Pipeline cleaning robot adaptive control system

Abstract

The present application relates to the technical field of adaptive control, in particular to a pipeline cleaning robot adaptive control system, the system comprises: a fluid sensing module, a path optimization module, a position calibration module, a pressure regulating module, and an effect evaluation module.In the present application, the fluid laminar flow index, turbulence intensity coefficient and backflow probability value are obtained through feature comparison, the flow pattern in the pipeline is mastered, the motion path and cleaning parameters of the robot are dynamically adjusted, the working requirements under different pipeline conditions are adapted, the motion stability and efficiency of the robot in the complex pipeline environment are ensured, the actual motion posture and position of the robot are analyzed in real time and compared with the preset trajectory, the positioning accuracy of the robot is improved, the pressure parameters of the cleaning nozzle and the rotary motor torque compensation value are dynamically adjusted, the accurate control of the cleaning pressure is ensured, the insufficient cleaning position is identified and the cleaning time is adjusted through the comparison of the image sequences before and after the pipeline wall cleaning, and the stable and good cleaning effect is maintained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of adaptive control, and particularly relates to a pipeline cleaning robot adaptive control system. BACKGROUND

[0002] The technical field of adaptive control includes control technology with self-adjusting capability in automatic control systems. In dynamic systems, when system parameters or external environment change, the parameters of the controller are automatically adjusted to maintain the stability of system performance. Adaptive control is applied to scenarios that require handling system uncertainty and changes, including aerospace, robotics, automobiles, and industrial automation. The core content is to obtain system state information in real time and make corresponding adjustments to the controller to ensure that the system can maintain good control effect under changing working conditions.

[0003] Among them, the pipeline cleaning robot adaptive control system refers to a control system for robot operation in response to changes in the environment and task requirements that may occur in the actual application of the pipeline cleaning robot. The technical matters solved by the patent subject mainly include the specific application of adaptive control algorithms in robot cleaning tasks, especially how to cope with the complex fluid environment changes inside the pipeline through adaptive control technology. The system uses sensors to monitor the changes inside the pipeline in real time and adjusts the robot behavior and cleaning parameters dynamically through adaptive algorithms to ensure the stability of the cleaning effect. Specifically, an adaptive control algorithm based on a feedback mechanism is used to accurately control the robot to adapt to the working requirements under different pipeline conditions, and by adjusting parameters such as motion path, cleaning pressure, and speed, the best cleaning effect is achieved.

[0004] The current pipeline cleaning robot is usually composed of a cleaning nozzle, a rotating motor, a driving system, a sensor and the like. When dealing with the complex fluid environment change inside the pipeline, the path control of the traditional pipeline cleaning robot control technology is based on fixed preset parameters and cannot be dynamically adjusted according to the fluid state, bend radius, pipe diameter change and other factors of the pipeline. It is difficult to adapt to the significant change caused by the change of the fluid state in the pipeline due to the change of flow rate, pressure and temperature, resulting in unstable cleaning effect. In a complex environment, the cleaning effect is poor, the control precision of the attitude and position is low, in the bend or narrow area of the pipeline, the robot is easy to deviate from the predetermined path, affecting the cleaning quality, in the pipeline environment with high turbulence intensity or backflow, the robot cannot timely adjust the motion path and cleaning pressure, resulting in uneven cleaning or substandard cleaning effect. There are deficiencies in the robot position calibration and attitude control, lack of real-time feedback and accurate adjustment capability of the actual motion attitude and position of the robot, resulting in positioning deviation and motion instability of the robot in the complex pipeline, lack of effective cleaning effect evaluation mechanism, unable to adjust the cleaning strategy in real time, resulting in incomplete cleaning of some areas, when dealing with complex pipeline environment, it is difficult to ensure the stability and consistency of the cleaning effect, limiting the application in a wider range of scenarios. SUMMARY

[0005] The purpose of the present application is to solve the problems existing in the prior art, and a pipeline cleaning robot adaptive control system is proposed.

[0006] In order to achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows: the pipeline cleaning robot adaptive control system comprises:

[0007] The fluid sensing module monitors the pipeline fluid state, obtains the instantaneous flow rate sequence, dynamic pressure waveform and pipe wall temperature value, calculates the flow rate fluctuation value, pressure gradient value and temperature change value, calculates the fluid laminar flow index, turbulence intensity coefficient and backflow probability value of multiple positions in the pipeline through feature comparison, and obtains the flow pattern coefficient;

[0008] The path optimization module calls the flow pattern coefficient, calculates the path curvature adjustment amount and motion speed by using the turbulence intensity coefficient and backflow probability value in combination with the bend curvature radius and pipe diameter contraction ratio parameters of the pipeline at multiple positions, obtains the bend deceleration ratio and straight pipe segment acceleration threshold, and generates the path trajectory parameters;

[0009] The position calibration module calls the path trajectory parameters, analyzes the actual motion attitude and position of the robot by using the inertial measurement unit and gyroscope, calculates the position offset and angle deviation by comparing with the preset trajectory, obtains the horizontal offset correction amount and attitude compensation angle, generates the position compensation parameters;

[0010] The pressure regulating module calls the position compensation parameter, uses a horizontal offset correction amount, combines a pipe wall contact pressure value collected by a pressure sensor in real time, calculates a difference between an expected value and a measured value of the contact pressure, adjusts a pressure parameter of the cleaning nozzle and a torque compensation value of a rotary motor, and generates a cleaning pressure parameter;

[0011] The effect evaluation module uses an image collection device to compare image sequences before and after pipe wall cleaning based on the cleaning pressure parameter, extracts a residual coverage area proportion and a texture definition difference value, identifies an insufficient cleaning position and adjusts a cleaning time length, and generates a pipeline cleaning operation parameter.

[0012] As a further scheme of the application, the flow mode coefficient includes a fluid laminar flow index, a turbulent flow intensity coefficient and a backflow probability value, the path trajectory parameter includes a robot working path, a curved path driving speed and a straight pipe advancing speed threshold value, the position compensation parameter includes a position offset correction amount, an angle offset correction amount and position offset data, the cleaning pressure parameter includes a cleaning nozzle control parameter and a rotary motor control parameter, and the pipeline cleaning operation parameter includes a residual coverage area proportion, a texture definition difference value and a cleaning time adjustment value.

[0013] As a further scheme of the application, the fluid sensing module includes:

[0014] The feature extraction submodule monitors a pipeline fluid state, acquires an instantaneous flow rate sequence by using a flow rate sensor, acquires a dynamic pressure waveform by using a pressure sensor, acquires a pipe wall temperature value by using a temperature sensor, calculates a flow rate fluctuation value, a pressure gradient value and a temperature change value under a current fluid state, and establishes a fluid state feature vector;

[0015] The feature comparison submodule calls the fluid state feature vector, extracts feature vector data of a plurality of known fluid states, and adopts a formula:

[0016]

[0017] judges the closeness of the current fluid state and the known state, and acquires a feature similarity score;

[0018] wherein S represents the feature similarity score, w i represents the weight of each feature item, X i represents an i-th feature value of the current state, represents an i-th feature value of the known fluid state, and n is the total number of features and i represents an i-th feature item in the feature vector;

[0019] The state calculation sub-module identifies the flow state of the plurality of positions in the pipeline by comparing with a plurality of known fluid states based on the feature similarity score, extracts the fluid laminar flow index, the turbulence intensity coefficient and the backflow probability value corresponding to the flow state, and obtains the flow mode coefficient.

[0020] As a further scheme of the present application, the path optimization module comprises:

[0021] The geometric feature extraction sub-module extracts the bend curvature radius and the pipe diameter contraction ratio parameter of the plurality of positions in the pipeline by using the geometric feature information of the pipeline based on the flow mode coefficient, and obtains the geometric feature analysis result;

[0022] The path adjustment calculation sub-module performs path curvature adjustment calculation based on the geometric feature analysis result, calls the turbulence intensity coefficient and the backflow probability value, combines the bend curvature radius and the pipe diameter contraction ratio, and uses the formula:

[0023]

[0024] to obtain the path curvature adjustment amount and generate the path adjustment parameter;

[0025] wherein C adjust is the path curvature adjustment amount, T curvature is the bend curvature radius, R is the response coefficient of the flow, P shrink is the pipe diameter contraction ratio, and L is the length of the flow path.

[0026] The motion trajectory planning sub-module calculates the motion speed of the robot at the plurality of positions in the pipeline according to the path adjustment parameter and in combination with the flow characteristics, obtains the bend deceleration ratio and the straight pipe segment acceleration threshold, and obtains the path trajectory parameter.

[0027] As a further scheme of the present application, the position calibration module comprises:

[0028] The attitude and position analysis sub-module calls the path trajectory parameter, identifies the actual motion position and attitude of the robot by analyzing the measurement data of the inertial measurement unit and the gyroscope, records the current coordinates and angle of the robot, and obtains the real-time position data of the robot;

[0029] The horizontal offset correction amount calculation sub-module uses the real-time position data of the robot, compares with the preset trajectory according to the actual coordinates of the robot, and uses the formula:

[0030]

[0031] to obtain the horizontal offset correction amount.

[0032] wherein D offset is the horizontal offset correction amount, X actLet X be the robot's actual X coordinate. ide For the preset X coordinate, Y act Y is the robot's actual Y coordinate. ide Preset Y coordinate;

[0033] The posture compensation angle calculation submodule calculates the robot's posture compensation angle based on the horizontal offset correction amount and the robot's actual posture by comparing it with the preset trajectory. It then adjusts the angle difference between the robot and the preset trajectory to generate position compensation parameters.

[0034] As a further aspect of the present invention, the pressure regulating module includes:

[0035] The pressure difference calculation submodule adjusts the deviation between the robot and the preset trajectory based on the position compensation parameters and the robot's real-time horizontal offset correction amount. It also calculates the difference between the measured pressure and the preset expected value by combining the contact pressure value of the pipe wall obtained by the pressure sensor, and obtains the pressure difference data.

[0036] The cleaning pressure adjustment submodule uses the pressure difference data and the formula:

[0037]

[0038] Calculate the adjusted cleaning nozzle pressure, adjust the pressure parameters of the cleaning nozzle, and obtain the pressure parameters of the cleaning nozzle;

[0039] Among them, P adj P is the adjusted cleaning nozzle pressure. des ΔP' is the preset target contact pressure, α is the pressure difference, i.e. the difference between the measured pressure and the target pressure, μ is the fluid viscosity coefficient, and D is the nozzle diameter.

[0040] The rotary motor torque compensation submodule calculates the torque compensation value of the rotary motor based on the pressure parameters of the cleaning nozzle, taking into account the pressure changes required by the cleaning nozzle and the load response characteristics of the motor, and adjusts the motor output to generate cleaning pressure parameters.

[0041] As a further aspect of the present invention, the effect evaluation module includes:

[0042] Based on the cleaning pressure parameters, the image comparison submodule acquires pipe wall images before and after cleaning using an image acquisition device. It then uses image analysis to extract the residue coverage area and texture clarity of multiple regions in the images, generating pipe wall image analysis results.

[0043] The cleaning effect analysis submodule analyzes the residual coverage area and the texture definition in the images before and after cleaning based on the pipe wall image analysis result, calculates the residual coverage area proportion and the texture definition difference value of multiple regions, and adopts the formula:

[0044]

[0045] The cleaning effect of multiple positions is evaluated, and a cleanliness score is calculated.

[0046] Wherein, C tot is the cleanliness score, measuring the cleaning effect, A bf,i' is the residual coverage area of region i' before cleaning, A af,i' is the residual coverage area of region i' after cleaning, T bf,i' is the texture definition of region i' before cleaning, T af,i' is the texture definition of region i' after cleaning, w1 is the weight coefficient of the residual coverage area, w2 is the weight coefficient of the texture definition, N' is the total number of regions divided by the image, and i' is the index of the region in the image.

[0047] The cleaning duration adjustment submodule calls the cleanliness score, identifies the insufficient cleaning position, and adjusts the cleaning duration of the robot to generate the pipeline cleaning operation parameter.

[0048] Compared with the prior art, the advantages and positive effects of the present application are:

[0049] In the present application, the fluid laminar flow index, the turbulent intensity coefficient and the backflow probability value are obtained through feature comparison, the flow pattern in the pipeline is mastered, the motion path and the cleaning parameter of the robot are dynamically adjusted, the working requirements under different pipeline conditions are adapted, it is ensured that the robot can adaptively adjust the motion trajectory according to the flow characteristics in the pipeline, the problem of path deviation of the traditional robot is solved, the actual motion posture and position of the robot are analyzed in real time and compared with the preset trajectory, the positioning accuracy of the robot is improved, it is ensured that the robot always maintains the accurate motion trajectory in the complex pipeline environment, the difference between the expected value and the measured value of the contact pressure value is calculated by combining the contact pressure value collected by the pressure sensor in real time, the pressure parameter of the cleaning nozzle and the torque compensation value of the rotating motor are dynamically adjusted, the accurate control of the cleaning pressure is ensured, the problems of incomplete cleaning or damage caused by excessively high or low pressure are avoided, the comparison of the image sequence before and after the pipe wall cleaning realizes the identification of the insufficient cleaning position and the adjustment of the cleaning duration, the stable cleaning effect is maintained in the complex and changeable pipeline environment, it is ensured that each region can be cleaned with high quality, the efficiency and effect of the pipeline cleaning operation are improved, and the cleaning efficiency and accuracy are improved. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 It is the system flowchart of the present application.

[0051] Figure 2 Flow chart of the fluid sensing module of the present application;

[0052] Figure 3 Flow chart of the path optimization module of the present application;

[0053] Figure 4 Flow chart of the position calibration module of the present application;

[0054] Figure 5 Flow chart of the pressure regulation module of the present application;

[0055] Figure 6 Flow chart of the effect evaluation module of the present application. DETAILED DESCRIPTION

[0056] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0057] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0058] Please refer to Figure 1 The pipeline cleaning robot adaptive control system comprises:

[0059] The fluid sensing module monitors the pipeline fluid state, acquires the instantaneous flow rate sequence, dynamic pressure waveform and pipe wall temperature value, calculates the flow rate fluctuation value, pressure gradient value and temperature change value, calculates the fluid laminar flow index, turbulence intensity coefficient and backflow probability value at multiple positions in the pipeline through feature comparison, and acquires the flow pattern coefficient;

[0060] The path optimization module calls the flow pattern coefficient, utilizes the turbulence intensity coefficient and backflow probability value, combines the bend curvature radius and pipe diameter contraction ratio parameter at multiple positions in the pipeline, calculates the path curvature adjustment amount and movement speed, acquires the bend deceleration ratio and straight pipe segment acceleration threshold, and generates the path trajectory parameter;

[0061] The position calibration module calls the path trajectory parameters, analyzes the actual motion posture and position of the robot by using the inertial measurement unit and the gyroscope, calculates the position offset and the angle deviation by comparing with the preset trajectory, obtains the horizontal offset correction and the posture compensation angle, and generates the position compensation parameters;

[0062] The pressure adjustment module calls the position compensation parameters, calculates the difference between the expected value and the measured value of the contact pressure by using the horizontal offset correction and combining the contact pressure value collected by the pressure sensor in real time, adjusts the pressure parameters of the cleaning nozzle and the torque compensation value of the rotating motor, and generates the cleaning pressure parameters;

[0063] The effect evaluation module generates the pipeline cleaning operation parameters based on the cleaning pressure parameters, uses the image acquisition device, compares the image sequences before and after the pipeline wall cleaning, extracts the residual coverage area ratio and the texture definition difference value, identifies the insufficient cleaning position and adjusts the cleaning time, and generates the pipeline cleaning operation parameters.

[0064] The flow pattern coefficient includes the fluid laminar flow index, the turbulent intensity coefficient, and the backflow probability value. The path trajectory parameters include the robot working path, the curve driving speed, and the straight pipe forward speed threshold. The position compensation parameters include the position offset correction, the angle offset correction, and the position offset data. The cleaning pressure parameters include the cleaning nozzle control parameters and the rotating motor control parameters. The pipeline cleaning operation parameters include the residual coverage area ratio, the texture definition difference value, and the cleaning time adjustment value.

[0065] Please refer to Figure 2 , the fluid perception module includes:

[0066] The feature extraction sub-module monitors the pipeline fluid state, obtains the instantaneous flow rate sequence by using the flow rate sensor, obtains the dynamic pressure waveform by using the pressure sensor, and obtains the pipe wall temperature value by using the temperature sensor. The flow rate fluctuation value, the pressure gradient value, and the temperature change value under the current fluid state are calculated, and the fluid state feature vector is established.

[0067] In the fluid state monitoring, first, the relevant data of the fluid is obtained by the flow rate sensor, the pressure sensor, and the temperature sensor. Assuming that the instantaneous flow rate sequence recorded by the flow rate sensor is [1.2, 1.3, 1.4, 1.2, 1.3] m / s, the dynamic pressure waveform recorded by the pressure sensor is [100, 102, 104, 103, 101] Pa, and the pipe wall temperature of the temperature sensor is [30.1, 30.2, 30.3, 30.1, 30.0] ℃. The flow rate fluctuation value is calculated as follows: the flow rate fluctuation value can be obtained by calculating the standard deviation of the flow rate sequence. The formula of the standard deviation is:

[0068]

[0069] wherein, V iVi is the i-th flow rate value, Vi is the i-th flow rate value, n is the length of the flow rate sequence.

[0070] For the flow rate sequence [1.2, 1.3, 1.4, 1.2, 1.3], first calculate the flow rate mean value

[0071]

[0072] Therefore, the flow rate fluctuation value is 0.1 m / s.

[0073] For pressure gradient value calculation, the pressure gradient value is obtained by calculating the pressure difference between adjacent measuring points. Assuming the distance between measuring points is Δx = 1 m, the pressure gradient formula is:

[0074]

[0075] Where ΔP is the pressure difference between the two adjacent measuring points, and Δx is the distance between the measuring points.

[0076] Assuming the pressure sequence is [100, 102, 104, 103, 101] (unit: Pa), and the distance between measuring points is assumed to be 1 meter. Then the pressure gradient value is calculated as follows:

[0077]

[0078] Therefore, the pressure gradient value is 2 Pa / m.

[0079] For temperature change value calculation, the temperature change value is obtained by calculating the maximum change in temperature. The formula for calculating the temperature change value is:

[0080] TC = max(T) - min(T);

[0081] Where T is the pipe wall temperature sequence.

[0082] The temperature sequence is [30.1, 30.2, 30.3, 30.1, 30.0] (unit: ℃), the maximum value is 30.3 ℃, and the minimum value is 30.0 ℃, so the temperature change value is:

[0083] TC = 30.3 - 30.0 = 0.3 ℃;

[0084] Therefore, the temperature change value is 0.3 ℃.

[0085] The feature comparison sub-module calls the fluid state feature vector, extracts the feature vector data of multiple known fluid states, and uses the formula:

[0086]

[0087] determine the closeness of the current fluid state and the known state, and obtain a feature similarity score;

[0088] wherein S represents the feature similarity score, w i represents the weight of each feature item, X i represents the i-th feature value of the current state, represents the i-th feature value of the known fluid state, n is the total number of features, and i represents the i-th feature item in the feature vector;

[0089] In the feature comparison process, first, the fluid state feature vector is called to compare with the known fluid state feature vector. Assuming that the known fluid state feature vector is: known state 1: [0.12, 0.025, 0.09], known state 2: [0.08, 0.03, 0.12], known state 3: [0.1, 0.02, 0.1], and the weight of each feature is w1=0.4, w2=0.3, w3=0.3, respectively, and the feature vector of the current fluid state is [0.1, 0.02, 0.1], the feature similarity score is calculated by substituting the formula:

[0090] The similarity score of known state 1 is calculated:

[0091] S1=0.4·|0.1-0.12|+0.3·|0.02-0.025|+0.3·|0.1-0.09|=0.0125;

[0092] The calculation for known state 2 is:

[0093] S2=0.4·|0.1-0.08|+0.3·|0.02-0.03|+0.3·|0.1-0.12|;

[0094] S2=0.4·0.02+0.3·0.01+0.3·0.02=0.008+0.003+0.006=0.018;

[0095] The calculation for known state 3 is:

[0096] S3=0.4·|0.1-0.1|+0.3·|0.02-0.02|+0.3·|0.1-0.1|;

[0097] S3=0.4·0+0.3·0+0.3·0=0;

[0098] As shown in Table 1, the example data shows the comparison of different fluid state features and the calculated similarity scores.

[0099]

[0100] As shown in Table 1, the calculated feature similarity scores help identify the current fluid state.

[0101] The final calculation result shows that the current fluid state is closest to the known state 3, as its feature similarity score is 0, meaning that the feature vector of the current fluid state completely matches the feature vector of the known state 3. For the known state 1 and the known state 2, the similarity scores are 0.0125 and 0.018, respectively, indicating that they have a lower degree of matching with the current state. Based on this, the system determines that the current fluid state is closest to the known state 3, and accordingly extracts the corresponding fluid laminar flow index, turbulence intensity coefficient, and backflow probability value.

[0102] The state calculation sub-module compares the feature similarity scores with multiple known fluid states to identify the flow state at multiple positions in the pipeline and extract the corresponding fluid laminar flow index, turbulence intensity coefficient, and backflow probability value to obtain the flow pattern coefficient.

[0103] Based on the obtained feature similarity scores, the system selects the closest known fluid state and extracts its corresponding fluid laminar flow index, turbulence intensity coefficient, and backflow probability value. Assuming that in the closest known state, the fluid laminar flow index is 0.85, the turbulence intensity coefficient is 0.12, and the backflow probability value is 0.07. The system will identify the current fluid state in the pipeline based on the results of the similarity scores. In this way, the system determines that the flow characteristics of the current fluid state are: fluid laminar flow index 0.85, turbulence intensity coefficient 0.12, and backflow probability value 0.07. The final result provides the basis for determining the flow pattern through these fluid state parameters.

[0104] Please refer to Figure 3 , the path optimization module includes:

[0105] The geometric feature extraction submodule calls the flow pattern coefficient, uses the geometric feature information of the pipeline, extracts the bend curvature radius and pipe diameter contraction ratio parameters at multiple positions in the pipeline, and obtains the geometric feature analysis result.

[0106] The geometric feature extraction submodule calls the flow pattern coefficient, uses the geometric feature information of the pipeline, extracts the bend curvature radius and pipe diameter contraction ratio parameters at multiple positions in the pipeline, and obtains the geometric feature analysis result.

[0107]

[0108] where P shrink represents the pipe diameter contraction ratio, D init represents the original pipe diameter, D new represents the current pipe diameter.

[0109] Substitute numerical calculation:

[0110]

[0111] It indicates that the pipe diameter at this position is reduced by 25%. For multiple position measurement data, record the curvature radius and pipe diameter contraction ratio parameters of all measurement points and perform normalization processing to ensure that the data can be used for subsequent path adjustment calculation, and finally obtain the geometric feature analysis result.

[0112] The path adjustment calculation submodule calls the turbulence intensity coefficient and backflow probability value based on the geometric feature analysis result, combines the bend curvature radius and pipe diameter contraction ratio, and uses the formula:

[0113]

[0114] to perform path curvature adjustment calculation, obtain the path curvature adjustment amount, and generate the path adjustment parameter;

[0115] where C adjust is the path curvature adjustment amount, T curvature is the bend curvature radius, R is the response coefficient of flow, P shrink is the pipe diameter contraction ratio, and L is the length of the flow path.

[0116] Based on the geometric feature analysis result, call the turbulence intensity coefficient and backflow probability value, combine the bend curvature radius and pipe diameter contraction ratio, and calculate the path curvature adjustment amount. In the process of pipeline flow optimization, the flow characteristics at different positions determine the change of path curvature. If the turbulence intensity at a certain position is large and the backflow probability is high, the path adjustment amount should be increased to reduce flow instability. The path curvature adjustment amount is calculated using the formula:

[0117]

[0118] where C adjust is the path curvature adjustment amount, T curvature is the bend curvature radius, R is the response coefficient of flow, P shrink is the pipe diameter contraction ratio, and L is the length of the flow path.

[0119] Suppose that in a certain pipeline section, the measured curvature radius T curvature = 2.5 m, the pipe diameter contraction ratio P shrink= 0.25, flow path length L = 5m, flow response coefficient R = 1.8, the formula is calculated as follows:

[0120]

[0121] The path curvature adjustment amount is calculated to be 4.49. According to the adjustment amount, the path is corrected, the path parameters are optimized, and finally the path adjustment parameters are generated.

[0122] The motion trajectory planning submodule calculates the motion speed of the robot at multiple positions in the pipeline according to the path adjustment parameters and the flow characteristics, obtains the bend deceleration ratio and the straight pipe segment acceleration threshold, and obtains the path trajectory parameters;

[0123] According to the path adjustment parameters and the flow characteristics in the pipeline, the motion speed of the robot at each position is calculated, and its speed is adjusted to match the flow state of the pipeline. For the bend area, due to the large change in curvature, a deceleration ratio needs to be set to ensure the smooth passage of the robot. Assuming that the path curvature adjustment amount is 4.49, the bend deceleration ratio is calculated as follows:

[0124]

[0125] Where S bend is the bend deceleration ratio, and C adjust is the path curvature adjustment amount. Substituting the calculation is as follows:

[0126]

[0127] That is, the bend deceleration ratio at this position is 18.2%, which means that in the bend area, the robot should reduce its speed by 18.2%.

[0128] For the straight pipe segment, an acceleration threshold needs to be set to take advantage of the lower resistance to increase the moving speed. Assuming that the current flow rate is 2m / s and the turbulence intensity coefficient is 0.12, the straight pipe segment acceleration threshold is calculated as follows:

[0129] A thresh = V flow ×(1+T intensity );

[0130] Where A thresh represents the straight pipe segment acceleration threshold, V flow represents the flow rate, and T intensity represents the turbulence intensity coefficient. Substituting the calculation is as follows:

[0131] A thresh = 2×(1+0.12) = 2×1.12 = 2.24m / s;

[0132] i.e. the acceleration threshold of straight pipe section is 2.24 m / s. Finally, combined with the deceleration ratio of curved pipe and the acceleration threshold of straight pipe section, the trajectory adjustment of each position is calculated, and the movement mode of robot in the pipe is optimized to obtain the path trajectory parameters.

[0133] Table 2: Path adjustment related data

[0134]

[0135] As shown in Table 2, the path curvature adjustment amount, the curved pipe deceleration ratio and the straight pipe acceleration threshold of each position are calculated and used to optimize the robot movement trajectory, ensuring that the path adjustment is reasonable and matches the fluid characteristics.

[0136] Referring to Figure 4 , the position calibration module comprises:

[0137] The attitude and position analysis submodule calls the path trajectory parameters, analyzes the measurement data of the inertial measurement unit and the gyroscope, identifies the actual movement position and attitude of the robot, records the current coordinates and angles of the robot, and obtains real-time position data of the robot;

[0138] In this submodule, the inertial measurement unit (IMU) and the gyroscope are first used to obtain real-time movement data of the robot, including coordinates (X, Y axis coordinates) and angles (attitude) of the robot. The sensors continuously collect dynamic data of the robot, and by analyzing these data, the current movement state and position of the robot can be accurately determined. Through the inertial measurement unit, the acceleration and angular velocity of the robot can be obtained, while the gyroscope provides angle information. Assuming that the current coordinates of the robot are X act = 5.2 m and Y act = 3.5 m, and the current angle is θ act = 45°, these data are measured and obtained in real time by sensors. Next, the coordinates and angles recorded by the sensors at each moment will be stored and used for subsequent trajectory comparison. At this time, the robot compares its real-time coordinates and angles with the preset trajectory data to determine whether there is deviation in its position in the current trajectory. Assuming that the preset trajectory position of the robot is X ideal = 5.0 m and Y ideal = 3.0 m, while the actual position is X act = 5.2 m and Y act=3.5m. By comparison, it can be identified whether the robot has deviated from the predetermined trajectory. The ultimate goal of this submodule is to acquire the robot's real-time position data and compare it with the preset trajectory, providing a data basis for subsequent calculation of horizontal offset correction. Assuming the robot starts from the starting point and travels along a preset trajectory, the path is formed by connecting multiple points. We need to monitor and record the robot's position in real time so that its trajectory can be corrected at any time. In this way, the robot can adjust its path at any time based on real-time feedback provided by inertial sensors, gyroscopes, and other devices, ensuring that it can accurately travel to the target position. If the robot deviates at a certain moment, the analysis function of this submodule can identify the position deviation in time and prepare the necessary data for subsequent path adjustment and attitude compensation.

[0139] The quantum module for calculating horizontal offset correction utilizes the robot's real-time position data. Based on the robot's actual coordinates, it compares them with a preset trajectory using the following formula:

[0140]

[0141] Obtain the horizontal offset correction amount;

[0142] Among them, D offset X is the horizontal offset correction amount. act Let X be the robot's actual X coordinate. ide For the preset X coordinate, Y act Y is the robot's actual Y coordinate. ide Preset Y coordinate;

[0143] This submodule calculates the horizontal offset correction between the robot's actual position data and the preset trajectory. The calculation formula is:

[0144]

[0145] Among them, D offset X is the horizontal offset correction amount. act Let X be the robot's actual X coordinate. ideal For the preset X coordinate, Y act Y is the robot's actual Y coordinate. ideal The Y-coordinate is the preset coordinate. The horizontal offset correction is calculated as the Euclidean distance between the robot's current position and the predetermined position, reflecting the degree to which the robot deviates from the preset trajectory.

[0146] Assume the robot's actual coordinates are X act =5.2m and Y act = 3.5m, and the preset trajectory coordinates are X ideal =5.0m and Y ideal =3.0m, then substitute these values ​​into the formula for calculation:

[0147]

[0148] Therefore, the horizontal offset correction is 0.54 m, which means there is a 0.54-meter deviation between the current position of the robot and the preset trajectory, and the robot needs to adjust accordingly. This correction provides the basis for subsequent posture compensation, ensuring that the robot can accurately follow the predetermined trajectory. If the robot continues to deviate during operation, by calculating the horizontal offset correction each time, the robot's path can be gradually adjusted to minimize deviation from the preset trajectory. This adjustment process is dynamic, correcting the robot's position in real time to ensure that it can eventually reach the target position without failure or unstable operation due to continuous deviation.

[0149] The posture compensation angle calculation submodule calculates the posture compensation angle of the robot based on the horizontal offset correction and the actual posture of the robot by comparing it with the preset trajectory, adjusts the angle difference between the robot and the preset trajectory, and generates position compensation parameters;

[0150] This submodule further corrects the motion direction of the robot by calculating the posture compensation angle to ensure that it travels correctly along the preset trajectory. The formula for calculating the posture compensation angle is:

[0151] θ comp =θ act -θ ideal ;

[0152] Where θ comp is the posture compensation angle, θ act is the actual angle of the robot, and θ ideal is the preset angle. The calculation of the posture compensation angle is to correct the turning direction of the robot so that it can move in the correct direction.

[0153] Suppose the actual angle of the robot is θ act = 45°, and the angle of the preset trajectory is θ ideal = 40°, then the calculation of the posture compensation angle is as follows:

[0154] θ comp = 45° - 40° = 5°;

[0155] The pose compensation angle is 5°, indicating that the robot needs to adjust 5° to the right to keep consistent with the preset trajectory. The calculation of this compensation angle is based on the difference between the current position angle of the robot and the angle of the preset trajectory, ensuring that the robot moves in the correct direction. Assuming that the robot's pose compensation process is dynamic, it is calculated in real time at each step based on the actual angle of the robot and the target angle, and the angle is adjusted. Through this mechanism, the robot can gradually correct the angle difference with the preset trajectory during operation, so that it finally travels along the predetermined route.

[0156] Please refer to Figure 5 , the pressure regulating module comprises:

[0157] The pressure difference calculation submodule adjusts the deviation of the robot from the preset trajectory based on the position compensation parameters and the real-time horizontal offset correction amount of the robot, and calculates the difference between the measured pressure and the preset expected value by combining the contact pressure value of the pipe wall obtained by the pressure sensor to obtain the pressure difference data.

[0158] In this submodule, first, the deviation of the robot from the preset trajectory is adjusted based on the position compensation parameters and the real-time horizontal offset correction amount of the robot. By adjusting the deviation of the robot in real time, this step ensures that the robot can accurately travel along the predetermined trajectory. The real-time offset amount (including horizontal and vertical offset) of the robot is detected by the sensors (such as IMU sensors and gyroscopes) of the robot body and dynamically updated in combination with the position compensation algorithm. For this step, the real-time deviation is calculated based on the difference between the actual motion and the expected trajectory, for example, the errors in X and Y axes between the actual position and the target position of the robot are measured and integrated and corrected to achieve the desired accuracy. The pressure difference calculation is the second part of this submodule, which calculates the difference between the measured pressure and the preset expected value by obtaining the contact pressure value of the pipe wall. Specifically, the contact pressure value comes from the pressure sensor, which measures and feeds back the data of the pressure inside the pipe in real time. This submodule compares these data with the preset target pressure to calculate the pressure difference between the measured pressure and the target pressure, and the calculation formula is:

[0159] ΔP' = P measured -P desired ;

[0160] Where ΔP' is the pressure difference, P measured is the measured pressure, and P desired is the target pressure.

[0161] Suppose the contact pressure of the pipe wall read by the pressure sensor is 4.8 MPa, and the target pressure value is set to 5.0 MPa, then the pressure difference is calculated as:

[0162] AP' = 4.8MPa - 5.0MPa = -0.2MPa;

[0163] The resulting pressure difference is -0.2MPa, which will be used as a basis for subsequent pressure adjustment.

[0164] The cleaning pressure adjustment submodule uses the formula:

[0165]

[0166] to calculate the adjusted cleaning nozzle pressure, adjust the pressure parameter of the cleaning nozzle, and obtain the pressure parameter of the cleaning nozzle.

[0167] where P adj is the adjusted cleaning nozzle pressure, P des is the preset target contact pressure, AP' is the pressure difference, i.e. the difference between the measured pressure and the target pressure, a is the correction coefficient for adjusting the influence of the pressure difference on the nozzle pressure adjustment, and μ is the fluid viscosity coefficient.

[0168] The function of this submodule is to adjust the pressure parameter of the cleaning nozzle according to the pressure difference data. First, based on the pressure difference data obtained from the pressure difference calculation submodule, the data is combined with the target pressure and adjusted through the formula. Specifically, the pressure of the cleaning nozzle needs to be corrected according to the difference between the measured pressure and the target pressure in order to achieve the set cleaning effect. The formula is as follows:

[0169]

[0170] where P adj is the adjusted cleaning nozzle pressure, P des is the preset target contact pressure, AP' is the pressure difference, i.e. the difference between the measured pressure and the target pressure, a is the correction coefficient, which adjusts the influence of the pressure difference on the adjustment of the nozzle pressure, μ is the fluid viscosity coefficient, which affects the resistance of fluid flow, and D is the nozzle diameter, which affects the flow rate and the size of the nozzle pressure.

[0171] Suppose in a certain cleaning task, the target contact pressure is 5.0MPa, the measured pressure is 4.8MPa, the viscosity coefficient μ = 0.001Pa·s, the nozzle diameter D = 0.05m, and the correction coefficient a = 1.2. Then the pressure difference AP' = -0.2MPa, and the formula gives:

[0172]

[0173] The final adjusted cleaning nozzle pressure is 4.9952 MPa. This adjustment ensures that the output pressure of the nozzle is very close to the target pressure value, thereby optimizing the cleaning effect and avoiding excessive pressure fluctuations affecting the cleaning quality.

[0174] The rotary motor torque compensation submodule calculates the rotary motor torque compensation value based on the pressure parameters of the cleaning nozzle, considers the pressure changes required by the cleaning nozzle, and combines the load response characteristics of the motor to further calculate the torque compensation value of the rotary motor, adjust the motor output, and generate the cleaning pressure parameters;

[0175] The main task of this submodule is to calculate the rotary motor torque compensation value based on the pressure parameters of the cleaning nozzle. The pressure change of the cleaning nozzle will affect the load of the motor, and the torque of the motor must be compensated according to the adjustment of the nozzle pressure to ensure that the motor can provide sufficient power. According to the pressure difference data, the load of the motor will change accordingly, thereby affecting its output torque. In this submodule, the pressure adjustment requirements of the cleaning nozzle are first identified, and the corresponding torque compensation value is calculated based on these requirements. Specifically, the torque compensation value of the motor is calculated by considering the relationship between pressure change and motor load. If the pressure adjustment of the cleaning nozzle is large, the torque compensation value of the motor needs to be increased accordingly to adapt to the changed pressure requirements. The calculation formula is:

[0176]

[0177] Where T adj is the adjusted rotary motor torque compensation value, T base is the reference torque, i.e. the output torque of the motor without pressure adjustment, β is the motor load response coefficient, used to adjust the relationship between the torque response of the motor and the pressure change, ΔP' is the pressure difference, i.e. the difference between the actual measured pressure and the target pressure, P des is the target pressure, i.e. the target contact pressure required by the cleaning nozzle.

[0178] Suppose the reference torque T base = 10 Nm, the motor load response coefficient β = 0.05, the pressure difference ΔP' = -0.2 MPa, and the target pressure P des = 5.0 MPa, then the formula is calculated as follows:

[0179]

[0180] Through calculation, the adjusted rotary motor torque compensation value is 9.98 Nm. This torque value is based on the adjustment of the load response of the motor based on the measured pressure difference, ensuring that the motor can provide appropriate power output during cleaning and maintain the stable working state of the cleaning nozzle.

[0181] In this process, the torque compensation value of the motor is proportional to the pressure difference, and by adjusting the motor load response characteristics, further optimization is achieved. This sub-module will eventually calculate the required rotating motor torque compensation value, thus providing appropriate adjustment for the motor, ensuring the stability and accuracy of the motor output during the cleaning process.

[0182] Referring to Figure 6 , the effect evaluation module includes:

[0183] The image contrast sub-module acquires the pipe wall images before and after cleaning through image acquisition devices based on the cleaning pressure parameters, extracts the residual coverage area and texture clarity of multiple regions in the images using image analysis, and generates pipe wall image analysis results.

[0184] The main task of this sub-module is to acquire the pipe wall images before and after cleaning through image acquisition devices and extract the residual coverage area of multiple regions in each image using image analysis techniques. Specifically, the image processing system first performs high-definition image acquisition on the inner wall of the pipeline to obtain image data before and after cleaning. Then, through image analysis algorithms, especially edge detection and binary processing, the system identifies the residual area in the image and calculates the coverage area of the region. The key to this step is to separate the areas before and after cleaning through threshold processing to calculate the proportion of residual in each region. Finally, the system outputs the residual coverage area data of each region for further cleaning effect analysis. The formula for calculating the residual coverage area in the image is as follows:

[0185]

[0186] Where A area,i' is the residual coverage area of region i', W and H are the width and height of the image respectively, I raw (x,y) is the pixel value at position (x,y) in the image, Mask(x,y) is the binary mask, which is 1 in the residual area and 0 in other positions, and ∑ represents the summation of all pixels in the image.

[0187] Suppose there is an image before cleaning, with a size of W=10 pixels and H=10 pixels. The residual in the image is represented by a binary mask (Mask), with a mask value of 1 in the residual area and 0 in other areas. Suppose the pixel value of the image is I raw (x,y) = 1 in the residual area and I raw (x,y) = 0 in other areas, and the mask has 25 pixels.

[0188] Calculate the coverage area of the residual:

[0189]

[0190] Since the pixel values of the residue coverage area in the image are 1 and the mask values are also 1, the coverage area is the number of pixel points with mask value 1, that is:

[0191] A area,1 = 25 pixels;

[0192] The results show that the residue coverage area is 25 pixel points.

[0193] The cleaning effect analysis submodule is based on the image analysis results of the pipe wall. By comparing the residue coverage area and the texture clarity in the images before and after cleaning, the residue coverage area proportion and the texture clarity difference value of multiple regions are calculated, and the formula is used:

[0194]

[0195] The cleaning effect of multiple positions is evaluated, and the cleanliness score is calculated;

[0196] Where C tot is the cleanliness score, which measures the cleaning effect, A bf,i' is the residue coverage area of region i' before cleaning, A af,i' is the residue coverage area of region i' after cleaning, T bf,i' is the texture clarity of region i' before cleaning, T af,i' is the texture clarity of region i' after cleaning, w1 is the weight coefficient of the residue coverage area, w2 is the weight coefficient of the texture clarity, N' is the total number of image divided regions, and i' is the index of the region in the image;

[0197] This submodule is based on the image analysis results provided by the image comparison submodule. The residue coverage area proportion and the texture clarity difference value of multiple regions in the images before and after cleaning are calculated. By comparing the images before and after cleaning, the system calculates the cleaning effect of each region and finally generates the overall cleanliness score. In order to evaluate the cleanliness, the following formula is used to weight the improvement effect of the residue coverage area and the texture clarity:

[0198]

[0199] Where A bf,i' is the residue coverage area of region i' before cleaning, A af,i' is the residue coverage area of region i' after cleaning, T bf,i′ is the texture clarity of region i' before cleaning, T af,i′ is the texture clarity of region i' after cleaning, w1 and w2 are the weight coefficients of the residue coverage area and the texture clarity respectively, N' is the total number of image divided regions, and C tot is the overall cleanliness score.

[0200] For example, assume there are three zones, Zone 1 : A bf,1 = 50%, A af,1 = 10%, T bf,1 = 0.8, T af,1 = 0.9, Zone 2: A bf,2 = 60%, A af,2 = 20%, T bf,2 = 0.7, T af,2 = 0.85, Zone 3: A bf,3 = 40%, A af,3 = 15%, T bf,3 = 0.75, T af,3 = 0.88, weight coefficients w1 = 0.6 and w2 = 0.4, calculate the cleanliness score:

[0201] Calculate the contribution of each zone separately:

[0202] Zone 1 :

[0203]

[0204] C1 = 0.6-0.8 + 0.4-0.125;

[0205] C1 = 0.48 + 0.05;

[0206] C1 = 0.53;

[0207] Zone 2:

[0208]

[0209] C2 = 0.6-0.6667 + 0.4-0.2143; C2 = 0.4 + 0.0857;

[0210] C2 = 0.4857;

[0211] Zone 3:

[0212]

[0213] C3 = 0.6-0.625 + 0.4-0.1733;

[0214] C3 = 0.375 + 0.0693;

[0215] C3 = 0.4443;

[0216] Overall cleanliness score:

[0217] C tot = C1 + C2 + C3;

[0218] Ctot = 0.53 + 0.4857 + 0.4443;

[0219] C tot = 1.46;

[0220] Therefore, the overall cleanliness score is 1.46.

[0221] The cleaning duration adjustment submodule calls the cleanliness score, identifies the insufficient cleaning position, and adjusts the cleaning duration of the robot to generate the pipeline cleaning operation parameters;

[0222] The cleaning duration adjustment submodule automatically identifies the insufficient cleaning area based on the cleanliness score of the cleaning effect analysis submodule and adjusts the cleaning duration. Specifically, the system determines which areas have insufficient cleaning effect according to the calculated cleanliness score. If the cleanliness score of a certain area is low, it means that the area is not completely cleaned. To ensure complete cleaning of the area, the system will accordingly extend the cleaning duration, especially in areas with a large residual coverage area or a small texture clarity difference value. In addition, the cleaning duration adjustment submodule will also consider the moving speed and cleaning efficiency of the robot in different areas, and comprehensively adjust the duration to optimize the cleaning process. According to the cleanliness score C tot and the cleaning effect of each area, the calculation formula of the cleaning duration T adj is as follows:

[0223]

[0224] Where T adj,i′ is the adjusted cleaning duration of area i', T base is the basic cleaning duration, a is the adjustment factor that controls the strength of duration adjustment, C tot,i′ is the cleanliness score of area i', and 1-C tot,i′ represents the degree of insufficient cleanliness.

[0225] For example, assume that the basic cleaning duration of area 1 is T base = 5 minutes, and the cleanliness score of the area is C tot,1 = 0.8, and assume a = 0.2, then the adjusted cleaning duration is:

[0226] T adj,1 = 5 x (1 + 0.2 x (1-0.8)) = 5 x (1 + 0.2 x 0.2) = 5 x 1.04 = 5.2 minutes;

[0227] 5.2 minutes;

[0228] Through this formula, the cleaning duration can be reasonably adjusted according to the cleaning effect to ensure that each area is sufficiently cleaned.

[0229] The above merely provides the preferred embodiment of the present application, and is not intended to limit the present application to other forms. Any person skilled in the art can make modifications and variations to the present application without departing from the spirit and scope of the present application. Therefore, the simple modifications, equivalent variations and improvements made to the above embodiments according to the technical spirit of the present application should be within the scope of the present application.

Claims

1. A self-adaptive control system for a pipeline cleaning robot, characterized by, The system comprises: The fluid sensing module monitors the pipeline fluid state, obtains flow rate, pressure, temperature data, calculates the fluid state of multiple positions in the pipeline through feature comparison, and obtains the flow pattern coefficient; The path optimization module calls the flow pattern coefficient, uses the turbulence intensity coefficient and the backflow probability value, combines the bend curvature radius and the pipe diameter contraction ratio at multiple positions of the pipeline, calculates the path curvature adjustment amount and the movement speed, and generates the path trajectory parameter; The position calibration module calls the path trajectory parameter, uses the inertial measurement unit and the gyroscope, analyzes the motion posture and position of the robot, and compares with the preset trajectory to obtain the horizontal offset correction amount and the posture compensation angle, and generates the position compensation parameter; The pressure adjustment module calls the position compensation parameter, uses the horizontal offset correction amount, combines the pipe wall contact pressure value, calculates the difference between the expected value and the measured value of the contact pressure, adjusts the pressure parameter of the cleaning nozzle and the torque compensation value of the rotating motor, and generates the cleaning pressure parameter; The effect evaluation module uses the image acquisition device to identify the insufficient cleaning position and adjust the cleaning time based on the cleaning pressure parameter by comparing the image sequence before and after the pipe wall cleaning, and generates the pipeline cleaning operation parameter.

2. The pipe cleaning robot adaptive control system of claim 1, wherein, The flow pattern coefficient includes the fluid laminar flow index, the turbulence intensity coefficient, and the backflow probability value, the path trajectory parameter includes the robot working path, the bend driving speed, and the straight pipe advancing speed threshold, the position compensation parameter includes the position offset correction amount, the angle offset correction amount, and the position offset data, the cleaning pressure parameter includes the cleaning nozzle control parameter and the rotating motor control parameter, and the pipeline cleaning operation parameter includes the residual coverage area ratio, the texture definition difference value, and the cleaning time adjustment value.

3. The pipe cleaning robot adaptive control system of claim 1, wherein, The fluid sensing module comprises: The feature extraction submodule monitors the pipeline fluid state, uses the flow rate sensor to obtain the instantaneous flow rate sequence, uses the pressure sensor to obtain the dynamic pressure waveform, uses the temperature sensor to obtain the pipe wall temperature value, calculates the flow rate fluctuation value, the pressure gradient value, and the temperature change value under the current fluid state, and establishes the fluid state feature vector; The feature comparison submodule calls the fluid state feature vector, extracts the feature vector data of multiple known fluid states, uses the formula: judges the closeness of the current fluid state and the known state, and obtains the feature similarity score; where S represents the feature similarity score, w i represents the weight of each feature item, X i represents the i-th feature value of the current state, represents the i-th feature value of the known fluid state, n is the total number of features, and i represents the i-th feature item in the feature vector. The state calculation submodule compares the fluid state of multiple positions in the pipeline with multiple known fluid states based on the feature similarity score, extracts the fluid laminar flow index, the turbulence intensity coefficient, and the backflow probability value corresponding to the fluid state, and obtains the flow pattern coefficient.

4. The pipe cleaning robot adaptive control system of claim 1, wherein, The path optimization module comprises: The geometric feature extraction submodule calls the flow pattern coefficient, uses the geometric feature information of the pipeline, extracts the bend curvature radius and the pipe diameter contraction ratio parameter at multiple positions in the pipeline, and obtains the geometric feature analysis result; The path adjustment calculation submodule calculates the path curvature adjustment amount based on the geometric feature analysis result, calls the turbulence intensity coefficient and the backflow probability value, combines the bend curvature radius and the pipe diameter contraction ratio, uses the formula: performs path curvature adjustment calculation, obtains the path curvature adjustment amount, and generates the path adjustment parameter; where C adjust is the path curvature adjustment, T curvature is the bend curvature radius, R is the response coefficient of the flow, P shrink is the pipe diameter contraction ratio, and L is the length of the flow path. The motion trajectory planning submodule calculates the motion speed of the robot at multiple positions in the pipeline according to the path adjustment parameter and in combination with the flow characteristics, obtains a deceleration ratio of a curved section and an acceleration threshold of a straight section, and obtains path trajectory parameters.

5. The pipe cleaning robot adaptive control system of claim 1, wherein, The position calibration module comprises: The attitude and position analysis submodule calls the path trajectory parameters, identifies the actual motion position and attitude of the robot by analyzing the measurement data of the inertial measurement unit and the gyroscope, records the current coordinates and angle of the robot, and obtains real-time position data of the robot; A horizontal offset correction amount calculation submodule obtains a horizontal offset correction amount by comparing the actual coordinates of the robot with the preset trajectory according to the real-time position data of the robot by using the formula: The attitude compensation angle calculation submodule calculates the attitude compensation angle of the robot by comparing the actual attitude of the robot with the preset trajectory based on the horizontal offset correction amount, adjusts the angle difference between the robot and the preset trajectory, and generates position compensation parameters. wherein D offset is a horizontal offset correction, X act is an actual X coordinate of the robot, X ide is a preset X coordinate, Y act is an actual Y coordinate of the robot, Y ide is a preset Y coordinate; The pressure adjustment module comprises:

6. The pipe cleaning robot adaptive control system of claim 1, wherein, A pressure difference calculation submodule adjusts the deviation between the robot and the preset trajectory in combination with the real-time horizontal offset correction amount of the robot according to the position compensation parameters, obtains the contact pressure value of the pipe wall in combination with the pressure sensor, calculates the difference between the measured pressure and the preset expected value, and obtains pressure difference data; A cleaning pressure adjustment submodule calculates the adjusted cleaning nozzle pressure by using the formula: The pressure parameter of the cleaning nozzle is adjusted, and the pressure parameter of the cleaning nozzle is obtained; A rotary motor torque compensation submodule further calculates the torque compensation value of the rotary motor by considering the pressure change required by the cleaning nozzle in combination with the load response characteristics of the motor according to the pressure parameter of the cleaning nozzle, adjusts the motor output, and generates the cleaning pressure parameter. where P adj is the adjusted cleaning nozzle pressure, P des is the preset target contact pressure, ΔP' is the pressure difference, i.e., the difference between the measured pressure and the target pressure, α is a correction factor for adjusting the influence of the pressure difference on the nozzle pressure adjustment, μ is the fluid viscosity coefficient, and D is the nozzle diameter. The effect evaluation module comprises:

7. The pipe cleaning robot adaptive control system of claim 1, wherein, An image comparison submodule obtains the pipe wall images before and after cleaning by using the image acquisition device according to the cleaning pressure parameter, extracts the residual coverage area and texture definition of multiple regions in the images by using image analysis, and generates pipe wall image analysis results; A cleaning effect analysis submodule calculates the residual coverage area proportion and texture definition difference value of multiple regions by comparing the residual coverage area and texture definition in the images before and after cleaning according to the pipe wall image analysis results, and uses the formula: The cleaning effect of multiple positions is evaluated, and the cleanliness score is calculated; A cleaning time adjustment submodule calls the cleanliness score, identifies the positions that are not cleaned enough, adjusts the cleaning time of the robot, and generates pipeline cleaning operation parameters. wherein C tot is the cleanliness score, measuring the cleaning effect, A bf,i′ is the residue coverage area of region i' before cleaning, A af,i′ is the residue coverage area of region i' after cleaning, T bf,i′ is the texture definition of region i' before cleaning, T af,i′ is the texture definition of region i' after cleaning, w1 is the weight coefficient of residue coverage area, w2 is the weight coefficient of texture definition, N' is the total number of regions divided in the image, and i' is the index of region in the image. ​

Images