Concrete floor flatness detection method and system and computer equipment

Abstract

The invention discloses a concrete terrace flatness detection method and system and computer equipment, and the method comprises the steps: S1, preparation before detection: preparing an intelligent mobile detection platform, and planning a detection path based on multiple factors of a terrace; s2, data acquisition: driving an intelligent mobile detection platform to move at a constant speed along a detection path, acquiring multi-source data of the terrace, and uploading the multi-source data to a data analysis and report generation module after preliminary preprocessing; s3, data analysis: a data analysis and report generation module constructs a three-dimensional model of the terrace according to the preliminarily preprocessed point cloud data, processes and identifies the preliminarily preprocessed image data based on an image segmentation algorithm, calculates the flatness and identifies a defect area of the terrace; and S4, report generation and output: a data analysis and report generation module generates a terrace quality evaluation detection report based on a data analysis result in S3. The method is more comprehensive, accurate and efficient in floor surface detection.

Description

Technical Field

[0001] The present invention relates to the technical field of floor flatness detection, and in particular to a method, system and computer equipment for detecting the flatness of a concrete floor. Background Art

[0002] In construction projects, the flatness of concrete floors is crucial for their subsequent use. In industrial plants, large, precision equipment relies on a highly flat floor. Even small fluctuations can cause vibrations, reducing machining accuracy and increasing defective product rates. This can impact automated production lines in automotive factories, even leading to breakdowns and production stoppages. In commercial spaces, uneven floors can easily cause customers to trip, detract from the aesthetics of the decor, and complicate cleaning and maintenance. For example, marble floors in high-end shopping malls are often constrained by the flatness of the base layer. In transportation hubs, the flatness of airport runways is crucial for aircraft takeoff and landing safety, while uneven train station platforms can cause inconvenience for passengers pushing their luggage.

[0003] However, existing methods for testing the flatness of concrete floors have obvious drawbacks, and the data processing link is particularly lagging. The test data needs to be manually entered, checked, and sorted, which is a cumbersome and error-prone process. Faced with massive amounts of data, manual work can only perform simple statistics, and it is difficult to uncover deep-seated quality issues, such as the flatness change trends in different areas. In construction projects, this slow data processing cannot provide accurate assessment reports in a timely manner, resulting in a lack of basis for construction decisions, delays in progress, and increased costs. Summary of the Invention

[0004] The present invention provides a more comprehensive, accurate and efficient concrete floor flatness detection method, system and computer equipment, which can solve at least one of the above technical problems.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] A method for detecting the flatness of a concrete floor comprises the following steps:

[0007] S1. Preparation before testing: Prepare the intelligent mobile testing platform and conduct a comprehensive calibration of the platform. Plan the testing path based on multiple factors of the floor. At the same time, set up positioning base stations around the testing area to provide a precise positioning benchmark for the intelligent mobile testing platform.

[0008] S2. Data Collection: Drive the intelligent mobile detection platform to move at a constant speed along the planned detection path. The multimodal sensor fusion module integrated in the intelligent mobile detection platform works synchronously to collect multi-source data of the floor. After preliminary pre-processing, the collected multi-source data is uploaded to the data analysis and report generation module.

[0009] S3. Data Analysis: The data analysis and report generation module constructs a three-dimensional model of the floor based on the pre-processed point cloud data. At the same time, it processes and identifies the pre-processed image data based on the image segmentation algorithm, integrates the pre-processed multi-source data for calibration, calculates the flatness, and identifies the defective areas on the floor surface.

[0010] S4. Report generation and output: The data analysis and report generation module generates a floor quality assessment and inspection report based on the data analysis results of S3, which includes at least floor flatness evaluation, various indicator data, defect distribution details and rectification suggestions.

[0011] Furthermore, in S1, the intelligent mobile detection platform has built-in floor detection software. The floor detection software plans the detection path using an optimization algorithm that integrates the A* algorithm and the Dijkstra algorithm. The concrete floor factors input into the optimization algorithm include at least layout and size. The global optimality is guaranteed based on the Dijkstra algorithm, and the heuristic search of the A* algorithm is combined to accelerate local path planning. While ensuring full coverage of the detection area, the shortest path is preferentially selected as the detection path to improve detection efficiency.

[0012] Furthermore, in S2, the multimodal sensor fusion module integrates at least a lidar, a linear array camera and an ultrasonic sensor. These multiple sensing devices work together and synchronously collect data while the intelligent mobile detection platform moves at a constant speed along the detection path. The collection frequency can be dynamically adjusted according to the complexity of the concrete floor surface to ensure accurate and efficient data collection.

[0013] Furthermore, in the S2, a real-time data processing and transmission module is integrated on the intelligent mobile detection platform. The multi-source data collected by the multimodal sensor fusion module are respectively imported into the real-time data processing and transmission module. The real-time data processing and transmission module uses an improved principal component analysis algorithm to perform preliminary preprocessing on the multi-source data. The preliminary preprocessing includes at least redundant information removal and key feature extraction. The data after preliminary preprocessing is uploaded to the data analysis and report generation module located at the remote end.

[0014] Furthermore, in S3, a three-dimensional model of the floor is constructed using the point cloud data collected by the lidar using a three-dimensional modeling software, and the image data collected by the linear array camera is processed and recognized using an image segmentation algorithm. The improved international flatness index is calculated according to the following formula, and the other key flatness indicators are calculated at the same time. The calculation expression is:

[0015]

[0016] Where IIRI stands for Improved International Roughness Index, N is the total number of measurement segments, and ω i Represents the weight coefficient of different detection areas, Δhi is the elevation difference between adjacent measuring points, L i is the measurement segment length.

[0017] Furthermore, in S4, the floor quality assessment and inspection report is presented in a three-dimensional visual form and supports output in multiple formats.

[0018] A concrete floor flatness detection system, applicable to the concrete floor flatness detection method, comprising:

[0019] The intelligent mobile detection platform is equipped with wheels for driving the platform, an integrated gyroscope and electronic compass for ensuring the stability of the mobile posture, an autonomous navigation unit for autonomous movement according to the planned path, a load adjustment unit for adjusting the platform equipment parameters to adapt to load changes, and an obstacle detection sensor for detecting obstacles and adjusting the detour;

[0020] A multimodal sensor fusion module, which is installed on the intelligent mobile detection platform and is integrated with a collection device for collecting multi-source data on the floor surface. The collection device includes at least a lidar, a linear array camera, and an ultrasonic sensor, and is equipped with an adaptive calibration unit for automatically calibrating the collection device according to fluctuations;

[0021] A real-time data processing and transmission module, which is installed on the mobile detection platform, connected to the output end of the multimodal sensor fusion module, and has a built-in chip integrating an improved principal component analysis algorithm and an encrypted communication protocol, and is used to perform preliminary preprocessing and encrypted transmission of multi-source data input by the multimodal sensor fusion module;

[0022] A data analysis and report generation module is connected to the output end of the real-time data processing and transmission module and is equipped with a cloud computing architecture. The cloud computing architecture is equipped with a convolutional neural network for calculating the flatness of the current floor and comparing it with historical calculation data to evaluate the change trend and generate a floor quality assessment and inspection report.

[0023] Furthermore, the multimodal sensor fusion module has a built-in time and space registration unit for unifying the timestamps and spatial coordinate systems of the multi-source collected data after measuring and calibrating the installation positions and installation angles of multiple collection devices.

[0024] Furthermore, the data analysis and report generation module includes a historical data comparison unit and a three-dimensional visualization display unit. The historical data comparison unit is used to compare the current calculation data with the historical calculation data, evaluate the flatness change trend of the same floor, and trigger an early warning when the change trend deteriorates. The three-dimensional visualization display unit is used to present the floor quality assessment and inspection report in three dimensions.

[0025] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned concrete floor flatness detection method.

[0026] The beneficial effects of the present invention are embodied in:

[0027] 1. The intelligent mobile detection platform prioritizes the shortest path while ensuring full coverage of the detection area and moves at a stable speed to ensure smooth and rapid completion of the detection task. In addition, the intelligent mobile detection platform is equipped with a gyroscope and an electronic compass. Regular calibration is used to ensure the platform's detection accuracy and stable moving posture. The platform's collection frequency can be dynamically adjusted according to the complexity of the floor surface, further improving the efficiency of data collection, saving detection time, and avoiding delays in construction progress due to long detection cycles.

[0028] 2. In the multimodal sensor fusion module, multiple sensing / acquisition devices work together and achieve data fusion through time and space registration technology to ensure the accuracy and completeness of the collected data. At the same time, the real-time data processing and transmission module uses an improved principal component analysis algorithm to pre-process the collected data from multiple sources to remove noise and redundant information, and uses convolutional neural networks for in-depth analysis. The combination of these measures makes the calculation of various flatness indicators more accurate, and can accurately identify floor defect areas, providing a reliable basis for floor quality assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0030] Figure 1 This is a flowchart of the overall process of the concrete floor flatness detection method according to an embodiment of the present invention.

[0031] Figure 2 This is a block diagram of the overall structure of the concrete floor flatness detection system according to an embodiment of the present invention.

[0032] Figure 3 It is a structural block diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement, etc. between the components under a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the meaning of "and / or" appearing throughout the text includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that meet both A and B. In addition, "multiple" refers to more than two.

[0035] See also Figure 1 The embodiment of the present invention provides a method for detecting the flatness of a concrete floor, comprising the following steps:

[0036] S1. Preparation before testing: Prepare the intelligent mobile testing platform and conduct a comprehensive calibration of the platform. Plan the testing path based on multiple factors of the floor. At the same time, set up positioning base stations around the testing area to provide a precise positioning benchmark for the intelligent mobile testing platform.

[0037] S2. Data Collection: Drive the intelligent mobile detection platform to move at a constant speed along the planned detection path. The multimodal sensor fusion module integrated in the intelligent mobile detection platform works synchronously to collect multi-source data of the floor. After preliminary pre-processing, the collected multi-source data is uploaded to the data analysis and report generation module.

[0038] S3. Data Analysis: The data analysis and report generation module constructs a three-dimensional model of the floor based on the pre-processed point cloud data. At the same time, it processes and identifies the pre-processed image data based on the image segmentation algorithm, integrates the pre-processed multi-source data for calibration, calculates the flatness, and identifies the defective areas on the floor surface.

[0039] S4. Report generation and output: The data analysis and report generation module generates a floor quality assessment and inspection report based on the data analysis results of S3, which includes at least floor flatness evaluation, various indicator data, defect distribution details and rectification suggestions.

[0040] In this embodiment, in S1, the intelligent mobile detection platform has built-in floor detection software. The floor detection software uses an optimization algorithm that integrates the A* algorithm and the Dijkstra algorithm to plan the detection path. The concrete floor factors input into the optimization algorithm include at least layout and size. The global optimality is guaranteed based on the Dijkstra algorithm, and the heuristic search of the A* algorithm is combined to accelerate local path planning. While ensuring full coverage of the detection area, the shortest path is preferentially selected as the detection path to improve detection efficiency.

[0041] The A* (A-Star) algorithm is the most effective method for finding the shortest path in a static road network. The expression formula is:

[0042] f(n)=g(n)+h(n)

[0043] Where f(n) is the cost function from the initial point to the target point via node n, g(n) is the actual cost from the initial node to node n in the state space, and h(n) is the estimated cost of the best path from n to the target node.

[0044] The key to ensuring the shortest path (optimal solution) is the selection of the evaluation function h(n):

[0045] If the estimated value h(n) ≤ the actual value of the distance from n to the target node, in this case, the number of search points is large, the search range is large, and the efficiency is low, but the optimal solution can be obtained;

[0046] If the estimated value h(n) is greater than the actual distance from n to the target node, in this case, the number of search points is small, the search range is small, and the efficiency is high, but the optimal solution cannot be guaranteed.

[0047] It can be seen that the closer the estimated value is to the actual value, the better the evaluation function f(n) is. For example, for a geometric road network, the Euclidean distance (straight-line distance) between two nodes can be taken as the estimated value, that is:

[0048] f(n)=g(n)+sqrt[(dx-nx)*(dx-nx)+(dy-ny)*(dy-ny)]

[0049] In this way, the evaluation function f(n) will be more or less restricted by the estimated value h when the g value is constant. The closer the node is to the target point, the smaller the h value is, and the f(n) value is relatively small, which can ensure that the shortest path search is carried out in the direction of the end point.

[0050] Dijkstra's algorithm uses breadth-first search to solve the single-source shortest path problem for a weighted directed graph. There are many variations of this algorithm; the original version of Dijkstra's algorithm finds the shortest path between two vertices, but a more common variation fixes a vertex as the source node and then finds the shortest paths from that vertex to all other nodes in the graph, producing a shortest path tree. This algorithm is often used in routing algorithms or as a submodule of other graph algorithms. For example, if the vertices in a graph represent cities, and the edge weights represent the driving distance between cities, this algorithm can be used to find the shortest path between two cities.

[0051] The input to Dijkstra's algorithm consists of a weighted directed graph G and a source vertex S in G, with V representing the set of all vertices in G. Each edge in the graph is an ordered pair of elements formed by two vertices. (u, v) indicates that there is a path from vertex u to v, and E represents the set of all edges in G. The weight of an edge is defined by the weight function w: E→[0,∞]. Therefore, w(u,v) is the non-negative weight from vertex u to vertex v. The weight of an edge can be imagined as the distance between two vertices. The weight of a path between any two points is the sum of the weights of all edges on that path. Given vertices s and t in V, Dijkstra's algorithm can find the lowest-weight path (i.e., the shortest path) from s to t. The algorithm can also find the shortest path from a vertex s to any other vertex in a graph.

[0052] At present, the fusion and improvement of the above two algorithms has formed a mature technical solution in the field of path planning. For example, in this application, the Dijkstra algorithm is used to ensure global optimization, and the heuristic search of the A* algorithm is combined to accelerate local path planning. Therefore, we will not go into details here. The purpose is that the intelligent mobile detection platform moves at a constant speed (optionally set to 0.8m / s) and fully covers the detection area. At the same time, the floor detection software uses an optimization algorithm that integrates the A* algorithm and the Dijkstra algorithm to plan the detection path, and gives priority to selecting the shortest path as the detection path.

[0053] In this embodiment, in S2, the multimodal sensor fusion module integrates at least a lidar, a linear array camera and an ultrasonic sensor. The multiple sensing devices work together and synchronously collect data while the intelligent mobile detection platform moves at a uniform speed along the detection path. The collection frequency can be dynamically adjusted according to the complexity of the concrete floor surface. For example, when encountering a complex floor area, the intelligent mobile detection platform will automatically increase the collection frequency to ensure accurate and efficient data collection.

[0054] In this embodiment, in S2, a real-time data processing and transmission module is integrated on the intelligent mobile detection platform. The multi-source data collected by the multimodal sensor fusion module are imported into the real-time data processing and transmission module respectively. The real-time data processing and transmission module uses an improved principal component analysis algorithm to perform preliminary preprocessing on the multi-source data. The preliminary preprocessing includes at least redundant information removal and key feature extraction. The data after preliminary preprocessing is uploaded to the data analysis and report generation module located at the remote end. The data transmission module can be optionally set to wireless, wired, Bluetooth, 5G network and other methods.

[0055] In this embodiment, in S3, existing professional 3D modeling software is used to construct a 3D model of the floor based on the point cloud data collected by the lidar. An image segmentation algorithm is used to process and identify the image data collected by the linear array camera. The improved international flatness index is calculated according to the following formula. At the same time, other key flatness indicators are calculated. The calculation expression is:

[0056]

[0057] Where IIRI stands for Improved International Roughness Index, N is the total number of measurement segments, and ω i Represents the weight coefficient of different detection areas, Δh i is the elevation difference between adjacent measuring points, L i is the measurement segment length.

[0058] The calculated flatness levels provide a scientific and reliable basis for the final floor quality assessment and inspection report.

[0059] In this embodiment, in S4, the floor quality assessment and inspection report is presented in a three-dimensional visual form and supports output in multiple formats, which is convenient for staff to view and use.

[0060] See also Figure 2 The embodiment of the present invention further provides a concrete floor flatness detection system, which is applicable to the concrete floor flatness detection method, and includes:

[0061] The intelligent mobile detection platform is equipped with wheels for driving the platform, an integrated gyroscope and electronic compass for ensuring the stability of the mobile posture, an autonomous navigation unit for autonomous movement according to the planned path, a load adjustment unit for adjusting the platform equipment parameters to adapt to load changes, and an obstacle detection sensor for detecting obstacles and adjusting the detour;

[0062] A multimodal sensor fusion module, which is installed on the intelligent mobile detection platform and is integrated with a collection device for collecting multi-source data on the floor surface. The collection device includes at least a lidar, a linear array camera, and an ultrasonic sensor, and is equipped with an adaptive calibration unit for automatically calibrating the collection device according to fluctuations;

[0063] A real-time data processing and transmission module, which is installed on the mobile detection platform, connected to the output end of the multimodal sensor fusion module, and has a built-in chip integrating an improved principal component analysis algorithm and an encrypted communication protocol, and is used to perform preliminary preprocessing and encrypted transmission of multi-source data input by the multimodal sensor fusion module;

[0064] A data analysis and report generation module is connected to the output end of the real-time data processing and transmission module and is equipped with a cloud computing architecture. The cloud computing architecture is equipped with a convolutional neural network for calculating the flatness of the current floor and comparing it with historical calculation data to evaluate the change trend and generate a floor quality assessment and inspection report.

[0065] In this embodiment, the intelligent mobile detection platform adopts a four-wheel drive design, and a gyroscope and an electronic compass are installed on the platform. The platform's detection accuracy is ensured through regular calibration, and the stability of the moving posture is guaranteed. It is equipped with an autonomous navigation unit and pre-recorded with map information of the detection area, so that the platform can move autonomously according to the planned path. In the event of the need to carry additional detection equipment, the load adjustment unit can automatically adjust parameters such as wheel tire pressure and motor power to adapt to changes in load, ensure smooth operation of the vehicle, and avoid affecting the detection accuracy. At the same time, when the obstacle detection sensor detects an obstacle ahead, the platform automatically plans and adjusts the moving path, bypasses the obstacle, and continues to complete the mobile detection operation.

[0066] In this embodiment, the multimodal sensor fusion module incorporates a built-in temporal and spatial registration unit, which is used to unify the timestamps and spatial coordinate systems of the multi-source collected data after measuring and calibrating the installation positions and angles of multiple acquisition devices. Before detection begins, the temporal and spatial registration unit precisely measures and calibrates the installation positions and angles of each sensor / acquisition device, unifying the timestamps and spatial coordinate systems of the data from each sensor / acquisition device. During the detection process, an adaptive calibration unit automatically calibrates the lidar, linear array camera, and ultrasonic sensor based on environmental factors and fluctuations in the detection data, improving detection accuracy.

[0067] In this embodiment, the real-time data processing and transmission module has a built-in high-performance chip, which integrates an improved principal component analysis algorithm, and can perform preliminary preprocessing on the input multi-source collected data, that is, removing redundant information and extracting key features. The preprocessed multi-source data is transmitted to the data analysis and report generation module. During the transmission process, an encryption transmission algorithm is used to encrypt the data to prevent the data from being stolen or tampered with.

[0068] In this embodiment, the data analysis and report generation module includes a historical data comparison unit and a three-dimensional visualization display unit. The historical data comparison unit is used to compare the current calculation data with the historical calculation data, evaluate the flatness change trend of the same floor, and trigger an early warning when the change trend deteriorates. The three-dimensional visualization display unit is used to intuitively present the floor quality assessment test report in three dimensions. The report presents the test results in an intuitive and easy-to-understand form, providing strong support for construction decisions.

[0069] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the above-mentioned concrete floor flatness detection method.

[0070] See also Figure 3 An embodiment of the present invention further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned concrete floor flatness detection method.

[0071] An embodiment of the present invention further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the steps of the above-mentioned method for detecting the flatness of a concrete floor.

[0072] It is understandable that the system, device and storage medium provided in the embodiments of the present invention correspond to the method provided in the embodiments of the present invention. The explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above-mentioned concrete floor flatness detection method.

[0073] It should be noted that those skilled in the art will understand that all or part of the steps implemented in the embodiments of the present invention can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using hardware, it can be implemented in whole or in part in the form of purchased standard parts or modified parts. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0074] In summary, the present invention provides a concrete floor flatness detection system and method to solve the problem that the current concrete floor flatness detection method cannot provide accurate evaluation reports in a timely manner, resulting in a lack of basis for construction decision-making, delays in progress and increased costs. The detection system includes an intelligent mobile detection platform, a multi-modal sensor fusion module, a real-time data processing and transmission module and a data analysis and report generation module. The multi-module sensor fusion module and the real-time data processing and transmission module are integrated and installed on the intelligent mobile detection platform. When the platform moves at a constant speed in the detection area, real-time collection, processing, analysis and transmission of multi-source data are performed respectively. The data analysis and report generation module is placed at the remote end, and the data is summarized to form a visual floor quality assessment and detection report for intuitive understanding and use by staff. The detection method performs detection operations based on the configuration of the detection system, and completes path optimization planning, data analysis and processing, three-dimensional modeling, flatness calculation and report generation in sequence. The whole process is efficient and fast, which greatly improves the efficiency of concrete floor surface condition analysis and promotes construction progress.

[0075] It should be understood that the examples and implementation methods described herein are for illustrative purposes only and are not intended to limit the present invention. Those skilled in the art may make various modifications or changes based on them. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting the flatness of a concrete floor, characterized in that: The following steps are involved: S1. Preparation before testing: Prepare the intelligent mobile testing platform and conduct a comprehensive calibration of the platform. Plan the testing path based on multiple factors of the floor. At the same time, set up positioning base stations around the testing area to provide a precise positioning benchmark for the intelligent mobile testing platform. S2. Data Collection: Drive the intelligent mobile detection platform to move at a constant speed along the planned detection path. The multimodal sensor fusion module integrated in the intelligent mobile detection platform works synchronously to collect multi-source data of the floor. After preliminary pre-processing, the collected multi-source data is uploaded to the data analysis and report generation module. S3. Data Analysis: The data analysis and report generation module constructs a three-dimensional model of the floor based on the pre-processed point cloud data. At the same time, it processes and identifies the pre-processed image data based on the image segmentation algorithm, integrates the pre-processed multi-source data for calibration, calculates the flatness, and identifies the defective areas on the floor surface. S4. Report generation and output: The data analysis and report generation module generates a floor quality assessment and inspection report based on the data analysis results of S3, which includes at least floor flatness evaluation, various indicator data, defect distribution details and rectification suggestions.

2. The method for detecting the flatness of a concrete floor according to claim 1, wherein: In S1, the intelligent mobile detection platform has built-in floor detection software. The floor detection software plans the detection path using an optimization algorithm that integrates the A* algorithm and the Dijkstra algorithm. The concrete floor factors input into the optimization algorithm include at least layout and size. The global optimality is guaranteed based on the Dijkstra algorithm. The heuristic search of the A* algorithm is combined to accelerate local path planning. While ensuring full coverage of the detection area, the shortest path is preferentially selected as the detection path to improve detection efficiency.

3. The method for detecting the flatness of a concrete floor according to claim 1, wherein: In S2, the multimodal sensor fusion module integrates at least a lidar, a linear array camera, and an ultrasonic sensor. These multiple sensing devices work together to synchronously collect data while the intelligent mobile detection platform moves at a constant speed along the detection path. The collection frequency can be dynamically adjusted according to the complexity of the concrete floor surface to ensure accurate and efficient data collection.

4. The method for detecting the flatness of a concrete floor according to claim 1, wherein: In the S2, a real-time data processing and transmission module is integrated on the intelligent mobile detection platform. The multi-source data collected by the multimodal sensor fusion module are imported into the real-time data processing and transmission module respectively. The real-time data processing and transmission module uses an improved principal component analysis algorithm to perform preliminary preprocessing on the multi-source data. The preliminary preprocessing includes at least redundant information removal and key feature extraction. The data after preliminary preprocessing is uploaded to the data analysis and report generation module located at the remote end.

5. The method for detecting the flatness of a concrete floor according to claim 3, wherein: In S3, a three-dimensional model of the floor is constructed using the point cloud data collected by the lidar using a three-dimensional modeling software, and the image data collected by the linear array camera is processed and recognized using an image segmentation algorithm. The improved international flatness index is calculated according to the following formula, and the other key flatness indicators are calculated at the same time. The calculation expression is: Where IIRI stands for Improved International Roughness Index, N is the total number of measurement segments, and ω i Represents the weight coefficient of different detection areas, Δh i is the elevation difference between adjacent measuring points, L i is the measurement segment length.

6. The method for detecting the flatness of a concrete floor according to claim 1, wherein: In S4, the floor quality assessment and inspection report is presented in a three-dimensional visual form and supports output in multiple formats.

7. A concrete floor flatness detection system, applicable to the concrete floor flatness detection method according to any one of claims 1 to 6, characterized in that: include: The intelligent mobile detection platform is equipped with wheels for driving the platform, an integrated gyroscope and electronic compass for ensuring the stability of the mobile posture, an autonomous navigation unit for autonomous movement according to the planned path, a load adjustment unit for adjusting the platform equipment parameters to adapt to load changes, and an obstacle detection sensor for detecting obstacles and adjusting the detour; A multimodal sensor fusion module, which is installed on the intelligent mobile detection platform and is integrated with a collection device for collecting multi-source data on the floor surface. The collection device includes at least a lidar, a linear array camera, and an ultrasonic sensor, and is equipped with an adaptive calibration unit for automatically calibrating the collection device according to fluctuations; A real-time data processing and transmission module, which is installed on the mobile detection platform, connected to the output end of the multimodal sensor fusion module, and has a built-in chip integrating an improved principal component analysis algorithm and an encrypted communication protocol, and is used to perform preliminary preprocessing and encrypted transmission of multi-source data input by the multimodal sensor fusion module; A data analysis and report generation module is connected to the output end of the real-time data processing and transmission module and is equipped with a cloud computing architecture. The cloud computing architecture is equipped with a convolutional neural network for calculating the flatness of the current floor and comparing it with historical calculation data to evaluate the change trend and generate a floor quality assessment and inspection report.

8. The concrete floor flatness detection system according to claim 7, characterized in that: The multimodal sensor fusion module has a built-in time and space registration unit for unifying the timestamps and spatial coordinate systems of the multi-source collected data after measuring and calibrating the installation positions and installation angles of multiple collection devices.

9. The concrete floor flatness detection system according to claim 7, characterized in that: The data analysis and report generation module includes a historical data comparison unit and a three-dimensional visualization display unit. The historical data comparison unit is used to compare the current calculation data with the historical calculation data, evaluate the flatness change trend of the same floor, and trigger an early warning when the change trend deteriorates. The three-dimensional visualization display unit is used to intuitively present the floor quality assessment and inspection report in three dimensions.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the concrete floor flatness detection method according to any one of claims 1 to 6.

Images