Detection device, method, equipment and medium for manufacturing abnormity of ship propulsion device

Abstract

The invention discloses a device, method and equipment for detecting manufacturing abnormity of a ship propulsion device and a medium, and belongs to the technical field of ship propulsion devices. The detection device comprises a point cloud data acquisition module used for acquiring point cloud data of propeller blades; the blade included angle identification module is used for identifying included angles among a plurality of blades of the propeller according to the point cloud data; the point cloud data comparison module is used for determining comparison point cloud data from each paddle according to the included angle and performing comparison to obtain a comparison result; the consistency determination module is used for determining whether the blade parameters have consistency or not according to a comparison result of the comparison point cloud data; and the report information generation module is used for generating report information with abnormal consistency when the blade parameters do not have consistency. According to the scheme, the manufacturing abnormity of the marine propeller can be detected by comparing the detected propeller with the standard point cloud data, the detection efficiency and precision of the marine propeller are improved, and manpower and time are saved.

Description

Technical Field

[0001] The present application belongs to the technical field of ship propulsion devices, and specifically relates to a device, method, equipment and medium for detecting manufacturing anomalies of ship propulsion devices. Background Art

[0002] As the most important propulsion device for ships, propellers convert the engine's rotational power into propulsion. They are an indispensable part of a ship's power system and have high quality requirements. Therefore, marine propellers must undergo rigorous qualification testing to ensure their normal operation.

[0003] Currently, marine propeller inspections often rely on manual testing of blade length, angle, and curvature. This requires high technical skills from the inspectors and is inefficient. Furthermore, if these tests are time-consuming during the manufacturing process, they can significantly impact the overall manufacturing process. Therefore, the challenge of accurately and efficiently detecting manufacturing anomalies in marine propellers remains a pressing issue for those skilled in the art. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a device, method, equipment and medium for detecting manufacturing anomalies of a ship propulsion device, which can improve the efficiency and accuracy of ship propeller testing and reduce the requirements for staff.

[0005] In a first aspect, an embodiment of the present application provides a device for detecting manufacturing anomalies of a ship propulsion device, the device comprising:

[0006] A point cloud data acquisition module, used to acquire point cloud data of propeller blades;

[0007] a blade angle recognition module, configured to recognize the angles between the plurality of blades of the propeller based on the point cloud data;

[0008] a point cloud data comparison module, configured to determine comparison point cloud data from each blade according to the included angle, and perform comparison to obtain a comparison result;

[0009] a consistency determination module, configured to determine whether the blade parameters are consistent based on a comparison result between the comparison point cloud data;

[0010] The report information generating module is used to generate report information of consistency abnormality when the blade parameters are inconsistent.

[0011] Furthermore, the device further comprises:

[0012] a blade parameter identification module, configured to identify blade curvatures and blade lengths of the plurality of blades of the propeller based on the point cloud data;

[0013] The extraction boundary determination module is used to determine the extraction boundary of the comparison point cloud data from each blade according to the blade curvature and the blade length.

[0014] Furthermore, the extraction boundary determination module is further configured to:

[0015] determining a width boundary of the comparison point cloud data according to the blade curvature;

[0016] as well as,

[0017] The length boundary of the comparison point cloud data is determined according to the blade length.

[0018] Furthermore, the point cloud data comparison module is specifically used to:

[0019] Determining comparative point cloud data from each blade according to the angle;

[0020] Annotating the compared point cloud data according to the blades to which they belong;

[0021] Rotating the comparison point cloud data according to the angle to obtain point cloud information with corresponding relationship;

[0022] The comparison result is determined based on the distance information between the points with corresponding point cloud information.

[0023] Furthermore, the point cloud data comparison module is also used to:

[0024] Determine a comparison cell of the comparison point cloud data on each blade;

[0025] According to the angle and the position information of the comparison cell, the points in the comparison cell are spatially transformed to obtain the distance information between the points and determine the comparison result.

[0026] Furthermore, the device further comprises:

[0027] a hub point cloud data recognition module, configured to recognize hub point cloud data in the point cloud data;

[0028] a hub comparison result acquisition module, configured to compare the hub point cloud data with predetermined hub model data to obtain a hub comparison result;

[0029] The hub manufacturing standard judgment module is used to determine whether the propeller hub meets the manufacturing standard based on the hub comparison result.

[0030] Furthermore, the hub comparison result acquisition module is further configured to:

[0031] Performing spatial transformation on the hub model data to obtain a spatial pose that matches the hub point cloud data;

[0032] Identify the plane data and surface data of the hub model in the current spatial position;

[0033] A hub comparison result is obtained based on comparing the plane point cloud data and the curved surface data with the plane point cloud data and the curved surface point cloud data of the hub point cloud data.

[0034] In a second aspect, an embodiment of the present application provides a method for detecting manufacturing anomalies of a ship propulsion device, the method comprising:

[0035] Obtain point cloud data of propeller blades;

[0036] identifying angles between a plurality of blades of the propeller according to the point cloud data;

[0037] Determining comparison point cloud data from each blade according to the included angle, and performing comparison to obtain a comparison result;

[0038] Determining whether the blade parameters are consistent based on a comparison result between the comparison point cloud data;

[0039] If not, a consistency exception report will be generated.

[0040] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0041] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0042] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0043] In an embodiment of the present application, point cloud data of a propeller blade is obtained; based on the point cloud data, the angle between the multiple blades of the propeller is identified; based on the angle, comparison point cloud data is determined from each blade, and a comparison result is obtained; based on the comparison result between the comparison point cloud data, whether the blade parameters are consistent is determined; if not, a report information indicating consistency anomaly is generated. Through the above-mentioned method for detecting manufacturing anomalies of a ship propulsion device, consistency detection of manufacturing anomalies of a ship propeller can be performed by establishing and comparing point cloud data of the tested propeller and a standard propeller, thereby improving the efficiency and accuracy of ship propeller detection and saving manpower and time. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 1 is a schematic structural diagram of a device for detecting manufacturing anomalies of a ship propulsion device provided in Example 1 of the present application;

[0045] Figure 2 This is a schematic structural diagram of a marine propeller provided in Example 1 of the present application;

[0046] Figure 3 Schematic diagram of the structure of a device for detecting manufacturing anomalies of a ship propulsion device provided in Example 2 of the present application;

[0047] Figure 4 Schematic diagram of the structure of a device for detecting manufacturing anomalies of a ship propulsion device provided in Example 3 of the present application;

[0048] Figure 5 1 is a schematic structural diagram of a device for detecting manufacturing anomalies of a ship propulsion device provided in Example 4 of the present application;

[0049] Figure 6 1 is a schematic structural diagram of a device for detecting manufacturing anomalies of a ship propulsion device provided in Example 5 of the present application;

[0050] Figure 7 1 is a schematic structural diagram of a device for detecting manufacturing anomalies of a ship propulsion device provided in Example 6 of the present application;

[0051] Figure 8 Schematic diagram of the structure of a device for detecting manufacturing anomalies of a ship propulsion device provided in Example 7 of the present application;

[0052] Figure 9 1 is a flow chart of a method for detecting manufacturing anomalies of a ship propulsion device provided in Example 8 of the present application;

[0053] Figure 10 This is a structural diagram of the electronic device provided in Example 9 of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. It should also be noted that, for ease of description, only parts related to the present application, not all of the contents, are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0055] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0056] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0057] The following, in conjunction with the accompanying drawings, describes in detail the device, method, equipment and medium for detecting manufacturing anomalies of a ship propulsion device provided in the embodiments of the present application through specific embodiments and their application scenarios.

[0058] Example 1

[0059] Figure 1 This is a schematic diagram of the structure of the device for detecting manufacturing anomalies of a ship propulsion device provided in Example 1 of the present application. Figure 1 As shown, the specific steps include:

[0060] a point cloud data acquisition module 110 for acquiring point cloud data of propeller blades;

[0061] a blade angle identification module 120 for identifying the angles between the plurality of blades of the propeller based on the point cloud data;

[0062] a point cloud data comparison module 130 for determining comparison point cloud data from each blade according to the angle, and performing comparison to obtain a comparison result;

[0063] A consistency determination module 140 is configured to determine whether the blade parameters are consistent based on the comparison result between the comparison point cloud data;

[0064] The report information generating module 150 is configured to generate report information indicating that the blade parameters are inconsistent.

[0065] First of all, the application scenario of this solution can be a scenario where an intelligent terminal or a test platform compares the point cloud data of the tested marine propeller with the point cloud data of a standard propeller for consistency, or compares the consistency of each blade based on the point cloud data of the tested marine propeller to determine whether there is a manufacturing abnormality in the tested marine propeller.

[0066] Based on the above application scenarios, it can be understood that the execution subject of this application can be the smart terminal or the test platform, or the test software running in the smart terminal, and no excessive restrictions are made here.

[0067] In this embodiment, a marine propeller can be used to convert engine rotational power into propulsion. Based on its structure, a marine propeller can be divided into a blade portion and a hub portion. The number of blades can be two or more, each blade can be connected to the hub, and the rearward surface of the blade is a helical surface or a helical-like surface.

[0068] Point cloud data acquisition module 110 can be a program designed for an intelligent terminal to acquire propeller blade point cloud data. Point cloud data can be a set of point data obtained by obtaining the spatial coordinates of each sampling point on the surface of a product using a measuring instrument during reverse engineering. Reverse engineering can be a method of performing three-dimensional scanning or measurement of an object's surface using a 3D laser scanner or a three-dimensional coordinate measuring machine to obtain the object's three-dimensional point data. Reverse engineering software can then be used to organize and edit the obtained three-dimensional scan data and obtain the required three-dimensional characteristic curves, ultimately expressing the object's appearance through a three-dimensional surface.

[0069] In this solution, point cloud data of propeller blades can be obtained through 3D laser scanning technology. Specifically, the principle of laser ranging can be utilized. By emitting a laser towards the propeller under test, the distance of each propeller data point can be calculated based on the laser propagation speed and the time it takes to receive the laser. Based on this distance and time information, a large number of dense points on the surface of the propeller under test, as well as information such as the 3D coordinates, reflectivity, and texture of these points, can be obtained. After obtaining the information of the surface points of the propeller under test, the intelligent terminal then filters these dense points to remove unnecessary stray points and obtain point cloud data.

[0070] The blade angle identification module 120 can be a program designed by the intelligent terminal for identifying blade angles. The blade angle can be the minimum angle formed by two adjacent propeller blades intersecting the propeller hub. During the calculation process, the minimum angle formed by two propeller blades at the same position, such as the centerline, intersecting the propeller hub can be used instead.

[0071] Figure 2 This is a structural diagram of a marine propeller provided in Example 1 of the present application. Figure 2 As shown, the angle α is the angle between the blades. The hub is the part where the blades are mounted and connected. It is located at the center of the propeller and is usually conical or truncated cone-shaped, driving the propeller to rotate.

[0072] The method for identifying the angle between the propeller blades can be to first determine the extraction boundary of the point cloud data, distinguish the position of each propeller blade according to the boundary, and then select a point at the same position of the two propeller blades to be identified on the plane where the hub section is located, take the line connecting the center point of the hub section and the two propeller blade points, and calculate the minimum angle formed by the two straight lines compared to the center point of the hub as the angle of the blade to be identified.

[0073] In this solution, a pre-built three-dimensional convolutional neural network (3DCNN) model can be used in the blade angle recognition module. Specifically, high-precision point cloud data of propeller blades can be obtained using devices such as laser radar and structured light scanning. In order to make the model have better generalization capabilities, it is necessary to collect data from multiple aspects such as different angles, different lighting conditions, and different propeller models. The collected point cloud data is pre-processed, including removing noise points, data normalization (normalizing the coordinate range of the point cloud data to a certain interval, such as [0, 1]), and data enhancement (expanding the data set by randomly rotating, translating, and scaling the point cloud data to increase data diversity). The true value of the angle between multiple blades in each propeller point cloud data is manually or semi-automatically labeled as supervisory information for model training. The structure of the three-dimensional convolutional neural network model can include an input layer that takes the pre-processed point cloud data as input. Since it is three-dimensional data, the input format can be an array of point coordinates (x, y, z). The convolution layer uses three-dimensional convolution kernels to perform convolution operations on point cloud data to extract local features at different scales. For example, multiple convolution layers can be set up, gradually increasing the number and size of convolution kernels to enable the model to learn more complex features. During the convolution process, the stride length of the convolution kernel is controlled by the stride to adjust the size of the feature map. The pooling layer uses operations such as max pooling or average pooling to downsample the feature map output by the convolution layer, reducing the data volume while retaining important feature information. Pooling reduces the computational complexity of the model and prevents overfitting. The fully connected layer expands the feature map after convolution and pooling into a one-dimensional vector and inputs it into the fully connected layer. The fully connected layer further transforms and combines the features through matrix multiplication and activation functions to extract global features. The output layer outputs the predicted angle values between multiple blades based on the angle recognition task requirements. The output layer can use a linear activation function to directly output continuous angle values. Specifically, an appropriate loss function can be selected to measure the difference between the model's predicted value and the true value. For example, the mean squared error (MSE) loss function is used in regression tasks to calculate the mean squared error between the predicted angle and the true angle. Using optimizers such as stochastic gradient descent (SGD) and Adam, the model parameters are updated based on the gradient of the loss function to minimize the loss function. During training, appropriate hyperparameters such as the learning rate and number of iterations can be set. During training, the annotated point cloud data can be divided into training, validation, and test sets. The model is iteratively trained on the training set, with a batch of point cloud data input each time. The loss function is calculated and the model parameters are updated. The model performance is evaluated on the validation set, and hyperparameters are adjusted based on the results to prevent overfitting. Once the model performance on the validation set stabilizes, a final evaluation is performed on the test set. Metrics such as mean squared error (MSE) and mean absolute error (MAE) are used to evaluate the model's prediction accuracy.By calculating these metrics, we can understand the average error between the model's predicted angle and the true value. The trained model is then applied to the actual propeller blade angle recognition task. By inputting newly collected point cloud data, the model outputs a predicted blade angle value, providing a basis for subsequent analysis and decision-making.

[0074] The point cloud data comparison module 130 can be a program design for comparing point cloud data in an intelligent terminal. The comparison point cloud data can be a reference point cloud data of a certain area selected at the same position of each blade, which is used to determine whether the tested propeller blade is consistent with the standard propeller blade. Specifically, the point cloud data contained in the entire blade can be compared with the point cloud data of the standard propeller blade. However, since the point cloud data of the entire blade is too dense, the amount of calculation required for consistency comparison detection is large, and the calculation time is long. Therefore, in this solution, a certain area of the blade can also be selected, and then the area is rotated multiple times according to the blade angle to obtain the regional point cloud data of each propeller blade, and the comparison point cloud data is composed for calculation to reduce the amount of calculation. For example, Figure 2 Region 1 is selected and rotated four times according to the blade angle to obtain regions 2, 3, and 4 at the same position on each blade. The point cloud data within regions 1, 2, 3, and 4 constitute the comparison point cloud data of the propeller blade. The comparison result can be the similarity between the reference point cloud data of the tested propeller blade and the reference point cloud data of the standard propeller blade.

[0075] Another comparison method is to compare the consistency between the blades of this propeller. Specifically, a region can be selected at the same position on each blade, the normal vector of the plane in which each region lies is calculated, and the direction of the normal vector of each region is compared to see if there is any deviation. In this embodiment, the comparison method can also be to select a region at the same position on each blade, rotate the selected region of one blade according to the angle between the blades, and compare the similarity of this region with the region at the same position on the adjacent blade.

[0076] The method for determining the comparison point cloud data may be to select a blade in the measurement plane to obtain the point cloud data of a random area on the blade, and after rotating the measured propeller by the angle between the blades, obtain the point cloud data of the original area position again, and repeat the process the same number of times as the number of blades to form a set of comparison point cloud data that can be compared with the point cloud data of the same position of a qualified propeller. Among them, the method for determining the measurement plane may be to randomly find three non-collinear points in the point cloud data of the propeller, determine a plane through the three points, and find points from the point cloud data of the propeller whose distance to the plane is less than a preset distance. Repeatedly update the three selected points to determine a new plane, and select the plane with the most points whose distance to the plane is less than a preset distance as the measurement plane. The method for determining the comparison result may be to compare the reference point cloud data of the measured propeller blade with the reference point cloud data of the standard propeller blade, calculate the degree of similarity between the two, and express the comparison result with the similarity.

[0077] In this solution, the point cloud data comparison module can use local feature descriptors (such as feature descriptors in PointNet++) to extract local features of each blade point cloud data.

[0078] PointNet++, a deep learning model developed based on PointNet, is designed for processing point cloud data. Through multi-level local feature extraction, it better captures the local geometric structure and semantic information of point cloud data. PointNet++ acquires point cloud data for each propeller blade. Similar to the data preprocessing performed in the blade angle recognition module, noise removal and normalization are performed to ensure data quality and consistency. The point cloud data for each blade is organized into a suitable format for input into the PointNet++ model. Point cloud data can be represented as a set of point coordinates, with each point containing its position information (x, y, z) in three-dimensional space. This solution uses the Farthest Point Sampling (FPS) algorithm to select a certain number of representative points from the input point cloud data, reducing the number of point cloud data while preserving the data distribution. These sampled points serve as the centers for subsequent local feature extraction. With the sampled point as the center, the surrounding points are divided into different local regions (neighborhoods) by setting a radius or number of neighborhood points. The point cloud data within each local region is used to extract local features. For each local region of point cloud data, a PointNet network structure (including a multi-layer perceptron and maximum pooling operations) is used to extract local features. The PointNet network transforms and combines the features of each point through a multi-layer perceptron, and then uses a maximum pooling operation to extract the global features of the local region as the feature descriptor for that local region. The extracted local features are mapped back to the original point cloud data through a feature propagation operation, so that each point has a feature descriptor for its local region. In this way, each point in the point cloud data of each blade contains the geometric and semantic information of the surrounding local region.

[0079] Specifically, based on the local feature descriptors of each blade point cloud data extracted, feature matching algorithms (such as nearest neighbor matching, matching based on distance metrics, etc.) can be used to find the corresponding local areas on different blades. By comparing the feature descriptors of these corresponding local areas, the similarities and differences between different blades can be determined. The feature descriptors of the matched local areas are compared and analyzed, and the difference metrics between them (such as Euclidean distance, cosine similarity, etc.) are calculated to obtain the point cloud data comparison results. These comparison results can be used to judge the consistency of blade parameters and provide a basis for subsequent decision-making. This setting of the present scheme can effectively construct a three-dimensional convolutional neural network model for blade angle recognition, and use the feature descriptors in PointNet++ to extract local features of point cloud data for comparative analysis.

[0080] In this embodiment, the following specific methods of point cloud comparison are provided for reference:

[0081] Calculate the feature description factors of the original blade point cloud data and the rotated blade point cloud data respectively, compare the points in the two point clouds based on the feature description factors, randomly select three or more pairs of comparison points, and calculate the rotation and translation matrices under the comparison, and calculate the corresponding error at this time. Repeat the steps of selecting comparison points, calculating the transformation matrix, and calculating the error, and take the rotation and displacement with the smallest error as the final result, and calculate the degree of overlap between the original blade point cloud data and the rotated blade point cloud data at this time. The core code of this method can be:

[0082] pcl::SampleConsensusInitialAlignment<pcl::PointXYZ,pcl::PointXYZ,pcl::FPF HSignature33> sac_ia;

[0083] sac_ia.setInputSource(source);

[0084] sac_ia.setSourceFeatures(source_fpfh);

[0085] sac_ia.setInputTarget(target);

[0086] sac_ia.setTargetFeatures(target_fpfh);

[0087] sac_ia.setMinSampleDistance(0.1);

[0088] sac_ia.setCorrespondenceRandomness(6);

[0089] pointcloud::Ptr align(new pointcloud);

[0090] sac_ia.align(*align);

[0091] In this solution, principal component analysis can also be used to compare point cloud data. For example, the principal axis directions of the original blade point cloud data and the rotated blade point cloud data are used for comparison. First, the covariance matrix of the two sets of point cloud data is calculated, and the main characteristic components, that is, the principal axis directions of the point cloud data, are calculated based on the covariance matrix. Then, the rotation matrix is obtained through the principal axis direction, and the offset of the center coordinates of the two sets of point clouds is calculated to directly obtain the translation vector. Finally, after the original blade point cloud data is transformed by the matrix, its degree of overlap with the rotated point cloud data is calculated. The core code of this method can be:

[0092]

[0093] Using a method similar to the above, the blade point cloud data can be compared.

[0094] Consistency determination module 140 may be a program designed by the intelligent terminal to determine whether blade parameters are consistent. Blade parameters may be geometric parameters of the propeller blades. These may include parameters such as the number of propeller blades, the angle between blades, and the length of the blades. Consistency may be a requirement criterion that describes whether the parameters of the tested propeller are consistent with those of qualified propellers. If consistency does not meet the requirements, the tested propeller fails the qualification test.

[0095] The method for determining whether the blade parameters are consistent can be to pre-set that when the comparison result reaches a preset value, the blade parameters are determined to be consistent. When the intelligent terminal obtains the comparison result between the comparison point cloud data, the comparison result is compared with the preset value to determine whether the measured propeller parameters are consistent. For example, if the comparison result is set to 97%, the blade parameters are determined to be consistent. The comparison result obtained is 93%, which does not reach the preset value, so the blade parameters are not consistent. If the comparison result is between 93% and 97%, a manual re-inspection instruction information can be generated so that the staff can re-inspect it.

[0096] Report information generation module 150 can be a program designed for the intelligent terminal to generate consistency exception report information. The report information can be relevant information that informs personnel that the tested propeller has failed. The report information may include information such as the tested propeller number and whether the propeller has consistency exceptions. For example, marine propeller No. 399, with a blade angle of 43°, has a consistency exception and failed the qualification test.

[0097] The method for generating a consistency exception can be that the test platform receives a signal of inconsistency and then sends a consistency exception report to the staff's smart terminal device. The staff's smart terminal device can be a multimedia device connected to the test platform for monitoring the test process and receiving test results. For example, a mobile phone, computer, or tablet computer.

[0098] It is understandable that, in another embodiment, when the comparison result is consistent, a consistency report may be generated to inform the staff of the final result of the current marine propeller inspection.

[0099] In an embodiment of the present application, a point cloud data acquisition module is used to acquire point cloud data of propeller blades; a blade angle identification module is used to identify the angle between multiple blades of the propeller based on the point cloud data; a point cloud data comparison module is used to determine comparison point cloud data from each blade based on the angle, and compare to obtain a comparison result; a consistency determination module is used to determine whether the blade parameters are consistent based on the comparison result between the comparison point cloud data; and a report information generation module is used to generate report information of consistency anomaly when the blade parameters are not consistent. By using the above-mentioned device for detecting manufacturing anomalies of a ship propulsion device, consistency detection of manufacturing anomalies of a ship propeller can be performed by establishing and comparing the point cloud data of the tested propeller and the standard propeller, thereby improving the efficiency and accuracy of ship propeller detection and saving manpower and time.

[0100] Example 2

[0101] Figure 3 This is a schematic diagram of the structure of a device for detecting manufacturing anomalies in a ship propulsion device, provided in Example 2 of the present application. This solution provides a superior improvement over the aforementioned embodiment, specifically comprising: the device further comprising: a blade parameter identification module for identifying the blade curvature and blade length of the propeller's multiple blades based on the point cloud data; and an extraction boundary determination module for determining an extraction boundary for comparison point cloud data on each blade based on the blade curvature and blade length.

[0102] like Figure 3 As shown, specifically including the following:

[0103] a point cloud data acquisition module 310 for acquiring point cloud data of propeller blades;

[0104] a blade angle identification module 320 for identifying the angles between the plurality of blades of the propeller based on the point cloud data;

[0105] a point cloud data comparison module 330 for determining comparison point cloud data from each blade according to the included angle, and performing comparison to obtain a comparison result;

[0106] A consistency determination module 340 is configured to determine whether the blade parameters are consistent based on the comparison result between the comparison point cloud data;

[0107] The report information generating module 350 is configured to generate report information of consistency abnormality when the blade parameters are inconsistent.

[0108] a blade parameter identification module 360 for identifying blade curvatures and blade lengths of the plurality of blades of the propeller based on the point cloud data;

[0109] The extraction boundary determination module 370 is configured to determine an extraction boundary of the comparison point cloud data from each blade according to the blade curvature and the blade length.

[0110] Blade parameter identification module 360 can be a program designed by an intelligent terminal to identify blade curvature and blade parameters. Blade curvature can be the ratio of the tangent angle of a point on the blade's curved edge away from the hub to its arc length. Defined by differentiation, it indicates the degree to which the curve deviates from a straight line. Blade length can be the distance between the blade's edge curve point away from the hub and the hub center point, as measured in the blade point cloud data on the same plane as the hub section.

[0111] The blade curvature can be identified by selecting a random point on the blade's curved edge away from the hub and calculating the ratio of the tangent angle to the arc length at that point as the blade curvature at that point. The blade length can be identified by selecting a random point on the blade's curved edge away from the hub from the blade point cloud data on the same plane as the hub section and measuring the distance from that point to the hub center. The selected measurement points are repeatedly updated, and the point farthest from the hub center is selected. The distance from that point to the hub center is used as the blade length.

[0112] Extraction boundary determination module 370 may be a program designed by the intelligent terminal to determine the extraction boundary of the comparison point cloud data. The extraction boundary of the comparison point cloud data may be a selected boundary of the comparison point cloud data, which may be the length and width boundaries of the extracted rectangle of the comparison point cloud. It is understood that the shape of the extraction boundary of the comparison point cloud data is not limited to a rectangle, but may also be a square, a circle, or any other arbitrary shape.

[0113] The method for determining the extraction boundary of the comparison point cloud data can be to determine the width boundary of the point cloud data based on the curvature of the blade and to determine the length boundary of the point cloud data based on the length of the blade. The width boundary of the point cloud data can be the length of the line segment on the side with the shorter length value within the extraction boundary of the point cloud data. The length boundary of the point cloud data can be the length of the line segment on the side with the longer length value within the extraction boundary of the point cloud data.

[0114] For example, if the blade length is 2m, 2m is used as the length boundary. For the determination of the width boundary, the curvature of a blade may be different at different locations. The same width boundary determination method can be adopted for all of them, for example, the width boundary can be uniformly set to 3cm. Alternatively, each area can be calculated separately, for example, when the curvature is less than 0.5m, the width boundary can be set to 3cm. -1 , then 5cm is determined as the width boundary; when the curvature reaches 0.5m -1 When , 2.5cm is used as the width boundary.

[0115] The advantage of this setting of the present scheme is that the extraction boundary of the point cloud data can be determined according to the curvature and length of the propeller blades, which limits the selection range of the point cloud data and removes some stray points outside the propeller, so that the point cloud data of the propeller can more realistically and accurately reflect the blade parameters of the measured propeller.

[0116] Example 3

[0117] Figure 4 This is a schematic diagram of the structure of the device for detecting manufacturing anomalies of a ship propulsion device provided in Example 3 of the present application. This solution provides a superior improvement over the above-mentioned embodiment, specifically: the extraction boundary determination module is further configured to: determine the width boundary of the comparison point cloud data based on the blade curvature; and determine the length boundary of the comparison point cloud data based on the blade length.

[0118] like Figure 4 As shown, specifically including the following:

[0119] a point cloud data acquisition module 410 for acquiring point cloud data of propeller blades;

[0120] a blade angle identification module 420 for identifying angles between the plurality of blades of the propeller based on the point cloud data;

[0121] a point cloud data comparison module 430 for determining comparison point cloud data from each blade according to the included angle, and performing comparison to obtain a comparison result;

[0122] A consistency determination module 440 is configured to determine whether the blade parameters are consistent based on the comparison result between the comparison point cloud data;

[0123] The report information generating module 450 is configured to generate report information indicating that the blade parameters are inconsistent.

[0124] a blade parameter identification module 460 for identifying blade curvatures and blade lengths of the plurality of blades of the propeller based on the point cloud data;

[0125] The extraction boundary determination module 470 is configured to determine an extraction boundary of the comparison point cloud data from each blade according to the blade curvature and the blade length.

[0126] The extraction boundary determination module 470 is further configured to determine a width boundary of the comparison point cloud data according to the blade curvature;

[0127] as well as,

[0128] The length boundary of the comparison point cloud data is determined according to the blade length.

[0129] The method for determining the width boundary of the comparison point cloud data can be to obtain parameters such as the curvature circle and the curvature radius based on the curvature, calculate the arc length of the part where the curvature circle and the blade edge curve overlap through the relevant parameters, and use the chord length corresponding to the arc length in the curvature circle as the width boundary of the point cloud data. It can be understood that when the curvature of the blade is large, the width boundary of the selected point cloud data is small; when the curvature of the blade is small, the width boundary of the selected point cloud data is large. For example, the smart terminal obtains that the curvature of the measured propeller is 0.2 through detection, then if Figure 2 As shown, a curvature circle with a curvature radius of 5 cm can be obtained. The chord length corresponding to the arc length of the overlapping part between the curvature circle and the blade edge curve is calculated to be 5 cm, so the width boundary of the point cloud data is 5 cm.

[0130] The length boundary of the comparison point cloud data can be determined by obtaining the length value of the propeller blade. For example, if the length value of the propeller blade obtained by the intelligent terminal through detection is 1 meter, the length boundary of the comparison point cloud data is 1 meter. Figure 2 Length boundaries shown.

[0131] The advantage of this arrangement of the present invention is that it can limit the selection range of the point cloud data, so that the point cloud data of the propeller can more realistically and accurately reflect the blade parameters of the measured propeller.

[0132] Example 4

[0133] Figure 5 This is a schematic diagram of the structure of the device for detecting manufacturing anomalies in a ship propulsion device provided in Example 4 of the present application. This solution provides a superior improvement over the above-mentioned embodiment, specifically comprising the following improvements: the point cloud data comparison module is specifically configured to: determine comparison point cloud data from each blade according to the included angle; annotate the comparison point cloud data according to the blade to which it belongs; rotate the comparison point cloud data according to the included angle to obtain corresponding point cloud information; and determine the comparison result based on the distance information between each point in the corresponding point cloud information.

[0134] like Figure 5 As shown, specifically including the following:

[0135] a point cloud data acquisition module 510 for acquiring point cloud data of propeller blades;

[0136] a blade angle identification module 520 for identifying angles between the plurality of blades of the propeller based on the point cloud data;

[0137] a point cloud data comparison module 530 for determining comparison point cloud data from each blade according to the included angle, and performing comparison to obtain a comparison result;

[0138] A consistency determination module 540 is configured to determine whether the blade parameters are consistent based on the comparison result between the comparison point cloud data;

[0139] The report information generating module 550 is configured to generate report information of consistency abnormality when the blade parameters are inconsistent.

[0140] The point cloud data comparison module 530 is specifically configured to determine comparison point cloud data from each blade according to the angle;

[0141] Annotating the compared point cloud data according to the blades to which they belong;

[0142] Rotating the comparison point cloud data according to the angle to obtain point cloud information with corresponding relationship;

[0143] The comparison result is determined based on the distance information between the points with corresponding point cloud information.

[0144] The method of determining the comparison point cloud data from each blade can be to determine the general outline of the propeller based on the angle between the blades and the extracted boundary of each blade, and distinguish the area where each blade of the propeller is located and the point cloud data within the area.

[0145] The blade to which each comparison point cloud data belongs may be the blade to which each comparison point cloud data belongs. The blade annotation may be to divide the blades on the propeller and to mark which blade each comparison point cloud data belongs to.

[0146] Blade annotation can be performed by labeling each blade with its number and the area it is located in, and then labeling the point cloud data within the area with the number of the blade to which it belongs. For example, if the four blades of a propeller are labeled 1, 2, 3, and 4, then all point cloud data within the area where blade 1 is located, such as points x1(1,1,1) and x2(1,1,2), will be labeled 1.

[0147] The point cloud information having corresponding relationships may be point cloud data having the same blade number marking before and after rotation.

[0148] The corresponding point cloud information can be obtained by rotating the comparison point cloud data according to the angle between the blades to obtain the point cloud data with the same annotations before and after the rotation. For example, if the angle between the blades is 72°, the comparison point cloud data can be rotated 72° to obtain the rotated comparison point cloud data. The point cloud data with the same annotations and the same position on the corresponding blade before and after the rotation are obtained as the corresponding point cloud information.

[0149] The distance information between each point of the corresponding point cloud information can be calculated by calculating the spatial distance between each point of the corresponding point cloud information. For example, the spatial coordinates of the points before and after the rotation of a pair of corresponding point clouds are (x1, y1, z1) and (x2, y2, z2), then the distance information of the points is:

[0150]

[0151] By using an algorithm similar to the above, the distance information between points with corresponding point cloud information can be obtained.

[0152] The comparison result may be determined by comparing the distance information between each point in the corresponding point cloud information with the distance information between each point in the qualified propeller point cloud data having the corresponding point cloud information, and analyzing the similarity between the two.

[0153] In addition, this solution can also use the ICP (Iterative Closest Point) algorithm. The basic idea of ICP is:

[0154] Given two point cloud sets:

[0155] X=left{x_{1},x_{2},cdots,x_{N_{x}}right};

[0156] P=left{p_{1},p_{2},cdots,p_{N_{p}}right};

[0157] Where x_{i} and p_{i} represent the point cloud coordinates, N_{x} and N_{p} represent the number of point clouds.

[0158] Solve the rotation matrix R and translation vector t to minimize the following result.

[0159] E(R,t)=frac{1}{N_{p}}sum_{i=1}^{N_{p}}left|x_{i}-R p_{i}-tright|^{2};

[0160] In actual engineering, it is impossible to know how the points of two point clouds are matched. We can only use iterative solution to gradually reduce the error and finally obtain the rotation matrix R and translation matrix t that minimize the error equation.

[0161] Algorithm flow:

[0162] 1) Find corresponding points

[0163] Typically, the odometry data from the encoder disk is used to obtain the pose difference, which is the current robot's pose in the previous robot coordinate system. This R and t are used as the first guess of the ICP algorithm to help the algorithm find corresponding points in the point cloud.

[0164] It should be noted here that if the laser sensor is not installed at the center of the robot coordinate system, there is a coordinate transformation relationship from the pose obtained by the odometer to the pose of the laser sensor.

[0165] 2) Calculate R and t based on the corresponding points.

[0166] This step is to construct the error equation based on the corresponding points. Ordinary ICP uses the point-to-point distance as the error. The error equation is as follows:

[0167] E(R,t)=frac{1}{N_{p}}sum_{i=1}^{N_{p}}left|x_{i}-R p_{i}-tright|^{2};

[0168] Then solve for R and t. The specific solution is as follows:

[0169] begin{aligned}E(R,t)&=frac{1}{N_{p}}sum_{i=1}^{N_{p}}left|x_{i}-Rp_{i}-tright|^{2}\E(R,t)&=frac{1}{N_{p}}sum_{i=1}^{N_{p}}le ft | ht)+left(u_{x}-Ru_{p}-tright)right|^{2}\=&frac{1}{N_{p}}sum_{i=1}^{N_{p}}left|x_{i}-u_{x}-Rleft(p_{i}-u_{p}right)right|^{2}+ left|u_{x}-Ru_{p}-tright|^{2}\&+2left(x_{i}-u_{x}-Rleft(p_{i}-u_{p}right)right)^{T}left(u_{x}-Ru_{p}-tright)\&=frac{1}{N_{p}}

[0170] sum_{i=1}^{N_{p}}left|x_{i}-u_{x}-Rleft(p_{i}-u_{p}right)right|^{2}+left|u_{x}-Ru_{p}-tright|^{2}end{aligned}

[0171] in,

[0172] u_{x}=frac{1}{N_{p}}sum_{i=1}^{N_{p}}x_{i}quad u_{p}=frac{1}{N_{p}}sum_{i=1}^{N_{p}}p_{i};

[0173] The left(x_{i}-u_{x}-Rleft(p_{i}-u_{p}right)right) term will be equal to 0 after accumulating N_{p} times.

[0174] In the final equation, only the term left|x_{i}-u_{x}-Rleft(p_{i}-u_{p}right)right|^{2} is related to R.

[0175] We can first set left|u_{x}-Ru_{p}-tright|^{2} to 0. Then, we only need to minimize left|x_{i}-u_{x}-Rleft(p_{i}-u_{p}right)right|^{2}. After solving for R, substitute left|u_{x}-Ru_{p}-tright|^{2}=0 to solve for t. Therefore, the error equation can be simplified to the following formula:

[0176] min E(R,t)=frac{1}{N_{p}}sum_{i=1}^{N_{p}}left|x_{i}-u_{x}-Rleft(p_{i}-u_{p}right)right|^{2}=frac{1}{N_{p}} sum_{i=1}^{N_{p}}left|x_{i}^{prime}-Rp_{i}^{prime}right|^{2}=frac{1}{N_{p}} sum_{i=1}^{N_{p}} p_{i}^{prime}-2x_{i}^{T}Rp_{i}^{prime}=sum_{i=1}^{N_{p}}-2x_{i}^{prime T}R p_{i}^{prime};

[0177] Since the term x_{i}^{T}x_{i}^{prime} has no relationship with the R matrix, we can ignore it. Since R is an orthogonal matrix, R^TR = I, and thus p_{i}^{T}R^{T}R p_{i}^{prime} = p_{i}^{T}p_{i}^{prime}. As you can see, this term has no relationship with R either, so we also ignore it. Finally, only one term is related to R.

[0178] The requirement is to minimize or maximize the following formula:

[0179] max sum_{i=1}^{N_{p}}x_{i}^{prime T}{{R}p_{i}^{prime}}=sum_{i=1}^{N_{p}}operatorname{Trace}left(R x_{i}^{prime}p_{i}^{T}right)=operatorname{Trace}(RH);

[0180] Where H = sum_{i=1}^{N_{p}}x_{i}^{prime}p_{i}^{prime T};

[0181] Using the theorem, assuming that matrix A is a positive definite symmetric matrix, then for any orthogonal matrix B, operatorname{Trace}(A)geq operatorname{Trace}(BA);

[0182] Perform SVD decomposition on H: H = U Lambda V^{T};

[0183] Let X = VU^{T}, then X is an orthogonal matrix.

[0184] XH=VU^{T}U Lambda V^{T}=V Lambda V^{T}to obtain a positive definite symmetric matrix.

[0185] but:

[0186] operatorname{Tr}operatorname{ace}(XH)geq operatorname{Tr}operatorname{ace}(BXH);

[0187] B is an arbitrary orthogonal matrix, and X is also an orthogonal matrix, so BX can take all orthogonal matrices. Therefore, BX also includes the rotation matrix T that needs to be solved, so

[0188] operatorname{Trace}(RH)leq operatorname{Trace}(XH);

[0189] When R=X, the equation holds. Therefore:

[0190] R=X=VU^{T}

[0191] Then mathrm{t}=u_{x}-Ru_{p}

[0192] 3) The calculated R and t are used for the next iterative calculation until the error value is less than the set threshold.

[0193] Here is an obvious flaw of ICP:

[0194] The points in two frames of laser point cloud data cannot represent the same position in space. Therefore, using the point-to-point distance as the error equation is bound to introduce random errors.

[0195] Point cloud comparison algorithms compare two frames of point cloud data to determine the difference in the sensor's (lidar or camera) pose before and after the image, often referred to as odometry. These algorithms have evolved from the original ICP method to include various improvements. These algorithms offer optimizations in areas such as finding registration points and error equations.

[0196] The advantage of this arrangement of the present invention is that the blades can be rotated according to the angle between the blades, and the distance information between the points with corresponding point cloud information can be analyzed. This can detect whether the distribution of the propeller blades is reasonable, thereby increasing the accuracy of the detection results.

[0197] Example 5

[0198] Figure 6 This is a schematic diagram of the structure of the device for detecting manufacturing anomalies in a ship propulsion device, provided in Example 5 of the present application. This solution provides a superior improvement over the above-mentioned embodiment, specifically: the point cloud data comparison module is further configured to: determine a comparison cell for the comparison point cloud data on each blade; spatially transform the points in the comparison cell according to the angle and the position information of the comparison cell, obtain distance information between the points, and determine the comparison result.

[0199] like Figure 6 As shown, specifically including the following:

[0200] a point cloud data acquisition module 610 for acquiring point cloud data of propeller blades;

[0201] a blade angle identification module 620, configured to identify angles between the plurality of blades of the propeller based on the point cloud data;

[0202] a point cloud data comparison module 630 for determining comparison point cloud data from each blade according to the included angle, and performing comparison to obtain a comparison result;

[0203] A consistency determination module 640 is configured to determine whether the blade parameters are consistent based on the comparison result between the comparison point cloud data;

[0204] The report information generating module 650 is configured to generate report information of consistency abnormality when the blade parameters are inconsistent.

[0205] The point cloud data comparison module 630 is specifically configured to determine comparison point cloud data from each blade according to the angle;

[0206] Performing blade annotation on the comparison point cloud data according to the blades to which they belong;

[0207] Rotating the comparison point cloud data according to the angle to obtain point cloud information with corresponding relationship;

[0208] The comparison result is determined based on the distance information between the points with corresponding point cloud information.

[0209] The cloud data comparison module 630 is further configured to determine a comparison cell of the comparison point cloud data on each blade;

[0210] According to the angle and the position information of the comparison cell, the points in the comparison cell are spatially transformed to obtain the distance information between the points and determine the comparison result.

[0211] The comparison cells of the comparison point cloud data can be used to divide the comparison point cloud data into regions, with the cell being the smallest region unit of the point cloud data. The size of the cell can be manually specified, or the appropriate size of the cell can be determined by analysis by the intelligent terminal.

[0212] The location information of the comparison cell may be the spatial coordinates of the comparison cell. The spatial transformation may be to transform the coordinate system of the points in the comparison cell after rotation to the spatial coordinate system of the points in the comparison cell before rotation, so as to facilitate the subsequent calculation of distance information.

[0213] The way to obtain the distance information between each point is to rotate the point cloud data in each blade according to the blade angle, and perform spatial transformation on the points in the comparison cell after rotation, and transform them into the spatial coordinate system where the points of the comparison cell before rotation are located, record the corresponding spatial coordinates after spatial transformation, and calculate the distance information with the point cloud data with the same annotation and position information before rotation.

[0214] The advantage of this setting of the scheme is that it can determine the position information of the point cloud data before and after rotation through cells, and put the points before and after rotation into the same space, which is conducive to quickly finding the distance information of the point cloud information with corresponding relationships.

[0215] Example 6

[0216] Figure 7 This is a schematic diagram of the structure of the device for detecting manufacturing anomalies of a ship propulsion device provided in Example 6 of the present application. This solution makes a superior improvement to the above-mentioned embodiment, specifically: the device further includes: a hub point cloud data recognition module for identifying hub point cloud data in the point cloud data; a hub comparison result acquisition module for comparing the hub point cloud data with predetermined hub model data to obtain a hub comparison result; and a hub manufacturing standard judgment module for determining whether the propeller hub meets the manufacturing standard based on the hub comparison result.

[0217] like Figure 7 As shown, specifically including the following:

[0218] a point cloud data acquisition module 710 for acquiring point cloud data of propeller blades;

[0219] A hub point cloud data identification module 720 is configured to identify hub point cloud data in the point cloud data;

[0220] A hub comparison result acquisition module 730 is configured to compare the hub point cloud data with predetermined hub model data to obtain a hub comparison result;

[0221] The hub manufacturing standard judgment module 740 is used to determine whether the propeller hub meets the manufacturing standard based on the hub comparison result.

[0222] The report information generating module 750 is used to generate report information of consistency abnormality when the propeller hub does not meet the manufacturing standards.

[0223] The hub point cloud data recognition module 720 may be a program designed by an intelligent terminal for recognizing hub point cloud data. The hub point cloud data may be point cloud data information of the propeller hub.

[0224] The method of identifying the hub point cloud data in the point cloud data may be to determine the extraction boundary of the hub based on the dimensional parameters of the hub, such as the length and width, and obtain the point cloud data within the extraction boundary.

[0225] Hub comparison result acquisition module 730 can be a program designed by the intelligent terminal to obtain hub point cloud data comparison results. The predetermined hub model data can be obtained by scanning a qualified propeller using 3D laser scanning technology and analyzing and extracting the hub point cloud data. This data is used to provide a comparison standard for the propeller hub being inspected.

[0226] The hub comparison result may be obtained by comparing the point cloud data of the detected propeller hub with the predetermined hub model data, and analyzing and determining the similarity of the point cloud data of the two.

[0227] Hub manufacturing standard determination module 740 may be a program designed by the intelligent terminal to determine whether a propeller hub meets manufacturing standards. This determination may be made by analyzing the similarity between the inspected propeller hub's point cloud data and pre-determined hub model data to see if it meets a specified value. For example, a 98% similarity between the inspected propeller hub's point cloud data and the pre-determined hub model data may be required to determine that the propeller hub meets manufacturing standards. If the comparison yields a similarity of 96%, the propeller hub does not meet manufacturing standards.

[0228] The advantage of this arrangement of the present invention is that the propeller hub can also be included in the detection range, making the detection results more comprehensive.

[0229] Example 7

[0230] Figure 8 This is a schematic diagram of the structure of the device for detecting manufacturing anomalies of a ship propulsion device provided in Example 7 of the present application. This solution makes a better improvement to the above-mentioned embodiment, specifically as follows: the hub comparison result acquisition module is further used to: perform spatial transformation on the hub model data to obtain a spatial pose that matches the hub point cloud data; identify the plane data and surface data of the hub model in the current spatial pose; and compare the plane point cloud data and the surface point cloud data of the hub point cloud data based on the plane data and the surface data to obtain a hub comparison result.

[0231] like Figure 8 As shown, specifically including the following:

[0232] a point cloud data acquisition module 810 for acquiring point cloud data of propeller blades;

[0233] A hub point cloud data identification module 820 is configured to identify hub point cloud data in the point cloud data;

[0234] A hub comparison result acquisition module 830 is configured to compare the hub point cloud data with predetermined hub model data to obtain a hub comparison result;

[0235] The hub manufacturing standard judgment module 840 is used to determine whether the propeller hub meets the manufacturing standard based on the hub comparison result.

[0236] The report information generating module 850 is used to generate report information of consistency abnormality when the propeller hub does not meet the manufacturing standards.

[0237] The hub comparison result acquisition module 830 is further configured to perform spatial transformation on the hub model data to obtain a spatial pose that matches the hub point cloud data.

[0238] Identify the plane data and surface data of the hub model in the current spatial position;

[0239] A hub comparison result is obtained based on comparing the plane point cloud data and the curved surface data with the plane point cloud data and the curved surface point cloud data of the hub point cloud data.

[0240] The spatial posture can be the spatial position and posture of the propeller hub.

[0241] The spatial pose can be obtained by spatially transforming the hub model data into the space containing the point cloud data of the measured hub, and determining the position and pose information of the hub model data in this space. The position and pose information of the hub model data in this space can include information such as the point cloud data and shape outline of the hub model.

[0242] Plane data can be point cloud data of a surface without any curves or twists in a qualified propeller hub. Curved surface data can be a collection of continuous motion trajectories of a straight line in space. Curved surface data can be point cloud data of a curved surface in a qualified propeller hub.

[0243] The method for distinguishing plane data from curved surface data can be determined by the intelligent terminal based on the spatial position parameters of the plane data and the curved surface data. Specifically, if two points on a straight line are in the same plane, then the surface where all points on the line are in the plane is identified as a plane, and the data information or point cloud data contained in the surface is plane data. A surface with ups and downs can be identified as a curved surface, and the data information or point cloud data contained in the surface is surface data. Using similar methods as described above, plane data and curved surface data can be distinguished.

[0244] The hub comparison result can be obtained by determining the similarity between the predetermined hub plane data and the curved surface data and the plane point cloud data and the curved surface point cloud data of the measured hub point cloud data. The comparison parameters for plane data can include information such as the size and spatial position of the hub plane; and for curved surface data, the comparison parameters can include information such as the size, spatial position, and curvature of the curved surface.

[0245] The advantage of this arrangement of the present invention is that the plane data and the curved surface data are compared separately, and different comparison data can be determined for different surfaces, making the comparison result more accurate.

[0246] Example 8

[0247] Figure 9 This is a schematic diagram of the structure of the device for detecting manufacturing anomalies of a ship propulsion device provided in Example 8 of the present application. Figure 9 As shown, the specific steps include:

[0248] S901, obtaining point cloud data of propeller blades;

[0249] S902, identifying angles between multiple blades of the propeller based on the point cloud data;

[0250] S903, determining comparison point cloud data from each blade according to the included angle, and performing comparison to obtain a comparison result;

[0251] S904 , determining whether the blade parameters are consistent based on the comparison result between the comparison point cloud data; if not, executing S905 ; if yes, ending the process.

[0252] S905: Generate report information of consistency exception.

[0253] In this embodiment, point cloud data of propeller blades is acquired; based on the point cloud data, the angles between the propeller blades are identified; based on the angles, comparison point cloud data is determined for each blade and compared to obtain a comparison result; based on the comparison results between the comparison point cloud data, whether the blade parameters are consistent is determined; if not, a consistency anomaly report is generated. This method for detecting manufacturing anomalies in ship propulsion devices can improve the efficiency and accuracy of ship propeller testing and reduce the requirements for personnel.

[0254] The method for detecting manufacturing abnormalities of a ship propulsion device provided in the embodiment of the present application and the device for detecting manufacturing abnormalities of a mining ship propulsion device provided in the above embodiment have the same functional modules and beneficial effects. To avoid repetition, they will not be described here.

[0255] Embodiment 9

[0256] like Figure 10As shown, embodiment nine of the present application also provides an electronic device 1000, including a processor 1001, a memory 1002, and a program or instruction stored in the memory 1002 and executable on the processor 1001. When the program or instruction is executed by the processor 1001, each process of the embodiment of the detection device for manufacturing abnormalities of the above-mentioned ship propulsion device is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0257] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0258] Example 10

[0259] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned embodiment of the detection device for manufacturing abnormalities of a ship propulsion device are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0260] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0261] Example 11

[0262] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned embodiment of the detection device for manufacturing abnormalities of the ship propulsion device, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0263] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0264] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0265] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0266] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0267] The above are only preferred embodiments of the present application and the technical principles employed. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that are possible for those skilled in the art will not depart from the scope of protection of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments and may include more other equivalent embodiments without departing from the concept of the present application. The scope of the present application is determined by the scope of the claims.

Claims

1. A device for detecting manufacturing anomalies of a ship propulsion device, characterized in that: The detection device comprises: A point cloud data acquisition module, used to acquire point cloud data of propeller blades; a blade angle recognition module, configured to recognize the angles between the plurality of blades of the propeller based on the point cloud data; a point cloud data comparison module, configured to determine comparison point cloud data from each blade according to the included angle, and perform comparison to obtain a comparison result; a consistency determination module, configured to determine whether the blade parameters are consistent based on a comparison result between the comparison point cloud data; The report information generating module is used to generate report information of consistency abnormality when the blade parameters are inconsistent.

2. The device for detecting manufacturing abnormalities of a ship propulsion device according to claim 1, characterized in that: The device further comprises: a blade parameter identification module, configured to identify blade curvatures and blade lengths of the plurality of blades of the propeller based on the point cloud data; The extraction boundary determination module is used to determine the extraction boundary of the comparison point cloud data from each blade according to the blade curvature and the blade length.

3. The device for detecting manufacturing abnormalities of a ship propulsion device according to claim 2, characterized in that: The extraction boundary determination module is further used to: determining a width boundary of the comparison point cloud data according to the blade curvature; as well as, The length boundary of the comparison point cloud data is determined according to the blade length.

4. The device for detecting manufacturing abnormalities of a ship propulsion device according to claim 1, characterized in that: The point cloud data comparison module is specifically used to: Determining comparative point cloud data from each blade according to the angle; Annotating the compared point cloud data according to the blades to which they belong; Rotating the comparison point cloud data according to the angle to obtain point cloud information with corresponding relationship; The comparison result is determined based on the distance information between the points with corresponding point cloud information.

5. The device for detecting manufacturing abnormalities of a ship propulsion device according to claim 4, characterized in that: The point cloud data comparison module is further used to: Determine a comparison cell of the comparison point cloud data on each blade; According to the angle and the position information of the comparison cell, the points in the comparison cell are spatially transformed to obtain the distance information between the points and determine the comparison result.

6. The device for detecting manufacturing abnormalities of a ship propulsion device according to claim 1, characterized in that: The device further comprises: a hub point cloud data recognition module, configured to recognize hub point cloud data in the point cloud data; a hub comparison result acquisition module, configured to compare the hub point cloud data with predetermined hub model data to obtain a hub comparison result; The hub manufacturing standard judgment module is used to determine whether the propeller hub meets the manufacturing standard based on the hub comparison result.

7. The device for detecting manufacturing abnormalities of a ship propulsion device according to claim 6, characterized in that: The hub comparison result acquisition module is further used to: Performing spatial transformation on the hub model data to obtain a spatial pose that matches the hub point cloud data; Identify the plane data and surface data of the hub model in the current spatial position; A hub comparison result is obtained based on comparing the plane data and the curved surface data with the plane point cloud data and the curved surface point cloud data of the hub point cloud data.

8. A method for detecting manufacturing anomalies of a ship propulsion device, characterized in that: The method comprises: Obtain point cloud data of propeller blades; identifying angles between a plurality of blades of the propeller according to the point cloud data; Determining comparison point cloud data from each blade according to the included angle, and performing comparison to obtain a comparison result; Determining whether the blade parameters are consistent based on a comparison result between the comparison point cloud data; If not, a consistency exception report will be generated.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein when the program or instruction is executed by the processor, the steps of the method for detecting manufacturing abnormalities of a ship propulsion device as claimed in claim 8 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the method for detecting manufacturing abnormalities of a ship propulsion device as claimed in claim 8 are implemented.

Images