Method and system for removing ice and snow on bridge floor based on neural network, terminal and medium

By installing data acquisition devices and neural network models on the bridge deck, the heating device is automatically controlled to heat the bridge, solving the problems of low efficiency in removing ice and snow and environmental pollution, and achieving a safe and efficient ice and snow removal effect.

CN118940804AActive Publication Date: 2024-11-12深圳开鸿数字产业发展有限公司

Patent Information

Application Number
CN202411065084.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-12
Estimated Expiration
2044-08-05

AI Technical Summary

Technical Problem

Existing technologies are insufficient for safely and efficiently removing ice and snow from bridges. Traditional methods are inefficient, pose safety risks, or are harmful to the environment.

Method used

Data acquisition equipment is used to collect bridge deck temperature and image data. A trained neural network model is used to generate heating levels and temperature thresholds, and the heating device is automatically controlled to remove ice and snow.

Benefits of technology

It has achieved safe and efficient removal of ice and snow from bridge surfaces, improved processing speed, reduced manpower input and environmental pollution risks, and optimized energy utilization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940804A_ABST
    Figure CN118940804A_ABST
Patent Text Reader

Abstract

The invention provides a bridge deck ice and snow removal method and system based on a neural network, a terminal and a medium. The method comprises the following steps: acquiring temperature data and image data of a bridge deck by using data acquisition equipment according to a preset frequency; inputting the image data into a trained neural network model, processing the image data through the neural network model, and outputting a heating grade and a temperature threshold corresponding to the image data; and comparing the temperature data with the temperature threshold value, and if the temperature data is lower than the temperature threshold value, starting a heating device on the bridge floor and heating according to the heating grade so as to remove ice and snow on the bridge floor. By combining the data acquisition equipment and the neural network model, the heating equipment on the bridge floor can be automatically controlled for heating, and the purpose of safely and efficiently removing the ice and snow on the bridge is effectively achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of road ice and snow management, and in particular to a method, system, terminal and medium for removing ice and snow from a bridge deck based on a neural network. Background Art

[0002] Facing ice and snow disasters, the safe passage of bridges faces severe challenges. The traditional response methods mainly rely on three methods: manual snow shoveling, chemical snow melting agents and mechanical snow removal, but these methods have certain limitations and shortcomings in practical applications.

[0003] Although manual snow shoveling is relatively inexpensive, it is inefficient and requires a lot of manpower. In addition, in extremely low temperature weather, there are safety risks when manual labor is working outdoors for a long time. Although chemical deicing agents melt snow quickly, their chemical composition will corrode the bridge structure and affect the service life of the bridge. In addition, melted snow water will also carry chemical substances into the environment, causing pollution to the soil, water bodies and vegetation, which is not conducive to the protection of the ecological environment. Mechanical snow removal is relatively efficient, but on bridges with complex structures and narrow spaces, mechanical equipment is difficult to operate flexibly, and the efficiency of snow removal will be greatly reduced. In summary, traditional bridge deicing methods are difficult to remove ice and snow from bridges safely and efficiently.

[0004] Therefore, the prior art has defects and needs to be improved and developed. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, a method, device, terminal and storage medium for removing ice and snow from bridge decks based on a neural network are provided, aiming to solve the problem that the prior art is difficult to achieve safe and efficient removal of ice and snow from bridges.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0007] In a first aspect, an embodiment of the present invention provides a method for removing ice and snow from a bridge deck based on a neural network, the method comprising:

[0008] Using data acquisition equipment to collect temperature data and image data of the bridge deck at a preset frequency;

[0009] Inputting the image data into a trained neural network model, and outputting a heating level and a temperature threshold corresponding to the image data after being processed by the neural network model;

[0010] The temperature data is compared with the temperature threshold. If the temperature data is lower than the temperature threshold, a heating device of the bridge deck is turned on and heating is performed according to the heating level to remove ice and snow from the bridge deck.

[0011] In one embodiment, the data acquisition device includes a temperature sensor and a camera, and the temperature sensor and the camera are evenly arranged on the bridge deck.

[0012] In one embodiment, the neural network model is a convolutional neural network model; the step of inputting the image data into a trained neural network model, processing the image data by the neural network model, and outputting a heating level and a temperature threshold corresponding to the image data includes:

[0013] Inputting the image data into the input layer of the trained convolutional neural network model, and processing the image data through the input layer to obtain normalized image data;

[0014] Inputting the normalized image data into the convolution layer of the convolution neural network model, and performing feature extraction on the normalized image data through the convolution layer to obtain first feature data;

[0015] Inputting the first feature data into an activation layer and transforming it through a nonlinear activation function to obtain second feature data;

[0016] Inputting the second feature data into the pooling layer of the convolutional neural network, and performing downsampling through the pooling layer to obtain third feature data;

[0017] Inputting the third feature data into the fully connected layer of the convolutional neural network model, and processing the data through the fully connected layer to obtain a heating level and a temperature threshold corresponding to the image data;

[0018] The heating level and temperature threshold corresponding to the image data are output via the output layer of the convolutional neural network model.

[0019] In one embodiment, the training step of the neural network model includes:

[0020] Constructing an initial neural network model, wherein the neural network model is a convolutional neural network model;

[0021] Acquire a training data set, wherein the training data set includes image data of a plurality of bridge decks;

[0022] The initial neural network model is trained using the training data set until the loss function converges to a preset value, thereby obtaining a trained neural network model.

[0023] In one embodiment, the method further comprises:

[0024] If the temperature data is higher than the temperature threshold, the heating device of the bridge deck is turned off.

[0025] In one embodiment, after the heating device of the bridge deck is turned on and heating is performed according to the heating level, the method further comprises:

[0026] Get the duration of the heating device on the bridge deck;

[0027] If the opening time exceeds the preset time threshold and the current temperature data is lower than the temperature threshold, an alarm message is generated;

[0028] The warning information is sent to target sanitation workers for artificial snow removal.

[0029] In one embodiment, the heating device is a heating net, and the heating net is evenly embedded in the bridge deck.

[0030] In a second aspect, an embodiment of the present invention further provides a bridge deck ice and snow removal system based on a neural network, comprising:

[0031] A data acquisition module, used to collect temperature data and image data of the bridge deck at a preset frequency using a data acquisition device;

[0032] A data processing module, used for inputting the image data into a trained neural network model, and outputting a heating level and a temperature threshold corresponding to the image data after being processed by the neural network model;

[0033] The ice and snow removal module is used to compare the temperature data with the temperature threshold. If the temperature data is lower than the temperature threshold, the heating device of the bridge deck is turned on and heated according to the heating level to remove ice and snow from the bridge deck.

[0034] In a third aspect, an embodiment of the present invention further provides a terminal, comprising: a memory, a processor, and a neural network-based bridge deck ice and snow removal program stored in the memory and executable on the processor, wherein the neural network-based bridge deck ice and snow removal program, when executed by the processor, implements the steps of the neural network-based bridge deck ice and snow removal method as described above.

[0035] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores a neural network-based bridge deck ice and snow removal program, and the neural network-based bridge deck ice and snow removal program can be executed to implement the steps of the neural network-based bridge deck ice and snow removal method as described above.

[0036] Beneficial effects of the present invention: The present invention uses data acquisition equipment to collect temperature data and image data of the bridge deck at a preset frequency; the image data is input into a trained neural network model, and after being processed by the neural network model, the heating level and temperature threshold corresponding to the image data are output; the temperature data is compared with the temperature threshold, and if the temperature data is lower than the temperature threshold, the heating device of the bridge deck is turned on and heated according to the heating level to remove ice and snow from the bridge deck. By combining data acquisition equipment and neural network models, the present invention can automatically control the heating device of the bridge deck to heat, effectively achieving the purpose of safely and efficiently removing ice and snow from bridges. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of a preferred embodiment of the bridge deck ice and snow removal method based on neural network in the present invention.

[0038] Figure 2 It is a functional principle block diagram of a preferred embodiment of the bridge deck ice and snow removal system based on neural network in the present invention.

[0039] Figure 3 It is a terminal principle block diagram of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0041] Facing ice and snow disasters, the safe passage of bridges faces severe challenges. The traditional response methods mainly rely on three methods: manual snow shoveling, chemical snow melting agents and mechanical snow removal, but these methods have certain limitations and shortcomings in practical applications.

[0042] Although manual snow shoveling is relatively inexpensive, it is inefficient and requires a lot of manpower. In addition, in extremely low temperature weather, there are safety risks when manual labor is working outdoors for a long time. Although chemical deicing agents melt snow quickly, their chemical composition will corrode the bridge structure and affect the service life of the bridge. In addition, melted snow water will also carry chemical substances into the environment, polluting the soil, water bodies and vegetation, which is not conducive to the protection of the ecological environment. Mechanical snow removal is relatively efficient, but on bridges with complex structures and narrow spaces, mechanical equipment is difficult to operate flexibly, and the efficiency of snow removal will be greatly reduced. In summary, traditional bridge deicing methods are difficult to achieve safe and efficient removal of bridge ice and snow.

[0043] In view of the above-mentioned defects of the prior art, the present invention provides a method, system, terminal and medium for removing ice and snow from a bridge deck based on a neural network. The method includes: using a data acquisition device to collect temperature data and image data of the bridge deck at a preset frequency; inputting the image data into a trained neural network model, processing the image data with the neural network model, and outputting a heating level and a temperature threshold corresponding to the image data; comparing the temperature data with the temperature threshold, and if the temperature data is lower than the temperature threshold, turning on the heating device of the bridge deck and heating it according to the heating level to remove ice and snow from the bridge deck. By combining the data acquisition device and the neural network model, the present invention can automatically control the heating device of the bridge deck to heat, effectively achieving the purpose of safely and efficiently removing ice and snow from the bridge.

[0044] See also Figure 1 The method for removing ice and snow from a bridge surface based on a neural network according to an embodiment of the present invention comprises the following steps:

[0045] Step S100: using data acquisition equipment to acquire temperature data and image data of the bridge deck at a preset frequency.

[0046] Specifically, the temperature data reflects the temperature of the bridge deck, and the image data reflects the environmental conditions of the bridge deck. The temperature data and image data of the bridge deck are collected by the data acquisition equipment at a preset frequency, and the temperature data and image data are subsequently processed to monitor the ice and snow conditions on the bridge deck in a timely manner. This method can effectively avoid the situation of manual inspections to monitor the ice and snow conditions, realize the dynamic grasp of the distribution of ice and snow disasters on the bridge deck, and improve the processing speed of ice and snow disasters. The preset frequency can be set according to actual needs and environmental conditions. For example, in the case of heavy snow, the preset frequency can be 5 minutes / time, and in the case of moderate snow, the preset frequency can be 10 minutes / time.

[0047] In one implementation, the preset frequency is generated by dynamic adjustment based on historical ice and snow data and weather forecasts.

[0048] Specifically, when snowfall or low temperature weather is predicted, the collection frequency is automatically increased; and when the weather improves or the ice and snow conditions ease, the collection frequency is reduced.

[0049] In one implementation, the data acquisition device includes a temperature sensor and a camera, and both the temperature sensor and the camera are disposed on the bridge deck.

[0050] Specifically, the present invention sets a temperature sensor and a camera on the bridge deck. The camera and the temperature sensor are used to collect data at a preset frequency so as to monitor the ice and snow conditions on the bridge deck. The field of view of the camera in the present invention can cover the entire bridge deck area, including but not limited to the bridge deck lane, the sidewalk and the guardrails on both sides of the bridge. The camera has high-definition night vision, anti-fog, waterproof and other functions, ensuring stable operation in any weather conditions and capturing clear image information.

[0051] See also Figure 1 The method for removing ice and snow from a bridge surface based on a neural network according to an embodiment of the present invention comprises the following steps:

[0052] Step S200: input the image data into a trained neural network model, and after being processed by the neural network model, output a heating level and a temperature threshold corresponding to the image data.

[0053] Specifically, each time the image data is collected at a preset frequency, the image data is input into the trained neural network model, and in particular, the heating level and temperature threshold corresponding to the current image data are processed and generated. The neural network model in the present invention is a convolutional neural network model. The convolutional neural network model extracts and learns the input data through convolution operations, and realizes tasks such as classification and regression of the input data, and is widely used in the field of image recognition. The present invention utilizes the convolutional neural network model to better learn the complex features in the image, and accurately predict the heating level and temperature threshold corresponding to the image data. The neural network model in the present invention can be deployed in a cloud server or in a physical server, and there is no limitation here.

[0054] In one implementation, the neural network model is a convolutional neural network model; the step of inputting the image data into a trained neural network model, processing the image data by the neural network model, and outputting a heating level and a temperature threshold corresponding to the image data includes:

[0055] Inputting the image data into the input layer of the trained convolutional neural network model, and processing the image data through the input layer to obtain normalized image data;

[0056] Inputting the normalized image data into the convolution layer of the convolution neural network model, and performing feature extraction on the normalized image data through the convolution layer to obtain first feature data;

[0057] Inputting the first feature data into an activation layer and transforming it through a nonlinear activation function to obtain second feature data;

[0058] Inputting the second feature data into the pooling layer of the convolutional neural network, and performing downsampling through the pooling layer to obtain third feature data;

[0059] Inputting the third feature data into the fully connected layer of the convolutional neural network model, and processing the data through the fully connected layer to obtain a heating level and a temperature threshold corresponding to the image data;

[0060] The heating level and temperature threshold corresponding to the image data are output via the output layer of the convolutional neural network model.

[0061] Specifically, the convolutional neural network model (CNN) includes an input layer, a convolutional layer, an activation layer, a pooling layer, a fully connected layer, and an output layer. The input layer is used to normalize the input image data to obtain normalized image data; the convolutional layer is responsible for extracting local features in the image data to obtain the first feature data; the activation layer transforms the first feature data using a nonlinear activation function to obtain the second feature data; the pooling layer is used to reduce the spatial dimension of the second feature data, increase the unique invariance to the image, and obtain the third feature data by downsampling; in the fully connected layer, the third feature data is flattened into a one-dimensional feature vector to obtain the third feature vector, and the third feature vector is transformed by a weighted sum activation function to finally obtain the heating level and temperature threshold corresponding to the image data; the heating level and temperature threshold corresponding to the image data are output through the output layer. The first feature data and the second feature data in the present invention are both in the form of feature maps. The second feature data is a feature map after activation, which is sparser than the first feature data, and while removing unnecessary redundant information, important feature information is retained. The third feature data is a pooled feature map set, which is smaller in size but contains more abstract and advanced feature information. In addition, the heating level and temperature threshold generated in the present invention can be displayed on the interface of the control system.

[0062] In one implementation, the image data is input into a trained neural network model, which is processed by the neural network model to output the heating level and temperature threshold corresponding to the image data, and also outputs the weather forecast and expected heating plan.

[0063] Specifically, the present invention can use image data to generate heating levels, temperature thresholds, weather forecasts, and expected heating plans. The weather forecasts and expected heating plans can be displayed on an interface of the control system.

[0064] In one implementation, the training step of the neural network model includes:

[0065] Constructing an initial neural network model, wherein the neural network model is a convolutional neural network model;

[0066] Acquire a training data set, wherein the training data set includes image data of a plurality of bridge decks;

[0067] The initial neural network model is trained using the training data set until the loss function converges to a preset value, thereby obtaining a trained neural network model.

[0068] Specifically, before obtaining the training data set, the training data set needs to be constructed. The present invention first obtains the original data set, which covers bridge deck images of different materials, different structures, and different aging degrees in different seasons and weather conditions. Then, the original data set is processed using data enhancement technology to obtain the training data set. The data enhancement technology includes random cropping, color jittering, adding noise, etc.

[0069] Random cropping increases the model's adaptability to changes in the field of view by randomly selecting a portion of the original image as a new training sample. In the image detection task of the bridge deck, this means that the model will learn to identify key bridge deck features from the local image, even if the position of these features in the image changes. This is particularly important for dealing with image changes caused by different shooting angles and distances in real scenes. Color jittering simulates bridge deck images under different lighting conditions by adjusting image properties such as brightness, contrast, and saturation. In the image detection task of the bridge deck, since the lighting conditions may change with time, weather, and seasons, color jittering technology can help the model learn how to accurately identify the bridge deck state under different lighting conditions. This helps to improve the stability and reliability of the model in practical applications. Adding noise means adding noise (such as Gaussian noise, etc.) to the image to simulate the interference that may be introduced during image transmission or acquisition. The bridge deck image may be contaminated by various noises during transmission, and by adding noise during training, the model will learn to ignore these noise interferences and focus on extracting useful bridge deck features. This helps to improve the robustness of the model to noise. By comprehensively applying a variety of data enhancement techniques and processing the original data set, the neural network model in the present invention can perform well in complex bridge deck detection tasks.

[0070] During the training process, supervised learning is used for training, and the gradient of the model parameters is calculated using the gradient descent optimization algorithm, and the gradient is back-propagated back to each layer of the model to update the model parameters. It can be understood that the model can achieve accurate understanding and evaluation of the bridge deck image by continuously learning and optimizing its internal parameters.

[0071] See also Figure 1 The method for removing ice and snow from a bridge surface based on a neural network according to an embodiment of the present invention further includes the following steps:

[0072] Step S300: compare the temperature data with the temperature threshold. If the temperature data is lower than the temperature threshold, turn on the heating device of the bridge deck and heat it according to the heating level to remove ice and snow from the bridge deck.

[0073] Specifically, whenever temperature data and image data are collected, the image data is input into the trained neural network model to obtain the temperature threshold and heating level, and then the temperature data is compared with the temperature threshold. As long as the temperature data is lower than the temperature threshold, an opening instruction is generated to turn on the heating device of the bridge deck, and the bridge deck is heated according to the heating level. In this way, more intelligent heating decisions can be made, making the removal of ice and snow on the bridge deck more efficient. When the heating device fails to start successfully for some reason, the system will immediately trigger the abnormal reporting process and send the startup failure information to the management personnel through the preset communication channel to ensure that the problem can be quickly discovered and handled. This instant feedback mechanism is crucial to ensure the safe passage of bridges in winter. It can effectively avoid the accumulation of ice and snow caused by the failure of the heating system and reduce the potential risk of road traffic accidents. In addition, all abnormal records will be automatically archived by the system to form a detailed event log, providing data support for subsequent equipment maintenance, performance evaluation and process optimization.

[0074] In one implementation, the method further includes:

[0075] If the temperature data is higher than the temperature threshold, the heating device of the bridge deck is turned off.

[0076] Specifically, by collecting temperature data at a preset frequency, as long as the temperature data is higher than the temperature threshold, it is considered that the bridge deck ice and snow removal task has been completed, and the bridge deck heating device is turned off in time, effectively avoiding energy waste. Through real-time monitoring and intelligent judgment, the system can accurately capture changes in the bridge deck state and adjust the heating strategy in a timely manner, thereby ensuring road safety while minimizing unnecessary energy consumption, achieving efficient resource utilization and sustainable environmental protection.

[0077] In one implementation, after shutting down the heating device of the bridge deck, the method further includes:

[0078] Generate task completion information;

[0079] And send the task completion information to relevant staff.

[0080] Specifically, after the heating device is turned off, the task completion information is sent in time to inform the relevant staff. The way of sending information may include but is not limited to text messages, emails, application notifications, etc., to ensure that the information can be conveyed quickly and accurately. When the relevant staff receives the task completion information, they can call up the camera to confirm the removal of ice and snow to visually evaluate the effect of ice and snow removal. In the case of heavy snow, when the ice and snow on the bridge surface are not completely removed, there is a situation of bridge closure. The present invention automatically sends the task completion information to inform the relevant staff. When the relevant staff calls up the camera to confirm again, the bridge closure can be lifted in time to restore traffic flow, reducing the social impact and economic losses caused by the bridge closure.

[0081] In one implementation, after turning on the heating device of the bridge deck and heating according to the heating level, the method further includes:

[0082] Get the duration of the heating device on the bridge deck;

[0083] If the opening time exceeds the preset time threshold and the current temperature data is lower than the temperature threshold, an alarm message is generated;

[0084] The warning information is sent to target sanitation workers for artificial snow removal.

[0085] Specifically, when the heating device of the bridge deck is turned on, the duration of the opening will be recorded. The preset time threshold is set comprehensively based on multiple factors such as the bridge deck material, climatic conditions, historical heating effects, etc., in order to ensure that the expected heating effect is achieved within a reasonable time. If the opening duration exceeds the preset time threshold, it is further determined whether the current temperature data is still lower than the temperature threshold. If the current temperature data is still lower than the temperature threshold, it means that the heating effect is not ideal and the purpose of removing ice and snow has not been achieved. At this time, an alarm message is generated in time and sent to the target sanitation worker for timely manual intervention. The heating device and the data processing module in the present invention, as well as the data acquisition device, are connected in a distributed soft bus manner. Data such as temperature threshold, heating level, and opening duration can be displayed on the interface of the control system, so that the control personnel can intuitively understand the current removal of ice and snow on the bridge deck.

[0086] In one implementation, the preset time threshold supports dynamic adjustment according to current weather conditions.

[0087] In one implementation, the method further includes:

[0088] Based on the heating level, determining the power consumption of the heating device corresponding to the heating level;

[0089] acquiring a first heating duration corresponding to the heating level, and multiplying the first heating duration by the power consumption to obtain a first energy consumption corresponding to the heating level;

[0090] By adding up all the first energy consumptions, the total energy consumption of the entire snow and ice removal task can be obtained.

[0091] Based on the power consumption and the heating time corresponding to the power consumption, the total energy consumption is obtained.

[0092] Specifically, different heating levels correspond to different power consumptions of the heating device. Once the heating level is obtained, the corresponding power consumption can be determined. During the entire bridge deck ice and snow removal task (i.e., the process from turning on to turning off the heating device), the different heating levels in the bridge deck ice and snow removal process are multiplied by the corresponding first heating duration at that time to obtain the first energy consumption corresponding to the different heating levels. All the first energy consumptions are added together to obtain the total energy consumption of the entire ice and snow removal task. The first energy consumption is the energy consumption of the heating level in the bridge deck ice and snow removal task. The total energy consumption is the energy consumption of the entire bridge deck ice and snow removal task process. The total energy consumption can be displayed on the control system interface, or it can be stored in the system to facilitate subsequent data analysis for energy efficiency optimization, and it can also serve as data support for subsequent adjustment of the preset time threshold. This method helps to improve the overall energy efficiency management level of the system.

[0093] In one implementation, the heating device is a heating net, and the heating net is evenly embedded in the bridge deck.

[0094] Specifically, the heating network of the present invention is composed of a plurality of conductive wires, and the material of the conductive wires can be a metal alloy or a special conductive material, which is not limited here. When the conductive wires are energized, heat can be released to heat the bridge deck. The present invention can ensure that the heat is evenly distributed on the entire bridge deck by evenly embedding the heating network in the bridge deck structure, avoiding local overheating or insufficient heating. This design not only improves the heating efficiency, but also extends the service life of the heating network, because the evenly distributed heat can reduce the stress concentration caused by the temperature gradient.

[0095] In summary, the present invention uses data acquisition equipment to collect temperature data and image data of the bridge deck at a preset frequency; the image data is input into a trained neural network model, and after being processed by the neural network model, the heating level and temperature threshold corresponding to the image data are output; the temperature data is compared with the temperature threshold, and if the temperature data is lower than the temperature threshold, the heating device of the bridge deck is turned on and heated according to the heating level to remove ice and snow from the bridge deck. By combining data acquisition equipment and neural network models, the present invention can automatically control the heating device of the bridge deck to heat, effectively achieving the purpose of safely and efficiently removing ice and snow from the bridge.

[0096] In one embodiment, if Figure 2As shown, based on the above-mentioned bridge deck ice and snow removal method based on neural network, the present invention also provides a bridge deck ice and snow removal system based on neural network, including:

[0097] The data acquisition module 100 is used to collect the temperature data and image data of the bridge deck according to a preset frequency using a data acquisition device;

[0098] The data processing module 200 is used to input the image data into a trained neural network model, and output a heating level and a temperature threshold corresponding to the image data after being processed by the neural network model;

[0099] The ice and snow removal module 300 is used to compare the temperature data with the temperature threshold. If the temperature data is lower than the temperature threshold, the heating device of the bridge deck is turned on and heated according to the heating level to remove ice and snow from the bridge deck.

[0100] In one embodiment, the neural network model is a convolutional neural network model; the data processing module includes:

[0101] A normalization processing unit, used for inputting the image data into an input layer of the trained convolutional neural network model, and obtaining normalized image data after processing by the input layer;

[0102] A first feature data generating unit, configured to input the normalized image data into a convolutional layer of the convolutional neural network model, and perform feature extraction on the normalized image data through the convolutional layer to obtain first feature data;

[0103] A second feature data generating unit, configured to input the first feature data into an activation layer, transform the first feature data through a nonlinear activation function, and obtain second feature data;

[0104] A third feature data generating unit, configured to input the second feature data into a pooling layer of the convolutional neural network, and perform downsampling through the pooling layer to obtain third feature data;

[0105] A result generating unit, configured to input the third feature data into a fully connected layer of the convolutional neural network model, and process the third feature data through the fully connected layer to obtain a heating level and a temperature threshold corresponding to the image data;

[0106] A result transmission unit is used to output the heating level and temperature threshold corresponding to the image data via the output layer of the convolutional neural network model.

[0107] In one embodiment, the system further comprises:

[0108] A first construction unit is used to construct an initial neural network model, wherein the neural network model is a convolutional neural network model;

[0109] A training set acquisition unit, used to acquire a training data set, wherein the training data set includes image data of a plurality of bridge decks;

[0110] The model training unit is used to train the initial neural network model using the training data set until the loss function converges to a preset value to obtain a trained neural network model.

[0111] In one embodiment, the system further comprises:

[0112] The equipment shut-down unit is used to shut down the heating device of the bridge deck if the temperature data is higher than the temperature threshold.

[0113] In one embodiment, the system further comprises:

[0114] A second data acquisition unit is used to acquire the opening time of the heating device of the bridge deck;

[0115] an alarm generating unit, configured to generate an alarm message if the opening time exceeds a preset time threshold and the current temperature data is lower than a temperature threshold;

[0116] The alarm sending unit is used to send the alarm information to the target sanitation workers so as to perform artificial snow removal.

[0117] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be shown as follows: Figure 3 As shown. The terminal includes a processor, a memory, a network interface and a display screen connected via a device bus. The processor of the terminal is used to provide computing and control capabilities. The memory of the terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating device and a bridge surface ice and snow removal program based on a neural network. The internal memory provides an environment for the operation of the operating device and the bridge surface ice and snow removal program based on a neural network in the non-volatile storage medium. The network interface of the terminal is used to communicate with an external terminal via a network connection. When the bridge surface ice and snow removal program based on a neural network is executed by the processor, the steps of any of the above-mentioned intelligent building energy control methods are implemented. The display screen of the terminal can be a liquid crystal display screen or an electronic ink display screen.

[0118] Those skilled in the art will understand that Figure 3 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0119] In one embodiment, a terminal is provided, which includes a memory, a processor, and a neural network-based bridge deck ice and snow removal program stored in the memory and executable on the processor. When the neural network-based bridge deck ice and snow removal program is executed by the processor, the steps of any one of the intelligent building energy control methods provided in the embodiments of the present invention are implemented.

[0120] An embodiment of the present invention also provides a computer-readable storage medium, on which a neural network-based bridge deck ice and snow removal program is stored. When the neural network-based bridge deck ice and snow removal program is executed by a processor, the steps of any one of the neural network-based bridge deck ice and snow removal methods provided in the embodiments of the present invention are implemented.

[0121] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0122] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the above-mentioned device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0123] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0125] In the embodiments provided by the present invention, it should be understood that the disclosed apparatus / terminal equipment and method can be implemented in other ways. For example, the apparatus / terminal equipment embodiments described above are only illustrative, for example, the division of the above modules or units is only a logical function division, and in actual implementation, other division methods can be used, for example, multiple units or components can be combined or integrated into another apparatus, or some features can be ignored or not executed.

[0126] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features therein may be replaced by equivalents. However, these modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for removing ice and snow from a bridge deck based on a neural network, characterized in that: The method comprises: Using data acquisition equipment to collect temperature data and image data of the bridge deck at a preset frequency; Inputting the image data into a trained neural network model, and processing the image data with the neural network model to output a heating level and a temperature threshold corresponding to the image data; The temperature data is compared with the temperature threshold. If the temperature data is lower than the temperature threshold, a heating device of the bridge deck is turned on and heating is performed according to the heating level to remove ice and snow from the bridge deck.

2. The method for removing ice and snow from bridge deck based on neural network according to claim 1, characterized in that: The data acquisition equipment includes a temperature sensor and a camera, and both the temperature sensor and the camera are arranged on the bridge deck.

3. The method for removing ice and snow from bridge deck based on neural network according to claim 1, characterized in that: The neural network model is a convolutional neural network model; the image data is input into a trained neural network model, and the image data is processed by the neural network model to output a heating level and a temperature threshold corresponding to the image data, including: Inputting the image data into the input layer of the trained convolutional neural network model, and processing the image data through the input layer to obtain normalized image data; Inputting the normalized image data into the convolution layer of the convolution neural network model, and performing feature extraction on the normalized image data through the convolution layer to obtain first feature data; Inputting the first feature data into an activation layer and transforming it through a nonlinear activation function to obtain second feature data; Inputting the second feature data into the pooling layer of the convolutional neural network, and performing downsampling through the pooling layer to obtain third feature data; Inputting the third feature data into the fully connected layer of the convolutional neural network model, and processing the data through the fully connected layer to obtain a heating level and a temperature threshold corresponding to the image data; The heating level and temperature threshold corresponding to the image data are output via the output layer of the convolutional neural network model.

4. The method for removing ice and snow from bridge decks based on neural network according to claim 1, characterized in that: The training steps of the neural network model include: Constructing an initial neural network model, wherein the neural network model is a convolutional neural network model; Acquire a training data set, wherein the training data set includes image data of a plurality of bridge decks; The initial neural network model is trained using the training data set until the loss function converges to a preset value, thereby obtaining a trained neural network model.

5. The method for removing ice and snow from bridge decks based on neural network according to claim 1, characterized in that: The method further comprises: If the temperature data is higher than the temperature threshold, the heating device of the bridge deck is turned off.

6. The method for removing ice and snow from bridge decks based on neural network according to claim 1, characterized in that: After the heating device of the bridge deck is turned on and heating is performed according to the heating level, the method further comprises: Get the duration of the heating device on the bridge deck; If the opening time exceeds the preset time threshold and the current temperature data is lower than the temperature threshold, an alarm message is generated; The warning information is sent to target sanitation workers for artificial snow removal.

7. The method for removing ice and snow from bridge decks based on neural network according to claim 1, characterized in that: The heating device is a heating net, and the heating net is evenly embedded in the bridge deck.

8. A bridge deck ice and snow removal system based on neural network, characterized in that: include: A data acquisition module, used to collect temperature data and image data of the bridge deck at a preset frequency using a data acquisition device; A data processing module, used for inputting the image data into a trained neural network model, and outputting a heating level and a temperature threshold corresponding to the image data after being processed by the neural network model; The ice and snow removal module is used to compare the temperature data with the temperature threshold. If the temperature data is lower than the temperature threshold, the heating device of the bridge deck is turned on and heated according to the heating level to remove ice and snow from the bridge deck.

9. A terminal, characterized in that: The terminal includes a memory, a processor, and a neural network-based bridge deck ice and snow removal program stored in the memory and executable on the processor. When the neural network-based bridge deck ice and snow removal program is executed by the processor, the steps of the neural network-based bridge deck ice and snow removal method as described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a neural network-based bridge deck ice and snow removal program. When the neural network-based bridge deck ice and snow removal program is executed by the processor, the steps of the neural network-based bridge deck ice and snow removal method as described in any one of claims 1-7 are implemented.

Citation Information

Patent Citations

  • Automatic deicing system of camera

    CN112672006A

  • Real-time estimation method for adhesion coefficient of mixed ice and snow pavement based on video data

    CN114332722A

  • Active ice and snow melting system for road surface and control method thereof

    CN114383341A

  • Method and device for judging icing based on electric heating deicing signal

    CN115649455A

  • Bridge active electric heating deicing control system and method

    CN116641281A

Cited By

  • Bridge deck ice and snow early warning method and system based on neural network and multi-modal data fusion

    CN120597191A

  • Bridge ice and snow early warning method and system based on neural network and multi-modal data fusion

    CN120597191B