Iot intelligent construction site environment monitoring and adaptive control method and system

Abstract

This invention proposes a method and system for intelligent monitoring and adaptive control of construction site environment based on the Internet of Things (IoT). The method includes: a target edge node acquiring first sensing data collected by sensor modules in its area, and performing forward prediction on the first sensing data based on a pre-configured local network model to obtain a first environmental state for the next time period; the target edge node receiving a second environmental state transmitted from its neighboring edge nodes; the target edge node generating an optimal control sequence based on a cooperative control objective function and a distributed model according to the first and second environmental states, and controlling a designated actuator in the area where the target edge node is located to perform relevant operations in real time according to the optimal control sequence. This invention improves control real-time performance by processing data through target edge nodes; simultaneously, it globally optimizes the control strategy, significantly improving the overall control effect.

Description

Technical Field

[0001] This invention relates to the field of intelligent environmental control technology, and in particular to a method and system for intelligent monitoring and adaptive control of construction site environment using the Internet of Things. Background Technology

[0002] In the current construction of large-scale projects such as dams, environmental control at the construction site (such as dust suppression spraying and intelligent sunshade) is crucial for ensuring operational safety, improving project quality, and promoting green construction. Existing mainstream solutions mostly adopt a centralized intelligent control mode based on cloud platforms. This mode typically relies on various sensors deployed on-site to collect environmental data, which is then transmitted via network to a remote cloud server. The cloud processes, analyzes, and makes decisions on the aggregated data, generating control commands which are then sent to the on-site actuators.

[0003] However, the centralized cloud processing model requires a long chain of processes involving "sensing-transmission-cloud computing-command feedback," with latency reaching seconds or even higher. For sudden and drastic environmental disturbances such as dust diffusion, instantaneous strong winds, and rapid temperature changes, this latency can lead to severe delays in control commands, making it impossible to achieve precise real-time suppression.

[0004] Secondly, existing cloud-based control solutions mostly make decisions based on isolated data from a single region, generating control schemes independently for each region. This can only achieve local optima in a single region, but ignores the strong correlations of the physical environment at the construction site (such as cross-regional diffusion of pollutants caused by airflow, heat radiation transfer, etc.). This "each fighting their own battle" strategy is highly likely to lead to conflicting or redundant control schemes. Summary of the Invention

[0005] This invention provides an IoT-based intelligent construction site environment monitoring and adaptive control method and system to address the problems existing in related technologies. The technical solution is as follows:

[0006] In a first aspect, embodiments of the present invention provide an IoT-based intelligent construction site environmental monitoring and adaptive control method, applied to target edge nodes in an edge node cluster, including:

[0007] The target edge node acquires the first sensing data collected by the sensor module in its area, and performs forward prediction on the first sensing data based on the pre-configured local network model to obtain the first environmental state in the next time period.

[0008] The target edge node receives a second environmental state transmitted by its neighboring edge nodes. The second environmental state is predicted by the neighboring edge nodes based on the second sensing data collected by the sensor modules in their respective areas.

[0009] The target edge node is based on a collaborative control objective function. Through a distributed model, it generates an optimal control sequence based on the first and second environmental states. Based on the optimal control sequence, it controls the designated execution mechanism in the area where the target edge node is located to perform relevant operations in real time.

[0010] In one implementation, it further includes:

[0011] When the target edge node acquires the first sensing data, it parses the region code of the first sensing data and compares the region code with its own pre-configured list of legal region codes. If they match, the data is verified and forward prediction is performed on the first sensing data through the local network model. If they do not match, the data is discarded. The list of legal region codes records the region code corresponding to each area in the construction site, as well as the edge node and sensor module bound to each region code.

[0012] In one implementation, the first sensing data includes temperature and humidity data, wind direction data, and dust concentration.

[0013] In one implementation, it further includes:

[0014] The target edge node calculates its azimuth relative to each of its neighboring edge nodes in real time. When the angle between the azimuth of any edge node and the current wind direction is within the tolerance range, the edge node is marked as a neighboring edge node.

[0015]

[0016] Where, x i (t) represents the first environmental state of the target edge node i at time t, x ref This is the ideal reference value, Q. i It is the weight matrix between the state and the reference value, u i (t) represents the control quantity of the specified actuator at time t, R i It is the weight matrix of the control quantity, x j (t) represents the second environmental state of the adjacent edge node j at time t, S ij This is the coupling penalty matrix.

[0017] In one implementation, it further includes:

[0018] Meteorological data is acquired from the cloud, and key parameters in the collaborative control objective function are dynamically adjusted based on the meteorological data to generate a new execution plan. The designated execution agency in the area where the control target edge node is located executes the new execution plan in real time.

[0019] In one implementation, it further includes:

[0020] The dust concentration in the first sensing data is compared with the preset limit value. When the dust concentration exceeds the preset limit value, the required spray intensity is directly calculated and the corresponding actuator is forced to perform spraying operation according to the required spray intensity.

[0021] Secondly, embodiments of the present invention provide an IoT-based intelligent construction site environmental monitoring and adaptive control system, comprising:

[0022] An edge node cluster, comprising multiple target edge nodes;

[0023] The target edge node is used to implement the IoT-based intelligent construction site environmental monitoring and adaptive control method described above.

[0024] Thirdly, embodiments of the present invention provide an electronic device comprising a memory and a processor. The memory and the processor communicate with each other via an internal connection path. The memory stores instructions, and the processor executes the instructions stored in the memory. When the processor executes the instructions stored in the memory, it causes the processor to perform the method described in any of the above embodiments.

[0025] Fourthly, embodiments of the present invention provide a computer-readable storage medium that stores a computer program, wherein when the computer program is run on a computer, the methods in any of the embodiments described above are executed.

[0026] The advantages or beneficial effects of the above technical solutions include at least the following:

[0027] This invention processes the sensing data collected by the sensor module directly through the target edge node, and generates a control scheme corresponding to its region based on the local model in the target edge node, replacing the traditional centralized cloud processing mode. This reduces the transmission delay between the edge node and the cloud and improves the real-time performance of the control. At the same time, this invention considers the strong correlation of the physical environment of the construction site. The target edge node combines the first environmental state of its region with the second state data of the adjacent regions to perform distributed control calculations, realize global optimization, and significantly improve the overall control effect.

[0028] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0029] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in the invention and should not be construed as limiting the scope of the invention.

[0030] Figure 1 This is a schematic diagram illustrating the connection between the edge node cluster and the cloud in this invention;

[0031] Figure 2 This is a flowchart illustrating the IoT-based intelligent construction site environmental monitoring and adaptive control method of the present invention.

[0032] Figure 3 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0033] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0034] Example 1

[0035] This embodiment presents an IoT-based intelligent construction site environmental monitoring and adaptive control method, which is applied to target edge nodes in an edge node cluster.

[0036] It should be noted that in this embodiment, the dam construction site is pre-divided into multiple areas, and each area is equipped with at least one edge node. The edge nodes are used to process data within that area and control the actuators within that area to achieve environmental regulation. For example... Figure 1 As shown, edge nodes from multiple regions form an edge node cluster, which is connected to the cloud. Data exchange between edge nodes within the cluster can be achieved using existing transmission technologies, such as wireless networks. Each edge node in the cluster can execute the IoT-based intelligent construction site environmental monitoring and adaptive control method of this embodiment. In this embodiment, any edge node currently executing the method of this embodiment is referred to as the target edge node, used only to distinguish subsequent adjacent edge nodes.

[0037] like Figure 2 As shown, the control method executed by the target edge node in this embodiment specifically includes:

[0038] Step S1: The target edge node acquires the first sensing data collected by the sensor module in its area, and performs forward prediction on the first sensing data based on the pre-configured local network model to obtain the first environmental state for the next time period.

[0039] It should be noted that each target edge node is responsible for a specific area, and each area is pre-deployed with corresponding sensor modules and actuators. Each area also has its own area code. Edge nodes, sensor modules, and actuators corresponding to the same area are pre-bound using the same area code, and a list of valid area codes is established. This list records the area code corresponding to each area on the construction site, as well as the edge nodes, sensor modules, and actuators bound to each area code, facilitating rapid equipment positioning.

[0040] In this embodiment, the sensor module in the area where the target edge node is located will detect the construction site environment. The sensor module will combine the detected environmental data with the area code it is bound to to generate first sensing data. The first sensing data includes, but is not limited to, temperature and humidity data, wind direction data, and dust concentration.

[0041] After receiving the first sensing data, the target edge node parses the region code of the first sensing data and compares the parsed region code with its own pre-configured list of valid region codes. If the parsed region code is the same as the region code of the region where the target edge node is located, it means that the information matches. At this time, the first sensing data is forward predicted through verification and the target edge node's local network model. If the parsed region code is different from the region code of the region where the target edge node is located, it means that the data match is unsuccessful. At this time, the data is discarded and new sensing data is received again.

[0042] The target edge node has a built-in lightweight local network model. This model can infer the first environmental state for the next time period based on the first perception data corresponding to the current environment. This local network model can be pre-trained using a large amount of historical data, identifying the relationship between environmental states in consecutive time periods. After training, the model is deployed on each edge node in the edge node cluster, allowing the prediction action to be performed at the target edge node, reducing latency issues caused by cloud transmission and processing. Take dam construction as an example:

[0043] The first sensing data x(t) corresponding to the current state: PM2.5 = 60, temperature = 35, wind speed = 5, wind direction = 180°, concrete temperature = 40;

[0044] Prediction model: A trained LSTM neural network that learned the pattern that "when the wind is southerly at 5 m / s, the dust at the current location will spread downwind, and the high temperature will cause the concrete temperature to rise."

[0045] The predicted environmental conditions for the next time period, x(t+n), are: PM2.5 = 45, temperature = 35, wind speed = 5, wind direction = 180°, and concrete temperature = 41. The local network model predicts that dust levels in its area will decrease due to dispersion, but the concrete temperature will rise due to the sustained high temperature.

[0046] This embodiment predicts the environmental conditions for the next time period in order to substitute them into the subsequent objective function to calculate whether it is necessary to turn on the shading or spray cooling in advance to prevent the concrete temperature from rising, even though the current dust concentration is decreasing.

[0047] It should be noted that although this embodiment uses edge nodes to process data instead of the cloud, data processing still takes time. To handle sudden and severe situations on-site in a timely manner, when the target edge node receives the first sensing data, it immediately compares the first sensing data with extreme conditions. For example, it compares the dust concentration in the first sensing data with a preset limit value. When the dust concentration exceeds the preset limit value, it indicates that the current environmental condition is very severe. At this time, the required spray intensity is directly calculated and the corresponding actuator is forced to spray at the required intensity. While forcing the spray operation, the current environmental sensing data continues to be collected, and the environmental condition for the next time period is predicted through a local network model to achieve a more precise control scheme.

[0048] If the first sensing data does not exceed the preset limit value, it means that the environment is not very harsh. At this time, the edge node can complete a series of calculations in steps S1 to S3 and then perform corresponding control operations according to the optimal control sequence.

[0049] Step S2: The target edge node receives the second environmental state transmitted by its neighboring edge nodes. The second environmental state is predicted by the neighboring edge nodes based on the second sensing data collected by the sensor modules in their respective areas.

[0050] While the target edge node predicts the environmental state of its area, other edge nodes in the cluster also predict the environmental state of their area.

[0051] The target edge node calculates the azimuth angle of each of its neighboring edge nodes relative to itself in real time based on the wind direction data in the first sensing data. When the angle between the azimuth angle of any edge node and the current wind direction is within the tolerance range, the edge node can be included in the wind flow neighbor set of the target edge node, and the edge nodes in the wind flow neighbor set are marked as adjacent edge nodes.

[0052] In this embodiment, adjacent edge nodes acquire second sensing data through the sensor modules in their respective regions, and predict the second environmental state for the next time period using their local network models. At this time, the adjacent edge nodes transmit the predicted second environmental state to the target edge node.

[0053] After receiving the second environmental state from the neighboring edge nodes, the target edge node can perform collaborative control calculations to achieve the most efficient and energy-saving global regulation.

[0054] Step S3: Based on the cooperative control objective function, the target edge node generates the optimal control sequence through a distributed model according to the first and second environmental states. Based on the optimal control sequence, the designated execution mechanism in the area where the target edge node is located is controlled to perform relevant operations in real time.

[0055] The main idea of ​​the collaborative control method in this embodiment is to divide the entire construction site into multiple areas, with each edge node responsible for one area. Distributed optimization is performed through a distributed model (DMPC). Each edge node considers the state of adjacent areas when optimizing its own control quantity, and the global optimum is achieved through iteration.

[0056]

[0057] Where, x i (t) represents the first environmental state (such as dust concentration, temperature, etc.) of the target edge node i at time t;

[0058] x ref It is an ideal state reference value, that is, a reference value that the desired state is to be achieved (such as the ideal dust concentration);

[0059] Q i Q is the weight matrix between the state and the reference value, representing the degree of importance attached to the state tracking error. i The larger the value, the more desirable the state x is. i (t) is close to the reference value x ref ;

[0060] u i (t) represents the control quantity (spray intensity, awning opening, etc.) of the specified actuator at time t;

[0061] R i This is the weight matrix of the control variables, representing the degree of importance attached to the control variables. R i The larger the value, the less desirable it is to use a large control quantity (i.e., the more desirable the control action is to be as small as possible to save energy or reduce wear and tear on the actuator).

[0062] x j(t) represents the second environmental state of the adjacent edge node j at time t;

[0063] S ij S is the coupling penalty matrix, representing the degree of importance placed on ensuring that the state of node i remains consistent with the state of node j. ij The larger the value, the more desirable it is for the states of two adjacent nodes to be as similar as possible.

[0064] N represents the N future time steps.

[0065] The overall objective function of cooperative control means finding an optimal control sequence u. i (0), u i (1), ..., u i Let (N) minimize the sum of the following three costs for all times from t=0 to t=N:

[0066] 1. The degree to which the state of target edge node i deviates from the reference value (multiplied by weight Q) i );

[0067] 2. The magnitude of the control variable (multiplied by the weight R) i );

[0068] 3. The difference between the state of the target edge node i and the state of its neighboring edge node j (multiplied by weight S) ij ).

[0069] At this point, the target edge node issues control commands to the corresponding actuator in its region according to the optimal control sequence, enabling the actuator to perform the corresponding operation.

[0070] For example, the target edge node i predicts a dust concentration of 55 μg / m³. 3 The concentration was only slightly exceeded, but the concentration difference between the spray and the adjacent edge node j downwind was detected to be increasing. If the spray is turned off at this point, the control cost term... It is 0, but the collaborative cost item is 0. The cost will increase dramatically, resulting in a high total cost. If spraying is maintained, the control cost increases slightly, but the cooperative cost decreases, leading to a lower total cost. Therefore, target edge node i chooses to continue spraying until the concentration difference decreases to a safe range, while the region of adjacent edge node j is protected, resulting in a better global state.

[0071] In this embodiment, the edge node cluster is connected to the cloud. After performing local calculations, the edge nodes can upload the calculation results (such as optimal control sequences and control commands) and key parameters from the calculation process (such as sensing data and environmental conditions for the next time period) to the cloud for storage. To further improve the accuracy of control, the cloud can be used to achieve self-calibration of the edge node control parameters through environmental assessment. Specifically:

[0072] When the designated execution agency in the area where the target edge node is located performs an operation, the target edge node uploads data to the cloud. At the same time, the cloud obtains real-time meteorological data of the geographical location of the construction site. Based on the real-time meteorological data, the cloud predicts the degree of impact of the weather on the construction environment, dynamically adjusts the key parameters in the collaborative control objective function, and generates a new execution plan. The designated execution agency in the area where the target edge node is located then executes the new execution plan in real time.

[0073] For example:

[0074] Meteorological data from the construction site was obtained from the cloud, and the data indicated that there would be a level 6 southerly wind in 2 hours.

[0075] The cloud-based system evaluates meteorological data based on a wind flow field model and predicts that southerly winds will cause dust to accumulate more easily at the upwind end A of the construction area, while dust at the downwind end B will be quickly dispersed.

[0076] Based on the assessment results, the cloud platform issued a more stringent temporary reference value for upwind location A: x ref _ A _ new =40μg / m 3 A flexible temporary reference value is issued for downwind yoke B: x ref _ B_new =60μg / m 3 .

[0077] At this point, the edge nodes execute according to the new reference values. Before the wind arrives, the target for upwind node A becomes "dust levels must be reduced to below 40," which is equivalent to increasing the spray intensity in advance to actively suppress dust to a lower level. When the strong wind arrives, because the baseline value is very low, even if dust is stirred up, it is unlikely to exceed the standard. The target for downwind node B is temporarily relaxed because the wind will naturally disperse the dust, eliminating the need for excessive spraying and thus saving a significant amount of water resources.

[0078] Alternatively, the cloud might retrieve a weather forecast predicting continued high temperatures and sunny skies this afternoon. The cloud then uses a concrete hydration heat model to assess the situation and predicts that the surface temperature will far exceed the critical temperature allowed for concrete curing. In this case, the cloud can generate a corresponding decision, such as issuing a more stringent temperature reference value (T) to relevant regional nodes at midday. ref_new =30℃. The edge nodes receive the new target in the early stage of temperature rise, thus deploying the shading net earlier and possibly activating the spray cooling system in advance, thereby effectively suppressing the temperature rise curve and keeping the concrete surface temperature below the safe threshold.

[0079] It should be noted that data processing performed in the cloud can be carried out simultaneously with data processing performed on the edge nodes, or cloud operations can be performed after the edge nodes have completed their calculations, in order to optimize the control results output by the edge nodes. The specific choice can be made based on the emergency situation of the site environment or the edge computing occupancy.

[0080] In another embodiment, an IoT-enabled intelligent construction site environment monitoring and adaptive control system is also provided. The system specifically includes an edge node cluster and a cloud connected to the edge node cluster. The target edge node in the edge node cluster is used to execute the IoT-enabled intelligent construction site environment monitoring and adaptive control method as described in Embodiment 1.

[0081] It should be noted that the functions implemented by this system can be found in the corresponding descriptions in the above methods, and will not be repeated here.

[0082] In another embodiment, an electronic device is also provided. Figure 3 A structural block diagram of an electronic device according to an embodiment of the present invention is shown. Figure 3 As shown, the electronic device includes a memory 100 and a processor 200. The memory 100 stores a computer program that can run on the processor 200. When the processor 200 executes the computer program, it implements the IoT-based intelligent construction site environmental monitoring and adaptive control method described in the above embodiment. The number of memories 100 and processors 200 can be one or more.

[0083] The electronic device also includes:

[0084] The communication interface 300 is used to communicate with external devices and perform data exchange and transmission.

[0085] If the memory 100, processor 200, and communication interface 300 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc.

[0086] Optionally, in a specific implementation, if the memory 100, processor 200, and communication interface 300 are integrated on a single chip, then the memory 100, processor 200, and communication interface 300 can communicate with each other through an internal interface.

[0087] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method provided in this invention.

[0088] This invention also provides a chip, which includes a processor for calling and executing instructions stored in a memory, causing a communication device on which the chip is installed to perform the method provided in this invention.

[0089] This invention also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method provided in this invention.

[0090] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting the Advanced Reduced Instruction Set Computing (RISC) machine (ARM) architecture.

[0091] Further, optionally, the aforementioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile or non-volatile, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0092] In the above embodiments, implementation can be achieved, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0093] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0094] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0095] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A construction site environment monitoring and self-adaptive control method based on Internet of Things intelligence, characterized in that, The application is performed on target edge nodes in an edge node cluster, including: The target edge node acquires the first sensing data collected by the sensor module in its area, and performs forward prediction on the first sensing data based on the pre-configured local network model to obtain the first environmental state in the next time period. The target edge node receives a second environmental state transmitted by its neighboring edge nodes. The second environmental state is predicted by the neighboring edge nodes based on the second sensing data collected by the sensor modules in their respective areas. The target edge node, based on a cooperative control objective function, generates an optimal control sequence using a distributed model according to the first and second environmental states. This optimal control sequence is then used to control a designated actuator in the region where the target edge node is located to perform relevant operations in real time. The cooperative control objective function is: ； in, Let i be the first environmental state of the target edge node i at time t. This is an ideal reference value. It is a weight matrix between the state and the reference value. R is the control quantity of the specified actuator at time t. i It is the weight matrix of the control quantity. S represents the second environmental state of the adjacent edge node j at time t. ij Let N be the coupling penalty matrix, and N be the future N time steps. 2.The construction site environment monitoring and self-adaptive control method of Internet of Things intelligence according to claim 1, characterized in that, Also includes: When the target edge node acquires the first sensing data, it parses the region code of the first sensing data and compares the region code with its own pre-configured list of legal region codes. If they match, the data is verified and forward prediction is performed on the first sensing data using the local network model. If they do not match, the data is discarded. The list of legal region codes records the region code corresponding to each area in the construction site, as well as the edge node and sensor module bound to each region code. 3.The construction site environment monitoring and self-adaptive control method of Internet of Things intelligence according to claim 1, characterized in that, The first sensing data includes temperature and humidity data, wind direction data, and dust concentration.

4. The IoT-based intelligent construction site environmental monitoring and adaptive control method according to claim 1, characterized in that, Also includes: The target edge node calculates its azimuth angle relative to each of its neighboring edge nodes in real time. When the angle between the azimuth angle of any edge node and the current wind direction is within the tolerance range, the edge node is marked as the neighboring edge node.

5. The IoT-based intelligent construction site environmental monitoring and adaptive control method according to claim 1, characterized in that, Also includes: Meteorological data is acquired from the cloud, and key parameters in the collaborative control objective function are dynamically adjusted based on the meteorological data to generate a new execution plan. The designated execution agency in the area where the target edge node is located is controlled to execute the new execution plan in real time. 6.The construction site environment monitoring and self-adaptive control method of Internet of Things intelligence according to claim 1, characterized in that, Also includes: The dust concentration in the first sensed data is compared with a preset limit value. When the dust concentration exceeds the preset limit value, the required spray intensity is directly calculated and the corresponding actuator is forced to perform spraying operation according to the required spray intensity.

7. The construction site environment monitoring and self-adaptive control system of Internet of Things intelligence, characterized in that, include: An edge node cluster, comprising multiple target edge nodes; The target edge node is used to execute the IoT-based intelligent construction site environmental monitoring and adaptive control method as described in any one of claims 1 to 6.

8. An electronic device, comprising: include: A processor and a memory, wherein the memory stores instructions that are loaded and executed by the processor to implement the IoT-based intelligent construction site environmental monitoring and adaptive control method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the IoT-based intelligent construction site environmental monitoring and adaptive control method as described in any one of claims 1 to 6.

Images