Lift shaft data modeling method based on unmanned aerial vehicle detection

Abstract

The invention discloses an elevator shaft data modeling method based on unmanned aerial vehicle detection, and relates to the technical field of data modeling, and the method comprises the steps: carrying a detection sensor group on an unmanned aerial vehicle, obtaining design drawing information of a target elevator shaft, carrying out flight path planning, and determining unmanned aerial vehicle detection path information; according to the unmanned aerial vehicle detection path information, the detection sensor set is adopted to detect and record the target elevator shaft, a multidirectional shaft detection point cloud data set is obtained, filtering denoising and point cloud reconstruction are carried out on the multidirectional shaft detection point cloud data set, and an elevator shaft three-dimensional point cloud model is built; and meanwhile, establishing a geological structure model to carry out fusion analysis and correction optimization on the three-dimensional point cloud model of the elevator shaft to obtain an optimized point cloud model of the elevator shaft. The technical effects that all-around efficient collection of elevator shaft data is achieved through unmanned aerial vehicle detection, the detection data processing comprehensiveness and the data modeling accuracy are improved, and then the data modeling efficiency is ensured are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data modeling, and in particular to an elevator shaft data modeling method based on drone detection. Background Art

[0002] Elevator shaft data modeling plays an important role in elevator engineering and elevator maintenance management. It can not only improve the design level of elevators, ensure the safety and operation efficiency of elevators, but also optimize the layout and configuration of elevator systems, and reduce errors and risks during installation and maintenance. In addition, through accurate data modeling, real-time monitoring and prediction of elevator performance can be achieved, providing strong support for preventive maintenance of elevators.

[0003] However, the existing elevator shaft data modeling method relies on manual measurement, has a low degree of intelligence, and has technical problems such as long measurement cycle and limited measurement accuracy. Summary of the invention

[0004] The present application provides an elevator shaft data modeling method based on drone detection, thereby solving the technical problems of low intelligence level, long measurement cycle and limited measurement accuracy of the elevator shaft data modeling method in the prior art. The application achieves the technical effect of realizing all-round and efficient collection of elevator shaft data through drone detection, improving the comprehensiveness of detection data processing and the accuracy of data modeling, thereby ensuring the efficiency of data modeling.

[0005] In view of the above problems, the present invention provides an elevator shaft data modeling method based on drone detection.

[0006] In the first aspect, the present application provides an elevator shaft data modeling method based on drone detection, the method comprising: carrying a detection sensor group on a drone, the detection sensor group comprising a three-dimensional laser scanning device, an infrared imaging sensor, a laser ranging sensor and a visual sensor; obtaining design drawing information of the target elevator shaft, performing flight path planning based on the design drawing information, and determining the drone detection path information; using the detection sensor group to detect and record the target elevator shaft according to the drone detection path information to obtain a multi-directional shaft detection point cloud data set; filtering, denoising and point cloud reconstruction of the multi-directional shaft detection point cloud data set to build a three-dimensional point cloud model of the elevator shaft; collecting and obtaining geological structure belt information, performing feature analysis and stereo modeling on the geological structure belt information, and establishing a geological structure model; based on the geological structure model, performing fusion analysis and correction optimization on the three-dimensional point cloud model of the elevator shaft to obtain an optimized point cloud model of the elevator shaft.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By adopting a detection sensor group mounted on a drone and performing flight path planning based on the design drawing information of the target elevator shaft, the drone detection path information is determined, and the detection sensor group is used to detect and record the target elevator shaft according to the drone detection path information, and a multi-directional shaft detection point cloud data set is obtained, which is used for filtering and denoising and point cloud reconstruction, and a three-dimensional point cloud model of the elevator shaft is built. The geological structure belt information is collected and obtained for feature analysis and three-dimensional modeling, and a geological structure model is established, so that the three-dimensional point cloud model of the elevator shaft is fused and analyzed and corrected and optimized based on the geological structure model, and a technical solution for obtaining an optimized point cloud model of the elevator shaft is obtained. Thus, the technical effect of realizing all-round and efficient collection of elevator shaft data through drone detection, improving the comprehensiveness of detection data processing and the accuracy of data modeling, and thus ensuring the efficiency of data modeling is achieved.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 This is a flow chart of the elevator shaft data modeling method based on drone detection in this application;

[0011] Figure 2 This is a schematic diagram of the process of obtaining a multi-directional shaft detection point cloud data set in the elevator shaft data modeling method based on drone detection in this application. DETAILED DESCRIPTION

[0012] The present application provides an elevator shaft data modeling method based on drone detection, thereby solving the technical problems of low intelligence level, long measurement cycle and limited measurement accuracy of the elevator shaft data modeling method in the prior art. The application achieves the technical effect of realizing all-round and efficient collection of elevator shaft data through drone detection, improving the comprehensiveness of detection data processing and the accuracy of data modeling, thereby ensuring the efficiency of data modeling.

[0013] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] The present application is described below in conjunction with the drawings in the present application.

[0015] Embodiment 1, as Figure 1 As shown, the present application provides an elevator shaft data modeling method based on drone detection, the method comprising:

[0016] Step S1: A detection sensor group is mounted on the drone, wherein the detection sensor group includes a three-dimensional laser scanning device, an infrared imaging sensor, a laser ranging sensor and a visual sensor.

[0017] Step S2: Obtain design drawing information of the target elevator shaft, perform flight path planning based on the design drawing information, and determine the drone detection path information.

[0018] Specifically, with the rapid development of drone technology, using drones to carry out data detection has become an efficient and accurate detection method. In order to achieve all-round and efficient collection of elevator shaft data, a detection sensor group is first mounted on the drone, which includes a three-dimensional laser scanning device for obtaining high-precision spatial data of the shaft; an infrared imaging sensor that can detect heat sources in the shaft, such as the working status of the elevator equipment, as well as potential obstacles or safety hazards; a laser ranging sensor that provides accurate distance measurement, such as shaft dimensions, distance data, etc.; and a visual sensor that is used to identify structural features, obstacles, and the entrance and exit of the elevator shaft in the shaft, so as to collect elevator shaft detection data in all aspects. Then, the design drawing information of the target elevator shaft is obtained through the elevator design database, including plan views, cross-sectional views, stereo views, etc. Use CAD software or other related tools to parse the design drawings, extract key information such as the size, shape, and floor location of the shaft, and then use path planning algorithms, such as the A* algorithm and the Dijkstra algorithm, to plan the flight path based on the key information in the design drawings. At the same time, set the maximum flight altitude and speed of the drone to ensure the safety of the drone during flight. Plan and determine the drone detection path information with the fastest detection efficiency to ensure that the detection sensor can cover the elevator shaft range and improve the comprehensiveness of data collection.

[0019] Step S3: using the detection sensor group to detect and record the target elevator shaft according to the drone detection path information to obtain a multi-directional shaft detection point cloud data set.

[0020] like Figure 2 As shown, further, the step of obtaining the multi-directional wellbore detection point cloud data set also includes:

[0021] According to the detection path information of the drone, the detection sensor group is used to detect and record the target elevator shaft, and a multi-dimensional data stream of shaft detection is obtained, and the multi-dimensional data stream of shaft detection includes three-dimensional laser scanning data, infrared imaging data, laser ranging data and visual image data; a detection data integration processing channel is constructed, and the three-dimensional laser scanning data, infrared imaging data, laser ranging data and visual image data are mapped and processed based on the detection data integration processing channel to obtain the integrated detection characteristics of the elevator shaft; according to the detection requirements of the elevator shaft, the elevator shaft entity detection standard is determined; based on the elevator shaft entity detection standard, the elevator shaft integrated detection feature is marked with an area of ​​interest, and the target detection entity area of ​​interest is determined; based on the target detection entity area of ​​interest, the detection sensor group is used to perform all-round detection and record of the target elevator shaft, and the multi-directional shaft detection point cloud data set is obtained.

[0022] Furthermore, the steps of constructing the detection data integration processing channel in this application also include:

[0023] Acquire a multi-dimensional shaft detection database, classify and identify the multi-dimensional shaft detection database according to the detection sensor type, and obtain a shaft sensor detection data set; determine a sensor data feature processing program according to the detection sensor type; perform feature extraction on the shaft sensor detection data set based on the sensor data feature processing program to obtain a key feature set of sensor data; perform network integration training and evaluation optimization on the key feature set of sensor data to construct the detection data integration processing channel.

[0024] Furthermore, the steps of constructing the detection data integration processing channel in this application also include:

[0025] The key feature set of the sensor data is aligned according to the time series to obtain a sensor data feature sample set, and the data characteristic analysis is performed on the sensor data feature sample set to obtain sensor data characteristic information; a deep learning network list is constructed, and the sensor data characteristic information is matched with the deep learning network list to determine a matching deep learning network set; based on the matching deep learning network set, the sensor data feature sample set is distributedly trained to generate a multi-sensor feature analysis network set; a model integration strategy is used to perform model integration training and evaluation optimization on the multi-sensor feature analysis network set to construct the detection data integration processing channel.

[0026] Specifically, according to the pre-planned UAV detection path information, the detection sensor group carried by the UAV is controlled to detect and record the target elevator shaft. During the detection process, the detection sensor group collects and obtains the shaft detection multi-dimensional data stream in real time, and the shaft detection multi-dimensional data stream includes: shaft section width, shaft section depth, top floor height, bottom pit depth, door opening reserved width, door opening reserved height, left and right door stack width, door head beam size, sill beam size, ring beam size, ring beam spacing, whether the shaft has protrusions and recesses of structural columns, the overall verticality of each shaft wall, holes in the shaft roof, hook identification and other elevator shaft clearance data. The sensor source types of the collected elevator shaft data include: three-dimensional laser scanning data, infrared imaging data, laser ranging data and visual image data.

[0027] In order to improve the processing efficiency of detection data, it is necessary to build a detection data integration processing channel, which is used to parallelly and efficiently process the multi-dimensional data streams of shaft detection from different sensor source types. The construction process is as follows: First, the shaft multi-dimensional detection database is acquired through big data technology. The shaft multi-dimensional detection database is a historical shaft sensor detection data set, including sensor detection source data and corresponding detection feature data. The shaft multi-dimensional detection database is classified and identified according to the detection sensor type to obtain the shaft sensor detection data set. The shaft sensor detection data set includes three-dimensional laser scanning data, infrared imaging data, laser ranging data, and visual image data. For each type of detection sensor, a sensor data feature processing program is determined. For example, the three-dimensional laser scanning data feature processing program includes denoising, normalization, and principal component analysis, etc., to extract the key features of the shaft data. Based on the sensor data feature processing program, the shaft sensor detection data set is respectively feature extracted to obtain the corresponding sensor data key feature set, such as shaft section ranging features, wall defect infrared features, etc.

[0028] Then, the sensor data key feature set is trained and evaluated for network integration. In the multi-sensor data features, each sensor may collect data at different time points. In order to perform effective data analysis and pattern recognition, it is necessary to ensure that the data of all sensors are consistent in time. Therefore, the sensor data key feature set is aligned according to the time series to obtain the integrated sensor data feature sample set, which includes the sensor key feature data and the corresponding detection feature data. The sensor data feature sample set is analyzed for data characteristics to obtain sensor data characteristic information, including the statistical properties, distribution characteristics, correlation, etc. of the data, as a basis for the subsequent selection of appropriate deep learning models and parameters. A deep learning network list is constructed, which includes a variety of different types of network architectures (such as convolutional neural network CNN, long short-term memory network LSTM, support vector machine, etc.), each of which is suitable for processing different types of sensor data characteristics. According to the sensor data characteristic information, the deep learning network list is matched, and the matching deep learning network set that best suits the current data characteristics is determined. Based on the matching deep learning network set, the sensor data feature sample set is distributed and simultaneously trained to generate a multi-sensor feature analysis network set, which is used to extract key features and analyze feature results of corresponding sensor types according to the multi-dimensional detection data of the well, such as well section size features, wall cavity features, structural column protrusions, well distance features, etc. The multi-sensor feature analysis network set is trained by model integration strategy, for example, the weight of the analysis network with higher accuracy in the integrated model is increased, so as to fuse the multi-sensor feature analysis network set, and the integrated model after fusion is evaluated and optimized to obtain a sensor feature integration analysis network with qualified model performance, so as to integrate and analyze the multi-sensor data features. Then, the sensor feature integration analysis network is embedded and integrated into the detection data integration processing channel, which can receive data input from multiple sensors and analyze and process it through the network set to generate useful output feature information, such as well target detection, well size features, and obstacle recognition.

[0029] Based on the detection data integration processing channel, the three-dimensional laser scanning data, infrared imaging data, laser ranging data and visual image data are mapped and processed to obtain the elevator shaft integrated detection feature, which is the key feature information of the elevator shaft obtained according to the current detection data, including shaft size, entity target, etc. According to the elevator shaft detection requirements, the elevator shaft entity detection standard is determined, and the elevator shaft entity detection standard is the physical information of the elevator shaft that needs to be detected to meet the modeling requirements, such as shaft section, door opening, door pier, top plate, hook, ring beam (span), etc. Based on the elevator shaft entity detection standard, the entities that meet the detection standards in the elevator shaft integrated detection feature are marked as areas of interest, and the target detection entity area of ​​interest is determined, such as the four walls, top, bottom, door opening, track installation area, etc. of the shaft. Based on the target detection focus entity area, the detection sensor group is used to perform all-round detection and recording of the target elevator shaft, and the position and angle of the sensor are adjusted to ensure that these areas are fully covered and recorded, so as to collect multi-directional shaft detection point cloud data sets, which include three-dimensional point clouds, infrared images, distance measurements, and visual images, etc. The all-round and efficient collection of elevator shaft data is achieved through drone detection, which improves the comprehensiveness of detection data processing and thus improves the accuracy of subsequent data modeling.

[0030] Furthermore, the step of obtaining the multi-directional wellbore detection point cloud data set also includes:

[0031] Based on the target detection entity area of ​​interest, the drone detection path information is additionally corrected to obtain the drone detection corrected path information; obstacle identification and obstacle avoidance adjustment optimization are performed on the drone detection corrected path information to determine the drone detection optimized path information; based on the drone detection optimized path information and the detection sensor group, the target elevator shaft is fully detected and recorded to obtain the multi-directional shaft detection point cloud data set.

[0032] Specifically, additional corrections are made to the original UAV detection path information based on the previously determined target detection entity areas of interest (such as the four walls, top, bottom, door openings, and other key areas of the shaft). Corrections may include adjusting the flight altitude, changing the flight direction, or increasing the density of detection points to ensure that these key areas are fully covered and detected in detail. On the corrected UAV detection path, the detection sensor group is used to perform real-time obstacle identification. Once an obstacle is identified (such as equipment, pipelines, maintenance platforms, etc. in the shaft), obstacle avoidance adjustments are immediately made, which may include changing the flight trajectory, raising or lowering the flight altitude, or even suspending the flight to avoid collision. Through algorithm optimization, such as A* algorithm, Dijkstra algorithm, or reinforcement learning, the best obstacle avoidance path is found to ensure that the UAV can continue the detection mission safely and efficiently. Combined with the results of obstacle identification and obstacle avoidance adjustment, the optimized path information for UAV detection is determined. This path should ensure full coverage of the target detection entity area of ​​interest while avoiding collisions with any obstacles in the shaft. Based on the drone detection optimization path information and detection sensor group, the target elevator shaft is detected and recorded in an all-round way. The drone performs flight detection according to the optimized drone detection optimization path information. At the same time, the sensor group is used to collect real-time 3D laser scanning data, infrared imaging data, laser ranging data and visual image data in the shaft, including shaft width and depth, ring beam spacing, door opening width and height, left and right door stack width, door head beam conditions and other key elevator shaft data. These data will be integrated into a multi-directional shaft detection point cloud data set to provide a basis for subsequent analysis and processing. Ensure that the drone can safely and efficiently cover the target detection focus area during the detection process, and collect comprehensive and accurate shaft detection data.

[0033] Step S4: filtering, denoising and reconstructing the point cloud data set of the multi-directional shaft detection to build a three-dimensional point cloud model of the elevator shaft.

[0034] Furthermore, the steps of building the three-dimensional point cloud model of the elevator shaft in this application also include:

[0035] The multi-directional shaft detection point cloud data set is filtered and denoised to obtain a usable multi-directional shaft detection point cloud data set; a triangulated reconstruction algorithm is used to align and triangulate the usable multi-directional shaft detection point cloud data set to obtain a shaft triangle mesh model; edge detection and model fitting training are performed based on the shaft triangle mesh model to determine panoramic modeling fitting parameters; the panoramic modeling fitting parameters are mapped to the shaft triangle mesh model to reconstruct the point cloud model, and a three-dimensional point cloud model of the elevator shaft is constructed.

[0036] Furthermore, the steps of obtaining a usable multi-directional wellbore detection point cloud data set in this application also include:

[0037] Noise characteristics are extracted from the multi-directional shaft detection point cloud data set to obtain point cloud noise characteristic information, and a wavelet selection threshold is determined based on the point cloud noise characteristic information; multi-scale decomposition is performed on the multi-directional shaft detection point cloud data set to obtain a point cloud multi-scale wavelet coefficient set; and the point cloud multi-scale wavelet coefficient set is screened, filtered and reconstructed according to the wavelet selection threshold to obtain the available multi-directional shaft detection point cloud data set.

[0038] Specifically, the multi-directional shaft detection point cloud data set is filtered, denoised and reconstructed. To ensure the quality of the point cloud data, the multi-directional shaft detection point cloud data set is first filtered, denoised, including noise characteristic extraction of the multi-directional shaft detection point cloud data set, which usually involves analyzing the outliers, outliers and high-frequency noise in the point cloud data to obtain the corresponding point cloud noise characteristic information. And according to the point cloud noise characteristic information, a soft threshold or hard threshold method is used to determine the retention threshold of the wavelet coefficient, that is, to determine the wavelet selection threshold. Selecting a suitable threshold can retain important geometric features while removing noise. The multi-directional shaft detection point cloud data set is subjected to multi-scale decomposition to obtain a multi-scale wavelet coefficient set of the point cloud at different scales. The multi-scale wavelet coefficient set of the point cloud is screened, filtered and reconstructed according to the wavelet selection threshold, the wavelet coefficient set at each scale is traversed, the coefficients below the threshold are set to zero (hard threshold) or shrunk (soft threshold), and the screened wavelet coefficients are inversely transformed to reconstruct the point cloud data to obtain a usable multi-directional wellbore detection point cloud data set that has been filtered and denoised.

[0039] The triangulated reconstruction algorithm is used to register, align and triangulate the available multi-directional shaft detection point cloud data set. First, according to the characteristics and requirements of the point cloud data, a suitable registration algorithm is selected, such as the ICP (iterative closest point) algorithm, the NDT (normal distribution transformation) algorithm, etc., and the selected registration algorithm is applied to spatially align the multi-directional shaft detection point cloud data set. Check the registered point cloud data to ensure that they are in the same coordinate system and there is no obvious misalignment. According to the density, noise level and other characteristics of the point cloud data, a suitable triangulation algorithm is selected, such as Delaunay triangulation, Poisson surface reconstruction, etc., and the selected triangulation algorithm is applied to convert the registered and aligned point cloud data into a shaft triangle mesh model to represent the geometric shape of the shaft. The edge detection algorithm is used to extract the edge features of the shaft from the shaft triangle mesh model, and the detected edge features are extracted and processed to obtain key geometric features such as corner points, straight line segments, etc., and then the extracted features are used for model fitting training, such as using the least squares method to fit geometric shapes such as planes and cylinders to determine panoramic modeling fitting parameters, such as plane parameters, cylinder parameters, etc. The panoramic modeling fitting parameters are mapped to the hoistway triangular mesh model to reconstruct the point cloud model. According to the mapped parameters, new point cloud data is generated on the mesh model to represent the structural dimensions of the hoistway. The generated point cloud model is optimized, such as removing redundant points, smoothing the surface, etc., and the optimized point cloud model is integrated into a complete three-dimensional point cloud model of the elevator hoistway, that is, the three-dimensional point cloud model of the elevator hoistway is constructed. Efficient and accurate processing of multi-directional hoistway detection point cloud data sets is achieved, thereby improving data modeling accuracy and modeling efficiency.

[0040] Step S5: Collect and obtain geological structure belt information, perform feature analysis and three-dimensional modeling on the geological structure belt information, and establish a geological structure model.

[0041] Specifically, the acquisition of geological structural belt information is the basis for establishing a geological structural model, which usually involves geological exploration, geological measurement and geological survey, etc., aiming to obtain detailed data of the geological structural belt, which may include the location, morphology, attributes, and intersection relationship of geological interfaces of the geological body. After obtaining the geological structural belt information, it is necessary to perform feature analysis on it to extract key geological structural features, which usually involves drawing geological profiles, analyzing geological structures and analyzing geological attributes. On the basis of feature analysis, three-dimensional geological modeling technology is used to perform stereoscopic modeling of the geological structural model and establish a three-dimensional model of the geological interface. According to the three-dimensional model of the geological interface, identification and fitting are performed, and the internal structure of the geological body is described to generate a closed geological body. The generated geological structural model is optimized, such as smoothing the surface, removing redundant points, etc., to obtain an optimized geological structural model to improve the accuracy and visualization of the model. The geological structural model can intuitively display the spatial distribution and geometric morphology of the geological structural belt to improve the accuracy and practicality of subsequent elevator shaft modeling.

[0042] Step S6: Based on the geological structure model, the three-dimensional point cloud model of the elevator shaft is subjected to fusion analysis and correction optimization to obtain an optimized point cloud model of the elevator shaft.

[0043] Furthermore, the steps of obtaining the optimized point cloud model of the elevator shaft in this application also include:

[0044] The geological structure model is aligned and matched with the elevator shaft three-dimensional point cloud model to obtain an elevator shaft fusion point cloud model; the elevator shaft fusion point cloud model is verified and evaluated to obtain model performance evaluation parameters; based on the model performance evaluation parameters, the elevator shaft fusion point cloud model is iteratively corrected and optimized to obtain the elevator shaft optimized point cloud model.

[0045] Specifically, based on the geological structure model, the three-dimensional point cloud model of the elevator shaft is subjected to fusion analysis and correction optimization. First, the geological structure model is aligned with the three-dimensional point cloud model of the elevator shaft to ensure that the data format, coordinate system and scale of the geological structure model and the three-dimensional point cloud model of the elevator shaft are consistent. The surface of the geological structure model is preliminarily aligned with the corresponding part of the three-dimensional point cloud model of the elevator shaft through the point cloud registration algorithm. On the basis of the preliminary alignment, the model is finely adjusted according to the actual situation of the geological structure and the design requirements of the elevator shaft to ensure the precise alignment of the two at key positions. Then, the aligned geological structure model and the three-dimensional point cloud model of the elevator shaft are fused, including point cloud merging, deduplication, smoothing and other processing, to obtain the corresponding fused point cloud model of the elevator shaft. The fused point cloud model of the elevator shaft is verified and evaluated to obtain model performance evaluation parameters, such as accuracy, integrity, consistency, etc., for evaluating the performance of the fused point cloud model.

[0046] The elevator shaft fusion point cloud model is iteratively corrected and optimized based on the model performance evaluation parameters. First, problems existing in the fusion point cloud model, such as missing data and insufficient precision, are identified according to the model performance evaluation parameters. Then, the fusion point cloud model is corrected and optimized for the identified problems, including adding data points, adjusting the model shape, smoothing the surface, and other processing. The corrected and optimized model is verified and evaluated again to ensure that the model performance is improved. If there are still deficiencies, the iterative correction and optimization process continues. After multiple iterative corrections and optimizations, the elevator shaft optimized point cloud model is finally obtained. The model is not only accurately aligned with the geological structure model, but also has high precision and integrity. Intelligent modeling and model iterative optimization of elevator shaft data are realized to improve data modeling accuracy and modeling efficiency.

[0047] In summary, the elevator shaft data modeling method based on drone detection provided by this application has the following technical effects:

[0048] By adopting a detection sensor group mounted on a drone and performing flight path planning based on the design drawing information of the target elevator shaft, the drone detection path information is determined, and the detection sensor group is used to detect and record the target elevator shaft according to the drone detection path information, and a multi-directional shaft detection point cloud data set is obtained, which is used for filtering and denoising and point cloud reconstruction, and a three-dimensional point cloud model of the elevator shaft is built. The geological structure belt information is collected and obtained for feature analysis and three-dimensional modeling, and a geological structure model is established, so that the three-dimensional point cloud model of the elevator shaft is fused and analyzed and corrected and optimized based on the geological structure model, and a technical solution for obtaining an optimized point cloud model of the elevator shaft is obtained. Thus, the technical effect of realizing all-round and efficient collection of elevator shaft data through drone detection, improving the comprehensiveness of detection data processing and the accuracy of data modeling, and thus ensuring the efficiency of data modeling is achieved.

[0049] This specification and the accompanying drawings are merely exemplary illustrations of the present application, but the protection scope of the present application is not limited thereto. It should be noted that any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and the desired results can still be achieved. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The elevator shaft data modeling method based on drone detection is characterized by: The method comprises: A detection sensor group is mounted on the drone, wherein the detection sensor group includes a three-dimensional laser scanning device, an infrared imaging sensor, a laser ranging sensor, and a visual sensor; Obtain design drawing information of the target elevator shaft, perform flight path planning based on the design drawing information, and determine the detection path information of the drone; According to the detection path information of the drone, the detection sensor group is used to detect and record the target elevator shaft, so as to obtain a multi-directional shaft detection point cloud data set; Perform filtering, denoising and point cloud reconstruction on the multi-directional shaft detection point cloud data set to build a three-dimensional point cloud model of the elevator shaft; Collecting and acquiring geological structure belt information, performing feature analysis and three-dimensional modeling on the geological structure belt information, and establishing a geological structure model; Based on the geological structure model, the three-dimensional point cloud model of the elevator shaft is subjected to fusion analysis and correction optimization to obtain an optimized point cloud model of the elevator shaft.

2. The elevator shaft data modeling method based on drone detection according to claim 1 is characterized in that: The multi-directional well detection point cloud data set is obtained, including: According to the detection path information of the drone, the detection sensor group is used to detect and record the target elevator shaft, and a shaft detection multi-dimensional data stream is obtained, wherein the shaft detection multi-dimensional data stream includes three-dimensional laser scanning data, infrared imaging data, laser ranging data, and visual image data; Constructing a detection data integrated processing channel, and mapping and processing the three-dimensional laser scanning data, infrared imaging data, laser ranging data, and visual image data based on the detection data integrated processing channel to obtain the elevator shaft integrated detection features; Determine the physical detection standard of the elevator shaft according to the detection requirements of the elevator shaft; Marking the area of ​​interest for the elevator shaft integrated detection feature based on the elevator shaft entity detection standard to determine the target detection entity area of ​​interest; Based on the target detection focus entity area, the detection sensor group is used to perform all-round detection and recording of the target elevator shaft to obtain the multi-directional shaft detection point cloud data set.

3. The elevator shaft data modeling method based on drone detection according to claim 2 is characterized in that: The construction of the detection data integration processing channel includes: Acquire a multi-dimensional well detection database, classify and identify the multi-dimensional well detection database according to the detection sensor type, and obtain a well sensor detection data set; Determining a sensor data feature processing procedure according to the detection sensor type; Based on the sensor data feature processing program, feature extraction is performed on the shaft sensor detection data set to obtain a key feature set of sensor data; Network integration training and evaluation optimization are performed on the key feature set of the sensor data to build the detection data integration processing channel.

4. The elevator shaft data modeling method based on drone detection according to claim 3 is characterized in that: The step of constructing the detection data integration processing channel comprises: Aligning the key feature set of the sensor data according to a time series to obtain a sensor data feature sample set, and performing data characteristic analysis on the sensor data feature sample set to obtain sensor data characteristic information; Constructing a deep learning network list, matching the sensor data characteristic information with the deep learning network list, and determining a matching deep learning network set; Performing distributed training on the sensor data feature sample set based on the matching deep learning network set to generate a multi-sensor feature analysis network set; A model integration strategy is adopted to perform model integration training and evaluation optimization on the multi-sensor feature analysis network set, and to construct the detection data integration processing channel.

5. The elevator shaft data modeling method based on drone detection according to claim 3 is characterized in that: The step of obtaining the multi-directional wellbore detection point cloud data set includes: Based on the target detection entity area of ​​interest, the drone detection path information is additionally corrected to obtain the drone detection corrected path information; Performing obstacle identification and obstacle avoidance adjustment optimization on the drone detection correction path information to determine the drone detection optimization path information; Based on the drone detection optimization path information and the detection sensor group, the target elevator shaft is detected and recorded in all directions to obtain the multi-directional shaft detection point cloud data set.

6. The elevator shaft data modeling method based on drone detection according to claim 1 is characterized in that: The construction of the three-dimensional point cloud model of the elevator shaft includes: Filtering and denoising the multi-directional shaft detection point cloud data set to obtain a usable multi-directional shaft detection point cloud data set; Using a triangulated reconstruction algorithm to perform registration, alignment and triangulation reconstruction on the available multi-directional shaft detection point cloud data set to obtain a shaft triangular mesh model; Perform edge detection and model fitting training based on the hoistway triangle mesh model to determine panoramic modeling fitting parameters; The panoramic modeling fitting parameters are mapped to the hoistway triangular mesh model to reconstruct the point cloud model and build the elevator hoistway three-dimensional point cloud model.

7. The elevator shaft data modeling method based on drone detection according to claim 6 is characterized in that: The method of obtaining a usable multi-directional well detection point cloud data set includes: Extracting noise characteristics from the multi-directional wellbore detection point cloud data set to obtain point cloud noise characteristic information, and determining a wavelet selection threshold according to the point cloud noise characteristic information; Performing multi-scale decomposition on the multi-directional wellbore detection point cloud data set to obtain a point cloud multi-scale wavelet coefficient set; The point cloud multi-scale wavelet coefficient set is screened, filtered and reconstructed according to the wavelet selection threshold to obtain the available multi-directional wellbore detection point cloud data set.

8. The elevator shaft data modeling method based on drone detection according to claim 1 is characterized in that: The step of obtaining the optimized point cloud model of the elevator shaft comprises: Aligning and matching the geological structure model with the elevator shaft three-dimensional point cloud model to obtain an elevator shaft fused point cloud model; The elevator shaft fusion point cloud model is verified and evaluated to obtain model performance evaluation parameters, and the elevator shaft fusion point cloud model is iteratively corrected and optimized based on the model performance evaluation parameters to obtain the elevator shaft optimized point cloud model.

Images