Tunnel construction safety monitoring and automatic spraying dust reduction method

Abstract

The application relates to the technical field of building engineering, in particular to a tunnel construction safety monitoring and automatic spraying dust-settling method. The method obtains sensing data of a construction area, the sensing data at least including dust concentration data at each detection position, humidity data and airflow data; according to the dust concentration data, a high dust concentration area and predicted dust concentration data of the high dust concentration area at a future time are determined; according to the dust concentration data, the predicted dust concentration data, the current position of a spraying device and the position of the high dust concentration area, and in combination with the humidity data and the airflow data, spraying control logic is determined; and according to the spraying control logic, the spraying device is controlled to spray water on the high dust concentration area to settle dust. The application effectively improves the dust-settling effect by monitoring the sensing data of the construction area and processing the sensing data to determine appropriate spraying control logic.

Description

Technical Field

[0001] This invention relates to the field of building engineering technology, specifically to a method for monitoring safety during tunnel construction and for automatic dust suppression via spraying. Background Technology

[0002] In underground engineering, especially during tunnel excavation and mining, dust control is a crucial aspect of ensuring construction safety and environmental protection. Traditional dust suppression methods typically rely on manual water spraying, which is not only inefficient and lacks real-time effectiveness, making it difficult to achieve full coverage and resulting in poor dust suppression. Furthermore, manual operation poses safety hazards, especially in complex underground environments. Therefore, developing an automated, continuous dust monitoring and spraying system for dust suppression, enabling real-time data acquisition and analysis, is of great significance. Summary of the Invention

[0003] The purpose of this invention is to provide a method for monitoring tunnel construction safety and automatic sprinkler dust suppression, which solves the problems of low timeliness and poor dust suppression effect of existing manual water spraying.

[0004] To address the aforementioned technical problems, in a first aspect, the present invention provides a method for tunnel construction safety monitoring and automatic sprinkler dust suppression, comprising the following steps:

[0005] Acquire sensor data of the construction area, including at least dust concentration data, humidity data, and airflow data at each detection location;

[0006] Based on the dust concentration data, the dust concentration data at different undetected locations are predicted, and high dust concentration areas are determined based on the dust concentration data at each detected and undetected location; based on the dust concentration data of the high dust concentration areas, the dust concentration is predicted, and the predicted dust concentration data of the high dust concentration areas at future times is determined.

[0007] Based on the dust concentration data, predicted dust concentration data, current position of the spray device, and location of high dust concentration areas, and in conjunction with the humidity data and airflow data, the spray control logic is determined. The spray control logic includes at least: spray flow rate, spray angle of the spray device nozzle, moving speed of the spray device, and spraying time.

[0008] According to the spray control logic, the spray device is controlled to spray water to reduce dust in areas with high dust concentration.

[0009] In conjunction with the first aspect described above, in some possible implementations, the method further includes:

[0010] The dust concentration data at each detection location is smoothed to achieve data cleaning, thereby obtaining the dust concentration data at each detection location after data cleaning.

[0011] In conjunction with the first aspect mentioned above, in some possible implementations, Kriging interpolation is used to predict the dust concentration data at different undetected locations based on the dust concentration data.

[0012] In conjunction with the first aspect above, among some possible implementation methods, areas with high dust concentrations are identified, including:

[0013] The dust concentration data at each detection location and the undetected location are compared with the dust concentration threshold. The locations where the dust concentration data is greater than the dust concentration threshold are identified as high dust concentration areas.

[0014] In conjunction with the first aspect mentioned above, in some possible implementations, a long short-term memory network is used to predict the dust concentration based on the dust concentration data of the high dust concentration area, thereby obtaining the predicted dust concentration data of the high dust concentration area at future times.

[0015] In conjunction with the first aspect mentioned above, the sprinkler control logic is determined among some possible implementation methods, including:

[0016] The dust concentration data at each detection location at the current time t are fused to obtain the dust concentration data at the current time t after data fusion.

[0017] Determine the maximum value among the predicted dust concentration data of all high dust concentration areas at future time, and determine the high dust concentration area corresponding to the maximum value as the target high dust concentration area;

[0018] Based on the dust concentration data at the current time t after data fusion, and combined with the humidity data at the current time t, the spray flow rate is determined;

[0019] Based on the airflow data at the current time t, determine the spray angle of the nozzle of the spray device, wherein the airflow data includes at least the airflow direction;

[0020] Based on the location of the target high dust concentration area and the current location of the spray device, a path is planned to determine the length of the planned movement path;

[0021] The moving speed of the spraying device is determined based on the length of the planned moving path and the specified moving time of the spraying device.

[0022] Based on the difference between the dust concentration data at the current time t after data fusion and the dust concentration threshold, and combined with the dust reduction efficiency of the spraying device, the spraying time of the spraying device is determined.

[0023] In conjunction with the first aspect mentioned above, in some possible implementation methods, a weighted average method is used to fuse the dust concentration data at each detection location at the current time t, so as to obtain the dust concentration data at the current time t after data fusion.

[0024] In conjunction with the first aspect mentioned above, in some possible implementations, the A* algorithm is used for path planning based on the location of the target high dust concentration area and the current location of the spraying device to obtain the planned movement path.

[0025] In conjunction with the first aspect above, among some possible implementations, determining the spray flow rate and the spraying time of the spraying device includes:

[0026] If the dust concentration data at the current time t after data fusion is less than or equal to the dust concentration threshold, then the spray flow rate is set to 0.

[0027] Otherwise, based on the highest dust concentration value and the dust concentration threshold, the dust concentration at the current time t after data fusion is...

[0028] The concentration data is normalized to obtain the dust concentration normalization result;

[0029] Negatively correlate the humidity data at the current time t to obtain negatively correlated humidity data;

[0030] The normalized dust concentration results and the negatively correlated humidity data are weighted and summed to obtain the spray flow rate;

[0031] Calculate the ratio of the difference between the dust concentration data at the current time t after data fusion and the dust concentration threshold to the dust reduction efficiency of the spray device.

[0032] The calculated ratio is used as the spraying time of the spraying device.

[0033] In conjunction with the first aspect mentioned above, among some possible implementation methods, a weighted average method is used to fuse the dust concentration data at each detection location at the current time t, including:

[0034] Based on the historical stability, real-time consistency, and health status of the sensors that collect dust concentration data at each detection location, the real-time data quality of the sensors that collect dust concentration data at each detection location is determined.

[0035] The weight of each detection location is determined based on the real-time data quality and coverage of the sensors that collect dust concentration data at each detection location, as well as the location distribution at each detection location.

[0036] Based on the weights at each detection location, the dust concentration data at the current time t at each detection location are fused.

[0037] To address the aforementioned technical problems, in a second aspect, the present invention also provides a tunnel construction safety monitoring and automatic sprinkler dust suppression device, the device comprising:

[0038] The sensing unit is used to: acquire sensing data of the construction area, wherein the sensing data includes at least dust concentration data, humidity data and airflow data at each detection location;

[0039] The data processing unit is configured to: predict dust concentration data at different undetected locations based on the dust concentration data, and determine high dust concentration areas based on the dust concentration data at each detected and undetected location; predict dust concentration based on the dust concentration data of the high dust concentration areas, and determine the predicted dust concentration data of the high dust concentration areas at future times; determine spray control logic based on the dust concentration data, predicted dust concentration data, the current position of the spray device, and the position of the high dust concentration areas, and in conjunction with the humidity data and airflow data, the spray control logic including at least: spray flow rate, spray angle of the spray device nozzles, moving speed of the spray device, and spraying time; and control the spray device to spray water to suppress dust in the high dust concentration areas according to the spray control logic.

[0040] To address the aforementioned technical problems, in a third aspect, the present invention also provides a tunnel construction safety monitoring and automatic sprinkler dust suppression system, including a memory and a processor. The memory stores executable program code, and the processor retrieves and runs the executable program code from the memory, causing the device to execute the methods described in the first aspect or any possible implementation thereof.

[0041] To address the aforementioned technical problems, in a fourth aspect, the present invention also provides a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0042] To address the aforementioned technical problems, in a fifth aspect, the present invention also provides a computer-readable storage medium storing computer program code that, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0043] This invention offers the following advantages: It acquires sensor data from the construction area, including at least dust concentration data, humidity data, and airflow data at each detection location. Based on the dust concentration data, it identifies high dust concentration areas and predicts their dust concentration at future times. Based on the dust concentration data, predicted dust concentration data, the current position of the spraying device, and the location of the high dust concentration areas, combined with humidity and airflow data, it determines the spraying control logic. This logic includes at least: spray flow rate, spray angle of the spraying device nozzles, moving speed of the spraying device, and spraying time. Based on this logic, it controls the spraying device to spray water to reduce dust in the high dust concentration areas. By monitoring and processing the sensor data from the construction area, this invention adaptively determines appropriate spraying control logic, ensuring dust reduction efficiency and effectively improving dust suppression results. Attached Figure Description

[0044] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of the basic process of a tunnel construction safety monitoring and automatic sprinkler dust suppression method according to an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the slide rail and spray device according to an embodiment of the present invention. Detailed Implementation

[0047] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings.

[0048] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0049] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0050] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0051] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0052] Although operations or steps are described in a specific order in the accompanying drawings in the embodiments of the present invention, this should not be construed as requiring these operations or steps to be performed in the specific order or serial order shown, or requiring all of the shown operations or steps to be performed to obtain the desired result. In the embodiments of the present invention, these operations or steps may be performed serially; they may be performed in parallel; or a portion of these operations or steps may be performed.

[0053] Furthermore, it is understood that the data involved in the technical solutions of this invention (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions. Unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains, and all parameters or indicators in the formulas involved in this invention are normalized values ​​that have eliminated the influence of dimensions.

[0054] To address the problems of low efficiency and difficulty in achieving full coverage in existing manual water spraying methods, this invention provides a method for monitoring tunnel construction safety and automatic dust suppression via sprinkler systems. This method monitors sensor data of the construction area in real time and uses an automatic sprinkler system for efficient dust suppression, ensuring construction safety and environmental protection.

[0055] The following will describe in detail, with reference to the accompanying drawings, a method for monitoring tunnel construction safety and automatic sprinkler dust suppression provided by an embodiment of the present invention.

[0056] Figure 1 This diagram illustrates the basic process of a tunnel construction safety monitoring and automatic sprinkler dust suppression method provided by an embodiment of the present invention. Figure 1 As shown, the method specifically includes the following steps:

[0057] S100: Acquire sensor data of the construction area, the sensor data including at least dust concentration data, humidity data and airflow data at each detection location.

[0058] Slide rails are installed on the underground arch in the tunnel construction area. The slide rails are made of corrosion-resistant materials, such as stainless steel or high-strength composite materials, and dust covers are added to prevent dust or gravel from clogging the rails. They are also designed as modular structures to facilitate installation and maintenance.

[0059] A spraying device is installed on the slide rail. This spraying device can move on the slide rail and spray water to suppress dust in specific areas as needed. Figure 2 A schematic diagram of the sliding rail and spray device is shown. The spray device is equipped with multiple nozzles to ensure uniform water spraying and coverage. It employs dynamic atomization technology to control the water mist particle size within 10-50 micrometers, improving dust capture efficiency. The nozzles are designed as rotating, multi-functional nozzles, supporting 360° rotation for wide and flexible coverage. The nozzles also feature multi-mode spraying, including wide-angle spraying and concentrated spraying modes to adapt to different dust concentrations in different areas. Each nozzle is equipped with an independent control module. The data processing unit dynamically adjusts the spray device's moving speed, spray flow rate, spray angle, and spraying time based on real-time dust concentration data. For example, when the dust concentration in a certain area is high, the spray device will increase its moving speed and spray volume. The nozzles also have built-in anti-clogging devices that periodically backwash to prevent blockages. To further enhance dust suppression, the spray device supports a multi-point spraying coordination mode, achieving staggered coverage in high dust concentration areas to quickly reduce dust concentration.

[0060] To enhance construction safety, the sprinkler system is equipped with high-brightness LED lights. The light intensity can be dynamically adjusted according to ambient light, and different colored lights indicate the current dust concentration; for example, green indicates safety, and red indicates danger. When the dust concentration exceeds the standard, an audible and visual alarm will be triggered, and the tunnel broadcast system will be activated to remind construction personnel to pay attention to safety. In addition, an automatic emergency spraying mode has been added, which immediately activates high-frequency water spraying after blasting to quickly suppress dust diffusion.

[0061] A laser particulate sensor is installed on top of the spray system, and it can follow the spray system along a sliding rail to detect dust. In addition to the laser particulate sensors installed along the sliding rail, laser particulate sensors are also deployed at various fixed locations within the tunnel construction area. The number and location of the laser particulate sensors are deployed according to the layout of the tunnel construction area and are not limited here. All laser particulate sensors form a network for monitoring, ensuring comprehensive dust detection without blind spots. Each laser particulate sensor can detect the dust concentration in the air at its corresponding detection location in real time, with the unit of dust concentration being mg / m³. 3This allows for the acquisition of dust concentration data at various monitoring locations within the construction area. The laser particulate sensor mounted on top of the spray system is primarily used for real-time monitoring and spray control, while laser particulate sensors positioned at various fixed locations within the tunnel construction area focus more on regional or global data collection and analysis. Working together, both sensors help the system respond more accurately in dynamic environments, ensuring the safety of construction personnel.

[0062] In addition, humidity sensors and airflow sensors are installed at appropriate locations in the tunnel construction area to enhance humidity and airflow monitoring capabilities. Humidity sensors are used to detect the humidity in the tunnel construction area in real time, facilitating dynamic adjustments to the spray water volume. Airflow sensors are used to detect the airflow velocity and direction in the tunnel construction area in real time. The unit for airflow velocity is m / s, and the unit for airflow direction is angle. Airflow velocity and direction are collectively referred to as airflow data, which helps analyze the direction of dust dispersion.

[0063] A laser particulate matter sensor, a humidity sensor, and an airflow sensor together constitute a multi-sensor system. Each sensor in the multi-sensor system is equipped with a dust cover and an automatic cleaning device to regularly remove adhering dust and ensure the accuracy of the monitoring data. The introduction of the multi-sensor system not only improves the detection accuracy of dust concentration but also provides the data processing unit with more diverse information inputs.

[0064] In a multi-sensor system, the laser particulate sensor, humidity sensor, and airflow sensor transmit collected dust concentration data, humidity data, and airflow data to the data processing unit via wireless or wired methods. Data transmission should employ high-bandwidth, low-latency communication technologies to ensure data real-time performance and integrity.

[0065] S200: Based on the dust concentration data, predict the dust concentration data at different undetected locations, and determine high dust concentration areas based on the dust concentration data at each detected and undetected location; based on the dust concentration data of the high dust concentration areas, predict the dust concentration and determine the predicted dust concentration data of the high dust concentration areas at future times.

[0066] A data processing unit, the core of the entire system, receives and analyzes real-time sensor data from the multi-sensor system. This data enables the generation of precise spray control logic. By incorporating automatic control algorithms, the data processing unit analyzes historical dust concentration data, predicts high-dust-concentration areas, and pre-determines spraying strategies. Simultaneously, real-time sensor data is used to dynamically optimize the spray path and frequency for precise dust suppression. The data processing unit possesses multi-tasking capabilities, processing data such as dust concentration, airflow direction, and humidity in real time and quickly generating spray control commands. Furthermore, it features fault tolerance and adaptive capabilities; if a sensor in one area malfunctions, it automatically compensates for data from other sensors, ensuring the continuity of dust suppression operations. Through cloud data uploads, construction managers can remotely view spray effect reports, providing support for subsequent optimization.

[0067] Specifically, after receiving the sensor data from the multi-sensor system, the data processing unit first preprocesses the dust concentration data. This preprocessing includes data cleaning and data fusion to obtain preprocessed dust concentration data. Data cleaning removes outliers and noise from the dust concentration data, ensuring its stability. Data fusion allows for the calculation of the overall dust concentration for the entire area.

[0068] Furthermore, in this embodiment of the invention, a moving average method is used to smooth the dust concentration data, thereby achieving data cleaning:

[0069]

[0070] Among them, C i ′(t) represents the dust concentration data at the current time t of the i-th detection position after data cleaning; N is the sliding window size; C i (tk) represents the dust concentration data at time tk at the i-th detection location.

[0071] Furthermore, in this embodiment of the invention, a weighted average method is used to fuse the dust concentration data after data cleaning:

[0072]

[0073] Among them, C avg (t) represents the dust concentration data at the current time t after data fusion; C i ω'(t) represents the dust concentration data at the i-th detection position at the current time t after data cleaning; iThe weight of the dust concentration data at the i-th detection position depends on the position and accuracy of the laser particulate sensor and can be set reasonably as needed; there is no limitation here. n represents the total number of different detection positions, that is, the total number of laser particulate sensors, including movable laser particulate sensors on the spray device.

[0074] For a movable laser particulate sensor on a spray device, its detection position dynamically changes as the slide rail moves, and its weight ω i It will be adjusted in real time, ω i The functional relationship can be expressed as:

[0075] ω i =g(d i ,a i ,q i )

[0076] The specific calculation method for the weight function is as follows:

[0077]

[0078] Where, d i Let be the distance between the i-th movable laser particulate sensor and the target detection area (the undetected location currently being evaluated or predicted for dust concentration, i.e., coordinate point (x, y)). The closer the distance, the higher the weight. i Let q represent the coverage area of ​​the i-th movable laser particle sensor, which is related to the sensor's detection accuracy; i α represents the real-time data quality of the i-th movable laser particle sensor, reflecting the sensor's detection stability and reliability; α is a constant representing the degree of influence of distance.

[0079] Among them, real-time data quality q i The method for determining it is as follows:

[0080] 1. Definition of core indicators:

[0081] Historical stability i Stability is assessed by evaluating the variance of dust concentration data from the sensor over the most recent T time steps (e.g., T = 10 minutes). A smaller variance indicates better stability. i The higher:

[0082]

[0083] Among them, Var max The maximum permissible variance preset by the system (set based on historical data statistics); Var is the variance function; C i (tT) represents the dust concentration data of the i-th movable laser particulate sensor at time tT.

[0084] Real-time consistency c i : Through the i-th sensor and its neighboring N 邻近 The smaller the difference in data from each sensor, the more consistent the evaluation; the smaller the difference, the better. i The higher:

[0085]

[0086] Where α is the attenuation coefficient (e.g., α = 0.1), controlling the sensitivity of differences to consistency; N 邻近 The number of sensors closest to the i-th sensor (e.g., N) 邻近 =3); C i (t) represents the dust concentration data of the i-th movable laser particulate sensor at time t; C k (t) represents the dust concentration data of the k-th neighbor of the i-th movable laser particulate sensor at time t; exp is an exponential function with the natural constant e as the base.

[0087] Health status h i Based on the sensor's self-test signal, the normal state is h. i =1, h needs to be calibrated i =0.5, fault or offline h i =0.

[0088] 2. Comprehensive calculation of q i :

[0089]

[0090] Where, ω s ω c and ω h These are the weights for historical stability, real-time consistency, and health status, respectively. The weights can be adjusted according to the scenario, and their sum is 1. In this embodiment, ω is set to... s =0.5, ω c =0.3, ω h =0.2.

[0091] 3. Dynamic update rules:

[0092] q is recalculated each time the slide rail moves or the sensor data is refreshed. i ;

[0093] If the sensor malfunctions h i =0, directly set q i =0, excluding its influence on the data.

[0094] Because the position and number of movable laser particulate matter sensors change as the slide rail moves, the system needs to recalculate the weight of each movable laser particulate matter sensor and perform data fusion based on the new sensor position each time the slide rail moves. This allows the system to more accurately reflect the dust concentration in different areas.

[0095] Based on the preprocessed dust concentration data, the optimized design of the data processing unit incorporates a time-series data modeling algorithm, which effectively identifies high dust concentration areas and improves the prediction accuracy of dust concentration. First, concentration distribution modeling is performed. Since the dust concentration inside the tunnel varies with time and space, interpolation algorithms, such as Kriging interpolation, are used to predict the dust concentration at undetected locations.

[0096]

[0097] Where C′(x,y,t) represents the dust concentration data at the undetected location (x,y) at the current time t; λ i C represents the interpolation weight at the i-th detection position; i ′(t) represents the dust concentration data at the current time t of the i-th detection position after data cleaning; n represents the total number of different positions, that is, the total number of laser particulate sensors at different positions.

[0098] Then, high-concentration areas are identified. A dust concentration threshold C0 is set, and the dust concentration C at each detection location is... i The concentration at a certain location is compared with the dust concentration threshold C0. If the concentration at a certain location exceeds the dust concentration threshold C0, the location is marked as a high dust concentration area.

[0099] There may be multiple high dust concentration areas. For each high dust concentration area, a time series model, such as a Long Short-Term Memory (LSTM) network, can be used to predict the dust concentration trend based on the dust concentration data at the current time t and previous times, thus enabling early spraying response. Assume there are currently m high dust concentration areas, denoted as p1, p2, ..., p... m For any j-th high dust concentration region p j The formula for predicting the trend of dust concentration is:

[0100]

[0101] in, Let p represent any j-th high dust concentration region. j Predicted dust concentration data at time t+Δt; p represents the high dust concentration region. j Given the dust concentrations at current time t and time t-Δt, if the high dust concentration region p j If the location is that of the laser particulate sensor, then the dust concentration data refers to the dust concentration data after data cleaning. If the high dust concentration area is p j If there is no sensor coverage, the dust concentration is estimated by interpolation algorithms (such as Kriging interpolation or inverse distance weighted interpolation); Δt represents the time step, that is, the time interval during continuous prediction, usually in seconds (s); f represents the prediction function corresponding to the time series model.

[0102] S300: Based on the dust concentration data, predicted dust concentration data, current position of the spray device, and position of the high dust concentration area, and in conjunction with the humidity data and airflow data, determine the spray control logic. The spray control logic includes at least: spray flow rate, spray angle of the spray device nozzle, moving speed of the spray device, and spraying time.

[0103] To prioritize high-concentration areas that have the greatest impact on the construction environment, the predicted dust concentration data for all areas can be sorted, and the predicted concentration can be selected. The area with the highest dust concentration is designated as the priority response area, i.e., the area with the highest dust concentration. Furthermore, multiple spray units can simultaneously and collaboratively respond to multiple areas based on prediction results, ensuring simultaneous spraying treatment in different areas. The allocation of spray units can be based on the predicted concentration of each area, combined with the area's location. The coverage area of ​​the equipment can be adjusted reasonably using scheduling algorithms (such as the Hungarian algorithm) to achieve the best response effect.

[0104] To more accurately predict dust diffusion paths, airflow data is introduced:

[0105] Δx=V(t)·cos(θ(t))·Δt;

[0106] Δy=V(t)·sin(θ(t))·Δt;

[0107] Where Δx and Δy represent the displacement of dust along the airflow direction in the horizontal and vertical directions, respectively, within the time interval Δt; V(t) represents the airflow velocity at the current time t; θ(t) represents the angle value corresponding to the airflow direction at the current time t; Δt represents the time step, that is, the time interval for continuous prediction, usually in seconds (s).

[0108] The above formulas are used to predict the direction and path of dust diffusion based on airflow speed and direction, thereby adjusting the spraying range.

[0109] Based on the data analysis results, the data processing unit generates precise spray control logic to ensure that the dust concentration is within a safe range. The spray control logic includes:

[0110] Water spray volume calculation: Based on the dust concentration data C at the current time t after data fusion. avg Given H(t) and the humidity at the current time t, calculate the spray flow rate Q:

[0111]

[0112] Where Q represents the spray flow rate; k1 and k2 are adjustment coefficients, and in this embodiment, k1 = 0.8 and k2 = 0.2 are set; C0 represents the dust concentration threshold; C max This represents the highest possible dust concentration in the system, used for normalization, and is expressed in mg / m³. 3 ; This represents the normalized result of the dust concentration exceeding the standard, ranging from [0,1]. When C... avg When (t)≤C0, it means the current dust concentration is below the safety threshold, so Q=0 is set directly, meaning no spraying is performed; when C avg When (t)>C0, the spray flow rate is calculated using the normalized formula.

[0113] Nozzle angle optimization: Adjust the nozzle spray angle α according to the angle value θ(t) corresponding to the airflow direction to ensure that the spray covers the high concentration area.

[0114] α=θ(t)+Δα corr

[0115] Where, Δα corr This indicates the environmental disturbance correction value.

[0116] Sprayer device movement path planning: based on the location coordinates (x, y) of the target high dust concentration area. h ,y h ) and the current position coordinates (x) of the current spray device c ,y c Using a shortest path algorithm, such as the A* algorithm, path planning is performed. If the location coordinates (x, y) of the target high dust concentration area are... h ,y h ) and the current position coordinates (x) of the spray device c ,y c The shortest path is a straight line, then we have:

[0117]

[0118] Where D represents the length of the planned movement path.

[0119] Control the speed of the spray system to ensure it reaches the high dust concentration area in a timely manner.

[0120]

[0121] Where v represents the moving speed of the spray device; t r The specified moving time of the sprinkler system is indicated by ; D represents the length of the planned moving path.

[0122] Water spraying time adjustment: The water spraying time is dynamically adjusted based on dust concentration data and spray flow rate.

[0123]

[0124] Where T represents the water spraying time; R represents the dust reduction efficiency of the spraying device, in mg / m³. 3 / s; C0 is the dust concentration threshold.

[0125] S400: According to the spray control logic, control the spray device to spray water to reduce dust in areas with high dust concentration.

[0126] Based on the spray control logic defined above, the data processing unit generates corresponding spray control commands. According to these commands, the spray device can be precisely moved to a high dust concentration area requiring dust suppression, and water sprayed to reduce dust in that area. In this embodiment, the high dust concentration area requiring dust suppression refers to the target high dust concentration area. During the process of precisely moving the spray device to the high dust concentration area requiring dust suppression, to achieve accurate positioning of the spray device, high-precision positioning technologies such as laser ranging, infrared positioning, or GPS can be used. Simultaneously, the device can have a built-in inertial navigation module to ensure that the spray device's positioning accuracy is calibrated in real time during its movement along the slide rail.

[0127] In addition, the spraying device and data processing unit also support remote monitoring. Construction personnel can view dust concentration data and the working status of the spraying device in real time via mobile phone or computer, and remotely control and adjust the spraying parameters.

[0128] The tunnel construction safety monitoring and automatic sprinkler dust suppression method provided in this embodiment of the invention can achieve the following effects:

[0129] Highly efficient dust suppression: The dust concentration is monitored in real time by a laser particulate sensor, and an automatic water spraying device is used to suppress dust, ensuring a clean and safe construction environment;

[0130] Real-time monitoring: The laser particulate sensor can continuously monitor the dust concentration on the ground and transmit data in real time to ensure safety during construction.

[0131] Multi-point water spray: The spraying device can be moved to different positions as needed to spray water at multiple points, ensuring the uniformity and comprehensiveness of the dust suppression effect;

[0132] Intelligent control: The data processing unit has intelligent control functions, which can automatically adjust the spray flow rate, the spray angle of the spray device nozzles, the moving speed of the spray device and the water spraying time according to the dust concentration, thereby improving the dust suppression efficiency.

[0133] Reduced human intervention: Automated systems reduce human intervention, thereby reducing the workload and safety risks for construction workers.

[0134] Based on the same inventive concept, this invention also provides a tunnel construction safety monitoring and automatic sprinkler dust suppression device, the device comprising:

[0135] The sensing unit is used to: acquire sensing data of the construction area, wherein the sensing data includes at least dust concentration data, humidity data and airflow data at each detection location;

[0136] The data processing unit is configured to: predict dust concentration data at different undetected locations based on the dust concentration data, and determine high dust concentration areas based on the dust concentration data at each detected and undetected location; predict dust concentration based on the dust concentration data of the high dust concentration areas, and determine the predicted dust concentration data of the high dust concentration areas at future times; determine spray control logic based on the dust concentration data, predicted dust concentration data, the current position of the spray device, and the position of the high dust concentration areas, and in conjunction with the humidity data and airflow data, the spray control logic including at least: spray flow rate, spray angle of the spray device nozzles, moving speed of the spray device, and spraying time; and control the spray device to spray water to suppress dust in the high dust concentration areas according to the spray control logic.

[0137] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0138] Based on the same inventive concept, this invention also provides a tunnel construction safety monitoring and automatic sprinkler dust suppression system. The system includes: a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the system can perform any of the tunnel construction safety monitoring and automatic sprinkler dust suppression methods described above.

[0139] In this embodiment of the invention, the system can be divided into functional modules according to the above method example. For example, each module can correspond to a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0140] Based on the same inventive concept, embodiments of the present invention also provide a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute any of the tunnel construction safety monitoring and automatic sprinkler dust suppression methods described above.

[0141] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform any of the tunnel construction safety monitoring and automatic sprinkler dust suppression methods described above.

[0142] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for safety monitoring and automatic sprinkler dust suppression during tunnel construction, characterized in that, Includes the following steps: Acquire sensor data of the construction area, including at least dust concentration data, humidity data, and airflow data at each detection location; Based on the dust concentration data, the Kriging interpolation method is used to predict the dust concentration data at different undetected locations, and based on the dust concentration data at each detected and undetected location, high dust concentration areas are determined. Based on dust concentration data in high dust concentration areas, dust concentration is predicted to determine the predicted dust concentration data for high dust concentration areas at future times. Based on the dust concentration data, predicted dust concentration data, current position of the spray device, and location of high dust concentration areas, and in conjunction with the humidity data and airflow data, the spray control logic is determined. The spray control logic includes at least: spray flow rate, spray angle of the spray device nozzle, moving speed of the spray device, and spraying time. According to the spray control logic, the spray device is controlled to spray water to reduce dust in areas with high dust concentration. in: Determining high dust concentration areas involves comparing dust concentration data at each detection location and non-detection location with a dust concentration threshold, and identifying high dust concentration areas at locations where the dust concentration data exceeds the dust concentration threshold. Based on the dust concentration data of high dust concentration areas, a long short-term memory network is used to predict the dust concentration, and the predicted dust concentration data of high dust concentration areas at future times is obtained. Determine the sprinkler control logic, including: A weighted average method is used to fuse the dust concentration data at each detection location at the current time t, resulting in fused dust concentration data at the current time t. This includes determining the real-time data quality of the sensors collecting dust concentration data at each detection location based on their historical stability, real-time consistency, and health status; and determining the weight of each detection location based on its real-time data quality, coverage area, and location distribution. Based on the weights at each detection location, the dust concentration data at each detection location at the current time t are fused. Determine the maximum value among the predicted dust concentration data of all high dust concentration areas at future time, and determine the high dust concentration area corresponding to the maximum value as the target high dust concentration area; Based on the dust concentration data at the current time t after data fusion, and combined with the humidity data at the current time t, the spray flow rate is determined; Based on the airflow data at the current time t, determine the spray angle of the nozzle of the spray device, wherein the airflow data includes at least the airflow direction; Based on the location of the target high dust concentration area and the current location of the spray device, a path is planned to determine the length of the planned movement path; The moving speed of the spraying device is determined based on the length of the planned moving path and the specified moving time of the spraying device. Based on the difference between the dust concentration data at the current time t after data fusion and the dust concentration threshold, and combined with the dust reduction efficiency of the spraying device, the spraying time of the spraying device is determined.

2. The method for tunnel construction safety monitoring and automatic sprinkler dust suppression according to claim 1, characterized in that, The method further includes: The dust concentration data at each detection location is smoothed to achieve data cleaning, thereby obtaining the dust concentration data at each detection location after data cleaning.

3. The method for tunnel construction safety monitoring and automatic sprinkler dust suppression according to claim 1, characterized in that, Based on the location of the target high dust concentration area and the current location of the spray device, the A* algorithm is used for path planning to obtain the planned movement path.

4. The method for tunnel construction safety monitoring and automatic sprinkler dust suppression according to claim 1, characterized in that, Determining the spray flow rate and the spraying time of the sprinkler system includes: If the dust concentration data at the current time t after data fusion is less than or equal to the dust concentration threshold, then the spray flow rate is set to 0. Otherwise, based on the highest dust concentration value and the dust concentration threshold, the dust concentration data at the current time t after data fusion is normalized to obtain the dust concentration normalization result. Negatively correlate the humidity data at the current time t to obtain negatively correlated humidity data; The normalized dust concentration results and the negatively correlated humidity data are weighted and summed to obtain the spray flow rate; Calculate the ratio of the difference between the dust concentration data at the current time t after data fusion and the dust concentration threshold to the dust reduction efficiency of the spray device. The calculated ratio is used as the spraying time of the spraying device.

Images