Dredge pump control system and method for river regulation

Abstract

The invention discloses a dredge pump control system and method for river regulation, and relates to the technical field of dredge pump control. The dredge pump control system comprises a sensing module, a centralized control module, an energy-saving execution module and a control parameter recording module; the sensing module is arranged on a multi-element sensor at a key part of a dredge pump for acquiring data, and the data is pre-processed by a microprocessor and then transmitted to the centralized control module at a high speed by a wireless transmission module, so that an accurate basis is provided for system control; according to the invention, by integrating multiple sensors and an advanced control algorithm, the dredging efficiency and accuracy of the dredge pump of the dredger are obviously improved; the sensing module can monitor key parameters of the dredge pump in real time, such as suction pressure, discharge flow, pump shaft temperature and sediment concentration, and it is ensured that the running state of the dredge pump is comprehensively known; and the centralized control module dynamically optimizes a control sequence by using a model predictive control and fuzzy logic control algorithm so as to adapt to variable working conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of mud pump control, and in particular to a mud pump control system and method for river channel regulation. Background Art

[0002] In the process of river management, mud pump control technology is a key link in achieving efficient and environmentally friendly management. Traditional mud pump control systems face many challenges in river management scenarios, such as insufficient real-time monitoring of mud pump operating status, poor adaptability to complex working conditions, and optimization issues of energy consumption and efficiency. In the process of river management, mud pumps need to operate under different geological conditions, sediment concentrations, and hydrological environments, but traditional control systems are difficult to accurately predict and adapt to these changes, resulting in low management efficiency, energy waste, and severe equipment wear; In addition, most existing mud pump control systems use simple feedback control strategies, which are difficult to cope with the changing working conditions and complex dynamic characteristics of river management. In terms of data collection and processing, existing technologies cannot fully utilize the full life cycle data of mud pump operation to optimize the control strategy, further limiting the efficiency and quality of river management. These problems urgently need a more advanced and intelligent control system to solve. Summary of the invention

[0003] The purpose of the present invention is to solve the problem of accurate control and optimized management of mud pumps under complex working conditions in river channel management, and to propose a mud pump control system and method for river channel management.

[0004] The purpose of the present invention can be achieved through the following technical solutions: Mud pump control system for river management, including: The sensing module is equipped with multiple sensors placed at different parts of the mud pump to collect data. After being pre-processed by the microprocessor, the data is transmitted to the centralized control module by the wireless transmission module to provide a basis for control. Centralized control module, multi-core processor processes sensor data, integrating model-based predictive control and fuzzy logic control algorithms; model-based predictive control plans the control sequence according to the mud pump model and working condition target and dynamically adjusts it; fuzzy logic control processes nonlinear working condition output adjustment instructions, the two work together, and take into account both automatic and manual control through the human-computer interaction interface; Energy-saving execution module, permanent magnet synchronous vector control variable frequency motor speed regulation according to instructions to save energy, cooling system self-adjustment according to temperature; regulating valve cooperates with motor to optimize pressure distribution, actuator self-holding when power off, quantitative correction of motor speed and valve opening according to feedback parameters to achieve dynamic optimization; The control parameter recording module integrates multi-system data, verifies and corrects errors, and stores them in a structured manner after screening, and conducts mining and analysis based on deep learning algorithms. It determines the optimal control parameters for the dredging area based on a comprehensive evaluation of dredging efficiency, energy consumption, and operating status parameters, and matches and stores and calls the control mud pump accordingly.

[0005] Furthermore, the execution steps of planning the control sequence and dynamically adjusting it based on the model predictive control algorithm in the centralized control module according to the mud pump model and the working condition target are as follows: Modeling and initialization: Combine the physical characteristics, mechanical structure, experimental data and actual working condition records of the mud pump to build a dynamic mathematical model of the mud pump; the dynamic mathematical model of the mud pump covers the relationship between the flow rate, head, power and motor speed, valve opening variables of the mud pump, and considers the external interference factors of sediment concentration, texture, suction and discharge pipeline resistance, and is expressed in the mathematical form of state space equations and transfer functions; according to the engineering planning and geological survey data of the dredger's upcoming operation, set the working condition target parameters, including the target flow range, the expected discharge sediment concentration value, and the allowable pump body pressure range; and initialize the controller's internal state variables, prediction time domain, and control time domain parameters. The prediction time domain determines the length of time the algorithm predicts the future working conditions of the mud pump, and the control time domain limits the length of the control action sequence solved each time; Real-time data acquisition and state estimation: Through the communication connection with the perception module, the real-time operation data of the mud pump is received from the sensor multiple times per second, including suction pressure, discharge flow, pump shaft temperature, and current sediment concentration information; the Kalman filter and particle filter state estimation algorithms are combined with the established mud pump mathematical model to calculate the current hidden internal state of the mud pump, including the degree of impeller wear and the siltation state of the mud suction pipe, and correct the deviation caused by sensor noise and model error, laying the foundation for subsequent accurate prediction; Prediction calculation and control sequence generation: Based on the current accurate state estimation value, the mud pump dynamic model is used to iteratively predict the operation state of the mud pump in the next several steps according to the set prediction time domain, and the change curves of key indicators such as flow, pressure, and energy consumption at different times are obtained; at the same time, with the preset working condition target as the constraint, in the control time domain, the quadratic programming and linear programming algorithms are used to solve the motor speed and valve action sequence that optimizes the performance indicators. The performance indicators cover the lowest energy consumption, the highest mud discharge efficiency, and the minimum equipment wear. Multi-dimensional weighted considerations; Control command output and execution feedback: The first step control command solved in the first control time domain is sent to the energy-saving execution module; after the execution module takes action, the perception module feeds back the new working condition data in real time, and verifies the deviation between the actual execution effect and the predicted value based on the model predictive control algorithm. If the deviation exceeds the threshold, the model parameters are corrected, the subsequent control sequence is adjusted, and a new round of prediction-control cycle is started to ensure that the mud pump closely tracks the preset working condition trajectory.

[0006] Furthermore, the specific operation steps of the fuzzy logic control in the centralized control module to process the nonlinear working condition output adjustment instruction are as follows: Fuzzy input variables: Determine the input variables associated with nonlinear and fuzzy boundary conditions, including the sediment texture change rate, suction pressure fluctuation amplitude, and discharge flow deviation ratio; divide the fuzzy subsets of each input variable based on expert experience and historical fault data, and set membership functions for each subset, including triangular and trapezoidal functions; collect the values ​​of these input variables in real time, calculate the degree to which they belong to each fuzzy subset through the membership function, and convert the input quantity into fuzzy language variables; Construction and reasoning of fuzzy rule base: Based on the experience of dredger operation and maintenance and mud pump control, fuzzy rules are summarized and stored in the fuzzy rule base. After the input variables are fuzzified, the fuzzy rule base is used to match the rules using the reasoning mechanism of Mamdani reasoning method and Sugeno reasoning method to obtain the fuzzy control conclusion, that is, a series of fuzzy outputs, which describe the adjustment direction and amplitude of the control action. Defuzzify the output control quantity: Use the center of gravity method to calculate the weighted center position according to the fuzzy output membership distribution to determine the final precise control quantity; the output control command is sent to the energy-saving execution module to drive the mud pump to operate.

[0007] Furthermore, the specific operation steps of the energy-saving execution module are as follows: The permanent magnet synchronous vector control variable frequency motor is used to change the speed according to the instructions of the centralized control module, adapt to the flow and head required by the actual working conditions, and reduce unnecessary energy consumption; the built-in heat dissipation system automatically adjusts the heat dissipation wind speed according to the motor temperature, further saving energy and increasing efficiency; Regulating valve group: The regulating valve is driven by an electric actuator; the size of the inlet and outlet valves is adjusted according to the mud discharge pressure and flow feedback, and the motor is coordinated to optimize the suction and discharge pressure distribution of the mud pump to reduce the backflow and throttling losses; the actuator has a power-off self-holding function, which maintains the current valve state in the event of an accidental power failure to prevent equipment damage caused by sudden changes in working conditions; Feedback correction: Feedback correction is performed on the mud pump by collecting and comprehensively analyzing the adjusted feedback parameters.

[0008] Furthermore, the process of feedback correction of the energy-saving execution module is as follows: Feedback parameters include: Flow parameter, set the actual flow value to The target flow rate is , flow stability is measured by flow standard deviation Indicates the measurement value of flow parameters Calculated by the following formula: in, and are the maximum and minimum flow ranges, respectively. and are the maximum and minimum ranges of the flow standard deviation, respectively; Head parameter, assuming the actual head is , the target lift is , the head-flow matching is expressed by the matching coefficient of the two , the head value that measures the head parameter Calculated as: in, and They are the maximum and minimum ranges of lift respectively; Energy consumption parameter standardization: Assume that the motor power consumption is , the power before adjustment is The total energy consumption of the system is , the total energy consumption before adjustment is , the consumption balance value of energy consumption parameters Calculated by: in, and are the maximum and minimum ranges of motor power, and are the maximum and minimum ranges of total energy consumption respectively; Pressure parameters: Assume the suction pressure is , the mud discharge pressure is , adjust the suction pressure before , adjust the front mud pressure to , the suction and discharge pressure difference is , adjust the front suction and discharge pressure difference to , the pressure balance value that measures the pressure parameter Calculated as: in, and They are the maximum and minimum ranges of the suction and discharge mud pressure, the suction and discharge mud pressure, and the difference between the suction and discharge pressures; According to the working characteristics and actual needs of the dredger mud pump, a weight is assigned to each feedback parameter, and the flow parameter weight, head parameter weight, energy consumption parameter weight and pressure parameter weight are recorded as ; Then the obtained measurement value , Yang Heng value , consumption balance value , pressure balance value After normalization, the following formula is entered: To obtain the comprehensive evaluation value V; The obtained comprehensive evaluation value V is then compared with several preset threshold intervals, which correspond to different adjustment ranges of the adjustment parameters, including the adjustment values ​​of the valve opening and the motor speed. When the threshold interval to which the comprehensive evaluation value V belongs is determined, the adjustment range required for fine-tuning the adjustment effect is determined. Optimization is achieved based on actual conditions and equipment characteristics. After adjustment, feedback parameters are continued to be collected, and the quantification and correction process is repeated to achieve dynamic optimization and adjustment of the mud pump system.

[0009] Furthermore, the execution process of the control parameter recording module is as follows: Continuously collect and store the operation data of the mud pump throughout its life cycle, covering information on different engineering geology, climate conditions, and operation duration; based on the deep learning algorithm, regularly train and optimize the built-in control model to enable autonomous learning of the best control strategy. The process is as follows: It is integrated with the sensing module to capture various physical parameters of the mud pump in real time, including motor speed, torque, pump body temperature, inlet and outlet pressure, valve opening, and synchronously collect environmental data of the operation site, including water depth, water flow speed, wind direction and wind force information at different times; and it is associated with the dredging ship positioning system data to record the dredging location coordinates, and combined with the geographic information system data to clarify the geological type and soil composition information of the area; these data are continuously accumulated to build a mud pump operation database; In the data collection link, multiple verification and error correction mechanisms are built in. When sensor anomalies, data transmission interruptions, or data values ​​outside the reasonable physical range are found, backup collection plans or repair algorithms are activated to ensure data integrity and accuracy. At the same time, the collected raw data is preliminarily screened to remove erroneous and duplicated data points, reducing the subsequent storage and computing burden. A distributed database architecture is used to store mud pump operation data in a structured manner according to time series, geographical area, and working condition type. To facilitate query and retrieval, an index system is established to locate data subsets of operation periods and dredging locations based on hash indexes. Inverted indexes are used to associate control parameter combinations corresponding to the same dredging effect under different working conditions for subsequent data mining and analysis. Analyze the operation duration and dredging effect related parameters for each dredging area to determine the optimal control parameters.

[0010] Furthermore, the specific operation steps for determining the optimal control parameters in the control parameter recording module are as follows: Through a comprehensive assessment of rating parameters, the evaluation parameters include: Dredging efficiency: includes the dredging volume per unit time and the rate of change of dredging depth. The dredging volume per unit time is quantified by calculating the volume of silt delivered by the dredger pump within a preset time. Specifically, the flow data is obtained through the flow sensor on the sludge discharge pipeline, and combined with the measured value of silt concentration, it is calculated according to the formula: dredging volume = flow rate × silt concentration × time. The rate of change of dredging depth uses the depth measuring equipment on the ship to record the dredging depth at different times, and the rate of change of depth is calculated by the formula: depth change rate = (current depth - initial depth) / operation time. After the calculated dredging volume and depth change rate are normalized, the dredging volume and depth change rate are used as the two right-angled sides of the right triangle respectively, and the other side of the right triangle is connected. A triangular pyramid model is established with the preset correction factor as the height, and the surface area of ​​the triangular pyramid model is calculated, which is recorded as the efficiency judgment value. Energy consumption parameters: Energy consumption per unit dredging volume, through the formula: Energy consumption per unit dredging volume = total energy consumption / dredging volume, where the total energy consumption is accumulated through the power monitoring device on the motor and other energy-consuming equipment; Energy consumption stability, through the statistical fluctuation of energy consumption during the operation and the calculation of the standard deviation of energy consumption data for quantitative measurement; The energy consumption per unit dredging volume and the standard deviation of energy consumption data are recorded as dh and df respectively, and the normalized processing is substituted into the following formula: To obtain the energy consumption evaluation value PO, where It is the correction index of the energy consumption assessment value; Mud pump operating status parameters: including pump pressure stability and motor load rate. The pump pressure stability is evaluated by monitoring the mud suction pressure and mud discharge pressure through the pressure sensor installed at the inlet and outlet of the mud pump, and calculating the pressure fluctuation standard deviation; the motor load rate is calculated by the formula: motor load rate = actual power / rated power; then the obtained pressure fluctuation standard deviation and motor load rate are recorded as yb and fz, and after normalization, they are entered into the following formula: To obtain the operation evaluation value PTY, where e is a constant; The obtained efficiency judgment value YP, energy consumption evaluation value PO and operation evaluation value PTY are normalized and substituted into the following formula: To obtain the comprehensive evaluation value ZJH, They are respectively the preset weight coefficients of the efficiency judgment value YP, the energy consumption evaluation value PO and the operation evaluation value PTY; The comprehensive evaluation values ​​ZJH calculated from different control parameters of each dredging area are sorted by size, and the control parameter with the largest comprehensive evaluation value ZJH is selected as the optimal control parameter of the dredging area and stored in matching with the specific location of the dredging area; when dredging operations are subsequently performed in the dredging area, the optimal control parameter is directly called to control the mud pump.

[0011] Furthermore, the execution steps of the perception module are as follows: Multi-sensor unit: A negative pressure sensor is installed at the suction end of the mud pump to monitor the suction pressure; a fiber Bragg grating temperature and vibration composite sensor is installed at the main shaft of the pump body to simultaneously monitor the shaft temperature, vibration frequency and amplitude; an ultrasonic concentration sensor and an electromagnetic flow sensor are used in the mud discharge pipeline to grasp the concentration and flow of discharged mud in real time, laying a solid data foundation for the scientific adjustment of subsequent control strategies; and temperature and humidity sensors and dust sensors are deployed in the surrounding environment of the mud pump to obtain the potential impact of environmental factors on equipment operation; Data preprocessing and transmission: The data from each sensor is first processed by the built-in microprocessor for preliminary noise reduction and filtering to eliminate invalid interference data and improve data accuracy; The processed data is then transmitted to the centralized control module via the wireless transmission module to ensure data real-time and integrity.

[0012] The mud pump control method for river channel regulation comprises the following steps: S1: Multiple sensors are deployed at different parts of the mud pump to collect data. After noise reduction and filtering by the microprocessor, the data is transmitted to the centralized control module in real time by the wireless transmission module, providing the data foundation for the system, covering pressure, temperature, concentration, flow and environmental information; S2: The multi-core processor serves as the data processing center, integrating MPC and FLC intelligent algorithms; MPC dynamically optimizes the control sequence based on the mud pump model and working condition planning; FLC outputs instructions to resolve nonlinear working condition problems. The two work together with the human-computer interaction interface to achieve automatic and manual intervention; S3: The permanent magnet synchronous vector variable frequency motor can adjust speed according to command to save energy and optimize heat dissipation. The regulating valve can coordinate with the motor to accurately control the pressure distribution according to the feedback of mud discharge pressure and flow. The actuator can be self-stabilized when power is off. The motor speed and valve opening can be dynamically optimized by quantitative analysis of flow, head, energy consumption and pressure parameter feedback. S4: Comprehensively integrates system data, multiple checks and error corrections, and structured storage after screening; based on deep learning mining and analysis, it integrates dredging efficiency, energy consumption, and operating status parameters, locks in the optimal control parameters for regional matching and storage, and directly uses them during dredging to improve efficiency and ensure quality.

[0013] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention significantly improves the dredging efficiency and accuracy of the dredging pump of the dredger by integrating multiple sensors and advanced control algorithms. The sensing module can monitor the key parameters of the dredging pump in real time, such as suction pressure, discharge flow, pump shaft temperature and sediment concentration, to ensure a comprehensive understanding of the operating status of the dredging pump. The centralized control module uses model predictive control (MPC) and fuzzy logic control (FLC) algorithms to dynamically optimize the control sequence to adapt to changing working conditions; the intelligent control method can accurately match the load requirements of different working conditions to ensure the stable and efficient operation of the dredging pump, thereby improving the quality and efficiency of dredging operations; (2) In the present invention, the energy-saving execution module adopts a permanent magnet synchronous vector control variable frequency motor, which adjusts the motor speed according to real-time data to adapt to the flow and head required by actual working conditions, effectively reducing energy consumption. The built-in heat dissipation system automatically adjusts the heat dissipation wind speed according to the motor temperature, further saving energy and increasing efficiency. The regulating valve group cooperates with the motor to optimize the suction and discharge pressure distribution of the mud pump, reduce reflux and throttling losses, reduce equipment wear, and extend the service life of the equipment; (3) In the present invention, the control parameter recording module uses deep learning algorithm mining and analysis to comprehensively consider dredging efficiency, energy consumption and operating status parameters, determine the optimal control parameters of the dredging area, and match and store them; this enables the dredger to call the optimal control parameters according to the specific conditions of each area, and realize intelligent control and optimization; this not only improves the efficiency and accuracy of dredging operations, but also reduces energy consumption and equipment wear, and realizes the intelligence and automation of the dredger mud pump control technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0015] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0017] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0018] like Figure 1As shown, the mud pump control system for river management includes a sensing module, a centralized control module, an energy-saving execution module and a control parameter recording module; The sensing module uses multiple sensors placed at key locations of the mud pump to collect data. After pre-processing by the microprocessor, the data is transmitted to the centralized control module at high speed by the wireless transmission module, providing an accurate basis for system control. Multi-sensor unit: A negative pressure sensor is installed at the suction end of the mud pump to monitor the suction pressure. Minute pressure fluctuations can be captured immediately to determine whether the mud suction pipe is blocked, leaking, or the concentration of the sucked mud is abnormal. The main shaft of the pump body is equipped with a fiber grating temperature and vibration composite sensor to simultaneously monitor the shaft temperature, vibration frequency and amplitude, and to gain early insight into potential fault hazards such as wear and imbalance of mechanical parts. Ultrasonic concentration sensors and electromagnetic flow sensors are used in the mud discharge pipeline to grasp the concentration and flow of discharged mud in real time, laying a solid data foundation for the scientific adjustment of subsequent control strategies. In addition, temperature and humidity sensors and dust sensors are deployed in the surrounding environment of the mud pump to consider the potential impact of environmental factors on equipment operation. Data preprocessing and transmission: The data from each sensor is first processed by the built-in microprocessor for preliminary noise reduction and filtering to eliminate invalid interference data and improve data accuracy. The processed data is then transmitted to the centralized control module stably and at high speed through a low-power, high-bandwidth wireless transmission module to ensure data real-time and integrity.

[0019] The centralized control module is used to process massive sensor data through a multi-core processor, integrating MPC and FLC algorithms. MPC plans the control sequence according to the mud pump model and working condition target and adjusts it dynamically; FLC processes nonlinear working conditions and outputs fine-tuning instructions. The two work together to take into account both automatic and manual control through the human-computer interaction interface. Core computing processor: Multi-core processor with powerful computing capability to process massive sensor data and provide hardware support for efficient operation of complex control algorithms; built-in large-capacity cache and non-volatile storage for temporary storage of real-time data and historical operating information for retrieval and comparison at any time; Intelligent control algorithm integration: integrating composite algorithms based on model predictive control (MPC) and fuzzy logic control (FLC); Based on the model predictive control (MPC), the motor speed and valve action sequence are planned in advance according to the dynamic mathematical model of the mud pump and the preset working condition target; the process is as follows: Modeling and initialization: First, the accurate dynamic mathematical model of the mud pump is constructed by combining the physical characteristics, mechanical structure, experimental data and actual working condition records of the mud pump. This model covers the relationship between the flow rate, head, power and motor speed and valve opening variables of the mud pump, and considers the external interference factors such as sediment concentration, texture and suction and discharge pipeline resistance. It is expressed in the mathematical form of state space equations and transfer functions. For example, a linear time-varying parameter model is used to adapt to the variable characteristics of the working conditions. According to the engineering planning and geological survey data of the dredger's upcoming operation, the working condition target parameters are set, including the target flow range, the expected discharge sediment concentration value, and the allowable pump body pressure range. The internal state variables, prediction time domain and control time domain key parameters of the MPC controller are initialized. The prediction time domain determines the length of time the algorithm predicts the future working conditions of the mud pump, and the control time domain limits the length of the control action sequence solved each time. Real-time data acquisition and state estimation: Through the communication connection with the perception module, the real-time operation data of the mud pump is received from the sensor multiple times per second, including suction pressure, discharge flow, pump shaft temperature, and current sediment concentration information; the Kalman filter and particle filter state estimation algorithms are combined with the established mud pump mathematical model to calculate the current hidden internal state of the mud pump, including the degree of impeller wear and the siltation state of the mud suction pipe, and correct the deviation caused by sensor noise and model error, laying the foundation for subsequent accurate prediction; Prediction calculation and control sequence generation: Based on the current accurate state estimation value, the mud pump dynamic model is used to iteratively predict the operation status of the mud pump in the next several steps (such as the next 10-20 seconds, depending on the complexity of the working conditions) according to the set prediction time domain, and the change curves of key indicators such as flow, pressure, and energy consumption at different times are obtained; at the same time, with the preset working condition target as a constraint, within the control time domain (such as planning control actions in the next 3-5 seconds), the optimization algorithm (quadratic programming, linear programming algorithm) is used to solve the motor speed and valve action sequence that optimizes the performance indicators. The performance indicators cover multi-dimensional weighted considerations such as the lowest energy consumption, the highest mud discharge efficiency, and the minimum equipment wear; Control command output and execution feedback: The first step control command solved in the first control time domain (such as the motor speed value and valve opening change that need to be adjusted immediately) is sent to the energy-saving execution module; after the execution module acts, the perception module feeds back the new working condition data in real time, and the MPC algorithm verifies the deviation between the actual execution effect and the predicted value. If the deviation exceeds the threshold, the model parameters are corrected, the subsequent control sequence is adjusted, and a new round of prediction-control cycle is started to ensure that the mud pump closely tracks the preset working condition trajectory.

[0020] Fuzzy logic control (FLC) handles nonlinear and fuzzy boundary conditions, such as the gradual change of sediment texture, and flexibly fine-tunes control instructions; the specific process is as follows: Fuzzy input variables: Determine the input variables that are strongly associated with nonlinear and fuzzy boundary conditions, such as the sediment texture change rate, suction pressure fluctuation amplitude, discharge flow deviation ratio, etc.; divide the fuzzy subsets of each input variable based on expert experience and historical fault data. For example, divide the sediment texture change rate into subsets such as "slow change", "moderate change", and "dramatic change", and set a membership function for each subset. Common membership functions include triangular and trapezoidal functions; collect the values ​​of these input variables in real time, calculate the degree to which they belong to each fuzzy subset through the membership function, and convert the precise input quantity into fuzzy linguistic variables.

[0021] Construction and reasoning of fuzzy rule base: Engineers and domain experts summarize and summarize fuzzy rules based on their years of experience in dredging vessel operation and maintenance and mud pump control, and store them in the fuzzy rule base. The rule form includes "If the mud texture changes dramatically and the suction pressure fluctuates greatly, then increase the motor speed appropriately and fine-tune the valve to increase the suction opening." After the input variables are fuzzified, the fuzzy rule base is used to match the rules using the reasoning mechanism of the Mamdani reasoning method and the Sugeno reasoning method to obtain the fuzzy control conclusion, that is, a series of fuzzy output quantities that describe the adjustment direction and amplitude of the control action. Defuzzify the output control quantity: Use the center of gravity method to calculate the weighted center position according to the fuzzy output membership distribution to determine the final precise control quantity; the output precise control command is sent to the energy-saving execution module to drive the mud pump to operate.

[0022] The two work together to accurately match the load requirements of different working conditions to ensure stable and efficient operation of the mud pump; it is also equipped with human-computer interaction interface software, so operators can remotely view equipment status and historical curves, and manually intervene in some instructions when necessary, taking into account both automation and manual flexibility.

[0023] The energy-saving execution module uses permanent magnet synchronous vector control variable frequency motor to adjust speed according to instructions to save energy, and the heat dissipation system is self-adjusting according to temperature; the high-precision control valve cooperates with the motor to optimize the pressure distribution, the actuator is self-holding when power is off, and the motor speed and valve opening are quantitatively corrected according to the feedback parameters to achieve dynamic optimization; The permanent magnet synchronous vector control variable frequency motor is used, which improves energy efficiency by more than 35% compared with traditional asynchronous motors. It can smoothly and steplessly adjust the speed within a very wide speed range (0-rated speed). The speed is changed according to the instructions of the centralized control module to adapt to the flow and head required by the actual working conditions, reducing unnecessary energy consumption. The built-in heat dissipation system automatically adjusts the heat dissipation wind speed according to the motor temperature, further saving energy and increasing efficiency. Regulating valve group: The high-precision regulating valve is driven by an electric actuator, and the valve opening control accuracy reaches 0.05 degrees; according to the mud discharge pressure and flow feedback, the inlet and outlet valve sizes are adjusted quickly and accurately, and the motor is coordinated to optimize the mud pump suction and discharge pressure distribution to reduce reflux and throttling losses; the actuator has a power-off self-holding function to maintain the current valve state in the event of an accidental power failure to prevent equipment damage caused by sudden changes in working conditions; Feedback correction: By collecting feedback parameters after adjustment, including: Flow parameter, set the actual flow value to The target flow rate is , flow stability is measured by flow standard deviation Indicates the measurement value of flow parameters Calculated by the following formula: in, and are the maximum and minimum flow ranges, respectively. and are the maximum and minimum ranges of the flow standard deviation respectively; the head parameter, assuming the actual head is , the target lift is , the head-flow matching is expressed by the matching coefficient of the two (determined by the proximity of the head-flow curve to the efficient working area, ), the head value that measures the lift parameter Calculated as: in, and are the maximum and minimum ranges of the lift respectively; energy consumption parameter standardization: assuming the motor power consumption is , the power before adjustment is The total energy consumption of the system is , the total energy consumption before adjustment is , the consumption balance value of energy consumption parameters Calculated by: in, and are the maximum and minimum ranges of motor power, and are the maximum and minimum ranges of the total energy consumption of the system respectively; pressure parameter: assuming the suction pressure is , the mud discharge pressure is , adjust the suction pressure before , adjust the front mud pressure to , the suction and discharge pressure difference is , adjust the front suction and discharge pressure difference to , the pressure balance value that measures the pressure parameter Calculated as: in, and They are the maximum and minimum ranges of the suction and discharge mud pressure, the suction and discharge mud pressure, and the difference between the suction and discharge pressures; According to the working characteristics and actual needs of the dredger mud pump, a weight is assigned to each feedback parameter, and the flow parameter weight, head parameter weight, energy consumption parameter weight and pressure parameter weight are recorded as ; Then the obtained measurement value , Yang Heng value , consumption balance value , pressure balance value After normalization, the following formula is entered: To obtain a comprehensive evaluation value V; the value range of V is between 0-1, the closer V is to 1, the better the regulation effect, and vice versa; then compare the obtained comprehensive evaluation value V with several preset threshold intervals, and the several threshold intervals correspond to different adjustment ranges of the regulation parameters, and the regulation parameters include the adjustment values ​​of the valve opening and the motor speed; when the threshold interval to which the comprehensive evaluation value V belongs is determined, the adjustment range required for fine-tuning the regulation effect is determined; further optimization is achieved according to the actual situation and equipment characteristics. After adjustment, feedback parameters continue to be collected, and the above quantification and correction process is repeated to achieve dynamic optimization and regulation of the mud pump system.

[0024] The control parameter recording module is used to integrate multi-system data, verify and correct errors, and store them in a structured manner after screening, and mine and analyze them based on deep learning algorithms. The optimal control parameters for the region are determined based on a comprehensive evaluation of dredging efficiency, energy consumption, and operating status parameters, and the dredging pumps are then matched, stored, and called for control; Continuously collect and store the operation data of the mud pump throughout its life cycle, covering information on different engineering geology, climate conditions, and operation duration; based on the deep learning algorithm, regularly train and optimize the built-in control model to allow it to "learn" the best control strategy autonomously; the specific process is as follows: Deeply integrated with the sensing module and other related systems on the dredger, it not only captures various physical parameters of the mud pump during operation in real time, such as motor speed, torque, pump body temperature, inlet and outlet pressures, and valve opening, but also simultaneously collects environmental data of the operation site, including water depth, water flow speed, wind direction and wind force at different times; and associates the dredger positioning system data to accurately record the coordinates of the dredging location, and combines with the geographic information system (GIS) data to clarify the geological type and soil composition of the area; these data are continuously accumulated at a high frequency (for example, key parameters are collected once per second) to build a massive, multi-dimensional mud pump operation database; in the data collection link, multiple verification and error correction mechanisms are built in. Once a sensor anomaly, data transmission interruption, or data value exceeds a reasonable physical range is found, the backup collection plan or intelligent repair algorithm is immediately activated to ensure data integrity and accuracy; at the same time, the collected raw data is preliminarily screened to eliminate erroneous and duplicated data points to reduce the subsequent storage and computing burden; A distributed database architecture is adopted to store massive mud pump operation data in a structured manner according to multiple dimensions such as time series, geographical area, and working condition type. To facilitate query and retrieval, an index system is established to quickly locate data subsets for specific operation periods and specific dredging locations based on hash indexes. An inverted index is used to associate control parameter combinations corresponding to similar dredging effects under different working conditions, facilitating the efficient implementation of subsequent data mining and analysis. The operation duration and dredging effect-related parameters of each dredging area are screened and analyzed to determine the optimal control parameters, specifically by comprehensively evaluating the rating parameters, which include: Dredging efficiency: includes the dredging volume per unit time and the rate of change of dredging depth, where the dredging volume per unit time is quantified by calculating the volume of sediment transported by the dredging pump within a certain period of time (such as every hour or every day). Specifically, the flow data can be obtained through the flow sensor on the dredging pipeline, and combined with the sediment concentration measurement value, it is calculated according to the formula: dredging volume = flow × sediment concentration × time; the rate of change of dredging depth uses the depth measurement equipment on the ship to record the dredging depth at different times, and the depth change rate is calculated by the formula: depth change rate = (current depth-initial depth) / operating time; the calculated dredging volume and depth change rate are normalized, and the dredging volume and depth change rate are used as the two right-angled sides of the right triangle respectively, and the other side of the right triangle is connected, and a triangular pyramid model is established based on the preset correction factor. , calculate the surface area of ​​the triangular pyramid model, record it as the effective judgment value, set the preset correction factor value between 2.5-9.2, and use the obtained effective judgment value as the standard for measuring dredging efficiency; energy consumption parameters: energy consumption per unit dredging volume, through the formula: energy consumption per unit dredging volume = total energy consumption / dredging volume, where the total energy consumption is accumulated through the power monitoring device on the motor and other energy-consuming equipment; energy consumption stability, through the statistical operation process of energy consumption fluctuations by calculating the standard deviation of energy consumption data for quantitative measurement; the obtained unit dredging volume energy consumption and energy consumption data standard deviation are recorded as dh and df respectively, and the normalized processing is substituted into the following formula: To obtain the energy consumption evaluation value PO, where is the correction index of the energy consumption evaluation value, and the value is set between 0.94 and 1.23; and the obtained energy consumption evaluation value PO is used as the standard for measuring energy consumption parameters; mud pump operation status parameters: including pump pressure stability and motor load rate. The pump pressure stability is evaluated by monitoring the mud suction pressure and mud discharge pressure through the pressure sensor installed at the inlet and outlet of the mud pump, and calculating the pressure fluctuation standard deviation; the motor load rate is calculated by the formula: motor load rate = actual power / rated power; and then the obtained pressure fluctuation standard deviation and motor load rate are recorded as yb and fz, and after normalization, they are entered into the following formula: To obtain the operation evaluation value PTY, where e is a constant; The obtained efficiency judgment value YP, energy consumption evaluation value PO and operation evaluation value PTY are normalized and substituted into the following formula: To obtain the comprehensive evaluation value ZJH, They are the preset weight coefficients of the efficiency judgment value YP, the energy consumption evaluation value PO and the operation evaluation value PTY respectively, and the obtained comprehensive evaluation value ZJH is used as the standard for measuring different control parameters of each dredging area; the comprehensive evaluation values ​​ZJH calculated from different control parameters of each dredging area are sorted according to size, and the control parameter with the largest comprehensive evaluation value ZJH is selected as the optimal control parameter of the dredging area to match and store with the specific location of the dredging area; and when dredging operations are carried out in the dredging area subsequently, the optimal control parameter is directly called to control the mud pump.

[0025] The mud pump control method for river channel regulation comprises the following steps: Multi-sensors are deployed at key locations of the mud pump to collect data, which is then filtered by a microprocessor for noise reduction and transmitted to the centralized control module in real time by a wireless transmission module, providing the system with accurate data foundation, including pressure, temperature, concentration, flow rate and environmental factor information; The multi-core processor serves as the data processing center, integrating MPC and FLC intelligent algorithms. MPC dynamically optimizes the control sequence based on the mud pump model and working condition planning; FLC resolves the problem of nonlinear working conditions and outputs fine-tuning instructions. The two work together with the human-computer interaction interface to achieve automatic precision and manual intervention. The permanent magnet synchronous vector variable frequency motor can adjust speed according to command to save energy and optimize heat dissipation. The high-precision regulating valve can coordinate with the motor to accurately control the pressure distribution according to the feedback of mud discharge pressure and flow. The actuator can be self-stabilized when power is off. The motor speed and valve opening can be dynamically optimized by quantitative analysis of flow, head, energy consumption and pressure parameter feedback. Comprehensively integrate system data, perform multiple checks and error corrections, and perform structured storage after screening. Based on deep learning mining and analysis, it integrates dredging efficiency (dredging volume, dredging depth change rate), energy consumption, and operating status parameters to accurately lock in the optimal control parameters for regional matching and storage, which can be used directly during dredging to improve efficiency and ensure quality.

[0026] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Mud pump control system for river management, characterized in that: include: The sensing module is equipped with multiple sensors placed at different parts of the mud pump to collect data. After being pre-processed by the microprocessor, the data is transmitted to the centralized control module by the wireless transmission module to provide a basis for control. Centralized control module, multi-core processor processes sensor data, integrating model-based predictive control and fuzzy logic control algorithms; model-based predictive control plans the control sequence according to the mud pump model and working condition target and dynamically adjusts it; fuzzy logic control processes nonlinear working condition output adjustment instructions, the two work together, and take into account both automatic and manual control through the human-computer interaction interface; Energy-saving execution module, permanent magnet synchronous vector control variable frequency motor speed regulation according to instructions to save energy, cooling system self-adjustment according to temperature; regulating valve cooperates with motor to optimize pressure distribution, actuator self-holding when power off, quantitative correction of motor speed and valve opening according to feedback parameters to achieve dynamic optimization; The control parameter recording module integrates multi-system data, verifies and corrects errors, and stores them in a structured manner after screening, and conducts mining and analysis based on deep learning algorithms. It determines the optimal control parameters for the dredging area based on a comprehensive evaluation of dredging efficiency, energy consumption, and operating status parameters, and matches and stores and calls the control mud pump accordingly.

2. The mud pump control system for river management according to claim 1, characterized in that: The execution steps of planning the control sequence and dynamically adjusting it based on the model predictive control algorithm in the centralized control module according to the mud pump model and working condition target are as follows: Modeling and initialization: Combine the physical characteristics, mechanical structure, experimental data and actual working condition records of the mud pump to build a dynamic mathematical model of the mud pump; the dynamic mathematical model of the mud pump covers the relationship between the flow rate, head, power and motor speed, valve opening variables of the mud pump, and considers the external interference factors of sediment concentration, texture, suction and discharge pipeline resistance, and is expressed in the mathematical form of state space equations and transfer functions; according to the engineering planning and geological survey data of the dredger's upcoming operation, set the working condition target parameters, including the target flow range, the expected discharge sediment concentration value, and the allowable pump body pressure range; and initialize the controller's internal state variables, prediction time domain, and control time domain parameters. The prediction time domain determines the length of time the algorithm predicts the future working conditions of the mud pump, and the control time domain limits the length of the control action sequence solved each time; Real-time data acquisition and state estimation: Through the communication connection with the perception module, the real-time operation data of the mud pump is received from the sensor multiple times per second, including suction pressure, discharge flow, pump shaft temperature, and current sediment concentration information; the Kalman filter and particle filter state estimation algorithms are combined with the established mud pump mathematical model to calculate the current hidden internal state of the mud pump, including the degree of impeller wear and the siltation state of the mud suction pipe, and correct the deviation caused by sensor noise and model error, laying the foundation for subsequent accurate prediction; Prediction calculation and control sequence generation: Based on the current accurate state estimation value, the mud pump dynamic model is used to iteratively predict the operation state of the mud pump in the next several steps according to the set prediction time domain, and the change curves of key indicators such as flow, pressure, and energy consumption at different times are obtained; at the same time, with the preset working condition target as the constraint, in the control time domain, the quadratic programming and linear programming algorithms are used to solve the motor speed and valve action sequence that optimizes the performance indicators. The performance indicators cover the lowest energy consumption, the highest mud discharge efficiency, and the minimum equipment wear. Multi-dimensional weighted considerations; Control command output and execution feedback: The first step control command solved in the first control time domain is sent to the energy-saving execution module; after the execution module takes action, the perception module feeds back the new working condition data in real time, and verifies the deviation between the actual execution effect and the predicted value based on the model predictive control algorithm. If the deviation exceeds the threshold, the model parameters are corrected, the subsequent control sequence is adjusted, and a new round of prediction-control cycle is started to ensure that the mud pump closely tracks the preset working condition trajectory.

3. The mud pump control system for river management according to claim 1, characterized in that: The specific operation steps of the fuzzy logic control in the centralized control module to process the nonlinear working condition output adjustment instruction are as follows: Fuzzy input variables: Determine the input variables associated with nonlinear and fuzzy boundary conditions, including the sediment texture change rate, suction pressure fluctuation amplitude, and discharge flow deviation ratio; divide the fuzzy subsets of each input variable based on expert experience and historical fault data, and set membership functions for each subset, including triangular and trapezoidal functions; collect the values ​​of these input variables in real time, calculate the degree to which they belong to each fuzzy subset through the membership function, and convert the input quantity into fuzzy language variables; Construction and reasoning of fuzzy rule base: Based on the experience of dredger operation and maintenance and mud pump control, fuzzy rules are summarized and stored in the fuzzy rule base. After the input variables are fuzzified, the fuzzy rule base is used to match the rules using the reasoning mechanism of Mamdani reasoning method and Sugeno reasoning method to obtain the fuzzy control conclusion, that is, a series of fuzzy outputs, which describe the adjustment direction and amplitude of the control action. Defuzzify the output control quantity: Use the center of gravity method to calculate the weighted center position according to the fuzzy output membership distribution to determine the final precise control quantity; the output control command is sent to the energy-saving execution module to drive the mud pump to operate.

4. The mud pump control system for river management according to claim 1, characterized in that: The specific operation steps of the energy-saving execution module are as follows: The permanent magnet synchronous vector control variable frequency motor is used to change the speed according to the instructions of the centralized control module, adapt to the flow and head required by the actual working conditions, and reduce unnecessary energy consumption; the built-in heat dissipation system automatically adjusts the heat dissipation wind speed according to the motor temperature, further saving energy and increasing efficiency; Regulating valve group: The regulating valve is driven by an electric actuator; the size of the inlet and outlet valves is adjusted according to the mud discharge pressure and flow feedback, and the motor is coordinated to optimize the suction and discharge pressure distribution of the mud pump to reduce the backflow and throttling losses; the actuator has a power-off self-holding function, which maintains the current valve state in the event of an accidental power failure to prevent equipment damage caused by sudden changes in working conditions; Feedback correction: Feedback correction is performed on the mud pump by collecting and comprehensively analyzing the adjusted feedback parameters.

5. The mud pump control system for river management according to claim 4, characterized in that: The process of feedback correction of the energy-saving execution module is as follows: Feedback parameters include: Flow parameter, set the actual flow value to The target flow rate is , flow stability is measured by flow standard deviation Indicates the measurement value of flow parameters Calculated by the following formula: in, and are the maximum and minimum flow ranges, respectively. and are the maximum and minimum ranges of the flow standard deviation, respectively; Head parameter, assuming the actual head is , the target lift is , the head-flow matching is expressed by the matching coefficient of the two , the head value that measures the head parameter Calculated as: in, and They are the maximum and minimum ranges of lift respectively; Energy consumption parameter standardization: Assume that the motor power consumption is , the power before adjustment is The total energy consumption of the system is , the total energy consumption before adjustment is , the consumption balance value of energy consumption parameters Calculated by: in, and are the maximum and minimum ranges of motor power, and are the maximum and minimum ranges of total energy consumption respectively; Pressure parameters: Assume the suction pressure is , the mud discharge pressure is , adjust the suction pressure before , adjust the front mud pressure to , the suction and discharge pressure difference is , adjust the front suction and discharge pressure difference to , the pressure balance value that measures the pressure parameter Calculated as: in, and They are the maximum and minimum ranges of the suction and discharge mud pressure, the suction and discharge mud pressure, and the difference between the suction and discharge pressures; According to the working characteristics and actual needs of the dredger mud pump, a weight is assigned to each feedback parameter, and the flow parameter weight, head parameter weight, energy consumption parameter weight and pressure parameter weight are recorded as ; Then the obtained measurement value , Yang Heng value , consumption balance value , pressure balance value After normalization, the following formula is entered: To obtain the comprehensive evaluation value V; The obtained comprehensive evaluation value V is then compared with several preset threshold intervals, which correspond to different adjustment ranges of the adjustment parameters, including the adjustment values ​​of the valve opening and the motor speed. When the threshold interval to which the comprehensive evaluation value V belongs is determined, the adjustment range required for re-adjustment according to the adjustment effect is determined. Optimization is achieved based on actual conditions and equipment characteristics. After adjustment, feedback parameters are continued to be collected, and the quantification and correction process is repeated to achieve dynamic optimization and adjustment of the mud pump system.

6. The mud pump control system for river management according to claim 1, characterized in that: The execution process of the control parameter recording module is as follows: Continuously collect and store the operation data of the mud pump throughout its life cycle, covering information on different engineering geology, climate conditions, and operation duration; based on the deep learning algorithm, regularly train and optimize the built-in control model to enable autonomous learning of the best control strategy. The process is as follows: It is integrated with the sensing module to capture various physical parameters of the mud pump in real time, including motor speed, torque, pump body temperature, inlet and outlet pressure, valve opening, and synchronously collect environmental data of the operation site, including water depth, water flow speed, wind direction and wind force information at different times; and it is associated with the dredging ship positioning system data to record the dredging location coordinates, and combined with the geographic information system data to clarify the geological type and soil composition information of the area; these data are continuously accumulated to build a mud pump operation database; In the data collection link, multiple verification and error correction mechanisms are built in. When sensor anomalies, data transmission interruptions, or data values ​​outside the reasonable physical range are found, backup collection plans or repair algorithms are activated to ensure data integrity and accuracy. At the same time, the collected raw data is preliminarily screened to remove erroneous and duplicated data points, reducing the subsequent storage and computing burden. A distributed database architecture is used to store mud pump operation data in a structured manner according to time series, geographical area, and working condition type. To facilitate query and retrieval, an index system is established to locate data subsets of operation periods and dredging locations based on hash indexes. Inverted indexes are used to associate control parameter combinations corresponding to the same dredging effect under different working conditions for subsequent data mining and analysis. Analyze the operation duration and dredging effect related parameters for each dredging area to determine the optimal control parameters.

7. The mud pump control system for river management according to claim 6, characterized in that: The specific operation steps for determining the optimal control parameters in the control parameter recording module are as follows: Through a comprehensive assessment of rating parameters, the evaluation parameters include: Dredging efficiency: includes the dredging volume per unit time and the rate of change of dredging depth. The dredging volume per unit time is quantified by calculating the volume of silt delivered by the dredger pump within a preset time. Specifically, the flow data is obtained through the flow sensor on the sludge discharge pipeline, and combined with the measured value of silt concentration, it is calculated according to the formula: dredging volume = flow rate × silt concentration × time. The rate of change of dredging depth uses the depth measuring equipment on the ship to record the dredging depth at different times, and the rate of change of depth is calculated by the formula: depth change rate = (current depth - initial depth) / operation time. After the calculated dredging volume and depth change rate are normalized, the dredging volume and depth change rate are used as the two right-angled sides of the right triangle respectively, and the other side of the right triangle is connected. A triangular pyramid model is established with the preset correction factor as the height, and the surface area of ​​the triangular pyramid model is calculated, which is recorded as the efficiency judgment value. Energy consumption parameters: Energy consumption per unit dredging volume, through the formula: Energy consumption per unit dredging volume = total energy consumption / dredging volume, where the total energy consumption is accumulated through the power monitoring device on the motor and other energy-consuming equipment; Energy consumption stability, through the statistical fluctuation of energy consumption during the operation and the calculation of the standard deviation of energy consumption data for quantitative measurement; The energy consumption per unit dredging volume and the standard deviation of energy consumption data are recorded as dh and df respectively, and the normalized processing is substituted into the following formula: To obtain the energy consumption evaluation value PO, where It is the correction index of the energy consumption assessment value; Mud pump operating status parameters: including pump pressure stability and motor load rate. The pump pressure stability is evaluated by monitoring the mud suction pressure and mud discharge pressure through the pressure sensor installed at the inlet and outlet of the mud pump, and calculating the pressure fluctuation standard deviation; the motor load rate is calculated by the formula: motor load rate = actual power / rated power; then the obtained pressure fluctuation standard deviation and motor load rate are recorded as yb and fz, and after normalization, they are entered into the following formula: To obtain the operation evaluation value PTY, where e is a constant; The obtained efficiency judgment value YP, energy consumption evaluation value PO and operation evaluation value PTY are normalized and substituted into the following formula: To obtain the comprehensive evaluation value ZJH, They are respectively the preset weight coefficients of the efficiency judgment value YP, the energy consumption evaluation value PO and the operation evaluation value PTY; The comprehensive evaluation values ​​ZJH calculated from different control parameters of each dredging area are sorted by size, and the control parameter with the largest comprehensive evaluation value ZJH is selected as the optimal control parameter of the dredging area and stored in matching with the specific location of the dredging area; when dredging operations are subsequently performed in the dredging area, the optimal control parameter is directly called to control the mud pump.

8. The mud pump control system for river management according to claim 1, characterized in that: The execution steps of the perception module are as follows: Multi-sensor unit: A negative pressure sensor is installed at the suction end of the mud pump to monitor the suction pressure; a fiber Bragg grating temperature and vibration composite sensor is installed at the main shaft of the pump body to simultaneously monitor the shaft temperature, vibration frequency and amplitude; an ultrasonic concentration sensor and an electromagnetic flow sensor are used in the mud discharge pipeline to grasp the concentration and flow of discharged mud in real time, laying a solid data foundation for the scientific adjustment of subsequent control strategies; and temperature and humidity sensors and dust sensors are deployed in the surrounding environment of the mud pump to obtain the potential impact of environmental factors on equipment operation; Data preprocessing and transmission: The data from each sensor is first processed by the built-in microprocessor for preliminary noise reduction and filtering to eliminate invalid interference data and improve data accuracy; The processed data is then transmitted to the centralized control module via the wireless transmission module to ensure data real-time and integrity.

9. A control method for a mud pump control system for river management according to any one of claims 1 to 8, characterized in that: The following steps are involved: S1: Multiple sensors are deployed at different parts of the mud pump to collect data. After noise reduction and filtering by the microprocessor, the data is transmitted to the centralized control module in real time by the wireless transmission module, providing the data foundation for the system, covering pressure, temperature, concentration, flow and environmental information; S2: The multi-core processor serves as the data processing center, integrating model-based predictive control and fuzzy logic control algorithms; the model-based predictive control algorithm dynamically optimizes the control sequence according to the mud pump model and working condition planning; the fuzzy logic control algorithm resolves the problem of nonlinear working conditions and outputs instructions. The two work together with the human-computer interaction interface to achieve automatic and manual intervention; S3: The permanent magnet synchronous vector variable frequency motor can adjust speed according to command to save energy and optimize heat dissipation. The regulating valve can coordinate with the motor to accurately control the pressure distribution according to the feedback of mud discharge pressure and flow. The actuator can be self-stabilized when power is off. The motor speed and valve opening can be dynamically optimized by quantitative analysis of flow, head, energy consumption and pressure parameter feedback. S4: Comprehensively integrates system data, performs multiple verification and error correction, and performs structured storage after screening; Based on deep learning mining and analysis, the dredging efficiency, energy consumption, and operating status parameters are comprehensively considered to lock the optimal control parameters of the area for matching and storage, which can be used directly during dredging to improve efficiency and ensure quality.

Images