Smoke exhaust fan control system and method

Abstract

The invention discloses a smoke exhaust fan control system and method, and relates to the technical field of fire fighting systems.The working performance of a smoke exhaust fan is predicted through a loss calculation unit, the working threshold value of the smoke exhaust fan is obtained through a temperature curve unit, and early smoke characteristics are recognized through a smoke monitoring unit; the smoke diffusion speed and the time required for occupying the preset proportion areas in the different fire protection zones are obtained through the smoke diffusion unit, then the first model and the second model are constructed through the temperature change construction unit, whether the smoke exhaust fan reaches the temperature threshold value or not in different states is obtained, early warning of different levels is carried out, and corresponding measures are executed. The situation that the smoke exhaust efficiency of the whole fire-fighting smoke exhaust system is reduced due to the fact that the performance of the smoke exhaust fan is reduced due to the temperature is reduced as much as possible, that is, the smoke exhaust fan is accurately regulated and controlled through the central control unit, and the smoke exhaust efficiency of the whole fire-fighting smoke exhaust system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire protection systems, and in particular to a smoke exhaust fan control system and method. Background Art

[0002] In modern buildings, the fire smoke exhaust system, as an important part of the safety system, plays a vital role. It can quickly remove smoke when a fire occurs, providing a valuable time window for personnel evacuation and fire rescue. This system is usually composed of key components such as smoke exhaust ports, smoke exhaust ducts, smoke exhaust fans, control systems and fire dampers. When a fire occurs, these components work together to exhaust the smoke in the building.

[0003] In small buildings, it is usually composed of one smoke exhaust fan and multiple smoke exhaust ducts. When the smoke detector detects a certain concentration of smoke, the smoke exhaust fan will work to exhaust the smoke; but in large buildings, there are multiple fire zones, each of which contains a smoke exhaust fan. When a fire occurs in a single fire zone, the corresponding smoke exhaust fan and the smoke exhaust fans of other fire zones will start working. However, the smoke exhaust fan will generate more heat when working, and since smoke also carries a lot of heat, the working environment temperature of the smoke exhaust fan will increase, thereby reducing the optimal performance of the smoke exhaust fan, resulting in a decrease in smoke exhaust air volume and smoke exhaust efficiency, and ultimately affecting the smoke exhaust efficiency of the entire fire smoke exhaust system. Summary of the Invention

[0004] In view of this, the present application provides a smoke exhaust fan control system and method to achieve precise regulation of the smoke exhaust fan and improve the smoke exhaust efficiency of the entire fire smoke exhaust system.

[0005] A first aspect of the present application provides a smoke exhaust fan control system, comprising:

[0006] Loss calculation unit: Builds and trains a loss model. Based on the trained loss model, it calculates the performance loss of all smoke exhaust fans in each fire zone to obtain loss calculation results.

[0007] a temperature curve acquisition unit for acquiring a first coordinate curve of the maximum power of the smoke exhaust fan as a function of temperature, and cleaning the data in the first coordinate curve based on the loss calculation result; and determining, based on the cleaned first coordinate curve, a temperature corresponding to a maximum decrease in the maximum power of the smoke exhaust fan, and recording the temperature as a temperature threshold;

[0008] Temperature change construction unit: In the preset simulation software, a first model is constructed for the temperature change of the smoke exhaust fan from startup to operation at maximum power in a smoke-free state; and a second model is constructed for the temperature change of the smoke exhaust fan when the smoke exhaust fan is operated at maximum power in a smoke-exposed state; the maximum power of the smoke exhaust fan in the first model and the second model are both the actual maximum power calculated by the loss model;

[0009] Smoke monitoring unit: Builds and trains a smoke recognition model. Based on the trained smoke recognition model, it identifies early smoke features in each fire zone.

[0010] Smoke diffusion unit: Builds and trains a smoke diffusion model, and simulates smoke diffusion in each fire zone based on the trained smoke diffusion model;

[0011] Central control unit: When a fire occurs in any fire zone, the smoke exhaust fan in the corresponding fire zone is turned on, and the data in the loss calculation unit, the temperature curve unit, the temperature change construction unit and the smoke diffusion unit are collected for analysis and processing, and the smoke exhaust fans in the remaining fire zones are precisely controlled.

[0012] In a possible implementation of the first aspect, building a loss model and training it includes:

[0013] Construct a loss function group for the air volume, air pressure, maximum power, efficiency and energy consumption of the smoke exhaust fan, specifically:

[0014]

[0015] L Q is the loss ratio of air volume, ω Q is the weight coefficient of air volume, Q ′ is the actual air volume, Q is the target air volume, L S is the loss ratio of wind pressure, ω S is the weight coefficient of wind pressure, S ′ is the actual wind pressure, S is the target wind pressure, L P is the maximum power loss ratio, ω P is the weight coefficient of maximum power, P ′ is the actual maximum power, P is the target maximum power, L η is the loss ratio of conversion efficiency, ω η is the weight coefficient of conversion efficiency, η ′ is the actual conversion efficiency, η is the target conversion efficiency, L E is the energy loss ratio, ω E is the weight coefficient of energy consumption, E ′is the actual energy consumption, and E is the target energy consumption;

[0016] Based on the loss function group, the loss coefficient of the smoke exhaust fan is constructed, specifically:

[0017]

[0018] Obtaining the loss coefficient of the smoke exhaust fan at multiple time scales to obtain an acquisition result;

[0019] Based on the obtained result, with the use time of the smoke exhaust fan as the horizontal coordinate and the loss coefficient of the smoke exhaust fan as the vertical coordinate, a coordinate curve showing the change of the loss coefficient with the use time is constructed and fitted.

[0020] In a possible implementation of the first aspect, performance loss calculation is performed on all smoke exhaust fans in each fire zone, and loss calculation results obtained include:

[0021] Obtaining the usage time of any exhaust fan as the first usage time, and the coordinate curve obtained through fitting as the second coordinate curve;

[0022] Predicting a loss coefficient at the first usage time node based on the fitted second coordinate curve, recorded as a first loss coefficient;

[0023] Based on the first loss coefficient, a loss calculation result of the corresponding smoke exhaust fan is calculated and obtained.

[0024] In a possible implementation of the first aspect, the cleaning of data in the first coordinate curve based on the loss calculation result includes:

[0025] Based on the loss calculation result, obtaining the actual maximum power of the smoke exhaust fan;

[0026] In the first coordinate curve, the data point corresponding to the actual maximum power is matched, and the curve data before the data point is cleaned.

[0027] In a possible implementation of the first aspect, determining the temperature threshold based on the first coordinate curve after the cleaning process includes:

[0028] In the first coordinate curve, taking the data point corresponding to the actual maximum power as a starting point, dividing the first coordinate curve after the data point into a plurality of equal intervals, and calculating the rate of change of the first coordinate curve in each interval to obtain a rate of change calculation result;

[0029] Based on the change rate calculation result, the interval corresponding to the maximum change rate is screened and recorded as the first interval;

[0030] The temperature value of the left port in the first interval is recorded as the temperature threshold.

[0031] In a possible implementation of the first aspect, building and training a smoke recognition model includes:

[0032] Collect surveillance video data of multiple time scales as sample sets and store them in the database;

[0033] Performing data enhancement on the sample set in the database to expand the data volume of the sample set;

[0034] Manually label the data-augmented sample set;

[0035] Based on the manually annotated sample set, a region proposal network is used to generate candidate regions containing smoke;

[0036] A convolutional neural network is used to perform classification and regression training on the candidate areas, and output the category and location coordinates of the smoke.

[0037] In a possible implementation of the first aspect, building and training a smoke diffusion model includes:

[0038] Constructing a smoke diffusion model and setting initial parameters for the smoke diffusion model, wherein the initial parameters include BIM data of the fire zone, the location of the smoke source, and the physical quantity of the smoke source;

[0039] Establish wind force model, diffusion force model and air resistance model and solve them separately, and combine the solution results to obtain external force data;

[0040] Solving the smoke diffusion model based on the set initial parameters and the combined external force data, and updating the velocity field, temperature field, and density field of the smoke;

[0041] Based on the size of the fire zone and the boundaries of obstacles, the movement of smoke is constrained, and the velocity field, temperature field and density field of the smoke are corrected;

[0042] Based on the modified velocity field, temperature field and density field of the smoke in the smoke diffusion model, the diffusion of the smoke is simulated and drawn in real time.

[0043] In a possible implementation of the first aspect, when a fire situation occurs in any fire zone, turning on the smoke exhaust fan in the corresponding fire zone includes:

[0044] Based on the smoke monitoring unit, obtain the type of smoke and the location coordinates of the smoke in any fire zone;

[0045] If the smoke is determined to be fire smoke, the smoke exhaust fan of the corresponding fire zone is turned on, and the location coordinates of the fire smoke are uploaded to the preset terminal.

[0046] In one possible implementation of the first aspect, the precise control of the smoke exhaust fans in the remaining fire zones includes:

[0047] When there is fire smoke in fire zone A, the time point at which the fire smoke occurs is recorded as t0;

[0048] Based on the smoke diffusion model, the time point when the fire smoke reaches the boundary of the adjacent fire zone B is recorded as t2, the time point when the fire smoke fills a preset proportion of the fire zone B is recorded as t3, and the time point when the fire smoke fills the entire fire zone B is recorded as t4;

[0049] Based on the loss model, the actual maximum power of the smoke exhaust fan in the fire zone B is calculated, and the time required for the smoke exhaust fan in the fire zone B to start and operate at the actual maximum power is obtained and recorded as T;

[0050] Calculate the difference between (t2-t0) and, in combination with T, control the start time of the smoke exhaust fan in the fire zone B to t1, so that when the fire smoke reaches the boundary of the fire zone B, the smoke exhaust fan in the fire zone B can operate at the actual maximum power;

[0051] In the time interval [t1, t3], based on the first model, the maximum value that the temperature of the smoke exhaust fan in the fire zone B can reach is output, recorded as the first temperature, and it is judged whether the first temperature exceeds the temperature threshold. If so, a first-level warning is issued and the smoke exhaust fans in all adjacent fire zones of the fire zone B are turned on. If not, in the time interval [t3, t4], based on the second model, the maximum value that the temperature of the smoke exhaust fan in the fire zone B can reach is output, recorded as the second temperature, and it is judged whether the second temperature exceeds the temperature threshold. If so, a second-level warning is issued and the smoke exhaust fans in a preset number of adjacent fire zones of the fire zone B are turned on. If not, no action is taken. The priority of the first-level warning is higher than the second-level warning.

[0052] A second aspect of the present application provides a smoke exhaust fan control method, comprising:

[0053] Construct and train a loss model. Based on the trained loss model, calculate the performance loss of all smoke exhaust fans in each fire zone to obtain loss calculation results.

[0054] Obtaining a first coordinate curve of the maximum power of the smoke exhaust fan as a function of temperature, and cleaning the data in the first coordinate curve based on the loss calculation result; determining, based on the cleaned first coordinate curve, a temperature corresponding to a maximum decrease in the maximum power of the smoke exhaust fan, and recording the temperature as a temperature threshold;

[0055] In the preset simulation software, a first model is constructed for the temperature change of the smoke exhaust fan from startup to operation at maximum power in a smoke-free state; and a second model is constructed for the temperature change of the smoke exhaust fan when the smoke exhaust fan is operated at maximum power in a smoke-presence state; the maximum power of the smoke exhaust fan in the first model and the second model are both the actual maximum power calculated by the loss model;

[0056] Build and train a smoke recognition model, and then identify early smoke features in each fire zone based on the trained smoke recognition model.

[0057] Build and train a smoke diffusion model, and simulate smoke diffusion in each fire zone based on the trained smoke diffusion model;

[0058] When a fire occurs in any fire zone, the smoke exhaust fan in the corresponding fire zone is turned on, and the data in the loss model, the temperature threshold, the first model, the second model and the smoke diffusion model are collected for analysis and processing, and the smoke exhaust fans in the remaining fire zones are precisely controlled.

[0059] Compared to the prior art, the present application provides a smoke exhaust fan control system and method, comprising: a loss calculation unit, a temperature curve acquisition unit, a temperature change construction unit, a smoke monitoring unit, and a central control unit;

[0060] Since the performance of the smoke exhaust fan will be reduced due to factors such as daily use and wear and tear, this application uses the loss calculation unit to predict and calculate the performance of the smoke exhaust fan after wear and tear, and uses it as the basic data of the smoke exhaust fan (such as maximum power, maximum air volume, etc.) for subsequent modules;

[0061] The temperature threshold of the smoke exhaust fan is obtained through the temperature curve unit. The setting basis is that as the temperature of the smoke exhaust fan increases, its working performance will be affected. When the temperature threshold is exceeded, its working performance decreases significantly. Therefore, the present application obtains a first coordinate curve and uses the loss calculation result in the loss calculation unit to clean the data in the first coordinate curve. Then, in the coordinate curve after data cleaning, the maximum power drop amplitude is used as an indicator to obtain the temperature threshold of the smoke exhaust fan;

[0062] In order to achieve precise control of the smoke exhaust fan, the present application also constructs a temperature change unit. In the preset simulation software, a first model of the temperature change of the smoke exhaust fan from startup to operation at maximum power in a smoke-free state is constructed, and a second model of the temperature change of the smoke exhaust fan when the smoke exhaust fan operates at maximum power in a smoke-presence state is constructed. It should be noted that the presence / absence of smoke state is determined by the smoke encroaching on the preset proportion area of ​​the fire protection zone. The reason why the first model and the second model are constructed by the simulation software is that if the smoke does not encroach on the preset proportion area of ​​the fire protection zone, and the operating temperature of the smoke exhaust fan has reached the temperature threshold (obtained by the first model), and the smoke encroaches on the preset proportion area of ​​the fire protection zone, and the operating temperature of the smoke exhaust fan reaches the temperature threshold (obtained by the second model), there is obviously a difference in the warning degree and treatment measures.

[0063] Since the existing technology only uses smoke concentration to trigger fire warnings and start subsequent smoke exhaust fans, it is impossible to immediately implement subsequent actions by discovering early smoke characteristics. Therefore, this application uses a smoke monitoring unit to build a smoke recognition model and train it. Based on the trained smoke recognition model, the early smoke characteristics in each fire zone are identified to achieve the goal of discovering fire public opinion in the fastest time and taking subsequent measures.

[0064] This application simulates smoke diffusion by constructing a smoke diffusion unit to obtain the speed of smoke diffusion and the time required to invade the preset proportion area of ​​other fire protection zones;

[0065] Finally, the central control unit integrates the data from the loss calculation unit, temperature curve unit, temperature change construction unit, smoke monitoring unit and smoke diffusion unit to achieve precise control of the smoke exhaust fan and improve the smoke exhaust efficiency of the entire fire smoke exhaust system.

[0066] Specifically, the working performance of the smoke exhaust fan is predicted through the loss calculation unit, the working threshold of the smoke exhaust fan is obtained through the temperature curve unit, the early smoke characteristics are identified through the smoke monitoring unit, the speed of smoke diffusion and the time required to occupy the preset proportion area in different fire protection zones are obtained through the smoke diffusion unit, and then the first model and the second model are constructed through the temperature change construction unit to obtain whether the smoke exhaust fan reaches the temperature threshold under different conditions, so as to carry out different levels of early warning and implement corresponding measures, so as to minimize the decline in smoke exhaust efficiency of the entire fire smoke exhaust system due to the decline in smoke exhaust fan performance caused by temperature.

[0067] Its beneficial effects are as follows: the present application constructs a loss calculation unit, a temperature curve unit, a temperature change construction unit, a smoke monitoring unit, a smoke diffusion unit and a central control unit, wherein the central control unit integrates the data of the loss calculation unit, the temperature curve unit, the temperature change construction unit, the smoke monitoring unit and the smoke diffusion unit, specifically predicts the working performance of the smoke exhaust fan through the loss calculation unit, obtains the working threshold of the smoke exhaust fan through the temperature curve unit, identifies early smoke characteristics through the smoke monitoring unit, obtains the speed of smoke diffusion and the time required to occupy the preset proportion area in different fire zones through the smoke diffusion unit, and then constructs the first model and the second model through the temperature change construction unit to obtain whether the smoke exhaust fan reaches the temperature threshold under different conditions, to carry out different levels of warnings and implement corresponding measures, so as to minimize the decline in the smoke exhaust efficiency of the entire fire smoke exhaust system due to the decline in the performance of the smoke exhaust fan caused by temperature, that is, to improve the smoke exhaust efficiency of the entire fire smoke exhaust system by achieving precise control of the smoke exhaust fan. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0069] Figure 1 This is a schematic diagram of the composition of a smoke exhaust fan control system provided in an embodiment of the present application;

[0070] Figure 2 This is a flow chart of a smoke exhaust fan control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0072] In this application, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0073] Example 1

[0074] From the above background technology, it can be seen that in large buildings, there are multiple fire zones, and each fire zone includes a smoke exhaust fan. When a fire occurs in a fire zone, the corresponding smoke exhaust fan and the smoke exhaust fans of other fire zones will start working, but the smoke exhaust fan will generate more heat when working, and because the smoke also carries a lot of heat, the working environment temperature of the smoke exhaust fan will increase, thereby reducing the optimal performance of the smoke exhaust fan, resulting in a decrease in the smoke exhaust air volume and smoke exhaust efficiency, and ultimately affecting the smoke exhaust efficiency of the entire fire smoke exhaust system.

[0075] In the existing technology, when a certain concentration of smoke is detected by the smoke detector, the smoke exhaust fan of the corresponding fire zone is turned on and the smoke exhaust fans in other fire zones are turned on synchronously. However, this control method ignores the impact of temperature on the working performance of the smoke exhaust fan. Because the smoke exhaust fan will generate a lot of heat when working, the smoke it generates will also carry a lot of heat. Therefore, how to achieve precise control of the smoke exhaust fan to reduce the impact of temperature on the working performance of the smoke exhaust fan, thereby improving the smoke exhaust efficiency of the entire fire smoke exhaust system.

[0076] Therefore, this application provides a smoke exhaust fan control system, such as Figure 1 Shown, including:

[0077] Loss calculation unit: Builds and trains a loss model. Based on the trained loss model, it calculates the performance loss of all smoke exhaust fans in each fire zone to obtain loss calculation results.

[0078] a temperature curve acquisition unit for acquiring a first coordinate curve of the maximum power of the smoke exhaust fan as a function of temperature, and cleaning the data in the first coordinate curve based on the loss calculation result; and determining, based on the cleaned first coordinate curve, a temperature corresponding to a maximum decrease in the maximum power of the smoke exhaust fan, and recording the temperature as a temperature threshold;

[0079] Temperature change construction unit: In the preset simulation software, a first model is constructed for the temperature change of the smoke exhaust fan from startup to operation at maximum power in a smoke-free state; and a second model is constructed for the temperature change of the smoke exhaust fan when the smoke exhaust fan is operated at maximum power in a smoke-exposed state; the maximum power of the smoke exhaust fan in the first model and the second model are both the actual maximum power calculated by the loss model;

[0080] Smoke monitoring unit: Builds and trains a smoke recognition model. Based on the trained smoke recognition model, it identifies early smoke features in each fire zone.

[0081] Smoke diffusion unit: Builds and trains a smoke diffusion model, and simulates smoke diffusion in each fire zone based on the trained smoke diffusion model;

[0082] Central control unit: When a fire occurs in any fire zone, the smoke exhaust fan in the corresponding fire zone is turned on, and the data in the loss calculation unit, the temperature curve unit, the temperature change construction unit and the smoke diffusion unit are collected for analysis and processing, and the smoke exhaust fans in the remaining fire zones are precisely controlled.

[0083] Among them, due to the influence of working years and working environment, the working parameters of the smoke exhaust fan will decrease to a certain extent compared with the calibrated parameters. Therefore, this embodiment constructs a loss model and trains it. The construction logic of the loss model is to construct a loss function group for air volume, air pressure, maximum power, efficiency and energy consumption, and calculate the loss ratio value of air volume, air pressure, maximum power, efficiency and energy consumption through the loss function group. Then, the above loss ratio values ​​are summed and their mean is calculated to obtain the loss coefficient of the smoke exhaust fan; then, the loss coefficient of the smoke exhaust fan under multiple time scales is collected, and a coordinate curve of the loss system changing with time is constructed for fitting processing. The coordinate curve data after fitting processing is used as the training set of the loss model to train the model, and then the trained loss model is used to predict the performance loss of the smoke exhaust fan.

[0084] Among them, the performance loss of the smoke exhaust fan is calculated based on the trained loss model, that is, the usage time of the smoke exhaust fan is obtained and input into the loss model, and then the loss model predicts the loss coefficient of the smoke exhaust fan by obtaining the corresponding coordinate curve of the smoke exhaust fan after fitting processing, and the loss degree of the smoke exhaust fan is calculated by the loss coefficient, that is, the calibration parameters and the loss coefficient are used as the actual parameters of the smoke exhaust fan.

[0085] Before leaving the factory, smoke exhaust fans undergo various performance tests, including air volume, air pressure, efficiency, and high-temperature tests. The high-temperature test measures the performance changes of the smoke exhaust fan under high-temperature conditions. A first coordinate curve showing the temperature variation of the smoke exhaust fan can be obtained by compiling factory test data. Alternatively, the performance parameters of the smoke exhaust fan tested under conventional conditions can be theoretically deduced and converted to high-temperature conditions (for details, refer to the journal "The Effect of Temperature on Performance Curves and Characteristic Curves of Smoke Exhaust Fans and Ducts"). This first coordinate curve can then be obtained. Based on the loss calculation results, the actual maximum power of the smoke exhaust fan is then calculated by multiplying the maximum rated power of the smoke exhaust fan by the loss coefficient. Data exceeding the actual maximum power in the first coordinate curve is cleaned, and the remaining first coordinate curve is then divided into equal intervals. The decrease in the actual maximum power within each interval (i.e., the slope of the curve) is calculated. Using mathematical differentiation, when a sufficient number of intervals are divided, the data point with the maximum slope of the curve can be obtained. In this embodiment, the data point with the temperature value at the left end of the interval is used as the data point with the maximum slope of the curve, i.e., the temperature threshold point.

[0086] It should be noted that the reason why the concept of temperature threshold is set in this embodiment is that after analyzing a large amount of historical data of smoke exhaust fans, it was found that when different smoke exhaust fans exceed the corresponding temperature threshold, their working performance will drop significantly. Therefore, how to control the smoke exhaust fan not to reach the temperature threshold or reduce the working time of the smoke exhaust fan in an environment exceeding the temperature threshold, so as to improve the smoke exhaust efficiency of the smoke exhaust fan, is an urgent problem that needs to be solved.

[0087] Among them, in the preset simulation software, the first model and the second model in two states are constructed. Modern simulation software is already fully capable of simulating the heat generation process and its thermodynamic behaviors such as heat conduction, convection and radiation when the equipment is working (as well as multi-physical field coupling, such as smoke scenes, heat dissipation scenes, etc.). Regarding the selection of preset simulation software, ANSYS Fluent / Mechanical, COMSOL Multiphysics and OpenFOAM and other software can be used, and this embodiment does not make specific limitations.

[0088] Among them, a first model of the temperature change of the smoke exhaust fan from startup to maximum power in a smoke-free state is constructed, and a second model of the temperature change of the smoke exhaust fan when the smoke exhaust fan works at maximum power in a smoke-presence state is constructed. It should be noted that the smoke / no smoke state is determined by the smoke encroaching on the preset proportion area of ​​the fire protection zone. For example, if the preset proportion area of ​​the fire protection zone is set to 30%, when the smoke diffusion or encroachment on the fire protection zone does not reach 30%, it is determined that the smoke exhaust fan is working in a smoke-free state. When the smoke diffusion or encroachment on the fire protection zone exceeds 30%, it is determined that the smoke exhaust fan is working in a smoke-free state. The smoke exhaust fan is designed to work in a smoke-prone environment. The first and second models are constructed using simulation software because the degree of early warning and treatment measures are obviously different when the smoke does not invade 30% of the fire compartment and the operating temperature of the smoke exhaust fan has reached the temperature threshold (obtained through the first model). This is different from when the smoke invades 30% of the fire compartment and the operating temperature of the smoke exhaust fan reaches the temperature threshold (obtained through the second model). This embodiment uses the first and second models to determine the degree of early warning and adopt treatment measures, thereby achieving precise control of the smoke exhaust fan.

[0089] Among them, by constructing a smoke recognition model and training it, early smoke features are identified based on the trained smoke recognition model. Regarding the construction and training of the smoke recognition model, a deep learning method is adopted, specifically: by collecting surveillance video data of multiple time scales (such as one or two years) as a sample set, and then performing data enhancement on the sample set, that is, cropping, flipping, scaling, translating, etc. on the data in the sample set to achieve the effect of expanding the data volume of the sample set; then the sample set after data enhancement is manually labeled, and the labeled attributes include but are not limited to the smoke position and size, the confidence score of whether the smoke area triggers an alarm, the smoke concentration and the fire level; based on the labeled sample set, a region candidate network (RPN) is used to generate candidate areas containing smoke, and then a convolutional neural network (CNN) is used to classify and regress the candidate areas, and finally the category and location coordinates of the smoke are output.

[0090] Among them, a smoke diffusion model is constructed to simulate the diffusion of indoor smoke. In the process of simulating indoor smoke diffusion, in order to calculate the values ​​of physical quantities such as smoke speed, pressure, density and temperature at any time step, it is necessary to set initial parameters for the solution of the smoke model, including the BIM data of the fire zone, the location of the smoke source and the initial values ​​of the physical quantities of the smoke source (speed, density and temperature, etc.). In order to enhance the details of the smoke simulation, wind force, diffusion force and air resistance are used as external forces, and wind force, diffusion force and air resistance models are established respectively for solution. The solution is a relatively mature technology for those skilled in the art and will not be elaborated in detail in this embodiment. Then, based on the set initial parameters and the external forces obtained by the solution, the smoke diffusion model is solved, that is, the velocity field, temperature field, and density field of the smoke are updated at each time step. Then, based on the size of the fire zone and the boundary of the obstacle, the changes in the velocity, temperature, and density of the smoke after encountering the wall and obstacle are calculated, thereby correcting and constraining the movement of the smoke. Based on the smoke density field, velocity field, and temperature field calculated by the smoke diffusion model, the diffusion of the smoke is simulated and drawn in real time.

[0091] The central control unit analyzes and processes the data in the loss calculation unit, the temperature curve unit, the temperature change construction unit, and the smoke diffusion unit. The smoke monitoring unit identifies the presence of fire smoke in fire zone A and turns on the smoke exhaust fan of fire zone A. At the same time, the loss calculation unit calculates the loss coefficient of the smoke exhaust fans in all fire zones, and calculates the actual maximum efficiency of the smoke exhaust fans in all fire zones based on the loss coefficient. At the same time, the temperature curve acquisition unit obtains the temperature threshold of the smoke exhaust fans in all fire zones.

[0092] Based on the smoke diffusion model, the time point when the fire smoke reaches the boundary of the adjacent fire zone B is recorded as t2, the time point when the fire smoke fills a preset proportion area (30%) of the fire zone B is recorded as t3, and the time point when the fire smoke fills the entire fire zone B is recorded as t4;

[0093] Based on the loss model, the actual maximum power of the smoke exhaust fan in the fire zone B is calculated, and the time required for the smoke exhaust fan in the fire zone B to start and operate at the actual maximum power is obtained and recorded as T;

[0094] Calculate the difference between t2 and t0, and combine it with T to control the start-up time of the smoke exhaust fan in fire zone B to t1, that is, t2-t1 ≥ T, and preferably t2-t1 = T. That is, when the fire smoke reaches the boundary of fire zone B, the smoke exhaust fan in fire zone B can operate at maximum power. This can not only ensure smoke exhaust efficiency, but also reduce the large amount of heat generated by starting the smoke exhaust fan prematurely, which will affect the working performance of the smoke exhaust fan;

[0095] In the time interval [t1, t3], based on the first model, the maximum value that the smoke exhaust fan temperature in the fire zone B can reach is output, recorded as the first temperature, and it is determined whether the first temperature exceeds the temperature threshold. If so, a first-level warning is issued and the smoke exhaust fans in all adjacent fire zones of the fire zone B are turned on. This means that when the fire smoke only invades a small area of ​​the fire zone B, the working performance of the smoke exhaust fan is greatly affected. At this time, if the smoke exhaust fans in all adjacent areas are not turned on in advance, the smoke exhaust efficiency of the smoke exhaust fan will become lower and lower as the fire smoke invades more areas, thereby causing greater safety hazards. If not, in the time interval [t3, t4], based on the second model, the output The maximum value that the temperature of the smoke exhaust fan in the fire zone B can reach is recorded as the second temperature, and it is determined whether the second temperature exceeds the temperature threshold. If so, a second-level warning is issued and the smoke exhaust fans in a preset number (generally one or two) adjacent fire zones of the fire zone B are turned on. This means that when the fire smoke occupies a larger area of ​​the fire zone B, the working performance of the smoke exhaust fan will be greatly affected. Therefore, at this time, it is only necessary to turn on the smoke exhaust fans in one or two fire zones in advance to ensure the smoke exhaust efficiency of the entire smoke exhaust fire protection system and minimize the time when the working performance of the smoke exhaust fan decreases due to the working temperature. If not, no action is taken; the priority of the first-level warning is higher than that of the second-level warning.

[0096] In some embodiments, building and training a loss model includes:

[0097] Construct a loss function group for the air volume, air pressure, maximum power, efficiency and energy consumption of the smoke exhaust fan, specifically:

[0098]

[0099] L Q is the loss ratio of air volume, ω Q is the weight coefficient of air volume, Q ′ is the actual air volume, Q is the target air volume, L S is the loss ratio of wind pressure, ω S is the weight coefficient of wind pressure, S ′ is the actual wind pressure, S is the target wind pressure, L P is the maximum power loss ratio, ω P is the weight coefficient of maximum power, P ′ is the actual maximum power, P is the target maximum power, L η is the loss ratio of conversion efficiency, ω η is the weight coefficient of conversion efficiency, η ′ is the actual conversion efficiency, η is the target conversion efficiency, L E is the energy loss ratio, ωE is the weight coefficient of energy consumption, E ′ is the actual energy consumption, and E is the target energy consumption;

[0100] Based on the loss function group, the loss coefficient of the smoke exhaust fan is constructed, specifically:

[0101]

[0102] Obtaining the loss coefficient of the smoke exhaust fan at multiple time scales to obtain an acquisition result;

[0103] Based on the obtained result, with the use time of the smoke exhaust fan as the horizontal coordinate and the loss coefficient of the smoke exhaust fan as the vertical coordinate, a coordinate curve showing the change of the loss coefficient with the use time is constructed and fitted.

[0104] In some embodiments, the performance loss calculation is performed on all smoke exhaust fans in each fire zone, and the loss calculation results include:

[0105] Obtaining the usage time of any exhaust fan as the first usage time, and the coordinate curve obtained through fitting as the second coordinate curve;

[0106] Predicting a loss coefficient at the first usage time node based on the fitted second coordinate curve, recorded as a first loss coefficient;

[0107] Based on the first loss coefficient, a loss calculation result of the corresponding smoke exhaust fan is calculated and obtained.

[0108] In some embodiments, based on the loss calculation result, cleaning the data in the first coordinate curve includes:

[0109] Based on the loss calculation result, obtaining the actual maximum power of the smoke exhaust fan;

[0110] In the first coordinate curve, the data point corresponding to the actual maximum power is matched, and the curve data before the data point is cleaned.

[0111] In some embodiments, determining the temperature threshold based on the first coordinate curve after the cleaning process includes:

[0112] In the first coordinate curve, taking the data point corresponding to the actual maximum power as a starting point, dividing the first coordinate curve after the data point into a plurality of equal intervals, and calculating the rate of change of the first coordinate curve in each interval to obtain a rate of change calculation result;

[0113] Based on the change rate calculation result, the interval corresponding to the maximum change rate is screened and recorded as the first interval;

[0114] The temperature value of the left port in the first interval is recorded as the temperature threshold.

[0115] In some embodiments, building and training a smoke recognition model includes:

[0116] Collect surveillance video data of multiple time scales as sample sets and store them in the database;

[0117] Performing data enhancement on the sample set in the database to expand the data volume of the sample set;

[0118] Manually label the data-augmented sample set;

[0119] Based on the manually annotated sample set, a region proposal network is used to generate candidate regions containing smoke;

[0120] A convolutional neural network is used to perform classification and regression training on the candidate areas, and output the category and location coordinates of the smoke.

[0121] In some embodiments, constructing and training a smoke diffusion model includes:

[0122] Constructing a smoke diffusion model and setting initial parameters for the smoke diffusion model, wherein the initial parameters include BIM data of the fire zone, the location of the smoke source, and the physical quantity of the smoke source;

[0123] Establish wind force model, diffusion force model and air resistance model and solve them separately, and combine the solution results to obtain external force data;

[0124] Solving the smoke diffusion model based on the set initial parameters and the combined external force data, and updating the velocity field, temperature field, and density field of the smoke;

[0125] Based on the size of the fire zone and the boundaries of obstacles, the movement of smoke is constrained, and the velocity field, temperature field and density field of the smoke are corrected;

[0126] Based on the modified velocity field, temperature field and density field of the smoke in the smoke diffusion model, the diffusion of the smoke is simulated and drawn in real time.

[0127] In some embodiments, when a fire situation occurs in any fire zone, turning on the smoke exhaust fan in the corresponding fire zone includes:

[0128] Based on the smoke monitoring unit, obtain the type of smoke and the location coordinates of the smoke in any fire zone;

[0129] If the smoke is determined to be fire smoke, the smoke exhaust fan of the corresponding fire zone is turned on, and the location coordinates of the fire smoke are uploaded to the preset terminal.

[0130] In some embodiments, precisely controlling the smoke exhaust fans in the remaining fire zones includes:

[0131] When there is fire smoke in fire zone A, the time point at which the fire smoke occurs is recorded as t0;

[0132] Based on the smoke diffusion model, the time point when the fire smoke reaches the boundary of the adjacent fire zone B is recorded as t2, the time point when the fire smoke fills a preset proportion of the fire zone B is recorded as t3, and the time point when the fire smoke fills the entire fire zone B is recorded as t4;

[0133] Based on the loss model, the actual maximum power of the smoke exhaust fan in the fire zone B is calculated, and the time required for the smoke exhaust fan in the fire zone B to start and operate at the actual maximum power is obtained and recorded as T;

[0134] Calculate the difference between (t2-t0) and, in combination with T, control the start time of the smoke exhaust fan in the fire zone B to t1, so that when the fire smoke reaches the boundary of the fire zone B, the smoke exhaust fan in the fire zone B can operate at the actual maximum power;

[0135] In the time interval [t1, t3], based on the first model, the maximum value that the temperature of the smoke exhaust fan in the fire zone B can reach is output, recorded as the first temperature, and it is judged whether the first temperature exceeds the temperature threshold. If so, a first-level warning is issued and the smoke exhaust fans in all adjacent fire zones of the fire zone B are turned on. If not, in the time interval [t3, t4], based on the second model, the maximum value that the temperature of the smoke exhaust fan in the fire zone B can reach is output, recorded as the second temperature, and it is judged whether the second temperature exceeds the temperature threshold. If so, a second-level warning is issued and the smoke exhaust fans in a preset number of adjacent fire zones of the fire zone B are turned on. If not, no action is taken. The priority of the first-level warning is higher than the second-level warning.

[0136] Example 2

[0137] Based on the smoke exhaust fan control system provided in the first embodiment of the present application, the second embodiment of the present application also provides a smoke exhaust fan control method, such as Figure 2 Shown, including:

[0138] Construct and train a loss model. Based on the trained loss model, calculate the performance loss of all smoke exhaust fans in each fire zone to obtain loss calculation results.

[0139] Obtaining a first coordinate curve of the maximum power of the smoke exhaust fan as a function of temperature, and cleaning the data in the first coordinate curve based on the loss calculation result; determining, based on the cleaned first coordinate curve, a temperature corresponding to a maximum decrease in the maximum power of the smoke exhaust fan, and recording the temperature as a temperature threshold;

[0140] In the preset simulation software, a first model is constructed for the temperature change of the smoke exhaust fan from startup to operation at maximum power in a smoke-free state; and a second model is constructed for the temperature change of the smoke exhaust fan when the smoke exhaust fan is operated at maximum power in a smoke-presence state; the maximum power of the smoke exhaust fan in the first model and the second model are both the actual maximum power calculated by the loss model;

[0141] Build and train a smoke recognition model, and then identify early smoke features in each fire zone based on the trained smoke recognition model.

[0142] Build and train a smoke diffusion model, and simulate smoke diffusion in each fire zone based on the trained smoke diffusion model;

[0143] When a fire occurs in any fire zone, the smoke exhaust fan in the corresponding fire zone is turned on, and the data in the loss model, the temperature threshold, the first model, the second model and the smoke diffusion model are collected for analysis and processing, and the smoke exhaust fans in the remaining fire zones are precisely controlled.

[0144] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computing software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0145] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0146] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A smoke exhaust fan control system, characterized in that: include: Loss calculation unit: Builds and trains a loss model. Based on the trained loss model, it calculates the performance loss of all smoke exhaust fans in each fire zone to obtain loss calculation results. a temperature curve acquisition unit for acquiring a first coordinate curve of the maximum power of the smoke exhaust fan as a function of temperature, and cleaning the data in the first coordinate curve based on the loss calculation result; and determining, based on the cleaned first coordinate curve, a temperature corresponding to a maximum decrease in the maximum power of the smoke exhaust fan, and recording the temperature as a temperature threshold; Temperature change construction unit: constructing a first model of the temperature change of the smoke exhaust fan from startup to operation at maximum power in a smoke-free state in a preset simulation software; and constructing a second model of the temperature change of the smoke exhaust fan when the smoke exhaust fan operates at maximum power in a smoke state; the maximum power of the smoke exhaust fan in the first model and the second model are both the actual maximum power calculated by the loss model; Smoke monitoring unit: Builds and trains a smoke recognition model. Based on the trained smoke recognition model, it identifies early smoke features in each fire zone. Smoke diffusion unit: Builds and trains a smoke diffusion model, and simulates smoke diffusion in each fire zone based on the trained smoke diffusion model; Central control unit: When a fire occurs in any fire zone, the smoke exhaust fan in the corresponding fire zone is turned on, and the data in the loss calculation unit, the temperature curve unit, the temperature change construction unit and the smoke diffusion unit are collected for analysis and processing, and the smoke exhaust fans in the remaining fire zones are precisely controlled.

2. A smoke exhaust fan control system according to claim 1, characterized in that: Building a loss model and training it involves: Construct a loss function group for the air volume, air pressure, maximum power, efficiency and energy consumption of the smoke exhaust fan, specifically: L Q is the loss ratio of air volume, ω Q is the weight coefficient of air volume, Q′ is the actual air volume, Q is the target air volume, L S is the loss ratio of wind pressure, ω S is the weight coefficient of wind pressure, S′ is the actual wind pressure, S is the target wind pressure, L P is the maximum power loss ratio, ω P is the weight coefficient of maximum power, P′ is the actual maximum power, P is the target maximum power, L η is the loss ratio of conversion efficiency, ω η is the weight coefficient of conversion efficiency, η′ is the actual conversion efficiency, η is the target conversion efficiency, L E is the energy loss ratio, ω E is the weight coefficient of energy consumption, E′ is the actual energy consumption, and E is the target energy consumption; Based on the loss function group, the loss coefficient of the smoke exhaust fan is constructed, specifically: Obtaining the loss coefficient of the smoke exhaust fan at multiple time scales to obtain an acquisition result; Based on the obtained result, with the use time of the smoke exhaust fan as the horizontal coordinate and the loss coefficient of the smoke exhaust fan as the vertical coordinate, a coordinate curve showing the change of the loss coefficient with the use time is constructed and fitted.

3. A smoke exhaust fan control system according to claim 2, characterized in that: The performance loss calculation of all smoke exhaust fans in each fire zone is performed, and the loss calculation results include: Obtaining the usage time of any exhaust fan as the first usage time, and the coordinate curve obtained through fitting as the second coordinate curve; Predicting a loss coefficient at the first usage time node based on the fitted second coordinate curve, recorded as a first loss coefficient; Based on the first loss coefficient, a loss calculation result of the corresponding smoke exhaust fan is calculated and obtained.

4. A smoke exhaust fan control system according to claim 1, characterized in that: Based on the loss calculation result, cleaning the data in the first coordinate curve includes: Based on the loss calculation result, obtaining the actual maximum power of the smoke exhaust fan; In the first coordinate curve, the data point corresponding to the actual maximum power is matched, and the curve data before the data point is cleaned.

5. A smoke exhaust fan control system according to claim 4, characterized in that: Determining the temperature threshold based on the first coordinate curve after the cleaning process includes: In the first coordinate curve, taking the data point corresponding to the actual maximum power as a starting point, dividing the first coordinate curve after the data point into a plurality of equal intervals, and calculating the rate of change of the first coordinate curve in each interval to obtain a rate of change calculation result; Based on the change rate calculation result, the interval corresponding to the maximum change rate is screened and recorded as the first interval; The temperature value of the left port in the first interval is recorded as the temperature threshold.

6. The smoke exhaust fan control system according to claim 1, characterized in that: Building a smoke recognition model and training it include: Collect surveillance video data of multiple time scales as sample sets and store them in the database; Performing data enhancement on the sample set in the database to expand the data volume of the sample set; Manually label the data-augmented sample set; Based on the manually annotated sample set, a region proposal network is used to generate candidate regions containing smoke; A convolutional neural network is used to perform classification and regression training on the candidate areas, and output the category and location coordinates of the smoke.

7. The smoke exhaust fan control system according to claim 1, characterized in that: Building and training a smoke diffusion model includes: Constructing a smoke diffusion model and setting initial parameters for the smoke diffusion model, wherein the initial parameters include BIM data of the fire zone, the location of the smoke source, and the physical quantity of the smoke source; Establish wind force model, diffusion force model and air resistance model and solve them separately, and combine the solution results to obtain external force data; Solving the smoke diffusion model based on the set initial parameters and the combined external force data, and updating the velocity field, temperature field, and density field of the smoke; Based on the size of the fire zone and the boundaries of obstacles, the movement of smoke is constrained, and the velocity field, temperature field and density field of the smoke are corrected; Based on the modified velocity field, temperature field and density field of the smoke in the smoke diffusion model, the diffusion of the smoke is simulated and drawn in real time.

8. The smoke exhaust fan control system according to claim 1, characterized in that: When a fire occurs in any fire zone, the smoke exhaust fans in the corresponding fire zone are turned on: Based on the smoke monitoring unit, obtain the type of smoke and the location coordinates of the smoke in any fire zone; If the smoke is determined to be fire smoke, the smoke exhaust fan of the corresponding fire zone is turned on, and the location coordinates of the fire smoke are uploaded to the preset terminal.

9. The smoke exhaust fan control system according to claim 8, characterized in that: Precise control of the smoke exhaust fans in the remaining fire zones includes: When there is fire smoke in fire zone A, the time point at which the fire smoke occurs is recorded as t0; Based on the smoke diffusion model, the time point when the fire smoke reaches the boundary of the adjacent fire zone B is recorded as t2, the time point when the fire smoke fills a preset proportion of the fire zone B is recorded as t3, and the time point when the fire smoke fills the entire fire zone B is recorded as t4; Based on the loss model, the actual maximum power of the smoke exhaust fan in the fire zone B is calculated, and the time required for the smoke exhaust fan in the fire zone B to start and operate at the actual maximum power is obtained and recorded as T; Calculate the difference between (t2-t0) and, in combination with T, control the start time of the smoke exhaust fan in the fire zone B to t1, so that when the fire smoke reaches the boundary of the fire zone B, the smoke exhaust fan in the fire zone B can operate at the actual maximum power; In the time interval [t1, t3], based on the first model, the maximum value that the temperature of the smoke exhaust fan in the fire zone B can reach is output, recorded as the first temperature, and it is judged whether the first temperature exceeds the temperature threshold. If so, a first-level warning is issued and the smoke exhaust fans in all adjacent fire zones of the fire zone B are turned on. If not, in the time interval [t3, t4], based on the second model, the maximum value that the temperature of the smoke exhaust fan in the fire zone B can reach is output, recorded as the second temperature, and it is judged whether the second temperature exceeds the temperature threshold. If so, a second-level warning is issued and the smoke exhaust fans in a preset number of adjacent fire zones of the fire zone B are turned on. If not, no action is taken. The priority of the first-level warning is higher than the second-level warning.

10. A smoke exhaust fan control method, characterized in that: include: Construct and train a loss model. Based on the trained loss model, calculate the performance loss of all smoke exhaust fans in each fire zone to obtain loss calculation results. Obtaining a first coordinate curve of the maximum power of the smoke exhaust fan as a function of temperature, and cleaning the data in the first coordinate curve based on the loss calculation result; determining, based on the cleaned first coordinate curve, a temperature corresponding to a maximum decrease in the maximum power of the smoke exhaust fan, and recording the temperature as a temperature threshold; In the preset simulation software, a first model is constructed for the temperature change of the smoke exhaust fan from startup to operation at maximum power in a smoke-free state; and constructing a second model of the temperature change of the smoke exhaust fan when the smoke exhaust fan operates at maximum power in a smoke state; the maximum power of the smoke exhaust fan in the first model and the second model are both the actual maximum power calculated by the loss model; Build and train a smoke recognition model, and then identify early smoke features in each fire zone based on the trained smoke recognition model. Build and train a smoke diffusion model, and simulate smoke diffusion in each fire zone based on the trained smoke diffusion model; When a fire occurs in any fire zone, the smoke exhaust fan in the corresponding fire zone is turned on, and the data in the loss model, the temperature threshold, the first model, the second model and the smoke diffusion model are collected for analysis and processing, and the smoke exhaust fans in the remaining fire zones are precisely controlled.

Images