Hydraulic pump control optimization method and system for rare earth magnetic material extraction

Abstract

The invention discloses a hydraulic pump control optimization method and system for rare earth magnetic material extraction, and relates to the technical field of hydraulic pump control, and the method comprises the steps: positioning a plurality of process stages with hydraulic pump services in a rare earth magnetic material extraction system, and directionally associating a plurality of hydraulic association index groups; local control strategy fitting is carried out according to the multiple hydraulic correlation index sets, and multiple initial pump control strategies are output; outputting a plurality of optimized pump control strategies through cross-stage coupling conflict arbitration; after a plurality of optimized pump control strategies are received and adopted, time sequence cooperative control is carried out on the hydraulic pump; and performing closed-loop dynamic updating on control parameters of a plurality of service hydraulic pumps in the rare earth magnetic material extraction system. The technical problem that in the prior art, the extraction stability and efficiency are low due to the fact that the control precision of a hydraulic pump is insufficient in the rare earth magnetic material extraction process is solved, and the technical effects that accurate control over the hydraulic pump in rare earth magnetic material extraction is achieved, and the stability and efficiency of the extraction process are improved are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydraulic pump control, and in particular to a hydraulic pump control optimization method and system for extracting rare earth magnetic materials. Background Art

[0002] In the extraction process of rare earth magnetic materials, hydraulic pumps, as key equipment in hydrometallurgical production lines, play a crucial role in power supply and material transport. Their operating status directly impacts extraction efficiency and product quality. Traditional hydraulic pump control methods often rely on single-parameter adjustment or centralized control, making them difficult to adapt to the differentiated requirements of different process stages. These methods are prone to cross-stage parameter interference, response lag, and excessive energy consumption, resulting in insufficient extraction process stability, resource waste, and fluctuations in product purity.

[0003] The existing technology has the technical problem of insufficient control accuracy of the hydraulic pump during the extraction of rare earth magnetic materials, resulting in low extraction stability and efficiency. Summary of the Invention

[0004] The present application provides a hydraulic pump control optimization method and system for rare earth magnetic material extraction, which is used to solve the technical problem in the prior art of insufficient hydraulic pump control accuracy during rare earth magnetic material extraction, resulting in low extraction stability and efficiency.

[0005] In view of the above problems, the present application provides a hydraulic pump control optimization method and system for rare earth magnetic material extraction.

[0006] In a first aspect of the present application, a hydraulic pump control optimization method for rare earth magnetic material extraction is provided, the method comprising: In the rare earth magnetic material extraction system, multiple process stages where hydraulic pump services are located are located, and multiple hydraulic-related indicator groups are directionally associated according to the functional attributes of the hydraulic pumps in the multiple process stages; multiple edge computing nodes independently deployed in the multiple process stages collect multiple real-time process information in real time according to the multiple hydraulic-related indicator groups in the multiple process stages to perform local control strategy fitting and output multiple initial pump control strategies; after the collaborative control center receives the multiple initial pump control strategies uploaded by the multiple edge computing nodes, it outputs multiple optimized pump control strategies through cross-stage coupling conflict arbitration; after the multiple edge computing nodes receive and adopt the multiple optimized pump control strategies issued by the collaborative control center, they implement time-series collaborative control of the multiple service hydraulic pumps in the multiple process stages; the multiple edge computing nodes perform closed-loop dynamic updates on the control parameters of the multiple service hydraulic pumps in the rare earth magnetic material extraction system according to the dynamic disturbance range of the multiple hydraulic-related indicator groups.

[0007] A second aspect of the present application provides a hydraulic pump control optimization system for rare earth magnetic material extraction, the system comprising: An indicator group association module is used to locate multiple process stages where hydraulic pump services are provided in the rare earth magnetic material extraction system, and to directionally associate multiple hydraulic-related indicator groups based on the functional properties of the hydraulic pumps in the multiple process stages; a pump control strategy output module is used to collect multiple real-time process information in real time at the multiple process stages according to the multiple hydraulic-related indicator groups by multiple edge computing nodes independently deployed in the multiple process stages, perform local control strategy fitting, and output multiple initial pump control strategies; a pump control strategy optimization module is used to output multiple optimized pump control strategies through cross-stage coupling conflict arbitration after the collaborative control center receives the multiple initial pump control strategies uploaded by the multiple edge computing nodes; a collaborative control module is used to implement time-series collaborative control of multiple service hydraulic pumps in the multiple process stages after the multiple edge computing nodes receive and adopt the multiple optimized pump control strategies issued by the collaborative control center; a closed-loop dynamic update module is used to perform closed-loop dynamic update of the control parameters of multiple service hydraulic pumps in the rare earth magnetic material extraction system according to the dynamic disturbance range of the multiple hydraulic-related indicator groups by the multiple edge computing nodes.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: In the rare earth magnetic material extraction system, multiple process stages where hydraulic pumps are located are directionally associated with multiple hydraulic-related indicator groups. Multiple edge computing nodes independently deployed in the multiple process stages collect multiple real-time process information in real time according to the multiple hydraulic-related indicator groups, perform local control strategy fitting, and output multiple initial pump control strategies. After receiving the multiple initial pump control strategies uploaded by the multiple edge computing nodes, the collaborative control center outputs multiple optimized pump control strategies. After receiving and adopting the multiple optimized pump control strategies issued by the collaborative control center, time-series collaborative control is implemented for multiple service hydraulic pumps in the multiple process stages. Based on the dynamic disturbance range of the multiple hydraulic-related indicator groups, closed-loop dynamic updates are performed on the control parameters of the multiple service hydraulic pumps in the rare earth magnetic material extraction system. This achieves the technical effect of achieving precise control of the hydraulic pumps in rare earth magnetic material extraction and improving the stability and efficiency of the extraction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flow chart of a hydraulic pump control optimization method for rare earth magnetic material extraction provided in an embodiment of the present application.

[0011] Figure 2 Schematic diagram of the structure of the hydraulic pump control optimization system for rare earth magnetic material extraction provided in an embodiment of the present application.

[0012] Description of the accompanying drawings: indicator group association module 10, pump control strategy output module 20, pump control strategy optimization module 30, collaborative control module 40, closed-loop dynamic update module 50. DETAILED DESCRIPTION

[0013] The present application provides a hydraulic pump control optimization method and system for rare earth magnetic material extraction, which is used to solve the technical problem in the prior art of insufficient hydraulic pump control accuracy during rare earth magnetic material extraction, resulting in low extraction stability and efficiency.

[0014] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0015] Example 1, as Figure 1 As shown, the present application provides a hydraulic pump control optimization method for rare earth magnetic material extraction, the method comprising: Step S100: locating multiple process stages served by hydraulic pumps in a rare earth magnetic material extraction system, and directionally associating multiple hydraulic-related indicator groups according to functional attributes of the hydraulic pumps in the multiple process stages.

[0016] Specifically, in the rare earth magnetic material extraction system as an entity, the system includes multiple process stages such as the slurry conveying stage, the filter press separation stage, the solvent extraction stage and the stripping and washing stage, from which the above-mentioned stages where hydraulic pumps provide process auxiliary services are located; then, based on the functional attributes of the hydraulic pumps in each process stage, such as the hydraulic pump in the slurry conveying stage is responsible for the material conveying power supply, the filter press separation stage is responsible for pressure regulation to achieve solid-liquid separation, the solvent extraction stage requires precise control of flow to ensure extraction efficiency, the stripping and washing stage requires stable pressure to ensure washing effect, etc., respectively, the hydraulic-related indicator groups that match each functional attribute are directionally associated, so that the hydraulic-related indicator groups of each process stage can accurately reflect the core operating parameters and process requirements of the hydraulic pump in that stage.

[0017] Step S200: The multiple edge computing nodes independently deployed in the multiple process stages collect multiple real-time process information in real time according to the multiple hydraulic-related indicator groups in the multiple process stages to perform local control strategy fitting and output multiple initial pump control strategies.

[0018] Specifically, in multiple process stages such as the slurry transportation stage, filtration separation stage, solvent extraction stage, and stripping and washing stage, corresponding edge computing nodes are independently deployed in each stage. Each edge computing node is based on the hydraulic-related indicator group associated with the stage. Through the pre-deployed dedicated sensing topology, such as the dedicated topology formed by local binding of the upload authority of the sensor network of a certain process stage, real-time process information including physical quantity layer information, chemical quantity layer information, and time series layer information is collected in real time in the corresponding process stage; then, hydraulic process auxiliary deviation identification is performed based on this information, and the information is analyzed to obtain data of various dimensions. The static deviation is calculated by comparing it with the preset multi-layer process set value, and the confidence is weighted by combining the dynamic trend feature analysis and the sensor accuracy attribute to output the hydraulic auxiliary deviation vector. Then, based on the deviation vector, a pump control correction model architecture including a static deviation layer, a dynamic feature layer, and a fusion output layer is constructed. The deviation and dynamic characteristics are processed separately by each layer and cross-coupling is performed to complete the local control strategy fitting, and finally the initial pump control strategy corresponding to each stage is output.

[0019] Step S300: After receiving the multiple initial pump control strategies uploaded by the multiple edge computing nodes, the collaborative control center outputs multiple optimized pump control strategies through cross-stage coupling conflict arbitration.

[0020] Specifically, after receiving multiple initial pump control strategies uploaded by independently deployed edge computing nodes in multiple process stages such as the slurry conveying stage, filtration separation stage, solvent extraction stage, and stripping and washing stage, the collaborative control center first performs adjacent strategy conflict detection on these initial pump control strategies, identifies and outputs a material balance conflict set, including: material accumulation or shortage caused by flow mismatch in each stage; energy consumption accumulation conflict set, including: excessive energy consumption caused by simultaneous high-pressure operation of multiple stages; and process interference conflict set, including: deviation in extraction effect caused by the mutual influence of pressure fluctuations between stages; then, based on the material balance conflict set, dynamic flow calibration is performed according to process priority to output a flow calibration strategy, and based on the energy consumption accumulation conflict set, time planning for time-sharing and peak-shifting pressurization is performed to output a timing avoidance strategy, and for the process interference conflict set, a transition buffer neutralization instruction is inserted to output a chemical isolation strategy; finally, the flow calibration strategy, timing avoidance strategy, and chemical isolation strategy are cross-mutually excluded to eliminate contradictions and duplications between strategies, and finally, multiple optimized pump control strategies adapted to each process stage are output.

[0021] Step S400: After receiving and adopting the multiple optimized pump control strategies issued by the collaborative control center, the multiple edge computing nodes implement time-series collaborative control on the multiple service hydraulic pumps in the multiple process stages.

[0022] Specifically, the edge computing nodes independently deployed in multiple process stages, such as the slurry conveying stage, filtration separation stage, solvent extraction stage, and stripping and washing stage, respectively receive the optimized pump control strategies adapted to their respective stages issued by the collaborative control center. Based on these strategies, they implement timing collaborative control of the service hydraulic pumps in each stage. By integrating and optimizing the reliable pressure control instructions, fatigue adaptive flow modulation, and dead time compression parameters in the pump control strategy, they coordinate the operation timing of the hydraulic pumps in different process stages. For example, after the material conveying is completed in the slurry conveying stage, the hydraulic pump in the filtration separation stage starts pressurization according to the preset timing. The hydraulic pumps in the solvent extraction stage and the stripping and washing stage also operate sequentially or collaboratively according to the timing plan to ensure that the operation rhythm of the hydraulic pumps in each stage matches the process connection requirements, reduce cross-stage interference, and improve the overall extraction efficiency.

[0023] Step S500: The plurality of edge computing nodes perform closed-loop dynamic updates on control parameters of a plurality of service hydraulic pumps in the rare earth magnetic material extraction system according to the dynamic disturbance ranges of the plurality of hydraulic-related indicator groups.

[0024] Specifically, the edge computing nodes in multiple process stages, such as the slurry transportation stage, filtration separation stage, solvent extraction stage, and stripping and washing stage, continuously monitor their corresponding hydraulic-related indicator groups, and capture the dynamic disturbance range of these indicators during operation in real time; based on this disturbance range, combined with the control requirements of the hydraulic pumps in each stage, the control parameters of each service hydraulic pump in the rare earth magnetic material extraction system, such as pressure, flow, response delay compensation, etc., are dynamically updated in a closed loop. Through continuous feedback adjustment, the pump control parameters are always adapted to the real-time process information, ensuring that the hydraulic pump can still operate stably when the indicators fluctuate, maintaining efficient coordination of each process stage, and thus ensuring the continuity and reliability of the rare earth magnetic material extraction process.

[0025] In one possible implementation, step S100 further includes: The multiple process stages include a slurry conveying stage, a filter pressing separation stage, a solvent extraction stage and a stripping and washing stage.

[0026] Specifically, the multiple process stages include slurry transportation, filter press separation, solvent extraction, and stripping and washing. The slurry transportation stage primarily uses a hydraulic pump to transport rare earth slurry from storage equipment to subsequent processing stages. The stability of the transport flow and pressure must be maintained to prevent slurry sedimentation or pipeline blockage. During the filter press separation stage, the hydraulic pump provides pressure to pass the slurry through the filter medium for solid-liquid separation. The pressure level and hold time must be precisely controlled to improve separation efficiency. The solvent extraction stage is a key step in rare earth separation and purification. The hydraulic pump is responsible for transporting the aqueous slurry and organic solvent in proportion to the extraction equipment. The accuracy of its flow control directly affects the extraction balance and separation effect. During the stripping and washing stage, the hydraulic pump delivers stripping agents and washing liquids to elute and purify the target rare earth elements in the loaded organic phase. Flow and pressure parameters must be coordinated to ensure stripping efficiency and product purity.

[0027] In one possible implementation, step S300 further includes: Step S310: performing adjacent strategy conflict detection on the multiple initial pump control strategies, and outputting a material balance conflict set, an energy consumption accumulation conflict set, and a process interference conflict set.

[0028] Step S320: Performing process priority dynamic flow calibration based on the material balance conflict set, and outputting a flow calibration strategy.

[0029] Step S330: performing time-sharing peak-shifting pressure sequence planning based on the energy consumption cumulative conflict set, and outputting a sequence avoidance strategy.

[0030] Step S340: performing transition buffer neutralization and instruction insertion for the process interference conflict set, and outputting a chemical isolation strategy.

[0031] Step S350: performing cross-exclusivity elimination on the flow calibration strategy, the timing avoidance strategy, and the chemical isolation strategy, and outputting the multiple optimized pump control strategies.

[0032] Specifically, the collaborative control center constructs a conflict detection matrix to compare and analyze the parameters of adjacent process stages in multiple initial pump control strategies. For material balance conflicts, it extracts the flow setting value and material transfer rate in each strategy, calculates the input-output difference of adjacent stages, and includes the difference in the material balance conflict set when it exceeds the preset balance threshold. For energy consumption accumulation conflicts, it counts the pressurization power and duration of each strategy, and superimposes the energy consumption data of adjacent stages. If the total energy consumption exceeds the energy consumption upper limit of the stage, it will be included in the energy consumption accumulation conflict set. For process interference conflicts, it analyzes the pressure fluctuation range and chemical reagent delivery rhythm of adjacent strategies. When there is a cross-influence of pressure fluctuations or a reagent delivery timing conflict, it will be included in the process interference conflict set, and finally output three types of conflict sets.

[0033] Based on the material accumulation or shortage problem caused by flow mismatch in adjacent process stages in the material balance conflict set, the process priority is first determined according to the core role of each process stage in the rare earth magnetic material extraction process. For example, the solvent extraction stage that directly affects the extraction purity has a higher priority than the slurry transportation stage. Then, the flow parameters involved in the conflict set are dynamically calibrated based on the priority. By calculating the difference in material demand between adjacent stages, the hydraulic pump flow in the low-priority stage is adaptively adjusted to match the material processing capacity of the high-priority stage. At the same time, the flow deviation is dynamically corrected in combination with data such as material concentration and transmission rate in real-time process information. Finally, a flow calibration strategy is output to ensure the balance of material input and output in each stage.

[0034] Based on the problem of excessive energy consumption due to simultaneous high-pressure operation of multiple adjacent process stages in the energy consumption accumulation conflict set, the parameters such as hydraulic pump pressurization power, pressurization time and operating time period corresponding to each initial pump control strategy in the conflict set are first analyzed. Then, combined with the necessity of pressurization and the energy consumption sensitivity of each process stage, time-sharing and peak-shifting pressurization timing planning is carried out. By adjusting the execution time of high-energy pressurization operations, the high-pressure operation time periods of different process stages are staggered. For example, the high-pressure conveying in the slurry conveying stage is arranged during the low-pressure holding period of the filter press separation stage to avoid concentrated energy consumption accumulation. At the same time, the pressurization timing interval threshold is set according to the process requirements of each stage to ensure that the peak-shifting arrangement does not affect the process continuity. Finally, a timing avoidance strategy is output to coordinate the pressurization timing of each stage to reduce the overall energy consumption.

[0035] In order to solve the mutual interference problem caused by pressure fluctuations, flow mutations, etc. in adjacent process stages where process interference conflicts are concentrated, the process connection nodes involved in the conflicts are first identified, and transition buffer zones are set at these nodes to clarify parameters such as the pressure range, flow fluctuation threshold and duration of the buffer zones; then, based on the buffer zone parameters, neutralization instructions are inserted into the relevant initial pump control strategies. For example, when transitioning from the slurry conveying stage to the filter press separation stage, pressure buffer adjustment instructions are inserted to smooth pressure fluctuations, and flow gradient instructions are inserted at the connection between the solvent extraction stage and the stripping and washing stage to reduce the impact of reagent delivery; by inserting these neutralization instructions, the process interferences of adjacent stages are isolated, and the adverse effects of parameter fluctuations on the chemical reaction conditions and separation effects of subsequent stages are avoided, and finally a chemical isolation strategy that can eliminate process interferences between stages is output.

[0036] The flow calibration strategy, timing avoidance strategy and chemical isolation strategy are cross-exclusive and eliminated. First, the three strategies are compared one by one in terms of parameter setting, timing arrangement, and process connection requirements to identify the existing contradictions. For example, the flow calibration strategy requires an increase in flow during a certain period, while the timing avoidance strategy limits the pressurization power during this period, resulting in the inability to increase flow, or the transition buffer period of the chemical isolation strategy conflicts with the dynamic adjustment period of the flow calibration. In response to these contradictions, priority trade-offs and parameter adjustments are made based on the core requirements of each process stage of rare earth magnetic material extraction to eliminate the mutual exclusivity between the strategies and ensure that the three strategies can adapt to each other and have no conflicts when working together. Finally, the resolved strategies are integrated to form and output multiple optimized pump control strategies that are adapted to each process stage such as slurry transportation, filter press separation, solvent extraction and stripping washing.

[0037] In one possible implementation, step S200 further includes: Step S210: performing local binding of upload permissions of the first sensor network pre-deployed in the first process stage according to the first hydraulic pressure-related indicator group to obtain a first dedicated sensor topology.

[0038] Step S220: The first edge computing node receives the first real-time process information uploaded by the first dedicated sensing topology.

[0039] Step S230: performing hydraulic process assistance deviation identification based on the first real-time process information, and outputting a first hydraulic assistance deviation vector.

[0040] Step S240: performing pump control parameter correction modeling according to the first hydraulic assistance deviation vector, and outputting a first initial pump control strategy.

[0041] Specifically, for the first process stage, according to the first hydraulic-related indicator group corresponding to this stage, covering indicators related to the operation of the hydraulic pump such as pressure, flow, and chemical reagent concentration, the upload authority of the pre-deployed first sensor network is locally bound, and the data upload range of the sensor network is limited to the local range of this process stage, ensuring that the information collected by the sensor is only transmitted in a direction to the edge computing node responsible for this stage, avoiding cross-stage data interference, and finally forming a first dedicated sensing topology dedicated to the first process stage.

[0042] The first edge computing node deployed in the first process stage receives the first real-time process information uploaded by the first dedicated sensor topology through a preset communication protocol. This information includes the physical quantity layer information of this stage: such as the pressure and flow data of the hydraulic pump; the chemical quantity layer information: such as the concentration and pH value of the extract; and the timing layer information: such as the time series of changes in each parameter, providing raw data support for subsequent local control strategy fitting.

[0043] When hydraulic process auxiliary deviation identification is performed based on the first real-time process information, the information is first parsed to extract the first physical quantity layer information, the first chemical quantity layer information and the first time series layer information; then the predefined first process stage multi-layer process setting value is called, and the above-mentioned extracted layers of information are mapped and compared with the corresponding setting values, and the first pressure dimension deviation, the first chemical dimension deviation and the first time series dimension deviation are obtained by calculating the difference values; at the same time, the dynamic trend feature analysis of the first physical quantity layer information is carried out to output the first dynamic trend feature group; finally, combined with the sensing accuracy attribute of the first dedicated sensing topology, the first dynamic trend feature group, the first pressure dimension deviation, the first chemical dimension deviation and the first time series dimension deviation are confidence-weighted, and the first hydraulic auxiliary deviation vector is comprehensively generated and output.

[0044] When performing pump control parameter correction modeling based on the first hydraulic auxiliary deviation vector, a pump control correction model architecture is first constructed, which includes a static deviation layer, a dynamic feature layer and a fusion output layer, wherein the static deviation layer and the dynamic feature layer are in parallel, and the output ends of both are connected to the fusion output layer; in the static deviation layer, the first pressure dimension deviation, the first chemical dimension deviation and the first timing dimension deviation are corrected and compensated in parallel, and the first basic pressure correction item, the first flow correction item and the first response delay compensation amount are output respectively; in the dynamic feature layer, multimodal compensation modeling is performed on the first dynamic trend feature group, and the first dynamic compensation instruction set including the first pressure shock pre-compensation pulse, the first PID integral adjustment amount, the first reverse damping control item and the first mechanical fatigue suppression coefficient is output; in the fusion output layer, the cross-coupling of the first dynamic compensation instruction set with the first basic pressure correction item, the first flow correction item and the first response delay compensation amount is executed, and the first initial pump control strategy is output after confidence weighting.

[0045] In one possible implementation, step S230 further includes: Step S231: parsing the first real-time process information to obtain first physical quantity layer information, first chemical quantity layer information and first timing layer information.

[0046] Step S232: predefine multi-layer process setting values ​​for the first process stage.

[0047] Step S233: Use the multi-layer process setting value mapping to compare the first physical quantity layer information, the first chemical quantity layer information and the first timing layer information, perform static deviation calculation, and output the first pressure dimension deviation, the first chemical dimension deviation and the first timing dimension deviation.

[0048] Step S234: performing dynamic trend feature analysis on the first physical quantity layer information, and outputting a first dynamic trend feature group.

[0049] Step S235: Based on the sensing accuracy attribute of the first dedicated sensing topology, confidence weighting of the first dynamic trend feature group, the first pressure dimension deviation, the first chemical dimension deviation and the first timing dimension deviation is performed, and the first hydraulic auxiliary deviation vector is output.

[0050] Specifically, the first real-time process information is analyzed, and the first physical quantity layer information reflecting the physical parameters of the hydraulic pump operation, such as pressure, flow, flow velocity, etc., the first chemical quantity layer information reflecting the chemical properties of the extraction system, such as solution concentration, pH value, ion content, etc., and the first time series layer information recording the changes of various parameters over time, such as the pressure fluctuation sequence over time, the time nodes of flow change, etc. are separated from the collected raw data.

[0051] According to the process requirements of the first process stage and the hydraulic pump operation standards, multi-layer process setting values ​​are predefined. The setting values ​​cover physical quantity standards such as pressure threshold and flow range corresponding to the first physical quantity layer information, chemical quantity standards such as solution concentration range and pH value allowable range corresponding to the first chemical quantity layer information, and timing standards such as parameter change cycle and response time limit corresponding to the timing layer information.

[0052] Using predefined multi-layer process setting values, they are mapped and compared with the first physical quantity layer information, the first chemical quantity layer information and the first timing layer information obtained by analysis. The physical quantity layer setting values ​​are compared one by one with the actual pressure and flow data in the first physical quantity layer information, and the difference between the actual value and the setting value is calculated to obtain the first pressure dimension deviation; the chemical quantity layer setting values ​​are matched and compared with the actual concentration, pH value and other data in the first chemical quantity layer information, and the first chemical dimension deviation is output through the deviation calculation; the timing layer setting values ​​are compared with the actual time series data in the first timing layer information, and the first timing dimension deviation is calculated based on the time difference or period deviation, and finally these three types of static deviations are output.

[0053] When performing dynamic trend feature analysis on the first physical quantity layer information, first perform rolling time series segmentation on the information based on the preset time window to obtain a continuous data block sequence; then extract the flow and pressure derivative feature items of the continuous data block sequence to obtain the first dynamic derivative feature set; then quantify the out-of-limit fluctuation state based on the continuous data block, and output the first out-of-limit fluctuation duration ratio and the first pressure oscillation spectrum intensity; then traverse the continuous data block to obtain the first cumulative number of pressurization cycles, and this number is associated with the first flow trend direction mark; finally, encapsulate the first dynamic derivative feature set, the first out-of-limit fluctuation duration ratio, the first pressure oscillation spectrum intensity, the first cumulative number of pressurization cycles and the first flow trend direction mark, and output the first dynamic trend feature group.

[0054] According to the sensing accuracy properties of the first dedicated sensing topology, including the accuracy level, data acquisition error range and signal stability parameters of each sensor in the topology, the confidence weights corresponding to the first dynamic trend feature group, the first pressure dimension deviation, the first chemical dimension deviation and the first timing dimension deviation are determined. For example, the features or deviations corresponding to the data collected by sensors with higher accuracy and smaller errors are assigned higher weights; then, these features and deviations are multiplied by their respective weights, and the calculation results are integrated to finally output the first hydraulic auxiliary deviation vector that comprehensively reflects the deviations and dynamic trends of each dimension.

[0055] In one possible implementation, step S240 further includes: Step S241: constructing a pump-controlled correction model architecture, wherein the pump-controlled correction model architecture includes a static bias layer, a dynamic feature layer and a fusion output layer, the static bias layer and the dynamic feature layer are connected in parallel, and the output end is connected to the fusion output layer.

[0056] Step S242: performing parallel correction compensation of the first pressure dimension deviation, the first chemical dimension deviation, and the first timing dimension deviation in the static deviation layer, and outputting a first basic pressure correction term, a first flow correction term, and a first response delay compensation amount.

[0057] Step S243: Perform multimodal compensation modeling of the first dynamic trend feature group in the dynamic feature layer, and output a first dynamic compensation instruction set, wherein the first dynamic compensation instruction set includes a first pressure shock pre-compensation pulse, a first PID integral adjustment amount, a first reverse damping control item and a first mechanical fatigue suppression coefficient.

[0058] Step S244: Execute the cross-coupling of the first dynamic compensation instruction set, the first basic pressure correction term, the first flow correction term and the first response delay compensation amount in the fusion output layer, and output the first initial pump control strategy.

[0059] Specifically, a pump control correction model architecture suitable for the first process stage hydraulic pump control was constructed. This architecture clearly includes three core layers: the static deviation layer, the dynamic feature layer, and the fusion output layer. The static deviation layer and the dynamic feature layer are set up in parallel. As parallel input processing layers of the model, they can independently process the input static deviation information and dynamic trend characteristics. At the same time, the output ends of the static deviation layer and the dynamic feature layer are both connected to the fusion output layer, so that the processing results of the two layers can be aggregated to the fusion output layer for comprehensive calculations, forming a model structure with two-level parallel processing and single-level fusion output, providing architectural support for the precise correction of subsequent pump control parameters.

[0060] In the static deviation layer, for the first pressure dimension deviation, the proportional-integral correction algorithm is used. The deviation value is multiplied by the preset pressure adjustment coefficient and then the integral compensation is superimposed to calculate the first basic pressure correction item; for the first chemical dimension deviation, by querying the chemical parameter-flow association mapping table, the table pre-stores the flow correction coefficients corresponding to different chemical deviations. The deviation value is substituted into the table to match the corresponding coefficient, and the first flow correction item is output after multiplying it with the baseline flow; for the first timing dimension deviation, based on the timing synchronization error formula: error value = actual response time - set response time, combined with the delay compensation factor, the first response delay compensation amount is calculated. The three correction operations are synchronously executed through the parallel computing module and the results are output.

[0061] Based on the pressure change rate in the first dynamic trend feature group, by matching the preset pressure shock compensation pulse parameter library, the first pressure shock pre-compensation pulse for offsetting the pressure mutation in advance is determined and output; then, according to the continuous proportion of the first over-limit fluctuation, the integral time constant of the flow PID controller is adjusted according to the preset rules, and the first PID integral adjustment amount that can suppress the flow fluctuation is output; then, based on the intensity of the first pressure oscillation spectrum, the reverse damping control parameter library is queried, and the first reverse damping control item that can weaken the pressure oscillation is matched and output; finally, combined with the cumulative number of the first pressurization cycle and the first flow trend direction mark, the first mechanical fatigue suppression coefficient for reducing equipment loss is calculated and output through the fatigue strength attenuation model. These four instructions together constitute the first dynamic compensation instruction set.

[0062] In the fusion output layer, a cross-coupling operation is performed on the first dynamic compensation instruction set, the first basic pressure correction item, the first flow correction item and the first response delay compensation amount. By linearly superimposing the first basic pressure correction item and the first pressure shock pre-compensation pulse, an initial anti-disturbance pressure instruction is generated, which is then injected into the first reverse damping control item to output a reliable pressure control instruction; a product operation is performed on the first flow correction item and the first mechanical fatigue suppression coefficient to obtain a reference fatigue adaptive flow, and then the first PID integral adjustment amount is applied to dynamically modulate the response rate of the flow, and the modulated fatigue adaptive flow is output; the timing components of the first response delay compensation amount and the first PID integral adjustment amount are integrated to output the dead time compression parameter; finally, the reliable pressure control instruction, the modulated fatigue adaptive flow and the dead time compression parameter are confidence-weighted, and the first initial pump control strategy is comprehensively output.

[0063] In one possible implementation, step S234 further includes: Step S2341: performing rolling time sequence segmentation on the first physical quantity layer information based on a preset time window to obtain a continuous data block sequence.

[0064] Step S2342: extracting flow and pressure derivative feature items from the continuous data block sequence to obtain a first dynamic derivative feature set.

[0065] Step S2343: quantifying the excessive fluctuation state based on the continuous data blocks, and outputting a first excessive fluctuation duration ratio and a first pressure oscillation spectrum intensity.

[0066] Step S2344: traverse the continuous data blocks to obtain the first cumulative number of pressurization cycles, wherein the first cumulative number of pressurization cycles is associated with a first flow trend direction mark.

[0067] Step S2345: Encapsulate the first dynamic derivative feature set, the first over-limit fluctuation duration ratio, the first pressure oscillation spectrum intensity, the first cumulative number of pressurization cycles and the first flow rate trend direction mark, and output the first dynamic trend feature group.

[0068] Specifically, rolling time series segmentation is performed on the first physical quantity layer information based on a preset time window (such as 10 seconds / window). That is, starting from the initial moment, after intercepting the data segment according to the length of the time window, the window is slid backward with a fixed step size (such as 5 seconds), and the interception is continued until all the information is covered. Finally, a continuous and partially overlapping sequence of continuous data blocks is obtained, thereby realizing the time series segmentation of the physical quantity information.

[0069] For the continuous data block sequence obtained by rolling time series segmentation of the first physical quantity layer information, the first-order derivative and second-order derivative of the flow and pressure parameters in each data block over time are calculated one by one, and the characteristic items such as the change rate of the flow-pressure ratio and the partial derivative of pressure with respect to flow are extracted. These characteristic items reflecting the dynamic change rate of the parameters are integrated and summarized to form the first dynamic derivative feature set that can reflect the dynamic response characteristics of the hydraulic system.

[0070] When quantifying the over-limit fluctuation state based on continuous data blocks, first set a normal fluctuation threshold range for the pressure, flow and other physical quantity parameters in each continuous data block, and the threshold is predefined based on the process requirements of the first process stage; then traverse each data block, count the duration of the physical quantity parameters exceeding the preset threshold, and take the ratio of this time to the total length of the data block as the single block over-limit ratio, and then take the average of the single block over-limit ratio of all data blocks to obtain the first over-limit fluctuation duration ratio; at the same time, perform spectral analysis on the pressure fluctuation signal in each data block, such as Fourier transform, to extract the energy intensity corresponding to the main oscillation frequency in the spectrum, and combine the analysis results of all data blocks to output the first pressure oscillation spectrum intensity that can reflect the severity of the pressure fluctuation.

[0071] Traverse each data block in the continuous data block sequence, identify the pressurization cycle process of the hydraulic pump in each data block, and when the pressure parameter in the data block rises from below the preset pressurization threshold to above the threshold, and then drops below the threshold, it is determined that a pressurization cycle is completed, and the number of cycles is accumulated and counted to finally obtain the first cumulative number of pressurization cycles; at the same time, when recording each pressurization cycle, the change direction of the flow parameter in the corresponding cycle process is combined, such as if the flow increases with the increase of pressure, it is marked as positive, and if it decreases with the increase of pressure, it is marked as reverse, and the first cumulative number of pressurization cycles is associated with the corresponding first flow trend direction mark, so as to realize the binding of the number of cycles and the flow change trend.

[0072] The first dynamic derivative feature set, the first over-limit fluctuation duration ratio, the first pressure oscillation spectrum intensity, the first cumulative number of pressurization cycles, and the associated first flow trend direction mark obtained by extraction are structured and packaged. According to the preset data format, these feature information are integrated into a complete feature set in the form of a feature matrix and label combination, and finally the first dynamic trend feature group that can comprehensively reflect the dynamic change trend of the first physical quantity layer information is output.

[0073] In one possible implementation, step S243 further includes: Step S2431: Outputting the first pressure shock pre-compensation pulse based on the pressure change rate matching of the first dynamic trend feature group.

[0074] Step S2432: adjusting the integral time constant of the flow PID controller based on the first continuous proportion of excessive fluctuations, and outputting a first PID integral adjustment value.

[0075] Step S2433: Outputting a first reverse damping control item according to the intensity matching of the first pressure oscillation spectrum.

[0076] Step S2434: Fatigue strength attenuation modeling is performed based on the first cumulative number of pressurization cycles and the first flow rate trend direction mark, and the first mechanical fatigue suppression coefficient is output.

[0077] Specifically, the pressure change rate contained in the first dynamic trend feature group, derived from the first dynamic derivative feature set, is matched against a pre-stored pressure shock pre-compensation pulse parameter library. This library contains parameters such as pulse amplitude, width, and trigger timing corresponding to different pressure change rates. When the pressure change rate reaches or exceeds the set shock warning threshold, the corresponding pulse parameters are selected based on the matching results, and a first pressure shock pre-compensation pulse is generated and output. This prevents the hydraulic pump from outputting pressure and offsets the impending pressure shock.

[0078] Based on the continuous proportion of the first over-limit fluctuation, the integral time constant of the flow PID controller is dynamically adjusted according to the preset adjustment rules. If the continuous proportion of the first over-limit fluctuation is high, it indicates that the flow fluctuation is more frequent and severe. At this time, the integral time constant is reduced to speed up the response speed of the integral action and enhance the ability to correct the flow deviation; if the proportion is low, it means that the flow is relatively stable, then the integral time constant is increased to avoid system oscillation caused by excessive integration, and finally the adjusted integral time constant is output as the first PID integral adjustment amount.

[0079] Based on the intensity of the first pressure oscillation spectrum, a preset reverse damping control parameter library is searched. This library stores parameters such as damping coefficients, suppression frequency ranges, and control strength for different spectral intensity ranges. Based on the specific value of the current first pressure oscillation spectrum intensity and the main oscillation frequency components, the optimal reverse damping parameter combination is matched from the parameter library. This is then generated and output as a first reverse damping control item for suppressing the pressure oscillations, thereby reducing the amplitude and duration of the pressure fluctuations.

[0080] Fatigue strength attenuation modeling is performed based on the cumulative number of the first pressurization cycles and the first flow trend direction mark. The cumulative number of pressurization cycles is first used as the core variable and substituted into the preset fatigue attenuation formula: fatigue strength = initial strength × e^(-k × number of cycles), where k is the attenuation coefficient. The attenuation coefficient k is then corrected in combination with the first flow trend direction mark. When the flow shows a reverse trend, the k value is increased to accelerate the attenuation correction. The compensation coefficient reflecting the current mechanical fatigue state of the hydraulic pump is calculated through this model, and finally the first mechanical fatigue suppression coefficient used to reduce equipment loss is output.

[0081] In one possible implementation, step S244 further includes: Step S2441: After generating an initial anti-disturbance pressure instruction by linearly superimposing the first basic pressure correction term and the first pressure shock pre-compensation pulse, the initial anti-disturbance pressure instruction is injected into the first reverse damping control term to output a reliable pressure control instruction.

[0082] Step S2442: Perform a multiplication operation on the first flow correction term and the first mechanical fatigue suppression coefficient to generate a reference fatigue adaptive flow, apply the first PID integral adjustment amount to dynamically modulate the response rate of the reference fatigue adaptive flow, and output the modulated fatigue adaptive flow.

[0083] Step S2443: Outputting a dead time compression parameter by integrating the timing components of the first response delay compensation amount and the first PID integral adjustment amount.

[0084] Step S2444: performing confidence weighting processing on the reliable pressure control instruction, the modulated fatigue adaptive flow rate and the dead time compression parameter, and outputting the first initial pump control strategy.

[0085] Specifically, the first basic pressure correction term and the first pressure shock pre-compensation pulse are first linearly superimposed, that is, by directly adding the numerical values ​​of the two according to the corresponding dimensions, an initial anti-disturbance pressure instruction that can initially resist sudden pressure interference is generated; then, the initial anti-disturbance pressure instruction is input into the first reverse damping control term, and the pressure fluctuation is further weakened by the inhibitory effect of the reverse damping, and finally a more stable and reliable pressure control instruction is output.

[0086] A product operation is performed on the first flow correction term and the first mechanical fatigue suppression coefficient, that is, by multiplying the values ​​of the two, a baseline fatigue adaptive flow that takes into account both the flow correction requirements and the mechanical fatigue suppression factors is obtained; then, the first PID integral adjustment amount is applied to dynamically modulate the response rate of the baseline fatigue adaptive flow, and the speed of the flow change is adjusted in real time according to the size of the integral adjustment amount, so that the flow response is more in line with the process timing requirements, and finally the modulated fatigue adaptive flow after rate modulation is output.

[0087] The time-related timing components in the first response delay compensation amount, such as the delay compensation duration and triggering time, and the timing components in the first PID integral adjustment amount, such as the starting time and adjustment period of the integral action, are extracted. These two components are integrated onto the same time axis through the timing alignment algorithm, and the comprehensive correction parameter that can shorten the system response dead zone, namely the dead zone time compression parameter, is calculated and output.

[0088] According to the importance and influence weight of the reliable pressure control instruction, modulated fatigue adaptive flow and dead time compression parameters in the rare earth magnetic material extraction process, corresponding confidence coefficients are assigned to these three parameters respectively. For example, the confidence coefficient of reliable pressure control is set to 0.4, the confidence coefficient of modulated fatigue adaptive flow is set to 0.3, and the confidence coefficient of dead time is set to 0.3; then each parameter is multiplied by its respective confidence coefficient, and the product results are summed and integrated to form a comprehensive control strategy parameter set, and finally the first initial pump control strategy that can guide the operation of the hydraulic pump in the first process stage is output.

[0089] Example 2, based on the same inventive concept as the hydraulic pump control optimization method for rare earth magnetic material extraction in the previous embodiment, Figure 2 As shown, the present application provides a hydraulic pump control optimization system for rare earth magnetic material extraction. The system and method embodiments in the present application are based on the same inventive concept. The system includes: The indicator group association module 10 is used to locate multiple process stages served by hydraulic pumps in the rare earth magnetic material extraction system, and directionally associate multiple hydraulic-related indicator groups according to the functional properties of the hydraulic pumps in the multiple process stages.

[0090] The pump control strategy output module 20 is used for the multiple edge computing nodes independently deployed in the multiple process stages to collect multiple real-time process information in real time according to the multiple hydraulic-related indicator groups in the multiple process stages to perform local control strategy fitting and output multiple initial pump control strategies.

[0091] The pump control strategy optimization module 30 is configured to output multiple optimized pump control strategies through cross-stage coupling conflict arbitration after the collaborative control center receives multiple initial pump control strategies uploaded by the multiple edge computing nodes.

[0092] The collaborative control module 40 is used to implement time-series collaborative control of multiple service hydraulic pumps in the multiple process stages after the multiple edge computing nodes receive and adopt the multiple optimized pump control strategies issued by the collaborative control center.

[0093] The closed-loop dynamic update module 50 is used for the multiple edge computing nodes to perform closed-loop dynamic update on the control parameters of the multiple service hydraulic pumps in the rare earth magnetic material extraction system according to the dynamic disturbance range of the multiple hydraulic-related indicator groups.

[0094] Furthermore, the system is also used to implement the following functions: Adjacent strategy conflicts are detected for the multiple initial pump control strategies, and a material balance conflict set, an energy consumption accumulation conflict set, and a process interference conflict set are output; dynamic flow calibration of process priority is performed based on the material balance conflict set, and a flow calibration strategy is output; time-sharing peak-shifting pressurization timing planning is performed based on the energy consumption accumulation conflict set, and a timing avoidance strategy is output; transition buffer neutralization instructions are inserted for the process interference conflict set, and a chemical isolation strategy is output; cross-mutual exclusivity elimination is performed on the flow calibration strategy, timing avoidance strategy, and chemical isolation strategy, and the multiple optimized pump control strategies are output.

[0095] Furthermore, the system is also used to implement the following functions: According to the first hydraulic-related indicator group, local binding of the upload authority of the first sensor network pre-deployed in the first process stage is performed to obtain a first dedicated sensor topology; the first edge computing node receives the first real-time process information uploaded by the first dedicated sensor topology; based on the first real-time process information, hydraulic process auxiliary deviation is identified, and a first hydraulic auxiliary deviation vector is output; according to the first hydraulic auxiliary deviation vector, pump control parameter correction modeling is performed, and a first initial pump control strategy is output.

[0096] Furthermore, the system is also used to implement the following functions: Analyze the first real-time process information to obtain first physical quantity layer information, first chemical quantity layer information and first timing layer information; predefine the multi-layer process setting value of the first process stage; use the multi-layer process setting value mapping to compare the first physical quantity layer information, the first chemical quantity layer information and the first timing layer information, perform static deviation calculation, and output the first pressure dimension deviation, the first chemical dimension deviation and the first timing dimension deviation; perform dynamic trend feature analysis on the first physical quantity layer information, and output the first dynamic trend feature group; according to the sensing accuracy attribute of the first dedicated sensing topology, perform confidence weighting on the first dynamic trend feature group, the first pressure dimension deviation, the first chemical dimension deviation and the first timing dimension deviation, and output the first hydraulic auxiliary deviation vector.

[0097] Furthermore, the system is also used to implement the following functions: A pump control correction model architecture is constructed, wherein the pump control correction model architecture includes a static deviation layer, a dynamic feature layer and a fusion output layer, the static deviation layer and the dynamic feature layer are connected in parallel, and the output end is connected to the fusion output layer; the first pressure dimension deviation, the first chemical dimension deviation and the first timing dimension deviation are corrected and compensated in parallel in the static deviation layer, and a first basic pressure correction item, a first flow correction item and a first response delay compensation amount are output; multimodal compensation modeling of the first dynamic trend feature group is performed in the dynamic feature layer, and a first dynamic compensation instruction set is output, wherein the first dynamic compensation instruction set includes a first pressure shock pre-compensation pulse, a first PID integral adjustment amount, a first reverse damping control item and a first mechanical fatigue suppression coefficient; cross-coupling of the first dynamic compensation instruction set, the first basic pressure correction item, the first flow correction item and the first response delay compensation amount is executed in the fusion output layer, and the first initial pump control strategy is output.

[0098] Furthermore, the system is also used to implement the following functions: Based on a preset time window, rolling time series segmentation is performed on the first physical quantity layer information to obtain a continuous data block sequence; flow and pressure derivative feature items are extracted from the continuous data block sequence to obtain a first dynamic derivative feature set; based on the continuous data blocks, the out-of-limit fluctuation state is quantified, and the first out-of-limit fluctuation duration ratio and the first pressure oscillation spectrum intensity are output; the continuous data blocks are traversed to obtain the first cumulative number of pressurization cycles, wherein the first cumulative number of pressurization cycles is associated with the first flow trend direction mark; the first dynamic derivative feature set, the first out-of-limit fluctuation duration ratio, the first pressure oscillation spectrum intensity, the first cumulative number of pressurization cycles and the first flow trend direction mark are encapsulated to output the first dynamic trend feature group.

[0099] Furthermore, the system is also used to implement the following functions: Based on the pressure change rate matching of the first dynamic trend feature group, the first pressure shock pre-compensation pulse is output; based on the first over-limit fluctuation duration ratio, the integral time constant of the flow PID controller is adjusted, and the first PID integral adjustment amount is output; based on the first pressure oscillation spectrum intensity matching, the first reverse damping control item is output; based on the cumulative number of the first pressurization cycles and the first flow trend direction mark, fatigue strength attenuation modeling is performed, and the first mechanical fatigue suppression coefficient is output.

[0100] Furthermore, the system is also used to implement the following functions: After generating an initial anti-disturbance pressure instruction by linearly superimposing the first basic pressure correction term and the first pressure shock pre-compensation pulse, the initial anti-disturbance pressure instruction is injected into the first reverse damping control term to output a reliable pressure control instruction; performing a product operation on the first flow correction term and the first mechanical fatigue suppression coefficient to generate a reference fatigue adaptive flow, the first PID integral adjustment amount is applied to dynamically modulate the response rate of the reference fatigue adaptive flow, and the modulated fatigue adaptive flow is output; by integrating the timing components of the first response delay compensation amount and the first PID integral adjustment amount, a dead time compression parameter is output; confidence-weighted processing is performed on the reliable pressure control instruction, the modulated fatigue adaptive flow and the dead time compression parameter, and the first initial pump control strategy is output.

[0101] Furthermore, the system is also used to implement the following functions: The multiple process stages include a slurry conveying stage, a filter pressing separation stage, a solvent extraction stage and a stripping and washing stage.

[0102] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0103] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0104] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A hydraulic pump control optimization method for rare earth magnetic material extraction, characterized in that: The method comprises: Locating multiple process stages served by hydraulic pumps in a rare earth magnetic material extraction system, and directionally associating multiple hydraulic-related indicator groups based on functional attributes of the hydraulic pumps in the multiple process stages; Multiple edge computing nodes independently deployed at the multiple process stages collect multiple real-time process information in real time at the multiple process stages according to the multiple hydraulic-related indicator groups, perform local control strategy fitting, and output multiple initial pump control strategies; After receiving the multiple initial pump control strategies uploaded by the multiple edge computing nodes, the collaborative control center outputs multiple optimized pump control strategies through cross-stage coupling conflict arbitration; After receiving and adopting the multiple optimized pump control strategies issued by the collaborative control center, the multiple edge computing nodes implement time-series collaborative control on the multiple service hydraulic pumps in the multiple process stages; The plurality of edge computing nodes perform closed-loop dynamic updates on control parameters of a plurality of service hydraulic pumps in the rare earth magnetic material extraction system according to dynamic disturbance ranges of the plurality of hydraulic-related indicator groups; After receiving the multiple initial pump control strategies uploaded by the multiple edge computing nodes, the collaborative control center outputs multiple optimized pump control strategies through cross-stage coupling conflict arbitration, including: Performing adjacent strategy conflict detection on the multiple initial pump control strategies, and outputting a material balance conflict set, an energy consumption accumulation conflict set, and a process interference conflict set; Performing dynamic flow calibration of process priorities based on the material balance conflict set and outputting a flow calibration strategy; Based on the energy consumption cumulative conflict set, a time-sharing peak-staggered pressure sequence planning is performed, and a sequence avoidance strategy is output; Performing transition buffer neutralization instruction insertion for the process interference conflict set and outputting a chemical isolation strategy; Cross-exclusivity elimination is performed on the flow calibration strategy, timing avoidance strategy, and chemical isolation strategy, and the plurality of optimized pump control strategies are output.

2. The hydraulic pump control optimization method for rare earth magnetic material extraction according to claim 1, characterized in that: Multiple edge computing nodes independently deployed in the multiple process stages collect multiple real-time process information in real time according to the multiple hydraulic-related indicator groups in the multiple process stages to perform local control strategy fitting and output multiple initial pump control strategies, the method comprising: Performing local binding of upload permissions of a first sensor network pre-deployed in a first process phase according to a first hydraulic pressure-related indicator group to obtain a first dedicated sensor topology; The first edge computing node receives first real-time process information uploaded by the first dedicated sensor topology; performing hydraulic process auxiliary deviation identification based on the first real-time process information, and outputting a first hydraulic auxiliary deviation vector; Pump control parameter correction modeling is performed based on the first hydraulic assistance deviation vector, and a first initial pump control strategy is output.

3. The hydraulic pump control optimization method for rare earth magnetic material extraction according to claim 2, characterized in that: Performing hydraulic process auxiliary deviation identification based on the first real-time process information and outputting a first hydraulic process auxiliary deviation vector, the method comprising: Parsing the first real-time process information to obtain first physical quantity layer information, first chemical quantity layer information, and first time sequence layer information; predefining multi-layer process setting values ​​for the first process stage; The first physical quantity layer information, the first chemical quantity layer information and the first timing layer information are compared using the multi-layer process setting value mapping, static deviation calculation is performed, and a first pressure dimension deviation, a first chemical dimension deviation and a first timing dimension deviation are output; Performing dynamic trend feature analysis on the first physical quantity layer information and outputting a first dynamic trend feature group; According to the sensing accuracy attribute of the first dedicated sensing topology, the confidence weighting of the first dynamic trend feature group, the first pressure dimension deviation, the first chemical dimension deviation and the first timing dimension deviation is performed to output the first hydraulic assistance deviation vector.

4. The hydraulic pump control optimization method for rare earth magnetic material extraction according to claim 3, characterized in that: Performing pump control parameter correction modeling based on the first hydraulic assistance deviation vector and outputting a first initial pump control strategy, the method includes: Constructing a pump-controlled correction model architecture, wherein the pump-controlled correction model architecture includes a static bias layer, a dynamic feature layer, and a fusion output layer, wherein the static bias layer and the dynamic feature layer are connected in parallel, and an output end is connected to the fusion output layer; Performing parallel correction and compensation of the first pressure dimension deviation, the first chemical dimension deviation, and the first timing dimension deviation in the static deviation layer, and outputting a first basic pressure correction term, a first flow correction term, and a first response delay compensation amount; Performing multimodal compensation modeling of the first dynamic trend feature group in the dynamic feature layer, and outputting a first dynamic compensation instruction set, wherein the first dynamic compensation instruction set includes a first pressure shock pre-compensation pulse, a first PID integral adjustment amount, a first reverse damping control item, and a first mechanical fatigue suppression coefficient; The cross-coupling of the first dynamic compensation instruction set, the first basic pressure correction term, the first flow correction term and the first response delay compensation amount is executed in the fusion output layer to output the first initial pump control strategy.

5. The hydraulic pump control optimization method for rare earth magnetic material extraction according to claim 4, characterized in that: Performing dynamic trend feature analysis on the first physical quantity layer information and outputting a first dynamic trend feature group, the method comprising: Perform rolling time sequence segmentation on the first physical quantity layer information based on a preset time window to obtain a continuous data block sequence; Extracting flow and pressure derivative feature items from the continuous data block sequence to obtain a first dynamic derivative feature set; quantifying an excessive fluctuation state based on the continuous data blocks, and outputting a first excessive fluctuation duration ratio and a first pressure oscillation spectrum intensity; Traversing the continuous data blocks to obtain a first cumulative number of pressurization cycles, wherein the first cumulative number of pressurization cycles is associated with a first flow rate trend direction mark; The first dynamic derivative feature set, the first over-limit fluctuation duration ratio, the first pressure oscillation spectrum intensity, the first cumulative number of pressurization cycles and the first flow rate trend direction mark are encapsulated, and the first dynamic trend feature group is output.

6. The hydraulic pump control optimization method for rare earth magnetic material extraction according to claim 5, characterized in that: Performing multimodal compensation modeling of the first dynamic trend feature group in the dynamic feature layer and outputting a first dynamic compensation instruction set, the method comprising: Outputting the first pressure shock pre-compensation pulse based on the pressure change rate matching of the first dynamic trend feature group; Adjusting the integral time constant of the flow PID controller based on the continuous proportion of the first excessive fluctuation, and outputting a first PID integral adjustment value; outputting a first reverse damping control item according to the intensity matching of the first pressure oscillation spectrum; Fatigue strength attenuation modeling is performed based on the accumulated number of the first pressurization cycles and the first flow rate trend direction mark, and the first mechanical fatigue suppression coefficient is output.

7. The hydraulic pump control optimization method for rare earth magnetic material extraction according to claim 4, characterized in that: The method includes executing cross-coupling of the first dynamic compensation instruction set, the first basic pressure correction term, the first flow correction term, and the first response delay compensation amount at the fusion output layer to output the first initial pump control strategy. After generating an initial anti-disturbance pressure command by linearly superimposing the first basic pressure correction term and the first pressure shock pre-compensation pulse, the initial anti-disturbance pressure command is injected into the first reverse damping control term to output a reliable pressure control command; performing a product operation on the first flow correction term and the first mechanical fatigue suppression coefficient to generate a reference fatigue adaptive flow, dynamically modulating a response rate of the reference fatigue adaptive flow by applying the first PID integral adjustment amount, and outputting a modulated fatigue adaptive flow; Outputting a dead time compression parameter by integrating the timing components of the first response delay compensation amount and the first PID integral adjustment amount; Confidence-weighted processing is performed on the reliable pressure control instruction, the modulation fatigue adaptive flow, and the dead time compression parameter, and the first initial pump control strategy is output.

8. The hydraulic pump control optimization method for rare earth magnetic material extraction according to claim 1, characterized in that: The multiple process stages include a slurry conveying stage, a filter pressing separation stage, a solvent extraction stage and a stripping and washing stage.

9. Hydraulic pump control optimization system for rare earth magnetic material extraction, characterized in that: The system is used to implement the hydraulic pump control optimization method for rare earth magnetic material extraction according to any one of claims 1 to 8, and the system comprises: An indicator group association module is used to locate multiple process stages served by hydraulic pumps in a rare earth magnetic material extraction system, and directionally associate multiple hydraulic-related indicator groups according to functional attributes of the hydraulic pumps in the multiple process stages; A pump control strategy output module is configured to collect multiple real-time process information in real time at the multiple process stages according to the multiple hydraulic-related indicator groups at the multiple edge computing nodes independently deployed at the multiple process stages, perform local control strategy fitting, and output multiple initial pump control strategies; A pump control strategy optimization module is configured to output multiple optimized pump control strategies through cross-stage coupling conflict arbitration after the collaborative control center receives multiple initial pump control strategies uploaded by the multiple edge computing nodes; a collaborative control module, configured to implement sequential collaborative control of the plurality of service hydraulic pumps in the plurality of process stages after the plurality of edge computing nodes receive and adopt the plurality of optimized pump control strategies issued by the collaborative control center; A closed-loop dynamic update module is used for the multiple edge computing nodes to perform closed-loop dynamic updates on the control parameters of multiple service hydraulic pumps in the rare earth magnetic material extraction system according to the dynamic disturbance ranges of the multiple hydraulic-related indicator groups.

Images