Intelligent stair life prediction and maintenance method based on multi-sensor fusion

Abstract

The invention relates to an intelligent stair life prediction and maintenance method and system based on multi-sensor fusion, computer equipment and a storage medium. The method comprises the steps that a laser sensor is adopted to scan a stair to obtain a wear data set of the stair; based on at least one pressure sensor preset in each designated area of the stairway, a pressure data set of each designated area of the stairway is obtained; identifying the type of the stair material by adopting a spectrum analyzer to obtain a wear-resistant coefficient and a maximum wear depth corresponding to the type of the stair material; and constructing a life prediction operator, calculating the life of each specified region of the staircase through the life prediction operator, predicting the overall life of the staircase according to a calculation result, and calculating maintenance data of the staircase through a K-means clustering algorithm. By adopting the method, the wear depth, the pressure distribution and the material fatigue condition of the stairs can be monitored and evaluated in real time, and the service life prediction and maintenance analysis are carried out by combining an algorithm.

Description

Technical Field

[0001] The present application relates to the technical field of building maintenance, and particularly to an intelligent staircase life prediction and maintenance method, system, computer device, and storage medium based on multi-sensor fusion. Background Art

[0003] Traditional staircase maintenance and life prediction rely on manual inspections and regular overhauls, which have certain subjectivity and limitations and are difficult to achieve accurate and real-time health monitoring. Traditional technologies are relatively weak in monitoring capabilities such as staircase wear detection, pressure distribution analysis, and material fatigue assessment, and cannot provide high-precision life prediction and scientific maintenance decision support. Therefore, there is an urgent need for an efficient, accurate, and intelligent staircase health monitoring and life prediction method that can achieve comprehensive, continuous, and non-destructive detection and evaluation of staircases by integrating multiple sensors and advanced algorithms to ensure the safety of staircases and optimize maintenance management. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide an intelligent staircase life prediction and maintenance method, system, computer device, and storage medium based on multi-sensor fusion that can automatically analyze the remaining life, historical maintenance times, and usage frequency of staircases.

[0005] In a first aspect, the present application provides an intelligent staircase life prediction and maintenance method based on multi-sensor fusion, which is used to predict the life of a staircase and generate a maintenance plan for the staircase, and includes:

[0006] Step S1: Use a laser sensor to scan the staircase to generate a wear depth map and obtain a wear data set of the staircase;

[0007] Step S2: Based on at least one pressure sensor preset for each specified area of the staircase, obtain a pressure data set for each specified area of the staircase;

[0008] Step S3: Use a spectral analyzer to identify the type of staircase material and obtain the wear resistance coefficient and maximum wear depth corresponding to the staircase material type;

[0009] Step S4: Based on the wear data set of the staircase, the pressure data set for each specified area of the staircase, the wear resistance coefficient and maximum wear depth corresponding to the staircase material type, construct a life prediction operator, calculate the life of each specified area of the staircase through the life prediction operator, predict the overall life of the staircase according to the calculation results, and calculate the maintenance data of the staircase through the K-means clustering algorithm.

[0010] In one embodiment, the life prediction operator in step S4 is as follows:

[0011]

[0012] Among them, d(x, y) is the wear depth in the wear dataset of the stairs, and d max is the maximum wear depth corresponding to the stair material type, is the pressure dataset of each specified area of the stairs, and K is the wear resistance coefficient corresponding to the stair material type.

[0013] In one embodiment, before constructing the life prediction operator in step S4, it further includes:

[0014] Establish a wear model using a two-dimensional Gaussian distribution to fit the wear dataset, where the wear dataset includes the wear center and wear diffusion range of each specified area of the stairs;

[0015] The wear dataset obtained by fitting the wear model established according to the two-dimensional Gaussian distribution is used to assist the life prediction operator to predict the overall life of the stairs and assist the K-means clustering algorithm to calculate the maintenance data of the stairs.

[0016] In one embodiment, the wear model established using a two-dimensional Gaussian distribution in step S4 is as follows:

[0017]

[0018] Among them, W(x, y) is the result obtained by fitting the wear model, x and y are the coordinates of each sampling point in the specified area of the stairs, μ x , μ y are the wear centers of each specified area of the stairs, and σ x , σ y are the wear diffusion ranges of each specified area of the stairs.

[0019] In one embodiment, before constructing the life prediction operator in step S4, it further includes:

[0020] Obtain the pedestrian flow data according to the pressure sensor, calculate the relationship formula between the pedestrian flow and wear using the Poisson distribution, and analyze the relationship formula between the usage frequency of the stairs and wear using the power-law model;

[0021] Based on the relationship formula between the pedestrian flow and wear and the relationship formula between the usage frequency of the stairs and wear, assist the life prediction operator to predict the overall life of the stairs and assist the K-means clustering algorithm to calculate the maintenance data of the stairs.

[0022] In one embodiment, calculating the life of each specified area of the stairs through the life prediction operator in step S4 and predicting the overall life of the stairs according to the calculation results includes:

[0023] Calculate the overall life of the stairs by the minimum value of the life of each specified area of the stairs;

[0024] Determine whether the overall lifespan of the staircase meets a pre-set expected value; if it does not meet the expected value, iterate the lifespan prediction operator through machine learning and calculate the overall lifespan of the staircase, and if it meets the expected value, output the calculated overall lifespan of the staircase to a display device.

[0025] In one embodiment, the method further includes:

[0026] Combine the wear dataset of the staircase obtained by the camera device and the laser sensor, and the pressure dataset of each specified area of the staircase obtained by the pressure sensor to generate a three-dimensional health analysis model of the staircase, which is used to detect the deformation vibration of the staircase and analyze the stability of the staircase.

[0027] In a second aspect, the present application further provides an intelligent staircase lifespan prediction and maintenance system based on multi-sensor fusion, including:

[0028] An integrated laser scanning module for scanning the staircase with a laser sensor to generate a wear depth map and obtain a wear dataset of the staircase;

[0029] A pressure sensing module for obtaining a pressure dataset of each specified area of the staircase based on at least one pressure sensor preset for each specified area of the staircase;

[0030] A material analysis module for identifying the type of staircase material using a spectral analyzer to obtain the wear resistance coefficient and the maximum wear depth corresponding to the staircase material type;

[0031] A data processing module for constructing a lifespan prediction operator based on the wear dataset of the staircase, the pressure dataset of each specified area of the staircase, the wear resistance coefficient and the maximum wear depth corresponding to the staircase material type, calculating the lifespan of each specified area of the staircase through the lifespan prediction operator and predicting the overall lifespan of the staircase according to the calculation results, and calculating the maintenance data of the staircase through the K-means clustering algorithm.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the intelligent staircase lifespan prediction and maintenance method based on multi-sensor fusion.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the intelligent staircase lifespan prediction and maintenance method based on multi-sensor fusion.

[0034] The above-mentioned intelligent staircase life prediction and maintenance method, system, computer device and storage medium based on multi-sensor fusion scan the staircase through the laser sensor of the laser scanning module to generate a wear depth map and obtain the wear data set of the staircase; obtain the pressure data set of each specified area of the staircase through the pressure sensing module, and obtain the wear resistance coefficient and the maximum wear depth corresponding to the staircase material type through the material analysis module. The multi-sensors not only collect the wear depth, pressure distribution and material property data on the surface of the staircase in real time, but also combine the comprehensive life prediction operator based on the Gaussian distribution and Poisson distribution to automatically analyze the remaining life, historical maintenance times and usage frequency of the staircase. This method and system have the characteristics of non-destructive detection, high-precision prediction and wide applicability, and can provide a scientific basis for fields such as building maintenance and archaeological research. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a heat map of usage frequency at different times and spaces obtained according to the Poisson distribution in one embodiment;

[0036] Figure 2 It is a K-means clustering result map of the wear data set in one embodiment;

[0037] Figure 3 It is a heat map of the error between the predicted life and the actual life data in one embodiment;

[0038] Figure 4 It is a schematic flow chart of predicting the life using the life prediction operator in the intelligent staircase life prediction and maintenance method based on multi-sensor fusion in one embodiment;

[0039] Figure 5 It is a wear gradient map at different positions of the staircase in one embodiment;

[0040] Figure 6 It is a schematic flow chart of the intelligent staircase life prediction and maintenance method based on multi-sensor fusion in one embodiment;

[0041] Figure 7 It is a schematic diagram of the intelligent staircase life prediction and maintenance system based on multi-sensor fusion in one embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] This application relates to an intelligent staircase life prediction and maintenance method and system based on multi-sensor fusion. The system integrates a laser scanning module, a pressure sensing module and a material analysis module to monitor and evaluate the wear depth, pressure distribution and material fatigue of the staircase in real time, and combines advanced algorithms for life prediction and maintenance analysis. This technology is widely used in fields such as building maintenance, facility management, and public safety, providing accurate health status monitoring for structures such as staircases, optimizing maintenance decisions, and improving the safety and service life of buildings.

[0043] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] In an exemplary embodiment, an intelligent staircase life prediction and maintenance method based on multi-sensor fusion is provided, including:

[0045] Step S1: Use a laser sensor to scan the staircase to generate a wear depth map and obtain a wear data set of the staircase;

[0046] Step S2: Based on at least one pressure sensor preset for each specified area of the staircase, obtain a pressure data set for each specified area of the staircase;

[0047] Step S3: Use a spectral analyzer to identify the type of staircase material and obtain the wear resistance coefficient and maximum wear depth corresponding to the staircase material type;

[0048] Step S4: Based on the wear data set of the staircase, the pressure data set for each specified area of the staircase, the wear resistance coefficient and maximum wear depth corresponding to the staircase material type, construct a life prediction operator, calculate the life of each specified area of the staircase through the life prediction operator, predict the overall life of the staircase according to the calculation results, and calculate the maintenance data of the staircase through the K-means clustering algorithm.

[0049] Specifically, the laser in the laser sensor scans to generate a three-dimensional wear map, the pressure sensor records the dynamic pressure, and the spectral analysis identifies the material type. A high-precision laser sensor with an accuracy of ±0.1 mm is used to scan the staircase surface to generate a three-dimensional wear depth map d(x, y) with a resolution of 0.01 mm 2 ; The resolution of the embedded pressure sensor array is 1 Pa, and the dynamic pressure distribution P(x, y, t) when pedestrians walk is recorded in real time. The material type is identified by a spectral analyzer (wavelength range 400 nm - 1000 nm), and the preset wear resistance coefficient K is matched. For example, for granite, K = 0.0001.

[0050] Furthermore, pressure sensors deployed at key load-bearing nodes of the staircase (such as the edge of the step, support beam, etc.) monitor the pressure distribution and dynamic load changes in real time to detect material fatigue or local stress concentration.

[0051] Furthermore, the built-in algorithm of the microcomputer main control module analyzes the multi-sensor data through the data processing module, generates a three-dimensional health model of the staircase structure in combination with 3D modeling technology (similar to 3D mesh), compares with historical data or building code standards (such as load-bearing thresholds, allowable deformation ranges), establishes a fatigue life database for staircase materials, predicts the remaining life through machine learning, and updates the detection results in real time. Fit the Gaussian distribution to extract wear parameters, estimate the Poisson flow rate λ, and calculate the remaining life T total . It has a built-in embedded processor that runs core algorithms including a two-dimensional Gaussian distribution wear model, a Poisson pedestrian flow model, a power-law model, etc.

[0052] In an exemplary embodiment, before constructing the life prediction operator in step S4, it further includes:

[0053] Establish a wear model using a two-dimensional Gaussian distribution to fit the wear data set, where the wear data set includes the wear center and wear diffusion range of each specified area of the staircase;

[0054] The wear data set obtained by fitting the wear model established according to the two-dimensional Gaussian distribution is used to assist the life prediction operator to predict the overall life of the staircase and assist the K-means clustering algorithm to calculate the maintenance data of the staircase.

[0055] Exemplarily, the wear data is fitted by the non-linear least squares method to extract the wear center (μ x , μy) and the diffusion range (σ x , σy) of each specified area of the staircase, and the accuracy is improved by 40% compared with the traditional method.

[0056] Specifically, the wear model established by the two-dimensional Gaussian distribution is as follows:

[0057]

[0058] Among them, W(x, y) is the result obtained by fitting the wear model, x and y are the coordinates of each sampling point in the specified area of the staircase, μ x 、μ y are the wear centers of each specified area of the staircase, and σ x 、σ y are the wear diffusion ranges of each specified area of the staircase.

[0059] In an exemplary embodiment, before constructing the life prediction operator in step S4, it further includes:

[0060] Obtain the pedestrian flow data according to the pressure sensor, calculate the relationship formula between the pedestrian flow and wear using the Poisson distribution, and analyze the relationship formula between the usage frequency of the staircase and wear using the power-law model;

[0061] Based on the relationship formula between the pedestrian flow and wear, and the relationship formula between the usage frequency of the stairs and wear, assist the life prediction operator to predict the overall life of the stairs and assist the K-means clustering algorithm to calculate the maintenance data of the stairs.

[0062] Specifically, the Poisson pedestrian flow model is used to estimate the usage frequency of the stairs. This model helps to understand the relationship between the pedestrian flow and wear, and optimize the prediction of the stairs' life. The formula is as follows:

[0063]

[0064] Where λ is the usage frequency of the stairs, x i is the coordinate of the position where the usage frequency of the stairs is to be estimated, and n is the number of positions where the usage frequency is to be estimated.

[0065] In this embodiment, the usage frequency heat map at different times and spaces obtained according to the Poisson distribution is as Figure 1 shown.

[0066] Furthermore, the power-law model is simultaneously used to analyze the relationship between the usage frequency of the stairs and wear, as shown in the following formula:

[0067] f(x,y) = C m ·(d(x,y)) α

[0068] Where the parameters C m and α are used to adjust the relationship between the usage frequency and the wear depth.

[0069] In an exemplary embodiment, a stairs life prediction operator is designed. According to the wear depth d(x,y) at each position of the stairs, combined with the maximum wear depth d max of the material and the pressure data calculate the remaining life of each position, so as to infer the local remaining life. The life prediction operator is as follows:

[0070]

[0071] Where d(x,y) is the wear depth in the wear dataset of the stairs, d max is the maximum wear depth corresponding to the stairs material type, is the pressure dataset of each specified area of the stairs, and K is the wear resistance coefficient corresponding to the stairs material type. Among them, the K-means clustering result of the wear dataset is as Figure 2 shown.

[0072] In an exemplary embodiment, in step S4, calculating the life of each specified area of the stairs through the life prediction operator and predicting the overall life of the stairs according to the calculation results includes:

[0073] Calculate the overall lifespan of the staircase by taking the minimum value of the lifespans of each specified area of the staircase;

[0074] Determine whether the overall lifespan of the staircase meets a pre-set expected value; if it does not meet the expected value, iterate the lifespan prediction operator through machine learning and calculate the overall lifespan of the staircase, and if it meets the expected value, output the calculated overall lifespan of the staircase to a display device.

[0075] Specifically, in this embodiment, the overall remaining lifespan is calculated by taking the minimum value of the remaining lifespans of all local parts of the staircase, and the formula is as follows:

[0076]

[0077] where T remaining (x, y) is the remaining lifespan of each position of the staircase.

[0078] Exemplarily, the error heat map of the predicted lifespan and the actual lifespan data in this embodiment is as Figure 3 shown.

[0079] In an exemplary embodiment, the K-means clustering algorithm is combined to identify the repaired areas and output the number of repairs, specifically as follows:

[0080]

[0081] where J is the number of repairs, d i represents the feature vector of the i-th sample, and μ k represents the center of the k-th cluster.

[0082] In an exemplary embodiment, in step S4, calculating the lifespan of each specified area of the staircase through the lifespan prediction operator and predicting the overall lifespan of the staircase based on the calculation results includes:

[0083] Calculate the overall lifespan of the staircase by taking the minimum value of the lifespans of each specified area of the staircase;

[0084] Determine whether the overall lifespan of the staircase meets a pre-set expected value; if it does not meet the expected value, iterate the lifespan prediction operator through machine learning and calculate the overall lifespan of the staircase, and if it meets the expected value, output the calculated overall lifespan of the staircase to a display device.

[0085] Specifically, the process of predicting the lifespan using the lifespan prediction operator in the intelligent staircase lifespan prediction and maintenance method based on multi-sensor fusion is as Figure 4As shown, data processing is performed on the wear data set of the stairs obtained by multiple sensors, the pressure data set of each specified area of the stairs obtained by the pressure sensor, and the wear resistance coefficient and maximum wear depth corresponding to the stair material type to construct a stair life prediction operator. Then, the wear data is fitted by a Gaussian distribution, and the remaining life of the stairs is calculated by combining with the Poisson traffic model to determine whether the overall life of the stairs meets the expectations. If it does not meet the expectations, the life prediction operator is iterated through machine learning and the overall life of the stairs is calculated. If it meets the expectations, the calculated overall life of the stairs is output to the touch screen to display a heat map, transmitted to the cloud via Bluetooth, and an alarm is sent to push an emergency notification.

[0086] Exemplarily, the present application is also provided with a display device, such as a touch screen, to display a heat map in real time, including a wear gradient map obtained by multiple sensors, a usage frequency distribution calculated by the Poisson pedestrian flow model, a life curve calculated by the life prediction operator, and maintenance data and repair suggestions for the stairs calculated by the K-means clustering algorithm, such as "the central area needs to be reinforced", and supports Wi-Fi / Bluetooth transmission of data to the cloud or a mobile terminal. The wear gradient map at different positions of the stairs is as Figure 5 shown.

[0087] Furthermore, a display device is set at the stair entrance or the management terminal to display the structural health status in real time (such as a deformation heat map, crack distribution); the data is synchronized to the mobile phone of the management personnel or the cloud platform via Bluetooth / Wi-Fi. When it is detected that the safety threshold is exceeded (such as crack width, pressure anomaly), an audible and visual alarm (such as a sound generator module) is triggered, and an emergency notification is pushed through the mobile terminal.

[0088] In an exemplary embodiment, the method further includes:

[0089] Combining the wear data set of the stairs obtained by the camera device and the laser sensor, and the pressure data set of each specified area of the stairs obtained by the pressure sensor, to generate a three-dimensional health analysis model of the stairs, which is used to detect the deformation vibration of the stairs and analyze the stability of the stairs.

[0090] Exemplarily, a high-precision camera is used, combined with reflective marker points or active LED markers, to perform three-dimensional modeling on the stair surface to capture structural anomalies such as cracks and deformations. An integrated vibration sensor is used to monitor the vibration frequency of the stairs caused by use or environmental factors (such as earthquakes, wind), and analyze the structural stability.

[0091] At least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages, and these steps or stages may be executed at different times, or may be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0092] Based on the same inventive concept, an embodiment of the present application further provides an intelligent staircase life prediction and maintenance system based on multi-sensor fusion for implementing the intelligent staircase life prediction and maintenance method based on multi-sensor fusion involved above. The solution provided by this system to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the intelligent staircase life prediction and maintenance system based on multi-sensor fusion provided below can refer to the limitations on the intelligent staircase life prediction and maintenance method based on multi-sensor fusion in the above text, and will not be repeated here.

[0093] In an exemplary embodiment, an intelligent staircase life prediction and maintenance system based on multi-sensor fusion is provided, including:

[0094] An integrated laser scanning module, configured to scan the staircase using a laser sensor, generate a wear depth map, and obtain a wear data set of the staircase;

[0095] A pressure sensing module, configured to obtain a pressure data set of each specified area of the staircase based on at least one pressure sensor preset for each specified area of the staircase;

[0096] A material analysis module, configured to identify the type of staircase material using a spectral analyzer, and obtain the wear resistance coefficient and the maximum wear depth corresponding to the staircase material type;

[0097] A data processing module, configured to construct a life prediction operator based on the wear data set of the staircase, the pressure data set of each specified area of the staircase, the wear resistance coefficient and the maximum wear depth corresponding to the staircase material type, calculate the life of each specified area of the staircase through the life prediction operator, predict the overall life of the staircase according to the calculation result, and calculate the maintenance data of the staircase through the K-means clustering algorithm.

[0098] Each module in the above intelligent staircase life prediction and maintenance system based on multi-sensor fusion can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0099] In an exemplary embodiment, the intelligent staircase life prediction and maintenance method based on multi-sensor fusion is as Figure 6As shown, the integrated laser scanning module uses a high-precision laser sensor. The laser beam is emitted from the laser sensor and irradiates the surface of the stairs, and then reflects back to the laser sensor. The laser sensor calculates the distance based on the return time of the light (time of flight). This process is carried out in a grid-like manner on the surface of the stairs. The scanned point data has high precision and can effectively capture the minute wear changes on the surface of the stairs. The laser sensor ensures a comprehensive scan of all key parts of the stairs by precisely controlling the scanning angle and scanning range. Through multiple scans and data acquisitions, the intelligent staircase life prediction and maintenance system based on multi-sensor fusion can obtain a more detailed wear data set, form a three-dimensional wear map with multiple levels and angles, and further improve the accuracy of wear detection. Through the integrated laser scanning module, the wear map of the stairs can be updated in real time. When the stairs are frequently used or repaired, the system can dynamically capture these changes, promptly generate a new three-dimensional wear map, and compare it with the historical data. This dynamic monitoring ability can detect problems immediately when new wear or damage appears on the surface of the stairs and issue an early warning.

[0100] Furthermore, the pressure sensing module provides real-time feedback on the usage status of the stairs by precisely monitoring the dynamic pressure changes on the surface of the stairs. The function of the pressure sensor to record dynamic pressure can not only help judge the load-bearing capacity of the stairs, but also identify potential fatigue damage or local stress concentration, providing important data support for the life prediction and maintenance management of the stairs. The pressure sensor can detect the pressure fluctuations generated when pedestrians walk in real time. These pressure signals are converted into voltage signals through the electronic components of the sensor and further transmitted to the data processing module. By analyzing these pressure fluctuations, the system can accurately record the load changes, application time, and pressure amplitude of each step, forming a fine dynamic pressure data map.

[0101] Furthermore, the material analysis module uses spectral analysis to identify the type of material on the stair surface. Using a spectrum analyzer, typically with a wavelength range of 400nm-1000nm, this device captures the material's spectral characteristics through the interaction between light and the material. Each material exhibits distinct absorption, reflection, and transmission characteristics for different wavelengths of light. The spectrum analyzer measures these variations and infers the material's type. This process leverages characteristic data such as the material's spectral reflectance and absorption peaks to accurately determine the material type of the stair surface, such as granite, marble, or wood. Using this technology, the intelligent stair life prediction and maintenance system based on multi-sensor fusion can identify and analyze the wear characteristics, durability, and lifespan of different materials, providing personalized recommendations for stair maintenance. The material analysis module integrates laser sensors and pressure sensors to provide more comprehensive data analysis. Combining data from multiple sensors, the intelligent stair life prediction and maintenance system based on multi-sensor fusion can provide a comprehensive health report for the staircase, including analysis of wear areas, frequency of use, material fatigue, and other dimensions.

[0102] The intelligent staircase life prediction and maintenance system based on multi-sensor fusion utilizes algorithms such as the Gaussian distribution model and the Poisson flow model to assist in predicting the remaining life of the stairs. The outputs of these algorithms continuously correct the results of the life prediction operator. Using continuously updated real-time data, the system analyzes factors such as wear, fatigue accumulation, and material degradation over the long term of stair use to predict the staircase's service life and when maintenance is necessary. By estimating the remaining life of each local area of the staircase, the intelligent staircase life prediction and maintenance system based on multi-sensor fusion ultimately determines the remaining life of the entire staircase by taking the minimum of all local remaining lifespans. This approach ensures a comprehensive assessment of the staircase's health.

[0103] Specifically, the intelligent staircase life prediction and maintenance system based on multi-sensor fusion uses the K-means clustering algorithm and combines historical data (such as the number of repairs, damage conditions, and repair records) to predict future maintenance needs and perform maintenance analysis. The repair records and repair areas of each stair step will be identified and provide data support for subsequent maintenance plans. Based on life prediction analysis and maintenance data, the intelligent staircase life prediction and maintenance system based on multi-sensor fusion will provide managers with optimized maintenance recommendations. The intelligent staircase life prediction and maintenance system based on multi-sensor fusion evaluates the maintenance priority of each area by analyzing the remaining life and repair history of each area.

[0104] Exemplarily, the system uses high-precision cameras and 3D modeling technologies, such as 3DMesh technology, to combine data from multiple sensors to generate a precise 3D model of the staircase. The 3D modeling process includes a detailed scan of each key part of the staircase, processes the data in the form of point clouds, and converts it into a 3D structure diagram. In this way, the intelligent staircase life prediction and maintenance system based on multi-sensor fusion can accurately reproduce the actual appearance and structural state of the staircase, providing an important basis for subsequent structural health detection. Through the generated 3D model, the system can monitor the health status of the staircase in real time. After each scan, the system compares the new data with the historical data to identify any changes in the staircase structure (such as cracks, deformations, etc.). These changes are converted into health assessment indicators for users to analyze the current state of the staircase. The intelligent staircase life prediction and maintenance system based on multi-sensor fusion detects deformation vibrations and analyzes the stability of the staircase. When vibrations are detected, it determines whether the vibrations are normal. If they are normal, the detection continues; if not, repairs are required. It analyzes whether the stability is qualified. If it is, the staircase can continue to be used; if not, reinforcement is carried out.

[0105] Exemplarily, the data real-time feedback and alarm function is an important part of ensuring the safety and efficient management of the staircase. Through this module, the intelligent staircase life prediction and maintenance system based on multi-sensor fusion can not only monitor the health status of the staircase in real time, but also timely feedback information to the management personnel and send out alarm signals when any abnormalities are detected, so as to immediately take countermeasures. The core goal of this function is to ensure the safety of the staircase throughout its life cycle, avoid the occurrence of potential safety hazards, and reduce possible losses. The intelligent staircase life prediction and maintenance system based on multi-sensor fusion has a certain intelligent learning function. Through machine learning, it can optimize itself according to historical data and alarm situations. For example, the system can learn the common wear patterns in certain areas, identify the wear characteristics that may occur under different usage frequencies, and adjust the alarm threshold. This intelligent optimization can reduce false alarms and improve the accuracy and effectiveness of the alarm system. The system not only provides real-time feedback of alarm information, but also records and stores the detailed information of each alarm (such as alarm time, alarm type, alarm location, etc.). These alarm records are saved in the database and can be queried and analyzed later. By analyzing the historical alarm data, the management personnel can understand the long-term health status changes of the staircase, identify the areas where problems often occur, and thus take more targeted preventive measures.

[0106] The intelligent staircase life prediction and maintenance system based on multi-sensor fusion first locally stores the real-time collected staircase health data (such as wear depth, pressure distribution, material type, environmental data, etc.). This system supports synchronizing the locally stored data to the cloud platform. Through a stable network connection, the system will upload the data to the cloud regularly or in real time to ensure instant backup and remote access of the data. Cloud synchronization can not only ensure the security of the data but also provide remote monitoring and analysis functions for managers. When the staircase health data changes, the system will immediately synchronize the new data to the cloud to ensure real-time global data update. This real-time synchronization function enables managers to obtain the latest staircase status data at any time. Among them, the schematic diagram of the physical simplification of the intelligent staircase life prediction and maintenance system of the staircase in this application is as shown in Figure 7 shown.

[0107] In one embodiment, a computer device is also provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0108] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0109] For those of ordinary skill in the art, without departing from the concept of this application, several deformations and improvements can also be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application should be subject to the appended claims.

Claims

1. An intelligent staircase life prediction and maintenance method based on multi-sensor fusion, characterized in that, The method is used to predict the lifespan of a staircase and generate a maintenance plan for the staircase, including: Step S1: Scanning the staircase using a laser sensor to generate a wear depth map and obtaining a wear dataset of the staircase; Step S2: Based on at least one pressure sensor preset for each specified area of the staircase, obtaining a pressure dataset for each specified area of the staircase; Step S3: Identifying the type of staircase material using a spectral analyzer to obtain the wear resistance coefficient and maximum wear depth corresponding to the staircase material type; Step S4: Based on the wear dataset of the staircase, the pressure dataset for each specified area of the staircase, the wear resistance coefficient and maximum wear depth corresponding to the staircase material type, constructing a lifespan prediction operator, calculating the lifespan of each specified area of the staircase through the lifespan prediction operator and predicting the overall lifespan of the staircase according to the calculation results, and calculating the maintenance data of the staircase through the K-means clustering algorithm.

2. The intelligent staircase life prediction and maintenance method based on multi-sensor fusion according to claim 1, characterized in that The lifespan prediction operator in step S4 is as follows: Among them, d(x, y) is the wear depth in the wear dataset of the staircase, and d max is the maximum wear depth corresponding to the staircase material type, is the pressure dataset of each specified area of the staircase, and K is the wear resistance coefficient corresponding to the staircase material type.

3. The intelligent staircase life prediction and maintenance method based on multi-sensor fusion according to claim 2, wherein, Before constructing the lifespan prediction operator in step S4, it also includes: Establishing a wear model using a two-dimensional Gaussian distribution to fit the wear dataset, where the wear dataset includes the wear center and wear diffusion range of each specified area of the staircase; The wear dataset obtained by fitting the wear model established according to the two-dimensional Gaussian distribution is used to assist the lifespan prediction operator in predicting the overall lifespan of the staircase and assist the K-means clustering algorithm in calculating the maintenance data of the staircase.

4. The intelligent staircase life prediction and maintenance method based on multi-sensor fusion according to claim 3, characterized in that The wear model established using a two-dimensional Gaussian distribution in step S4 is as follows: Among them, W(x, y) is the result obtained by fitting the wear model, where x and y are the coordinates of each sampling point in the specified area of the staircase, and μ x , μ y are the wear centers of each specified area of the staircase, and σ x , σ y are the wear diffusion ranges of each specified area of the staircase.

5. A method for predicting the lifespan and maintaining an intelligent staircase based on multi-sensor fusion according to claim 4, characterized in that, Before constructing the lifespan prediction operator in step S4, it also includes: Obtaining the pedestrian flow data according to the pressure sensor, calculating the relationship formula between the pedestrian flow and wear using the Poisson distribution, and analyzing the relationship formula between the usage frequency of the staircase and wear using the power-law model; Based on the relationship formula between the pedestrian flow and wear and the relationship formula between the usage frequency of the staircase and wear, assisting the lifespan prediction operator in predicting the overall lifespan of the staircase and assisting the K-means clustering algorithm in calculating the maintenance data of the staircase.

6. The intelligent staircase life prediction and maintenance method based on multi-sensor fusion according to claim 1, wherein, In step S4, calculating the lifespan of each specified area of the staircase through the lifespan prediction operator and predicting the overall lifespan of the staircase according to the calculation results includes: Calculating the overall lifespan of the staircase through the minimum value of the lifespan of each specified area of the staircase; Judging whether the overall lifespan of the staircase meets a preset expected value; if it does not meet the expected value, iterating the lifespan prediction operator through machine learning and calculating the overall lifespan of the staircase, and if it meets the expected value, outputting the calculated overall lifespan of the staircase to a display device.

7. A method for predicting the lifespan and maintaining an intelligent staircase based on multi-sensor fusion according to claim 1, characterized in that The method also includes: Combining the wear dataset of the staircase obtained by the camera device and the laser sensor and the pressure dataset of each specified area of the staircase obtained by the pressure sensor to generate a three-dimensional health analysis model of the staircase, and the three-dimensional health analysis model is used to detect the deformation and vibration of the staircase and analyze the stability of the staircase.

8. An intelligent staircase life prediction and maintenance system based on multi-sensor fusion, characterized in that, The system includes: An integrated laser scanning module for scanning the staircase using a laser sensor to generate a wear depth map and obtaining a wear dataset of the staircase; A pressure sensing module for obtaining a pressure dataset for each specified area of the staircase based on at least one pressure sensor preset for each specified area of the staircase; A material analysis module, which is used to identify the type of staircase material by using a spectral analyzer, and obtain the wear resistance coefficient and the maximum wear depth corresponding to the staircase material type; A data processing module, which is used to construct a life prediction operator based on the wear data set of the staircase, the pressure data set of each specified area of the staircase, the wear resistance coefficient and the maximum wear depth corresponding to the staircase material type, calculate the life of each specified area of the staircase through the life prediction operator, predict the overall life of the staircase according to the calculation results, and calculate the maintenance data of the staircase through the K-means clustering algorithm.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images