used to classify and discriminate the cell state according to the process parameters obtained by the electrolytic process data acquisition module. The electrolytic cell state evaluation module includes an electrolytic process data receiving unit, an electrolytic cell state preset evaluation and classification unit, and an electrolytic cell state determination and output unit. The electrolytic cell state evaluation module can accurately classify and discriminate the state of the electrolytic cell, providing accurate input variables for the next electrolysis prediction parameter optimization module; Among them, the rare earth oxide feeding rate parameter, oxide concentration parameter, electrolytic cell voltage parameter, electrolytic temperature parameter, and electrolytic current parameter are classified by the electrolytic process data acquisition module as input variables of the electrolytic cell state evaluation module. The electrolytic process data receiving unit is used to receive the input variables and transmit them to the electrolytic cell state preset evaluation and classification unit. The electrolytic cell state preset evaluation and classification unit classifies and determines the input variables, and the electrolytic cell state determination and output unit outputs the discrimination result of the electrolytic cell state.

[0031] Specifically, when the temperature of the electrolytic cell is between 1062 degrees Celsius and 1072 degrees Celsius, the state of the electrolytic cell is the most stable. When the temperature is higher than 1072 degrees Celsius, the electrolytic cell is in a hot disease state. When the temperature is lower than 1062 degrees Celsius, the electrolytic cell is in a cold disease state. As long as the electrolytic cell is in a disease state, the electrolysis efficiency is relatively poor at this time.

[0032] In this embodiment, as Figure 4 shown, the electrolysis parameter prediction module is used to predict the process parameters in the rare earth electrolysis process according to the time series characteristics of the electrolysis data. The electrolysis parameter prediction module includes an electrolytic process data receiving unit, a process data feature extraction unit, and an electrolysis data prediction unit; Among them, the rare earth oxide feeding rate parameter, oxide concentration parameter, electrolytic cell voltage parameter, electrolytic temperature parameter, and electrolytic current parameter are classified by the electrolytic process data acquisition module as input variables of the electrolysis parameter prediction module , the input variables Received by the electrolysis process data receiving unit and transmitted to the process data feature extraction unit, the process data feature extraction unit is used to extract the feature information between the process parameter data during electrolysis and retain the time series feature of the data. The electrolysis data prediction unit is used to receive the data processed by the process data feature extraction unit, and the electrolysis data prediction unit outputs the predicted electrolysis process parameters after operation with the goal of optimal current efficiency. The electrolysis parameter prediction module can also effectively predict the current efficiency during the rare earth electrolysis production process.

[0033] In this embodiment, as Figure 5 shown, the electrolysis prediction parameter optimization module is used to construct an objective optimization function based on the determination result of the electrolysis cell state evaluation module and the optimal solution of the electrolysis parameter prediction module. That is, on the basis that the electrolysis cell state is in a steady state and the current efficiency is in a high-efficiency interval, the electrolysis prediction parameter optimization module includes an algorithm optimization unit. The algorithm optimization unit performs an optimization search based on multiple sets of output parameters of the objective optimization function and the high mutual dependence between the output parameters, and then outputs the optimal solution process parameters. Among them, the formula of the objective optimization function is: (1) In its formula (1), is the function of the electrolysis data prediction unit, K is a constant, C is the discrimination result output by the electrolysis cell state determination output unit , F(x) is in the interval (0, 1), Ω is the feasible solution space, and is the input variable of the electrolysis cell state evaluation module and the electrolysis parameter prediction module.

[0034] In this embodiment, specifically: during the rare earth electrolysis process, there is a high mutual dependence between various parameters. This intelligent feeding algorithm module uses the algorithm optimization unit to determine the best process parameters and uses them as the final decision-making basis.

[0035] In this embodiment, specifically: the algorithm optimization unit outputs the optimal solution process parameters, and the controller reads the optimal solution process parameters output by the algorithm optimization unit and responds to output the mapping parameter instruction to control the feeding rate of the rare earth feeder.

[0036] In this embodiment, as Figure 6 shown, the rare earth feeder includes a weighing and feeding unit 10 and a feeding speed regulating unit 20, and the weighing and feeding unit 10 is connected to the feeding speed regulating unit 20.

[0037] In this embodiment, specifically: the blanking speed regulation unit 20 includes a blanking chute 204. After the weighing and blanking unit 10 quantitatively weighs and feeds rare earth oxides into the blanking speed regulation unit 20, the rotation speed of the blanking chute 204 in the blanking speed regulation unit 20 controls the blanking speed of the rare earth oxides.

[0038] In this embodiment, referring to Figure 8 and Figure 11 , the weighing and blanking unit 10 includes a quantitative feeding tank 101, a tank support frame 103, and a blanking baffle 104. The quantitative feeding tank 101 is embedded and connected in the tank support frame 103. Four corners at the upper end of the quantitative feeding tank 101 are each connected with a weight sensor 102. The weight sensor 102 is used to weigh the rare earth oxides in the quantitative feeding tank 101. The weight sensor 102 is threadedly connected to the tank support frame 103. A feeding slot is opened at the lower part of the quantitative feeding tank 101. The blanking baffle 104 is used to control the opening and closing of the feeding slot. The blanking baffle 104 is connected to the quantitative feeding tank 101 through a rotating shaft. The tank support frame 103 is fixedly connected to the blanking speed regulation unit 20; Referring to Figure 8 and Figure 11 , the weighing and blanking unit 10 further includes a baffle driving member 105. The baffle driving member 105 is driven by an instruction from the controller. The blanking baffle 104 functions to open and close the blanking of the rare earth oxides in the quantitative feeding tank 101; Specifically, the controller can be a programmable logic controller (PLC). It adjusts the rotation speed of the motor according to the given input signal and set parameters. Applied in this embodiment, the PLC receives the output signal from the intelligent feeding algorithm module and issues an instruction to adjust the rotation speed of the blanking speed regulation driving member 206 according to the preset parameters.

[0039] In some embodiments, referring to Figure 11 , the blanking baffle 104 is hinged to the quantitative feeding tank 101 through a hinge, which is used to realize the closing and opening functions of the blanking baffle 104 for the quantitative feeding tank 101.

[0040] In this embodiment, referring to Figure 9 , specifically: the blanking speed regulation unit 20 further includes a temporary storage tank 201, a blanking speed regulation fixing frame 203, and a blanking speed regulation driving member 206. A storage tank inner cavity 202 is opened inside the temporary storage tank 201. The storage tank inner cavity 202 is a conical cylinder structure to facilitate the smooth blanking of rare earth oxides; Referring to Figure 9 and Figure 11, the blanking speed regulation fixing frame 203 is connected to the temporary storage tank 201. Both ends of the blanking chute 204 are connected with connecting shafts 205. The connecting shafts 205 and the blanking chute 204 are both rotatably connected within the blanking speed regulation fixing frame 203. The blanking chute 204 is arranged at the lower end of the inner cavity 202 of the storage tank. One end of a group of connecting shafts 205 away from the blanking chute 204 is fixedly connected to the output end of the blanking speed regulation driving member 206, and the blanking speed regulation driving member 206 is bolted to the blanking speed regulation fixing frame 203. The tank support frame 103 is fixedly connected to the temporary storage tank 201; Reference Figure 9 , specifically, the blanking chute 204 is used for the material pushing function of rare earth oxides and can be in a groove structure or a blade structure.

[0041] In this embodiment, reference Figure 6 , the rare earth blanking machine further includes a transparent material pipe 30. One end of the transparent material pipe 30 is connected to the temporary storage tank 201, and the other end of the transparent material pipe 30 is connected to the feed inlet of the electrolytic cell.

[0042] In this embodiment, specifically: the feeding method includes: A1: Obtain electrolysis process data, which includes rare earth oxide blanking rate parameters, oxide concentration parameters, electrolytic cell voltage parameters, electrolysis temperature parameters, and electrolysis current parameters; A2: Perform algorithm optimization based on the electrolysis process data obtained in A1, and output optimal solution parameters. The optimal solution parameters are the process parameters output after the intelligent feeding algorithm module performs optimization; A3: Respond to the optimal solution parameters and output a mapping parameter instruction to control the rotation speed of the blanking speed regulation driving member 206 of the rare earth blanking machine.

[0043] To more clearly understand the working process of an intelligent feeding system for rare earth metal electrolysis and its usage method in an embodiment of the present application, refer to Figures 1 - 11 , the following describes it in detail with a specific embodiment: When running for the first time, the electrolysis process data acquisition module obtains rare earth oxide blanking rate parameters, oxide concentration parameters, electrolytic cell voltage parameters, electrolysis temperature parameters, and electrolysis current parameters through sensors. Then, the electrolysis process data receiving unit receives the obtained process parameters and cleans the process parameter data. At this time, the electrolytic cell state preset evaluation and classification unit classifies and discriminates the cleaned process parameter data, and the electrolytic cell state determination output unit outputs the discrimination result of the electrolytic cell state; The electrolysis process data acquisition module obtains the rare earth oxide feeding rate parameter, oxide concentration parameter, electrolytic cell voltage parameter, electrolysis temperature parameter, and electrolysis current parameter through sensors. Then, the electrolysis process data receiving unit receives the obtained process parameters and cleans the process parameter data. Next, the process data feature extraction unit normalizes the cleaned process parameter data, extracts the feature information between the data, and retains the time series feature of the data. Further, the electrolysis data prediction unit receives the output data from the process data feature extraction unit and outputs the corresponding process prediction data under the condition of the best current efficiency during the rare earth electrolysis production process; Then, the electrolysis prediction parameter optimization module constructs an objective optimization function, receives the discrimination result data of the electrolytic cell state output from the electrolytic cell state determination output unit and the process prediction data output from the electrolysis data prediction unit respectively. Then, the objective optimization function outputs multiple groups of process parameters under the dual constraint conditions that the electrolytic cell state evaluation result is in a steady state and the electrolysis current efficiency is optimal. Thereafter, the algorithm optimization unit outputs the optimal solution parameters Finally, the controller responds to the optimal solution parameters and sends a control instruction to the feeding speed adjustment drive 206 to adjust the rotation speed of the feeding chute 204 in real time, and controls the feeding rate of the rare earth oxide-containing material in real time to adjust the temperature of the electrolytic cell.

[0044] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent feeding system for rare earth metal electrolysis, characterized in that: include An intelligent feeding algorithm module, a controller and a rare earth blanking machine, wherein the controller is used to receive the parameters output by the intelligent feeding algorithm module, and the controller is also used to send a blanking instruction to the rare earth blanking machine; The intelligent feeding algorithm module includes an electrolysis process data acquisition module, an electrolytic cell state evaluation module, an electrolysis parameter prediction module, and an electrolysis prediction parameter optimization module; The electrolysis prediction parameter optimization module is used to calculate and output the optimal feeding rate parameters when the electrolytic cell state is in a steady state with the output parameters of the electrolytic cell state evaluation module and the electrolysis parameter prediction module as constraints, and the electrolysis process data acquisition module is used to obtain rare earth oxide feeding rate parameters, oxide concentration parameters, electrolytic cell voltage parameters, electrolysis temperature parameters and electrolysis current parameters through sensors; After the intelligent feeding algorithm module obtains the rare earth electrolysis process parameters through the electrolysis process data acquisition module, it calculates the optimal feeding rate parameters and transmits them to the controller while ensuring that the electrolytic cell state is under stable conditions, and the controller issues instructions to adjust the feeding rate of the feeding machine.

2. The intelligent feeding system for rare earth metal electrolysis according to claim 1, characterized in that: The electrolytic cell state evaluation module is used to classify and distinguish the cell state according to the process parameters obtained by the electrolysis process data acquisition module, and the electrolytic cell state evaluation module includes an electrolysis process data receiving unit, an electrolytic cell state preset evaluation classification unit and an electrolytic cell state determination output unit; Among them, the rare earth oxide feeding rate parameter, oxide concentration parameter, electrolytic cell voltage parameter, electrolytic temperature parameter and electrolytic current parameter are classified by the electrolytic process data acquisition module as input variables of the electrolytic cell state evaluation module. The electrolysis process data receiving unit is used to receive input variables and transmitted to the electrolytic cell state preset evaluation classification unit, which processes the input variable Classify and judge, the electrolytic cell state judgment output unit outputs the judgment result of the electrolytic cell state .

3. The intelligent feeding system for rare earth metal electrolysis according to claim 1, characterized in that: The electrolysis parameter prediction module is used to predict the process parameters in the rare earth electrolysis process according to the time series characteristics of the electrolysis data, and the electrolysis parameter prediction module includes an electrolysis process data receiving unit, a process data feature extraction unit and an electrolysis data prediction unit; Among them, the rare earth oxide feeding rate parameter, oxide concentration parameter, electrolytic cell voltage parameter, electrolysis temperature parameter and electrolysis current parameter are classified by the electrolysis process data acquisition module as input variables of the electrolysis parameter prediction module. , the input variable The electrolysis process data receiving unit receives and transmits the data to the process data feature extraction unit, and the process data feature extraction unit is used to extract feature information between process parameter data during the electrolysis process and retain the time series characteristics of the data. The electrolysis data prediction unit is used to receive processed data from the process data feature extraction unit, and the electrolysis data prediction unit outputs predicted electrolysis process parameters after calculation with the optimal current efficiency as the goal.

4. The intelligent feeding system for rare earth metal electrolysis according to claim 1, characterized in that: The electrolysis prediction parameter optimization module is used to construct a target optimization function according to the determination result of the electrolytic cell state evaluation module and the optimal solution of the electrolysis parameter prediction module. The electrolysis prediction parameter optimization module includes an algorithm optimization unit. The algorithm optimization unit performs an optimization search according to multiple groups of output parameters of the target optimization function and the high interdependence between the output parameters, and then outputs the optimal solution process parameters; Wherein, the formula of the objective optimization function is: （1） In formula (1), is the function of the electrolysis data prediction unit, K is a constant, and C is the judgment result output by the electrolytic cell state judgment output unit. , F(x) is in the interval (0, 1), and Ω is The feasible solution space is It is the input variable of the electrolytic cell state evaluation module and the electrolysis parameter prediction module.

5. The intelligent feeding system for rare earth metal electrolysis according to claim 4, characterized in that: The algorithm optimization unit outputs the optimal solution process parameters, and the controller reads the optimal solution process parameters output by the algorithm optimization unit and controls the feeding rate of the rare earth feeding machine in response to the output mapping parameter instruction.

6. The intelligent feeding system for rare earth metal electrolysis according to claim 1, characterized in that: The rare earth blanking machine comprises a weighing blanking unit and a blanking speed regulating unit, and the weighing blanking unit is connected to the blanking speed regulating unit.

7. The intelligent feeding system for rare earth metal electrolysis according to claim 6, characterized in that: The material unloading speed regulating unit comprises a material unloading trough. After the weighing unloading unit quantitatively weighs and feeds the rare earth oxide into the material unloading speed regulating unit, the rotation speed of the material unloading trough in the material unloading speed regulating unit controls the unloading speed of the rare earth oxide.

8. The intelligent feeding system for rare earth metal electrolysis according to claim 7, characterized in that: The weighing and unloading unit includes a quantitative feeding tank, a tank support frame and a unloading baffle. The quantitative feeding tank is embedded in the tank support frame. The four corners of the upper end of the quantitative feeding tank are connected with weight sensors. The weight sensor is used to weigh the rare earth oxides in the quantitative feeding tank. The weight sensor is threadedly connected to the tank support frame. A feeding trough is opened at the bottom of the quantitative feeding tank. The unloading baffle is used to control the opening and closing of the feeding trough. The tank support frame is fixedly connected to the unloading speed regulation unit.

9. The intelligent feeding system for rare earth metal electrolysis according to claim 8, characterized in that: The material unloading speed regulation unit also includes a temporary material storage tank, a material unloading speed regulation fixed frame and a material unloading speed regulation driving component. The interior of the temporary material storage tank is provided with a material storage tank inner cavity, and the material storage tank inner cavity is a conical cylinder structure. The material unloading speed regulation fixed frame is connected to the temporary material storage tank, and both ends of the material unloading slot are connected with connecting shafts, and the connecting shaft and the material unloading slot are rotatably connected to the material unloading speed regulation fixed frame, and the material unloading slot is arranged at the lower end of the material storage tank inner cavity, and one end of a group of the connecting shafts away from the material unloading slot is fixedly connected to the output end of the material unloading speed regulation driving component, and the material unloading speed regulation driving component is bolted to the material unloading speed regulation fixed frame, and the tank support frame is fixedly connected to the temporary material storage tank.

10. A method for using rare earth metal electrolysis feed, characterized in that: The intelligent feeding system for rare earth metal electrolysis according to any one of claims 1 to 9, wherein the feeding method comprises: A1: Obtaining electrolysis process data, wherein the electrolysis process data includes rare earth oxide feeding rate parameters, oxide concentration parameters, electrolytic cell voltage parameters, electrolysis temperature parameters, and electrolysis current parameters; A2: performing algorithm optimization according to the electrolysis process data obtained in A1, and outputting the optimal solution parameters, wherein the optimal solution parameters are the process parameters outputted by the intelligent feeding algorithm module after optimization; A3: Respond to the optimal solution parameters and output mapping parameter instructions to control the speed of the loading and unloading speed regulating drive parts of the rare earth blanking machine.

Images