Intelligent engineering supervision system based on multistage linkage and multi-device linkage

Abstract

The invention relates to the field of engineering construction, and discloses an intelligent engineering supervision system based on multistage linkage and multi-device linkage, which comprises a data acquisition module, an edge calculation module, an equipment cooperative control module, a communication optimization module and a task scheduling module. The system realizes real-time sensing and intelligent analysis of field data through multi-modal information acquisition and structured processing; the edge calculation module performs local processing on the structured data to generate a control instruction and task optimization data; the task scheduling module dynamically adjusts task distribution based on the communication state; the device cooperative control module ensures efficient linkage of multiple devices; the communication optimization module guarantees low time delay and high reliability of system data transmission. According to the invention, through a multi-stage linkage and multi-device cooperation mechanism, links of data acquisition, edge calculation, task scheduling and equipment control are broken through, and full-chain closed-loop control of construction site supervision is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering construction, and specifically to an intelligent engineering supervision system based on multi-level linkage and multi-device linkage. Background Art

[0002] Currently, in the field of engineering construction, on-site supervision generally relies on decentralized systems. Monitoring is one system, equipment control is another system, and task scheduling is yet another set. There are serious data gaps, and the linkage between modules is poor. When problems occur on-site, the transmission of instructions is often lagged. Schedulers can only rely on experience to judge, and it is difficult to guarantee the response speed.

[0003] Most traditional systems adopt a centralized architecture, and all data is uploaded to the cloud for processing. At first glance, it seems unified, but in fact, the efficiency is slowed down. Once there are network fluctuations in data transmission, task execution is likely to be delayed. The on-site situation changes rapidly, the cloud feedback is slow, and the equipment linkage response cannot keep up with the rhythm. This "front-end collection, back-end decision-making" mode often seems powerless in complex working conditions.

[0004] In terms of equipment scheduling, existing systems mostly rely on fixed rules or static algorithms. Once a task is issued, the change cost is high. The equipment load distribution is not flexible enough. One machine is idle while another is overloaded. The collaborative efficiency is low, the resource scheduling is not precise enough, resulting in a double waste of time and energy.

[0005] Communication problems cannot be ignored either. The construction site environment is complex, with many metal structures and obstacles, and the stability of traditional communication links is limited. Once the signal is interfered or the bandwidth is limited, the task instructions cannot be transmitted, and the equipment status cannot be transmitted back. The scheduling system cannot immediately grasp the on-site situation and can only "guess", which is prone to errors.

[0006] Furthermore, the multi-modal data acquisition ability is generally limited. Existing solutions often focus on video or simple sensor data and lack means of fusion processing. Environmental data, personnel status, and equipment working conditions cannot form a unified understanding. The true on-site situation cannot be fully restored by the system, resulting in large subsequent judgment deviations and a decline in execution efficiency.

[0007] Therefore, the present invention proposes an intelligent engineering supervision system based on multi-level linkage and multi-device linkage to solve the deficiencies of the prior art. Summary of the Invention

[0008] In view of the deficiencies of the prior art, the present invention provides an intelligent engineering supervision system based on multi-level linkage and multi-device linkage, which solves the problems of system dispersion, lagging response, low scheduling efficiency, and insufficient equipment coordination in existing engineering supervision.

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: An intelligent engineering supervision system based on multi-level linkage and multi-device linkage, including: A data acquisition module, which is used to obtain multi-modal information of the construction site, convert the multi-modal information of the construction site into structured data, and then provide it to the edge computing module for preprocessing, and support the task scheduling module to call the structured data; An edge computing module, which is used to locally preprocess the structured data provided by the data acquisition module, generate construction equipment control instructions and task optimization data, and provide them to the equipment collaborative control module and the task scheduling module respectively; An equipment collaborative control module, which is used to execute the construction equipment control instructions provided by the edge computing module, ensure the linkage control of construction equipment, and at the same time feedback the execution status to the task scheduling module; A communication optimization module, which is used to establish a communication network with low latency and high reliability to ensure stable and efficient data interaction between the equipment collaborative control module and the task scheduling module; A task scheduling module, which is used to execute the task optimization data provided by the edge computing module, optimize task allocation based on the network status provided by the communication optimization module to improve the overall execution efficiency of the system, and at the same time send task instructions to the equipment collaborative control module and request necessary information updates from the data acquisition module.

[0010] Preferably, the multi-modal information includes: Video surveillance data, which is used to monitor the safety situation, equipment operation status and personnel activities at the construction site in real time; Environmental sensor data, at least including temperature, humidity, air pressure, wind speed, and light environment information, which is used to evaluate the safety of the construction environment; Equipment operation data, at least including the location, status, operation speed, load, temperature, and vibration of construction equipment, to ensure the normal operation and maintenance requirements of the equipment; Personnel positioning and behavior data, which is used to obtain the location, health status, and behavior patterns of construction personnel through intelligent wearable devices to ensure operation safety; Geographic information system data, which is used to obtain the precise geographical location, equipment distribution, and construction area geographical data of the construction site; Sensor monitoring data, at least including mechanical pressure, sensor pressure, flow rate, and noise, which is used to monitor the physical indicators during the construction process through various sensors.

[0011] Preferably, the edge computing module adopts an adaptive computing architecture, which supports dynamically adjusting the computing resource allocation based on the task complexity, and is used to improve the processing efficiency and reduce energy consumption.

[0012] Preferably, the construction equipment control instructions include: Device start / stop instruction, which controls the start and stop of construction equipment to ensure that the equipment works or stops working as required; Operation parameter adjustment instruction, which adjusts the operation parameters of the equipment according to the on-site tasks and equipment status; Device linkage control instruction, which generates linkage instructions to ensure the coordinated operation of each device when multiple construction equipment work together; Fault warning and maintenance instruction: According to the equipment sensor data, generate fault warning instructions and send maintenance and repair instructions to ensure the safety and long-term stability of the equipment; Automatic adjustment instruction: Automatically adjust the working mode, power or operation path of the equipment according to the environmental changes at the construction site.

[0013] Preferably, the task optimization data includes: Task priority ranking data, which optimizes the task execution order according to the construction plan, task urgency and resource availability; Task allocation data, according to the equipment operation status, construction personnel configuration and available resources; Operation adjustment data, which optimizes the task execution method by combining environmental monitoring and safety data; Dynamic scheduling data, which adjusts the task execution plan based on the real-time construction progress and emergencies; Optimization strategy data, which generates scheduling optimization strategies by combining historical data analysis.

[0014] Preferably, the equipment collaborative control module includes an intelligent scheduling unit, which optimizes the scheduling strategy of construction equipment based on the reinforcement learning algorithm.

[0015] Preferably, the communication optimization module is based on a dynamic network protocol and uses a distributed optimization algorithm for intelligent regulation of data traffic.

[0016] Preferably, the steps of establishing a low-latency and high-reliability communication network include: Select a suitable communication protocol to ensure low latency and high stability during data transmission; Configure communication equipment and optimize the network topology to reduce the delay in the signal transmission path; Deploy redundant communication links to ensure the reliability and high availability of the network in case of failures; Use network load balancing technology to dynamically adjust network traffic and avoid communication bottlenecks and congestion; Monitor the communication quality and adjust network parameters in real time to ensure reliable data exchange even in harsh environments.

[0017] Preferably, the task scheduling module adopts a heterogeneous computing task scheduling strategy, which combines edge computing resources and cloud computing resources for task allocation and execution order.

[0018] Preferably, the task scheduling module includes the following submodules: The task allocation module reasonably allocates tasks to various construction equipment and personnel according to the construction progress, task priority and resource status; the task monitoring module monitors the execution of tasks in real time, obtains the working status of various equipment and personnel, and ensures that tasks are executed as planned; The task optimization module dynamically adjusts task allocation based on field data and equipment status, and optimizes the task execution path and sequence; the resource scheduling module dynamically adjusts resource allocation based on the real-time status of equipment and personnel; The task feedback module collects feedback information during the task execution process, analyzes the task execution effect, provides improvement suggestions and makes adjustments.

[0019] The present invention provides an intelligent engineering supervision system based on multi-level linkage and multi-device linkage. It has the following beneficial effects: 1. The present invention connects data collection, edge computing, task scheduling and equipment control through a multi-level linkage and multi-device coordination mechanism, and realizes full-chain closed-loop control of construction site supervision. Compared with the traditional system that relies on manual inspection and isolated equipment operation, it greatly improves the response speed and control accuracy, and effectively solves the problems of on-site information asymmetry and delayed task allocation.

[0020] 2. The present invention introduces edge computing architecture, data is processed on-site, control instructions are generated in real time, and task scheduling is updated in real time. On-site problems can be solved on-site without frequent reliance on the cloud. Compared with the "half-beat" mode of the previous centralized architecture, this method is more flexible, more real-time, and more energy-efficient, truly making the system run faster and more stable.

[0021] 3. The present invention adopts dynamic protocols and distributed optimization algorithms through the communication module, and the network transmission is stable and does not drop the link. Multi-path and multi-link guarantees can ensure real-time information even in complex construction site environments. Compared with the problems of signal packet loss and command delay in the old system, this solution makes on-site dispatch more confident.

[0022] 4. The present invention constructs an intelligent strategy system for task scheduling. The reinforcement learning algorithm runs through the entire scheduling process. Task allocation is more in line with reality and adjustments are more timely. Different from the traditional scheduling method that relies on fixed rules and lacks adaptability, this strategy enables the entire system to have the ability to "adjust itself", which is more efficient and more resistant to emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a system architecture diagram of the present invention; Figure 2 This is a task scheduling module architecture diagram of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] Please refer to Figure 1 and Figure 2 The embodiments of the present invention provide an intelligent engineering supervision system based on multi-level linkage and multi-device linkage, including: A data acquisition module, which is used to obtain multi-modal information of the construction site, convert the multi-modal information of the construction site into structured data, and then provide it to the edge computing module for preprocessing, and support the task scheduling module to call the structured data; The data acquisition module obtains the multi-modal information of the construction site and converts this information into structured data, providing accurate input for the subsequent processing modules. The data acquisition module is the starting point of the entire system, and the data it collects provides the basis for the operation of subsequent modules such as edge computing and task scheduling. Specifically, the data acquisition module collects diverse data of the construction site in real time through various sensors and monitoring devices, including video surveillance data, environmental sensor data, equipment operation data, personnel positioning and behavior data, geographic information data, and sensor monitoring data.

[0026] Generally, the data acquisition module comprehensively and real-time monitors the construction site through various sensors and monitoring systems. The data sources of the construction site are mainly divided into the following categories: Video surveillance data: The situation of the construction site is captured in real time through cameras, including personnel activities, equipment operation status, safety conditions of the construction area, etc. Video surveillance data can provide intuitive data support for the safety management of the construction site, ensuring timely discovery of potential safety hazards or abnormal behaviors.

[0027] Environmental sensor data: This type of data is collected through environmental sensors deployed at the construction site, mainly including information such as temperature, humidity, air pressure, wind speed, and light. These data can reflect the basic conditions of the construction environment and provide data support for judging whether the construction meets safety requirements. For example, too high a temperature may cause equipment overheating, and too high humidity may affect the construction quality.

[0028] Equipment operation data: Equipment operation data is mainly collected by sensors installed on construction equipment to obtain the status information of the equipment in real time, including the location, load, vibration, temperature, operating speed, etc. of the equipment. The collection of these data helps to grasp the working conditions of construction equipment in real time, ensure that the equipment is in the best working state, and can promptly detect potential equipment failures.

[0029] Personnel positioning and behavior data: To ensure the safety of construction personnel, the data collection module also obtains the location information, health status, behavior patterns, etc. of personnel through intelligent wearable devices. These data can monitor the location and safety of construction personnel in real time, especially in dangerous areas or during special operations, and can issue real-time warnings to personnel.

[0030] Geographic Information System (GIS) data: This type of data can accurately provide information such as the geographic coordinates of the construction site and the distribution of construction areas. Through GIS data, the system can accurately locate the positions of equipment and personnel, providing the necessary location information for the scheduling module.

[0031] Sensor monitoring data: In addition to the above-mentioned types of data, sensor monitoring data also includes physical parameters such as mechanical pressure, sensor pressure, flow rate, and noise. These data can monitor the specific construction process at the construction site in real time, providing support for process optimization and safety management during construction.

[0032] In the data collection module, all the collected data will first undergo preliminary preprocessing to convert different types of data into structured data in a unified format. This process is to convert the original data on-site into a format that can be processed by a computer. The work of the data collection module is not limited to collecting raw data, but also includes preliminary screening, denoising, and necessary calibration of the data. For example, during the collection of environmental data, if the temperature and humidity sensors malfunction or the data is abnormal, the system will perform data calibration through the set fault tolerance mechanism to ensure the accuracy and effectiveness of the collected data.

[0033] As an option, the data collection module can transmit the collected data to the edge computing module for further processing through wireless transmission technology. To reduce the latency during data transmission and ensure the transmission stability of the data, the data collection module can use a local area network or a dedicated communication network to communicate with the edge computing module. This communication method can improve the data transmission efficiency and avoid affecting the real-time performance and accuracy of subsequent modules due to network latency or data loss.

[0034] Specifically, the working steps of the data collection module can be summarized as follows: Real-time data collection: Through devices such as sensors and cameras, various data at the construction site are obtained in real time, including video, environmental, equipment, personnel, geographic information, etc. data.

[0035] Data preprocessing: Conduct preliminary processing on the collected raw data, including denoising, data screening, format conversion, etc., to ensure the accuracy and availability of the data.

[0036] Data structured conversion: Convert data from different sources into structured data for subsequent module processing. Data structuring usually adopts a unified data format, such as JSON, XML, or CSV, etc.

[0037] Data transmission: Transmit the processed structured data to the edge computing module through a high-speed communication network. During the data transmission process, encryption and data verification technologies are adopted to ensure the security and integrity of the data.

[0038] Real-time monitoring and feedback: The data acquisition module continuously monitors various data at the construction site and adjusts the acquisition strategy in a timely manner according to the changes on-site. For example, if a certain sensor fails, the system will automatically switch to a backup sensor for data acquisition to ensure the continuity of the data.

[0039] In some embodiments, the data acquisition module can also adopt a distributed acquisition method, that is, multiple sensors are distributed at different positions on the construction site for local data acquisition and real-time processing. This distributed data acquisition method can more flexibly cope with the complex environment and changing task requirements at the construction site.

[0040] In some embodiments, the data acquisition module may adopt advanced multi-sensor fusion technology to further improve the accuracy of data acquisition. For example, when multiple sensors collect the same data (such as temperature, humidity, etc.), through the multi-sensor data fusion algorithm, the system can remove the deviation that may be brought by a single sensor and improve the reliability of the data. This multi-sensor fusion technology can still maintain the accuracy and stability of the system data when a sensor fails or has a large error.

[0041] Through the data acquisition module, the system can comprehensively and real-time obtain various information at the construction site and conduct structured processing on this information. Compared with the traditional manual monitoring method, the data acquisition module can greatly improve the acquisition speed and accuracy of the construction site data, reduce human operation errors. The data acquisition module can also capture safety hazards at the construction site in real-time and provide reliable input data for the subsequent edge computing module, thus ensuring the efficient operation of the entire system.

[0042] In addition, the data acquisition module can also ensure that various data at the construction site can be seamlessly connected to subsequent task scheduling, equipment collaborative control and other modules through optimized data processing and transmission methods. The accuracy, real-time and integrity of the data provide high-quality data support for subsequent modules, thus playing a crucial role in the entire system.

[0043] Through the optimization and implementation of the data acquisition module, the entire intelligent engineering supervision system can achieve efficient, accurate, and reliable on-site data acquisition and transmission, providing strong technical support for intelligent scheduling, equipment collaborative control, safety monitoring, etc. during the construction process.

[0044] An edge computing module, which is used to perform local preprocessing on the structured data provided by the data acquisition module, generate construction equipment control instructions and task optimization data, and provide them to the equipment collaborative control module and the task scheduling module respectively; The edge computing module performs local preprocessing on the structured data obtained from the data acquisition module. The core function of this module is to process on-site data in real time, generate construction equipment control instructions and task optimization data, and transmit them to the equipment collaborative control module and the task scheduling module respectively. The edge computing module is located at the front end of the system, receives various on-site information from the data acquisition module, performs efficient real-time calculations, and provides data support for subsequent operations of the system.

[0045] In the overall system architecture, the edge computing module plays a bridging role, ensuring the smooth transfer of data from on-site collection to subsequent execution. The connection with the data acquisition module enables this module to obtain real-time data from the site in a timely manner and perform local processing on the data. In this way, the edge computing module effectively reduces network latency while improving data processing efficiency and system response speed.

[0046] Generally, the edge computing module first receives structured data from the data acquisition module. These data contain various information about the construction site, such as equipment operating status, environmental conditions, personnel locations, etc. After receiving this data, the edge computing module will further analyze and process it. Specifically, the main tasks of the edge computing module include: Data preprocessing: The edge computing module preprocesses the structured data from the data acquisition module. This process includes operations such as data cleaning, denoising, and data correction to ensure the accuracy and availability of the data. For example, environmental data may be interfered by external noise, and the edge computing module will filter out unnecessary interference information through set algorithms to ensure the accuracy of the data.

[0047] Task optimization: The edge computing module generates task optimization data based on the real-time data on the site and the requirements of construction tasks. The core of task optimization data is to optimize the execution order, priority, and resource allocation of tasks to ensure the efficient completion of construction tasks. For each construction task, the edge computing module will dynamically adjust the execution plan of the task according to multiple factors such as equipment operating status, resource availability, and safety requirements, thereby improving the overall construction efficiency.

[0048] Generation of Construction Equipment Control Instructions: The edge computing module generates construction equipment control instructions according to preset rules and algorithms. These control instructions include equipment start / stop, work mode adjustment, and collaborative control between devices. Specifically, the edge computing module generates specific control instructions based on the real-time status of the equipment, such as load, speed, temperature, etc., to ensure that the equipment executes according to the predetermined tasks and coordinates between different tasks. For some complex tasks, the edge computing module can ensure the collaborative work of each device through the linkage control between devices to improve the operation efficiency.

[0049] Adaptive Computing Resource Allocation: In some embodiments, the edge computing module adopts an adaptive computing architecture that can dynamically adjust the allocation of computing resources according to the complexity of the task and the real-time situation on-site. Specifically, when the task is relatively simple, the edge computing module allocates fewer computing resources, thus reducing the energy consumption of the system; while when the task is relatively complex, the module automatically increases the computing resources to ensure that the task can be completed efficiently. This dynamic resource allocation method adopted by the edge computing module not only improves the computing efficiency but also reduces the energy consumption, thus realizing green construction.

[0050] Feedback of Task Data and Equipment Status: During the execution process, the edge computing module also receives the feedback data from the equipment collaborative control module and the task scheduling module in real time, and adjusts the task optimization data and control instructions according to the feedback information. For example, when a device fails or the task progress is delayed, the edge computing module adjusts the priority of the task according to the feedback data, optimizes the resource allocation and task sequence to ensure the smooth operation of the system.

[0051] In a possible implementation, the edge computing module processes data by setting up a computing node. This computing node is equipped with a high-performance processor and sufficient storage space, and can efficiently process a large amount of data generated on-site. These computing nodes perform data interaction with the data acquisition module, the equipment collaborative control module, and the task scheduling module through a dedicated network.

[0052] The edge computing module performs local processing on some data that does not need to be transmitted to the cloud through local computing and data storage. This not only reduces the burden on the communication network but also can reduce the network latency and improve the real-time performance of the system. Specifically, the edge computing module can divide data processing into two parts: real-time data processing and batch data processing. The real-time data processing part mainly processes the real-time data from the data acquisition module and generates construction equipment control instructions and task optimization data. The batch data processing part is responsible for processing the historical data and analysis data during the construction process and is used to generate optimization strategies and improvement plans.

[0053] In some embodiments, the edge computing module also adopts machine learning-based algorithms for task optimization. Through machine learning, the edge computing module can automatically adjust the optimization strategy based on historical data and on-site feedback, making the execution of construction tasks more intelligent. In this way, the edge computing module can continuously learn and adjust during the execution process, thereby achieving the best optimization of tasks.

[0054] Through local computing and data processing, the edge computing module effectively improves the system's response speed and processing efficiency. Compared with the traditional centralized computing method, the edge computing module in this embodiment can reduce data transmission time and latency, ensuring that on-site real-time data can be quickly processed and fed back to the task scheduling and device collaborative control module. This method reduces the dependence on cloud computing and avoids delays caused by network problems.

[0055] Through the adaptive computing resource allocation mechanism, the edge computing module can dynamically adjust the allocation of computing resources without affecting the system performance, effectively reducing energy consumption. In addition, the edge computing module can adjust the task execution order and device operation mode in real time according to the actual on-site situation and device status, further improving construction efficiency and ensuring safety.

[0056] In this embodiment, the computing process of the edge computing module can be described by the following formula: T opt = f(D task , D env , R resources ); Where, T opt represents task optimization data, which is an optimized scheduling scheme generated according to the task complexity and resource status on-site; D task represents task data, including the priority, time requirements, etc. of construction tasks; D env represents environmental data, including information such as temperature and humidity at the construction site; R resources represents the currently available computing resources and device status.

[0057] The edge computing module of the present invention provides strong technical support for the entire intelligent project supervision system through multiple functions such as real-time data processing, task optimization, generation of device control instructions, and adaptive computing resource allocation. Its local computing and data processing methods not only improve the real-time performance and stability of the system but also effectively reduce the energy consumption of the system. Through close cooperation with other modules, the edge computing module can ensure the efficient and orderly execution of various tasks at the construction site.

[0058] The device collaborative control module is used to execute the construction equipment control instructions provided by the edge computing module to ensure the interlocking control of construction equipment and at the same time feedback the execution status to the task scheduling module; The equipment collaborative control module is responsible for the dynamic control and collaborative operation of construction equipment, ensuring the orderly operation between equipment, optimizing the construction process, and improving operation efficiency. This module receives and executes the construction equipment control instructions generated by the edge computing module, and at the same time collects and feeds back the equipment operation status for dynamic adjustment. Its core goal is to achieve multi-equipment collaborative operation through intelligent scheduling methods at the construction site, improve construction efficiency, reduce resource waste, and quickly adjust the equipment operation strategy in case of emergencies to meet the requirements of complex construction environments.

[0059] Generally, before the start of a construction task, the equipment collaborative control module determines the initial operation status of each equipment according to the equipment control instructions provided by the edge computing module, and makes adjustments based on real-time data during the task execution. As an option, the equipment collaborative control module can perform parallel scheduling of multiple devices through a distributed computing architecture to reduce decision-making latency and optimize the collaborative operation strategy of the devices. In one possible implementation, the equipment collaborative control module adopts an optimization method based on deep reinforcement learning, enabling the equipment to dynamically adjust the working mode in different construction scenarios to adapt to the changes in the construction environment.

[0060] The core functions of the equipment collaborative control module include equipment status monitoring, control instruction execution, task collaborative scheduling, exception handling and feedback, etc. Specifically, this module generates specific control strategies by collecting the operation status of the equipment in real time (such as equipment load, speed, energy consumption, vibration conditions, etc.) and combining parameters such as task requirements and environmental factors to coordinate the collaborative relationship between equipment.

[0061] In some embodiments, the equipment collaborative control module can intelligently allocate the workload based on the working characteristics and task requirements of different types of equipment. For example, in a construction task where an excavator, a crane, and a transport vehicle need to collaborate, the equipment collaborative control module will determine the working sequence, operation time, and task allocation method of the equipment according to the current status of the equipment, task priority, load capacity, and construction environment to ensure the efficient execution of the construction task.

[0062] Specifically, the operation logic of the equipment collaborative control module is as follows: The equipment collaborative control module first receives the task planning data from the edge computing module and parses information such as the initial status, availability, and task requirements of each equipment.

[0063] This module optimizes the task execution sequence, load distribution, and energy consumption management of the equipment by combining real-time equipment operation data to ensure the efficient collaborative operation of the equipment.

[0064] During the operation of the device, the device collaborative control module continuously monitors the device status. When detecting device anomalies (such as overload, failure, or insufficient resources), it automatically adjusts the task scheduling and assigns other devices to take over the current task to reduce the downtime.

[0065] After the task is completed, this module feeds back the device execution status to the task scheduling module and records the task execution data to optimize the subsequent task allocation strategy.

[0066] In this embodiment, the device collaborative control module adopts an adaptive control algorithm combined with machine learning methods to ensure efficient collaboration and intelligent scheduling among devices. The core technology implementation of this module includes the following aspects: Device status monitoring and data collection. The device collaborative control module collects the operating status of the device in real time through the sensor network, including but not limited to: Device speed (v d ), representing the operating speed of the current device (m / s); Device load (L d ), representing the load currently borne by the device (kg); Device energy consumption (E d ), representing the current energy consumption situation of the device (kWh); Device temperature (T d ), representing the current operating temperature of the device (°C); Device vibration status (V d ), used to monitor whether there is abnormal vibration in the device; Device location (P d ), used to record the geographical location coordinates (GPS) of the device.

[0067] Parsing and execution of device control instructions. The device collaborative control module parses the device control instructions generated by the edge computing module and executes the corresponding device control operations, including: Start-stop control, controlling the start or stop of the device according to the task requirements.

[0068] Speed adjustment, adjusting the operating speed of the device according to the construction task progress to match the operation rhythm of other devices.

[0069] Load management, allocating appropriate task loads according to the current bearing capacity of the device to prevent the device from overloading.

[0070] Job sequence adjustment, coordinating the working sequences of multiple devices to optimize the execution efficiency of construction tasks.

[0071] Multi-device task collaborative optimization. In some embodiments, the device collaborative control module uses reinforcement learning methods to optimize multi-device tasks, enabling the efficiency of device collaborative operations to reach the optimal level. This optimization problem can be described by the following mathematical model: Among them, O opt represents the task optimization objective function, comprehensively considering the task completion time and energy consumption cost; w d represents the task weight of device d, which determines its importance in the task; T comp (d) represents the task completion time (s) of device d; E d represents the total energy consumption (kWh) of device d during task execution; λ is the energy consumption weight coefficient, controlling the importance of energy consumption in the optimization objective; N is the total number of devices at the construction site.

[0072] The significance of this optimization objective function is to minimize the energy consumption of devices as much as possible on the premise of ensuring that the task is completed on time, so as to optimize the resource utilization rate at the construction site.

[0073] The device collaborative control module plays a connecting role in the entire system architecture. First, it receives and executes device control instructions from the edge computing module, and based on the task information provided by the task scheduling module, it monitors and adjusts the device status. Second, it feeds back the real-time operating status of the device to the task scheduling module, so that the task scheduling module can adjust the task allocation strategy according to the latest device information.

[0074] In some embodiments, the device collaborative control module can also be combined with an intelligent fault diagnosis system to achieve real-time monitoring and predictive maintenance of the device status. For example, when the device collaborative control module detects that the abnormal vibration value of the device exceeds the threshold, it can immediately trigger an alarm and notify the task scheduling module to reallocate tasks to reduce the impact of device failures on the construction progress.

[0075] The device collaborative control module realizes the efficient cooperation of multiple devices through real-time status monitoring, intelligent device scheduling, and task optimization strategies, ensuring the smooth completion of construction tasks. This embodiment uses reinforcement learning methods to optimize device scheduling and combines an adaptive control algorithm to adjust the operating status of the device, thereby improving the utilization rate of the device, reducing energy consumption, and reducing the delay of construction tasks. The device collaborative control module plays a core role in the intelligent engineering supervision system, closely collaborating with the edge computing module, task scheduling module, etc., to achieve intelligent management and efficient operation of the construction site devices.

[0076] The communication optimization module is used to establish a low-latency and highly reliable communication network to ensure stable and efficient data interaction between the device collaborative control module and the task scheduling module; The communication optimization module undertakes a crucial task, ensuring stable and efficient data transmission between modules and dynamically adjusting communication strategies according to the real-time situation at the construction site. Due to the complex environment at the construction site, data transmission may be affected by various factors, such as signal interference, device distance, network congestion, etc. Therefore, the communication optimization module needs to optimize the network transmission link to improve the reliability and timeliness of data transmission.

[0077] Generally, the communication optimization module maintains real-time communication with the data acquisition module, edge computing module, device collaborative control module, and task scheduling module to ensure that data can be quickly transmitted between modules and ensure the accurate execution of instructions. As an option, the communication optimization module can combine multi-path communication strategies to increase the redundancy of data transmission and reduce the impact of damaged communication links. In one possible implementation, the module can also use dynamic spectrum management technology to adaptively adjust the communication frequency band to improve channel utilization and reduce the impact of external interference.

[0078] In this embodiment, the communication optimization module adopts an adaptive communication strategy, adjusts the data transmission path, optimizes the data packaging method, and schedules and manages the communication between devices according to the communication requirements and network conditions at the construction site to reduce latency and data loss.

[0079] Specifically, the core work of this module includes: Communication link optimization: Based on the real-time network conditions, select the optimal data transmission path to ensure that data can be transmitted to the target device in the shortest time.

[0080] Data compression and coding optimization: Reduce the amount of data transmitted through data compression algorithms, and at the same time use anti-interference coding to improve the reliability of data.

[0081] Network congestion control: When multiple devices communicate in parallel, optimize the data transmission rate to prevent congestion in the communication network.

[0082] Dynamic spectrum management: In a wireless communication environment, detect the channel status in real time and select the frequency band with the least interference for communication to improve the stability of data transmission.

[0083] In some embodiments, the communication optimization module can analyze historical communication data based on deep learning algorithms and predict future network conditions to adjust communication strategies. For example, when the system detects that the error rate of a certain data channel continues to increase, it can automatically switch to a backup channel to avoid a decline in communication quality.

[0084] In this embodiment, the implementation of the communication optimization module includes the following key technologies: Adaptive Data Transmission Optimization: This module can adaptively select data transmission strategies according to the network status and data type. For example: When the network status is good, adopt a high-throughput transmission strategy to improve the data transmission rate.

[0085] When the network signal is weak, enable the low-power mode to reduce the data transmission rate and reduce data loss.

[0086] When the communication distance between devices is far, adopt the relay communication method to increase data relay nodes and ensure accurate data transmission.

[0087] This optimization process can be described by the following formula: Where, T trans represents the data transmission time (s); S data represents the size of the data packet (MB); B eff represents the effective bandwidth of the current communication channel (Mbps); D path represents the total distance of the data transmission path (m); V net represents the data transmission speed in the network (m / s).

[0088] This formula shows that the data transmission time is limited by the data size, channel bandwidth, and network transmission speed. Therefore, optimizing the communication link and improving bandwidth utilization are the keys to reducing the data transmission time.

[0089] Anti-interference Coding Technology: In a wireless communication environment, the communication channel is vulnerable to external interferences, such as electromagnetic interference and device signal interference. In this embodiment, the communication optimization module adopts anti-interference coding technology to improve the stability of data transmission.

[0090] The error correction coding method adopted can be expressed as: S recv = S send ·(1 - P err ); Where, S recv represents the amount of data successfully received at the receiving end (MB); S send represents the amount of data sent by the sending end (MB); P err represents the channel bit error rate, and the value range is 0 ≤ P err ≤ 1.

[0091] By adopting low-density parity-check code (LDPC) or convolutional code (ConvolutionalCode), the communication optimization module can effectively reduce the bit error rate and improve the accuracy of data reception.

[0092] Multi - path Communication Optimization: In some embodiments, the communication optimization module adopts multi - path communication technology, splits data into multiple data streams, and transmits them through different communication links to improve the redundancy of data transmission and reduce transmission latency.

[0093] This optimization process can be expressed as: Where: D total represents the total data transmission volume (MB); D i represents the data volume (MB) transmitted on the i - th communication link; N represents the number of available communication links.

[0094] This method can effectively improve the reliability of data transmission. Even if a certain communication link fails, the system can still continue to transmit data through other links to ensure data integrity.

[0095] The close cooperation between the communication optimization module and other modules is the key to the stable operation of the system. First, this module combines with the data acquisition module to ensure that the collected environmental data and device status data can be transmitted to the edge computing module for analysis in a timely manner. Second, it cooperates with the edge computing module to ensure that the calculation results can be quickly transmitted to the device cooperative control module, enabling the device control instructions to be executed in real - time. In addition, the cooperation between the communication optimization module and the task scheduling module can ensure the accuracy of task allocation and improve the overall work efficiency of the construction site.

[0096] In some embodiments, the communication optimization module can also be combined with an intelligent fault diagnosis system to monitor the health status of the communication network. When the system detects an abnormal communication link, it can automatically adjust the data transmission path and send a warning signal to the management system so that maintenance personnel can conduct fault troubleshooting in a timely manner to ensure the stability of the communication link.

[0097] The communication optimization module ensures stable and efficient data transmission within the intelligent engineering supervision system through technologies such as dynamic data transmission optimization, anti - interference coding, and multi - path communication. This module performs adaptive optimization in combination with the real - time network status to reduce data transmission latency, improve the accuracy of data transmission, and ensure the real - time nature of task scheduling and device cooperative control. The effective operation of the communication optimization module enables the entire system to maintain efficient operation in a complex construction environment and provides strong support for the intelligent management of the construction site.

[0098] The task scheduling module is used to execute the task optimization data provided by the edge computing module, optimize task allocation based on the network status provided by the communication optimization module, improve the overall execution efficiency of the system, and at the same time send task instructions to the device cooperative control module and request necessary information updates from the data acquisition module; The task scheduling module rationally allocates construction tasks based on factors such as real-time data at the construction site, equipment status, and task priorities, ensuring the high efficiency and coordination of the overall system operation. This module receives on-site information from the data acquisition module and combines the optimized calculation results of the edge computing module to dynamically adjust the task allocation plan to adapt to changes in the construction environment.

[0099] Generally, the task scheduling module needs to consider various factors, such as the time requirements of construction tasks, the operating status of equipment, the availability of operating personnel, and the real-time changes in the construction environment. As an option, this module can adopt a distributed scheduling strategy to collaboratively allocate computing resources among multiple task scheduling subunits to improve task scheduling efficiency. In a possible implementation, this module uses reinforcement learning or genetic algorithms to optimize the task scheduling plan, maximizing the utilization rate of construction resources and ensuring that tasks are completed within the shortest time.

[0100] In this embodiment, the task scheduling module realizes the reasonable allocation and dynamic adjustment of construction tasks based on an optimization scheduling algorithm with multiple constraints. Specifically, the main functions of this module include: Task allocation optimization: Calculate the optimal task allocation plan based on factors such as task priorities, equipment availability, and resource consumption to ensure the rationality and efficiency of task execution.

[0101] Equipment and personnel scheduling: Combine the data of the equipment collaborative control module to ensure that the task allocation of equipment matches the operation status and reasonably schedule operating personnel to improve the overall construction efficiency.

[0102] Task real-time adjustment: During the construction process, if the status of equipment or personnel changes, this module can adjust the task arrangement according to real-time data to ensure that the construction progress is not affected.

[0103] Task completion monitoring: Real-time track the execution status of tasks and provide key indicators such as task completion rate, execution time, and equipment utilization rate to optimize subsequent task scheduling strategies.

[0104] In some embodiments, the task scheduling module adopts a hierarchical scheduling architecture, including a global scheduling unit and a local scheduling unit. The global scheduling unit is responsible for the overall task planning, and the local scheduling unit adjusts the task execution order according to on-site data and coordinates the operation rhythm between equipment to adapt to changes in the construction environment.

[0105] In this embodiment, the task scheduling module conducts intelligent allocation and dynamic adjustment of construction tasks through a multi-objective optimization algorithm to maximize construction efficiency and resource utilization rate.

[0106] Task Allocation Optimization Algorithm: The task scheduling module adopts an optimization model based on linear programming. With the optimal task allocation plan as the goal, the following mathematical model is constructed: Among them, U ij represents the benefit value brought by allocating task i to device j; α ij is the task allocation decision variable. If task i is allocated to device j, then α ij = 1, otherwise α ij = 0; N is the total number of tasks; M is the total number of devices.

[0107] The optimization goal aims to maximize the overall benefit of task allocation while meeting the capacity constraints of the devices and the requirements of task execution timing.

[0108] Task Execution Time Prediction: In the process of task scheduling, the prediction of task execution time is crucial. In this embodiment, the task execution time can be calculated by the following formula: Among them, T exec represents the total task execution time (s); S i represents the computing resources or workload required for task i (unit: MB or man-hours); P j represents the processing capacity of device j (MB / s or man-hours / unit).

[0109] This formula shows that the task execution time is affected by the task scale and the device processing capacity, and needs to be dynamically adjusted during the scheduling process to ensure that the task is completed in the shortest time.

[0110] Task Dynamic Adjustment Strategy: In some embodiments, the task scheduling module combines a reinforcement learning algorithm and uses historical task data to train the task scheduling model so that it can adaptively adjust the task allocation plan. For example, when the system detects that a certain device cannot execute a task due to a failure, the task scheduling module can immediately reallocate the task to other available devices and optimize the task execution order to reduce construction delays.

[0111] The task adjustment strategy can be described by the following formula: Among them, R adjust is the task adjustment cost, which represents the time deviation cost brought about by the change of the task scheduling plan. The smaller its value, the better the scheduling adjustment plan; N is the total number of tasks, indicating the number of tasks that need to be scheduled in the system; W i is the priority weight of task i, representing the importance of the task. The larger the value, the higher the priority of the task; T expected$T_{i}^{0}$ is the originally planned completion time of task $i$ (unit: seconds or minutes), that is, the time when the task is expected to be completed in the initial task scheduling plan; $T$ actual $T_{i}$ is the actual completion time of task $i$ (unit: seconds or minutes), that is, the time when the task is actually completed at the construction site; $|T$ expected $-T$ actual $|$ represents the completion time deviation value of task $i$, reflecting the error between the actual completion time and the originally planned time of the task.

[0112] This formula indicates that when the deviation of the task execution time is large, the task scheduling module needs to adjust the task allocation plan in a timely manner to reduce the deviation of the construction plan.

[0113] The task scheduling module plays a core scheduling role in the system architecture, and its collaboration with other modules is as follows: Collaboration with the data acquisition module: The task scheduling module relies on the real-time data of the construction site provided by the data acquisition module, including equipment status, environmental parameters, task progress, etc., to ensure the accuracy of the scheduling plan.

[0114] Collaboration with the edge computing module: The edge computing module processes the data and generates task optimization data, and the task scheduling module adjusts the task allocation plan accordingly to improve the construction efficiency.

[0115] Collaboration with the equipment collaborative control module: After the task scheduling module assigns tasks, it needs the equipment collaborative control module to execute the task scheduling plan and adjust the equipment operation status in real time to ensure the smooth execution of the tasks.

[0116] Collaboration with the communication optimization module: The task scheduling module relies on the stable data transmission provided by the communication optimization module to ensure that the task instructions can be accurately issued and the task completion status can be feedback in real time.

[0117] In some embodiments, the task scheduling module can also combine with the cloud computing architecture, upload historical task data to the cloud for storage, and use big data analysis technology to optimize future task scheduling plans, improving the intelligent level of task scheduling.

[0118] The task scheduling module realizes efficient construction task management through technologies such as intelligent task allocation, task execution time prediction, and task dynamic adjustment. This embodiment adopts a task allocation algorithm based on linear programming and combines reinforcement learning to optimize the task scheduling plan to ensure that the construction tasks can be completed in the shortest time. The task scheduling module plays a core role in the entire intelligent project supervision system, and closely collaborates with the data acquisition module, edge computing module, equipment collaborative control module, and communication optimization module to ensure the efficient scheduling and execution of tasks at the construction site.

[0119] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent engineering supervision system based on multi-level linkage and multi-device linkage, characterized in that: include: The data acquisition module is used to obtain multimodal information of the construction site, convert the multimodal information of the construction site into structured data, provide it to the edge computing module for preprocessing, and support the task scheduling module to call the structured data; The edge computing module is used to perform local preprocessing on the structured data provided by the data acquisition module, generate construction equipment control instructions and task optimization data, and provide them to the equipment collaborative control module and the task scheduling module respectively; The equipment collaborative control module is used to execute the construction equipment control instructions provided by the edge computing module to ensure the linkage control of the construction equipment and to feedback the execution status to the task scheduling module; The communication optimization module is used to establish a low-latency, high-reliability communication network to ensure stable and efficient data interaction between the equipment collaborative control module and the task scheduling module; The task scheduling module is used to execute the task optimization data provided by the edge computing module, and optimize the task allocation based on the network status provided by the communication optimization module to improve the overall execution efficiency of the system. At the same time, it sends task instructions to the device collaborative control module and requests necessary information updates from the data acquisition module.

2. According to claim 1, an intelligent engineering supervision system based on multi-level linkage and multi-device linkage is characterized in that: The multimodal information includes: Video surveillance data, used to monitor the safety of the construction site, equipment operating status, and personnel activities in real time; Environmental sensor data, including at least temperature, humidity, air pressure, wind speed, and light environment information, is used to assess the safety of the construction environment; Equipment operation data, including at least the location, status, operating speed, load, temperature, and vibration of the construction equipment, to ensure the normal operation and maintenance requirements of the equipment; Personnel positioning and behavior data: Use smart wearable devices to obtain the location, health status, and behavior patterns of construction workers to ensure operational safety; Geographic Information System data, used to obtain the precise geographic location of the construction site, equipment distribution, and construction area geographic data; The sensor monitoring data includes at least mechanical pressure, sensor pressure, flow, and noise, and various sensors are used to monitor the physical indicators during the construction process in real time.

3. According to claim 1, an intelligent engineering supervision system based on multi-level linkage and multi-device linkage is characterized in that: The edge computing module adopts an adaptive computing architecture and supports dynamic adjustment of computing resource allocation based on task complexity, so as to improve processing efficiency and reduce energy consumption.

4. The intelligent engineering supervision system based on multi-level linkage and multi-device linkage according to claim 1 is characterized in that: The construction equipment control instructions include: Equipment start and stop instructions control the start and stop of construction equipment to ensure that the equipment works or stops working as needed; Operation parameter adjustment instructions: adjust the equipment's operation parameters according to on-site tasks and equipment status; Equipment linkage control instructions: when multiple construction equipment work together, linkage instructions are generated to ensure coordinated operation among the equipment; Fault warning and maintenance instructions: Generate fault warning instructions based on equipment sensor data, and send maintenance and repair instructions to ensure the safety and long-term stability of the equipment; Automatic adjustment instructions: Automatically adjust the equipment's working mode, power or operation path according to environmental changes at the construction site.

5. The intelligent engineering supervision system based on multi-level linkage and multi-device linkage according to claim 1 is characterized in that: The task optimization data includes: Task prioritization data to optimize the order in which tasks are executed based on construction schedule, task urgency, and resource availability; Task allocation data based on equipment operating status, construction staffing and available resources; Operation adjustment data, combined with environmental monitoring and safety data, to optimize the way tasks are performed; Dynamic scheduling data, adjusting task execution plans based on real-time construction progress and emergencies; Optimize strategy data and combine it with historical data analysis to generate scheduling optimization strategies.

6. The intelligent engineering supervision system based on multi-level linkage and multi-device linkage according to claim 1 is characterized in that: The equipment collaborative control module includes an intelligent scheduling unit that optimizes the scheduling strategy of construction equipment based on a reinforcement learning algorithm.

7. The intelligent engineering supervision system based on multi-level linkage and multi-device linkage according to claim 1 is characterized in that: The communication optimization module is based on a dynamic network protocol and uses a distributed optimization algorithm for intelligent regulation of data traffic.

8. The intelligent engineering supervision system based on multi-level linkage and multi-device linkage according to claim 1 is characterized in that: The steps of establishing a low-latency, high-reliability communication network include: Select appropriate communication protocols to ensure low latency and high stability during data transmission; Configure communication equipment and optimize network topology to reduce delays in signal transmission paths; Deploy redundant communication links to ensure network reliability and high availability in the event of a failure; Use network load balancing technology to dynamically adjust network traffic and avoid communication bottlenecks and congestion; Monitor communication quality and adjust network parameters in real time to ensure reliable data exchange even in harsh environments.

9. The intelligent engineering supervision system based on multi-level linkage and multi-device linkage according to claim 1 is characterized in that: The task scheduling module adopts a heterogeneous computing task scheduling strategy, combining edge computing resources and cloud computing resources, for task allocation and execution order.

10. The intelligent engineering supervision system based on multi-level linkage and multi-device linkage according to claim 1 is characterized in that: The task scheduling module includes the following submodules: The task allocation module reasonably allocates tasks to various construction equipment and personnel according to the construction progress, task priority and resource status; Task monitoring module: monitors task execution in real time, obtains the working status of each device and personnel, and ensures that tasks are executed as planned; Task optimization module, dynamically adjusts task allocation based on field data and equipment status, and optimizes task execution path and sequence; Resource scheduling module dynamically adjusts resource allocation according to the real-time status of equipment and personnel; The task feedback module collects feedback information during the task execution process, analyzes the task execution effect, provides improvement suggestions and makes adjustments.

Images