A method for optimizing the path of an underwater screed based on the characteristics of the bed porosity

Abstract

The application discloses a kind of based on bed pore feature underwater screed path optimization method, it is related to marine engineering technical field;Utilize multi-source perception and control system and multi-beam sounding method measure the three-dimensional terrain data and pore distribution characteristic data of the bed of the water area to be flattened, establish the digital terrain model of the bed to be flattened, by constructing initial construction path, generate candidate optimization flattening path adapted to geological features, evaluate the engineering feasibility of flattening operation and output the optimal position of each path point after iteration optimization as optimization flattening path in combination with optimization algorithm, complete the leveling of underwater screed;Intelligently analyze the pore distribution characteristics and three-dimensional terrain data of seabed bed, obtain reliable environmental data and form initial construction blueprint, provide basis for optimization, by fusing pore feature analysis and intelligent optimization algorithm, realize the dynamic generation and online correction of path, achieve efficient, uniform, high-precision autonomous flattening operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ocean engineering, in particular to a path optimization method for an underwater screed based on pore characteristics of a bed. BACKGROUND

[0002] At present, the path planning of the underwater screed mainly relies on artificial experience or fixed mode of back-and-forth operation. These methods are simple and easy to implement, but have the following limitations: 1. Lack of pore adaptability; ignoring the spatial heterogeneity of pore distribution of the bed, resulting in uneven compactness after leveling, affecting the stability of the foundation. 2. Insufficient dynamic response; static path is difficult to adapt to complex seabed topography (such as steep slope, gully) in real time, and local area is repeated or missed seriously. 3. Efficiency bottleneck is prominent; the rate of redundant path is high, which significantly increases the operation time and energy consumption.

[0003] In the prior art, the leveling boat only relies on GPS positioning and simple inclination sensor, and cannot sense the influence of pore distribution on the leveling effect, which easily leads to path deviation when the porosity suddenly changes, and has the problems of poor geological adaptability, lagging dynamic response and lack of pore characteristic quantization; the traditional method does not take the pore characteristics into the path planning model, which may cause local collapse. SUMMARY

[0004] The purpose of the present application is to provide a path optimization method for an underwater screed based on pore characteristics of a bed, to establish a multi-source perception system integrating inclination sensors, pressure sensors, underwater cameras and sonar devices, to collect data of the screed in real time. The path is optimized, and the hydraulic legs, vector thrusters and ballast systems are controlled to complete the material distribution operation and the machine moving operation according to the action instructions, to realize efficient and accurate leveling based on the pore characteristics of the bed, and dynamic optimization of the operation path of the screed.

[0005] The path optimization method for an underwater screed based on pore characteristics of a bed provided by the present application comprises the following steps:

[0006] The three-dimensional terrain data and pore distribution characteristic data of the bed to be leveled in the water area are measured by using the multi-source perception and control system and the multi-beam sounding method, a digital terrain model of the bed to be leveled is established, and real-time adjustment and update are performed, the positions of the path points are output by using the path planning algorithm, the initial leveling path is obtained according to the positions of the path points, and the initial construction path is constructed;

[0007] Based on the pore distribution characteristic data of the bed and the initial leveling path, the operation weaknesses of the screed in the porosity are identified by using the geological sensitivity analysis algorithm, a weak feature set of the bed is constructed, the initial construction path is directionally adjusted by target keeping based on the weak feature set of the bed by using the geological parameter mapping method, and the candidate optimized leveling path adapted to the geological characteristics is generated by using the fuzzy control method;

[0008] The engineering feasibility of the candidate optimized grading path is evaluated by using the terrain similarity measure and the geological feature projection algorithm, and the optimal position of each path point after iteration optimization is output as the optimized grading path by combining the optimization algorithm, and based on the optimized grading path, the leveling of the underwater grading machine is completed by using the pressure sensor and the inclination sensor components in the multi-source perception and control system;

[0009] The optimized grading path parameters are dynamically adjusted according to the operation effect of the grading machine on the optimized grading path, and the grading machine is controlled to complete the material distribution operation and the machine moving operation according to the action instruction.

[0010] The position of each grading path point is output by using the path planning algorithm, and the initial grading path is obtained according to the position of each grading path point, and the initial construction path is constructed, including:

[0011] The gridding data of the digital terrain of the base to be graded is input, the path planning algorithm is used to calculate the key point set of the grading path, the coordinate sequence of the path point is output to obtain the initial grading path, and the initial construction path is constructed by connecting the path points by using the uniform B-spline curve.

[0012] Based on the base pore distribution feature data and the initial grading path, the operation weak point of the grading machine on the porosity is identified by combining the geological sensitivity analysis algorithm, and the base weak feature set is constructed, including:

[0013] The initial grading path data is subjected to gradient analysis, the influence degree of the porosity change in different regions on the grading quality is calculated, and the porosity is taken as the main dimension of the base feature;

[0014] A simulated disturbance is applied to the base region, the grading quality fluctuation data is recorded, the grading effect deviation under different geological disturbances is quantified, and the quality unstable region is identified;

[0015] The disturbance sensitivity data is clustered and analyzed, the base weak feature set containing the weak region geological parameters is constructed according to the associated pore type.

[0016] Based on the base weak feature set, the initial construction path is subjected to directional adjustment of target keeping by using the geological parameter mapping method, and the candidate optimized grading path adapted to the geological features is generated by combining the fuzzy control method, including:

[0017] The path control parameters are constructed according to the weak feature set, and the fuzzy control algorithm is established with the grading effect feedback as the input and the path parameter adjustment amount as the output;

[0018] For each grading path, the parameter adjustment amplitude is calculated by fuzzy reasoning according to the real-time detected porosity compliance rate; and the candidate optimized grading path adapted to the base pore features and targeted at the weak geology is generated according to the parameter adjustment amplitude.

[0019] The engineering feasibility of the candidate optimized grading path and the initial construction path is evaluated by using a terrain similarity measure and a geological feature projection algorithm, which includes:

[0020] The candidate optimized grading path is mapped to a geological feature space, and the terrain differences of the water-based bed path coverage area to be graded are compared by a three-dimensional point cloud similarity algorithm; the Euclidean distance of the two paths in the porosity space is calculated to determine the consistency of the geological conditions of the water-based bed to be graded;

[0021] If the Euclidean distance of the candidate optimized grading path in the geological feature space is less than or equal to the threshold value, it is determined that the engineering is feasible; if the Euclidean distance is greater than the threshold value, it is determined that the geological conditions deviate too much.

[0022] The optimal position of each path point after iteration optimization is output as the optimized grading path in combination with the optimization algorithm, which includes:

[0023] A path optimization objective function covering the porosity feature is established, the path optimization objective function is iteratively solved, the coordinate sequence of the path point is updated by iteration, and the optimized grading path is obtained in combination with the engineering feasibility determination.

[0024] The path optimization objective function F covering the porosity feature is:

[0025]

[0026] Wherein, F is the path optimization objective function value; is the total length of the grading path, wherein is the spatial coordinate of the grading path point at time j, is the spatial coordinate of the grading path point at time j+1, and r is the grading path time; represents the standard deviation of the porosity of the i-th sub-block bed area to be graded, wherein is the average porosity index of the i-th sub-block bed area to be graded, and M is the number of sub-blocks of the area to be graded; i is the sub-block coverage efficiency, wherein A c,i is the coverage area of the i-th sub-block bed area, and A z,i is the total area of the i-th sub-block bed area; 、 、 is a weight coefficient, and satisfies .

[0027] The path optimization objective function is iteratively solved, and the coordinate sequence of the path point is updated by iteration, which includes:

[0028] The particle velocity and position of each path point in the grading path are initialized, the fitness value of each path point particle is calculated, and the sequence of the path point is:

[0029]

[0030] In the formula, The spatial coordinates of the kth path point, and m is the number of path points.

[0031] The material distribution operation is:

[0032] After the leveling machine completes the diving, the GPS positioning and the inclination sensor are used to adjust the equipment levelness, the material is moved, the total station is used to position the high layer of the equipment, and the design elevation is met; the walking chassis support legs are adjusted, after the equipment is leveled, the transverse trolley and the longitudinal trolley are moved to the material starting point, and the material distribution is performed according to the material distribution path of the divided base area.

[0033] The machine moving operation is:

[0034] After the leveling and material distribution operation of the divided base area is completed, the equipment is started, the transverse trolley and the longitudinal trolley are moved to the equipment center position, the walking chassis support legs are jacked up, the material distribution chassis support legs are retracted, the walking oil cylinder is jacked up, and the propeller is moved to complete the forward movement or backward movement of the material distributor; then the material distribution chassis support legs are jacked up, the material distribution chassis support legs are retracted, and the walking oil cylinder is retracted, and the operation is continuously cycled until the leveling machine moves to the specified coordinate position.

[0035] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0036] The present application uses a multi-source perception and control system and a multi-beam sounding method to obtain data of the base of the water area to be leveled, forms an initial construction blueprint by obtaining reliable environmental data, provides a basis for optimization, and avoids blind construction; based on the base porosity distribution characteristic data and the initial leveling path, the geological sensitivity analysis algorithm is combined to identify the operation weaknesses of the leveling machine in the porosity, solve the problems of instability, subsidence or low efficiency of the leveling machine caused by the unevenness of the base during operation, and improve the adaptability of the path to the geological characteristics and reduce the construction risk by identifying these weaknesses through the geological sensitivity analysis algorithm, constructing a weak feature set, quantifying the risk area, and improving the adaptability of the path to the geological characteristics and reducing the construction risk;

[0037] The present application uses a terrain similarity measurement and geological feature projection algorithm to evaluate the engineering feasibility of the candidate optimized leveling path and the initial construction path, compares the terrain consistency of the candidate path, evaluates the geological constraints, and ensures the safety of the path; the optimization algorithm solves the problem of selecting the best solution from multiple candidate paths, and realizes the dynamic generation and online correction of the path by fusing the porosity feature analysis and the intelligent optimization algorithm, so that the efficient, uniform and high-precision autonomous leveling operation is achieved;

[0038] The target function in the path optimization method fully considers the base bed pore characteristics, fully considers the spatial heterogeneity of the pore distribution of different block base bed regions, and the compactness after grading is more uniform, each path point is iteratively optimized, the global optimal position of each path point in the grading path is obtained, the overlapping grading area in the traditional construction operation process is avoided, and dynamic adjustment planning of the path is performed in real time according to the terrain feedback data. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 is a flowchart of a base bed pore characteristic-based underwater grader path optimization method provided by an embodiment of the application;

[0040] Figure 2 is a structural schematic diagram of an underwater grader provided by an embodiment of the application;

[0041] In the figure, the underwater grader shows components including a walking chassis leg 1, a distribution chassis truss 2, a distribution chassis main beam 3, a transverse moving trolley 4, a longitudinal moving cart 5, a distribution pipe 6, a positioning instrument 7, a measuring tower 8, a walking chassis 9, a distribution chassis leg 10, and a propeller 11. DETAILED DESCRIPTION

[0042] The application will be described in detail below with reference to the accompanying drawings.

[0043] Embodiment 1

[0044] As Figure 1 described, the application provides a base bed pore characteristic-based underwater grader path optimization method, including the following steps:

[0045] Three-dimensional terrain data and pore distribution characteristic data of the base bed to be graded are measured by using a multi-source perception and control system and a multi-beam sounding method, a digital terrain model of the base bed to be graded is established, and real-time adjustment and update are performed, a path planning algorithm is used to output the positions of the path points, an initial grading path is obtained according to the positions of the path points, and an initial construction path is constructed;

[0046] Based on the base bed pore distribution characteristic data and the initial grading path, a geology sensitivity analysis algorithm is used to identify the operation weak points of the grader in the porosity, a base bed weak feature set is constructed, a geology parameter mapping method is used to perform directional adjustment of the initial construction path based on the target retention, and a fuzzy control method is used to generate a candidate optimized grading path that adapts to the geological characteristics;

[0047] The engineering feasibility of the candidate optimized grading path is evaluated by using a terrain similarity measure and a geological feature projection algorithm, and the optimal position of each path point after iteration optimization is output as the optimized grading path by combining the optimization algorithm, and based on the optimized grading path, the leveling of the underwater grading machine is completed by using the pressure sensor and the inclination sensor components in the multi-source perception and control system;

[0048] The optimization grading path parameters are dynamically adjusted according to the operation effect of the grading machine on the optimization grading path, and the underwater grading machine is controlled to complete the material distribution operation and the machine moving operation according to the action instruction;

[0049] The multi-source perception and control system is a system integrating various sensors and control technologies, which is used for acquiring and processing various data; when measuring the water area bed, various sensors are used for data acquisition, including but not limited to pressure sensors, inclination sensors, sonars, underwater cameras, and the measurement strategy can be adjusted in real time through the control system; the multi-beam sounding measures the water depth in multiple directions by emitting multiple sound beams; the obtained three-dimensional terrain data and pore distribution characteristic data of the water area bed to be graded are preprocessed; the data space is registered to a unified coordinate system, and a digital terrain model of the bed to be graded is generated by a Kriging interpolation algorithm, and a feature vector is labeled on the grid node; the multi-source data acquisition is triggered once at an interval, and the pore distribution characteristic index of the area to be graded is calculated;

[0050]

[0051] In the formula, n i is the porosity of the i-th sub-block bed area to be graded; V p,i is the pore volume of the i-th sub-block bed to be graded; V z,i is the total volume of the i-th sub-block bed to be graded, and M is the number of sub-blocks of the area to be graded;

[0052] The position of each grading path point is output by using a path planning algorithm, and the initial grading path is obtained according to the position of each grading path point, and the initial construction path is constructed, including:

[0053] The gridded data of the digital terrain of the bed to be graded is input, the path planning algorithm is used to calculate the key points of the grading path, the coordinate sequence of the path points is output to obtain the initial grading path, and the initial construction path is constructed by connecting the path points by using a uniform B-spline curve;

[0054] The path planning algorithm includes but is not limited to Dijkstra algorithm, heuristic search algorithm, and fast random tree algorithm;

[0055] Based on the pore distribution characteristic data of the bed and the initial grading path, the operation weakness of the grading machine on the porosity is identified by combining a geological sensitivity analysis algorithm, and a weak feature set of the bed is constructed, including:

[0056] Gradient analysis is performed on the initial grading path data to calculate the influence of porosity changes in different areas on the grading quality, with porosity as the main dimension of the subgrade characteristics;

[0057] Simulated disturbances are applied to the subgrade area, and grading quality fluctuation data is recorded to quantify the deviation of the grading effect under different geological disturbances and identify unstable quality areas;

[0058] Cluster analysis is performed on the disturbance sensitivity data, and based on the associated porosity types, a weak subgrade feature set containing geological parameters of weak areas is constructed;

[0059] Specifically, the gradient analysis includes determining the direction in which the gradient needs to be calculated based on the initial grading path data, using the difference method to calculate the gradient value of each path point coordinate, generating a gradient data set, calculating the average value of the gradient to analyze the gradient data, evaluating the severity of the overall gradient change, and obtaining the grading quality data; Obtain porosity data in each block area to form a porosity data set, use linear regression to establish a relationship model between porosity and grading quality, and use the regression coefficient to quantify the influence of porosity changes on grading quality; Analyze the relationship between porosity and grading quality in different areas to identify areas where porosity changes have a greater impact on grading quality;

[0060] Different types of disturbances are designed, such as vibration, pressure change, temperature change, etc.; Adjust the disturbance parameters according to the actual engineering requirements to determine the strength and frequency of the disturbance, apply the designed disturbance to the subgrade area; Use special equipment such as a vibration table, a pressure pump, etc. to realize the disturbance; During the disturbance process, the change of the grading quality is recorded in real time; Record the grading quality data after each disturbance to form a fluctuation data set; Compare the grading quality data after disturbance with the data before disturbance, calculate the deviation value of each area, the deviation value can be calculated by the following formula: deviation value = grading quality after disturbance - grading quality before disturbance, analyze the deviation data, identify areas with large deviation values; Determine the range of unstable areas, identify the specific areas of unstable grading quality according to the size of the deviation value, and determine the disturbance sensitive areas;

[0061] The disturbance sensitivity data includes parameters such as porosity, disturbance type, bias value, etc. of each area; a clustering algorithm is selected, which includes K-means clustering or hierarchical clustering; parameters of clustering are determined, and clustering analysis is performed to cluster the disturbance sensitivity data; the data is divided into different categories, and each category represents a group of areas with similar sensitivity. The associated pore types are identified, which show similar sensitivity under disturbance. Through the clustering results, the response law of different pore types to disturbance is understood; the geological parameters related to weak areas are extracted from the clustering results, such as porosity, disturbance sensitivity, bias value, etc.; the extracted features are combined into a feature set, and in actual engineering, the feature set is used to identify potential weak areas.

[0062] Based on the weak feature set of the base bed, the initial construction path is adjusted in a target-keeping and directional manner through a geological parameter mapping method, and a candidate optimized grading path that adapts to the geological features is generated by combining a fuzzy control method, which includes:

[0063] According to the weak feature set, a path control parameter is constructed, and a fuzzy control algorithm is established with the grading effect feedback as input and the path parameter adjustment amount as output;

[0064] For each grading path, the parameter adjustment amplitude is calculated through fuzzy reasoning according to the real-time detected porosity compliance rate; and a candidate optimized grading path that adapts to the base bed porosity features and targets weak geology is generated according to the parameter adjustment amplitude;

[0065] Specifically, key geological parameters such as porosity, disturbance sensitivity, bias value, etc. are extracted from the weak feature set; the influence degree of these parameters on the grading quality is analyzed to determine which parameters are the main influencing factors; according to the key parameters in the weak feature set, control variables related to the grading path are selected. A flatness threshold is used to define the maximum allowable flatness deviation; a porosity threshold is used to define the maximum allowable porosity range; a disturbance threshold is used to define the maximum allowable disturbance sensitivity; a reasonable range is set for each control variable, and all selected control variables are combined into a control parameter set; the control parameter set is represented as {flatness threshold, porosity threshold, disturbance threshold}; a fuzzy set of grading effect feedback is defined, including "good", "general", and "poor"; a fuzzy set of path parameter adjustment amount is defined, such as "fine tuning", "medium tuning", and "large tuning";

[0066] According to the flattening effect feedback and the weak feature set, a fuzzy rule is formulated, and as a specific embodiment, if the flattening effect is "good", the path parameter adjustment amount is "fine tuning"; if the flattening effect is "general", the path parameter adjustment amount is "medium tuning"; if the flattening effect is "poor", the path parameter adjustment amount is "large tuning"; the real-time detected flattening effect feedback is fuzzified and mapped into a fuzzy set; the effect feedback includes flatness deviation and porosity compliance rate; according to the fuzzy rule table, the rule corresponding to the current input is matched; the path parameter adjustment amount is calculated through fuzzy reasoning, the fuzzy output is de-fuzzified, and the specific adjustment value is obtained.

[0067] The porosity of the base bed is detected in real time, the porosity compliance rate is calculated according to the matching degree of the actual porosity and the target porosity, the porosity compliance rate is fuzzified and mapped into a fuzzy set, and according to the fuzzy rule table, the rule corresponding to the current porosity compliance rate is matched; the path parameter adjustment amount is calculated through fuzzy reasoning, the fuzzy output is de-fuzzified, and the specific adjustment value is obtained; according to the adjustment amount obtained by fuzzy reasoning, the control parameters of the flattening path are adjusted; according to the adjusted parameters, the flattening path is redesigned; a plurality of candidate optimized flattening paths are generated, each of which is adapted to the porosity characteristics of the base bed and optimized for weak geology.

[0068] The engineering feasibility of the candidate optimized flattening path and the initial construction path is evaluated by using the terrain similarity measure and the geological feature projection algorithm, which includes:

[0069] The candidate optimized flattening path is mapped to the geological feature space, and the terrain difference of the path coverage area of the water-based bed to be flattened is compared by using a three-dimensional point cloud similarity algorithm; the Euclidean distance of the two paths in the porosity space is calculated to judge the consistency of the geological conditions of the water-based bed to be flattened;

[0070] If the Euclidean distance of the candidate optimized flattening path in the geological feature space is less than or equal to a threshold value, it is determined that the engineering is feasible; if the Euclidean distance is greater than the threshold value, it is determined that the geological conditions deviate too much;

[0071] The elevation, coordinate data and geological feature data of the candidate optimized flattening path are collected, including porosity, terrain elevation, disturbance sensitivity; all the geological feature data are standardized to the same dimension, and the coordinate and elevation data of the key points are extracted from the candidate optimized flattening path.

[0072] For each path point, a feature vector is constructed, which contains the porosity, terrain elevation and disturbance sensitivity of the point; the feature vector of each path point is mapped to the geological feature space to form the feature point cloud of the path.

[0073] A three-dimensional point cloud similarity algorithm is selected, which includes an ICP (Iterative Closest Point) algorithm, a feature matching-based algorithm, etc., which is not specifically limited here; the selected algorithm is used to align the candidate path point cloud with the initial path point cloud, and the best matching between the point clouds is calculated; the similarity between the aligned point clouds is calculated, and the similarity is obtained by calculating the root mean square error or the average distance between the point clouds; according to the similarity calculation result, the terrain difference of the two path coverage areas is evaluated. The Euclidean distance of the two paths in the porosity space is calculated; according to the size of the Euclidean distance, the geological condition consistency of the two paths is evaluated; a reasonable terrain difference threshold is set to determine whether the terrain difference is within an acceptable range; a reasonable porosity Euclidean distance threshold is set to determine the consistency of the geological conditions. If the terrain difference is less than or equal to the terrain difference threshold, the terrain difference is within an acceptable range; if the porosity Euclidean distance is less than or equal to the porosity Euclidean distance threshold, the geological conditions are consistent; if both the terrain difference and the porosity distance are less than or equal to the corresponding threshold, it is determined that the candidate optimized grading path and the initial construction path have good consistency in the geological feature space, and the project is feasible; if the terrain difference or the porosity distance is greater than the corresponding threshold, it is determined that the geological conditions deviate too much, and the project is not feasible.

[0074] The output of the optimization algorithm includes:

[0075] An optimization target function covering the porosity characteristics is established, the optimization target function is iteratively solved, the coordinate sequence of the path point is updated by iteration, and the optimized grading path is obtained in combination with the project feasibility determination;

[0076] The optimization target function covering the porosity characteristics F is:

[0077]

[0078] Wherein, F is the value of the optimization target function; is the total length of the grading path, wherein is the spatial coordinate of the grading path point at time j, is the spatial coordinate of the grading path point at time j+1, and r is the grading path time; represents the standard deviation of the porosity of the i th sub-block base area of the area to be graded, wherein is the average porosity index of the i th sub-block base area of the area to be graded, and M is the number of sub-blocks of the area to be graded; i is the sub-block coverage efficiency, , wherein A c,i is the coverage area of the i th sub-block base area, A z,i is the total area of the i th sub-block base area; 、 、 is a weight coefficient, and satisfies ;

[0079] The path optimization objective function is iteratively solved, and the coordinate sequence of the path point is updated by iteration, comprising:

[0080] Initializing the particle velocity and position of each path point in the flattening path, and calculating the fitness value of each path point particle; the sequence of the path point is:

[0081]

[0082] wherein, is the spatial coordinate of the kth path point, and m is the number of path points;

[0083] The fitness F b is calculated by the following formula:

[0084]

[0085] wherein, is the target function value corresponding to the kth path point at time t+1; the higher the fitness value, the better the position of the particle corresponds to the path;

[0086] The local optimal position and the global optimal position of the path point particle are obtained, the velocity of the path point particle at the next time is calculated, and the position of the path point particle is updated;

[0087] The velocity update formula is:

[0088]

[0089] wherein, represents the velocity of particle k at time t+1, represents the velocity of particle k at time t; represents the position of particle k at time t; is an inertia weight, which controls the inertia of the particle to maintain the current motion state; c1 and c2 are individual learning factor and social learning factor respectively, which are used to control the speed of the particle to the local optimal position p b and the global optimal position g b ; r1 and r2 are two random variables distributed in the range of [0, 1]; p b is the local optimal position searched by the particle so far; g b is the global optimal position searched by the entire particle group so far.

[0090] The position is updated:

[0091]

[0092] wherein, represents the position of particle k at time t+1;

[0093] Combined with the engineering feasibility determination, the path scheme with consistent and optimal geological conditions is reserved;

[0094] According to the operation effect of the screed machine on the optimized screeding path, the optimized screeding path parameters are dynamically adjusted, and the underwater screed machine is controlled to complete the material distribution operation and the machine moving operation, including:

[0095] The pore standard rate index is obtained by the screed machine operation, and the parameters are iteratively adjusted; the screed machine is controlled according to the adjusted parameters to perform the material distribution operation and the machine moving operation;

[0096] Specifically, in the screed machine operation process, the porosity data is continuously collected, and the porosity value of each operation point is recorded; the target range of porosity is set, for each operation point, it is judged whether the porosity is within the target range, and the pore standard rate of the whole operation area is calculated; the initial screeding path parameters are set, such as material distribution speed, material distribution amount, machine moving speed, etc.; according to the pore standard rate, the parameter adjustment rule is formulated; as a specific embodiment, if the pore standard rate is lower than the target value, the material distribution amount is increased or the material distribution speed is adjusted; the screeding path parameters are dynamically adjusted according to the real-time monitored pore standard rate; the screed machine is controlled according to the adjusted parameters to perform the material distribution operation and the machine moving operation.

[0097] Example 2

[0098] As Figure 2 shown, the underwater screed machine shows components including walking chassis outrigger 1, material distribution chassis truss 2, material distribution chassis girder 3, transverse moving trolley 4, longitudinal moving cart 5, material distribution pipe 6, positioning instrument 7, measuring tower 8, walking chassis 9, material distribution chassis outrigger 10, propeller 11; the underwater screed machine includes power driving device, execution screeding work device, support and frame structure device, positioning and guiding system, multi-source perception and control system, the execution screeding work device is located in the center of the screed machine, the power driving device is located in the periphery of the execution screeding work device, the support and frame structure device connects the power driving device and the execution screeding work device, the multi-source perception and control system is connected with the power driving device, the execution screeding device and the support and frame structure device, and the positioning and guiding system is connected with the multi-source perception and control system.

[0099] Further, the power driving device includes a propeller, a walking chassis outrigger, and a material distribution chassis outrigger, the walking chassis outrigger is located at the four corners of the periphery of the screed machine, the material distribution chassis outrigger is located inside the walking chassis outrigger, and the propeller is connected with the material distribution chassis outrigger and the walking chassis outrigger.

[0100] Further, the execution flattening device comprises a material distribution hopper, a transverse moving trolley, and a longitudinal moving cart, the material distribution hopper is connected with the transverse moving trolley, the transverse moving trolley is connected with the longitudinal moving cart, and the longitudinal moving cart is connected with the support and frame structure device.

[0101] Further, the support and frame structure device comprises a material distribution chassis truss and a material distribution chassis girder, the material distribution chassis truss is located at both sides of the periphery of the underwater flattening machine, and the material distribution chassis girder is connected with the material distribution chassis truss.

[0102] In particular, the positioning and guiding system comprises a positioning instrument and a measuring tower, the positioning instrument is located at the top of the measuring tower, and the measuring tower is located at the four corners of the underwater flattening machine and connected with the material distribution chassis truss.

[0103] In particular, the multi-source sensing and control system comprises a pressure sensor, an inclination sensor, a sonar, and an underwater camera, the pressure sensor and the inclination sensor are installed at the center of the material distribution chassis truss in the support and frame structure device and are rigidly connected, the sonar and the underwater camera are installed at the transverse moving trolley in the execution flattening device, and the sensor assembly is connected with the power driving device, the execution flattening device, and the positioning and guiding system.

[0104] After the flattening machine completes the diving, the horizontal degree of the device is adjusted by using the GPS positioning and the inclination sensor, the material is moved, the high layer of the device is positioned by using the total station, and the design elevation is met; the walking chassis support legs are adjusted, the transverse moving trolley and the longitudinal moving cart are moved to the material starting point after the device is leveled, and the material is distributed according to the material distribution path of the divided block bed area;

[0105] The machine moving operation specifically comprises:

[0106] After the flattening and material distribution operation of the divided block bed area is completed, the device is started, the transverse moving trolley and the longitudinal moving cart are moved to the center position of the device, the walking chassis support legs are lifted, the material distribution chassis support legs are retracted, the walking oil cylinder is lifted, the propeller is moved, the material distribution machine is moved forward or backward, then the material distribution chassis support legs are lifted, the material distribution chassis support legs are retracted, the walking oil cylinder is retracted, and the operation is continuously cycled until the flattening machine moves to the specified coordinate position.

[0107] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some examples, well-known methods, structures, and techniques are not shown in detail in order not to obscure the understanding of the present specification.

[0108] Furthermore, those skilled in the art will recognize that, in the practice of the present application, residual amounts of the starting materials, intermediates, and processing agents, for example, can be present in the products which are prepared according to the procedures of the present application. In addition, those skilled in the art will recognize that, while certain aspects of the embodiments disclosed herein can include some features of the described embodiments, not others, combinations of these features are within the scope of the application and form different embodiments. Any of the claimed embodiments can also be used in combination with one another, in any combination.

Claims

1. A path optimization method for underwater leveling machines based on the porosity characteristics of the substrate bed, characterized in that, The method comprises the following steps: Three-dimensional terrain data and pore distribution characteristic data of the water area subgrade to be flattened are measured by using a multi-source perception and control system and a multi-beam sounding method, a digital terrain model of the water area subgrade to be flattened is established, and real-time adjustment and update are performed, a position of each flattening path point is output by using a path planning algorithm, an initial flattening path is obtained according to the position of each flattening path point, and an initial construction path is constructed; Based on the pore distribution characteristic data of the subgrade and the initial flattening path, a weak feature set of the subgrade is constructed by combining a geological sensitivity analysis algorithm to identify weak points of the flattening machine in porosity, including: Gradient analysis is performed on the initial flattening path data, the influence degree of porosity variation in different regions on the flattening quality is calculated, and the porosity is taken as the main dimension of the subgrade feature; a simulation disturbance is applied to the subgrade region, and flattening quality fluctuation data are recorded, the flattening effect deviation under different geological disturbances is quantified, and a quality unstable region is identified; the disturbance sensitivity data are clustered and analyzed, the weak feature set of the subgrade containing weak region geological parameters is constructed according to the associated pore types; Based on the weak feature set of the subgrade, the initial construction path is directionally adjusted by target keeping through a geological parameter mapping method, and a candidate optimized flattening path adapted to the geological features is generated by combining a fuzzy control method; The engineering feasibility of the candidate optimized flattening path is evaluated by using a terrain similarity measurement and a geological feature projection algorithm, including: The candidate optimized flattening path is mapped to the geological feature space, the terrain difference of the path coverage region of the water area subgrade to be flattened is compared by using a three-dimensional point cloud similarity algorithm; the Euclidean distance of the two paths in the porosity space is calculated to judge the consistency of the geological conditions of the water area subgrade to be flattened; If the Euclidean distance of the candidate optimized flattening path in the geological feature space is less than or equal to a threshold value, it is determined that the engineering is feasible; if the Euclidean distance is greater than the threshold value, it is determined that the geological conditions deviate too much; The optimal position of each path point after iteration optimization is output as an optimized flattening path by combining an optimization algorithm, and the leveling of the underwater flattening machine is completed by using the pressure sensor and the inclination sensor components in the multi-source perception and control system based on the optimized flattening path; The optimized flattening path parameters are dynamically adjusted according to the operation effect of the flattening machine on the optimized flattening path, and the underwater flattening machine is controlled to complete the material distribution operation and the machine moving operation according to the action instructions.

2. The method of claim 1, wherein, The position of each flattening path point is output by using a path planning algorithm, the initial flattening path is obtained according to the position of each flattening path point, and the initial construction path is constructed, including: The gridded data of the digital terrain of the water area subgrade to be flattened is input, a path planning algorithm is used to calculate a flattening path key point set, a path point coordinate sequence is output to obtain an initial flattening path, and a uniform B-spline curve is used to connect the path points to construct an initial construction path.

3. The method of claim 1, wherein, Based on the weak feature set of the subgrade, the initial construction path is directionally adjusted by target keeping through a geological parameter mapping method, and a candidate optimized flattening path adapted to the geological features is generated by combining a fuzzy control method, including: Path control parameters are constructed according to the weak feature set, a fuzzy control algorithm is established with flattening effect feedback as input and path parameter adjustment amount as output; For each grading path, a parameter adjustment range is calculated by fuzzy reasoning according to the real-time detected porosity compliance rate; and a candidate optimized grading path is generated according to the parameter adjustment range, which is adaptive to the porosity characteristics of the subgrade and targets weak geology.

4. The method of claim 1, wherein, The optimal position of each path point after iteration optimization is output as the optimized grading path by combining the optimization algorithm, including: A path optimization objective function covering porosity characteristics is established, and the path optimization objective function is iteratively solved to obtain the optimized grading path by iteratively updating the coordinate sequence of the path points and combining the engineering feasibility determination.

5. The method of claim 4, wherein, The path optimization objective function F covering porosity characteristics is: wherein F is the path optimization objective function value; is the total length of the grading path, wherein (xj, yj) is the spatial coordinate of the grading path point at time j, , , ) is the spatial coordinate of the grading path point at time j+1, and r is the grading path time; , , ) is the spatial coordinate of the grading path point at time j+1, and r is the grading path time; represents the standard deviation of the porosity of the i-th sub-block base area of the area to be graded, wherein is the average porosity index of the i-th sub-block base area of the area to be graded, and M is the number of sub-blocks of the area to be graded; is the sub-block coverage efficiency, wherein is the coverage area of the i-th sub-block base area, is the total area of the i-th sub-block base area; , , is a weight coefficient, and satisfies + + =1.

6. The method of claim 4, wherein, The path optimization objective function is iteratively solved to obtain the coordinate sequence of the path points by iteratively updating the coordinate sequence of the path points, including: The particle velocity and position of each path point in the grading path are initialized, the fitness value of each path point particle is calculated, and the sequence of the path points is: In the formula, ( ) represents the spatial coordinates of the k-th path point, and m represents the number of path points.

7. The method of claim 1, wherein, The material placement operation is: After the grader completes the diving, the device levelness is adjusted using the GPS positioning and the inclination sensor, the material is moved, the device elevation is positioned using the total station, and the design elevation is met; the walking chassis support legs are adjusted, the grader is leveled, the transverse trolley and the longitudinal carriage are moved to the material starting point, and the material is placed according to the material path of the determined subgrade area.

8. The method of claim 1, wherein, The machine moving operation is: After the grading and material placement operation for the subgrade area is completed, the device is started, the transverse trolley and the longitudinal carriage are moved to the device center position, the walking chassis support legs are jacked up, the material placement chassis support legs are retracted, the walking oil cylinder is jacked up, the propeller is moved, and the material placement machine is moved forward or backward; then the material placement chassis support legs are jacked up, the material placement chassis support legs are retracted, the walking oil cylinder is retracted, and the operation is continuously cycled until the grader is moved to the specified coordinate position.

Images