Safety detection system and method for outer frame crawling ladder

Abstract

The invention provides an outer frame crawling ladder safety detection system and method, and belongs to the technical field of steel crawling frames, the outer frame crawling ladder safety detection system comprises a collection layer, a detection layer, an evaluation layer, a monitoring layer, an early warning layer and an outer frame, the collection layer collects related data of an outer frame crawling ladder by using collection equipment, the detection layer simplifies the collected data by using a dimension reduction technology, and the evaluation layer is used for evaluating the safety of the outer frame crawling ladder. The data acquisition layer is used for acquiring spectral data of the outer frame ladder stand and establishing different models for the simplified data, the evaluation layer is used for applying the detected data to the spectral data of the outer frame ladder stand, performing safety prediction, performing evaluation according to a prediction result and monitoring the outer frame ladder stand, and the monitoring layer is used for transmitting the detected data to a cloud end in real time by utilizing an Internet of Things technology. And the early warning layer is used for carrying out early warning prompt on the safety state of the crawling ladder after the safety state of the crawling ladder is detected. The problems that an existing safety monitoring technology can only monitor a construction site, certain potential safety hazards exist in the using process of the outer frame ladder stand, and real-time monitoring and safety detection are not conducted on the outer frame ladder stand are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of steel climbing frames, and in particular, relates to a safety detection system and method for an external frame ladder. Background Art

[0002] In modern construction, external ladders are a common vertical transportation tool, widely used in the construction, maintenance, cleaning and other operations of high-rise buildings. External ladders are usually composed of ladder sections, handrails, cross braces, vertical poles and other components. They are fixed to the outer wall of the building through connectors to provide construction workers with a passage for going up and down.

[0003] Various safety monitoring technologies have been widely used in modern construction to effectively monitor the safety of construction sites. By installing cameras at the construction site and transmitting video signals to the monitoring center, the safety of the construction site can be monitored in real time. The staff of the monitoring center can observe the construction site through the monitor and take timely measures to intervene if safety hazards are found.

[0004] However, the above existing safety monitoring technology can only monitor the construction site, and there are certain safety hazards in the use of external frame ladders, such as loose fixation of the ladder, wear and corrosion of parts, etc. Therefore, it is necessary to perform real-time monitoring and safety detection of external frame ladders. To this end, a safety detection system and method for external frame ladders are designed. Summary of the invention

[0005] The embodiments of the present invention provide a system and method for detecting the safety of an external frame ladder, which solves the problem that the existing safety monitoring technology can only monitor the construction site, while the external frame ladder has certain safety hazards during use, such as the ladder is not firmly fixed, parts are worn and rusted, and there is no real-time monitoring and safety detection of the external frame ladder.

[0006] In view of the above problems, the technical solution proposed by the present invention is:

[0007] The present invention provides an external frame ladder safety detection system, comprising a collection layer, a detection layer, an evaluation layer, a monitoring layer, an early warning layer and an external frame;

[0008] The acquisition layer uses acquisition equipment to collect relevant data of the external frame ladder and collects the collected data;

[0009] The detection layer uses dimensionality reduction technology to simplify the collected data and establishes different models for the simplified data;

[0010] The evaluation layer is used to apply the detected data to the spectral data of the external frame ladder to make a safety prediction, and to evaluate and monitor the external frame ladder based on the prediction results;

[0011] The monitoring layer uses the Internet of Things technology to transmit the detected data to the cloud in real time, and uses big data analysis to provide data support for the safety detection of external ladders;

[0012] The early warning layer is used to give an early warning of the safety status of the ladder after detecting the safety status of the ladder;

[0013] The outer frame includes an outer frame steel pipe, a ladder and a steel welded pipe. The ladder is arranged at the corner of the outer frame steel pipe. The steel welded pipe is arranged between the ladder and the outer frame steel pipe and welded to the ladder and the outer frame steel pipe. The ladder includes a main keel and an angle steel keel.

[0014] As a preferred technical solution of the present invention, the main keel 2012 adopts square steel with a model of 60*40*2.5mm, the spacing between the main keels 2012 is 600mm, the angle steel keel 2023 is L40*3mm angle steel, and the vertical distance is 200mm. The two ends of the ladder 202 adopt the steel bar welded pipe 203 and the external frame steel pipe 201 double-sided welding, and the weld is 60mm. The ladder 202 is arranged at the corner position of the external frame steel pipe 201, with 4 runs on each side.

[0015] As a preferred technical solution of the present invention, the acquisition layer includes a near-infrared spectrum scanning module, a sensor group and a multi-source data fusion module;

[0016] The near-infrared spectrum scanning module selects the material of the external frame ladder as a sample, and uses a near-infrared spectrometer to scan the samples at different parts of the external frame ladder to collect spectrum data;

[0017] The sensor group is used to set monitoring points at key parts of the ladder, and sensors are installed at the monitoring points to collect the operating status and stress conditions of the external frame ladder;

[0018] The multi-source data fusion module is used to integrate the data from the near-infrared spectrum scanning module and the sensor group.

[0019] As a preferred technical solution of the present invention, the detection layer includes a principal component analysis module, a relationship model building module and a classification model building module;

[0020] The principal component analysis module is used to extract the main components of the data in the near infrared spectrum scanning module, and use the score graph and load graph of the principal component analysis module to identify abnormal values ​​in the data;

[0021] The relationship model building module uses partial least squares method to associate the data of the near infrared spectrum scanning module to build a model;

[0022] The classification model building module uses the principal components of the model built by the relationship model building module as input features of the classification model, and uses the random forest algorithm to build the classification model to distinguish between safe and unsafe external frame ladder samples.

[0023] As a preferred technical solution of the present invention, the detailed steps of the relationship model building module are as follows:

[0024] Step A, using the principal component number analyzed by the principal component analysis module, multiplying the principal component number by the regression coefficient matrix of the response variable to obtain the regression coefficient matrix;

[0025] Step B, multiply the regression coefficient matrix by the eigenvector matrix to obtain the coefficient matrix of the predicted variables.

[0026] As a preferred technical solution of the present invention, the detailed steps of the classification model building module are as follows:

[0027] Step a, taking the principal components extracted by the partial least squares model as the input features of the model;

[0028] Step b, at each node, according to the feature set after feature sampling, select the best split point to divide the data set into two subsets and construct a decision tree;

[0029] Step c, repeating the process of step b for the subset until a preset stop condition is reached;

[0030] In step d, the data set is divided into a training set and a test set, each decision tree is used to predict the test set, and the mode or mean of each prediction result is calculated as the final prediction result.

[0031] As a preferred technical solution of the present invention, the evaluation layer includes a model application module, a result analysis module and a real-time monitoring module;

[0032] The model application module is used to apply the established partial least squares model and random forest algorithm model to the spectral data of the external frame ladder to predict the safety index of the external frame ladder;

[0033] The result analysis module evaluates the safety of the external ladder based on the results predicted by the model in the detection layer;

[0034] The real-time monitoring module installs a near-infrared spectroscopy device near the external frame ladder to perform real-time monitoring of the external frame ladder.

[0035] As a preferred technical solution of the present invention, the monitoring layer includes an Internet of Things cloud platform and a big data analysis module;

[0036] The IoT cloud platform uses IoT technology to remotely transmit, store and monitor detection data;

[0037] The big data analysis module uses big data analysis technology, combines historical safety accident data and real-time monitoring data, and uses algorithms to establish a risk assessment model to provide data support for the safety management of external scaffolding ladders.

[0038] On the other hand, a method for detecting the safety of an external ladder comprises the following steps:

[0039] S1, using several external frame steel pipes to build a frame, setting the width and height of the ladder according to the needs, welding the main keel and the angle steel keel to form a ladder, and welding the two ends of the assembled ladder to the corners of the external frame using steel welded pipes;

[0040] S2, a near infrared spectrometer is set up near the ground at the external frame to collect near infrared spectrum data of the external frame ladder, and sensors are used to collect data related to ladder safety according to the designed monitoring points, and the collected data are pre-processed;

[0041] S3, use principal component analysis to reduce the dimension of near-infrared spectral data, extract the main components reflecting the material characteristics of the external frame ladder, and combine with sensor data to perform feature-level fusion;

[0042] S4, using partial least squares method to establish the relationship model between spectral data and sensor data, and using random forest algorithm to classify and analyze the safety of external ladder;

[0043] S5, combined with the Internet of Things technology, uses near-infrared spectroscopy and sensors to collect real-time data on the working status of the external rack ladder, and uses the random forest model to analyze the real-time data;

[0044] S6, judging the safety status of the external frame ladder, setting a threshold using the early warning module, and issuing an early warning when the real-time data exceeds the threshold;

[0045] S7, through the IoT cloud platform, remotely transmits monitoring data to the terminal for monitoring, and uses big data analysis technology, combined with historical data and real-time monitoring data, to establish a risk assessment model through an algorithm to analyze the safety of external scaffolding ladders.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] Compared with the traditional method of using BIM model for safety detection, the present invention uses near-infrared spectroscopy technology combined with partial least squares method, random forest and principal component analysis method. Near-infrared spectroscopy technology can obtain spectral information of materials in real time, partial least squares method and random forest can process multivariate data, and principal component analysis can be combined to reduce data dimension and extract key features, so as to obtain higher prediction accuracy and robustness. In addition, near-infrared spectroscopy technology does not destroy samples, is suitable for on-site detection, and can be suitable for real-time monitoring.

[0048] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a block diagram of an external frame ladder safety detection system disclosed in the present invention;

[0050] Figure 2 It is a schematic diagram of a method flow of an external frame ladder safety detection system disclosed in the present invention;

[0051] Figure 3 It is a structural schematic diagram of an external frame ladder safety detection system disclosed in the present invention;

[0052] Figure 4 It is a partial structural schematic diagram of an external frame ladder safety detection system disclosed in the present invention;

[0053] Explanation of the accompanying drawings: 101, acquisition layer; 1011, near-infrared spectrum scanning module; 1012, sensor group; 1013, multi-source data fusion module; 102, detection layer; 1021, principal component analysis module; 1022, relationship model building module; 1023, classification model building module; 103, evaluation layer; 1031, model application module; 1032, result analysis module; 1033, real-time monitoring module; 104, monitoring layer; 1041, Internet of Things cloud platform; 1042, big data analysis module; 105, early warning layer; 200, external frame; 201, external frame steel pipe; 202, ladder; 2021, main keel; 2022, angle steel keel; 203, steel bar welded pipe; 300, near-infrared spectrometer; 400, monitoring point. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0057] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0058] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0059] Embodiment 1

[0060] Refer to the attached Figure 1 As shown, the present invention provides a technical solution: an external frame ladder safety detection system, including a collection layer 101, a detection layer 102, an evaluation layer 103, a monitoring layer 104, an early warning layer 105 and an external frame 200;

[0061] The collection layer 101 uses collection equipment to collect relevant data of the external frame ladder and collects the collected data;

[0062] The detection layer 102 uses dimensionality reduction technology to simplify the collected data and builds different models for the simplified data;

[0063] The evaluation layer 103 is used to apply the detected data to the spectral data of the external frame ladder, make safety predictions, and make evaluations based on the prediction results to monitor the external frame ladder;

[0064] The monitoring layer 104 uses the Internet of Things technology to transmit the detected data to the cloud in real time, and uses big data analysis to provide data support for the safety detection of the external ladder;

[0065] The early warning layer 105 is used to give an early warning of the safety status of the ladder after detecting the safety status of the ladder;

[0066] The outer frame 200 includes an outer frame steel pipe 201, a ladder 202 and a steel welded pipe 203. The ladder 202 is arranged at the corner of the outer frame steel pipe 201. The steel welded pipe 203 is arranged between the ladder 202 and the outer frame steel pipe 201 and welded to the ladder 202 and the outer frame steel pipe 201. The ladder 202 includes a main keel 2012 and an angle steel keel 2023.

[0067] The embodiment of the present invention is also implemented through the following technical solutions.

[0068] In an embodiment of the present invention, the main keel 2012 adopts square steel with a model of 60*40*2.5mm, the spacing between the main keels 2012 is 600mm, the angle steel keel 2023 is L40*3mm angle steel, the vertical distance is 200mm, and the two ends of the ladder 202 adopt steel welded pipe 203 and external frame steel pipe 201 double-sided welding, the weld seam is 60mm, and the ladder 202 is arranged at the corner position of the external frame steel pipe 201, with 4 runs on each side.

[0069] In the embodiment of the present invention, the acquisition layer 101 includes a near infrared spectrum scanning module 1011, a sensor group 1012 and a multi-source data fusion module 1013;

[0070] The near infrared spectrum scanning module 1011 selects the material of the external frame ladder as a sample, and uses the near infrared spectrometer 300 to scan the samples at different parts of the external frame ladder to collect spectrum data;

[0071] The sensor group 1012 is used to set monitoring points 400 at key positions of the ladder, and install sensors on the monitoring points 400 to collect the operating status and stress conditions of the external frame ladder, including strain gauge sensors used to measure the strain of structural components, thereby inferring the stress conditions; displacement sensors monitor the displacement changes of the structure and are used to detect the stability of the structure; acceleration sensors measure the vibration frequency and amplitude of the structure and evaluate the dynamic response of the structure; temperature sensors monitor the changes in ambient temperature, especially the impact on the safety of the structure under extreme weather conditions; load sensors are used to measure the load size borne by the structure and can determine whether the structure is overloaded; crack sensors are used to monitor the width and development of cracks on the surface of the structure and evaluate the integrity of the structure;

[0072] The multi-source data fusion module 1013 is used to integrate the data from the near-infrared spectrum scanning module 1011 and the sensor group 1012, and perform feature extraction through PCA to reduce the data dimension and improve data processing efficiency.

[0073] In the embodiment of the present invention, the detection layer 102 includes a principal component analysis module 1021, a relationship model building module 1022 and a classification model building module 1023;

[0074] The principal component analysis module 1021 is used to extract the main components of the data in the near infrared spectrum scanning module 1011, reduce the data dimension, and use the score graph and load graph of the principal component analysis module 1021 to identify abnormal values ​​in the data, which may indicate the inhomogeneity or damage of the material, and intuitively show the direct differences of the samples;

[0075] The relationship model building module 1022 uses the partial least squares method to associate the data of the near infrared spectrum scanning module 1011 to build a model;

[0076] The classification model building module 1023 uses the principal components of the model built by the relationship model building module 1022 as input features of the classification model, and uses the random forest algorithm to build the classification model to distinguish between safe and unsafe external frame ladder samples.

[0077] In the embodiment of the present invention, the detailed steps of the relationship model building module 1022 are as follows:

[0078] Step A, standardize the data to zero mean and unit variance to eliminate the dimensional differences between variables, perform singular value decomposition on the standardized data matrix to obtain an eigenvector matrix, a singular value matrix and a transposed matrix of the singular value matrix, use the principal component number analyzed by the principal component analysis module 1021, multiply the principal component number by the regression coefficient matrix of the response variable to obtain a regression coefficient matrix;

[0079] Step B, multiplying the regression coefficient matrix by the eigenvector matrix to obtain a coefficient matrix of the predicted variables, each element in the regression coefficient matrix corresponds to a specific wavelength or spectral region in the original spectral data matrix, and is explained by the partial least squares model. Each element in the regression coefficient matrix (i.e., the coefficient of each wavelength or spectral region) is used to predict the value of the response variable (such as the chemical composition or physical property of the material), thereby predicting and evaluating the safety of the external frame ladder material based on the near-infrared spectral scanning data;

[0080] In the embodiment of the present invention, the detailed steps of the classification model building module 1023 are as follows:

[0081] Step a, using the principal components extracted by the partial least squares model as the input features of the model, and using the random forest algorithm to train the classification model to distinguish between safe and unsafe external ladder climbing samples;

[0082] Step b, at each node, according to the feature set after feature sampling, select the best split point to divide the data set into two subsets, build a decision tree, repeat N times, build multiple decision trees, and by integrating multiple decision trees, random forest can reduce the randomness and overfitting of individual decision trees;

[0083] Step c, repeating the process of step b for the subset until a preset stop condition is reached (such as the subset size is less than a threshold);

[0084] Step d, the data set is divided into a training set and a test set, each decision tree is used to predict the test set, and which features have the greatest impact on the prediction results are evaluated to obtain the safety status classification of the external frame ladder, and the mode or average of each prediction result is calculated as the final prediction result;

[0085] In addition, the detection layer 102 also includes a model established by combining the relationship model establishment module 1022 and the classification model establishment module 1023 to establish a joint prediction model, use the training set to establish a partial least squares model, use the test set to verify the prediction ability of the model, use the test set to evaluate the prediction accuracy of the models in the relationship model establishment module 1022 and the classification model establishment module 1023, use the established model to predict the test set data, and obtain the safety status classification of the external frame ladder.

[0086] In the embodiment of the present invention, the evaluation layer 103 includes a model application module 1031, a result analysis module 1032 and a real-time monitoring module 1033;

[0087] The model application module 1031 is used to apply the established partial least squares model and random forest algorithm model to the spectral data of the external frame ladder, predict the safety index of the external frame ladder, set the threshold value according to the prediction result and the safety standard, and judge the safety of the sample;

[0088] The result analysis module 1032 evaluates the safety of the external ladder based on the results predicted by the model in the detection layer 102. If the predicted value exceeds the preset safety threshold, it indicates that there may be a safety hazard.

[0089] The real-time monitoring module 1033 installs a near-infrared spectroscopy device near the external frame ladder to perform real-time monitoring of the external frame ladder and promptly discover potential safety issues.

[0090] In an embodiment of the present invention, the monitoring layer 104 includes an IoT cloud platform 1041 and a big data analysis module 1042;

[0091] The IoT cloud platform 1041 uses IoT technology to remotely transmit, store and monitor detection data. Through the IoT platform, remote transmission and monitoring of monitoring data are realized, and monitoring data is stored in the cloud for easy access and management by multiple terminals;

[0092] The big data analysis module 1042 uses big data analysis technology, combines historical safety accident data and real-time monitoring data, and uses algorithms to establish a risk assessment model to provide data support for the safety management of external scaffolding ladders.

[0093] Embodiment 2

[0094] See attached Figure 2 As shown, an embodiment of the present invention further provides a method for detecting the safety of an external frame ladder, comprising the following steps:

[0095] S1, use a number of external frame steel pipes 201 to build a frame, set the width and height of the ladder 202 according to the requirements, weld the main keel 2012 and the angle steel keel 2023 to form a ladder, and weld the two ends of the assembled ladder 202 to the corners of the external frame 200 using steel welded pipes 203 to complete the installation of the ladder;

[0096] S2, a near infrared spectrometer 300 is set near the ground at the external frame to collect near infrared spectrum data of the external frame ladder, including chemical composition and structural information of the material, and sensors are used to collect data related to ladder safety according to the designed monitoring points 400, and the collected data is pre-processed, including denoising, normalization and outlier processing;

[0097] S3, use principal component analysis to reduce the dimension of near-infrared spectral data, extract the main components reflecting the material characteristics of the external frame ladder, select the first few principal components according to the cumulative variance contribution rate, these principal components can reflect the key characteristics of the external frame ladder, combine with sensor data, and perform multi-source data fusion to obtain a more comprehensive feature representation;

[0098] S4, using partial least squares method to establish a relationship model between spectral data and sensor data, that is, to associate spectral data with known safety indicators (such as mechanical properties of materials), so as to understand how different factors affect the safety of ladders, and use the principal components of the relationship model as input features of the random forest algorithm to perform classification and / or regression analysis on the safety of external ladders. The random forest algorithm can handle nonlinear relationships and high-dimensional data and provide variable importance assessment;

[0099] Among them, the classification analysis of the external ladder in step S4 is to calculate the predicted category of all decision trees for each test sample, and then select the category with the largest number of occurrences as the final prediction result;

[0100] Regression analysis is to calculate the predicted values ​​of all decision trees for each test sample, and then calculate the average of these values ​​as the final prediction result;

[0101] Through these two methods, the random forest algorithm can improve the accuracy and robustness of predictions. The prediction results of multiple decision trees can complement each other. The final prediction result is a combination of the prediction results of multiple decision trees, which more accurately reflects the actual situation of the test samples.

[0102] S5, combined with the Internet of Things technology, uses near-infrared spectroscopy and sensors to collect real-time working status data of the external frame ladder, such as temperature, humidity, vibration, etc., and uses the random forest model to analyze the real-time data;

[0103] S6, judging the safety status of the external frame ladder, setting a threshold using the early warning module 105, issuing an early warning when the real-time data exceeds the threshold, and proposing corresponding maintenance or repair suggestions to optimize the safety management of the ladder;

[0104] S7, through the IoT cloud platform 1041, remotely transmits the monitoring data to the terminal for monitoring, and uses big data analysis technology, combined with historical data and real-time monitoring data, to establish a risk assessment model through an algorithm to analyze the safety of the external scaffolding ladder and predict potential safety risks.

[0105] The detailed steps of multi-source data fusion in step S2 are as follows:

[0106] Step S21, performing conventional preprocessing on the data collected by the near infrared spectrum scanning module 1011 and the sensor group 1012;

[0107] Step S22, identifying associations between different data sources, such as timestamp matching, geographic location association, keyword matching, etc., and matching and associating different data sources based on the associations;

[0108] Step S23, using a fusion algorithm to perform data fusion, such as feature-level fusion, decision-level fusion, etc.;

[0109] The detailed steps of risk assessment using big data analysis technology in step S6 are as follows:

[0110] S61, extracting historical data and real-time status data of the external rack ladder relevance in the IoT cloud platform 1041, and performing conventional preprocessing on the data;

[0111] S62, use statistical methods to find patterns and associations in data, and display them in the form of graphs to facilitate understanding of the relationships between data;

[0112] S63, select a suitable machine learning algorithm, such as a decision tree, a neural network, etc., use the model for training, and perform data prediction based on the results of the model training.

[0113] Considering that the goal of this application is to monitor the safety status of the external scaffolding ladder in real time, it is more appropriate to use near-infrared spectroscopy technology combined with partial least squares method, random forest and principal component analysis method. If it is necessary to comprehensively manage the entire life cycle of the construction project, including design, construction, operation and maintenance, then the data collected by the sensor can be combined with BIM for monitoring. In practical applications, the two technologies can complement each other and jointly improve the safety and efficiency of construction projects.

[0114] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0115] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0116] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0117] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. An external ladder safety detection system, characterized in that: It includes a collection layer (101), a detection layer (102), an evaluation layer (103), a monitoring layer (104), an early warning layer (105) and an external frame (200); The acquisition layer (101) uses acquisition equipment to collect relevant data of the external frame ladder and collects the collected data; The detection layer (102) uses dimensionality reduction technology to simplify the collected data, and establishes different models for the simplified data; The evaluation layer (103) is used to apply the detected data to the spectral data of the external frame ladder to make a safety prediction, and to make an evaluation based on the prediction result to monitor the external frame ladder; The monitoring layer (104) uses the Internet of Things technology to transmit the detected data to the cloud in real time, and uses big data analysis to provide data support for the safety detection of the external ladder; The early warning layer (105) is used to provide an early warning prompt of the safety status of the ladder after detecting the safety status of the ladder; The external frame (200) comprises an external frame steel pipe (201), a ladder (202) and a steel welded pipe (203); the ladder (202) is arranged at a corner of the external frame steel pipe (201); the steel welded pipe (203) is arranged between the ladder (202) and the external frame steel pipe (201) and is welded to the ladder (202) and the external frame steel pipe (201); the ladder (202) comprises a main keel (2012) and an angle steel keel (2023).

2. The external ladder safety detection system according to claim 1 is characterized in that: The main keel (2012) is made of square steel with a model of 60*40*2.5mm, the spacing between the main keels (2012) is 600mm, the angle steel keel (2023) is an angle steel with a size of L40*3mm, and the vertical distance is 200mm. The two ends of the ladder (202) are double-sided welded with the steel bar welded pipe (203) and the external frame steel pipe (201), and the weld seam is 60mm. The ladder (202) is arranged at the corner position of the external frame steel pipe (201), with 4 runs on each side.

3. The external ladder safety detection system according to claim 2 is characterized in that: The acquisition layer (101) comprises a near-infrared spectrum scanning module (1011), a sensor group (1012) and a multi-source data fusion module (1013); The near-infrared spectrum scanning module (1011) selects the material of the external frame ladder as a sample, and uses a near-infrared spectrometer (300) to scan the samples at different positions of the external frame ladder to collect spectrum data; The sensor group (1012) is used to set monitoring points (400) at key positions of the ladder, and to install sensors at the monitoring points (400) to collect the operating status and stress conditions of the external frame ladder; The multi-source data fusion module (1013) is used to integrate the data from the near-infrared spectrum scanning module (1011) and the sensor group (1012).

4. The external ladder safety detection system according to claim 3 is characterized in that: The detection layer (102) includes a principal component analysis module (1021), a relationship model establishment module (1022) and a classification model establishment module (1023); The principal component analysis module (1021) is used to extract the main components of the data in the near-infrared spectrum scanning module (1011), and to identify abnormal values ​​in the data using the score graph and the load graph of the principal component analysis module (1021); The relationship model building module (1022) uses the partial least squares method to associate the data of the near-infrared spectrum scanning module (1011) to build a model; The classification model building module (1023) uses the principal components of the model built by the relationship model building module (1022) as input features of the classification model, and uses the random forest algorithm to build the classification model to distinguish between safe and unsafe external frame ladder samples.

5. The external ladder safety detection system according to claim 4 is characterized in that: The detailed steps of the relationship model building module (1022) are as follows: Step A, using the number of principal components analyzed by the principal component analysis module (1021), multiplying the number of principal components by the regression coefficient matrix of the response variable to obtain a regression coefficient matrix; Step B, multiply the regression coefficient matrix by the eigenvector matrix to obtain the coefficient matrix of the predicted variables.

6. The external ladder safety detection system according to claim 5, characterized in that: The detailed steps of the classification model building module (1023) are as follows: Step a, taking the principal components extracted by the partial least squares model as the input features of the model; Step b, at each node, according to the feature set after feature sampling, select the best split point to divide the data set into two subsets and construct a decision tree; Step c, repeating the process of step b for the subset until a preset stop condition is reached; In step d, the data set is divided into a training set and a test set, each decision tree is used to predict the test set, and the mode or mean of each prediction result is calculated as the final prediction result.

7. The external ladder safety detection system according to claim 6 is characterized in that: The evaluation layer (103) includes a model application module (1031), a result analysis module (1032) and a real-time monitoring module (1033); The model application module (1031) is used to apply the established partial least squares model and random forest algorithm model to the spectral data of the external frame ladder to predict the safety index of the external frame ladder; The result analysis module (1032) evaluates the safety of the external ladder based on the results predicted by the model in the detection layer (102); The real-time monitoring module (1033) installs a near-infrared spectroscopy device near the external frame ladder to perform real-time monitoring of the external frame ladder.

8. The external ladder safety detection system according to claim 7, characterized in that: The monitoring layer (104) includes an Internet of Things cloud platform (1041) and a big data analysis module (1042); The Internet of Things cloud platform (1041) uses Internet of Things technology to remotely transmit, store and monitor detection data; The big data analysis module (1042) uses big data analysis technology, combines historical safety accident data and real-time monitoring data, and uses algorithms to establish a risk assessment model to provide data support for the safety management of external frame ladders.

9. A method for using an external frame ladder safety detection system, applied to an external frame ladder safety detection system according to any one of claims 1 to 8, characterized in that: The following steps are involved: S1, using a plurality of external frame steel pipes (201) to build a frame, setting the width and height of the ladder (202) according to requirements, welding the main keel (2012) and the angle steel keel (2023) to form a ladder, and welding the two ends of the assembled ladder (202) to the corners of the external frame (200) using steel welded pipes (203); S2, a near infrared spectrometer (300) is arranged near the ground at the external frame to collect near infrared spectrum data of the external frame ladder, and data related to ladder safety is collected using sensors according to the designed monitoring points (400), and the collected data is pre-processed; S3, use principal component analysis to reduce the dimension of near-infrared spectral data, extract the main components reflecting the material characteristics of the external frame ladder, and combine with sensor data to perform feature-level fusion; S4, using partial least squares method to establish the relationship model between spectral data and sensor data, and using random forest algorithm to classify and analyze the safety of external ladder; S5, combined with the Internet of Things technology, uses near-infrared spectroscopy and sensors to collect real-time data on the working status of the external rack ladder, and uses the random forest model to analyze the real-time data; S6, judging the safety status of the external frame ladder, setting a threshold using the early warning module (105), and issuing an early warning when the real-time data exceeds the threshold; Through the Internet of Things cloud platform (1041), the monitoring data is remotely transmitted to the terminal for monitoring, and big data analysis technology is used to combine historical data and real-time monitoring data, and a risk assessment model is established through an algorithm to analyze the safety of the external scaffolding ladder.

Images