Bridge monitoring over-limit early warning method and device, electronic equipment and storage medium

Abstract

The invention provides a bridge monitoring overrun early warning method and device, electronic equipment and a storage medium, and belongs to the technical field of bridge monitoring, and the method comprises the steps: obtaining to-be-detected sensing data collected by a sensor at a bridge section, and carrying out the preprocessing of the to-be-detected sensing data, and obtaining first preprocessing data; the sensing data comprises bridge structure response data and environment data; inputting the first preprocessed data into a time sequence prediction model to obtain a prediction value; when the predicted value belongs to a preset alarm threshold range, early warning is carried out; the time sequence prediction model is obtained based on the following steps: obtaining historical sensing data collected by a sensor at a bridge section; preprocessing the historical sensing data to obtain second preprocessed data; and training a preset neural network model based on the second preprocessed data to obtain a time sequence prediction model. According to the method, the predicted value is obtained through the time sequence prediction model obtained through training, and the purpose of accurately predicting and recognizing bridge damage is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge monitoring, and in particular to a bridge monitoring over-limit early warning method, device, electronic equipment and storage medium. Background Art

[0002] Highway bridges are an important part of transportation infrastructure and a node connection channel. Once problems occur, it is bound to affect traffic and driving safety, and even cause great loss of life and property in serious cases. With the increase in the service life of bridges, maintaining the disaster prevention capacity and structural resilience of in-service bridges has also become one of the main problems currently faced. Therefore, it is very important to establish structural health monitoring of bridges. Structural health monitoring of bridges can ensure the structural safety of bridges and improve the accuracy of bridge safety event warnings.

[0003] The damage identification process in the bridge health monitoring system is based on the analysis of the actual response data of the bridge structure under static and dynamic conditions, so as to detect, locate and evaluate the extent of bridge damage. Existing solutions cannot accurately predict and identify bridge damage. Summary of the invention

[0004] In view of this, it is necessary to provide a bridge monitoring over-limit warning method, device, electronic equipment and storage medium to achieve the purpose of accurate prediction and identification of bridge damage.

[0005] In order to solve the above problems, on the one hand, the present invention provides a bridge monitoring over-limit early warning method, comprising: Acquire sensor data to be measured collected by sensors at the bridge cross section, and pre-process the sensor data to be measured to obtain first pre-processed data; the sensor data includes bridge structure response data and environment data; Inputting the first preprocessed data into the time series prediction model to obtain a predicted value; When the predicted value falls within the preset alarm threshold range, an early warning is issued; The time series prediction model is obtained based on the following steps: Obtain historical sensor data collected by sensors at the bridge section; Preprocessing the historical sensor data to obtain second preprocessed data; A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model. In a possible implementation, preprocessing includes: cleaning outliers, denoising, and normalization.

[0006] In a possible implementation, training a preset neural network model based on the second preprocessed data to obtain a time series prediction model includes: A preset neural network model is trained based on the second preprocessed data. During training, a random initialization method is adopted or data weights are set according to the historical sensor data to obtain a time series prediction model.

[0007] In a possible implementation, training a preset neural network model based on the second preprocessed data to obtain a time series prediction model further includes: During training, the parameters of the neural network model are updated based on the Adam algorithm or the SGD algorithm.

[0008] In a possible implementation, the neural network model includes a recurrent neural network model and / or a convolutional neural network model; The recurrent neural network model includes: an input layer, a hidden layer, an output layer and a Dropout layer. The input layer, the hidden layer and the output layer are connected in sequence, and the Dropout layer is used to limit overfitting of the recurrent neural network model.

[0009] In a possible implementation, the bridge structure response data includes at least one of displacement, stress and vibration data of the bridge, and the environmental data includes temperature data.

[0010] In a possible implementation, the characteristic values ​​selected in the neural network model are displacement, vibration data and temperature data, and the target value is stress.

[0011] On the other hand, the present invention also provides a bridge monitoring over-limit early warning device, comprising: An acquisition module is used to acquire sensor data to be measured collected by sensors at the bridge section, and preprocess the sensor data to be measured to obtain first preprocessed data; the sensor data includes bridge structure response data and environment data; A preprocessing module, used for inputting the first preprocessed data into the time series prediction model to obtain a prediction value; An early warning module is used to issue an early warning when the predicted value falls within the preset alarm threshold range; The time series prediction model is obtained based on the following steps: Obtain historical sensor data collected by sensors at the bridge section; Preprocessing the historical sensor data to obtain second preprocessed data; A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model.

[0012] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of any one of the above-mentioned bridge monitoring over-limit early warning methods.

[0013] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the bridge monitoring over-limit warning method as described in any one of the above items are implemented.

[0014] The beneficial effects of adopting the above-mentioned implementation method are as follows: the bridge monitoring over-limit warning method, device, electronic device and storage medium provided by the present invention use historical sensor data to train the neural network model, and then use the sensor data to be tested to perform time series prediction on the characteristic values ​​in the bridge structure health monitoring. At the same time, a reasonable threshold range is set, and when the predicted value exceeds or falls below the set threshold, the warning mechanism is automatically triggered, thereby realizing real-time monitoring and warning of the health status of the bridge structure. The bridge monitoring over-limit warning method provided by the present invention can achieve the purpose of accurate prediction and identification of bridge damage, provide a scientific basis for bridge maintenance, and use fiber optic sensing, neural networks, and time series prediction technology to deeply integrate and apply with bridge structure health monitoring to improve the accuracy of system warnings and reduce blind spots in manual inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A flow chart of an embodiment of the bridge monitoring over-limit early warning method provided by the present invention; Figure 2 A flow chart of another embodiment of the bridge monitoring over-limit early warning method provided by the present invention; Figure 3 A neural network model training prediction flow chart provided by the present invention; Figure 4 A principle block diagram of an embodiment of the bridge monitoring over-limit early warning device provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0018] In the description of the embodiments of the present application, unless otherwise specified, “plurality” means two or more than two.

[0019] The terms "including" and "having" and any variations thereof in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or equipment comprising a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or equipment.

[0020] The naming or numbering of the steps in the embodiments of the present invention does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The execution order of the named or numbered process steps can be changed according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0021] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] The present invention provides a bridge monitoring over-limit early warning method, device, electronic equipment and storage medium, which are respectively described below.

[0023] like Figure 1 As shown, the present invention provides a bridge monitoring over-limit early warning method, comprising: S101, acquiring sensor data to be measured collected by sensors at a bridge cross section, and preprocessing the sensor data to be measured to obtain first preprocessed data; the sensor data includes bridge structure response data and environment data; S102, inputting the first preprocessed data into a time series prediction model to obtain a prediction value; S103, when the predicted value falls within the preset alarm threshold range, issuing an early warning; The time series prediction model is obtained based on the following steps: Obtain historical sensor data collected by sensors at the bridge section; Preprocessing the historical sensor data to obtain second preprocessed data; A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model. It is understandable that the response data of the bridge structure can be monitored in real time by installing sensors on the bridge structure, such as acceleration sensors, displacement sensors, strain sensors, etc. These data are input into the neural network model, and the model can predict the damage in the bridge structure by learning and training the data. When a complete neural network model is established, the historical data is used to perform time series prediction of the characteristic values ​​in the health monitoring of the bridge structure. At the same time, a reasonable threshold range is set. When the predicted value exceeds or falls below the set threshold, the early warning mechanism is automatically triggered, thereby realizing real-time monitoring and early warning of the health status of the bridge structure.

[0024] The bridge structure health monitoring and early warning method provided by the present invention provides a scientific basis for bridge maintenance. With the help of optical fiber sensing, neural network, and time series prediction technology, it is deeply integrated with bridge structure health monitoring to improve the accuracy of system early warning and reduce blind spots in manual inspections.

[0025] In some embodiments, preprocessing includes: cleaning outliers, denoising and normalization.

[0026] In some embodiments, a preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model, including: A preset neural network model is trained based on the second preprocessed data. During training, a random initialization method is adopted or data weights are set according to the historical sensor data to obtain a time series prediction model.

[0027] In some embodiments, training a preset neural network model based on the second preprocessed data to obtain a time series prediction model further includes: During training, the parameters of the neural network model are updated based on the Adam algorithm or the SGD algorithm (‌Stochastic Gradient Descent algorithm).

[0028] As you can understand, Adam is a first-order optimization algorithm that can replace the traditional stochastic gradient descent process, which can iteratively update the weights of the neural network based on the training data. The stochastic gradient descent (SGD) algorithm is a variant of the gradient descent algorithm used to optimize machine learning models. SGD significantly improves computational efficiency, especially when dealing with large datasets, by using only one random training sample (or mini-batch of samples) per iteration to calculate the gradient and update the model parameters.

[0029] In some embodiments, the neural network model includes a recurrent neural network model and / or a convolutional neural network model; The recurrent neural network model includes: an input layer, a hidden layer, an output layer and a Dropout layer. The input layer, the hidden layer and the output layer are connected in sequence, and the Dropout layer is used to limit overfitting of the recurrent neural network model.

[0030] In some embodiments, the bridge structure response data includes at least one of displacement, stress and vibration data of the bridge, and the environmental data includes temperature data.

[0031] In some embodiments, the characteristic values ​​selected in the neural network model are displacement, vibration data and temperature data, and the target value is stress.

[0032] In some embodiments, Figure 2 As shown, the main process of the bridge monitoring over-limit early warning method provided by the present invention includes: 1. Data collection: Collect sensor data deployed on a certain section for bridge structural health monitoring, such as displacement, stress, vibration and temperature data.

[0033] 2. Data preprocessing: The data is cleaned of outliers, denoised and normalized to improve the data quality and prediction accuracy.

[0034] 3. Neural network model training: refer to Figure 3 As shown in the figure, according to the characteristics of the data and prediction requirements, select the appropriate neural network model, such as recurrent neural network (RNN), convolutional neural network (CNN), etc.

[0035] The neural network is trained using historical data to improve the fit between the model prediction results and the actual results. The characteristic values ​​selected in the model are displacement, vibration and temperature, and the target value is stress.

[0036] 4. Threshold setting: According to the characteristics and safety requirements of the bridge structure, a reasonable threshold range can be set, which can be set based on statistical analysis of historical data combined with expert experience or relevant technical standards.

[0037] 5. Time series prediction and over-limit warning: The trained neural network model is used to perform time series prediction on the feature values.

[0038] The predicted value is compared with the set threshold value. When the predicted value exceeds or falls below the threshold value, the early warning mechanism is automatically triggered. The early warning mechanism can include sending alarm information, launching emergency plans and other measures to ensure the safe operation of the bridge structure.

[0039] The key points of interaction of the bridge monitoring over-limit early warning method provided by the present invention include: 1. Data processing Improve data quality: exclude data outliers and normalize the data to improve model training efficiency and the fit between prediction results and actual values. 2. Time series prediction method based on neural network Recurrent Neural Network (RNN) is a neural network model specifically designed to process sequence data. It allows information to be transmitted in the network, can process input sequences of arbitrary length, and share parameters when processing sequences. It usually includes an input layer, a hidden layer, and an output layer. The hidden layer is the core part of the RNN, which is responsible for receiving the hidden state of the previous time step (Timestep) and the input of the current time step, and generating a new hidden state as output. This way of updating the hidden state allows the model to remember previous information and use it in subsequent time steps.

[0040] When using RNN, a large amount of training data needs to be prepared. Insufficient training data may cause the model to overfit. To avoid overfitting, the Dropout layer is added to limit the model to avoid overfitting.

[0041] Model parameter initialization and subsequent optimization: Initialize the weight and bias parameters of the RNN. You can use random initialization or set data weights based on the training sample data. Use optimization algorithms such as Adam and SGD to update the model parameters.

[0042] 3. Threshold setting and updating By comparing historical data or predicted data with the set threshold, when the data exceeds the threshold, the early warning mechanism is triggered and a warning signal is issued.

[0043] 4. Decision support Based on the early warning signals, preset decision-making rules are automatically executed, such as initiating emergency response, adjusting production plans, etc.

[0044] The bridge monitoring over-limit early warning method provided by the present invention has the following beneficial effects: 1. Quick response to improve real-time analysis efficiency; 2. Accurate prediction to improve the safety of bridge structures; 3. Real-time monitoring to reduce labor costs.

[0045] like Figure 4 As shown, the present invention also provides a bridge monitoring over-limit warning device 400, comprising: The acquisition module 401 is used to acquire the sensor data to be measured collected by the sensor at the bridge section, and pre-process the sensor data to be measured to obtain first pre-processed data; the sensor data includes bridge structure response data and environment data; A preprocessing module 402, used for inputting the first preprocessed data into a time series prediction model to obtain a prediction value; An early warning module 403 is used to issue an early warning when the predicted value falls within a preset alarm threshold range; The time series prediction model is obtained based on the following steps: Obtain historical sensor data collected by sensors at the bridge section; Preprocessing the historical sensor data to obtain second preprocessed data; A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model.

[0046] The bridge monitoring over-limit warning device provided in the above embodiment can implement the technical solution described in the above bridge monitoring over-limit warning method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above bridge monitoring over-limit warning method embodiment, which will not be repeated here.

[0047] like Figure 5 As shown, the present invention also provides an electronic device 500. The electronic device 500 includes a processor 501, a memory 502 and a display 503. Figure 5 Only some components of the electronic device 500 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0048] In some embodiments, the memory 502 may be an internal storage unit of the electronic device 500, such as a hard disk or memory of the electronic device 500. In other embodiments, the memory 502 may also be an external storage device of the electronic device 500, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 500.

[0049] Furthermore, the memory 502 may include both an internal storage unit of the electronic device 500 and an external storage device. The memory 502 is used to store application software installed in the electronic device 500 and various data.

[0050] In some embodiments, the processor 501 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 502, such as the bridge monitoring over-limit warning method of the present invention.

[0051] In some embodiments, the display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 503 is used to display information on the electronic device 500 and to display a visual user interface. The components 501-503 of the electronic device 500 communicate with each other via a system bus.

[0052] In some embodiments of the present invention, when the processor 501 executes the bridge monitoring over-limit warning program in the memory 502, the following steps may be implemented: Acquire sensor data to be measured collected by sensors at the bridge cross section, and pre-process the sensor data to be measured to obtain first pre-processed data; the sensor data includes bridge structure response data and environment data; Inputting the first preprocessed data into a time series prediction model to obtain a predicted value; When the predicted value falls within the preset alarm threshold range, an early warning is issued; The time series prediction model is obtained based on the following steps: Obtain historical sensor data collected by sensors at the bridge section; Preprocessing the historical sensor data to obtain second preprocessed data; A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model.

[0053] It should be understood that: when the processor 501 executes the bridge monitoring over-limit warning program in the memory 502, in addition to the above functions, other functions can also be realized. For details, please refer to the description of the corresponding method embodiment above.

[0054] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 500 mentioned, and the electronic device 500 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 500 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0055] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the bridge monitoring over-limit early warning method provided by the above methods is implemented, and the method comprises: Acquire sensor data to be measured collected by sensors at the bridge cross section, and pre-process the sensor data to be measured to obtain first pre-processed data; the sensor data includes bridge structure response data and environment data; Inputting the first preprocessed data into the time series prediction model to obtain a predicted value; When the predicted value falls within the preset alarm threshold range, an early warning is issued; The time series prediction model is obtained based on the following steps: Obtain historical sensor data collected by sensors at the bridge section; Preprocessing the historical sensor data to obtain second preprocessed data; A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model.

[0056] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0057] The above is a detailed introduction to the bridge monitoring over-limit warning method, device, electronic device and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A bridge monitoring over-limit early warning method, characterized in that: include: Acquire sensor data to be measured collected by sensors at the bridge cross section, and pre-process the sensor data to be measured to obtain first pre-processed data; The sensing data includes the bridge structure response data and the environment data; Inputting the first preprocessed data into a time series prediction model to obtain a predicted value; When the predicted value falls within the preset alarm threshold range, an early warning is issued; The time series prediction model is obtained based on the following steps: Obtain historical sensor data collected by sensors at the bridge section; Preprocessing the historical sensor data to obtain second preprocessed data; A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model.

2. The bridge monitoring overrun warning method according to claim 1 is characterized in that: Preprocessing includes: cleaning outliers, denoising and normalization.

3. The bridge monitoring over-limit early warning method according to claim 1 is characterized in that: A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model, including: A preset neural network model is trained based on the second preprocessed data. During training, a random initialization method is adopted or data weights are set according to the historical sensor data to obtain a time series prediction model.

4. The bridge monitoring over-limit early warning method according to claim 3 is characterized in that: Training a preset neural network model based on the second preprocessed data to obtain a time series prediction model also includes: During training, the parameters of the neural network model are updated based on the Adam algorithm or the SGD algorithm.

5. The bridge monitoring overrun warning method according to claim 1 is characterized in that: The neural network model includes a recurrent neural network model and / or a convolutional neural network model; The recurrent neural network model includes: an input layer, a hidden layer, an output layer and a Dropout layer. The input layer, the hidden layer and the output layer are connected in sequence, and the Dropout layer is used to limit overfitting of the recurrent neural network model.

6. The bridge monitoring overrun warning method according to any one of claims 1 to 5, characterized in that: The bridge structure response data includes at least one of displacement, stress and vibration data of the bridge, and the environmental data includes temperature data.

7. The bridge monitoring overrun warning method according to claim 6 is characterized in that: The characteristic values ​​selected in the neural network model are displacement, vibration data and temperature data, and the target value is stress.

8. A bridge monitoring over-limit warning device, characterized in that: include: An acquisition module is used to acquire sensor data to be measured collected by sensors at the bridge cross section, and pre-process the sensor data to be measured to obtain first pre-processed data; The sensing data includes the bridge structure response data and the environment data; A preprocessing module, used for inputting the first preprocessed data into the time series prediction model to obtain a prediction value; An early warning module is used to issue an early warning when the predicted value falls within the preset alarm threshold range; The time series prediction model is obtained based on the following steps: Obtain historical sensor data collected by sensors at the bridge section; Preprocessing the historical sensor data to obtain second preprocessed data; A preset neural network model is trained based on the second preprocessed data to obtain a time series prediction model.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the bridge monitoring over-limit early warning method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the bridge monitoring over-limit early warning method as claimed in any one of claims 1 to 7 are implemented.

Images