Intelligent linkage control system for tunnel electromechanical equipment

Abstract

The invention relates to the technical field of intelligent control, in particular to an intelligent linkage control system for tunnel electromechanical equipment, which comprises an environment sensing module, a data analysis module, an intelligent decision module, a linkage control module, a user interaction module and an emergency response module, wherein the environment sensing module is used for acquiring environment parameters in a tunnel; the data analysis module is used for generating an environment trend prediction and anomaly detection result; the intelligent decision module is used for generating a linkage control strategy in combination with a preset fuzzy logic algorithm; the linkage control module is used for adjusting electromechanical equipment in the tunnel to realize intelligent linkage control of the equipment; the user interaction module is used for providing multiple interaction modes; and the emergency response module is used for immediately starting emergency measures when an emergency occurs. According to the invention, through real-time monitoring, intelligent adjustment and effective emergency response, the safety, reliability and emergency processing capability of the tunnel are significantly improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent linkage control system for tunnel electromechanical equipment. Background Art

[0002] As an important part of transportation infrastructure, tunnels undertake important tasks in urban transportation. With the acceleration of urbanization and the increase in traffic volume, the requirements for tunnel safety and operation efficiency are increasing. However, there are some problems with the control systems of many tunnel electromechanical equipment. For example, traditional control systems often lack intelligence and automation, and are difficult to adapt to the complex and changeable tunnel environment and operation requirements, resulting in insufficient tunnel operation management and increased safety risks.

[0003] At present, the control systems of tunnel electromechanical equipment often adopt methods based on traditional logic control, lacking real-time perception of the tunnel environment and intelligent decision-making capabilities, which leads to inefficient tunnel operation management and increased safety risks. In addition, the traditional emergency response mechanism also has shortcomings, lacks pertinence and immediacy, cannot effectively respond to emergencies, and cannot ensure the safety of personnel and equipment in the tunnel.

[0004] Therefore, there is an urgent need for a new type of intelligent linkage control system for tunnel electromechanical equipment that can realize real-time perception, intelligent decision-making and automatic adjustment of the tunnel environment, and provide an effective emergency response mechanism to ensure the safety and efficiency of tunnel operation. Summary of the invention

[0005] Based on the above purpose, the present invention provides an intelligent linkage control system for tunnel electromechanical equipment.

[0006] An intelligent linkage control system for tunnel electromechanical equipment includes an environment perception module, a data analysis module, an intelligent decision-making module, a linkage control module, a user interaction module and an emergency response module; wherein:

[0007] Environmental perception module: collects environmental parameters in the tunnel in real time through a variety of sensors, including wind speed, wind direction, light intensity and gas concentration, and transmits the data to the data analysis module;

[0008] Data analysis module: Use machine learning algorithms and big data analysis technology to conduct in-depth mining and analysis of environmental data, generate environmental trend predictions and anomaly detection results, and transmit the analysis results to the intelligent decision-making module;

[0009] Intelligent decision-making module: generates linkage control strategies based on the environmental data analysis results provided by the data analysis module and combined with the preset fuzzy logic algorithm, and transmits the control strategies to the linkage control module;

[0010] Linkage control module: receives control strategy instructions from the intelligent decision-making module, automatically adjusts the electromechanical equipment in the tunnel, and realizes intelligent linkage control of the equipment;

[0011] User interaction module: used to provide multiple interaction methods, allowing users to monitor and operate the system anytime and anywhere;

[0012] Emergency response module: used to immediately initiate emergency measures according to the preset emergency plan of the intelligent decision-making module in the event of an emergency, to ensure the safety of personnel and equipment in the tunnel.

[0013] Furthermore, the environment perception module includes a wind speed sensor unit, a wind direction sensor unit, a light intensity sensor unit, a gas sensor unit and a data acquisition unit; wherein,

[0014] Wind speed sensor unit: used to monitor the wind speed changes in the tunnel in real time, convert the wind speed value into an electrical signal through the sensing element and transmit it to the data acquisition unit;

[0015] Wind direction sensor unit: used to monitor the wind direction changes in the tunnel in real time, convert the wind direction value into an electrical signal through the sensing element and transmit it to the data acquisition unit;

[0016] Light intensity sensor unit: used to monitor the light intensity in the tunnel in real time, convert the light intensity value into an electrical signal through the sensing element and transmit it to the data acquisition unit;

[0017] Gas sensor unit: used to monitor the gas concentration in the tunnel in real time, including harmful gases such as CO2 and CO. The gas concentration value is converted into an electrical signal through the sensing element and transmitted to the data acquisition unit;

[0018] Data acquisition unit: used to receive electrical signals from each sensor unit, convert these signals into digital signals, and then transmit the digital signals to the data analysis module through the data transmission line.

[0019] Furthermore, the data analysis module includes a data preprocessing unit, a feature extraction unit, a machine learning algorithm unit and an anomaly detection unit; wherein,

[0020] Data preprocessing unit: used to perform denoising and normalization preprocessing operations on the received environmental data to ensure data quality;

[0021] Feature extraction unit: extracts features from environmental data by performing feature extraction on preprocessed data, including the changing trends of wind speed, wind direction, and light intensity;

[0022] Machine learning algorithm unit: Use machine learning algorithms based on support vector machines to train and learn the extracted features to establish an environmental data model;

[0023] Anomaly detection unit: Based on the established environmental data model, it analyzes the environmental data received in real time, and identifies abnormal conditions in the environment by comparing the differences between real-time data and model data, including abnormal wind speed, abnormal wind direction, abnormal light intensity, and emergencies.

[0024] Furthermore, the machine learning algorithm unit includes:

[0025] Feature extraction: First, extract features from the preprocessed environmental data. Suppose the extracted features are a feature matrix X containing n samples, where each sample has m features, that is, X = [x 1 , x 2 , …, x n ] T , where x i is an m-dimensional feature vector;

[0026] Label setting: Mark each sample with a category label. There are two category labels, y i ∈{-1, 1} means that two class labels are used to indicate whether the sample belongs to a normal state or an abnormal state;

[0027] Model training: The feature matrix X is trained using the support vector machine algorithm. The support vector machine separates samples of different categories by finding an optimal hyperplane. The specific formula is:

[0028]

[0029] sty i (w·x i +b)≥1-ξ i ,ξ i ≥0,i=1,2,…,n, where w is the normal vector of the hyperplane, b is the bias of the hyperplane, ξ i is a slack variable, C is a regularization parameter, which is used to balance the complexity of the model and the training error. By solving the optimization problem, the optimal hyperplane parameters w and b can be obtained;

[0030] Model prediction: Finally, the trained support vector machine model is used to classify and predict the new samples. Specifically, for the new feature vector x new , predict its category y new The formula is:

[0031] y new =sign(wx new +b), where sign(·) represents the sign function. If w·x new +b is greater than zero, then y newis a positive category, otherwise it is a negative category.

[0032] Furthermore, the abnormality detection unit includes:

[0033] Real-time data acquisition: First, the real-time environmental data received from the environmental perception module is obtained, including parameters such as wind speed and direction, light intensity, and gas concentration;

[0034] Model data acquisition: Then use the environmental data model established by the data analysis module to obtain the environmental data predicted by the model;

[0035] Difference comparison: Next, the real-time environmental data received is compared with the environmental data predicted by the model. For each environmental parameter, the difference between the real-time data and the model data is calculated;

[0036] Abnormality recognition: Identify abnormal conditions in the environment based on the size and trend of the difference. Specifically, when the wind speed or wind direction suddenly changes and exceeds the preset threshold, it is judged as a wind abnormality; when the light intensity suddenly drops or increases and exceeds the preset threshold, it is judged as a light intensity abnormality.

[0037] Furthermore, the intelligent decision-making module includes an analysis result receiving unit, a fuzzy logic rule definition unit, a fuzzification unit, a fuzzy reasoning unit and a defuzzification unit; wherein,

[0038] Analysis result receiving unit: used to receive environmental data analysis results from the data analysis module, including wind speed and direction and light intensity prediction and anomaly detection results;

[0039] Fuzzy logic rule definition unit: defines a series of fuzzy logic rules to describe the linkage control strategies to be adopted under different environmental conditions. The specific rules include:

[0040] Rule 1: If CO concentration is abnormally high, increase the efficiency of the ventilation system;

[0041] Rule 2: If the CO concentration drops abnormally, reduce the efficiency of the ventilation system;

[0042] Rule 3: If an emergency is detected, the emergency lighting system is activated immediately;

[0043] Fuzzification unit: The environmental data analysis results are fuzzified by this unit, and the actual environmental parameter values ​​are mapped to fuzzy sets, which are matched and inferred with fuzzy logic rules. The fuzzification process is operated through membership functions, which include Gaussian functions and trigonometric functions.

[0044] Fuzzy reasoning unit: Based on fuzzy logic rules and fuzzified environmental data, the linkage control strategy is derived using the fuzzy reasoning method to determine the final control solution. The fuzzy reasoning method specifically uses the minimum-maximum method for reasoning. The calculation process of the linkage control strategy includes:

[0045] a. Calculate the activation degree of the rules based on the input fuzzy logic rules and the fuzzified environmental data;

[0046] b. For each rule, fuzzy reasoning is performed based on the fuzzy set corresponding to the activation degree to obtain the fuzzy output;

[0047] c. Synthesize all fuzzy outputs to obtain the final fuzzy control strategy;

[0048] Defuzzification unit: The obtained fuzzy control strategy is defuzzified by using the weighted average method and converted into specific control commands or instructions to facilitate the actual linkage control operation of the electromechanical equipment in the tunnel.

[0049] Furthermore, the defuzzification unit includes:

[0050] Fuzzy control strategy acquisition: obtain the fuzzy control strategy from the intelligent decision-making module and express it in the form of fuzzy sets;

[0051] Weighted average calculation: Perform weighted average calculation on the fuzzy control strategy to obtain specific control commands or instructions. The calculation formula of weighted average is: Where C represents the final control command or instruction; n is the number of fuzzy control strategies; w i is the weight of the i-th fuzzy control strategy; C i is the i-th fuzzy control strategy;

[0052] Weight determination: weight w i It is used to reflect the importance or credibility of each fuzzy control strategy. The weight will be determined according to the activation degree of the fuzzy control strategy. The higher the activation degree of the strategy, the greater its weight. The formula for calculating the weight is as follows: Among them, w i Indicates the weight of the i-th fuzzy control strategy; ActivationDegree i represents the activation degree of the i-th fuzzy control strategy; n is the number of fuzzy control strategies;

[0053] Control command generation: Finally, based on the result C obtained by weighted average calculation, a specific control command or instruction is generated. The control command or instruction will be directly applied to the electromechanical equipment in the tunnel to realize intelligent linkage control.

[0054] Furthermore, the linkage control module includes an instruction receiving unit, a control adjustment unit and a feedback monitoring unit; wherein,

[0055] Instruction receiving unit: used to receive control strategy instructions provided by the intelligent decision-making module;

[0056] Control and adjustment unit: After receiving the control strategy instruction, it will adjust the electromechanical equipment in the tunnel according to the instruction. Specifically, it will adjust the parameters of the equipment according to the instruction, including the speed of the fan and the brightness of the light, to achieve intelligent linkage control;

[0057] Feedback monitoring unit: During the equipment adjustment process, the feedback monitoring unit is used to detect the environmental conditions in the tunnel and provide real-time feedback to the intelligent decision-making module.

[0058] Furthermore, the user interaction module includes a graphical interface unit and a voice interaction unit; wherein,

[0059] Graphical interface unit: used to provide a graphical user interface. By displaying graphical information and control buttons, users can intuitively understand the system status and perform operations, including displaying the status of each device in the tunnel, real-time changes in environmental parameters, and control buttons on the display screen;

[0060] Voice interaction unit: Receives user's voice commands and converts them into commands that the system can recognize through voice recognition technology, allowing users to interact with the system through voice to monitor and operate the system.

[0061] Furthermore, the emergency response module includes a preset emergency plan unit, an emergency monitoring unit, an intelligent decision-making unit and an emergency measure execution unit; wherein,

[0062] Preset emergency plan unit: used to store pre-set emergency plans for various emergency situations, including fire and power failure;

[0063] Emergency Monitoring Unit: used to monitor the environmental parameters and equipment status in the tunnel in real time. When an abnormal situation that may lead to an emergency is detected, an alarm signal is immediately sent to the intelligent decision-making module and the emergency response procedure is triggered;

[0064] Emergency measures initiation unit: When receiving instructions from the intelligent decision-making module or an alarm signal from the emergency monitoring unit, the emergency measures initiation unit immediately activates the preset emergency plan and executes corresponding emergency measures, including automatically adjusting the information board, lane indicators, starting the fan, and sending alarm information to the emergency rescue department.

[0065] Beneficial effects of the present invention:

[0066] The present invention realizes real-time monitoring of environmental parameters in the tunnel through the environmental perception module, and combined with the intelligent analysis capability of the data analysis module, can accurately grasp the environmental change trend and abnormal conditions in the tunnel, thereby improving the safety and reliability of the tunnel.

[0067] The present invention, by adopting an intelligent decision-making module combined with a fuzzy logic algorithm, generates a linkage control strategy according to the results of environmental data analysis, thereby realizing intelligent adjustment and linkage control of tunnel electromechanical equipment. This intelligent control method not only improves the efficiency and accuracy of equipment operation, but also effectively reduces errors and missed controls in human operations, thereby reducing the operating costs of the tunnel.

[0068] The present invention can initiate emergency measures in a timely manner according to a preset emergency plan through an emergency response module, effectively respond to various emergency situations, and ensure the safety of personnel and equipment in the tunnel. This timely and effective emergency response mechanism not only improves the emergency handling capability of the tunnel, but also can reduce accident losses and the impact on transportation, further enhancing the safety and reliability of the tunnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 A schematic diagram of an intelligent linkage control system for electromechanical equipment according to an embodiment of the present invention;

[0071] Figure 2 Schematic diagram of an intelligent decision-making module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0072] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0073] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. The words "include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects.

[0074] like Figure 1-Figure 2As shown, an intelligent linkage control system for tunnel electromechanical equipment includes an environment perception module, a data analysis module, an intelligent decision-making module, a linkage control module, a user interaction module and an emergency response module; wherein,

[0075] Environmental perception module: collects environmental parameters in the tunnel in real time through a variety of sensors, including wind speed, wind direction, light intensity and gas concentration, and transmits the data to the data analysis module;

[0076] Data analysis module: Use machine learning algorithms and big data analysis technology to conduct in-depth mining and analysis of environmental data, generate environmental trend predictions and anomaly detection results, and transmit the analysis results to the intelligent decision-making module;

[0077] Intelligent decision-making module: generates linkage control strategies based on the environmental data analysis results provided by the data analysis module and combined with the preset fuzzy logic algorithm, and transmits the control strategies to the linkage control module;

[0078] Linkage control module: receives control strategy instructions from the intelligent decision-making module, automatically adjusts the electromechanical equipment in the tunnel, and realizes intelligent linkage control of the equipment;

[0079] User interaction module: used to provide multiple interaction methods, allowing users to monitor and operate the system anytime and anywhere;

[0080] Emergency response module: used to immediately initiate emergency measures according to the preset emergency plan of the intelligent decision-making module in the event of an emergency, to ensure the safety of personnel and equipment in the tunnel.

[0081] The environment perception module includes a wind speed sensor unit, a wind direction sensor unit, a light intensity sensor unit, a gas sensor unit and a data acquisition unit; wherein,

[0082] Wind speed sensor unit: used to monitor the wind speed changes in the tunnel in real time, convert the wind speed value into an electrical signal through the sensing element and transmit it to the data acquisition unit;

[0083] Wind direction sensor unit: used to monitor the wind direction changes in the tunnel in real time, convert the wind direction value into an electrical signal through the sensing element and transmit it to the data acquisition unit;

[0084] Light intensity sensor unit: used to monitor the light intensity in the tunnel in real time, convert the light intensity value into an electrical signal through the sensing element and transmit it to the data acquisition unit;

[0085] Gas sensor unit: used to monitor the gas concentration in the tunnel in real time, including harmful gases such as CO2 and CO. The gas concentration value is converted into an electrical signal through the sensing element and transmitted to the data acquisition unit;

[0086] Data acquisition unit: used to receive electrical signals from each sensor unit and convert these signals into digital signals, and then transmit the digital signals to the data analysis module through the data transmission line. In this way, the environmental perception module can accurately collect environmental parameters in the tunnel in real time and transmit the data to the data analysis module, providing necessary environmental information for the system's intelligent decision-making.

[0087] The data analysis module includes a data preprocessing unit, a feature extraction unit, a machine learning algorithm unit and an anomaly detection unit; among them,

[0088] Data preprocessing unit: used to perform denoising and normalization preprocessing operations on the received environmental data to ensure data quality;

[0089] Feature extraction unit: extracts features from environmental data by performing feature extraction on preprocessed data, including the changing trends of wind speed, wind direction, and light intensity;

[0090] Machine learning algorithm unit: Use the machine learning algorithm based on support vector machine to train and learn the extracted features to establish an environmental data model, which can effectively describe and predict the environment in the tunnel;

[0091] Abnormality detection unit: Based on the established environmental data model, it analyzes the environmental data received in real time and identifies abnormal conditions in the environment by comparing the differences between the real-time data and the model data, including abnormal wind speed, abnormal wind direction, abnormal light intensity, and emergencies such as fire and leakage.

[0092] Through the above units, the data analysis module can conduct in-depth mining and analysis of the tunnel environment, and generate environmental trend predictions and anomaly detection results, providing effective environmental information and decision support for the intelligent decision-making module.

[0093] The machine learning algorithm unit includes:

[0094] Feature extraction: First, extract features from the preprocessed environmental data. Suppose the extracted features are a feature matrix X containing n samples, where each sample has m features, that is, X = [x 1 , x 2 , ..., x n ] T , where x i is an m-dimensional feature vector;

[0095] Label setting: Mark each sample with a category label. There are two category labels, y i ∈{-1, 1} means that two class labels are used to indicate whether the sample belongs to a normal state or an abnormal state;

[0096] Model training: The feature matrix X is trained using the support vector machine algorithm. The support vector machine separates samples of different categories by finding an optimal hyperplane. The specific formula is:

[0097]

[0098] sty i (w·x i +b)≥1-ζ i ,ζ i ≥0,i=1,2,…,n, where w is the normal vector of the hyperplane, b is the bias of the hyperplane, ζ i is a slack variable, C is a regularization parameter, which is used to balance the complexity of the model and the training error. By solving the optimization problem, the optimal hyperplane parameters w and b can be obtained;

[0099] Model prediction: Finally, the trained support vector machine model is used to classify and predict the new samples. Specifically, for the new feature vector x new , predict its category y new The formula is:

[0100] y new =sign(wx new +b), where sign(·) represents the sign function. If w·x new +b is greater than zero, then y new It is a positive category, otherwise it is a negative category. In this way, the model training and prediction of environmental data are completed, and an environmental data model based on support vector machine is established.

[0101] The anomaly detection unit includes:

[0102] Real-time data acquisition: First, the real-time environmental data received from the environmental perception module is obtained, including parameters such as wind speed and direction, light intensity, and gas concentration;

[0103] Model data acquisition: Then use the environmental data model established by the data analysis module to obtain the environmental data predicted by the model. These model data are trained based on historical data and can reflect the parameter range and trend under normal environment;

[0104] Difference comparison: Next, the real-time environmental data received is compared with the environmental data predicted by the model. For each environmental parameter, the difference between the real-time data and the model data is calculated;

[0105] Abnormality recognition: Identify abnormal conditions in the environment based on the size and trend of the difference. Specifically, when the wind speed or wind direction suddenly changes and exceeds the preset threshold, it is judged as a wind abnormality; when the light intensity suddenly drops or increases and exceeds the preset threshold, it is judged as a light intensity abnormality; in addition, by monitoring the changes in multiple environmental parameters and combining prior knowledge or rules, possible emergencies such as fire and leakage can be identified.

[0106] The intelligent decision-making module includes an analysis result receiving unit, a fuzzy logic rule definition unit, a fuzzification unit, a fuzzy reasoning unit and a defuzzification unit; wherein,

[0107] Analysis result receiving unit: used to receive environmental data analysis results from the data analysis module, including wind speed and direction and light intensity prediction and anomaly detection results;

[0108] Fuzzy logic rule definition unit: defines a series of fuzzy logic rules to describe the linkage control strategies to be adopted under different environmental conditions. The specific rules include:

[0109] Rule 1: If CO concentration is abnormally high, increase the efficiency of the ventilation system;

[0110] Rule 2: If the CO concentration drops abnormally, reduce the efficiency of the ventilation system;

[0111] Rule 3: If an emergency is detected, the emergency lighting system is activated immediately;

[0112] Fuzzification unit: The environmental data analysis results are fuzzified by this unit, and the actual environmental parameter values ​​are mapped to fuzzy sets, which are matched and inferred with fuzzy logic rules. The fuzzification process is operated through membership functions, which include Gaussian functions and trigonometric functions.

[0113] Fuzzy reasoning unit: Based on fuzzy logic rules and fuzzified environmental data, the linkage control strategy is derived using the fuzzy reasoning method to determine the final control solution. The fuzzy reasoning method specifically uses the minimum-maximum method for reasoning. The calculation process of the linkage control strategy includes:

[0114] a. Calculate the activation degree of the rules based on the input fuzzy logic rules and the fuzzified environmental data;

[0115] b. For each rule, fuzzy reasoning is performed based on the fuzzy set corresponding to the activation degree to obtain the fuzzy output;

[0116] c. Synthesize all fuzzy outputs to obtain the final fuzzy control strategy;

[0117] Defuzzification unit: The obtained fuzzy control strategy is defuzzified by using the weighted average method and converted into specific control commands or instructions to facilitate the actual linkage control operation of the electromechanical equipment in the tunnel;

[0118] Through the synergistic effect of the above specific units, the intelligent decision-making module can generate an effective linkage control strategy based on the environmental data analysis results provided by the data analysis module and combined with the preset fuzzy logic rules, so as to realize the intelligent linkage control of the tunnel electromechanical equipment, thereby improving the efficiency and safety of tunnel operation.

[0119] The defuzzification unit includes:

[0120] Fuzzy control strategy acquisition: Obtain the fuzzy control strategy from the intelligent decision-making module. The control strategy describes the linkage control measures taken under different environmental conditions and is expressed in the form of fuzzy sets;

[0121] Weighted average calculation: Perform weighted average calculation on the fuzzy control strategy to obtain specific control commands or instructions. The calculation formula of weighted average is: Where C represents the final control command or instruction, which is the result obtained based on the fuzzy control strategy and is used to adjust the electromechanical equipment in the tunnel; n is the number of fuzzy control strategies, which represents the number of fuzzy control strategies obtained by the anomaly detection unit; w i is the weight of the i-th fuzzy control strategy, reflecting the importance or credibility of the strategy; C i is the i-th fuzzy control strategy, which describes the linkage control measures taken for different environmental conditions and is expressed in the form of fuzzy sets;

[0122] Weight determination: weight w i It is used to reflect the importance or credibility of each fuzzy control strategy. The weight will be determined according to the activation degree of the fuzzy control strategy. The higher the activation degree of the strategy, the greater its weight. The formula for calculating the weight is as follows: Among them, w i Represents the weight of the i-th fuzzy control strategy, which reflects the importance or credibility of each fuzzy control strategy in the entire control process; ActivationDegree i represents the activation degree of the i-th fuzzy control strategy. In the anomaly detection unit, this activation degree indicates the applicability or responsiveness of the fuzzy control strategy to the current environmental conditions; n is the number of fuzzy control strategies, indicating the number of fuzzy control strategies obtained by the anomaly detection unit;

[0123] Control command generation: Finally, based on the result C obtained by weighted average calculation, a specific control command or instruction is generated. The control command or instruction will be directly applied to the electromechanical equipment in the tunnel to achieve intelligent linkage control. For example, if the result C obtained by weighted average calculation indicates to reduce the fan speed, a control command to reduce the fan speed is generated and sent to the corresponding fan control system.

[0124] Through the above steps, the anomaly detection unit can effectively defuzzify the fuzzy control strategy and convert it into specific control commands or instructions to achieve intelligent linkage control of tunnel electromechanical equipment.

[0125] The linkage control module includes a command receiving unit, a control adjustment unit and a feedback monitoring unit; wherein,

[0126] Instruction receiving unit: used to receive control strategy instructions provided by the intelligent decision-making module, which describe the linkage control measures to be taken according to the current tunnel environment conditions;

[0127] Control and adjustment unit: After receiving the control strategy instruction, it will adjust the electromechanical equipment in the tunnel according to the instruction. Specifically, it will adjust the parameters of the equipment according to the instruction, including the speed of the fan and the brightness of the light, to achieve intelligent linkage control;

[0128] Feedback monitoring unit: During the process of adjusting the equipment, the feedback monitoring unit is used to detect the environmental conditions in the tunnel and provide real-time feedback to the intelligent decision-making module; in this way, the intelligent decision-making module can adjust the control strategy according to the actual situation to better adapt to the changes in the tunnel;

[0129] Through the collaboration of the above units, the linkage control module can automatically adjust the electromechanical equipment in the tunnel according to the control strategy instructions provided by the intelligent decision-making module, and realize intelligent linkage control of the equipment. The design principle of this linkage control module is simple and efficient, and can effectively improve the safety and efficiency of tunnel operation.

[0130] The user interaction module includes a graphical interface unit and a voice interaction unit; wherein,

[0131] Graphical interface unit: used to provide a graphical user interface. By displaying graphical information and control buttons, users can intuitively understand the system status and perform operations, including displaying the status of each device in the tunnel, real-time changes in environmental parameters, and control buttons on the display screen;

[0132] Voice interaction unit: Receives user voice commands and converts them into commands that the system can recognize through voice recognition technology, allowing users to interact with the system through voice to monitor and operate the system. For example, users can use voice commands to query the wind speed and direction in the tunnel, and request to adjust the light brightness, etc.

[0133] Through the collaboration of the above units, the user interaction module can provide a variety of interaction methods, allowing users to monitor and operate the system anytime and anywhere. This diverse interaction method not only improves the user's convenience and operating experience, but also enhances the system's availability and flexibility, thereby better meeting user needs.

[0134] The emergency response module includes a preset emergency plan unit, an emergency monitoring unit, an intelligent decision-making unit, and an emergency measures execution unit;

[0135] Preset emergency plan unit: used to store pre-set emergency plans for various emergency situations, including fire and power failure. Each plan has been carefully designed and demonstrated, including emergency measures, equipment dispatch plans, etc.

[0136] Emergency Monitoring Unit: used to monitor the environmental parameters and equipment status in the tunnel in real time. When an abnormal situation that may lead to an emergency is detected, an alarm signal is immediately sent to the intelligent decision-making module and the emergency response procedure is triggered;

[0137] Emergency measures initiation unit: When receiving instructions from the intelligent decision-making module or an alarm signal from the emergency monitoring unit, the emergency measures initiation unit immediately initiates the preset emergency plan and executes corresponding emergency measures, including automatically adjusting the information board, lane indicators, starting the smoke exhaust fan, and sending alarm information to the emergency rescue department;

[0138] Through the collaboration of the above units, the emergency response module can immediately initiate corresponding emergency measures according to the preset emergency plan of the intelligent decision-making module in case of an emergency, so as to ensure the safety of personnel and equipment in the tunnel. This emergency response mechanism can effectively deal with various emergencies, minimize accident losses, and improve the safety and reliability of tunnel operation.

[0139] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent linkage control system for tunnel electromechanical equipment, characterized in that: It includes environment perception module, data analysis module, intelligent decision-making module, linkage control module, user interaction module and emergency response module; among them, Environmental perception module: collects environmental parameters in the tunnel in real time through a variety of sensors, including wind speed, wind direction, light intensity and gas concentration, and transmits the data to the data analysis module; Data analysis module: Use machine learning algorithms and big data analysis technology to conduct in-depth mining and analysis of environmental data, generate environmental trend predictions and anomaly detection results, and transmit the analysis results to the intelligent decision-making module; Intelligent decision-making module: generates linkage control strategies based on the environmental data analysis results provided by the data analysis module and combined with the preset fuzzy logic algorithm, and transmits the control strategies to the linkage control module; Linkage control module: receives control strategy instructions from the intelligent decision-making module, automatically adjusts the electromechanical equipment in the tunnel, and realizes intelligent linkage control of the equipment; User interaction module: used to provide multiple interaction methods, allowing users to monitor and operate the system anytime and anywhere; Emergency response module: used to immediately initiate emergency measures according to the preset emergency plan of the intelligent decision-making module in the event of an emergency, to ensure the safety of personnel and equipment in the tunnel.

2. According to claim 1, the intelligent linkage control system for tunnel electromechanical equipment is characterized in that: The environment sensing module includes a wind speed sensor unit, a wind direction sensor unit, a light intensity sensor unit, a gas sensor unit and a data acquisition unit; wherein, Wind speed sensor unit: used to monitor the wind speed changes in the tunnel in real time, convert the wind speed value into an electrical signal through the sensing element and transmit it to the data acquisition unit; Wind direction sensor unit: used to monitor the wind direction changes in the tunnel in real time, convert the wind direction value into an electrical signal through the sensing element and transmit it to the data acquisition unit; Light intensity sensor unit: used to monitor the light intensity in the tunnel in real time, convert the light intensity value into an electrical signal through the sensing element and transmit it to the data acquisition unit; Gas sensor unit: used to monitor the gas concentration in the tunnel in real time, including harmful gases such as CO2 and CO. The gas concentration value is converted into an electrical signal through the sensing element and transmitted to the data acquisition unit; Data acquisition unit: used to receive electrical signals from each sensor unit, convert these signals into digital signals, and then transmit the digital signals to the data analysis module through the data transmission line.

3. The intelligent linkage control system for tunnel electromechanical equipment according to claim 1 is characterized in that: The data analysis module includes a data preprocessing unit, a feature extraction unit, a machine learning algorithm unit and an anomaly detection unit; wherein, Data preprocessing unit: used to perform denoising and normalization preprocessing operations on the received environmental data to ensure data quality; Feature extraction unit: extracts features from environmental data by performing feature extraction on preprocessed data, including the changing trends of wind speed, wind direction, and light intensity; Machine learning algorithm unit: Use machine learning algorithms based on support vector machines to train and learn the extracted features to establish an environmental data model; Anomaly detection unit: Based on the established environmental data model, it analyzes the environmental data received in real time, and identifies abnormal conditions in the environment by comparing the differences between real-time data and model data, including abnormal wind speed, abnormal wind direction, abnormal light intensity, and emergencies.

4. The intelligent linkage control system for tunnel electromechanical equipment according to claim 3 is characterized in that: The machine learning algorithm unit includes: Feature extraction: First, extract features from the preprocessed environmental data. Suppose the extracted features are a feature matrix X containing n samples, where each sample has m features, that is, X = [x1, x2, ..., x n ] T , where x i is an m-dimensional feature vector; Label setting: Mark each sample with a category label. There are two category labels, y i ∈{-1, 1} means that two class labels are used to indicate whether the sample belongs to a normal state or an abnormal state; Model training: The feature matrix X is trained using the support vector machine algorithm. The support vector machine separates samples of different categories by finding an optimal hyperplane. The specific formula is: sty i (w·x i +b)≥1-ζ i ,ζ i ≥0,i=1,2,…,n, where w is the normal vector of the hyperplane, b is the bias of the hyperplane, ξ i is a slack variable, C is a regularization parameter, which is used to balance the complexity of the model and the training error. By solving the optimization problem, the optimal hyperplane parameters w and b can be obtained; Model prediction: Finally, the trained support vector machine model is used to classify and predict the new samples. Specifically, for the new feature vector x new , predict its category y new The formula is: y new =sign(wx new +b), where sign(·) represents the sign function. If w·x new +b is greater than zero, then y new is a positive category, otherwise it is a negative category.

5. The intelligent linkage control system for tunnel electromechanical equipment according to claim 4 is characterized in that: The abnormality detection unit comprises: Real-time data acquisition: First, the real-time environmental data received from the environmental perception module is obtained, including parameters such as wind speed and direction, light intensity, and gas concentration; Model data acquisition: Then use the environmental data model established by the data analysis module to obtain the environmental data predicted by the model; Difference comparison: Next, the real-time environmental data received is compared with the environmental data predicted by the model. For each environmental parameter, the difference between the real-time data and the model data is calculated; Abnormality recognition: Identify abnormal conditions in the environment based on the size and trend of the difference. Specifically, when the wind speed or wind direction suddenly changes and exceeds the preset threshold, it is judged as a wind abnormality; when the light intensity suddenly drops or increases and exceeds the preset threshold, it is judged as a light intensity abnormality.

6. The intelligent linkage control system for tunnel electromechanical equipment according to claim 5 is characterized in that: The intelligent decision-making module includes an analysis result receiving unit, a fuzzy logic rule definition unit, a fuzzification unit, a fuzzy reasoning unit and a defuzzification unit; wherein, Analysis result receiving unit: used to receive environmental data analysis results from the data analysis module, including wind speed and direction and light intensity prediction and anomaly detection results; Fuzzy logic rule definition unit: defines a series of fuzzy logic rules to describe the linkage control strategies to be adopted under different environmental conditions. The specific rules include: Rule 1: If CO concentration is abnormally high, increase the efficiency of the ventilation system; Rule 2: If the CO concentration drops abnormally, reduce the efficiency of the ventilation system; Rule 3: If an emergency is detected, the emergency lighting system is activated immediately; Fuzzification unit: The environmental data analysis results are fuzzified by this unit, and the actual environmental parameter values ​​are mapped to fuzzy sets, which are matched and inferred with fuzzy logic rules. The fuzzification process is operated through membership functions, which include Gaussian functions and trigonometric functions. Fuzzy reasoning unit: Based on fuzzy logic rules and fuzzified environmental data, the linkage control strategy is derived using the fuzzy reasoning method to determine the final control solution. The fuzzy reasoning method specifically uses the minimum-maximum method for reasoning. The calculation process of the linkage control strategy includes: a. Calculate the activation degree of the rules based on the input fuzzy logic rules and the fuzzified environmental data; b. For each rule, fuzzy reasoning is performed based on the fuzzy set corresponding to the activation degree to obtain the fuzzy output; c. Synthesize all fuzzy outputs to obtain the final fuzzy control strategy; Defuzzification unit: The obtained fuzzy control strategy is defuzzified by using the weighted average method and converted into specific control commands or instructions to facilitate the actual linkage control operation of the electromechanical equipment in the tunnel.

7. The intelligent linkage control system for tunnel electromechanical equipment according to claim 6 is characterized in that: The defuzzification unit comprises: Fuzzy control strategy acquisition: obtain the fuzzy control strategy from the intelligent decision-making module and express it in the form of fuzzy sets; Weighted average calculation: Perform weighted average calculation on the fuzzy control strategy to obtain specific control commands or instructions. The calculation formula of weighted average is: Where C represents the final control command or instruction; n is the number of fuzzy control strategies; w i is the weight of the i-th fuzzy control strategy; C i is the i-th fuzzy control strategy; Weight determination: weight w i It is used to reflect the importance or credibility of each fuzzy control strategy. The weight will be determined according to the activation degree of the fuzzy control strategy. The higher the activation degree of the strategy, the greater its weight. The formula for calculating the weight is as follows: Among them, w i Indicates the weight of the i-th fuzzy control strategy; ActivationDegree i represents the activation degree of the i-th fuzzy control strategy; n is the number of fuzzy control strategies; Control command generation: Finally, based on the result C obtained by weighted average calculation, a specific control command or instruction is generated. The control command or instruction will be directly applied to the electromechanical equipment in the tunnel to realize intelligent linkage control.

8. The intelligent linkage control system for tunnel electromechanical equipment according to claim 1 is characterized in that: The linkage control module includes an instruction receiving unit, a control adjustment unit and a feedback monitoring unit; wherein, Instruction receiving unit: used to receive control strategy instructions provided by the intelligent decision-making module; Control and adjustment unit: After receiving the control strategy instruction, it will adjust the electromechanical equipment in the tunnel according to the instruction. Specifically, it will adjust the parameters of the equipment according to the instruction, including the speed of the fan and the brightness of the light, to achieve intelligent linkage control; Feedback monitoring unit: During the equipment adjustment process, the feedback monitoring unit is used to detect the environmental conditions in the tunnel and provide real-time feedback to the intelligent decision-making module.

9. The intelligent linkage control system for tunnel electromechanical equipment according to claim 1, characterized in that: The user interaction module includes a graphical interface unit and a voice interaction unit; wherein, Graphical interface unit: used to provide a graphical user interface. By displaying graphical information and control buttons, users can intuitively understand the system status and perform operations, including displaying the status of each device in the tunnel, real-time changes in environmental parameters, and control buttons on the display screen; Voice interaction unit: Receives user's voice commands and converts them into commands that the system can recognize through voice recognition technology, allowing users to interact with the system through voice to monitor and operate the system.

10. The intelligent linkage control system for tunnel electromechanical equipment according to claim 1, characterized in that: The emergency response module includes a preset emergency plan unit, an emergency monitoring unit, an intelligent decision-making unit and an emergency measure execution unit; wherein, Preset emergency plan unit: used to store pre-set emergency plans for various emergency situations, including fire and power failure; Emergency Monitoring Unit: used to monitor the environmental parameters and equipment status in the tunnel in real time. When an abnormal situation that may lead to an emergency is detected, an alarm signal is immediately sent to the intelligent decision-making module and the emergency response procedure is triggered; Emergency measures initiation unit: When receiving instructions from the intelligent decision-making module or an alarm signal from the emergency monitoring unit, the emergency measures initiation unit immediately activates the preset emergency plan and executes corresponding emergency measures, including automatically adjusting the information board, lane indicators, starting the fan, and sending alarm information to the emergency rescue department.

Images