Intelligent bridge deck ice and snow removing method and system, terminal and storage medium

Abstract

The invention provides an intelligent bridge deck ice and snow removing method and system, a terminal and a storage medium. The method comprises the steps that a temperature sensor is used for collecting temperature data of a bridge deck according to a first preset frequency; the temperature data are compared with a preset temperature threshold value, and if the temperature data are lower than the preset temperature threshold value, heating equipment on the bridge floor is started for heating; acquiring image data of a bridge floor by using a camera, and inputting the image data into the trained neural network model to obtain an ice and snow removal analysis result corresponding to the image data; and if the ice and snow removal is completed, closing the heating equipment on the bridge floor. The bridge floor temperature is collected by the temperature sensor, the heating equipment is intelligently started in combination with the preset temperature threshold value, and the ice and snow removal effect is accurately evaluated by the neural network model based on the image data captured by the camera, so that the accurate control of the heating equipment is realized while the efficient response to the snow removal demand is ensured, and the ice and snow removal efficiency is improved. And the safety and efficiency of the ice and snow removing process are effectively guaranteed.

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 storage medium for intelligent ice and snow removal on a bridge deck. Background Art

[0002] Traditional methods of bridge de-icing and snow removal usually rely on manual snow shoveling. Manual snow shoveling requires the emergency mobilization of personnel and the preparation of snow shoveling tools and equipment. This series of processes is time-consuming, especially in remote or inconvenient bridge areas, where the time lag problem is particularly serious. Due to the inability to respond to ice and snow removal needs in a timely manner, the effectiveness of manual snow shoveling in emergency situations is greatly reduced. In addition, in extreme weather conditions such as severe cold, strong winds, and blizzards, the safety risks of manual snow removal increase significantly, and it is difficult to ensure snow removal efficiency.

[0003] Therefore, the prior art has defects and needs to be improved and developed. Summary of the invention

[0004] 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 intelligent ice and snow removal on a bridge deck are provided, aiming to solve the problem that the prior art is difficult to respond quickly to ice and snow removal needs and difficult to ensure the safety and efficiency of the ice and snow removal process.

[0005] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for intelligently removing ice and snow from a bridge deck, the method comprising:

[0007] Using a temperature sensor to collect temperature data of the bridge deck at a first preset frequency;

[0008] The temperature data is compared with a preset temperature threshold, and if the temperature data is lower than the preset temperature threshold, a heating device of the bridge deck is turned on to heat the bridge deck according to a preset heating level;

[0009] After the preset heating time, the camera is used to collect image data of the bridge deck at a second preset frequency, and the image data is input into the trained neural network model to obtain ice and snow removal analysis results corresponding to the image data;

[0010] If the de-icing and snow removal analysis result shows that the de-icing and snow removal has been completed, the heating equipment of the bridge deck is turned off.

[0011] In one embodiment, before comparing the temperature data with a preset temperature threshold, the method further includes:

[0012] Obtain historical snow and ice removal data, bridge deck material data, and weather forecast data;

[0013] generating a preset temperature threshold by combining the historical snow and ice removal data, the bridge deck material data and the weather forecast data;

[0014] The historical ice and snow removal data include temperature, snow accumulation and ice and snow removal effect data during the historical ice and snow removal process.

[0015] In one embodiment, after inputting the image data into a trained neural network model to obtain an ice and snow removal analysis result corresponding to the image data, the method further includes:

[0016] If the de-icing and snow removal analysis result shows that de-icing and snow removal is not completed, the heating level of the heating device is adjusted and heating is continued.

[0017] In one embodiment, the training step of the neural network model includes:

[0018] Constructing an initial neural network model, wherein the neural network model is a convolutional neural network model;

[0019] Acquire a training data set, wherein the training data set includes image data of a plurality of bridge decks under different deicing and snow removal conditions;

[0020] The initial neural network model is trained using the training data set, and the loss function is minimized using the Adam optimization algorithm until a preset training round is reached to obtain a trained neural network model.

[0021] In one embodiment, the method for generating the training data set includes:

[0022] Obtaining a basic data set, the basic data set including pictures of several bridge deck materials, weather conditions, and ice and snow removal status;

[0023] Removing pictures with a resolution lower than a preset resolution from the basic data set to obtain a first data set;

[0024] Data enhancement is performed on the first data set to obtain a training data set.

[0025] In one embodiment, the heating device of the open bridge deck heats according to a preset heating level and further comprises:

[0026] Monitoring the status of the heating device in real time;

[0027] If the status is abnormal, an alarm message is generated and sent to maintenance personnel.

[0028] In one implementation, the temperature sensor, the camera, and the heating device are connected via a distributed soft bus.

[0029] In a second aspect, an embodiment of the present invention further provides a bridge deck intelligent ice and snow removal system, comprising:

[0030] A temperature acquisition module, used to collect temperature data of the bridge deck according to a first preset frequency using a temperature sensor;

[0031] A bridge deck heating module is used to compare the temperature data with a preset temperature threshold, and if the temperature data is lower than the preset temperature threshold, turn on the heating device of the bridge deck to heat the bridge deck according to a preset heating level;

[0032] An ice and snow removal analysis module is used to collect image data of the bridge deck using a camera at a second preset frequency after heating for a preset time, input the image data into a trained neural network model, and obtain an ice and snow removal analysis result corresponding to the image data;

[0033] The equipment shut-down module is used to shut down the heating equipment on the bridge deck if the de-icing and snow removal analysis result shows that the de-icing and snow removal has been completed.

[0034] In a third aspect, an embodiment of the present invention further provides a terminal, comprising: a memory, a processor, and an intelligent bridge deck ice and snow removal program stored in the memory and executable on the processor, wherein the intelligent bridge deck ice and snow removal program, when executed by the processor, implements the steps of the intelligent 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, wherein the computer-readable storage medium stores a bridge deck intelligent ice and snow removal program, and the bridge deck intelligent ice and snow removal program can be executed to implement the steps of the bridge deck intelligent ice and snow removal method as described above.

[0036] Beneficial effects of the present invention: The present invention uses a temperature sensor to collect temperature data of the bridge deck at a first preset frequency; compares the temperature data with a preset temperature threshold, and if the temperature data is lower than the preset temperature threshold, turns on the heating equipment of the bridge deck for heating; uses a camera to collect image data of the bridge deck, inputs the image data into a trained neural network model, and obtains an analysis result of ice and snow removal corresponding to the image data; if ice and snow removal is completed, turns off the heating equipment of the bridge deck. The present invention collects the temperature of the bridge deck using a temperature sensor, intelligently starts the heating equipment in combination with a preset temperature threshold, and uses a neural network model to accurately evaluate the ice and snow removal effect based on the image data captured by the camera, thereby ensuring efficient response to snow removal needs while achieving precise control of the heating equipment, effectively ensuring the safety and efficiency of the ice and snow removal process. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of a preferred embodiment of the intelligent ice and snow removal method for bridge decks in the present invention.

[0038] Figure 2 It is a functional principle block diagram of a preferred embodiment of the intelligent ice and snow removal system for bridge decks 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] Traditional methods of bridge de-icing and snow removal usually rely on manual snow shoveling. Manual snow shoveling requires the emergency mobilization of personnel and the preparation of snow shoveling tools and equipment. This series of processes is time-consuming, especially in remote or inconvenient bridge areas, where the time lag problem is particularly serious. Due to the inability to respond to ice and snow removal needs in a timely manner, the effectiveness of manual snow shoveling in emergency situations is greatly reduced. In addition, in extreme weather conditions such as severe cold, strong winds, and blizzards, the safety risks of manual snow removal increase significantly, and it is difficult to ensure snow removal efficiency.

[0042] In view of the above-mentioned defects of the prior art, the present invention provides a method, system, terminal and storage medium for intelligent snow and ice removal on a bridge deck, the method comprising: using a temperature sensor to collect temperature data of the bridge deck at a first preset frequency; comparing the temperature data with a preset temperature threshold, if the temperature data is lower than the preset temperature threshold, turning on the heating device of the bridge deck for heating; using a camera to collect image data of the bridge deck, inputting the image data into a trained neural network model, and obtaining an analysis result of snow and ice removal corresponding to the image data; if snow and ice removal is completed, turning off the heating device of the bridge deck. The present invention collects the temperature of the bridge deck using a temperature sensor, intelligently starts the heating device in combination with a preset temperature threshold, and uses a neural network model to accurately evaluate the snow and ice removal effect based on the image data captured by the camera, thereby ensuring efficient response to snow removal needs while achieving precise control of the heating device, effectively ensuring the safety and efficiency of the snow and ice removal process.

[0043] See also Figure 1 The intelligent snow and ice removal method for bridge decks according to the embodiment of the present invention comprises the following steps:

[0044] Step S100: using a temperature sensor to collect temperature data of the bridge deck at a first preset frequency.

[0045] Specifically, the present invention deploys a temperature sensor on the bridge deck. The temperature data of the bridge deck can be collected according to a first preset frequency, and the first preset frequency can be adjusted according to the real-time weather conditions. When the weather is monitored as sleet, the first preset frequency is set to 10 minutes / time, which not only ensures the timeliness of the data, but also avoids the waste of resources caused by excessively frequent collection in a complex environment of rain and snow. When the weather is monitored as light snow, the first preset frequency is set to 8 minutes / time to more closely track the temperature change trend; when the weather is monitored as moderate snow, the first preset frequency is set to 5 minutes / time to ensure that key information can be captured when the snow first appears; when the weather is monitored as heavy snow, the first preset frequency is set to 1 minute / time to achieve real-time monitoring of the temperature change of the bridge deck, ensure that ice and snow removal work can be started quickly, and effectively curb the potential threat of snow and ice to traffic safety.

[0046] In one implementation, the collected temperature data will be transmitted to a data center in real time for storage and analysis.

[0047] Specifically, through data visualization technology, managers can intuitively see the changing trend and distribution of bridge deck temperature. At the same time, combined with big data analysis methods, they can also predict and evaluate future weather conditions and bridge deck conditions, providing more comprehensive and scientific guidance for ice and snow removal work.

[0048] See also Figure 1 The intelligent snow and ice removal method for bridge decks according to the embodiment of the present invention comprises the following steps:

[0049] Step S200: compare the temperature data with a preset temperature threshold. If the temperature data is lower than the preset temperature threshold, turn on the heating device of the bridge deck to heat the bridge deck according to a preset heating level.

[0050] Specifically, when the temperature data is lower than the preset temperature threshold, the heating device is turned on for heating. In this way, the de-icing operation can be started immediately, which effectively overcomes the time wasted in organizing personnel and equipment to the site in the traditional de-icing method, and can effectively improve the response speed and efficiency of the de-icing operation. When the temperature data is equal to or higher than the preset temperature threshold, it means that there is no need to perform de-icing operations, and the heating device can be kept closed at this time. The heating device has a preset heating level, which can be set according to historical data.

[0051] In one implementation, before comparing the temperature data with a preset temperature threshold, the method further includes:

[0052] Obtain bridge deck material data and weather forecast data;

[0053] The preset temperature threshold is generated by combining the bridge deck material data and the weather forecast data.

[0054] Specifically, in order to set the temperature threshold, it is necessary to obtain the bridge deck material data and weather forecast data in advance. Different bridge deck materials have different sensitivity to temperature changes and snow adhesion. For materials that are easy to adhere to snow, it is necessary to start the snow and ice removal operation as soon as possible, so a lower temperature threshold can be set. Weather forecast data provides meteorological information such as temperature and snowfall in the future, which is an important basis for formulating snow and ice removal plans, including but not limited to predictions of temperature, humidity, precipitation, wind speed, wind direction, and whether it is snowing or icing. These data can be obtained through the meteorological service interface (API) to ensure accuracy and real-time performance. Higher humidity increases the possibility of ice on the bridge deck, while strong winds may cause snow to be blown off the bridge deck, reducing the need for snow and ice removal. When setting the temperature threshold, these multi-dimensional meteorological data can be combined. The present invention generates a preset temperature threshold by combining the bridge deck material data and the weather forecast data, which can not only improve the efficiency of snow and ice removal and reduce resource waste, but also ensure road safety and effectively respond to severe weather challenges.

[0055] See also Figure 1 The intelligent snow and ice removal method for bridge decks according to the embodiment of the present invention comprises the following steps:

[0056] Step S300: After the preset heating time, the camera is used to collect image data of the bridge deck at a second preset frequency, and the image data is input into a trained neural network model to obtain an ice and snow removal analysis result corresponding to the image data;

[0057] Specifically, in the present invention, a high-definition camera is arranged on the bridge deck to monitor the environment of the bridge deck. After the preset heating time, the camera needs to be used to collect image data of the bridge deck to judge the effect of snow and ice removal. The preset time can be set based on historical experience. The present invention uses the camera to collect image data of the bridge deck after the preset heating time, and then judges the effect of snow removal, which can avoid energy waste caused by premature activation of the camera, help extend the life of the equipment, and reduce maintenance costs.

[0058] The acquired image data is input into the trained neural network model. The neural network model learns the characteristic differences between snow, ice and bridge deck background through a large amount of training data, and can automatically identify and classify different elements in the image. When the neural network model receives new image data, it will quickly extract features and classify and output the corresponding snow and ice removal analysis results. Since the entire snow and ice removal process is a dynamic adjustment process. The present invention continuously adjusts the heating level and heating strategy of the heating equipment according to the real-time collected image data and the analysis results of the neural network model to ensure the optimization of the snow and ice removal effect. When the snow and ice removal analysis result shows that the snow and ice removal has been completed, the heating equipment is turned off in time to save energy and avoid damage to the bridge deck caused by excessive heating. In addition, the present invention supports recording the data of each snow and ice removal operation for subsequent analysis and model training to continuously improve the intelligence level of the system and the snow and ice removal effect.

[0059] In one implementation, the training step of the neural network model includes:

[0060] Constructing an initial neural network model, wherein the neural network model is a convolutional neural network model;

[0061] Acquire a training data set, wherein the training data set includes image data of a plurality of bridge decks under different deicing and snow removal conditions;

[0062] The initial neural network model is trained using the training data set, and the loss function is minimized using the Adam optimization algorithm until a preset training round is reached to obtain a trained neural network model.

[0063] Specifically, the neural network model of the present invention is a convolutional neural network model. The convolutional neural network model has advantages in processing image data and can automatically extract hierarchical features in the image. These features gradually transition from low-level edge and texture information to high-level complex concepts such as shapes and objects, providing a solid foundation for subsequent image classification, detection or recognition tasks. The training data set of the present invention not only contains a wealth of bridge deck image samples, but also covers a variety of different ice and snow removal states, such as light snow accumulation, heavy ice, partial melting, etc. This diverse data set helps to improve the generalization ability of the model, so that it can maintain stable performance when facing various complex situations that may arise in practical applications.

[0064] During the training process, the training data is input into the model in batches, and the loss function of each batch of data is calculated. The Adam optimization algorithm is used to update the model parameters to minimize the loss function. The Adam algorithm can adaptively adjust the learning rate of each parameter, so that faster convergence speed and better optimization effect can be achieved in most cases. By continuously iteratively updating the model parameters, the convolutional neural network model (CNN) gradually learns how to map the input bridge deck image to its corresponding deicing state label. The training is continued until the preset training rounds are reached, and a convolutional neural network model that can identify the deicing effect of the bridge deck is obtained. In practical applications, the model can receive new bridge deck image data and output corresponding deicing analysis results to provide decision support for subsequent deicing operations.

[0065] In one implementation, the method for generating the training data set includes:

[0066] Obtaining a basic data set, the basic data set including pictures of several bridge deck materials, weather conditions, and ice and snow removal status;

[0067] Removing pictures with a resolution lower than a preset resolution from the basic data set to obtain a first data set;

[0068] Data enhancement is performed on the first data set to obtain a training data set.

[0069] Specifically, in order to generate a training data set, the basic data set needs to be processed. The basic data set is a picture covering several bridge deck materials, weather conditions and de-icing and snow removal status. The richness of the basic data set can effectively improve the training effect of the model, making the de-icing and snow removal analysis results identified by the model more accurate. In the basic data set, firstly, screening is performed to remove pictures with resolutions lower than the preset resolution to obtain the first data set. Then, data enhancement is performed on each picture in the first data set. Data enhancement methods include geometric transformation, color transformation, noise addition, etc. Specifically, geometric changes can include operations such as rotation, scaling, translation, cropping, and flipping, which can change the spatial layout of the image without changing its content; color transformation can adjust the brightness, contrast, saturation, hue and other properties of the image to simulate images under different lighting conditions or weather conditions; noise addition mainly adds random noise (such as Gaussian noise, salt and pepper noise, etc.) to the image to increase the robustness of the model. Through this data enhancement method, multiple variants can be generated for each picture, and these variants and the original picture together constitute a training data set. When generating variant images, the present invention can intelligently process the annotation information to avoid introducing erroneous or inconsistent labels, and ensure that the annotation information (i.e., de-icing and snow removal status labels) of all variants is consistent with the original image. Through the above steps, a high-quality and diversified training data set can be extracted from the basic data set, providing a data basis for the subsequent training of the neural network model.

[0070] In one implementation, the heating device of the open bridge deck performs heating according to a preset heating level and further includes:

[0071] Monitoring the status of the heating device in real time;

[0072] If the status is abnormal, an alarm message is generated and sent to maintenance personnel.

[0073] Specifically, while the heating equipment is heating, the status of the heating equipment needs to be monitored in real time. When an abnormality is found, an alarm message is generated in time for maintenance. In this way, potential faults or abnormal conditions, such as overheating, short circuit, etc., can be discovered in time, thereby avoiding the occurrence of safety accidents, reducing the operation interruption time caused by equipment failure, and ensuring the efficiency of bridge deck ice and snow removal. The alarm information can be sent to maintenance personnel via text messages, voice calls or application message push. The content of the alarm information includes the type of fault, the location of the fault, and the time of the fault. After receiving the alarm information, the maintenance personnel will go to the site to investigate and repair according to the type of fault and the location of the fault.

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

[0075] Receive and store maintenance record information from maintenance personnel.

[0076] Specifically, after the heating equipment is repaired, the fault type, handling process, repair results, etc. of each repair are recorded in detail. By regularly analyzing the maintenance records, common faults and maintenance experience are summarized to provide reference for subsequent equipment maintenance and management.

[0077] See also Figure 1 The intelligent snow and ice removal method for bridge decks according to the embodiment of the present invention further comprises the following steps:

[0078] Step S400: If the de-icing and snow removal analysis result shows that the de-icing and snow removal has been completed, the heating equipment on the bridge deck is turned off.

[0079] Specifically, by shutting down the heating equipment in time, it is helpful to achieve the goal of energy conservation and emission reduction and reduce operating costs. Long-term high-temperature heating may cause damage to bridge deck materials (such as concrete, asphalt, etc.), such as cracking, deformation, etc. It can be understood that the deicing of the present invention is not a single opening and closing of the heating equipment, but a continuous process. After the heating equipment is turned off, the temperature sensor is used to continue to collect the temperature data of the bridge deck. Once the temperature is monitored to drop below the preset low temperature threshold again, it means that there is a risk of ice and snow re-accumulation or some areas are covered with ice and snow again. The system will automatically trigger the secondary start of the heating device. This instant response mechanism ensures that ice and snow are effectively contained in the early stage of formation, prevents ice and snow from accumulating to a level that is difficult to handle, and can more intelligently remove ice and snow from the bridge deck, effectively avoiding the slow response and low efficiency of deicing in traditional methods. The present invention can not only ensure the deicing effect, but also minimize the negative impact on the bridge deck materials through an intelligent deicing control strategy, so as to achieve a win-win situation of economic and environmental benefits. The intelligent and automated snow and ice removal management system can not only improve the efficiency and quality of snow and ice removal, reduce manual intervention and operating costs, but also effectively protect bridge deck materials and extend the service life of bridges. In addition, the system's instant response mechanism can quickly respond to changes in snowy weather, reduce traffic congestion and safety hazards caused by road closures due to snow and ice, and improve road capacity and public safety.

[0080] In one implementation, the method further includes:

[0081] In response to the heating device shut-down instruction, the heating device is shut down.

[0082] Specifically, the present invention supports users to manually input shutdown instructions on the operation interface to deal with emergencies or special situations, such as sudden weather changes, insufficient energy supply or safety considerations. The immediacy of the shutdown instruction ensures that the user can control the status of the heating equipment and avoid unnecessary energy consumption and potential safety risks. By combining automatic and manual methods to shut down the heating equipment, the present invention achieves dual protection for the control of the heating equipment. The automatic mechanism ensures the stable operation and efficient energy consumption management of the system under normal circumstances, while the manual mechanism provides users with flexible means to deal with emergencies. This dual control mode provides the system with additional processing power, which not only improves the safety and reliability of the system, but also enhances the user experience and satisfaction.

[0083] In one implementation, the method further includes:

[0084] Record the on time when the heating equipment is turned on and the off time when it is turned off;

[0085] Data analysis is performed in combination with the opening time, the closing time and the weather forecast data to obtain a data analysis result.

[0086] Specifically, the actual time consumed for each ice and snow removal operation can be calculated through the opening time and the closing time. This helps to evaluate the efficiency of ice and snow removal under different weather conditions, so as to adjust the heating strategy, such as preheating in advance, extending the heating time, or adjusting the heating level. Combining weather forecast data (such as temperature, humidity, wind speed, precipitation, etc.) with the time record of ice and snow removal operations provides rich background information for data analysis. Data analysis is performed in combination with the opening time, the closing time, and the weather forecast data to obtain data analysis results, which include how weather factors affect the speed of ice and snow formation, the melting efficiency, and the performance of the heating equipment. Based on the data analysis results, the system intelligently adjusts the bridge deck ice and snow removal strategy. The operating data, temperature data, and image data of the heating equipment in the present invention support cloud storage.

[0087] In one implementation, after inputting the image data into a trained neural network model to obtain an ice and snow removal analysis result corresponding to the image data, the method further includes:

[0088] If the de-icing and snow removal analysis result shows that de-icing and snow removal is not completed, the heating level of the heating device is adjusted and heating is continued.

[0089] Specifically, when the task of snow and ice removal is not completed after the preset heating time, it is considered that the heating level needs to be adjusted. The current heating level is adjusted to a higher heating level to achieve the purpose of quickly completing snow and ice removal. It is understandable that different heating levels are preset for the heating device. When the heating device is started, the preset heating level is used, and when it is found that the snow and ice removal effect is not ideal, the heating level is increased. In this way, the heating device can be accurately controlled, which helps to balance efficiency and power consumption.

[0090] In one implementation, the temperature sensor, the camera, and the heating device are connected via a distributed soft bus.

[0091] Specifically, the distributed soft bus provides a unified communication method for different devices, so that these devices are seamlessly connected to form an integrated system. As the system demand grows, new sensors and devices can be added through the distributed soft bus without large-scale changes to the existing system. It has good scalability and provides convenience for long-term upgrades and optimizations. At the same time, the distributed soft bus supports high-bandwidth, low-latency communication capabilities, ensuring fast and accurate data transmission between temperature sensors, cameras and heating equipment. The distributed soft bus of the present invention has built-in intelligent routing algorithms and load balancing mechanisms. It can automatically select the best data transmission path according to the network status and device status, and reasonably allocate communication resources to ensure smooth and efficient data transmission. The distributed soft bus of the present invention adopts redundant design and fault-tolerant mechanism to ensure that the system can still maintain normal operation when some devices or communication links fail. This is crucial for ice and snow removal systems because they need to continue to work under severe weather conditions to ensure the safety and smoothness of roads.

[0092] In summary, the present invention uses a temperature sensor to collect temperature data of the bridge deck at a first preset frequency; compares the temperature data with a preset temperature threshold, and if the temperature data is lower than the preset temperature threshold, turns on the heating device of the bridge deck for heating; uses a camera to collect image data of the bridge deck, inputs the image data into a trained neural network model, and obtains an analysis result of ice and snow removal corresponding to the image data; if ice and snow removal is completed, turns off the heating device of the bridge deck. The present invention uses a temperature sensor to collect the temperature of the bridge deck, intelligently starts the heating device in combination with a preset temperature threshold, and uses a neural network model to accurately evaluate the ice and snow removal effect based on the image data captured by the camera, thereby ensuring efficient response to snow removal needs while achieving precise control of the heating device, effectively ensuring the safety and efficiency of the ice and snow removal process.

[0093] In one embodiment, if Figure 2 As shown, based on the above-mentioned intelligent deicing and snow removal method for bridge deck, the present invention also provides an intelligent deicing and snow removal system for bridge deck, including:

[0094] The temperature acquisition module 100 is used to collect the temperature data of the bridge deck according to a first preset frequency using a temperature sensor;

[0095] The bridge deck heating module 200 is used to compare the temperature data with a preset temperature threshold, and if the temperature data is lower than the preset temperature threshold, turn on the heating device of the bridge deck to heat the bridge deck according to a preset heating level;

[0096] The de-icing and snow analysis module 300 is used to collect image data of the bridge deck using a camera at a second preset frequency after heating for a preset time, input the image data into a trained neural network model, and obtain de-icing and snow analysis results corresponding to the image data;

[0097] The equipment shut-down module 400 is used to shut down the heating equipment of the bridge deck if the de-icing and snow removal analysis result shows that the de-icing and snow removal has been completed.

[0098] In one embodiment, the system further comprises:

[0099] An acquisition unit, used to acquire historical deicing and snow data, bridge deck material data, and weather forecast data;

[0100] A threshold generation unit is used to generate a preset temperature threshold by combining the historical ice and snow removal data, bridge deck material data and weather forecast data; wherein the historical ice and snow removal data includes temperature, snow accumulation and ice and snow removal effect data during the historical ice and snow removal process.

[0101] In one embodiment, the system further comprises:

[0102] The heating unit is maintained to adjust the heating level of the heating device and continue heating if the de-icing and snow removal analysis result shows that the de-icing and snow removal is not completed.

[0103] In one embodiment, the system further comprises:

[0104] A model building unit, used to build an initial neural network model, wherein the neural network model is a convolutional neural network model;

[0105] A training data acquisition unit, used to acquire a training data set, wherein the training data set includes image data of a plurality of bridge decks under different deicing and snow removal conditions;

[0106] The model training unit is used to train the initial neural network model using the training data set, and minimize the loss function using the Adam optimization algorithm until a preset training round is reached to obtain a trained neural network model.

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

[0108] A basic data set acquisition unit, used to acquire a basic data set, wherein the basic data set includes pictures of several bridge deck materials, weather conditions, and de-icing and snow removal status;

[0109] A first preprocessing unit, configured to remove pictures with a resolution lower than a preset resolution from the basic data set to obtain a first data set;

[0110] The second preprocessing unit is used to perform data enhancement on the first data set to obtain a training data set.

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

[0112] A real-time monitoring unit, used for monitoring the state of the heating device in real time;

[0113] The alarm unit is used to generate an alarm message and send it to the maintenance personnel if the state is abnormal.

[0114] 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 deck intelligent ice and snow removal program. The internal memory provides an environment for the operation of the operating device and the bridge deck intelligent ice and snow removal program 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 deck intelligent ice and snow removal program 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 or an electronic ink display.

[0115] 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.

[0116] In one embodiment, a terminal is provided, which includes a memory, a processor, and a bridge deck intelligent ice and snow removal program stored in the memory and executable on the processor. When the bridge deck intelligent 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.

[0117] An embodiment of the present invention also provides a computer-readable storage medium, on which a bridge deck intelligent ice and snow removal program is stored. When the bridge deck intelligent ice and snow removal program is executed by a processor, the steps of any one of the bridge deck intelligent ice and snow removal methods provided in the embodiment of the present invention are implemented.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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 bridge deck intelligent ice and snow removal method, characterized in that: The method comprises: Using a temperature sensor to collect temperature data of the bridge deck at a first preset frequency; The temperature data is compared with a preset temperature threshold, and if the temperature data is lower than the preset temperature threshold, a heating device of the bridge deck is turned on to heat the bridge deck according to a preset heating level; After the preset heating time, the camera is used to collect image data of the bridge deck at a second preset frequency, and the image data is input into the trained neural network model to obtain ice and snow removal analysis results corresponding to the image data; If the de-icing and snow removal analysis result shows that the de-icing and snow removal has been completed, the heating equipment of the bridge deck is turned off.

2. The intelligent bridge deck snow and ice removal method according to claim 1, characterized in that: Before comparing the temperature data with the preset temperature threshold, the method further includes: Obtain bridge deck material data and weather forecast data; The preset temperature threshold is generated by combining the bridge deck material data and the weather forecast data.

3. The intelligent bridge deck snow and ice removal method 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 under different deicing and snow removal conditions; The initial neural network model is trained using the training data set, and the loss function is minimized using the Adam optimization algorithm until a preset training round is reached to obtain a trained neural network model.

4. The intelligent bridge deck snow and ice removal method according to claim 3 is characterized in that: The method for generating the training data set includes: Obtaining a basic data set, the basic data set including pictures of several bridge deck materials, weather conditions, and ice and snow removal status; Removing pictures with a resolution lower than a preset resolution from the basic data set to obtain a first data set; Data enhancement is performed on the first data set to obtain a training data set.

5. The intelligent bridge deck snow and ice removal method according to claim 1, characterized in that: The heating device of the open bridge deck performs heating according to the preset heating level, and also includes: Monitoring the status of the heating device in real time; If the status is abnormal, an alarm message is generated and sent to maintenance personnel.

6. The intelligent bridge deck snow and ice removal method according to claim 1, characterized in that: After inputting the image data into a trained neural network model to obtain an ice and snow removal analysis result corresponding to the image data, the method further includes: If the de-icing and snow removal analysis result shows that de-icing and snow removal is not completed, the heating level of the heating device is adjusted and heating is continued.

7. The intelligent bridge deck snow and ice removal method according to claim 1, characterized in that: The temperature sensor, the camera and the heating device are connected via a distributed soft bus.

8. An intelligent bridge deck ice and snow removal system, characterized in that: include: A temperature acquisition module, used to collect temperature data of the bridge deck according to a first preset frequency using a temperature sensor; A bridge deck heating module is used to compare the temperature data with a preset temperature threshold, and if the temperature data is lower than the preset temperature threshold, turn on the heating device of the bridge deck to heat the bridge deck according to a preset heating level; An ice and snow removal analysis module is used to collect image data of the bridge deck using a camera at a second preset frequency after heating for a preset time, input the image data into a trained neural network model, and obtain an ice and snow removal analysis result corresponding to the image data; The equipment shut-down module is used to shut down the heating equipment on the bridge deck if the de-icing and snow removal analysis result shows that the de-icing and snow removal has been completed.

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

Images