Subway interval tunnel piston wind parameter determination method, monitoring system and electronic equipment

Abstract

The invention provides a subway interval tunnel piston wind parameter determination method, a monitoring system and electronic equipment. The method comprises the steps that piston wind parameters collected by multiple sensors installed at local positions of an interval tunnel are acquired; based on a fluid flow model, wind speeds and wind pressures of other positions of the interval tunnel are determined according to the wind speeds and the wind pressures collected at the local positions; and inputting the wind speeds and the wind pressures of other positions into a pre-trained regression model for regression prediction to obtain other piston wind parameters related to the wind speeds and the wind pressures. Local piston wind parameters are collected through multiple sensors installed locally, piston wind parameters of other positions are obtained through the fluid flow model and the regression model, comprehensive piston wind parameters in the interval tunnel can be obtained, manpower and time cost of wiring, installation and later maintenance is greatly reduced, efficiency is improved, and the method is suitable for large-scale popularization and application. And instability caused by faults of the sensor and the like is reduced, and the stability of piston wind parameter acquisition is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of piston wind monitoring, and in particular to a method for determining piston wind parameters in a subway tunnel, a monitoring system and electronic equipment. Background Art

[0002] With the acceleration of urbanization and the continuous increase in urban population, subways have become widely used as an efficient urban public transportation tool. Subway tunnels are an important part of subway lines and contain a large number of electromechanical equipment. Trains running in tunnels generate piston wind, which can have a significant impact on electromechanical equipment, shortening its service life and even causing it to fall off the wall or even be damaged. Therefore, monitoring and analyzing the piston wind effect in tunnels is crucial to ensuring safe subway operation.

[0003] Currently, subway monitoring and analysis of the piston wind effect in tunnels has the following deficiencies: Analyzing the piston wind effect requires multiple parameters, such as temperature, humidity, and wind speed in the tunnel. However, due to the length of the tunnel sections, a large number of sensors need to be installed in the tunnel, which not only increases wiring, installation, and equipment costs, but also affects the overall accuracy of subsequent piston wind effect analysis if a sensor at a certain location fails. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method for determining piston wind parameters in a subway section tunnel, a monitoring system and electronic equipment to reduce the cost of collecting piston wind parameters and improve the stability of piston wind parameter collection.

[0005] In a first aspect, a method for determining piston wind parameters in a subway tunnel is provided, the method comprising:

[0006] Obtain piston wind parameters collected by multiple sensors installed at local locations in the section tunnel; the piston wind parameters include at least wind speed and wind pressure;

[0007] Based on the fluid flow model, the wind speed and pressure at other locations in the section tunnel are determined according to the wind speed and pressure collected at the local location. Among them, the other locations are the locations in the section tunnel where no sensors are installed.

[0008] The wind speed and wind pressure at other locations are input into the pre-trained regression model for regression prediction to obtain other piston wind parameters related to wind speed and wind pressure;

[0009] The piston wind parameters collected in real time at local locations and the piston wind parameters at other locations obtained through the fluid flow model and regression model are jointly determined as the target piston wind parameters of the tunnel in this section.

[0010] Optionally, the training process of the regression model includes:

[0011] Obtain historical piston wind parameters; historical piston wind parameters include at least wind speed and wind pressure;

[0012] Determine other piston wind parameters related to wind speed and wind pressure through correlation models;

[0013] The wind speed, wind pressure and other related piston wind parameters are input as training data into the regression model to be trained for iterative training to optimize the model parameters and obtain the regression model with minimum loss. The regression model expression is:

[0014] Y=β0+β1X1+β2X2+…+β n X n

[0015] Among them, X1, X2, X n are independent variables, i.e. wind speed, wind pressure and other piston wind parameters related to them; Y is the dependent variable, i.e. other piston wind parameters related to wind speed and wind pressure that are predicted; β0 is the intercept; β1, β2, β n is the regression coefficient.

[0016] Optionally, other piston wind parameters related to wind speed and wind pressure determined by the correlation model include:

[0017] Calculate the correlation coefficients of other piston wind parameters with wind speed and wind pressure based on the Pearson correlation coefficient model; other piston wind parameters include at least temperature and humidity, vehicle speed, and wind direction;

[0018] Comparing each calculated correlation coefficient with a preset correlation coefficient threshold;

[0019] Other piston wind parameters that are greater than or equal to a preset correlation coefficient threshold are determined as piston wind parameters related to wind speed and wind pressure.

[0020] Optionally, the piston wind parameter also includes vehicle speed, and the process of determining the vehicle speed includes:

[0021] The photoelectric sensor installed in the section tunnel collects the first switch signal and the second switch signal when the train head and the parking space pass through the photoelectric sensor;

[0022] The time difference between the two switching signals is calculated based on the first switching signal and the second switching signal. The calculation formula is:

[0023] T=T b -T a

[0024] The train speed is calculated based on the time difference and train length. The calculation formula is:

[0025]

[0026] Among them, T b is the time when the rear of the train passes the photoelectric sensor, in seconds; T is the time when the front of the train passes the photoelectric sensor, in seconds; V t is the train speed, in m / s; L t is the train length in meters; T is the time difference between the front and rear of the train passing the photoelectric sensor.

[0027] Optionally, the method further comprises:

[0028] Each target piston wind parameter is input into the pre-trained piston wind parameter prediction model to obtain the predicted value of each target piston wind parameter at a future time.

[0029] In a second aspect, a subway tunnel piston wind parameter monitoring system is provided, which includes: multiple environmental sensors, photoelectric sensors, a data isolation module, a data acquisition module, a local display module, a PLC processing module, and an industrial control computer; wherein:

[0030] A variety of environmental sensors are installed at local locations within the tunnel to collect various environmental data at the local locations and send the collected environmental data to the data isolation module; the various environmental data include at least temperature and humidity, wind speed, wind direction and wind pressure;

[0031] The data isolation module is used to separate various environmental data into two channels. One channel is sent to the data acquisition module, which performs analog-to-digital conversion on the various environmental data and transmits them to the local display module for display. The other channel is sent to the PLC processing module.

[0032] The photoelectric sensor is used to collect the switch signal when the train passes by and send the switch signal to the PLC processing module;

[0033] The PLC processing module is used to calculate the train speed based on the switch signal and send the train speed to the local display module for display; on the other hand, it is used to send the train speed and various environmental data as local piston wind parameters to the industrial computer;

[0034] The industrial control computer is used to calculate the piston wind parameters at other locations in the interval tunnel based on the local piston wind parameters, and use the local piston wind parameters and the piston wind parameters at other locations as target piston wind parameters.

[0035] Optionally, the industrial computer is further configured to input each target piston wind parameter into a pre-trained piston wind parameter prediction model to obtain a predicted value of each target piston wind parameter at a future time.

[0036] Optionally, the industrial computer includes a data storage module and a piston wind parameter determination module, and the reading and writing speed of the data storage module is greater than the environmental data acquisition speed.

[0037] According to a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus.

[0038] Memory for storing computer programs;

[0039] The processor is configured to implement any one of the method steps of the first aspect when executing a program stored in the memory.

[0040] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step of the first aspect is implemented.

[0041] The embodiment of the present invention provides a method, monitoring system and electronic equipment for determining piston wind parameters in a subway section tunnel. The method obtains piston wind parameters collected by multiple sensors installed at local locations in the section tunnel; based on a fluid flow model, the wind speed and wind pressure at other locations in the section tunnel are determined according to the wind speed and wind pressure collected at the local location; the wind speed and wind pressure at other locations are input into a pre-trained regression model for regression prediction to obtain other piston wind parameters related to the wind speed and wind pressure; the piston wind parameters collected in real time at the local location and the piston wind parameters at other locations obtained by the fluid flow model and the regression model are jointly determined as the target piston wind parameters of the section tunnel. The present invention collects local piston wind parameters by using multiple sensors installed locally, and obtains piston wind parameters at other locations by using a fluid flow model and a regression model. It can not only obtain comprehensive piston wind parameters in the section tunnel, but also greatly reduces the manpower and time costs of wiring, installation and subsequent maintenance, improves efficiency, reduces instability caused by sensor failures, and improves the stability of piston wind parameter collection.

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 A flow chart of a method for determining piston wind parameters in a subway tunnel provided by an embodiment of the present invention is shown;

[0045] Figure 2 The following is a schematic diagram showing the structure of a subway tunnel piston wind parameter monitoring system provided by an embodiment of the present invention;

[0046] Figure 3 The figure shows a circuit operation diagram of a photoelectric sensor and a PLC vehicle speed calculation module provided by an embodiment of the present invention;

[0047] Figure 4 It shows a schematic structural diagram of an industrial computer data storage module provided by an embodiment of the present invention;

[0048] Figure 5 A flowchart showing the working process of the piston wind parameter determination module provided in an embodiment of the present invention is shown;

[0049] Figure 6 A schematic structural diagram of an electronic device provided by an embodiment of the present invention is shown.

[0050] Explanation of main component symbols: 201, environmental sensor; 202, photoelectric sensor; 203, data isolation module; 204, data acquisition module; 205, local display module; 206, PLC processing module; 207, industrial computer; 2061, PLC input unit; 2062, PLC vehicle speed calculation unit; 2063, PLC output unit; 2071, data storage module; 2072, piston wind parameter determination module. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0052] Currently, collecting piston wind parameters requires installing a large number of sensors within tunnels. This not only increases wiring, installation, and equipment costs, but also affects the overall accuracy of subsequent piston wind effect analysis if a sensor failure occurs. Therefore, embodiments of the present invention provide a method and system for determining piston wind parameters in subway tunnels, which are described below through examples.

[0053] An embodiment of the present invention provides a method for determining piston wind parameters in a subway tunnel, the method comprising the following steps:

[0054] Step S101: Obtain piston wind parameters collected by multiple sensors installed at local locations in the section tunnel; the piston wind parameters include at least wind speed and wind pressure.

[0055] An interval tunnel refers to a tunnel between two subway stations. The length of an interval tunnel is generally 300-500 meters. If you want to collect piston wind parameters in such a long tunnel, you need to deploy a large number of sensors, which is time-consuming and labor-intensive in terms of wiring, installation and subsequent maintenance.

[0056] Therefore, in the embodiment of the present invention, sensors may be arranged at key locations of the section tunnel, and acquisition may be performed at other locations using the method of steps S102 - S103 .

[0057] In one example, a group of sensors is set at the entrance, exit and every 100 meters between the entrance and exit of the interval tunnel. This group of sensors includes at least a wind speed sensor, a wind pressure sensor, a wind direction sensor, a temperature and humidity sensor and a photoelectric sensor.

[0058] Step S102: Based on the fluid flow model, the wind speed and wind pressure at other locations in the section tunnel are determined according to the wind speed and wind pressure collected at the local location; wherein the other locations are locations in the section tunnel where no sensors are installed.

[0059] In an embodiment of the present invention, the fluid (piston wind) in the interval tunnel is incompressible and there is no energy loss within a short distance. Therefore, the fluid flow model can adopt the Bernoulli equation. The Bernoulli equation is a basic equation in fluid mechanics that describes the energy conservation relationship of an ideal fluid in stable flow.

[0060] The Bernoulli equation is as follows:

[0061]

[0062] Among them, P1 is the wind pressure collected at the location where the sensor is installed, v1 is the wind speed collected at the location where the sensor is installed, h1 is the height of the tunnel at the location where the sensor is installed, P2 is the wind pressure at the location where the sensor is not installed, v2 is the wind speed at the location where the sensor is not installed, and h2 is the height of the tunnel at the location where the sensor is not installed.

[0063] In the embodiment of the present invention, h1 and h2 can be considered to be approximately the same, so the above formula can be simplified to obtain the following formula:

[0064]

[0065] By knowing the data of P1 and v1, the data of P2 and v2 can be calculated.

[0066] By utilizing the fluid flow characteristics to obtain the piston wind parameters at other locations, the piston wind effect in the interval tunnel can be connected, enabling a more comprehensive evaluation of the piston wind effect in the interval tunnel.

[0067] Step S103: inputting the wind speed and wind pressure at other locations into the pre-trained regression model for regression prediction to obtain other piston wind parameters related to the wind speed and wind pressure.

[0068] In an embodiment of the present invention, other piston wind parameters related to wind speed and wind pressure include, for example, temperature and humidity, vehicle speed, and wind direction. The greater the wind speed, the lower the temperature in the tunnel and the lower the humidity. Conversely, the lower the wind speed, the higher the temperature in the tunnel and the higher the humidity. For example, wind direction will also affect wind pressure and wind speed. Wind speed and wind pressure will also affect vehicle speed. For example, the greater the vehicle speed, the greater the wind pressure, and the lower the vehicle speed, the lower the wind pressure.

[0069] In an embodiment of the present invention, the regression model adopts a multiple linear regression model, and the multiple linear regression analysis can predict the dependent variables (such as temperature and humidity, wind direction, vehicle speed, etc.) based on the known independent variables (such as wind speed, wind pressure, etc.).

[0070] Step S104: The piston wind parameters collected in real time at a local position and the piston wind parameters at other positions obtained through the fluid flow model and the regression model are jointly determined as the target piston wind parameters of the tunnel in this section.

[0071] In the embodiment of the present invention, after the target piston wind parameter is obtained, the piston wind effect can be analyzed based on the target piston wind parameter.

[0072] Through the above embodiments, it can be understood that the present invention collects local piston wind parameters through multiple locally installed sensors, and obtains piston wind parameters at other locations through fluid flow models and regression models. It can not only obtain comprehensive piston wind parameters in the interval tunnel, but also greatly reduce the manpower and time costs of wiring, installation and subsequent maintenance, improve efficiency, and reduce instability caused by sensor failures, thereby improving the stability of piston wind parameter collection.

[0073] Based on the above embodiment, the training process of the regression model includes the following steps:

[0074] Step S103A: Obtain historical piston wind parameters. The historical piston wind parameters include at least wind speed and wind pressure.

[0075] In this step, after obtaining the historical piston wind parameters, data preprocessing can be performed on the parameters, such as data cleaning, processing missing values ​​and outliers, standardizing or normalizing the data, etc.

[0076] Step S103B: Determine other piston wind parameters related to wind speed and wind pressure through a correlation model.

[0077] In this step, the correlation model can be used to obtain piston wind parameters that are highly correlated with wind speed and wind pressure as training numbers, thereby filtering out some piston wind parameters that are not highly correlated, which is more conducive to the subsequent training of the regression model and improves the efficiency and accuracy of the subsequent regression model training.

[0078] Step S103C: Input wind speed, wind pressure, and other related piston wind parameters as training data into the regression model to be trained for iterative training to optimize the model parameters and obtain a regression model with minimum loss. The regression model expression is:

[0079] Y=β0+β1X1+β2X2+…+β n X n (3);

[0080] Among them, X1, X2, X n are independent variables, i.e. wind speed, wind pressure and other piston wind parameters related to them; Y is the dependent variable, i.e. other piston wind parameters related to wind speed and wind pressure that are predicted; β0 is the intercept; β1, β2, β n is the regression coefficient.

[0081] In the embodiment of the present invention, the regression coefficient can be solved by gradient descent method, least square method or other optimization methods to obtain the optimal regression model.

[0082] In an embodiment of the present invention, the training data can be divided into a training set and a test set according to a preset ratio. Training is performed using the training set, and the performance of the model is evaluated using the test set. Commonly used evaluation indicators include mean square error (MSE), coefficient of determination (R2), etc.

[0083] Based on the above embodiment, other piston wind parameters related to wind speed and wind pressure determined by the correlation model include:

[0084] Step S103B1: Calculate the correlation coefficients of other piston wind parameters with wind speed and wind pressure based on the Pearson correlation coefficient model.

[0085] In this step, other piston wind parameters include at least temperature and humidity, vehicle speed, and wind direction.

[0086] The Pearson correlation coefficient, also known as the Pearson product-moment correlation coefficient, is a statistical indicator used to measure the degree of linear correlation between two variables. It is usually represented by the symbol r and has a value range between -1 and 1.

[0087] The expression of the Pearson correlation coefficient model is:

[0088]

[0089] Where r is the correlation coefficient; x i is the parameter value of wind speed or wind pressure at different positions i in the tunnel; y i are other piston wind parameter values ​​at different locations in the tunnel; is the average value of wind speed or wind pressure parameters at different locations in the tunnel; are the average values ​​of other piston wind parameters at different locations in the tunnel.

[0090] In a feasible implementation manner, each other piston wind parameter is used to calculate the correlation coefficient with wind pressure and the correlation coefficient with wind speed using the above formula.

[0091] Step S103B2: Compare the calculated correlation coefficients with a preset correlation coefficient threshold.

[0092] Step S103B3: Determine other piston wind parameters that are greater than or equal to a preset correlation coefficient threshold as piston wind parameters related to wind speed and wind pressure.

[0093] In this step, if the correlation coefficient is greater than or equal to the preset threshold, it means that the parameter has a strong correlation with the wind speed or wind pressure.

[0094] Based on the above embodiment, the piston wind parameter also includes vehicle speed, and the process of determining the vehicle speed includes:

[0095] Step a: A photoelectric sensor installed in a section tunnel collects a first switching signal and a second switching signal when the train head and the parking space pass through the photoelectric sensor.

[0096] When the front of the train passes by, the photoelectric sensor in the tunnel will continue to generate a high-level switching signal. When the rear of the train passes by the photoelectric sensor, the high-level signal becomes a low-level signal.

[0097] Step b: Calculate the time difference between the two switching signals based on the first switching signal and the second switching signal; the calculation formula is:

[0098] T=T b -T a (5);

[0099] Among them, T bis the time when the rear end of the train passes the photoelectric sensor, in seconds; T is the time when the front end of the train passes the photoelectric sensor, in seconds.

[0100] In this step, the time difference between the two signals is calculated by the PLC controller, and the time difference accuracy is at the millisecond level.

[0101] Step c: Calculate the train speed based on the time difference and train length. The calculation formula is:

[0102]

[0103] Among them, V t is the train speed, in m / s; L t is the train length in meters; T is the time difference between the front and rear of the train passing the photoelectric sensor.

[0104] Through the above embodiments, it can be understood that the present invention also takes train speed as a parameter for analyzing the piston wind effect, fully considers the influence of train speed on the piston wind effect, and takes train speed as an important parameter for analyzing the piston wind effect, which helps to comprehensively analyze and control the influence of piston wind.

[0105] Based on the above embodiment, the method further includes:

[0106] Each target piston wind parameter is input into the pre-trained piston wind parameter prediction model to obtain the predicted value of each target piston wind parameter at a future time.

[0107] In the embodiment of the present invention, the piston wind parameter prediction model adopts the LSTM long short-term memory neural network model, which consists of an input gate, a forget gate, and an output gate. The expression of the input gate is as follows:

[0108] I t =σ(W i X+b i ) (7);

[0109] Where, I t is the input gate; σ is the sigmoid function; W i is the input gate weight matrix; b i is the input gate bias; X is the target piston wind parameter at time t, which is one of wind speed, wind pressure, wind direction, temperature and humidity, and vehicle speed.

[0110] The expression of the forget gate is as follows:

[0111] F t =σ(W f X+b f ) (8);

[0112] Where, Ft For the forget gate; W f is the forget gate weight matrix; b f Bias for the forget gate.

[0113] The expression of the output gate is as follows:

[0114] O t =σ(W o X+b o ) (9);

[0115] Where, O t is the output gate; W o is the output gate weight matrix; b o Bias for the output gate.

[0116] The present invention predicts the piston wind parameters for a period of time in the future based on the current piston wind parameters, so that the changing trend of the piston wind parameters over time can be understood in advance. Potential problems can be discovered in time through abnormal values ​​in the prediction results, so that the operating status of the train or the equipment in the tunnel can be adjusted in time to improve the safety of train operation.

[0117] Based on the same inventive concept, a subway tunnel piston wind parameter monitoring system is provided. Figure 2 As shown, the system includes: multiple environmental sensors 201, photoelectric sensors 202, data isolation module 203, data acquisition module 204, local display module 205, PLC processing module 206 and industrial computer 207; wherein:

[0118] Multiple environmental sensors 201 are installed at local locations within the tunnel to collect multiple environmental data at the local locations and send the collected multiple environmental data to the data isolation module 203; the multiple environmental data include at least temperature and humidity, wind speed, wind direction, and wind pressure;

[0119] In an embodiment of the present invention, for example, a group of environmental sensors 201 and photoelectric sensors 202 are set at the entrance, exit, and approximately every 100 meters between the entrance and exit of the interval tunnel. Each group of environmental sensors 201 includes at least a wind speed sensor, a wind pressure sensor, a wind direction sensor, and a temperature and humidity sensor.

[0120] The data isolation module 203 is used to separate the various environmental data into two data paths, one path is sent to the data acquisition module 204, and the data acquisition module 204 is used to convert the various environmental data into analog and digital data and transmit them to the local display module 205 for display; the other path is sent to the PLC processing module 206.

[0121] The data isolation module 203 can copy the collected environmental data into two copies and transmit them through two paths respectively. Data isolation can reduce data conflicts and competitions and improve the stability of the system.

[0122] The photoelectric sensor 202 is used to collect the switching signal when a train passes by and send the switching signal to the PLC processing module 206.

[0123] On the one hand, the PLC processing module 206 is used to calculate the train speed based on the switch signal and send the train speed to the local display module 205 for display; on the other hand, it is used to send the train speed and various environmental data as local piston wind parameters to the industrial computer 207.

[0124] In the embodiment of the present invention, the PLC processing module 206 includes a PLC input unit 2061, a PLC vehicle speed piston wind parameter determination module 2072 and a PLC output unit 2063;

[0125] PLC input unit 2061, used to convert various environmental data into PLC digital quantities;

[0126] The PLC speed piston wind parameter determination module 2072 stores a speed calculation program for calculating the train speed based on the switch signal; Figure 3 As shown, a circuit operation diagram of the photoelectric sensor 202 and the PLC vehicle speed calculation module is given.

[0127] Figure 3 The "+" and "-" are respectively the positive and negative of the 24V power supply interface of the device, "com" is the switch signal when the front of the train passes the photoelectric sensor 202; "out" is the switch signal when the rear of the train passes the photoelectric sensor 202, "M" is the common negative pole of the PLC switch signal, and "I0.0" is the input of the switch signal.

[0128] The working principle of calculating the vehicle speed is as follows: when the front of the train passes the photoelectric sensor 202, the photoelectric sensor 202 will send a high-level signal and transmit the signal to the PLC vehicle speed piston wind parameter determination module 2072. The PLC vehicle speed piston wind parameter determination module 2072 starts timing at this time. When the rear of the train passes the photoelectric sensor 202, the high level becomes a low level. At this time, the timing of the PLC piston wind parameter determination module 2072 ends. The timing accuracy is in milliseconds. The speed of the train is the train length divided by the time difference between the start and end of the PLC timing.

[0129] The PLC output module is used to transmit various digital environmental data and calculated vehicle speed to the industrial computer 207 for storage based on the 485 interface using the MODBUS RTU protocol, and to send the vehicle speed to the local display module 205 in the form of analog quantity.

[0130] The industrial control computer 207 is used to calculate the piston wind parameters of other positions in the interval tunnel based on the local piston wind parameters, and use the local piston wind parameters and the piston wind parameters of other positions as target piston wind parameters.

[0131] In an embodiment of the present invention, the piston wind parameters at other locations in the interval tunnel can be calculated based on the local piston wind parameters by referring to the method in the above example, such as through fluid flow model, regression model, correlation model, etc., which will not be repeated here.

[0132] In an embodiment of the present invention, data transmission can be carried out between the sensor and the data isolation module 203, the data isolation module 203 and the data acquisition module 204, the data acquisition module 204 and the local display module 205, and the data isolation module 203 and the PLC processing module 206, and the PLC and the industrial computer 207 by wired or wireless means, and the wireless means include but are not limited to Wi-Fi and 4G / 5G networks.

[0133] Based on the above embodiment, the industrial computer 207 is further used to input each target piston wind parameter into a pre-trained piston wind parameter prediction model to obtain a predicted value of each target piston wind parameter in the future.

[0134] Based on the above embodiment, the industrial computer 207 includes a data storage module 2071 and a piston wind parameter determination module 2072. The reading and writing speed of the data storage module 2071 is greater than the environmental data acquisition speed.

[0135] When a train passes through a facility, the surrounding environment changes dramatically within a short period of time, and environmental data changes rapidly. If the read and write speed of data storage module 2071 is too slow, it will not be able to accurately capture piston wind and pressure changes. Therefore, by setting the read and write speed of data storage module 2071 to be faster than the environmental data collection speed, the read and write speed is in the millisecond range, which can accurately capture environmental changes in the tunnel.

[0136] In one example, Figure 4 A workflow diagram of the industrial computer data storage module 2071 is given. The data storage module 2071 is configured with a master station sensor receiving unit, an SQL database storage unit, an ODBC interface and a database. First, the master station sensor program in the station sensor receiving unit receives temperature, humidity, wind speed, wind direction, pressure and vehicle speed. Then, the SQL database storage program in the SQL database storage unit stores the data received by the master station in the database via the ODBC (Open Database Connectivity) interface.

[0137] like Figure 5 As shown, the piston wind parameter determination module 2072 can perform correlation analysis, multivariate linear regression analysis, flow analysis and piston wind parameter prediction on the piston wind parameters.

[0138] Based on the same technical concept, an embodiment of the present invention further provides an electronic device, such as Figure 6 As shown, it includes a processor 601 , a communication interface 602 , a memory 603 and a communication bus 604 , wherein the processor 601 , the communication interface 602 , and the memory 603 communicate with each other via the communication bus 604 .

[0139] Memory 603, used for storing computer programs;

[0140] The processor 601 is configured to implement the steps of the method for determining piston wind parameters in a subway tunnel when executing the program stored in the memory 603 .

[0141] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0142] The communication interface is used for communication between the above electronic device and other devices.

[0143] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0144] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0145] The computer program product for determining the piston wind parameters of a subway tunnel provided in an embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be found in the method embodiment and will not be repeated here.

[0146] The modules in the subway tunnel section piston wind parameter monitoring system provided by the embodiment of the present invention can be specific hardware on the device or software or firmware installed on the device. The system provided by the embodiment of the present invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference can be made to the corresponding content in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0147] In the embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some communication interface, device or unit, which may be electrical, mechanical or other forms.

[0148] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0149] In addition, each functional unit in the embodiment provided by the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0150] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0151] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0152] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. However, such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. They should all be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for determining piston wind parameters in a subway tunnel, characterized in that: The method comprises: Obtain piston wind parameters collected by multiple sensors installed at local locations of the interval tunnel; the piston wind parameters include at least wind speed and wind pressure; Based on the fluid flow model, the wind speed and wind pressure at other locations of the interval tunnel are determined according to the wind speed and wind pressure collected at the local location; wherein the other locations are locations in the interval tunnel where no sensors are installed; Inputting the wind speed and wind pressure at other locations into a pre-trained regression model for regression prediction to obtain other piston wind parameters related to the wind speed and wind pressure; The piston wind parameters collected in real time at a local position and the piston wind parameters at other positions obtained through the fluid flow model and the regression model are jointly determined as the target piston wind parameters of the tunnel in this section.

2. The method according to claim 1, characterized in that: The training process of the regression model includes: Acquire historical piston wind parameters; the historical piston wind parameters at least include wind speed and wind pressure; Determine other piston wind parameters related to the wind speed and wind pressure through a correlation model; The wind speed, wind pressure and other piston wind parameters related thereto are input as training data into the regression model to be trained for iterative training to optimize the model parameters and obtain a regression model with minimum loss. The expression of the regression model is: Y=β0+β1X1+β2X2+…+βnX Among them, X1, X2, X n are the independent variables, i.e. wind speed, wind pressure and other piston wind parameters related to them; Y is the dependent variable, i.e. other piston wind parameters related to wind speed and wind pressure that are predicted; β0 is the intercept; β1, β2, β n is the regression coefficient.

3. The method according to claim 2, characterized in that The other piston wind parameters related to the wind speed and wind pressure determined by the correlation model include: Calculate the correlation coefficients of other piston wind parameters with the wind speed and wind pressure respectively based on the Pearson correlation coefficient model; the other piston wind parameters include at least temperature and humidity, vehicle speed, and wind direction; Comparing each calculated correlation coefficient with a preset correlation coefficient threshold; Other piston wind parameters that are greater than or equal to the preset correlation coefficient threshold are determined as piston wind parameters related to the wind speed and wind pressure.

4. The method according to claim 1, characterized in that: The piston wind parameter also includes vehicle speed, and the process of determining the vehicle speed includes: The photoelectric sensor installed in the section tunnel collects the first switch signal and the second switch signal when the train head and the parking space pass through the photoelectric sensor; The time difference between the two switching quantity signals is calculated based on the first switching quantity signal and the second switching quantity signal; the calculation formula is: T=Tb-T a a The train speed is calculated based on the time difference and the train length, and the calculation formula is: Among them, T b is the time when the rear of the train passes the photoelectric sensor, in seconds; T is the time when the front of the train passes the photoelectric sensor, in seconds; V t is the train speed, in m / s; L t is the length of the train, in meters; T is the time difference between the front and rear of the train passing the photoelectric sensor.

5. The method according to claim 1, characterized in that The method further comprises: The target piston wind parameters are respectively input into the pre-trained piston wind parameter prediction model to obtain the predicted values ​​of the target piston wind parameters at a future time.

6. A subway section tunnel piston wind parameter monitoring system, characterized in that: The system includes: multiple environmental sensors, photoelectric sensors, data isolation modules, data acquisition modules, local display modules, PLC processing modules and industrial computers; The multiple environmental sensors are installed at local locations in the section tunnel, and are used to collect multiple environmental data at the local locations, and send the collected multiple environmental data to the data isolation module; the multiple environmental data at least include temperature and humidity, wind speed, wind direction and wind pressure; The data isolation module is used to separate the various environmental data into two paths of data, one path is sent to the data acquisition module, and the data acquisition module is used to perform analog-to-digital conversion on the various environmental data and transmit it to the local display module for display; the other path is sent to the PLC processing module; The photoelectric sensor is used to collect the switch signal when the train passes by, and send the switch signal to the PLC processing module; The PLC processing module is used, on the one hand, to calculate the train speed according to the switch signal and send the train speed to the local display module for display; on the other hand, it is used to send the train speed and various environmental data as local piston wind parameters to the industrial computer; The industrial computer is used to calculate the piston wind parameters of other positions in the interval tunnel according to the local piston wind parameters, and use the local piston wind parameters and the piston wind parameters of other positions as target piston wind parameters.

7. The system according to claim 6, characterized in that The industrial computer is also used to input each of the target piston wind parameters into a pre-trained piston wind parameter prediction model to obtain a predicted value of each target piston wind parameter at a future time.

8. The system according to claim 6, characterized in that The industrial computer comprises a data storage module and a piston wind parameter determination module, and the reading and writing speed of the data storage module is greater than the environmental data acquisition speed.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 5 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 5 are implemented.

Images