A train network control management system based on the Internet of Things

Abstract

The present invention relates to the field of Internet of Things train management technology, and specifically to a train network control management system based on the Internet of Things, including: a data acquisition module: by deploying sensor equipment in the train to monitor the status and environmental parameters of various components of the train, using cameras to monitor the inside and outside of the carriage, and monitoring passenger behavior; an operation status management module: collecting train operation data, analyzing and predicting the train operation status; an intelligent decision-making module: adjusting and optimizing the train operation plan according to the data analysis results; an operation safety monitoring module: real-time monitoring of the train's location information to ensure the safety of the train on the track. The present invention monitors the status and environmental parameters of various components of the train, as well as passenger behavior, and uses an intelligent decision-making module to adjust and optimize the train operation plan, thereby achieving real-time monitoring and control of the train operation status.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things train management, and in particular to a train network control management system based on the Internet of Things. Background Art

[0002] Airplanes, cars and trains are three important ways for modern people to travel. Among them, the invention of the train is of epoch-making significance and is an important symbol of the first industrial revolution in the West. It has greatly improved the transportation capacity of human society. Subsequently, rail transit represented by trains developed rapidly and has been widely used in life, deriving various forms such as intercity railways, subways and trams. In recent years, with the development of China's urbanization process, the population has gathered in major central cities, and transportation has become a big problem. Urban rail transit has many advantages such as intensive and efficient, large capacity and all-weather, and is the main artery of urban transportation. Rail transit can not only solve the difficulty of traveling in large cities, but also optimize the urban structure layout and promote economic and social development, and has huge added value. Rail transit is strongly supported by the government, occupies a huge share in urban transportation construction, and is an important part of the urban transportation system.

[0003] The existing train management system lacks automated data collection equipment and relies on manual monitoring of the status of train components and passenger behavior, which is prone to blind spots and untimely monitoring. Since it is impossible to collect data and monitor information in real time, safety monitoring often cannot respond and predict in a timely manner, increasing the risk of accidents. Secondly, the lack of camera monitoring and passenger behavior monitoring makes it impossible to effectively maintain order in the carriages. Summary of the invention

[0004] The present invention aims at solving the technical problems existing in the prior art and provides a train network control management system based on the Internet of Things.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: A train network control management system based on the Internet of Things, comprising: a data acquisition module: by deploying sensor equipment in the train to monitor the status and environmental parameters of various components of the train, using cameras to monitor the inside and outside of the carriage, and monitoring passenger behavior;

[0006] Operation status management module: collects train operation data, analyzes and predicts the train operation status;

[0007] Intelligent decision-making module: adjust and optimize the train operation plan based on data analysis results;

[0008] Operation safety monitoring module: monitors the train's location information in real time to ensure the train's running safety on the track.

[0009] In a preferred embodiment, the data acquisition module deploys sensor equipment and cameras on the train according to the train structure, including: temperature sensors, humidity sensors, vibration sensors, acceleration sensors, indoor cameras and outdoor cameras, connects the sensors and cameras to the general control end of the train, ensures that the sensors and cameras can transmit the collected data to the general control end, and the general control end sets the parameters and thresholds of the sensors to accurately monitor the status and environmental parameters of various components of the train. The upper and lower limits of the sensors are set based on the collected sensor data so as to trigger an alarm when an abnormal situation occurs, and the lower limit of the sensor data is set to T min , the upper limit is T max , then the specific formula for the abnormal situation is expressed as:

[0010]

[0011] Among them, Alarm represents a Boolean variable, which is True when the condition for triggering the alarm is met, otherwise it is False. The image data collected by the camera is used to analyze the passenger behavior monitored by the camera to monitor the abnormal behavior of the passengers. The collected image data is preprocessed, including image denoising and image enhancement, to improve the accuracy of subsequent behavior detection, and the passenger behavior characteristics are extracted from the preprocessed image data. For each frame of the image, the pixel displacement between two adjacent frames of the image is calculated by the optical flow method to obtain the displacement vector of each pixel point, which represents the movement of the passenger. Two consecutive frames of images are represented as I t (x,y),I t+1 (x, y), where t represents time and (x, y) represents the pixel coordinates in the image. The specific calculation formula for the motion is as follows:

[0012]

[0013] in, as well as Represents image I t+1 The partial derivatives in the x, y and t directions, u represents the component of the optical flow in the x direction, which represents the displacement of the pixel in the x direction from time t to t+1, and v represents the component of the optical flow in the y direction, which represents the displacement of the pixel in the y direction from time t to t+1. The calculated motion data is used to extract the passenger's behavioral characteristics, including speed and direction. The motion data in the entire image data is averaged to obtain a vector representing the overall motion direction and speed. The specific calculation formula is as follows:

[0014]

[0015] Among them, V avgrepresents the average movement speed, M represents the sum of speed data points, V i Represents the i-th speed data point. The number of optical flow vectors in a certain area reflects the degree of motion activity in the area. The specific calculation formula is as follows:

[0016]

[0017] Where N represents the number of people in the area, A represents the area of ​​the area, and the passenger's movement trajectory is extracted and the passenger's movement speed is calculated according to the time information. The specific calculation formula is as follows:

[0018]

[0019] Wherein, distance represents the total distance moved by the passenger, and time represents the time required for the passenger to move the total distance. Based on the calculated movement speed of the passenger, if the movement speed exceeds the preset threshold, the passenger's behavior is determined to be running. Image recognition technology is used to identify and classify the items carried by the passenger, and whether the identified items belong to the preset dangerous goods category is determined. The specific operation steps are as follows:

[0020] S1. Collect image data of items carried by the user and pre-process the image data, including image scaling and normalization. The specific calculation formula for image scaling is as follows:

[0021]

[0022] Among them, l' represents the pixel value after scaling, min(l) and max(l) represent the minimum and maximum values ​​of the original image pixel values, new_max and new_min represent the maximum and minimum values ​​of the target range, and l represents the pixel value of the original image. The specific calculation formula for normalization is as follows:

[0023]

[0024] Image normalization is used to convert the pixel values ​​of the image to the range of [0, 1];

[0025] S2. Construct a convolutional neural network model to identify and classify the items carried by passengers, determine whether the items carried by passengers belong to the category of dangerous goods, and perform a convolution operation on the preprocessed image data to extract the features of the items. The specific calculation formula of the convolution operation is as follows:

[0026]

[0027] Among them, S(i,j) represents the value of the feature map after convolution at position (i,j), I represents the input image, K represents the convolution kernel, m and n represent the size of the convolution kernel, and the feature map is downsampled to reduce the spatial size of the data and retain the important features in the image data. The specific calculation formula is as follows:

[0028]

[0029] Among them, P(i,j) represents the value after pooling, I represents the input feature map, R represents the area of ​​the pooling window, and s represents the step size of the pooling. The extracted important features are mapped to the output space. The specific calculation formula is as follows:

[0030] H=σ(W·q+b)

[0031] Among them, q represents the input feature, W represents the weight matrix, which is used to map the input feature to the output space, b represents the bias term, σ represents the activation function, and H represents the output. The difference between the model prediction result and the actual category is measured based on the output result. The specific calculation formula is as follows:

[0032]

[0033] Among them, y i The true label represents the probability that the sample belongs to the i-th category, and pi represents the probability predicted by the model, which represents the probability that the sample belongs to the i-th category. The prediction result is continuously optimized through the optimization algorithm. The specific calculation formula is as follows:

[0034]

[0035] Among them, θ represents the model parameters, α represents the learning rate, which is used to control the step size of parameter update. It indicates the sensitivity of the loss function to each parameter. The model outputs the category to which each item belongs and displays the recognition results to relevant personnel.

[0036] In a preferred embodiment, the operation status management module collects the real-time operation status data of the train, including speed, position, time and fault information, integrates the historical data of the train operation, including historical operation records and maintenance records, checks and deletes duplicate records and data points, fills in missing data using interpolation, identifies outliers through statistical methods and performs smoothing, and standardizes the processed data. The specific calculation formula for standardization is as follows:

[0037]

[0038] Among them, k represents the original data, min(k) and max(k) represent the minimum and maximum values ​​in the data respectively. The real-time data after cleaning and standardization is integrated with the historical data to form a complete data set. The features related to the train running status are extracted from the complete data, including acceleration, deceleration and average speed. These features are used as the input of the model, and the forget gate is used to decide to retain the features related to the train running status at a certain moment. The specific calculation formula is as follows:

[0039] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0040] Among them, f t Represents the output of the forget gate, which determines the data C at the previous moment t-1 How much information needs to be retained until the current moment C t , σ represents a function that compresses the output value to between 0 and 1, W f represents the weight matrix of the forget gate, b f represents the bias term of the forget gate, h t-1 represents the hidden state of the LSTM unit at the previous moment, x t Represents the input at the current moment. The train operation information at the current moment is processed through the input gate to generate new train operation information. The specific calculation formula of the input gate is as follows:

[0041] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0042] C t =tanh(W c ·[h t-1 ,x t ]+b c )

[0043] Among them, i t Represents the output of the input gate, which determines the train operation information C at the current moment t How much information needs to be updated to the cell state? Tanh represents the hyperbolic tangent function, which compresses the output value between -1 and 1. W i and W c The weight matrix representing the input gate and train operation information, b i and b c The bias term representing the input gate and train operation information reflects the latest status of the train operation through the cell state update. The specific calculation formula is as follows:

[0044] C t =f t ⊙C t-1 +i t ⊙C t

[0045] Among them, C t It represents the train operation information at the current moment. It combines the historical information retained by the forget gate and the new information brought by the input gate. It summarizes the train operation status based on the current information and generates an output. The specific calculation formula is as follows:

[0046] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0047] h t =o t ⊙tanh(C t )

[0048] Among them, t Represents the output of the output gate, which determines the train operation information C t How much information needs to be passed to the current hidden state h of the LSTM unit? t , W o represents the weight matrix of the output gate, b o represents the bias term of the output gate, h t Represents the hidden state of the LSTM unit at the current moment, which will be used as the input h of the next time step t-1 .

[0049] In a preferred embodiment, the intelligent decision-making module adjusts and optimizes the train operation plan according to the results of model prediction to improve the punctuality rate and operation efficiency of the train. The train operation line includes multiple operation intervals, each operation interval has a different speed limit, and the time allocation of the speed limit is affected by the length of the operation interval and the size of the speed limit value. The train operation front includes several speed limit intervals. When allocating the running time of the train in the current interval, the time allocation signal of each interval needs to be calculated. The specific calculation formula is as follows:

[0050] F q =(Q i -Q i-1 ) / v i_i

[0051] Among them, Q i Indicates the length of the current section, that is, the distance of the current section that the train needs to pass through, Q i-1represents the length of the previous interval, that is, the distance of the previous interval that the train has passed, v i_i Indicates the speed limit value of the current section, indicating the maximum allowed speed of the train in the current section. When the train runs in the current speed limit section, the remaining running section changes in real time, corresponding to the time allocation signal F of the current section q If dynamic real-time calculation is required, the specific calculation formula for the remaining running time in the current interval is as follows:

[0052] F q =(Q i -Q) / v i_i

[0053]

[0054] Where Q represents the distance the train has traveled, s t Indicates the remaining running time of the current interval, S t Indicates the total remaining time of the train in the entire journey, It indicates the sum of the time allocation signals of each section ahead, and is used to calculate the remaining running time of the current section. When reaching the speed limit section, the train brakes and slows down in advance to ensure the safe operation of the train. When the train enters the speed limit section, it starts to brake and slow down until it drops to meet the speed limit requirements. The specific calculation formula is as follows:

[0055]

[0056] Among them, ΔS represents the distance that the train needs to decelerate, that is, the formal distance that the train needs to reduce during the braking process, and A represents the deceleration of the train, that is, the deceleration of the train when braking. By calculating the distance that the train needs to decelerate, it can help the train to brake and decelerate in advance when entering the speed limit section, so as to ensure the safe operation of the train within the speed limit section.

[0057] In a preferred embodiment, the operation safety monitoring module uses a GPS positioning system to monitor the position information of the train in real time, compares the actual position (X_1, Y_1) of the train with the correct running position (X_2, Y_2), ensures that the train runs correctly on the track, and the distance deviation between the actual position and the correct running position is calculated by the following formula:

[0058]

[0059] Where d represents the distance deviation. By calculating the deviation between the actual position and the correct running position, it is determined whether the train deviates from the scheduled track and the running position of the train is appropriately adjusted according to the deviation.

[0060] The beneficial effects of the present invention are as follows: the present invention monitors the status and environmental parameters of various train components, as well as passenger behavior, and uses an intelligent decision-making module to adjust and optimize the train operation plan, thereby achieving real-time monitoring and control of the train operation status, and monitoring the train position information in real time through a safety monitoring module to ensure the safe operation of the train on the track, improve the operating efficiency and safety of the train, and achieve intelligent and efficient train management and operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a system block diagram of the present invention;

[0062] Figure 2 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0064] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0065] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0066] like Figure 1-2 ,This embodiment provides a train network control management system based on the Internet of Things, including: a data acquisition module, an operation status management module, an intelligent decision-making module and an operation safety monitoring module;

[0067] Data acquisition module: By deploying sensor equipment in the train to monitor the status of each train component and environmental parameters, using cameras to monitor the inside and outside of the carriage and monitor passenger behavior;

[0068] Operation status management module: collects train operation data, analyzes and predicts the train operation status;

[0069] Intelligent decision-making module: adjust and optimize the train operation plan based on data analysis results;

[0070] Operation safety monitoring module: monitors the train's location information in real time to ensure the train's running safety on the track.

[0071] In this embodiment, it is necessary to specifically explain the data acquisition module. The data acquisition module deploys sensor equipment and cameras on the train according to the train structure, including: temperature sensors, humidity sensors, vibration sensors, acceleration sensors, indoor cameras and outdoor cameras. The sensors and cameras are connected to the main control end of the train to ensure that the sensors and cameras can transmit the collected data to the main control end. The main control end sets the parameters and thresholds of the sensors to accurately monitor the status and environmental parameters of various components of the train. The upper and lower limits of the sensors are set based on the collected sensor data so as to trigger an alarm when an abnormal situation occurs. The lower limit of the sensor data is set to T min , the upper limit is T max , then the specific formula for the abnormal situation is expressed as:

[0072]

[0073] Among them, Alarm represents a Boolean variable, which is True when the condition for triggering the alarm is met, otherwise it is False. The image data collected by the camera is used to analyze the passenger behavior monitored by the camera to monitor the abnormal behavior of the passengers. The collected image data is preprocessed, including image denoising and image enhancement, to improve the accuracy of subsequent behavior detection, and the passenger behavior characteristics are extracted from the preprocessed image data. For each frame of the image, the pixel displacement between two adjacent frames of the image is calculated by the optical flow method to obtain the displacement vector of each pixel point, which represents the movement of the passenger. Two consecutive frames of images are represented as I t (x,y),I t+1 (x, y), where t represents time and (x, y) represents the pixel coordinates in the image. The specific calculation formula for the motion is as follows:

[0074]

[0075] in, as well as Represents image I t+1 The partial derivatives in the x, y and t directions, u represents the component of the optical flow in the x direction, which represents the displacement of the pixel in the x direction from time t to t+1, and v represents the component of the optical flow in the y direction, which represents the displacement of the pixel in the y direction from time t to t+1. The calculated motion data is used to extract the passenger's behavioral characteristics, including speed and direction. The motion data in the entire image data is averaged to obtain a vector representing the overall motion direction and speed. The specific calculation formula is as follows:

[0076]

[0077] Among them, V avg represents the average movement speed, M represents the sum of speed data points, V i Represents the i-th speed data point. The number of optical flow vectors in a certain area reflects the degree of motion activity in the area. The specific calculation formula is as follows:

[0078]

[0079] Where N represents the number of people in the area, A represents the area of ​​the area, and the passenger's movement trajectory is extracted and the passenger's movement speed is calculated according to the time information. The specific calculation formula is as follows:

[0080]

[0081] Wherein, distance represents the total distance moved by the passenger, and time represents the time required for the passenger to move the total distance. Based on the calculated movement speed of the passenger, if the movement speed exceeds the preset threshold, the passenger's behavior is determined to be running. Image recognition technology is used to identify and classify the items carried by the passenger, and whether the identified items belong to the preset dangerous goods category is determined. The specific operation steps are as follows:

[0082] S1. Collect image data of items carried by the user and pre-process the image data, including image scaling and normalization. The specific calculation formula for image scaling is as follows:

[0083]

[0084] Among them, l' represents the pixel value after scaling, min(l) and max(l) represent the minimum and maximum values ​​of the original image pixel values, new_max and new_min represent the maximum and minimum values ​​of the target range, and l represents the pixel value of the original image. The specific calculation formula for normalization is as follows:

[0085]

[0086] Image normalization is used to convert the pixel values ​​of the image to the range of [0, 1];

[0087] S2. Construct a convolutional neural network model to identify and classify the items carried by passengers, determine whether the items carried by passengers belong to the category of dangerous goods, and perform a convolution operation on the preprocessed image data to extract the features of the items. The specific calculation formula of the convolution operation is as follows:

[0088]

[0089] Among them, S(i,j) represents the value of the feature map after convolution at position (i,j), I represents the input image, K represents the convolution kernel, m and n represent the size of the convolution kernel, and the feature map is downsampled to reduce the spatial size of the data and retain the important features in the image data. The specific calculation formula is as follows:

[0090]

[0091] Among them, P(i,j) represents the value after pooling, I represents the input feature map, R represents the area of ​​the pooling window, and s represents the step size of the pooling. The extracted important features are mapped to the output space. The specific calculation formula is as follows:

[0092] H=σ(W·q+b)

[0093] Among them, q represents the input feature, W represents the weight matrix, which is used to map the input feature to the output space, b represents the bias term, σ represents the activation function, and H represents the output. The difference between the model prediction result and the actual category is measured based on the output result. The specific calculation formula is as follows:

[0094]

[0095] Among them, y i The true label represents the probability that the sample belongs to the i-th category, and pi represents the probability predicted by the model, which represents the probability that the sample belongs to the i-th category. The prediction result is continuously optimized through the optimization algorithm. The specific calculation formula is as follows:

[0096]

[0097] Among them, θ represents the model parameters, α represents the learning rate, which is used to control the step size of parameter update. It indicates the sensitivity of the loss function to each parameter. The model outputs the category to which each item belongs and displays the recognition results to relevant personnel.

[0098] It should be noted that the image denoising method in this application includes: median filtering and Gaussian filtering. The specific calculation formula of median filtering is as follows:

[0099] g(x,y)=median{f(xi,yi),(ij)∈W}

[0100] Among them, f(x, y) represents the original image, g(x, y) represents the denoised image, W represents the filter window, i and j represent the relative coordinates within the filter window, and the specific calculation formula of Gaussian filtering is as follows:

[0101]

[0102] Among them, h(i,j) represents the Gaussian kernel function.

[0103] It should be noted that the image enhancement method in this application includes: histogram equalization and contrast stretching. The specific formula of histogram equalization is as follows:

[0104]

[0105] Among them, r k Represents the gray value of the original image, S k Represents the gray level after equalization, n j represents the number of pixels with gray level j, N represents the total number of pixels in the image, and the specific calculation formula for contrast stretching is as follows:

[0106]

[0107] Among them, r represents the grayscale of the original image, s represents the grayscale after stretching, and r max and r min Represents the maximum and minimum gray levels of the original image, s max and min Indicates the maximum and minimum gray levels after stretching.

[0108] In this embodiment, it is necessary to specifically explain the operation status management module, which collects the real-time operation status data of the train, including speed, position, time and fault information, integrates the historical data of the train operation, including historical operation records and maintenance records, checks and deletes duplicate records and data points, fills in missing data using interpolation, identifies abnormal values ​​through statistical methods and performs smoothing, and standardizes the processed data. The specific calculation formula for standardization is as follows:

[0109]

[0110] Among them, k represents the original data, min(k) and max(k) represent the minimum and maximum values ​​in the data respectively. The real-time data after cleaning and standardization is integrated with the historical data to form a complete data set. The features related to the train running status are extracted from the complete data, including acceleration, deceleration and average speed. These features are used as the input of the model, and the forget gate is used to decide to retain the features related to the train running status at a certain moment. The specific calculation formula is as follows:

[0111] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0112] Among them, f t Represents the output of the forget gate, which determines the data C at the previous moment t-1 How much information needs to be retained until the current moment C t , σ represents a function that compresses the output value to between 0 and 1, W f represents the weight matrix of the forget gate, b f represents the bias term of the forget gate, h t-1 represents the hidden state of the LSTM unit at the previous moment, x t Represents the input at the current moment. The train operation information at the current moment is processed through the input gate to generate new train operation information. The specific calculation formula of the input gate is as follows:

[0113] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0114] C t =tanh(W c ·[h t-1 ,x t ]+b c )

[0115] Among them, i t Represents the output of the input gate, which determines the train operation information C at the current moment t How much information needs to be updated to the cell state? Tanh represents the hyperbolic tangent function, which compresses the output value between -1 and 1. W i and W c The weight matrix representing the input gate and train operation information, b i and b c The bias term representing the input gate and train operation information reflects the latest status of the train operation through the cell state update. The specific calculation formula is as follows:

[0116] C t =f t ⊙C t-1 +i t ⊙C t

[0117] Among them, C t It represents the train operation information at the current moment. It combines the historical information retained by the forget gate and the new information brought by the input gate. It summarizes the train operation status based on the current information and generates an output. The specific calculation formula is as follows:

[0118] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0119] h t =o t ⊙tanh(C t )

[0120] Among them, t Represents the output of the output gate, which determines the train operation information C t How much information needs to be passed to the current hidden state h of the LSTM unit? t , W o represents the weight matrix of the output gate, b o represents the bias term of the output gate, h t Represents the hidden state of the LSTM unit at the current moment, which will be used as the input h of the next time step t-1 .

[0121] It should be noted that the acceleration is obtained by calculating the rate of change of velocity over time. The specific calculation formula is as follows:

[0122]

[0123] Among them, a represents acceleration, v represents speed, and t represents time. When the acceleration is negative, it is deceleration. The average speed is obtained by calculating the comprehensive speed over a period of time and dividing it by the period of time. The specific calculation formula is as follows:

[0124]

[0125] Among them, V avg represents the average speed, vi represents the speed at each time point, T represents the length of the time period,

[0126] It should be noted that the interpolation method in the present invention is a type of linear interpolation and polynomial interpolation, which will not be described in detail here.

[0127] In this embodiment, it is necessary to specifically explain the intelligent decision-making module. The intelligent decision-making module adjusts and optimizes the train operation plan according to the results of model prediction to improve the punctuality rate and operation efficiency of the train. The train operation line includes multiple operation intervals, and the speed limit of each operation interval is different. The time allocation of the speed limit is affected by the length of the operation interval and the size of the speed limit value. The train operation front includes several speed limit intervals. When allocating the running time of the train in the current interval, the time allocation signal of each interval needs to be calculated. The specific calculation formula is as follows:

[0128] F q =(Q i -Q i-1 ) / v i_i

[0129] Among them, Q i Indicates the length of the current section, that is, the distance of the current section that the train needs to pass through, Q i-1 represents the length of the previous interval, that is, the distance of the previous interval that the train has passed, v i_i Indicates the speed limit value of the current section, indicating the maximum allowed speed of the train in the current section. When the train runs in the current speed limit section, the remaining running section changes in real time, corresponding to the time allocation signal F of the current section q If dynamic real-time calculation is required, the specific calculation formula for the remaining running time in the current interval is as follows:

[0130] F q =(Q i -Q) / v i_i

[0131]

[0132] Where Q represents the distance the train has traveled, s t Indicates the remaining running time of the current interval, S t Indicates the total remaining time of the train in the entire journey, It indicates the sum of the time allocation signals of each section ahead, and is used to calculate the remaining running time of the current section. When reaching the speed limit section, the train brakes and slows down in advance to ensure the safe operation of the train. When the train enters the speed limit section, it starts to brake and slow down until it drops to meet the speed limit requirements. The specific calculation formula is as follows:

[0133]

[0134] Among them, ΔS represents the distance that the train needs to decelerate, that is, the formal distance that the train needs to reduce during the braking process, and A represents the deceleration of the train, that is, the deceleration of the train when braking. By calculating the distance that the train needs to decelerate, it can help the train to brake and decelerate in advance when entering the speed limit section, so as to ensure the safe operation of the train within the speed limit section.

[0135] In this embodiment, it is necessary to specifically explain the operation safety monitoring module, which uses the GPS positioning system to monitor the position information of the train in real time, compares the actual position (X_1, Y_1) of the train with the correct running position (X_2, Y_2), and ensures that the train runs correctly on the track. The distance deviation between the actual position and the correct running position is calculated by the following formula:

[0136]

[0137] Where d represents the distance deviation. By calculating the deviation between the actual position and the correct running position, it is determined whether the train deviates from the scheduled track and the running position of the train is appropriately adjusted according to the deviation.

[0138] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0139] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0141] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0143] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0144] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A train network control management system based on the Internet of Things, characterized in that: include: Data acquisition module: By deploying sensor equipment in the train to monitor the status of each train component and environmental parameters, using cameras to monitor the inside and outside of the carriage and monitor passenger behavior; According to the train structure, sensor equipment and cameras are deployed on the train, including: temperature sensor, humidity sensor, vibration sensor, acceleration sensor, indoor camera and outdoor camera. The sensors and cameras are connected to the main control end of the train to ensure that the sensors and cameras can transmit the collected data to the main control end. The main control end sets the parameters and thresholds of the sensors to accurately monitor the status and environmental parameters of each component of the train. The upper and lower limits of the sensors are set based on the collected sensor data so as to trigger an alarm when an abnormal situation occurs. The lower limit of the sensor data is set to T min , the upper limit is T max , then the specific formula for the abnormal situation is expressed as: Among them, Alarm represents a Boolean variable, which is True when the condition for triggering the alarm is met, otherwise it is False. The image data collected by the camera is used to analyze the passenger behavior monitored by the camera, monitor the abnormal behavior of the passengers, and pre-process the collected image data, including image denoising and image enhancement, to improve the accuracy of subsequent behavior detection; By extracting the behavioral characteristics of passengers from the preprocessed image data, for each frame of image, the pixel displacement between two adjacent frames of image is calculated by the optical flow method, and the displacement vector of each pixel is obtained to represent the movement of the passenger. Two consecutive frames of image are represented as I t (x,y),I t+1 (x, y), where t represents time and (x, y) represents the pixel coordinates in the image. The specific calculation formula for the motion is as follows: in, as well as Represents image I t+1 The partial derivatives in the x, y and t directions, u represents the component of the optical flow in the x direction, which represents the displacement of the pixel in the x direction from time t to t+1, and v represents the component of the optical flow in the y direction, which represents the displacement of the pixel in the y direction from time t to t+1. The calculated motion data is used to extract the passenger's behavioral characteristics, including speed and direction. The motion data in the entire image data is averaged to obtain a vector representing the overall motion direction and speed. The specific calculation formula is as follows: Among them, V avg represents the average movement speed, M represents the sum of speed data points, and Vi represents the i-th speed data point; The passenger's behavior characteristics, including speed and direction, are reflected by the number of optical flow vectors in a certain area to show the degree of motion activity in the area. The specific calculation formula is as follows: Where N represents the number of people in the area, A represents the area of ​​the area, and the passenger's movement trajectory is extracted and the passenger's movement speed is calculated according to the time information. The specific calculation formula is as follows: Wherein, distance represents the total distance moved by the passenger, and time represents the time required for the passenger to move the total distance. Based on the calculated passenger's movement speed, if the movement speed exceeds the preset threshold, the passenger's behavior is determined to be running. Image recognition technology is used to identify and classify the items carried by the passenger to determine whether the identified items belong to the preset dangerous goods category. Identifying and classifying items carried by passengers specifically includes the following steps: S1. Collect image data of items carried by the user and pre-process the image data, including image scaling and normalization. The specific calculation formula for image scaling is as follows: Among them, l′ represents the pixel value after scaling, min(l) and max(l) represent the minimum and maximum values ​​of the original image pixel values, new_max and new_min represent the maximum and minimum values ​​of the target range, and l represents the pixel value of the original image. The specific calculation formula for normalization is as follows: Image normalization is used to convert the pixel values ​​of the image to the range of [0, 1]; S2. Construct a convolutional neural network model to identify and classify the items carried by passengers, determine whether the items carried by passengers belong to the category of dangerous goods, and perform a convolution operation on the preprocessed image data to extract the features of the items. The specific calculation formula of the convolution operation is as follows: Among them, S(i, j) represents the value of the feature map after convolution at position (i, j), α represents the input image, K represents the convolution kernel, m and n represent the size of the convolution kernel, and the feature map is downsampled to reduce the spatial size of the data and retain the important features in the image data. The specific calculation formula is as follows: Among them, P(i, j) represents the value after pooling, β represents the input feature map, R represents the area of ​​the pooling window, and s represents the step size of the pooling. The extracted important features are mapped to the output space. The specific calculation formula is as follows: H=σ(W·q+b) Among them, q represents the input feature, W represents the weight matrix, which is used to map the input feature to the output space, b represents the bias term, σ represents the activation function, and H represents the output. The difference between the model prediction result and the actual category is measured based on the output result. The specific calculation formula is as follows: Among them, y i The true label represents the probability that the sample belongs to the i-th category, and pi represents the probability predicted by the model, which represents the probability that the sample belongs to the i-th category. The prediction result is continuously optimized through the optimization algorithm. The specific calculation formula is as follows: Among them, θ represents the model parameters, α represents the learning rate, which is used to control the step size of parameter update. Indicates the sensitivity of the loss function to each parameter, outputs the category to which each item belongs through the model, and displays the recognition results to relevant personnel; Operation status management module: collects train operation data, analyzes and predicts the train operation status; Intelligent decision-making module: adjust and optimize the train operation plan based on data analysis results; Operation safety monitoring module: real-time monitoring of train location information to ensure the safety of trains on the track; Use the GPS positioning system to monitor the train's location information in real time, compare the train's actual location (X_1, Y_1) with the correct location (X_2, Y_2), and ensure that the train runs correctly on the track. The distance deviation between the actual location and the correct location is calculated using the following formula: Where d represents the distance deviation. By calculating the deviation between the actual position and the correct running position, it is determined whether the train deviates from the scheduled track and the running position of the train is appropriately adjusted according to the deviation.

2. According to the Internet of Things-based train network control management system of claim 1, it is characterized in that: The operation status management module collects the real-time operation status data of the train, including speed, position, time and fault information, integrates the historical data of the train operation, including historical operation records and maintenance records, checks and deletes duplicate records and data points, fills in missing data using interpolation, identifies outliers through statistical methods and performs smoothing, and standardizes the processed data. The specific calculation formula for standardization is as follows: Among them, k represents the original data, min(k) and max(k) represent the minimum and maximum values ​​in the data respectively. The real-time data after cleaning and standardization is integrated with the historical data to form a complete data set. The features related to the train running status are extracted from the complete data, including acceleration, deceleration and average speed. These features are used as the input of the model, and the forget gate is used to decide to retain the features related to the train running status at a certain moment. The specific calculation formula is as follows: f t =σ(W f ·[h t-1 ,x t ]+b f ) Among them, f t Represents the output of the forget gate, which determines the data C at the previous moment t-1 How much information needs to be retained until the current moment C t , σ represents a function that compresses the output value to between 0 and 1, W f represents the weight matrix of the forget gate, b f represents the bias term of the forget gate, h t-1 represents the hidden state of the LSTM unit at the previous moment, x t Represents the input at the current moment. The train operation information at the current moment is processed through the input gate to generate new train operation information. The specific calculation formula of the input gate is as follows: i t =σ(W i ·[h t-1 ,x t ]+b i ) C t =tanh(W c ·[h t-1 ,x t ]+b c ) Among them, i t Represents the output of the input gate, which determines the train operation information C at the current moment t How much information needs to be updated to the cell state? Tanh represents the hyperbolic tangent function, which compresses the output value between -1 and 1. W i and W c The weight matrix representing the input gate and train operation information, b i and b c The bias term representing the input gate and train operation information reflects the latest status of the train operation through the cell state update. The specific calculation formula is as follows: C t =f t ☉C t-1 +i t ☉C t Among them, C t It represents the train operation information at the current moment. It combines the historical information retained by the forget gate and the new information brought by the input gate. It summarizes the train operation status based on the current information and generates an output. The specific calculation formula is as follows: the t =σ(W o ·[h t-1 ,x t ]+b o ) h t =o t ⊙tanh(C t ) Among them, t Represents the output of the output gate, which determines the train operation information C t How much information needs to be passed to the current hidden state h of the LSTM unit? t , W o represents the weight matrix of the output gate, b o represents the bias term of the output gate, h t Represents the hidden state of the LSTM unit at the current moment, which will be used as the input h of the next time step t-1 .

3. According to the Internet of Things-based train network control management system of claim 1, it is characterized in that: The intelligent decision-making module adjusts and optimizes the train operation plan according to the results of model prediction to improve the punctuality and operation efficiency of the train. The train operation line includes multiple operation intervals, each of which has a different speed limit. The time allocation of the speed limit is affected by the length of the operation interval and the size of the speed limit value. The train operation front includes several speed limit intervals. When allocating the train operation time in the current interval, the time allocation signal of each interval needs to be calculated. The specific calculation formula is as follows: F q =(Q i -Q i-1 ) / v i_i Among them, Q i Indicates the length of the current section, that is, the distance of the current section that the train needs to pass through, Q i-1 represents the length of the previous interval, that is, the distance of the previous interval that the train has passed, v i_i Indicates the speed limit value of the current section, indicating the maximum allowed speed of the train in the current section. When the train runs in the current speed limit section, the remaining running section changes in real time, corresponding to the time allocation signal F of the current section q If dynamic real-time calculation is required, the specific calculation formula for the remaining running time in the current interval is as follows: F q =(Q i -Q) / v i_i Where Q represents the distance the train has traveled, s t Indicates the remaining running time of the current interval, S t Indicates the total remaining time of the train in the entire journey, It indicates the sum of the time allocation signals of each section ahead, and is used to calculate the remaining running time of the current section. When reaching the speed limit section, the train brakes and slows down in advance to ensure the safe operation of the train. When the train enters the speed limit section, it starts to brake and slow down until it drops to meet the speed limit requirements. The specific calculation formula is as follows: Among them, ΔS represents the distance that the train needs to decelerate, that is, the formal distance that the train needs to reduce during the braking process, and A represents the deceleration of the train, that is, the deceleration of the train when braking. By calculating the distance that the train needs to decelerate, it can help the train to brake and decelerate in advance when entering the speed limit section, so as to ensure the safe operation of the train within the speed limit section.

Images