Multi-mode adaptive underwater thruster and control method thereof

Abstract

The present invention relates to a multi-modal adaptive underwater thruster and a control method thereof. The multi-modal adaptive underwater thruster comprises: an information acquisition module, which includes a sonar sensor, a magnetic sensor, an inertial measurement unit, and a water pressure sensor; a data analysis module, which receives multi-source data from the information acquisition module and generates a unified environmental state model through a multi-source information fusion algorithm; a mode switching module, which calculates the risk level of the current operating state based on a preset comprehensive evaluation index and selects a corresponding operating mode according to the risk level; a power regulation module, which adjusts the power output characteristics of the thruster according to the selected operating mode; and a redundant fault-tolerant module, which is configured with a backup sensor group and switching logic. When the main sensor group is interfered with or fails, the backup sensor group is automatically enabled and the environmental state model is recalculated.

Description

Technical Field

[0001] The present invention relates to the field of underwater vehicles and propulsion technology, and in particular to a multi-mode adaptive underwater propeller and a control method thereof. Background Art

[0002] With the growing demand for marine resource development, marine scientific research, underwater environmental monitoring, and national defense security, underwater propulsion systems (AUVs), including automated underwater vehicles (AUVs), revolving vehicles (ROVs), and underwater gliders, are playing an increasingly important role in various underwater missions. These tasks encompass a wide range of areas, including seafloor topography mapping, pipeline inspection, underwater archaeology, shipwreck search, hydrographic data collection, aquaculture monitoring, and underwater structure installation and maintenance. Underwater propulsion systems are used in underwater vehicles such as submarines, unmanned underwater vehicles (UUVs), and underwater robots (AUVs), providing power for their movement through the water. As the core power unit of underwater vehicles, the evolution of underwater propulsion technology and the expansion of its application scenarios are profoundly impacting the development of ocean exploration, military defense, and civilian applications.

[0003] The underwater environment is complex and has many influencing factors. Ensuring the reasonable switching of underwater thrusters between different modes is an important prerequisite for their efficient completion of tasks. Current control modes are usually set independently based on the operating tasks or underwater environments. For example, the energy-saving mode is used by default in the exploration mode to reduce the frequency of sensor use or extend the information collection interval, thereby reducing energy consumption; however, the underwater environment changes significantly in dynamic terms. When the thruster enters an area with turbulent water flow or dense obstacles, a fast-response vector propulsion mode is required. In this process, there are the following limitations: electromagnetic interference, water pressure changes, water flow noise and other factors in the underwater environment may affect the accuracy of the intelligent control system's perception of environmental information and task requirements, thereby leading to errors in propulsion mode switching and affecting operational efficiency and safety; in addition, the existing technology lacks a clear logical basis when judging the mode switching conditions, which may lead to inaccurate switching timing or failure to effectively verify the environmental status after switching, further increasing the risk of misoperation. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a multi-modal adaptive underwater thruster and control method thereof, designed to resolve conflicts between the operational tasks and the control modes independently set for the underwater environment. By integrating multi-source sensor data, constructing an anti-interference processing mechanism, and designing indicator-driven mode switching logic, this system achieves accurate perception and efficient adaptation to complex and dynamic underwater environments. This technical solution aims to enhance the underwater thruster's autonomous decision-making capabilities under different operating conditions, reduce the risk of misoperation, and optimize energy consumption and operational efficiency.

[0005] The information acquisition module includes a sonar sensor, a magnetic sensor, an inertial measurement unit, and a water pressure sensor. The data analysis module receives multi-source data and generates an environmental state model through a multi-source information fusion algorithm based on Kalman filtering. The mode switching module calculates the risk level and switches the mode based on a comprehensive evaluation index including water flow disturbance intensity, obstacle density, and attitude stability. The power regulation module adjusts power parameters such as thrust size and direction adjustment rate according to the mode. The redundant fault-tolerant module is configured with a backup sensor group and automatically switches when the health status value of the main sensor group exceeds the threshold.

[0006] In a first aspect, the present invention provides a multi-mode adaptive underwater thruster, comprising:

[0007] An information acquisition module, comprising a main sensor group including a sonar sensor, a magnetic sensor, an inertial measurement unit, and a water pressure sensor, for respectively acquiring sonar echo signals, magnetic field strength, inertial motion parameters, and water pressure distribution data;

[0008] A data analysis module receives multi-source data from the information acquisition module and generates a unified environmental state model through a multi-source information fusion algorithm;

[0009] A mode switching module, which calculates the risk level of the current operating state based on a preset comprehensive evaluation index and selects a corresponding operating mode according to the risk level;

[0010] a power regulation module, the power regulation module adjusting the power output characteristics of the propeller according to the selected operating mode;

[0011] The redundant fault-tolerant module is configured with a backup sensor group and switching logic. When the main sensor group is disturbed or fails, the backup sensor group is automatically enabled and the environmental state model is recalculated.

[0012] In an optional embodiment, the execution logic of the multi-source information fusion algorithm includes: receiving obstacle distance information from the sonar sensor, receiving magnetic field change values ​​from the magnetic sensor, receiving attitude angle change rate and acceleration information from the inertial measurement unit, receiving pressure values ​​from the water pressure sensor, and then assigning corresponding weight coefficients according to the sensor type, inputting the weighted data into the Kalman filter for noise reduction and correction, and then calculating the fused environmental state value and generating an environmental state model.

[0013] In an optional embodiment, the environmental state model includes water flow disturbance intensity, obstacle density, and propeller attitude stability parameters, which serve as input basis for the subsequent mode switching module.

[0014] In an optional embodiment, the switching logic of the mode switching module includes: determining whether the comprehensive evaluation index exceeds a preset threshold, and if so, switching to the fast response mode; otherwise, maintaining the current mode;

[0015] After the switch is completed, the comprehensive evaluation index is recalculated and compared with the index before the switch to verify the switching effect; if the newly calculated R value is more than 20% lower than before the switch, the switch is confirmed to be successful; otherwise, the environmental status is re-evaluated.

[0016] In an optional embodiment, the power regulation module adjusts the power output characteristics of the propeller according to the selected operating mode, including thrust magnitude, direction adjustment rate, and steering angle range.

[0017] In an optional embodiment, the adjustment of the power output characteristics is based on a preset dynamic model, combined with key parameters in the current environmental state model for real-time calculation, and the adjusted power output parameters are transmitted to the propulsion device for execution.

[0018] In an optional embodiment, the redundant fault-tolerant module is configured with a backup sensor group and switching logic. When the health status value exceeds a preset threshold, the switching logic is triggered, the backup sensor group is automatically enabled and the environmental status model is recalculated. The redundant fault-tolerant module feeds back the health status monitoring results to the data analysis module so as to update the environmental status model in a timely manner.

[0019] In an optional embodiment, the sonar sensor is installed in the center of the front end housing of the thruster to detect the distance information of surrounding obstacles; the magnetic sensors are distributed on the housings on both sides of the thruster to sense the changes in the underwater magnetic field; the inertial measurement unit is fixed at the center position inside the thruster to obtain the attitude angle change rate and acceleration; the water pressure sensor is embedded in the bottom housing of the thruster to measure the pressure value at the depth.

[0020] In a second aspect, the present invention further provides a multi-modal adaptive underwater thruster control method, which is applied to a multi-modal adaptive underwater thruster and includes the following steps:

[0021] The information acquisition module acquires sonar echo signals, magnetic field strength, inertial motion parameters and water pressure distribution data in real time;

[0022] The data analysis module receives multi-source data from the information acquisition module and generates a unified environmental state model through a multi-source information fusion algorithm;

[0023] The mode switching module calculates the risk level of the current operating state based on the comprehensive evaluation indicators and selects the corresponding operating mode according to the risk level;

[0024] The power regulation module adjusts the power output characteristics of the propeller according to the selected operating mode;

[0025] Redundant fault-tolerant modules monitor the health of sensors and trigger switchover logic when necessary.

[0026] In an optional embodiment, an update strategy based on dynamic changes in the environment is further included, and the update strategy includes:

[0027] Calculate the data acquisition frequency adjustment coefficient based on the water velocity change rate and obstacle distance;

[0028] The multi-source information fusion algorithm, comprehensive evaluation index calculation, and mode switching logic are re-executed based on the adjustment coefficient.

[0029] Beneficial effects of the present invention:

[0030] By fusing multi-source sensor data to generate an environmental state model, mode switching is achieved based on comprehensive evaluation indicators, and power output characteristics are dynamically adjusted. It also has sensor health monitoring and redundant fault tolerance capabilities, which can effectively cope with complex underwater environmental challenges, improve the thruster's autonomous decision-making ability, operational efficiency and anti-interference performance, while reducing the risk of misoperation and energy waste, and is suitable for a variety of dynamic underwater operation scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a schematic diagram of the overall structure of the multi-modal adaptive underwater thruster of the present invention, showing the layout relationship of the information acquisition module, data analysis module, mode switching module, power regulation module and redundant fault-tolerant module.

[0032] Figure 2 This is a working principle diagram of the information acquisition module, illustrating the collection process and flow of sonar echo signals, magnetic field strength, inertial motion parameters, and water pressure distribution data.

[0033] Figure 3 This is a flowchart of the data analysis module, showing the process of multi-source information fusion algorithm to reduce noise and correct sensor data and generate a unified environmental state model.

[0034] Figure 4 This is a logical diagram of the mode switching module, which describes the specific processes of comprehensive evaluation index calculation, risk level judgment, and operation mode switching.

[0035] Figure 5 This is a schematic diagram of the health status monitoring mechanism of the redundant fault-tolerant module, showing the calculation method of the sensor health status value and the switching logic trigger conditions.

[0036] The accompanying drawings are numbered as follows:

[0037] 1. Information acquisition module; 2. Data analysis module; 3. Mode switching module; 4. Power regulation module; 5. Redundant fault-tolerant module; 6. Sonar sensor; 7. Magnetic sensor; 8. Inertial measurement unit; 9. Water pressure sensor. DETAILED DESCRIPTION

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0039] It should be noted that when a component is referred to as being "fixed to" another component, it may be directly on the other component or there may also be a central component. When a component is considered to be "connected to" another component, it may be directly connected to the other component or there may also be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may also be a central component. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0041] The present invention proposes a multi-mode adaptive underwater thruster, such as Figure 1 As shown, including:

[0042] An information acquisition module 1 includes a main sensor group, which includes a sonar sensor 6, a magnetic sensor 7, an inertial measurement unit 8, and a water pressure sensor 9, which are respectively used to obtain sonar echo signals, magnetic field strength, inertial motion parameters, and water pressure distribution data;

[0043] Data analysis module 2, the data analysis module 2 receives multi-source data from the information acquisition module 1 and generates a unified environmental state model through a multi-source information fusion algorithm. The multi-source information fusion algorithm adopts a weighted Kalman fusion method, and its execution logic is as follows: first, the initial weight is assigned according to the sensor accuracy (sonar 0.3, magnetism 0.25, inertia 0.25, water pressure 0.2). When the sensor's measurement relative error rate is greater than 5%, the weight is reduced by 0.05. It is dynamically adjusted every 10 minutes based on the latest error data. The weighted data is then input into the Kalman filter, where the process noise covariance Q is set to 0.01 (based on the power spectrum density test results of underwater electromagnetic interference. When the interference intensity is 100μT, this value can effectively suppress noise), and the measurement noise covariance R is set to 0.05 (determined based on the experiment of the influence of water flow noise on sensor output). Noise reduction and correction are performed, and finally the fused environmental state value is calculated using the environmental state value formula. .

[0044] .

[0045] The execution logic of the multi-source information fusion algorithm includes: receiving obstacle distance information from the sonar sensor 6, receiving magnetic field change values ​​from the magnetic sensor 7, receiving attitude angle change rate and acceleration information from the inertial measurement unit 8, receiving pressure values ​​from the water pressure sensor 9, and then assigning corresponding weight coefficients according to the sensor type and accuracy. , The dynamic adjustment range is 0.2-0.3, the adjustment step is 0.05, and the adjustment basis is the measurement error rate of the sensor. In this application, the measurement error rate of the sensor is dynamically adjusted every 10 minutes. The weighted data is input into the Kalman filter, the process noise covariance is set to 0.01, and the measurement noise covariance is set to 0.05 for noise reduction and correction. The parameter setting is based on the statistical characteristics of electromagnetic interference and water flow noise in the underwater environment, that is, it is obtained by statistical analysis of a large amount of underwater environment monitoring data, which can effectively suppress the influence of electromagnetic interference and water flow noise. Then, the fused environmental state value is calculated and an environmental state model is generated. The environmental state model includes water disturbance intensity F (unit: m / s², calculated by the rate of change of water velocity), obstacle density D (unit: number / m³, based on sonar echo signal analysis) and thruster attitude stability parameter P (based on the rate of change of Euler angle, unit: rad / s), which serves as the input basis for the subsequent mode switching module 3.

[0046] Mode switching module 3, the mode switching module 3 calculates the risk level of the current operating state based on a preset comprehensive evaluation index R, the comprehensive evaluation index In this implementation, the risk level is divided into three levels: low (R<0.4), medium (0.4≤R<0.7), and high (R≥0.7), namely the weight coefficient =0.4, =0.3, =0.3, F is the water disturbance intensity, D is the obstacle density, P is the thruster attitude stability parameter, and the level classification is based on the analytic hierarchy process (AHP). The underwater test data of the group verified that the weight distribution can make the risk level judgment accuracy reach 92%, ensuring the reasonable evaluation of water flow disturbance, obstacle distribution and thruster attitude stability, and selecting the corresponding operating mode according to the risk level. When the risk level is high, it switches to the fast response mode (the thrust adjustment rate is increased by 50%, the direction adjustment rate is increased by 40%, and the steering angle range is expanded by 30%, which is suitable for areas with turbulent water flow or dense obstacles). When the risk level is medium, the standard mode is maintained. When the risk level is low, it switches to the energy-saving mode. The switching logic of the mode switching module 3 includes: judging whether the comprehensive evaluation index R exceeds the preset threshold R_th (R_th=0.7). If so, switch to the fast response mode; otherwise, maintain the current mode; after the switching is completed, recalculate the comprehensive evaluation index R and compare it with the index before the switching. If the newly calculated R value is lower than that before the switching by more than 20%, the switching is confirmed to be successful; otherwise, re-evaluate the environmental status;

[0047] Power adjustment module 4, which adjusts the power output characteristics of the propeller according to the selected operating mode, including thrust size, direction adjustment rate and steering angle range. The adjustment of the power output characteristics is based on the preset dynamic model. , where T represents the thrust of the propeller (unit: N), m represents the mass of the propeller (unit: kg), represents the target acceleration (unit: m / s², generated by the path planning algorithm, and the maximum value does not exceed 80% of the maximum acceleration of the thruster), k represents the water flow influence coefficient (the value range is 0.5-1.0, and is set in sections according to the water flow velocity: when the water flow velocity <0.5m / s, k=0.5; when 0.5m / s≤ <1.0m / s, k=0.7; when ≥1.0m / s, k=1.0, this segment setting is based on fluid mechanics test data). Indicates the water flow velocity (unit: m / s), combines the key parameters in the current environmental state model for real-time calculation, and transmits the adjusted power output parameters to the propulsion device for execution;

[0048] Redundant fault-tolerant module 5, which is equipped with a backup sensor group and switching logic. When the health status value H exceeds the preset threshold H_th (H_th=0.3), the switching logic is triggered. The calculation formula of the health status value H is H=ΔS / , where ΔS represents the maximum fluctuation amplitude of sensor data within a continuous 10-second time window, The 10-second time window represents the average value of sensor data within the same time window. The selection of the 10-second time window is based on the time constant of changes in underwater environmental parameters. When the switching logic is triggered, the backup sensor group is automatically activated and the environmental state model is recalculated. The redundant fault-tolerant module 5 feeds back the health status monitoring results to the data analysis module 2 for timely updating of the environmental state model. The sonar sensor 6 is installed in the center of the front housing of the thruster. It uses an ultrasonic probe with a frequency of 200kHz and can detect obstacles within a range of 0.1-50m. The magnetic sensors 7 are distributed on both sides of the thruster housing and have an accuracy of 1nT. They are used to sense abnormal changes in the geomagnetic field. The inertial measurement unit 8 is fixed in the center of the thruster and contains a three-axis gyroscope (accuracy of 0.1° / h) and a three-axis accelerometer (accuracy of 0.01m / s²). The water pressure sensor 9 is embedded in the bottom housing of the thruster and has a measurement range of 0-1000m and an accuracy of 0.1% FS.

[0049] like Figure 2 In the working principle diagram of the information acquisition module shown, the sonar sensor 6 transmits ultrasonic signals and receives echo signals, converts the echo signals into electrical signals and transmits them to the data analysis module 2. The magnetic sensor 7 generates magnetic intensity signals by sensing magnetic field changes and transmits them to the data analysis module 2. The inertial measurement unit 8 detects the attitude angle change rate and acceleration of the propeller in real time through the built-in gyroscope and accelerometer and sends the data to the data analysis module 2. The water pressure sensor 9 generates a pressure signal according to the external water pressure change and transmits it to the data analysis module 2.

[0050] After receiving the multi-source data, the data analysis module 2 processes it according to the preset multi-source information fusion algorithm. First, it assigns a weight coefficient to each type of sensor data. The weight coefficient is dynamically adjusted according to the sensor accuracy and reliability, and then the fused environmental state value is calculated through the environmental state value formula , the calculation formula of the environmental state value formula is:

[0051]

[0052] in Indicates the The raw measurement values ​​of sensors such as (such as obstacle distance of sonar, magnetic field strength of magnetism, etc.), is the number of sensor types, namely, sonar sensor, magnetic sensor, inertial measurement unit, and water pressure sensor. is the weight coefficient after dynamic adjustment, the numerator It is a summation operation, which takes the weight coefficient of each type of sensor as The corresponding original measurement value Multiplying them together and then adding all these products together has the effect of weighting the raw measurements by the weight of each sensor, the denominator Is a summation operation that adds the weight coefficients of all sensors Add, and then normalize the weighted sum of the molecules to avoid the deviation of the results caused by the different sums of the weight coefficients. Dynamically adjust according to the accuracy and reliability of the sensor;

[0053] The water disturbance intensity F (unit: m / s²) is obtained by calculating the average of the absolute values ​​of the first-order differences of the water velocity in the past 10 seconds, that is, , =1 second;

[0054] Obstacle density D (unit: number / m³) is defined as the number of obstacles with a size ≥ 10 cm divided by the volume of a spherical area with a radius of 5 m centered on the propeller. The obstacle size is identified by the intensity and width of the sonar echo signal using the Hough transform algorithm.

[0055] The thruster attitude stability parameter P (unit: rad / s) is the root mean square value of the rate of change of pitch angle, yaw angle and roll angle, that is, in 、 、 are the three-axis angular velocities respectively;

[0056] During this process, the Kalman filter is used to denoise and correct the received raw data to reduce the impact of electromagnetic interference and water flow noise, and finally generate a unified environmental state model.

[0057] like Figure 3In the flowchart of the data analysis module shown, the specific execution process of the multi-source information fusion algorithm includes: first, obstacle distance information is received from the sonar sensor 6, magnetic field change values ​​are received from the magnetic sensor 7, attitude angle change rate and acceleration information are received from the inertial measurement unit 8, and pressure values ​​are received from the water pressure sensor 9. Then, various types of data are preliminarily processed, including removing outliers and filling missing values. Then, corresponding weight coefficients are assigned according to the sensor type and accuracy (for example, the initial weight coefficient of the sonar sensor is set to 0.3 due to its high accuracy. If its measurement error rate exceeds 5%, the weight coefficient is reduced by 0.05). The weighted data is input into the Kalman filter (process noise covariance Q is set to 0.01, and measurement noise covariance R is set to 0.05) for noise reduction and correction.

[0058] The environmental state model is generated. This model includes key parameters such as water disturbance intensity F, obstacle density D, and thruster attitude stability P. These parameters serve as input for the subsequent mode switching module 3.

[0059] like Figure 4 In the logic diagram of the mode switching module shown, the calculation of the comprehensive evaluation index R is R=0.4F+0.3D+0.3P. The mode switching module 3 judges the risk level of the current operating state based on the calculated comprehensive evaluation index R. When R exceeds the preset threshold, the operating mode switching logic is triggered and switched to the fast response mode. After the switch is completed, the comprehensive evaluation index R is recalculated and compared with the comprehensive evaluation index R before the switch. If the newly calculated R value is lower than that before the switch by more than 20%, the switch is confirmed to be successful. Otherwise, the environmental state is re-evaluated. The mode switching module 3 transmits the selected operating mode information to the power regulation module 4 through the data bus, ensuring information interaction and collaborative work between different modules in the system. The power regulation module 4 adjusts the power output or other related parameters accordingly based on the received operating mode information. The adjustment is based on the dynamic model Target acceleration Generated by the path planning algorithm, the maximum does not exceed 80% of the maximum acceleration of the propeller. The water flow influence coefficient k is set according to the water flow velocity: when the water flow velocity <0.5m / s, k=0.5; when 0.5m / s< <1.0m / s, k=0.7; when When ≥1.0m / s, k=1.0.

[0060] During the mission, the data acquisition frequency adjustment coefficient is calculated based on the water flow velocity change rate and obstacle distance. ,in Take the average value of the first 10% maximum flow rate values ​​recorded during the operation of the equipment, Take the average of the first 10% minimum distance values ​​recorded during the operation of the equipment. For example, if the historical maximum water flow velocity average is 1.5m / s, the historical minimum obstacle distance average is 2m, the current water flow velocity is 1.0m / s, and the nearest obstacle distance is 1m, then the data collection frequency adjustment coefficient =0.571, at this time the acquisition frequency is increased by 50% to ensure the real-time and accuracy of the environmental state model, and then the power regulation module 4 transmits the adjusted power output parameters to the propulsion device for execution through the control signal line.

[0061] like Figure 5 In the diagram of the health status monitoring mechanism of the redundant fault-tolerant module shown, the redundant fault-tolerant module 5 is configured with a backup sensor group and switching logic. The main sensor group and the backup sensor group are connected to the redundant fault-tolerant module 5 via independent monitoring lines. The health status monitoring result is obtained by comparing the data fluctuation amplitude within the continuous time window. The calculation formula of the health status value H is:

[0062]

[0063] Indicates the maximum fluctuation amplitude of sensor data within a continuous 10-second time window. It represents the average value of sensor data in the same time window. When the health status value H exceeds the preset threshold, the switching logic is triggered.

[0064] In actual application scenarios, such as submarine pipeline inspection tasks, after the thruster is started, the information acquisition module 1 begins to acquire sonar echo signals, magnetic field strength, inertial motion parameters and water pressure distribution data in real time. After receiving these data, the data analysis module 2 generates a unified environmental state model through a multi-source information fusion algorithm. When dense obstacles are detected ahead and the water flow disturbance is large, the mode switching module 3 calculates the comprehensive evaluation index R and determines whether it is necessary to switch to the fast response mode. If switching is required, the switching instruction is passed to the power adjustment module 4. The power adjustment module 4 adjusts the thrust size and direction according to the new operating mode to avoid obstacles and maintain a stable posture. At the same time, the redundant fault-tolerant module 5 continuously monitors the health status of each sensor group. If the main sensor group is found to have a fault, it immediately switches to the backup sensor group and recalculates the environmental state model to ensure the normal operation of the thruster. During the execution of the task, the data acquisition frequency adjustment coefficient is calculated according to the water flow velocity change rate and the obstacle distance. , The calculation formula is as follows:

[0065]

[0066] in, Indicates the water flow rate, Indicates the distance to the nearest obstacle. Indicates the maximum value of water flow velocity, Indicates the maximum value of the obstacle distance. In this application, Take the historical maximum flow rate in the operating area (take the average of the first 10% maximum flow rate values ​​recorded during the equipment operation, and the time range is the entire operating cycle), Indicates the historical minimum obstacle distance (the average of the first 10% minimum distance values ​​recorded during the operation of the equipment, the time range is the entire operation cycle), based on the adjustment coefficient Re-execute the multi-source information fusion algorithm, comprehensive evaluation index calculation and mode switching logic, It is positively correlated with the acquisition frequency. >0.5, the acquisition frequency increases by 50%; when 0.3≤ ≤0.5, the acquisition frequency is increased by 20%, <0.3, the acquisition frequency remains unchanged.

[0067] In order to better enable relevant personnel in this technical field to fully understand and implement the present invention, the specific implementation principles of the present invention are supplemented below with reference to specific application scenarios:

[0068] In actual application scenarios, such as submarine pipeline inspection tasks, after the thruster is started, the information acquisition module 1 begins to obtain sonar echo signals, magnetic field strength, inertial motion parameters and water pressure distribution data in real time. After receiving these data, the data analysis module 2 generates a unified environmental state model through a multi-source information fusion algorithm. When dense obstacles are detected ahead and the water flow disturbance is large, the mode switching module 3 calculates the comprehensive evaluation index R=0.4F+0.3D+0.3P. If R≥0.7, it switches to the fast response mode. In this mode, the thrust adjustment rate is increased by 50%, the direction adjustment rate is increased by 40%, and the steering angle range is expanded by 30% to quickly avoid obstacles. At the same time, the redundant fault-tolerant module 5 continuously monitors the health status of each sensor group. If H=ΔS / If ≥0.3, the switching logic is triggered and the backup sensor group is enabled, where ΔS is the maximum fluctuation amplitude of the sensor data within 10 consecutive seconds, and S is the average value within this time period. The 10-second time window can balance the real-time and stability requirements of the data.

[0069] During the mission, the data acquisition frequency adjustment coefficient is calculated based on the water flow velocity change rate and obstacle distance. For example, if the average historical maximum water flow rate is =1.5m / s, the average value of the historical minimum obstacle distance =2m, current water flow velocity =1.0m / s, distance to the nearest obstacle =1m, then =(1.0+1.0) / (1.5+2.0)=0.571>0.5, at this time the acquisition frequency is increased by 50% to ensure the real-time and accuracy of the environmental state model. The power adjustment module 4 is based on the dynamic model Adjust the thrust, where the k value is based on the current water flow rate =1.0m / s is determined as 1.0, the target acceleration Generated by the path planning algorithm, it does not exceed 80% of the maximum acceleration of the thruster, ensuring that the thruster maintains stable operation in complex environments.

[0070] Through the above steps, the thruster can adjust its operating mode in time according to dynamic changes in the environment, avoid obstacles and maintain a stable posture, thereby efficiently completing the submarine pipeline inspection task. This process not only improves the thruster's autonomous decision-making ability, but also significantly reduces the risk of misoperation and optimizes energy consumption and operating efficiency.

[0071] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions based on the principles of the present invention are within the scope of protection of the present invention. It should be noted that improvements and modifications that do not depart from the principles of the present invention are within the scope of protection of the present invention.

Claims

1. A multi-mode adaptive underwater thruster, characterized by: include: An information acquisition module (1), comprising a main sensor group, the main sensor group including a sonar sensor (6), a magnetic sensor (7), an inertial measurement unit (8), and a water pressure sensor (9), for respectively acquiring sonar echo signals, magnetic field strength, inertial motion parameters, and water pressure distribution data; A data analysis module (2), wherein the data analysis module (2) receives multi-source data from the information acquisition module (1) and generates a unified environmental state model through a multi-source information fusion algorithm; A mode switching module (3), wherein the mode switching module (3) calculates the risk level of the current operating state based on a preset comprehensive evaluation index and selects a corresponding operating mode according to the risk level; A power adjustment module (4), wherein the power adjustment module (4) adjusts the power output characteristics of the propeller according to the selected operating mode; A redundant fault-tolerant module (5), wherein the redundant fault-tolerant module (5) is configured with a backup sensor group and a switching logic, and when the main sensor group is disturbed or fails, the backup sensor group is automatically enabled and the environmental state model is recalculated; The execution logic of the multi-source information fusion algorithm includes: receiving obstacle distance information from the sonar sensor (6), receiving magnetic field change values ​​from the magnetic sensor (7), receiving attitude angle change rate and acceleration information from the inertial measurement unit (8), receiving pressure values ​​from the water pressure sensor (9), then assigning corresponding weight coefficients according to the sensor types, inputting the weighted data into the Kalman filter for noise reduction and correction, and then calculating the fused environmental state value and generating an environmental state model; The environmental state model includes water flow disturbance intensity, obstacle density and propeller attitude stability parameters, which serve as the input basis for the subsequent mode switching module (3).

2. The multi-mode adaptive underwater thruster according to claim 1, characterized in that: The mode switching module (3) calculates the risk level of the current operating state based on a preset comprehensive evaluation index, and selects a corresponding operating mode according to the risk level, switching to a quick response mode when the risk level is high, maintaining a standard mode when the risk level is medium, and switching to an energy-saving mode when the risk level is low.

3. The multi-mode adaptive underwater thruster according to claim 2, characterized in that: The switching logic of the mode switching module (3) includes: judging whether the comprehensive evaluation index exceeds a preset threshold value, and if so, switching to a fast response mode; otherwise, maintaining the current mode; After the switch is completed, the comprehensive evaluation index is recalculated and compared with the index before the switch to verify the switch effect; if it is significantly lower, the switch is confirmed to be successful; otherwise, the environmental status is re-evaluated.

4. The multi-mode adaptive underwater thruster according to claim 3, characterized in that: The power adjustment module (4) adjusts the power output characteristics of the propeller according to the selected operation mode, including the thrust magnitude, direction adjustment rate and steering angle range.

5. The multi-mode adaptive underwater thruster according to claim 4, characterized in that: The adjustment of the power output characteristics is based on the preset dynamic model and is calculated in real time in combination with the key parameters in the current environmental state model. The adjusted power output parameters are then transmitted to the propulsion device for execution.

6. The multi-mode adaptive underwater thruster according to claim 1, characterized in that: The redundant fault-tolerant module (5) is configured with a backup sensor group and a switching logic. When the health status value exceeds a preset threshold, the switching logic is triggered, the backup sensor group is automatically enabled, and the environmental state model is recalculated. The redundant fault-tolerant module (5) feeds back the health status monitoring result to the data analysis module (2) so as to update the environmental state model in a timely manner.

7. A multi-mode adaptive underwater thruster control method, applied to the multi-mode adaptive underwater thruster according to any one of claims 1 to 6, characterized in that: The following steps are involved: The information acquisition module (1) acquires sonar echo signals, magnetic field strength, inertial motion parameters and water pressure distribution data in real time; The data analysis module (2) receives multi-source data from the information acquisition module (1) and generates a unified environmental state model through a multi-source information fusion algorithm; The mode switching module (3) calculates the risk level of the current operating state based on the comprehensive evaluation index and selects the corresponding operating mode according to the risk level; The power adjustment module (4) adjusts the power output characteristics of the propeller according to the selected operation mode; The redundant fault-tolerant module (5) monitors the health status of the sensors and triggers the switching logic when necessary.

8. The multi-mode adaptive underwater thruster control method according to claim 7, characterized in that: It also includes an update strategy based on dynamic changes in the environment, which includes: Calculate the data acquisition frequency adjustment coefficient based on the water velocity change rate and obstacle distance; The multi-source information fusion algorithm, comprehensive evaluation index calculation, and mode switching logic are re-executed based on the adjustment coefficient.

Images