Intelligent underground space smoke exhaust system

Abstract

The embodiment of the invention discloses an intelligent underground space smoke exhaust system which comprises a mechanical smoke exhaust device, a smoke exhaust control device, a smoke exhaust control device and a smoke exhaust control device. The natural smoke exhaust equipment comprises a smoke exhaust fan, and the smoke exhaust fan has an adjustable fan rotating speed; the sensing module comprises sensor equipment, and the sensor equipment is used for monitoring environmental parameters in the underground space in real time; the identification module is used for determining a flue gas distribution matrix according to the coordinate parameters and the environmental parameters of the sensor equipment; the control module is used for dynamically adjusting the fan rotating speed of the smoke exhaust fan and the opening degree of the smoke exhaust window according to the smoke distribution matrix and the data of the mechanical smoke exhaust equipment and the natural smoke exhaust equipment, and mutual interference between the natural smoke exhaust equipment and the mechanical smoke exhaust equipment is reduced.

Description

Technical Field

[0001] The present invention relates to the field of fire smoke exhaust, and in particular to an intelligent underground space smoke exhaust system. Background Art

[0002] Smoke exhaust systems are a crucial component of building fire protection facilities, primarily used to rapidly remove smoke, high-temperature gases, and toxic gases during fires, ensuring the safe evacuation of personnel and creating favorable conditions for firefighters to extinguish and rescue. Underground spaces, such as garages, subway stations, civil air defense projects, and tunnels, face numerous unique challenges in the design and operation of smoke exhaust systems due to their enclosed structures and poor ventilation. Underground spaces lack direct external openings, resulting in a limited number of natural smoke exhaust vents and slow exhaust speeds. Natural smoke exhaust relies on the natural rise of smoke, but the low ceilings and winding passageways of underground spaces make smoke easily accumulate in corners. Therefore, mechanical smoke exhaust equipment plays a vital role in underground spaces.

[0003] However, due to the relatively closed environment of underground spaces, the simultaneous operation of mechanical and natural smoke exhaust systems can lead to numerous problems: the high-speed suction of the mechanical exhaust fan can disrupt the thermal pressure differential that natural exhaust relies on, causing some of the exhausted smoke to be re-absorbed into the space; the mechanical forced airflow and natural convection create unpredictable vortices within the complex space, delaying smoke exhaust; and when natural and mechanical smoke exhaust systems are co-located in a closed environment, the natural exhaust port may become an air inlet. In short, the coordinated operation of natural and mechanical smoke exhaust requires overcoming challenges such as airflow coupling instability and control timing conflicts.

[0004] Therefore, designing an intelligent underground space smoke exhaust system is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, an embodiment of the present invention provides an intelligent underground space smoke exhaust system, which dynamically controls the operation of natural smoke exhaust equipment and mechanical smoke exhaust equipment, reduces mutual interference between natural smoke exhaust equipment and mechanical smoke exhaust equipment, and improves smoke exhaust efficiency.

[0006] In order to achieve the purpose of the invention, the present invention adopts the following technical solutions:

[0007] An intelligent underground space smoke exhaust system, characterized by comprising:

[0008] Mechanical smoke exhaust equipment, including a smoke exhaust window, wherein the smoke exhaust window has an adjustable opening;

[0009] Natural smoke exhaust equipment, including a smoke exhaust fan, wherein the smoke exhaust fan has an adjustable fan speed;

[0010] A sensing module, comprising a sensor device, wherein the sensor device is used to monitor environmental parameters in the underground space in real time;

[0011] an identification module, configured to determine a smoke distribution matrix based on coordinate parameters of the sensor device and the environmental parameters;

[0012] The control module is used to dynamically adjust the fan speed of the smoke exhaust fan and the opening of the smoke exhaust window according to the data of the smoke distribution matrix, the mechanical smoke exhaust equipment and the natural smoke exhaust equipment, so as to reduce the mutual interference between the natural smoke exhaust equipment and the mechanical smoke exhaust equipment.

[0013] Optionally, the sensor device includes a temperature sensor and a smoke sensor, and the sensor device is arranged on the ceiling of the underground space to cover the entire underground space. The perception module obtains real-time environmental parameters of various locations in the underground space.

[0014] Optionally, the identification module obtains spatial information of the underground space, determines the shortest path distance between any two sensor devices based on the spatial information of the underground space and the coordinate parameters of any two sensor devices, and determines the shortest path distance between each predicted point and all sensor devices based on the spatial information of the underground space, the coordinate parameters of the sensor devices and the coordinate parameters of the predicted points.

[0015] Optionally, the identification module determines a weight vector based on the shortest path distance between any two of the sensor devices and the environmental parameters, obtains the predicted environmental parameters of the prediction point based on the shortest path distance between each prediction point and all sensor devices and the weight vector, and obtains the flue gas distribution matrix based on the predicted environmental parameters and coordinate parameters of the prediction point and the environmental parameters and coordinate parameters of the sensor.

[0016] Optionally, the control module includes a spatial coding module, a temporal feature extraction module, a cross-attention module, an interference suppression module and a collaborative decision-making module. The control module inputs multiple smoke distribution matrices at different consecutive time points into the spatial coding module to obtain a spatial attention feature map.

[0017] Optionally, the time series feature extraction module is used to obtain the time series features of the mechanical smoke exhaust device and the time series features of the natural smoke exhaust device respectively based on the data of the mechanical smoke exhaust device and the natural smoke exhaust device. The data of the mechanical smoke exhaust device include the opening of the smoke exhaust window, the wind speed outside the window, the indoor and outdoor temperature difference, and the historical smoke exhaust efficiency at different time points. The data of the natural smoke exhaust device include the fan speed, current, static pressure, and filter pressure difference at different time points. The time series feature extraction module includes a parallel GRU module and a TCN module. The data of the mechanical smoke exhaust device and the natural smoke exhaust device are respectively output through the GRU module to output the long-term time features of the mechanical smoke exhaust device and the natural smoke exhaust device. The data of the mechanical smoke exhaust device and the natural smoke exhaust device are respectively output through the TCN module to output the local time features of the mechanical smoke exhaust device and the natural smoke exhaust device. The long-term time features and the local time features of the mechanical smoke exhaust device are fused, and the long-term time features and the local time features of the natural smoke exhaust device are fused to output the time series features of the mechanical smoke exhaust device and the time series features of the natural smoke exhaust device.

[0018] Optionally, the timing characteristics and position parameters of the mechanical smoke exhaust device and the timing characteristics and position parameters of the natural smoke exhaust device are input into the cross attention module to obtain a spatiotemporal coupling weight matrix representing the interference area.

[0019] Optionally, the interference suppression module is used to obtain a suppression heat map based on the spatiotemporal coupling weight matrix, the position parameters of the natural smoke exhaust equipment and the mechanical smoke exhaust equipment. The interference suppression module includes an interference intensity analysis unit and a suppression coefficient generation unit. The interference intensity analysis unit extracts the spatiotemporal features of the spatiotemporal coupling weight matrix. The spatiotemporal features are sequentially subjected to multi-head attention and maximum pooling operations to obtain intermediate features, and a fully connected layer is used to map the intermediate features to interference intensity scores. The suppression coefficient generation unit adjusts the steepness parameter of the sigmoid function according to the average value of the interference intensity score. The suppression coefficient generation unit uses the sigmoid function to obtain the suppression coefficient according to the steepness parameter and the interference intensity score. The interference suppression module forms a suppression heat map based on the suppression coefficient and the position parameters of the smoke exhaust equipment.

[0020] Optionally, the collaborative decision-making module determines the fan speed of each smoke exhaust fan and the opening of the smoke exhaust window according to the spatial attention feature map and the suppression heat map.

[0021] Optionally, the collaborative decision-making module includes a strategy module and a value judgment module. The strategy module is equipped with an independent strategy sub-network for each natural smoke exhaust device and mechanical smoke exhaust device. The spatial attention feature map, the inhibition heat map and the position parameters of the smoke exhaust device are input into the strategy sub-network to obtain the action probability distribution of the smoke exhaust device. The value judgment module establishes an independent value evaluation model for each smoke exhaust device, calculates the advantage function value and the objective function of each state-action pair, updates the parameters of the strategy sub-network according to the advantage function and the objective function, and after multiple iterative updates, outputs the fan speed of each smoke exhaust fan and the opening of the smoke exhaust window that makes the objective function reach the maximum value.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] The intelligent underground space smoke exhaust system provided by the present invention obtains the data of the prediction point based on the shortest path distance between each sensor in the underground space, the shortest path distance between the prediction point and the sensor, and the sensor data, so as to more accurately predict the smoke distribution of the entire underground space, and provide a solid data foundation for the subsequent control of the smoke exhaust equipment; according to the historical data and location distribution of the natural smoke exhaust equipment and the mechanical smoke exhaust equipment, the interference between the smoke exhaust equipment is determined, and an inhibition thermal map for equipment control is generated, and data suggestions are given for the control decision of the final equipment, thereby reducing the mutual influence between the smoke exhaust equipment and improving the smoke exhaust efficiency in the underground enclosed space.

[0024] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other objects, features, and advantages of the present invention will become more apparent through a more detailed description of the embodiments of the present invention in conjunction with the accompanying drawings. The accompanying drawings are provided to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and are not intended to limit the present invention. In the drawings, the same reference numerals generally represent the same components or steps.

[0026] Figure 1 It is a structural diagram of an intelligent underground space smoke exhaust system provided by an exemplary embodiment of the present invention.

[0027] Figure 2 It is a structural diagram of a control module provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0028] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0029] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0030] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0031] It should also be understood that, in the embodiments of the present invention, “a plurality of” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0032] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0033] Example 1

[0034] like Figure 1 As shown, the intelligent underground space smoke exhaust system 100 provided in this embodiment includes:

[0035] The mechanical smoke exhaust device 110 includes a smoke exhaust window, wherein the smoke exhaust window has an adjustable opening;

[0036] The natural smoke exhaust device 120 includes a smoke exhaust fan having an adjustable fan speed;

[0037] The sensing module 130 includes a sensor device for monitoring environmental parameters in the underground space in real time;

[0038] an identification module 140 for determining a smoke distribution matrix based on coordinate parameters of the sensor device and the environmental parameters;

[0039] The control module 150 is used to dynamically adjust the fan speed of the smoke exhaust fan and the opening of the smoke exhaust window according to the data of the smoke distribution matrix, the mechanical smoke exhaust equipment and the natural smoke exhaust equipment, so as to reduce the mutual interference between the natural smoke exhaust equipment and the mechanical smoke exhaust equipment.

[0040] Among them, the smoke exhaust fan of the mechanical smoke exhaust equipment 110 quickly exhausts fire smoke from the building through forced extraction, ensuring the safe evacuation of personnel and the smooth progress of fire rescue. It can quickly extract high-temperature toxic smoke during a fire, prevent smoke accumulation, reduce the temperature of the fire scene, and suppress the spread of fire. It forms an effective airflow organization through negative pressure smoke exhaust and positive pressure air supply.

[0041] The smoke exhaust windows of the natural smoke exhaust system 120 are openable exterior windows, skylights, and louvers designed specifically for fire smoke exhaust. They rely on thermal pressure (the chimney effect) and wind pressure to exhaust smoke. They utilize the rising heat generated by a fire to expel high-temperature smoke, reducing smoke accumulation within the building and improving visibility. The opening degree of these windows, skylights, and louvers can all be electrically controlled to ensure effective ventilation.

[0042] The sensor equipment includes a temperature sensor and a smoke sensor. The sensor equipment is arranged on the ceiling of the underground space and covers the entire underground space. The perception module obtains real-time environmental parameters of various locations in the underground space.

[0043] In the present invention, due to cost and placement requirements, it's impossible to densely cover the entire underground space with sensor devices. Data generated solely by these sensors cannot directly reflect the distribution of smoke throughout the entire underground space, nor can it provide a solid data foundation for subsequent smoke exhaust system control. Therefore, to address this issue, identification module 140 uses an algorithm to predict environmental parameters at other locations based on the spatial information of the underground space, the coordinate parameters of each sensor device, and the environmental parameters, thereby generating a smoke distribution matrix for the entire underground space.

[0044] Specifically, the identification module 140 obtains spatial information of the underground space and determines the shortest path distance between any two sensor devices based on the spatial information of the underground space and the coordinate parameters of any two sensor devices. The closer the distance between two sensor devices, the stronger their correlation. Calculating the distance between two sensor devices can reflect the spatial correlation between data points. However, underground spaces are often blocked by walls. The straight-line distance between sensor devices on either side of the wall is very small, while their actual physical paths are long. Therefore, the shortest path distance between sensor devices that bypasses obstacles can better reflect their correlation.

[0045] The selection of the shortest path can be achieved by using algorithms such as Dijkstra algorithm, Bellman-Ford algorithm, TEB algorithm, etc. There are n sensor devices in the underground space, and an arbitrary algorithm is used to calculate the shortest path distance between all known sensor devices to generate an n×n distance matrix.

[0046] Identification module 140 determines the shortest path distance between each prediction point and all sensor devices based on the spatial information of the underground space, the coordinate parameters of the sensor devices, and the coordinate parameters of the prediction points. A prediction point is an unknown location in the underground space for which environmental parameters need to be predicted. Predicting the environmental parameters at the prediction point provides full coverage of the underground space, reflecting the smoke threat landscape. Calculating the shortest path distance between each prediction point and all known sensor devices reveals the spatial correlation between data points. If there are n sensor devices and m prediction points in the underground space, an n×m distance matrix is generated.

[0047] The identification module 140 determines a weight vector based on the shortest path distance between any two sensor devices and the environmental parameters. The weight vector represents the optimal weight of the data points of the known sensor devices relative to the predicted points. The dot product of the weight vector and the matrix of the shortest path distances between any two sensor devices is equal to the matrix of the environmental parameters, as shown in the following formula:

[0048]

[0049] in, is the matrix of the shortest path distances between sensor devices, F is the environmental parameter matrix of sensor devices, and β is the weight vector.

[0050] The identification module 140 obtains the predicted environmental parameters of the predicted point based on the shortest path distance between each predicted point and all sensor devices and the weight vector. The dot product of the matrix of the shortest path distance between each predicted point and all sensor devices and the weight vector is equal to the predicted environmental parameter matrix of the predicted point, as shown in the following formula:

[0051] γ·β=z

[0052] Among them, γ is the matrix of the shortest path distance between each prediction point and all sensor devices, β is the weight vector, and z is the matrix of predicted environmental parameters.

[0053] Finally, the identification module 140 obtains the smoke distribution matrix based on the predicted environmental parameters and coordinate parameters of the predicted points and the environmental parameters and coordinate parameters of the sensor, that is, combines the data points of the known sensors with the predicted points to obtain the smoke distribution matrix of the entire underground space.

[0054] like Figure 2 As shown, the control module 150 includes a spatial encoding module 151, a temporal feature extraction module 152, a cross-attention module 153, an interference suppression module 154 and a collaborative decision-making module 155.

[0055] The control module 150 inputs multiple smoke distribution matrices at different consecutive time points into the spatial encoding module 151 to obtain a spatial attention feature map. Specifically, the spatial encoding module 151 uses a convolutional long short-term memory network model (ConvLSTM). ConvLSTM is a hybrid architecture that combines a convolutional neural network and a long short-term memory network. It can process both spatial and temporal data. By introducing convolution operations into the LSTM gating mechanism, it retains the spatial structure of the input data while utilizing the local receptive field and parameter sharing characteristics of the convolution operation to improve the efficiency and performance of the model. The spatial encoding module 151 comprises a dilated convolution layer, a spatial attention mechanism module, a three-level convolutional feature extraction layer, and a ConvLSTM module.

[0056] The input data of the spatial encoding module 151 is a plurality of smoke distribution matrices at different consecutive time points. The smoke distribution matrix is input to the dilated convolution layer. The dilated convolution layer is used to expand the receptive field and capture smoke-related information in a larger range. The output feature map of the dilated convolution layer is input to the spatial attention mechanism module; the spatial attention mechanism module calculates the importance weight of each position, highlights the key areas, and automatically weakens the abnormal points of the sensor, such as points with weights lower than 0.2. The spatial attention mechanism module performs spatial attention calculation on the output feature map of the dilated convolution, applies the weights to the output feature map of the dilated convolution, and obtains the weighted feature map; the three-level volume The convolution feature extraction layer extracts spatiotemporal features from the feature map output by the spatial attention mechanism module to obtain a spatiotemporal feature map. The first-level convolution extraction layer is used to extract local concentration information and can use a 3×3 convolution kernel to extract local features. The second-level convolution extraction layer is used to capture regional diffusion patterns and can use a 5×5 convolution kernel to capture regional features in a larger range. The third-level convolution extraction layer is used to extract global smoke movement trends and uses a 7×7 convolution kernel to extract global features. The ConLSTM module is used to process multiple continuous spatiotemporal feature maps, capture the changing trend in the time series, and output a spatial attention feature map for subsequent task processing.

[0057] The time series feature extraction module 152 is used to capture the inertial characteristics of the smoke exhaust window and smoke exhaust fan control, identify the historical dependency of equipment operation, and analyze the time-varying interaction between natural smoke exhaust and mechanical smoke exhaust. It obtains the time series characteristics of the mechanical smoke exhaust equipment and the time series characteristics of the natural smoke exhaust equipment based on the data of the mechanical smoke exhaust equipment and the natural smoke exhaust equipment, respectively. The data of the mechanical smoke exhaust equipment and the natural smoke exhaust equipment are the dynamic behavior historical data of the smoke exhaust fan and the smoke exhaust window, respectively. The data of the mechanical smoke exhaust equipment include the fan speed, current, static pressure, and filter pressure difference at different time points. The data of the natural smoke exhaust equipment include the opening of the smoke exhaust window, the wind speed outside the window, the indoor and outdoor temperature difference, and the historical smoke exhaust efficiency at different time points.

[0058] The time series feature extraction module 152 includes a parallel GRU module and a TCN module. GRU can capture the long-term dependencies of time series, while TCN can efficiently extract local time features. By combining these two models in parallel, their advantages can be fully utilized to achieve more comprehensive feature extraction. Among them, GRU (Gated Recurrent Unit) is a recurrent neural network that can solve the gradient vanishing and gradient exploding problems of traditional RNN when processing long sequence data. By introducing a "gating mechanism" to control the flow of information, it can effectively capture the long-term dependencies in time series data; TCN (Time Convolutional Network) is a time series modeling architecture based on convolutional neural networks, which is specifically used to process time series data.

[0059] The GRU module includes a two-layer GRU layer. The first layer GRU captures short-term fluctuations, and the second layer GRU identifies long-term patterns. The data of mechanical smoke exhaust equipment and natural smoke exhaust equipment are processed by the GRU module respectively, and the long-term time characteristics of the mechanical smoke exhaust equipment and natural smoke exhaust equipment are output.

[0060] The TCN module is used to extract the local time features of the time series. The data of the mechanical smoke exhaust equipment and the natural smoke exhaust equipment are processed by the TCN module respectively, and the local time features of the mechanical smoke exhaust equipment and the natural smoke exhaust equipment are output.

[0061] The long-term time features and local time features of the mechanical smoke exhaust device are fused, and the long-term time features and local time features of the natural smoke exhaust device are fused to obtain a comprehensive feature representation, and the time series features of the mechanical smoke exhaust device and the time series features of the natural smoke exhaust device are output.

[0062] The cross-attention module 153 is used to generate a spatiotemporal coupling weight matrix representing the interference region based on the temporal and spatial characteristics of the mechanical and natural smoke exhaust systems, namely, the temporal characteristics and position parameters of the mechanical and natural smoke exhaust systems. The cross-attention module 153 interacts the characteristic flows of the natural and mechanical smoke exhaust systems through multi-head attention. The output spatiotemporal coupling weight matrix indicates the region where the flows of the two systems cancel each other out, namely, the interference region. The position parameters of the mechanical smoke exhaust system include the x-coordinate, y-coordinate, distance from the nearest smoke exhaust window, and installation height, while the position parameters of the natural smoke exhaust system include the x-coordinate, y-coordinate, and orientation angle.

[0063] The cross-attention module 153 maps the input sequence to the query, key, and value spaces respectively, obtains the attention weight by calculating the dot product of the query and the key, and uses the attention weight to perform weighted summation on the value to obtain the spatiotemporal coupling weight matrix.

[0064] The interference suppression module 154 is used to obtain a suppression heat map based on the spatiotemporal coupling weight matrix, the position parameters of the natural smoke exhaust equipment and the mechanical smoke exhaust equipment. The suppression heat map provides a physically reasonable feature representation for the collaborative decision-making module 155, showing the degree of suppression at each position in the space.

[0065] Interference suppression module 154 includes an interference intensity analysis unit and a suppression coefficient generation unit. The spatiotemporal coupling weight matrix of cross-attention module 154 is input to the interference intensity analysis unit, which uses 3D convolution to extract the spatiotemporal features of the spatiotemporal coupling weight matrix. These spatiotemporal features are then subjected to multi-head attention and maximum pooling operations to obtain intermediate features. The multi-head attention mechanism is used to analyze the relationship between devices, while the maximum pooling operation is used to compress the output of the multi-head attention in the time and window dimensions. Finally, the interference intensity analysis unit uses a fully connected layer to map the intermediate features into interference intensity scores in the range [0, 1].

[0066] The suppression coefficient generation unit is used to generate a suppression coefficient based on the interference intensity score. The suppression coefficient represents the degree of interference of each smoke exhaust device. A higher suppression coefficient means that the smoke exhaust device is subject to greater interference and requires more suppression, and vice versa. Although the interference intensity score directly reflects the degree of interference between smoke exhaust devices, these scores may be too sensitive or not sensitive enough in certain intervals. For example, the score may change too quickly or too slowly in certain intervals, making it difficult for the collaborative decision-making module to effectively utilize this information. The suppression coefficient unit maps the score to a more appropriate range through a nonlinear function (sigmoid function), which can better reflect the actual interference impact. Moreover, by setting the lower limit of the suppression coefficient, it can ensure that certain characteristic information is retained even in high-interference areas. This is very important in practical applications, because completely suppressing certain areas may cause information loss and affect the overall performance of the system.

[0067] The suppression coefficient generation unit first adjusts the steepness of the sigmoid function based on the average value of the interference intensity score. Specifically, the mean of the interference intensity score is calculated to obtain a scalar, and the mean is multiplied by 10 to obtain a preliminary steepness parameter. The preliminary steepness parameter is limited to a preset interval, such as between 5.0 and 20.0. If the preliminary steepness parameter is less than the minimum value of the preset interval, the minimum value is set as the steepness parameter. If the preliminary steepness parameter is greater than the maximum value of the preset interval, the maximum value is set as the steepness parameter. If the preliminary steepness parameter is within the preset interval, the preliminary steepness parameter is set as the steepness parameter. This is to ensure that the steepness parameter is not too large or too small, thereby ensuring the stability and effectiveness of the sigmoid function.

[0068] The suppression coefficient generation unit obtains the suppression coefficient according to the steepness parameter and the interference intensity score, as shown in the following formula:

[0069] s=sigmoid(k*(a-0.5))

[0070] Where s is the suppression coefficient, sigmoid() is the sigmoid function, k is the steepness parameter, and a is the interference intensity score.

[0071] The interference suppression module 154 maps the coordinate values of the smoke exhaust equipment and the suppression coefficient into a two-dimensional matrix according to the suppression coefficient and the position parameters of the smoke exhaust equipment, thereby forming a suppression heat map.

[0072] The collaborative decision module 155 determines the fan speed of each exhaust fan and the opening of the exhaust window according to the spatial attention feature map and the suppression heat map. The collaborative decision module 155 adopts a reinforcement learning network, including a strategy module and a value judgment module.

[0073] The strategy module equips each natural smoke exhaust device and mechanical smoke exhaust device with an independent strategy sub-network. The spatial attention feature map, inhibition heat map, and the location parameters of the smoke exhaust device are input into the strategy sub-network to obtain the action probability distribution of the smoke exhaust device, such as the change in the opening of the smoke exhaust window or the change in the speed of the fan. The value judgment module establishes an independent value evaluation model for each smoke exhaust device and calculates the advantage function value of each state-action pair. The advantage function is:

[0074] A(s,a)=β1Alocal(s,a)+β2Aglobal(s,a)

[0075] =β1(Qi-μ Qi ) / σ Qi +β2α·ΔCsys / Δt

[0076] Among them, β1, β2, β3 are weight coefficients, Alocal(s,a) is the local advantage of the device, Aglobal(s,a) is the global advantage of the system, Atime(s,a) is the timing advantage, Qi is the action value of smoke exhaust device i, μ Qi and σ Qi are the mean and standard deviation of Qi, α is the weight of the smoke exhaust effect, ΔCsys is the rate of change of the system smoke exhaust efficiency, and Δt is the time interval.

[0077] Then, use the calculated advantage function value to update the policy subnetwork and establish the objective function:

[0078] L(θ)=E t [min(r t (θ)A(s,a),clip(r t (θ),1-∈,1+∈)A(s,a))]

[0079] Where θ is the updated policy network parameter, ∈ is the clipping parameter, and r t (θ) is the ratio of the old and new strategies, clip(r t (θ),1-∈,1+∈) is the clipping function, and the contrast ratio r t (θ) is clipped and restricted to the range of [1-∈, 1+∈] to prevent the policy update from being too large. A(s, a) is the advantage function.

[0080] The advantage function and the objective function are combined to update the parameters of the strategy subnetwork. After multiple iterative updates, the objective function is maximized. The action that maximizes the objective function, namely the fan speed of each smoke exhaust fan and the opening of the smoke exhaust window, is output as the optimal strategy.

[0081] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0082] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. For system embodiments, since they largely correspond to method embodiments, their description is relatively simple. For relevant parts, references to the description of the method embodiments are sufficient.

[0083] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0084] The methods and apparatus of the present disclosure may be implemented in many ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers recording media that store programs for executing the methods according to the present disclosure.

[0085] It should also be noted that, in the apparatus, equipment and method of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present disclosure. The above description of the disclosed aspects is provided to enable any technician in this field to make or use the present disclosure. Various modifications to these aspects will be very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown here, but to the widest range consistent with the principles and novel features disclosed herein.

[0086] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. An intelligent underground space smoke exhaust system, characterized in that: include: Mechanical smoke exhaust equipment, including a smoke exhaust window, wherein the smoke exhaust window has an adjustable opening; Natural smoke exhaust equipment, including a smoke exhaust fan, wherein the smoke exhaust fan has an adjustable fan speed; A sensing module, comprising a sensor device, wherein the sensor device is used to monitor environmental parameters in the underground space in real time; an identification module, configured to determine a smoke distribution matrix based on coordinate parameters of the sensor device and the environmental parameters; The control module is used to dynamically adjust the fan speed of the smoke exhaust fan and the opening of the smoke exhaust window according to the data of the smoke distribution matrix, the mechanical smoke exhaust equipment and the natural smoke exhaust equipment, so as to reduce the mutual interference between the natural smoke exhaust equipment and the mechanical smoke exhaust equipment.

2. The system according to claim 1, wherein: The sensor equipment includes a temperature sensor and a smoke sensor. The sensor equipment is arranged on the ceiling of the underground space and covers the entire underground space. The perception module obtains real-time environmental parameters of various locations in the underground space.

3. The system according to claim 2, characterized in that The identification module obtains the spatial information of the underground space, determines the shortest path distance between any two sensor devices based on the spatial information of the underground space and the coordinate parameters of any two sensor devices, and determines the shortest path distance between each predicted point and all sensor devices based on the spatial information of the underground space, the coordinate parameters of the sensor devices and the coordinate parameters of the predicted points.

4. The system according to claim 3, characterized in that The identification module determines a weight vector based on the shortest path distance between any two of the sensor devices and the environmental parameters, obtains the predicted environmental parameters of the prediction point based on the shortest path distance between each prediction point and all sensor devices and the weight vector, and obtains the flue gas distribution matrix based on the predicted environmental parameters and coordinate parameters of the prediction point and the environmental parameters and coordinate parameters of the sensor devices.

5. The system according to claim 1, wherein: The control module includes a spatial coding module, a temporal feature extraction module, a cross-attention module, an interference suppression module and a collaborative decision-making module. The control module inputs multiple smoke distribution matrices at different consecutive time points into the spatial coding module to obtain a spatial attention feature map.

6. The system according to claim 5, characterized in that The temporal feature extraction module includes a parallel GRU module and a TCN module. The data of the mechanical smoke exhaust device and the natural smoke exhaust device are respectively output through the GRU module to output the long-term time features of the mechanical smoke exhaust device and the natural smoke exhaust device. The data of the mechanical smoke exhaust device and the natural smoke exhaust device are respectively output through the TCN module to output the local time features of the mechanical smoke exhaust device and the natural smoke exhaust device. The long-term time features and local time features of the mechanical smoke exhaust device are fused, and the long-term time features and local time features of the natural smoke exhaust device are fused to output the temporal features of the mechanical smoke exhaust device and the temporal features of the natural smoke exhaust device.

7. The system according to claim 6, characterized in that The timing characteristics and position parameters of the mechanical smoke exhaust equipment and the timing characteristics and position parameters of the natural smoke exhaust equipment are input into the cross-attention module to obtain a spatiotemporal coupling weight matrix representing the interference area. The interference suppression module is used to obtain a suppression heat map based on the spatiotemporal coupling weight matrix, the position parameters of the natural smoke exhaust equipment and the mechanical smoke exhaust equipment.

8. The system according to claim 7, characterized in that The interference suppression module includes an interference intensity analysis unit and a suppression coefficient generation unit. The interference intensity analysis unit extracts the spatiotemporal features of the spatiotemporal coupling weight matrix. The spatiotemporal features are sequentially subjected to multi-head attention and maximum pooling operations to obtain intermediate features, and a fully connected layer is used to map the intermediate features to interference intensity scores. The suppression coefficient generation unit adjusts the steepness parameter of the sigmoid function according to the average value of the interference intensity score. The suppression coefficient generation unit uses the sigmoid function to obtain the suppression coefficient according to the steepness parameter and the interference intensity score. The interference suppression module forms a suppression heat map based on the suppression coefficient and the position parameters of the smoke exhaust equipment.

9. The system according to claim 8, characterized in that The collaborative decision-making module determines the fan speed of each smoke exhaust fan and the opening of the smoke exhaust window according to the spatial attention feature map and the suppression heat map.

10. The system according to claim 9, characterized in that The collaborative decision-making module includes a strategy module and a value judgment module. The strategy module is equipped with an independent strategy sub-network for each natural smoke exhaust device and mechanical smoke exhaust device. The spatial attention feature map, the inhibition heat map and the position parameters of the smoke exhaust device are input into the strategy sub-network to obtain the action probability distribution of the smoke exhaust device. The value judgment module establishes an independent value evaluation model for each smoke exhaust device, calculates the advantage function value and the objective function of each state-action pair, updates the parameters of the strategy sub-network according to the advantage function and the objective function, and after multiple iterative updates, outputs the fan speed of each smoke exhaust fan and the opening of the smoke exhaust window that maximizes the objective function.

Images