Control method and system for tunnel energy-saving ventilation based on fuzzy control

Abstract

The present application provides a control method and system for tunnel energy-saving ventilation based on fuzzy control, which relates to the technical field of tunnel ventilation. The method comprises: obtaining vehicle flow data in the current tunnel; obtaining predicted pollutant concentrations corresponding to the vehicle flow data and predicted required air volume corresponding to the predicted pollutants based on a traffic flow prediction model and a pollution diffusion model; inputting the predicted pollutant concentrations and predicted required air volume into the fuzzy control model to obtain the number of fans required for the current tunnel, thereby improving ventilation efficiency, reducing resource loss, improving road safety, and reducing operation and maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel energy saving, and in particular to a control method and system for tunnel energy-saving ventilation based on fuzzy control. Background Art

[0002] With the acceleration of urbanization, the number of tunnel construction has increased significantly, especially in the construction of long highway tunnels. Vehicles will emit a large amount of pollutants when driving in long tunnels, affecting health and driving safety. In order to ensure the timely discharge of harmful gases, it is necessary to accurately grasp the concentration of pollutants to regulate the operation of fans. However, there is a time delay in sensor detection and data transmission in the tunnel, and the dynamic changes in traffic flow are significantly random and unpredictable, which brings challenges to real-time control.

[0003] The inventors found in their research that the current fan control strategies are divided into direct, indirect and automatic control. Direct control relies on sensor data, but the information is delayed and easily disturbed, and the resource utilization efficiency is low. Although indirect control can respond to ventilation needs, the control rules are rough and do not precisely correlate pollutant concentration with fan operation. Automatic control faces the difficulty of improving model complexity and prediction accuracy, especially for the treatment of nonlinear and time-varying pollutant characteristics in tunnels. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a control method and system for tunnel energy-saving ventilation based on fuzzy control, so as to improve ventilation efficiency, reduce resource loss, improve road safety, and reduce operation and maintenance costs.

[0005] In a first aspect, the present invention provides a control method for tunnel energy-saving ventilation based on fuzzy control, comprising:

[0006] Get the traffic flow data in the current tunnel;

[0007] Based on the traffic flow prediction model and the pollution diffusion model, the predicted pollutant concentration corresponding to the vehicle flow data and the predicted required air volume corresponding to the predicted pollutants are obtained;

[0008] The predicted pollutant concentration and predicted required air volume are input into the fuzzy control model to obtain the number of fans required for the current tunnel.

[0009] Optionally, based on the traffic flow prediction model and the pollution diffusion model, the predicted pollutant concentration corresponding to the vehicle flow data is obtained, including:

[0010] Inputting the traffic flow data into the traffic flow prediction model to obtain predicted traffic flow data, wherein the predicted traffic flow data is the traffic flow data for the next cycle;

[0011] The predicted traffic flow data is input into the pollution diffusion model to obtain predicted pollutant concentrations, wherein the predicted pollutant concentrations include a first pollutant concentration and a second pollutant concentration.

[0012] Optionally, the predicted traffic flow data is input into a pollution diffusion model to obtain predicted pollutant concentrations, including:

[0013] Inputting the predicted traffic flow data into a first pollutant model to obtain a first pollutant concentration;

[0014] The predicted traffic flow data is input into a second pollutant model to obtain a second pollutant concentration.

[0015] Optionally, based on the traffic flow prediction model and the pollution diffusion model, the predicted required air volume corresponding to the predicted pollutants corresponding to the vehicle flow data is obtained, including:

[0016] Inputting the first pollutant concentration into a first required air volume model to obtain a first required air volume;

[0017] The second pollutant concentration is input into the second required air volume model to obtain the second required air volume.

[0018] Optionally, the predicted pollutant concentration and the predicted required air volume are input into the fuzzy control model to obtain the number of fans required for the current tunnel, wherein the predicted required air volume includes a first required air volume and a second required air volume, including:

[0019] Determining a first predicted concentration deviation value and a first designed concentration deviation value of the first pollutant concentration based on the first pollutant concentration;

[0020] Determining a second predicted concentration deviation value and a second designed concentration deviation value of the second pollutant concentration based on the second pollutant concentration;

[0021] Inputting a first predicted concentration deviation value, a first designed concentration deviation value and a first required air volume into a fuzzy control model to obtain a first required number of fans;

[0022] Inputting the second predicted concentration deviation value, the second designed concentration deviation value and the second required air volume into the fuzzy control model to obtain the second required number of fans;

[0023] The number of fans required for the current tunnel is determined based on the first required number of fans and the second required number of fans.

[0024] Optionally, the method further comprises:

[0025] Get the current pollutant concentration in the current tunnel;

[0026] The current pollutant concentration is input into the fuzzy control model to determine the current number of fans required for the current pollutant concentration.

[0027] Optionally, the traffic flow prediction model is trained according to the following steps:

[0028] Obtaining a historical data set, the historical data set including pollutant concentrations and required air volumes corresponding to the pollutant concentrations;

[0029] Based on the historical data set, the initial traffic flow prediction model is iteratively trained until the predicted number of iterations is reached to obtain the target traffic flow prediction model. Each iterative training includes: inputting the historical data set into the initial traffic prediction model to obtain the initial determination coefficient value; optimizing the convergence factor in the GWO algorithm based on the determination coefficient difference and the inverse tangent function to obtain the OGWO algorithm; optimizing the individuals in the OGWO algorithm based on the differential evolution algorithm to obtain the OGWO-DE algorithm; optimizing the learning rate and shrinkage factor in the traffic flow prediction model based on the OGWO-DE algorithm, and obtaining the target determination coefficient value using the optimized traffic flow prediction model; obtaining the target determination coefficient difference based on the initial determination coefficient and the target determination coefficient; and updating the initial traffic prediction model according to the target determination coefficient difference, the optimized learning rate and shrinkage factor.

[0030] The second invention, the present invention provides a control system for tunnel energy-saving ventilation based on fuzzy control, comprising:

[0031] An acquisition module is used to obtain the traffic flow data in the current tunnel;

[0032] A prediction module is used to obtain the predicted pollutant concentration corresponding to the vehicle flow data and the predicted required air volume corresponding to the predicted pollutants based on the traffic flow prediction model and the pollution diffusion model;

[0033] The decision module is used to input the predicted pollutant concentration and the predicted required air volume into the fuzzy control model to obtain the number of fans required for the current tunnel.

[0034] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned fuzzy control-based tunnel energy-saving ventilation control method when executing the computer program.

[0035] In a fourth aspect, the present invention further provides a computer-readable storage medium storing machine executable instructions, which, when called and executed by a processor, implement the above-mentioned control method for tunnel energy-saving ventilation based on fuzzy control.

[0036] The present invention provides a control method and system for tunnel energy-saving ventilation based on fuzzy control, which obtains the vehicle flow data in the current tunnel; based on the traffic flow prediction model and the pollution diffusion model, obtains the predicted pollutant concentration corresponding to the vehicle flow data and the predicted air volume required corresponding to the predicted pollutants; inputs the predicted pollutant concentration and the predicted air volume required into the fuzzy control model to obtain the number of fans required for the current tunnel, thereby improving ventilation efficiency, reducing resource loss, improving road safety, and reducing operation and maintenance costs.

[0037] 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

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A flow chart of a control method for tunnel energy-saving ventilation based on fuzzy control provided by an embodiment of the present invention is shown;

[0040] Figure 2 A curve chart showing vehicle flow data provided by an embodiment of the present invention is shown;

[0041] Figure 3 A schematic diagram of the structure of a fuzzy controller provided by an embodiment of the present invention is shown;

[0042] Figure 4 A flow chart showing another method for controlling tunnel energy-saving ventilation based on fuzzy control provided by an embodiment of the present invention;

[0043] Figure 5 A schematic structural diagram of a tunnel energy-saving ventilation control system based on fuzzy control provided by an embodiment of the present invention is shown;

[0044] Figure 6 A schematic structural diagram of an electronic device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0045] 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 here 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 belong to the scope of protection of the present invention.

[0046] The following are explanations of some terms in the present invention:

[0047] Traffic volume: refers to the total number of vehicles passing through a specific road section or area within a specific period of time. Traffic volume reflects the actual number of vehicles existing or passing on the road.

[0048] Traffic flow: refers to the overall flow of vehicles and pedestrians in an area within a certain period of time, including but not limited to benchmark vehicles, number of vehicles, traffic flow, vehicle speed, vehicle density coefficient, vehicle condition coefficient, number of vehicle types, vehicle type coefficient, etc.

[0049] Traffic prediction flow model: Traffic flow characteristics can be used to predict traffic flow and provide data support for subsequent calculation of pollutant concentrations.

[0050] KTBoost: Enhances the performance of the prediction model by combining regression trees and ridge regression functions in reproducing kernel Hilbert space (RKHS) (i.e., the posterior mean of the Gaussian process) in each round of boosting iteration. The purpose of this algorithm is to take advantage of the advantages of regression trees on discontinuous functions and complex decision boundaries, and the advantages of RKHS regression functions on continuous functions and smoothness, thereby achieving a more comprehensive and accurate fit to the data.

[0051] OGWO (Optimized Grey Wolf Optimization): A heuristic optimization algorithm based on the social behavior model of grey wolves. This algorithm simulates the coordination and cooperation behavior of grey wolf populations and the group intelligence they display when searching for prey. Based on this, the OGWO algorithm introduces optimization strategies to solve some problems existing in the GWO (Grey Wolf Optimization) algorithm, such as premature convergence and low convergence accuracy, so as to improve the solution accuracy and convergence speed of the algorithm.

[0052] Fuzzy Control: also known as Fuzzy Logic Control, is a computer digital control technology based on fuzzy set theory, fuzzy language variables and fuzzy logic reasoning. The core of fuzzy control is to imitate human fuzzy reasoning and decision-making process to deal with and solve the fuzziness and uncertainty problems existing in complex systems.

[0053] Aerodynamic model: The main function of this model is to obtain airflow velocity and provide data support for subsequent calculation of pollutants.

[0054] Pollutant diffusion model: This model is mainly used to calculate the pollutant concentration in the tunnel. Changes in the air flow velocity in the tunnel and the pollutant emissions under different traffic flows will cause changes in the pollutant concentration.

[0055] Fan control model: This model performs fuzzy reasoning on pollutant concentrations to calculate the appropriate number of fans to be opened, thereby achieving energy-saving control of tunnel ventilation.

[0056] Figure 1 The present invention provides a flow chart of a method for controlling tunnel energy-saving ventilation based on fuzzy control. Figure 1 As shown, the method comprises the following steps:

[0057] Step S110: Obtain the traffic flow data in the current tunnel.

[0058] The timestamp data of each sensor installed in the tunnel is obtained, and the vehicle data within the time characteristics of week / day / hour / minute are extracted from the timestamp, which is the traffic flow data.

[0059] Specifically, Figure 2 As shown in the figure, the horizontal axis is the minute value of each day, and the vertical axis is the traffic volume. The daily traffic volume in the tunnel is basically in the range of 50 to 800 vehicles. The lowest peak is around 4 a.m., when the traffic volume is about 60 vehicles per minute; the highest peak is around 13:00 noon, when the traffic volume is about 780 vehicles per minute.

[0060] Step S120: Based on the traffic flow prediction model and the pollution diffusion model, the predicted pollutant concentration corresponding to the vehicle flow data and the predicted required air volume corresponding to the predicted pollutants are obtained.

[0061] In an optional embodiment, based on the traffic flow prediction model and the pollution diffusion model, the predicted pollutant concentration corresponding to the vehicle flow data is obtained, which also includes:

[0062] Inputting the traffic flow data into the traffic flow prediction model to obtain predicted traffic flow data, wherein the predicted traffic flow data is the traffic flow data for the next cycle;

[0063] The predicted traffic flow data is input into the pollution diffusion model to obtain predicted pollutant concentrations, wherein the predicted pollutant concentrations include a first pollutant concentration and a second pollutant concentration.

[0064] Among them, the acquired vehicle flow data is input into the traffic flow prediction model to obtain the traffic flow data of the next cycle, and the traffic flow data of the next cycle is input into the pollution diffusion model to obtain the predicted pollutant concentration in the future. Based on the predicted pollutant concentration, the working number of tunnel fans can be predicted in advance, thereby effectively reducing the frequency of fan startup, improving control accuracy, and meeting the energy-saving goals.

[0065] In an optional embodiment, the traffic flow prediction model is trained according to the following steps:

[0066] Obtaining a historical data set, the historical data set including pollutant concentrations and required air volumes corresponding to the pollutant concentrations;

[0067] Based on the historical data set, the initial traffic flow prediction model is iteratively trained until the predicted number of iterations is reached to obtain the target traffic flow prediction model. Each iterative training includes: inputting the historical data set into the initial traffic prediction model to obtain the initial determination coefficient value; optimizing the convergence factor in the GWO algorithm based on the determination coefficient difference and the inverse tangent function to obtain the OGWO algorithm; optimizing the individuals in the OGWO algorithm based on the differential evolution algorithm to obtain the OGWO-DE algorithm; optimizing the learning rate and shrinkage factor in the traffic flow prediction model based on the OGWO-DE algorithm, and obtaining the target determination coefficient value using the optimized traffic flow prediction model; obtaining the target determination coefficient difference based on the initial determination coefficient and the target determination coefficient; and updating the initial traffic prediction model according to the target determination coefficient difference, the optimized learning rate and shrinkage factor.

[0068] Furthermore, a traffic flow prediction model is constructed using a KTBoost model that takes pollutant concentration as input and the required air volume corresponding to the pollutant concentration as output, and sets parameters such as the learning rate, the number and depth of decision trees, the loss function, and the minimum number of samples of the KTBoost model.

[0069] Based on the historical data set, the GWO algorithm is constructed and relevant parameters such as population size and maximum number of iterations are set;

[0070] Initialize the DE (Differential Evolution) population, and set each individual in the differential evolution algorithm as a set of parameters of the KTBoost model. In this application, the parameters are the learning rate and the shrinkage factor, and set the relevant parameters of the differential evolution algorithm, such as the mutation factor and the crossover probability.

[0071] Furthermore, the OGWO-DE algorithm is used to train the KTBoost model to obtain the target traffic flow prediction model. The specific training process is as follows:

[0072] Firstly, the historical data set is input into the initial KTBoost model to obtain the initial determination coefficient value. Based on the determination coefficient difference and the inverse tangent function, the convergence factor in the GWO algorithm is optimized to obtain the OGWO algorithm, thereby increasing the global search capability.

[0073] In order to maintain the convergence factor value in the interval (0,2), the inverse tangent function is used. The inverse tangent function is a monotonically increasing function in the interval (0,1) when the independent variable is in the interval (0,+∞). The inverse tangent function is multiplied by a coefficient value of 2.53 to ensure that the convergence factor value is in the interval (0,2); the initial value of the random value is set to 0.01, and the random value is set to 1 when the number of iterations is a multiple of 3. By adaptively setting the range of random values, excessive aggregation at the initial position is avoided, and the diversity of the algorithm search path is increased, so that the GOW algorithm has the ability to jump out of the local optimum to a certain extent, and the possibility of the GOW algorithm finding the global optimal solution is increased. The algorithm for optimizing the convergence factor of the GOW algorithm is:

[0074]

[0075] Where a is the convergence factor, suba is the determination coefficient value, i is the number of iterations of the convergence factor, and random is a random value.

[0076] Secondly, based on the differential evolution algorithm, the individuals in the OGWO algorithm are optimized to obtain the OGWO-DE algorithm, thereby accelerating the convergence speed.

[0077] The candidate solutions obtained by the OGWO algorithm are optimized using the mutation, crossover and selection operations of differential evolution: in the mutation operation, three individuals are selected, which do not include the current individual, and a new candidate solution is generated using the mutation factor; in the crossover operation, it is determined whether the new candidate solution crosses with the current individual to generate a new individual based on the crossover probability; in the selection operation, the fitness of the generated new individual is compared with that of the original individual, and the individual with higher fitness is retained as the individual in the next iteration until the iteration ends. In this application, the fitness is the determination coefficient value.

[0078] Then, the learning rate and shrinkage factor in the traffic flow prediction model are optimized based on the OGWO-DE algorithm, and the target determination coefficient value is obtained using the optimized traffic flow prediction model.

[0079] Based on the OGWO-DE algorithm, the learning rate and the shrinkage factor in the initial KTBoost model are updated to obtain the target learning rate and the target shrinkage factor, and based on the target learning rate and the target shrinkage factor, the target KTBoost model is obtained. The target determination coefficient is calculated using the target KTBoost model.

[0080] Finally, based on the initial determination coefficient and the target determination coefficient, the target determination coefficient difference is obtained; and the initial traffic prediction model is updated according to the target determination coefficient difference, the optimized learning rate and the shrinkage factor.

[0081] Based on the initial determination coefficient and the target determination coefficient, the target determination coefficient difference is obtained; based on the target determination coefficient difference, the GWO algorithm is optimized to obtain the OGWO-DE algorithm, and the OGWO-DE algorithm is used to optimize the KTBoost model with the target learning rate and the target shrinkage factor until the number of iterations reaches the preset number of iterations. The target KTBoost model outputted for the last time is the traffic flow prediction model.

[0082] The traffic flow prediction model optimizes the convergence factor in the Grey Wolf Algorithm based on the inverse tangent function, the difference in determination coefficient and the differential evolution algorithm, which not only increases the global search capability but also accelerates the convergence speed, thereby improving its optimization efficiency within the effective iteration. The optimized OGWO-DE algorithm is then used to fine-tune the KTBoost model parameters, thereby enhancing the prediction accuracy of the combined model, as well as its adaptability and prediction ability for complex traffic flow data.

[0083] In an optional embodiment, the predicted traffic flow data is input into a pollution diffusion model to obtain a predicted pollutant concentration, including:

[0084] Inputting the predicted traffic flow data into a first pollutant model to obtain a first pollutant concentration;

[0085] The predicted traffic flow data is input into a second pollutant model to obtain a second pollutant concentration.

[0086] Among them, the present invention mainly deals with the two pollutant concentrations of CO (carbon monoxide) and VI (smoke) with high content in the tunnel. The first pollutant concentration is CO, and the second pollutant concentration is VI. In a long highway tunnel, the CO concentration that humans can withstand is 100ppm, and the residence time should not exceed 15 minutes. Therefore, it is necessary to calculate the emission of CO in the tunnel through the first pollutant model, and the first pollutant model is specifically:

[0087]

[0088] In the formula, Q co is the total CO emission in the tunnel (the first pollutant concentration), qco is the CO benchmark vehicle, f a is the vehicle condition coefficient. The value of expressways and first-class highways is generally 1.0. d is the vehicle density coefficient, f h is the altitude coefficient, f iv is the longitudinal slope-vehicle speed coefficient, L is the tunnel length, n is the number of vehicle types, N m is the design traffic volume of the corresponding vehicle type, f m is the model coefficient.

[0089] Furthermore, vehicle drivers mainly observe the surrounding environment through their eyes while driving. When the tunnel smoke formed by automobile exhaust interferes with the driver's visual cognition, it will be difficult for the driver to avoid obstacles in time, thus posing a threat to the driver's personal safety. In the latest regulations, the design concentration of smoke in the tunnel is shown in Table 1-1:

[0090] Table 1-1 VI design concentration

[0091] Vehicle speed (km / m) 100 80 60 40 <![CDATA[K(m -1 )]]> 0.0065 0.007 0.0075 0.009

[0092] Therefore, in a standard tunnel environment, the distance that the driver looks straight ahead is 60 to 160 meters, and the perception range of both eyes is about 100 degrees to the left and right, 50 degrees upward, and 75 degrees downward. However, the emission of VI will affect the driver's field of vision and reduce the accuracy of identifying obstacles to a certain extent. Therefore, it is necessary to calculate the emission of VI in the tunnel through the second pollutant model. The specific second pollutant model is:

[0093]

[0094] In the formula, Q VI is the smoke emission (second pollutant concentration), q VI is the smoke baseline emission vehicle, n D is the vehicle category coefficient.

[0095] In an optional embodiment, based on the traffic flow prediction model and the pollution diffusion model, the predicted required air volume corresponding to the predicted pollutants corresponding to the vehicle flow data is obtained, and the predicted required air volume includes a first required air volume and a second required air volume, including:

[0096] Inputting the first pollutant concentration into a first required air volume model to obtain a first required air volume;

[0097] The second pollutant concentration is input into the second required air volume model to obtain the second required air volume.

[0098] Specifically, the first required air volume to dilute CO to the national standard control air quality can be calculated through CO emissions, so as to achieve effective early warning and timely ventilation of the CO environment and ensure the safety of drivers and passengers. The first required air volume model is specifically:

[0099]

[0100] In the formula, Q req(co) is the required air volume for dilution tunnel (the first required air volume), δ is the design concentration of CO, P0 is the standard atmospheric pressure, P is the design air pressure of the tunnel, T is the design air temperature of the tunnel, and T0 is the standard temperature.

[0101] The second required air volume model is used to obtain the second required air volume, so that smoke can be discharged in time, ensuring that the driver can accurately grasp the road traffic status, take correct operating steps for sudden changes, and make timely judgments. The second required air volume model is specifically as follows:

[0102]

[0103] In the formula, Q req(VI) The air volume required to dilute VI (the second required air volume), K is the VI design concentration.

[0104] Furthermore, in order to ensure safe passage, it is necessary to ensure that the pollutants in the tunnel meet the standard requirements to the greatest extent possible. Therefore, in general, the CO air volume requirement and the VI air volume requirement are compared, and the larger value is taken as the final air volume requirement of the tunnel. The calculation formula for the final air volume requirement is as follows:

[0105] Q req =max{Q req(co) ,Q req(VI)}

[0106] Step S130: input the predicted pollutant concentration and the predicted required air volume into the fuzzy control model to obtain the number of fans required for the current tunnel.

[0107] In an optional embodiment, the fuzzy control model is an OGKT-AFSA fuzzy control model.

[0108] like Figure 3 As shown, the fuzzy control model structure includes fuzzification, fuzzy reasoning, clarification, a controlled object and a sensor system, wherein fuzzification, fuzzy reasoning and clarification constitute a fuzzy controller.

[0109] Specifically, fuzzification includes selecting the linguistic variables of the fuzzy controller and designing the fuzzy domain of each variable. Among them, the linguistic variables of the fuzzy controller are selected as three linguistic variables, namely, pollutant prediction deviation (E), pollutant measured deviation (), and the number of fans turned on (U), where E and E are input variables and U is the output variable; the fuzzy domain of each variable is designed, including the CO fuzzy controller, the discrete domain of CO prediction concentration deviation is defined as: {-6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6} The discrete domain of CO measured concentration deviation is defined as: {-6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6} In practical applications, the continuous value range of CO prediction deviation is [-6, 6], the continuous value range of CO measured deviation is [-30, 30], and the quantization factors are 1 and 0.2 respectively. In order to obtain sufficient similarity, it is necessary to determine an appropriate number of discrete domains. When the number is too large, it is easy to increase the complexity.

[0110]

[0111] Where: K e is the prediction bias; K e′ is the measured deviation; m and n are the value ranges of the predicted deviation and the measured deviation respectively; e H is the highest value; e L is the lowest value.

[0112] According to actual needs, the domain is divided into seven levels, namely NB (negative large), NM (negative medium), NS (negative small), O (zero), PS (positive small), PM (positive medium), and PB (positive large).

[0113] The knowledge base records all the data and rules in fuzzification, defuzzification, and reasoning mechanisms. The database mainly stores the domains related to input and output variables, membership functions, definitions of corresponding fuzzy subsets, and necessary data for implementing fuzzy reasoning, etc. Among them, fuzzy control rules are very important, and the determination of their establishment methods is very critical. In the tunnel ventilation control system, when the predicted concentration of input pollutants is very high and the measured concentration is very high, the number of fans should be increased rapidly. This rule can be described as If E=PB and=PB Then U=PB. Similarly, other fuzzy rules can be established.

[0114] Fuzzy reasoning is to implement fuzzy reasoning operations for fuzzy input through relevant rules in the knowledge base, relevant data in the database and reasoning decision-making mechanisms, so as to obtain the output value of the fuzzy controller. After obtaining the fuzzy relationship, the fuzzy subsets on the known input variables are combined to obtain the fuzzy subsets of the output domain according to the reasoning synthesis rules;

[0115] The fuzzy output value obtained by fuzzy reasoning is actually a fuzzy subset, and the output fuzzy set is converted into an accurate output value, and the converted value can be input into the actuator of the controlled object. That is, the process of selecting a single value that best represents the fuzzy set from the fuzzy quantity is called clarification, and this determined single value can be used to control the actuator.

[0116] Fuzzy judgment adopts weighted average method, and the calculation formula is as follows:

[0117]

[0118] Where: u is the output value; n is the number of domain sets; x i is the domain point; μ(x i ) is x i The membership function value of .

[0119] Furthermore, the fuzzy control model is trained based on the AFSA (artificial fish swarm) algorithm. The specific process is as follows:

[0120] 3.1. Initialize the relevant parameters of the AFSA algorithm, including the target search space n is 2-dimensional, the number of artificial fish N is 100, the maximum number of iterations is 300, the maximum number of trials is 100, the patrol range is 1, the crowding factor is 0.5 and the step size is 0.1;

[0121] 3.2. Initialize the fish school: determine the variable range and number of variables, randomly select a position within the patrol range, the range of the random number is [-1,1], initialize the optimal independent variable bestX and the optimal function value bestY, and define the objective function in the AFSA algorithm;

[0122] 3.3. Operation iteration number gen: The behavior operation starts from the first artificial fish. The behavior operation is divided into clustering behavior and tail-chasing behavior. In the clustering function, the dist function for solving the Euclidean distance is mainly used to find the fish within the patrol range. If there is a fish within the patrol range, its center position is found and the fitness value of the point is calculated. Through these two behaviors, two positions can be obtained. The size is compared to determine which position is better. The larger value bestY is retained. After the behavior operation is performed on the remaining 99 artificial fish, the number of iterations is increased by 1;

[0123] 3.4. Start recording the optimal value Ymax: If Ymax>bestY, the larger value will be recorded, otherwise the original value will be retained;

[0124] 3.5. If the number of updates exceeds the maximum number of iterations, stop updating and obtain the optimal solution; otherwise, re-execute 3.3.

[0125] In an optional embodiment, the predicted pollutant concentration and the predicted required air volume are input into the fuzzy control model to obtain the number of fans required for the current tunnel, including:

[0126] Determining a first predicted concentration deviation value and a first designed concentration deviation value of the first pollutant concentration based on the first pollutant concentration;

[0127] Determining a second predicted concentration deviation value and a second designed concentration deviation value of the second pollutant concentration based on the second pollutant concentration;

[0128] Inputting a first predicted concentration deviation value, a first designed concentration deviation value and a first required air volume into a fuzzy control model to obtain a first required number of fans;

[0129] Inputting the second predicted concentration deviation value, the second designed concentration deviation value and the second required air volume into the fuzzy control model to obtain the second required number of fans;

[0130] The number of fans required for the current tunnel is determined based on the first required number of fans and the second required number of fans.

[0131] Specifically, taking the deviation as the pollutant concentration is an ideal performance indicator in the process of tunnel ventilation. However, the actual pollutant concentration read by the sensor is always lagging, and there is usually an error between the two. Therefore, in general, the error is defined as the input of the fuzzy controller.

[0132] Furthermore, the first predicted concentration deviation value can be obtained by subtracting the design concentration value from the CO predicted concentration value (the first pollutant concentration) as e co ;

[0133] The first design concentration deviation value e′ is obtained by subtracting the CO predicted concentration value (the first pollutant concentration) from the CO measured concentration value co ;

[0134] The second predicted concentration deviation value can be obtained by subtracting the design concentration value from the VI predicted concentration value (the second pollutant concentration) VI ;

[0135] The second design concentration deviation value e′ is obtained by subtracting the VI predicted concentration value (the second pollutant concentration) from the VI measured concentration value VI ;

[0136] The first predicted concentration deviation value, the first designed concentration deviation value and the first required air volume are input into the fuzzy control model to obtain the first required number of fans u co , where the first required number of fans u co The number of fans added or reduced in the CO fuzzy controller;

[0137] The second predicted concentration deviation value, the second designed concentration deviation value and the second required air volume are input into the fuzzy control model to obtain the second required number of fans u VI , where the second required number of fans u VI is the number of fans added or reduced in the VI fuzzy controller;

[0138] To u co and u VI Compare the two. If both are to increase the number of fans, the larger one is selected as the final result of increasing the number of fans; if both are to reduce the number of fans, the smaller one is selected as the final result of reducing the number of fans;

[0139] Finally, the number of fans output is averaged every 20 minutes and then rounded up to get the number of fans that need to be turned on, thereby realizing the operation of the fans.

[0140] In an optional embodiment, after the predicted pollutant concentration and the predicted required air volume are input into the fuzzy control model to obtain the number of fans required for the current tunnel, the following further comprises:

[0141] Get the current pollutant concentration in the current tunnel;

[0142] The current pollutant concentration is input into the fuzzy control model to determine the current number of fans required for the current pollutant concentration.

[0143] Specifically, turning on the fan will reduce the pollutant concentration in the tunnel. After detecting the pollutant concentration, the sensor will feed back the detection result (current pollutant concentration) to the fuzzy controller, and then combine it with the real-time predicted pollutant concentration and the designed pollutant concentration to obtain the input of the fuzzy controller, which will continue to be processed by the fuzzy controller to form a closed loop.

[0144] like Figure 4 As shown, the specific process of the control method of tunnel energy-saving ventilation based on fuzzy control of the present invention is as follows:

[0145] First, the predicted traffic flow is obtained through the traffic flow prediction model, and then the model is combined with the pollutant diffusion model to obtain the predicted pollutant concentration, which includes the CO predicted concentration and the VI predicted concentration;

[0146] Secondly, according to the predicted CO concentration, the predicted VI concentration, the designed concentration and the actual concentration, the predicted concentration deviation value and the designed concentration deviation value of CO and VI are obtained respectively;

[0147] Then, the predicted concentration deviation value and the design concentration deviation value of CO and VI are input into the fuzzy control, and the increase and decrease numbers of fans in the fuzzy controller of CO and VI are obtained respectively. If both increase the number of fans, the larger one of the two is selected as the final result of increasing the number of fans; if both reduce the number of fans, the smaller one of the two is selected as the final result of reducing the number of fans, and the output number of fans is averaged in units of 20 minutes, and then rounded up, so as to obtain the number of fans that need to be turned on, and realize the operation of the fans;

[0148] Finally, turning on the fan will reduce the pollutant concentration in the tunnel. After detecting the pollutant concentration, the sensor will immediately feed it back to the fuzzy controller. It will then be combined with the real-time predicted pollutant concentration and the designed pollutant concentration to obtain the input of the fuzzy controller, which will continue to be processed by the fuzzy controller, thus forming a closed loop.

[0149] The control method for tunnel energy-saving ventilation based on fuzzy control provided by the embodiment of the present invention has the following beneficial effects:

[0150] 1. In order to achieve real-time and accurate prediction of pollutant concentration in the tunnel and ensure that the fan group can respond to ventilation needs immediately, an OGWO-KTBoost traffic flow prediction model was constructed. This model optimizes the convergence factor of the Gray Wolf optimization algorithm to improve its optimization efficiency within effective iterations, and then uses the optimized OGWO algorithm to fine-tune the KTBoost model parameters, thereby enhancing the prediction accuracy of the combined model and its adaptability and prediction ability for complex traffic flow data;

[0151] 2. In order to build an efficient and energy-saving tunnel ventilation control system, the traffic flow prediction model, pollutant diffusion model and fuzzy controller are integrated, and the OGKT fuzzy controller is innovatively designed. By applying the AFSA algorithm to optimize the membership function of the fuzzy controller, its global search capability is significantly enhanced, thereby improving the overall control performance and efficiency, and effectively reducing the frequency of fan startup, meeting the energy-saving target, and showing excellent performance advantages.

[0152] Figure 5 The schematic diagram of the structure of a tunnel energy-saving ventilation control system based on fuzzy control provided by an embodiment of the present invention. Figure 5 As shown, the system mainly includes:

[0153] An acquisition module 210 is used to acquire the vehicle flow data in the current tunnel;

[0154] A prediction module 220, for obtaining predicted pollutant concentrations corresponding to vehicle flow data and predicted required air volume corresponding to predicted pollutants based on a traffic flow prediction model and a pollution diffusion model;

[0155] The decision module 230 is used to input the predicted pollutant concentration and the predicted required air volume into the fuzzy control model to obtain the number of fans required for the current tunnel.

[0156] In an optional embodiment, the prediction module 220 is further configured to:

[0157] Inputting the traffic flow data into the traffic flow prediction model to obtain predicted traffic flow data, wherein the predicted traffic flow data is the traffic flow data for the next cycle;

[0158] The predicted traffic flow data is input into the pollution diffusion model to obtain the predicted pollutant concentration.

[0159] In an optional embodiment, the prediction module 220 is further configured to:

[0160] Inputting the predicted traffic flow data into a first pollutant model to obtain a first pollutant concentration;

[0161] The predicted traffic flow data is input into a second pollutant model to obtain a second pollutant concentration.

[0162] In an optional embodiment, the prediction module 220 is further configured to:

[0163] Inputting the first pollutant concentration into a first required air volume model to obtain a first required air volume;

[0164] The second pollutant concentration is input into the second required air volume model to obtain the second required air volume.

[0165] In an optional embodiment, the decision module 230 is further configured to:

[0166] Determining a first predicted concentration deviation value and a first designed concentration deviation value of the first pollutant concentration based on the first pollutant concentration;

[0167] Determining a second predicted concentration deviation value and a second designed concentration deviation value of the second pollutant concentration based on the second pollutant concentration;

[0168] Inputting a first predicted concentration deviation value, a first designed concentration deviation value and a first required air volume into a fuzzy control model to obtain a first required number of fans;

[0169] Inputting the second predicted concentration deviation value, the second designed concentration deviation value and the second required air volume into the fuzzy control model to obtain the second required number of fans;

[0170] The number of fans required for the current tunnel is determined based on the first required number of fans and the second required number of fans.

[0171] In an optional embodiment, the decision module 230 is further configured to:

[0172] Get the current pollutant concentration in the current tunnel;

[0173] The current pollutant concentration is input into the fuzzy control model to determine the current number of fans required for the current pollutant concentration.

[0174] In an optional embodiment, the prediction module 2320 is further configured to:

[0175] Obtaining a historical data set, the historical data set including pollutant concentrations and required air volumes corresponding to the pollutant concentrations;

[0176] Based on the historical data set, the initial traffic flow prediction model is iteratively trained until the predicted number of iterations is reached to obtain the target traffic flow prediction model. Each iterative training includes: inputting the historical data set into the initial traffic prediction model to obtain the initial determination coefficient value; optimizing the convergence factor in the GWO algorithm based on the determination coefficient difference and the inverse tangent function to obtain the OGWO algorithm; optimizing the individuals in the OGWO algorithm based on the differential evolution algorithm to obtain the OGWO-DE algorithm; optimizing the learning rate and shrinkage factor in the traffic flow prediction model based on the OGWO-DE algorithm, and obtaining the target determination coefficient value using the optimized traffic flow prediction model; obtaining the target determination coefficient difference based on the initial determination coefficient and the target determination coefficient; and updating the initial traffic prediction model according to the target determination coefficient difference, the optimized learning rate and shrinkage factor.

[0177] The implementation principle and technical effects of the system provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0178] like Figure 6 As shown, an electronic device 600 provided in an embodiment of the present application includes: a processor 601, a memory 602 and a bus, the memory 602 stores machine-readable instructions executable by the processor 601, when the electronic device is running, the processor 601 communicates with the memory 602 through the bus, and the processor 601 executes the machine-readable instructions to perform the steps of the control method for tunnel energy-saving ventilation based on fuzzy control as mentioned above.

[0179] Specifically, the above-mentioned memory 602 and processor 601 can be general-purpose memories and processors, which are not specifically limited here. When the processor 601 runs the computer program stored in the memory 602, it can execute the above-mentioned control method for tunnel energy-saving ventilation based on fuzzy control.

[0180] The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 601. The above processor 601 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 gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the above method in combination with its hardware.

[0181] Corresponding to the above-mentioned control method for tunnel energy-saving ventilation based on fuzzy control, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned control method for tunnel energy-saving ventilation based on fuzzy control.

[0182] The control system for energy-saving tunnel ventilation based on fuzzy control provided in the embodiment of the present application can be specific hardware on the equipment or software or firmware installed on the equipment. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0183] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0184] For another example, the flowchart and block diagram in the accompanying drawings show the possible architecture, functions and operations of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0185] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0186] In addition, each functional unit in the embodiments provided in the present application 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.

[0187] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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, including a number of instructions for an electronic device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the vehicle marking method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0188] 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.

[0189] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application. They should all be covered within the protection scope of the present application.

Claims

1. A control method for tunnel energy-saving ventilation based on fuzzy control, characterized in that: include: Get the traffic flow data in the current tunnel; Based on the traffic flow prediction model and the pollution diffusion model, the predicted pollutant concentration corresponding to the vehicle flow data and the predicted required air volume corresponding to the predicted pollutants are obtained; The predicted pollutant concentration and the predicted required air volume are input into a fuzzy control model to obtain the number of fans required for the current tunnel.

2. The control method for tunnel energy-saving ventilation based on fuzzy control according to claim 1 is characterized in that: The method of obtaining the predicted pollutant concentration corresponding to the vehicle flow data based on the traffic flow prediction model and the pollution diffusion model includes: Inputting the vehicle flow data into the traffic flow prediction model to obtain predicted traffic flow data, wherein the predicted traffic flow data is the traffic flow data for the next cycle; The predicted traffic flow data is input into the pollution diffusion model to obtain the predicted pollutant concentration, wherein the predicted pollutant concentration includes a first pollutant concentration and a second pollutant concentration.

3. The control method for tunnel energy-saving ventilation based on fuzzy control according to claim 2 is characterized in that: The step of inputting the predicted traffic flow data into the pollution diffusion model to obtain the predicted pollutant concentration includes: Inputting the predicted traffic flow data into a first pollutant model to obtain the first pollutant concentration; The predicted traffic flow data is input into a second pollutant model to obtain the second pollutant concentration.

4. The control method for tunnel energy-saving ventilation based on fuzzy control according to claim 3 is characterized in that: Based on the traffic flow prediction model and the pollution diffusion model, the predicted required air volume corresponding to the predicted pollutants corresponding to the vehicle flow data is obtained, wherein the predicted required air volume includes a first required air volume and a second required air volume, including: Inputting the first pollutant concentration into a first required air volume model to obtain the first required air volume; The second pollutant concentration is input into a second required air volume model to obtain the second required air volume.

5. The control method for tunnel energy-saving ventilation based on fuzzy control according to claim 4 is characterized in that: The step of inputting the predicted pollutant concentration and the predicted required air volume into a fuzzy control model to obtain the number of fans required for the current tunnel includes: Based on the first pollutant concentration, determining a first predicted concentration deviation value and a first designed concentration deviation value of the first pollutant concentration; Determining a second predicted concentration deviation value and a second designed concentration deviation value of the second pollutant concentration based on the second pollutant concentration; Inputting the first predicted concentration deviation value, the first designed concentration deviation value and the first required air volume into the fuzzy control model to obtain a first required number of fans; Inputting the second predicted concentration deviation value, the second designed concentration deviation value and the second required air volume into the fuzzy control model to obtain a second required number of fans; The number of fans required for the current tunnel is determined based on the first required number of fans and the second required number of fans.

6. The control method for tunnel energy-saving ventilation based on fuzzy control according to claim 1 is characterized in that: The method further comprises: Obtaining a current pollutant concentration in the current tunnel; The current pollutant concentration is input into the fuzzy control model to determine the current number of fans required for the current pollutant concentration.

7. The control method for tunnel energy-saving ventilation based on fuzzy control according to claim 1 is characterized in that: The traffic flow prediction model is trained according to the following steps: Obtaining a historical data set, the historical data set including pollutant concentrations and required air volumes corresponding to the pollutant concentrations; Based on the historical data set, the initial traffic flow prediction model is iteratively trained until the predicted number of iterations is reached to obtain the target traffic flow prediction model. Each iterative training includes: inputting the historical data set into the initial traffic prediction model to obtain the initial determination coefficient value; optimizing the convergence factor in the GWO algorithm based on the determination coefficient difference and the inverse tangent function to obtain the OGWO algorithm; optimizing the individuals in the OGWO algorithm based on the differential evolution algorithm to obtain the OGWO-DE algorithm; optimizing the learning rate and shrinkage factor in the traffic flow prediction model based on the OGWO-DE algorithm, and obtaining the target determination coefficient value using the optimized traffic flow prediction model; obtaining the target determination coefficient difference based on the initial determination coefficient and the target determination coefficient; and updating the initial traffic prediction model according to the target determination coefficient difference, the optimized learning rate and shrinkage factor.

8. A tunnel energy-saving ventilation control system based on fuzzy control, characterized in that: include: An acquisition module is used to obtain the traffic flow data in the current tunnel; A prediction module, for obtaining a predicted pollutant concentration corresponding to the vehicle flow data and a predicted required air volume corresponding to the predicted pollutants based on a traffic flow prediction model and a pollution diffusion model; The decision module is used to input the predicted pollutant concentration and the predicted required air volume into a fuzzy control model to obtain the number of fans required for the current tunnel.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the control method for tunnel energy-saving ventilation based on fuzzy control as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine executable instructions, and when the machine executable instructions are called and executed by the processor, the control method for tunnel energy-saving ventilation based on fuzzy control as described in any one of claims 1 to 7 is implemented.

Images