A method and system for detecting the structural strength of a PVC guardrail

Abstract

The present invention provides a method and system for detecting the structural strength of a PVC guardrail, which relates to the technical field of detecting the physical properties of materials. The system architecture includes a data acquisition unit for collecting data, a data processing unit for processing data, a management database unit, a system feedback and summary unit, a detection work unit for detecting the strength of the PVC guardrail, and a system calibration and maintenance unit; the detection work unit includes a detection category selection module, a temperature and humidity control module, and a detection process recording module, and the detection category selection module includes impact strength detection, compressive strength detection, and bending strength detection. By setting up the detection work unit, the impact strength detection, compressive strength detection, and bending strength detection can be effectively integrated, and specific adjustments can be made when implementing specific detection items, which is beneficial to improving the convenience and efficiency of detecting the structural strength of the PVC guardrail.

Description

Technical Field

[0001] The present invention relates to the technical field of material physical property detection, and specifically to a method and system for detecting the structural strength of a PVC guardrail. Background Art

[0002] In the fields of modern architecture, road safety protection, and garden landscapes, PVC guardrails have been widely used due to their advantages such as corrosion resistance, beauty, and easy installation. The structural strength of PVC guardrails is directly related to their safety and reliability in actual use. If the strength is insufficient, it may be damaged when subjected to external force impacts, heavy pressure, or long-term environmental effects, and thus fail to play its due protective role, leading to safety accidents.

[0003] Currently, there are many deficiencies in the detection of the structural strength of PVC guardrails. For example, when detecting different types of structural strengths of PVC guardrails (impact resistance structural strength detection, compressive strength detection, and bending resistance structural strength detection), multiple detection systems are required, resulting in a relatively cumbersome detection process. At the same time, when analyzing the detected data, manual comparison and analysis are mainly used, which leads to low efficiency in data analysis. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] Aiming at the deficiencies of the prior art, the present invention provides a method and system for detecting the structural strength of a PVC guardrail, which solves the problems that there are many deficiencies in the current detection of the structural strength of PVC guardrails. For example, when detecting different types of structural strengths of PVC guardrails (impact resistance structural strength detection, compressive strength detection, and bending resistance structural strength detection), multiple detection systems are required, resulting in a relatively cumbersome detection process. At the same time, when analyzing the detected data, manual comparison and analysis are mainly used, which leads to low efficiency in data analysis.

[0006] (II) Technical Solutions

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions: A system for detecting the structural strength of a PVC guardrail includes a data acquisition unit for collecting data, a data processing unit for processing data, a management database unit, a system feedback and summary unit, a detection work unit for detecting the strength of the PVC guardrail, and a system calibration and maintenance unit.

[0008] The detection work unit includes a detection category selection module, a temperature and humidity control module for regulating the temperature and humidity during the detection of the strength of the PVC guardrail, and a detection process recording module.

[0009] Further, the detection category selection module includes impact strength detection, compressive strength detection, and flexural strength detection. Among them, the impact strength detection includes pendulum impact test and drop hammer impact test;

[0010] The pendulum impact test can be carried out in a simply supported beam or cantilever beam type. Install the PVC guardrail specimen on the impact machine according to the standard requirements, and let the pendulum fall freely to strike the specimen. Then, in the simply supported beam impact test, the pendulum strikes the center of the simply supported beam test; for the cantilever beam, the pendulum strikes the free end of the notched cantilever beam, and record the impact energy consumed per unit area or unit width when the specimen breaks, so as to determine its impact strength;

[0011] In the drop hammer impact test, a ball or hammer of a certain mass is freely dropped from a specific height to impact the PVC guardrail specimen. Then, observe the damage condition of the guardrail, such as whether there are cracks or fractures, and at the same time record the impact energy or height that can cause a specific damage degree to the guardrail, and then evaluate its impact strength based on this.

[0012] Further, the compressive strength detection is to use a pressure testing machine. Place the PVC guardrail specimen on the working table of the testing machine, and apply a uniform axial pressure to the specimen through the indenter of the testing machine. Gradually increase the pressure until the specimen deforms and breaks, resulting in the failure phenomenon of the PVC guardrail. Then record the pressure value at this time to obtain the compressive strength of the PVC guardrail.

[0013] Further, the flexural strength detection is to place the PVC guardrail specimen on two supports, apply a load perpendicular to the specimen at the middle position of the specimen, so as to cause the specimen to produce bending deformation. Then measure the bending deflection under the specified load or the bending load under the specified deflection, and thus calculate the flexural strength of the PVC guardrail.

[0014] Further, the data processing unit includes a data preprocessing module, a data intelligent processing module, and a data filtering and conversion module. The data preprocessing module is mainly used to clean the collected data to remove interference data. The data intelligent processing module is mainly used to perform intelligent analysis and processing on the collected data. The data filtering and conversion module filters, amplifies, and performs analog-to-digital conversion on the collected data, and then transmits it to the next stage for processing.

[0015] Further, the database management unit includes a historical data comparison module, a data classification storage module, and a data monitoring module. The historical data comparison module compares and analyzes the collected data with the historical data stored in the database. The data classification storage module is mainly used to classify and store the data to be stored according to categories. The data monitoring module is mainly used to scan and monitor the data stored in the database.

[0016] Furthermore, the calibration and maintenance unit needs to regularly calibrate hardware devices such as the loading device and sensors to ensure the accuracy of the detection data. The calibration process records the calibration results according to relevant standards. If it is found that the device error exceeds the allowable range, adjustments or repairs can be made in a timely manner. At the same time, a daily maintenance plan for the system is formulated, including equipment cleaning, checking whether the connections of each component are loose, and software system updates. Subsequently, the data storage device is backed up regularly to prevent data loss.

[0017] Furthermore, the system feedback and summary unit automatically generates a detailed test report according to the analysis results of the software system. The report clearly shows various performance parameters of the guardrail, the conclusion of whether it is qualified, and relevant analysis charts. At the same time, the data after analysis is evaluated, and combined with historical data to judge the aspects where the structural strength of the PVC guardrail needs to be improved.

[0018] A method for detecting the structural strength of a PVC guardrail includes the following detection steps:

[0019] Step 1: Detection preparation. Select the corresponding detection equipment according to the selected detection category. For example, when conducting a compressive strength test on a PVC guardrail, a pressure testing machine needs to be prepared; when conducting an impact resistance test on a PVC guardrail, a pendulum hammer or a drop hammer needs to be prepared to conduct an impact test on the PVC guardrail.

[0020] Step 2: Start detection. Detect the structural strength of the PVC guardrail according to the selected detection category. For example, when conducting a lateral thrust test on a PVC guardrail, apply a certain magnitude and direction of thrust on the side of the guardrail, and observe whether the guardrail will experience unstable phenomena such as tipping over or excessive deformation, and evaluate its stability under the action of lateral force.

[0021] Step 3: Collect detection data. Collect the data generated during the detection of the PVC guardrail, and record the detection steps at the same time. For example, use pressure sensors, displacement sensors, and acceleration sensors. The pressure sensor is used to measure the magnitude of the force during the loading process; the displacement sensor can monitor the deformation of the guardrail when it is stressed; the acceleration sensor can measure the acceleration change during the impact test in the impact test, and then analyze the impact force.

[0022] Step 4: Intelligently analyze the collected data. Through intelligent analysis of the collected detection data, judge whether the structural strength of the PVC guardrail is qualified. Realize intelligent analysis of the collected data through a convolutional neural network model, and set a data threshold red line at the same time. When the data is lower than the threshold red line, it indicates that the structural strength of the PVC guardrail is unqualified.

[0023] Step 5: Summarize and evaluate the analysis results. By comparing the analysis results with historical data, determine the improvement direction of the PVC guardrail. Continuously test new PVC guardrail processing techniques, and then compare the detected and analyzed data with that of PVC guardrails made using mature techniques to continuously improve the quality of the PVC guardrail.

[0024] Further, when using the convolutional neural network model to analyze data in Step 4, it is first necessary to prepare the data, then input the data into the constructed model for training, and finally use the model to achieve intelligent analysis of the data.

[0025] (III) Beneficial effects

[0026] The present invention provides a method and system for detecting the structural strength of a PVC guardrail. It has the following beneficial effects:

[0027] 1. In this solution, by setting up a detection work unit, the impact resistance strength detection, compressive strength detection, and bending strength detection can be effectively integrated, and specific adjustments can be made when implementing specific detection items, which is beneficial to improving the convenience and efficiency of detecting the structural strength of the PVC guardrail.

[0028] 2. In this solution, by using a convolutional neural network model to perform intelligent analysis on the detected data, it can be intelligently compared with historical data, which can effectively improve the efficiency of data analysis and thus improve the accuracy of the improvement direction of the structural strength of the PVC guardrail. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a schematic flowchart of a system for detecting the structural strength of a PVC guardrail proposed by the present invention;

[0030] Figure 2 is a schematic diagram of the architecture of the data processing unit of a system for detecting the structural strength of a PVC guardrail proposed by the present invention;

[0031] Figure 3 is a schematic diagram of the architecture of the database management unit of a system for detecting the structural strength of a PVC guardrail proposed by the present invention;

[0032] Figure 4 is a schematic diagram of the structure of the detection work unit of a system for detecting the structural strength of a PVC guardrail proposed by the present invention;

[0033] Figure 5 is a schematic flowchart of a method for detecting the structural strength of a PVC guardrail proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0035] Embodiment:

[0036] As Figures 1-5 shown, the embodiment of the present invention provides a PVC guardrail structure strength detection system, and the system architecture includes a data acquisition unit for collecting data. The data acquisition unit includes a pressure sensor, a displacement sensor, an acceleration sensor, etc. The pressure sensor is used to measure the magnitude of the force during the loading process; the displacement sensor can monitor the deformation amount of the guardrail when it is stressed; the acceleration sensor can measure the acceleration change during the impact test in the impact test and then analyze data such as the impact force.

[0037] A data processing unit for processing data. The data processing unit includes a data preprocessing module, a data intelligent processing module, and a data filtering and conversion module. The data preprocessing module mainly cleans the collected data to remove interference data. The data intelligent processing module mainly performs intelligent analysis and processing on the collected data. The data filtering and conversion module filters, amplifies, and performs analog-to-digital conversion on the collected data, and then transmits it to the next stage for processing.

[0038] The database management unit includes a historical data comparison module, a data classification storage module, and a data monitoring module. The historical data comparison module compares and analyzes the collected data with the historical data stored in the database. The data classification storage module mainly classifies and stores the data to be stored according to categories. The data monitoring module mainly scans and monitors the data stored in the database.

[0039] The system feedback summary unit automatically generates a detailed test report according to the analysis result by the software system. The report clearly shows various performance parameters of the guardrail, the conclusion of whether it is qualified, and relevant analysis charts. At the same time, it evaluates the analyzed data and combines historical data to judge the aspects where the structure strength of the PVC guardrail needs to be improved.

[0040] The calibration and maintenance unit for the system needs to regularly calibrate hardware devices such as the loading device and sensors to ensure the accuracy of the detection data. The calibration process records the calibration results according to relevant standards. If it is found that the equipment error exceeds the allowable range, adjustments or repairs can be made in a timely manner. At the same time, a daily maintenance plan for the system is formulated, including equipment cleaning, checking whether the connections of each component are loose, and software system updates. Subsequently, the data storage device is regularly backed up to prevent data loss.

[0041] A detection work unit for detecting the strength of a PVC guardrail. The detection work unit includes a detection category selection module, which includes impact strength detection, compressive strength detection, and flexural strength detection. Among them, the impact strength detection includes pendulum impact test and drop hammer impact test;

[0042] The pendulum impact test can be carried out in a simply supported beam or cantilever beam type. Install the PVC guardrail specimen on the impact machine according to the standard requirements, and let the pendulum fall freely to strike the specimen; then in the simply supported beam impact test, the pendulum strikes the center of the simply supported beam test; for the cantilever beam, the pendulum strikes the free end of the notched cantilever beam, and record the impact energy consumed per unit area or unit width when the specimen breaks, so as to determine its impact strength;

[0043] In the drop hammer impact test, a ball or hammer of a certain mass is freely dropped from a specific height to impact the PVC guardrail specimen, and then observe the damage condition of the guardrail, such as whether there are cracks or fractures, and at the same time record the impact energy or height that can cause a specific damage degree to the guardrail, and then evaluate its impact strength based on this;

[0044] The compressive strength detection is to use a pressure testing machine. Place the PVC guardrail specimen on the working table of the testing machine, and apply a uniform axial pressure to the specimen through the indenter of the testing machine, and gradually increase the pressure until the specimen deforms and breaks, resulting in the failure phenomenon of the PVC guardrail. Then record the pressure value at this time to obtain the compressive strength of the PVC guardrail;

[0045] The flexural strength detection is to place the PVC guardrail specimen on two supports, apply a load perpendicular to the specimen at the middle position of the specimen, so as to cause the specimen to bend and deform, and then measure the flexural deflection under the specified load or the flexural load under the specified deflection, so as to calculate the flexural strength of the PVC guardrail;

[0046] A temperature and humidity control module and a detection process recording module for regulating the temperature and humidity when detecting the strength of the PVC guardrail. The temperature and humidity control module is mainly used to adjust the temperature and humidity during the detection process of the structural strength of the PVC guardrail, so as to realize the structural strength of the PVC guardrail under different temperature and humidity conditions, and then judge the influence of temperature and humidity on the structural strength of the PVC guardrail.

[0047] A method for detecting the structural strength of a PVC guardrail includes the following detection steps:

[0048] Step 1: Detection preparation. Select the corresponding detection equipment according to the selected detection category. For example, when conducting a compressive strength test on a PVC guardrail, a pressure testing machine needs to be prepared; when conducting an impact strength test on a PVC guardrail, a pendulum or a drop hammer needs to be prepared to carry out the impact test on the PVC guardrail;

[0049] Step 2: Start the detection. Detect the structural strength of the PVC guardrail according to the selected detection category. For example, when conducting a lateral thrust test on the PVC guardrail, apply a thrust of a certain magnitude and direction to the side of the guardrail, and observe whether the guardrail will experience unstable phenomena such as tipping over or excessive deformation, and evaluate its stability under the action of lateral force;

[0050] Step 3: Collect detection data. Collect the data generated from the detection of the PVC guardrail, and record the detection steps at the same time. For example, use pressure sensors, displacement sensors, and acceleration sensors. The pressure sensor is used to measure the magnitude of the force during the loading process; the displacement sensor can monitor the deformation of the guardrail when it is stressed; the acceleration sensor can measure the acceleration change during the impact test in the impact test, and then analyze the impact force;

[0051] Step 4: Conduct intelligent analysis on the collected data. Through intelligent analysis of the collected detection data, judge whether the structural strength of the PVC guardrail is qualified. Implement intelligent analysis on the collected data through a convolutional neural network model, and set a data threshold red line at the same time. When the data is lower than the threshold red line, it indicates that the structural strength of the PVC guardrail is unqualified;

[0052] Step 5: Summarize and evaluate the analysis results. By analyzing and comparing the analysis results with historical data, judge the improvement direction of the PVC guardrail. Through continuous experimentation with new PVC guardrail processing technologies, and then compare the detected and analyzed data with the data of PVC guardrails made with mature technologies, so as to continuously improve the quality of the PVC guardrail.

[0053] When using the convolutional neural network model to analyze data in Step 4, first prepare the data, then input the data into the constructed model for training, and finally use the model to achieve intelligent analysis of the data;

[0054] First, collect and preprocess the data:

[0055] 1. Data collection: During the detection of the structural strength of the PVC guardrail, collect various sensor data, such as the pressure data collected by the force sensor, the deformation data recorded by the displacement sensor, the impact acceleration data captured by the acceleration sensor, etc., and record the corresponding detection results at the same time, such as whether the guardrail is damaged and the degree of damage;

[0056] 2. Data cleaning: Check whether there are missing values and outliers in the data. For missing values, methods such as mean filling and linear interpolation can be used for processing; for outliers, according to the data distribution characteristics, methods such as the 3σ criterion are used for identification and correction or elimination;

[0057] 3. Data Normalization: Normalize sensor data in different ranges to the interval [0, 1] or [-1, 1] to eliminate the dimensional differences between data features, thereby improving the model training effect. For example, for force sensor data , the formula can be used for normalization, where and are the minimum and maximum values of this type of data respectively;

[0058] Data Reshaping: Since convolutional neural networks usually process data with specific dimensions, one-dimensional sensor data needs to be reshaped into a multi-dimensional tensor suitable for CNN input. For example, force sensor data collected sequentially over a period of time is reshaped into a two-dimensional matrix, where the rows of the matrix represent time steps and the columns represent different features (such as force values at different positions);

[0059] Then construct a convolutional neural network model:

[0060] 1. Input Layer: Determine the size of the input layer according to the dimension of the preprocessed data. If the data is reshaped into two-dimensional matrix, the number of neurons in the input layer is ;

[0061] 2. Convolutional Layer: Set multiple convolutional layers, and each convolutional layer contains multiple convolutional kernels. The size (such as 3×3, 5×5) and number (such as 16, 32) of the convolutional kernels are adjusted according to the data features and model complexity requirements. The convolutional layer extracts local features in the data through convolutional operations. For example, the change patterns of data at different time steps and positions;

[0062] 3. Pooling Layer: Add a pooling layer after the convolutional layer. Common pooling methods include max pooling and average pooling. The pooling layer can reduce the data dimension and thus reduce the computational amount, while retaining the main features. For example, using a 2×2 max pooling kernel, the maximum value in each 2×2 region is used as the output;

[0063] 4. Fully Connected Layer: Unfold the feature map after convolution and pooling and connect it to the fully connected layer. The fully connected layer comprehensively analyzes the extracted features and outputs the final prediction result. For example, use one or more fully connected layers, and then determine the number of neurons in the output layer according to the detection task (such as judging whether the guardrail is qualified, predicting the damage degree, etc.);

[0064] 5. Activation Function: Use activation functions such as the ReLU (Rectified Linear Unit) function after the convolutional layer and the fully connected layer to increase the non-linear expression ability of the model, and the formula is .

[0065] Subsequently, train and optimize the model:

[0066] 1. Loss function selection: Select an appropriate loss function according to the type of detection task. For binary classification tasks (such as determining whether a guardrail is qualified), the cross-entropy loss function can be used; for regression tasks (such as predicting strength values), the mean squared error loss function can be adopted.

[0067] 2. Optimizer selection: Select optimizers such as Stochastic Gradient Descent (SGD), Adagrad, Adam, etc. to update the model's parameters. Taking the Adam optimizer as an example, it combines the advantages of Adagrad and Adadelta and can adaptively adjust the learning rate to make the model converge faster.

[0068] 3. Training process: Divide the preprocessed data into a training set, a validation set, and a test set, generally in the ratio of 70%, 15%, 15%. During the training process, input the training set data into the model, calculate the prediction results through forward propagation, then calculate the error between the predicted value and the true value according to the loss function, and then update the model parameters through backpropagation. Monitor the performance of the model on the validation set to prevent overfitting.

[0069] Finally, evaluate and apply the model:

[0070] 1. Evaluation metrics: Use metrics such as accuracy, recall, F1-score, root mean square error, etc. to evaluate the model performance. For classification tasks, focus on accuracy, recall, and F1-score; for regression tasks, mainly evaluate the root mean square error.

[0071] 2. Model application: After training and evaluation, apply the model with good performance to the analysis of the actual PVC guardrail structural strength detection data. Real-time collect the sensor data, preprocess it, and then input it into the model. The model can quickly give the detection results and thus achieve intelligent analysis.

[0072] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting the structural strength of a PVC guardrail, characterized in that: It includes the following detection steps: Step 1: Detection preparation. According to the selected detection category, select the corresponding detection equipment. When conducting a compressive strength test on a PVC guardrail, a pressure testing machine needs to be prepared; when conducting an impact resistance test on a PVC guardrail, a pendulum needs to be prepared to perform an impact test on the PVC guardrail; Step 2: Start detection. According to the selected detection category, detect the structural strength of the PVC guardrail. When conducting a lateral thrust test on the PVC guardrail, apply a thrust on the side of the guardrail and observe whether the guardrail topples or has excessive deformation and instability, and evaluate its stability under the action of lateral force; Step 3: Collect detection data. Collect the data generated during the detection of the PVC guardrail, and record the detection steps at the same time. Use a pressure sensor to measure the magnitude of the force during the loading process; Use a displacement sensor to monitor the deformation of the guardrail when it is stressed; Then use an acceleration sensor to measure the acceleration change during the impact process in the impact test, and then analyze the impact force; Step 4: Intelligently analyze the collected data. Through the intelligent analysis of the collected detection data, judge whether the structural strength of the PVC guardrail is qualified. Realize the intelligent analysis of the collected data through a convolutional neural network model, and set a data threshold red line at the same time. When the data is lower than the threshold red line, it indicates that the structural strength of the PVC guardrail is unqualified; Through collecting sensor data and detection results, perform data cleaning, normalization, and reshaping; Then construct a CNN model, including an input layer, a convolutional layer, a pooling layer, a fully connected layer, and use an activation function; then select a loss function and an optimizer for model training, divide the dataset and monitor the performance to prevent overfitting; finally, measure the model performance through evaluation metrics, and apply the well-trained model to the intelligent analysis of actual detection data; Data collection: Collect various sensor data from the process of detecting the structural strength of the PVC guardrail; Data cleaning: Check whether there are missing values and outliers in the data. For missing values, use the mean filling and linear interpolation methods for processing; for outliers, use the 3σ criterion method for identification and elimination according to the data distribution characteristics; Data normalization: Normalize sensor data within different ranges to the interval [0, 1] or [-1, 1] to eliminate the dimensional differences between data features, thereby improving the model training effect. For force sensor data , use the formula for normalization, where and are the minimum and maximum values of this type of data respectively; Data reshaping: Since a convolutional neural network usually processes data with specific dimensions, it is necessary to reshape the one-dimensional sensor data into a multi-dimensional tensor suitable for the input of the CNN; Step 5: Summarize and evaluate the analysis results. By analyzing and comparing the analysis results with historical data, judge the improvement direction of the PVC guardrail. Through continuous experimentation with new PVC guardrail processing technologies, and then compare the detected and analyzed data with the data of PVC guardrails made with mature technologies, so as to continuously improve the quality of the PVC guardrail.

2. The method for detecting the structural strength of a PVC guardrail according to claim 1, wherein: When using a convolutional neural network model to analyze data in the above Step 4, it is first necessary to prepare the data, then input the data into the constructed model for training, and finally realize the intelligent analysis of the data through the model.

Images