Intelligent construction site equipment remote monitoring management method and system based on Internet of Things

Abstract

The invention provides an intelligent construction site equipment remote monitoring management method and system based on the Internet of Things, and relates to the technical field of monitoring management, and the method comprises the steps: collecting the operation parameters of target construction site equipment through an Internet of Things sensor; constructing a life monitoring model in combination with the operation parameters; performing remote monitoring on the target construction site equipment based on the life monitoring model to obtain an equipment operation condition; and performing equipment maintenance management according to the equipment operation condition. According to the invention, the technical problem that the construction progress and the engineering efficiency are further influenced due to the lack of personalization and precision of maintenance decisions caused by insufficient management of the life cycle of construction site equipment in the prior art can be solved, the technical targets of intelligent monitoring and optimal management of the whole life cycle of the equipment are achieved, and the purposes of improving the operation efficiency of the equipment and reducing the construction cost are achieved. And the technical effect of finishing the project on time is ensured.

Description

Technical Field

[0001] This application relates to the field of monitoring and management technology, and in particular to a method and system for remote monitoring and management of smart construction site equipment based on the Internet of Things. Background Technology

[0002] With the continuous advancement of technologies such as the Internet of Things (IoT), cloud computing, and big data, remote equipment monitoring and intelligent management are gradually becoming mainstream. IoT technology allows sensors to be installed on equipment to collect real-time data on operating status, temperature, vibration, fuel consumption, and other parameters, transmitting this data to a cloud platform for analysis and processing. However, existing intelligent equipment monitoring technologies still have some shortcomings.

[0003] Currently, existing systems often lack consideration for equipment lifecycle management and fail to fully integrate information such as the equipment's service life, fault history, and maintenance records. This results in maintenance decisions that are not personalized and precise, and maintenance costs and downtime are difficult to control effectively.

[0004] In summary, existing technologies suffer from insufficient lifecycle management of construction site equipment, leading to a lack of personalized and precise maintenance decisions, which further impacts construction progress and project efficiency. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for remote monitoring and management of smart construction site equipment based on the Internet of Things, in order to solve the technical problems in the existing technology where insufficient life cycle management of construction site equipment leads to a lack of personalized and precise maintenance decisions, which further affects construction progress and project efficiency.

[0006] In view of the above problems, this application provides a method and system for remote monitoring and management of smart construction site equipment based on the Internet of Things.

[0007] Firstly, this application provides a method for remote monitoring and management of smart construction site equipment based on the Internet of Things (IoT), implemented through an IoT-based smart construction site equipment remote monitoring and management system, comprising: collecting operating parameters of target construction site equipment through IoT sensors; constructing a life monitoring model based on the operating parameters; remotely monitoring the target construction site equipment based on the life monitoring model to obtain the equipment operating status; and performing equipment maintenance and management based on the equipment operating status.

[0008] Secondly, this application also provides an IoT-based smart construction site equipment remote monitoring and management system for executing the IoT-based smart construction site equipment remote monitoring and management method as described in the first aspect, comprising: a parameter acquisition module for acquiring operating parameters of the target construction site equipment through IoT sensors; a model building module for constructing a life monitoring model based on the operating parameters; an equipment monitoring module for remotely monitoring the target construction site equipment based on the life monitoring model to obtain the equipment operating status; and a maintenance management module for performing equipment maintenance management based on the equipment operating status.

[0009] The technical solution provided in this application has at least the following technical effects or advantages: by achieving the technical goal of intelligent monitoring and optimized management of the entire equipment life cycle, it can improve the operating efficiency of the equipment and ensure the timely completion of the project.

[0010] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating the IoT-based smart construction site equipment remote monitoring and management method of this application. Figure 2 This is a schematic diagram of the structure of the IoT-based smart construction site equipment remote monitoring and management system of this application.

[0013] Explanation of reference numerals in the attached diagram: Parameter acquisition module 11, Model building module 12, Equipment monitoring module 13, Maintenance management module 14. Detailed Implementation

[0014] This application provides a method and system for remote monitoring and management of smart construction site equipment based on the Internet of Things (IoT). This addresses the technical problem in existing technologies where insufficient lifecycle management of construction site equipment leads to a lack of personalized and precise maintenance decisions, further impacting construction progress and project efficiency. The application achieves the technical goal of intelligent monitoring and optimized management of the entire equipment lifecycle, thereby improving equipment operating efficiency and ensuring timely project completion.

[0015] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0016] Example 1, please refer to the appendix. Figure 1 This application provides a method for remote monitoring and management of smart construction site equipment based on the Internet of Things (IoT), which is applied to a remote monitoring and management system for smart construction site equipment based on the IoT. Specifically, it includes the following steps: S1: Collect operating parameters of equipment at the target construction site through IoT sensors.

[0017] Specifically, target construction site equipment refers to the equipment that needs to be monitored. Internet of Things (IoT) sensors are sensors with network connectivity that can transmit collected data to remote servers or cloud platforms via wireless or wired networks for analysis and management. IoT sensors detect and record various operating parameters of the target construction site equipment; for example, power sensors can measure the power consumption of electric motors, while pressure sensors can measure the pressure of hydraulic systems. By analyzing the trends in these operating parameters, the health status of the equipment can be predicted, allowing for proactive maintenance and reducing the probability of malfunctions, thereby improving the efficiency of construction site equipment utilization.

[0018] S2: Divide the equipment life cycle into stages, match the operating parameters according to the equipment life cycle to obtain life cycle operating parameters, construct an intelligent learning framework in the equipment life cycle, train the intelligent learning framework through the life cycle operating parameters to obtain a life cycle monitoring model, wherein the equipment life cycle includes the procurement stage, installation stage, usage stage, maintenance stage and scrapping stage.

[0019] Specifically, the entire lifecycle of equipment is segmented for clearer management. Lifecycle stages represent the different phases an equipment goes through from procurement to final disposal, each with different management methods and focuses. The equipment lifecycle includes the procurement stage, installation stage, usage stage, maintenance stage, and disposal stage, each with different management objectives and methods. The procurement stage refers to the process from demand analysis to purchase completion. In this stage, factors such as equipment performance, price, and supplier reputation need to be considered. The installation stage refers to the process of installation and commissioning after the equipment arrives at the construction site. For example, when installing a tower crane, the foundation needs to be reinforced to ensure the tower is vertical, and load tests are conducted to verify its load-bearing capacity. The usage stage refers to the process of the equipment being put into construction work. For example, if an excavator excavates 500 cubic meters of earth per day and operates for eight hours, during the usage stage, the equipment's fuel consumption, work efficiency, and malfunctions need to be monitored. The maintenance stage refers to the upkeep and repairs performed to ensure the normal operation of the equipment, including regular lubricant changes, filter cleaning, and electrical wiring inspections. For example, a concrete mixer needs its mixing blades replaced every 1,000 hours of operation to prevent blade wear from affecting the mixing effect. The end-of-life stage refers to the process by which equipment reaches the end of its service life or is taken out of service due to irreparable damage. For example, after ten years of continuous use, a bulldozer's engine and hydraulic system show severe aging, resulting in excessively high maintenance costs, and therefore it is phased out. Table 1 records the management content of data collection for each stage of the equipment's life cycle.

[0020] Table 1: Management Content Records of Equipment Lifecycle Data Collection

[0021] Relevant operational data is matched according to the equipment's life cycle stage. For example, in the procurement stage, the focus is on the equipment's purchase cost, supplier information, and factory test data; while in the usage stage, the focus is on the equipment's working efficiency, energy consumption, and failure rate. In the maintenance stage, the focus is on the equipment's repair records, spare parts replacement status, and operational stability; and in the scrapping stage, the focus is on the equipment's residual value, dismantling methods, and recyclable parts. Life cycle operational parameters refer to the key operational indicators extracted for each stage of the equipment's life cycle.

[0022] Building an intelligent learning framework throughout the equipment's lifecycle is crucial for subsequent data analysis and prediction. An intelligent learning framework is a machine learning-based computing system that extracts patterns from historical equipment data and uses this information to predict future operational status. For example, by analyzing the operational data of a crane over the past five years, an intelligent learning framework can identify common failure modes and predict potential anomalies at a future point in time.

[0023] The intelligent learning framework is trained using lifecycle parameters. Lifecycle parameter training refers to optimizing the intelligent learning framework using key data from different stages of the equipment's lifecycle, enabling it to accurately predict the equipment's operating conditions. For example, in the procurement stage, training data includes the equipment's purchase price, brand quality rating, and factory inspection results; in the usage stage, training data includes the equipment's energy consumption, load changes, and temperature profiles; and in the maintenance stage, training data includes repair time, fault types, and replaced parts. Trained on this data, the intelligent learning framework can identify the equipment's health status and predict potential future faults. After training, the intelligent learning framework forms a lifecycle monitoring model. The lifecycle monitoring model is an intelligent analysis system capable of monitoring the equipment's operating status in real time and predicting future faults.

[0024] S3: Based on the life monitoring model, remote monitoring of the target construction site equipment is performed to obtain the equipment operating status.

[0025] Specifically, remote monitoring relies on life monitoring models to perform tasks, analyze equipment operating status, predict potential failures, and provide maintenance recommendations. For example, a tower crane's life monitoring model can predict the equipment's health status based on engine temperature, cable tension, and boom load changes. Remote monitoring refers to controlling equipment via wireless or wired networks using IoT technology. The operating status of the equipment is analyzed through cloud platforms or edge computing. For example, a remote monitoring system for an excavator can collect data such as engine speed, hydraulic system pressure, and fuel consumption in real time and send alarms when abnormalities occur.

[0026] S4: Perform equipment maintenance and management based on the equipment's operating status.

[0027] Specifically, equipment maintenance management refers to the comprehensive management of equipment upkeep, repair, and monitoring. Maintenance decisions are made based on the actual operating conditions of the equipment, such as regular inspections, parts replacement, lubrication replenishment, and emergency troubleshooting.

[0028] Furthermore, this application also includes: acquiring the operating status, energy consumption data, location data, environmental data, and fault information of the target construction site equipment based on the IoT sensor, wherein the IoT sensor includes smart sensors and smart terminal devices; performing data cleaning on the operating status, energy consumption data, location data, environmental data, and fault information, and combining them using time series data to obtain the operating parameters.

[0029] Specifically, the Internet of Things (IoT) refers to connecting various devices to a network using wireless communication technology to achieve data exchange and remote management. A sensor is a device capable of sensing changes in the environment or equipment status. IoT sensors indicate that these sensors have network connectivity and can upload data in real time. IoT sensors are divided into smart sensors and smart terminal devices. Smart sensors not only sense data but also have preliminary calculation or data filtering capabilities; for example, vibration sensors can detect abnormal vibration patterns and preprocess the data before uploading. Smart terminal devices refer to devices capable of processing, storing, and transmitting data, such as industrial controllers, remote data acquisition modules, or edge computing devices. They can aggregate data from multiple sensors and transmit it to the cloud or local servers. IoT sensors are used to collect and acquire the operating status, energy consumption data, location data, environmental data, and fault information of equipment at a target construction site. The target construction site equipment refers to the specific construction equipment that needs to be monitored, such as tower cranes, excavators, and concrete mixers. These devices operate on the construction site and require status monitoring. Operating status indicates the current working condition of the equipment. Energy consumption data refers to the energy consumed by the equipment during operation. Location data refers to the specific geographical location of the device, obtained through the Global Positioning System (GPS) or the BeiDou Navigation Satellite System. Environmental data refers to the environmental information surrounding the device. Fault information refers to problems that occur during the operation of the device.

[0030] Data cleaning is performed on operating status, energy consumption, location, environmental data, and fault information, and then time series data is combined to obtain operating parameters. Data cleaning refers to preprocessing before data analysis to ensure data accuracy and consistency, including removing duplicate data, correcting erroneous data, and completing missing data. Time series data represents a set of data arranged in chronological order; in equipment monitoring, each data point carries time information. Different types of data are integrated according to the time dimension. For example, at the same point in time, the operating status, energy consumption, location, environment, and fault information of the equipment are recorded to form a complete set of data entries. Operating parameters refer to key indicators formed after data cleaning and time series processing, such as the equipment's average load, energy consumption per unit time, and failure rate. These data can be used for further analysis and decision-making. Table 2 shows the operating parameter record of a certain device in its most recent collection.

[0031] Table 2: Record of operating parameters collected most recently by a certain device

[0032] Furthermore, this application also includes: using the life operation parameters as input and combining equipment maintenance decisions as output to perform monitoring learning, and setting a model learning environment; setting equipment safety constraints as model learning constraints, wherein the equipment safety constraints include hardware security, data security, network security, operational security and environmental security; and training the life monitoring model by combining the model learning constraints and the model learning environment.

[0033] Specifically, equipment maintenance decisions refer to maintenance strategies formulated based on equipment operating status, historical fault records, and lifespan predictions. The model relies on lifespan operating parameters as input and outputs equipment maintenance decisions, representing maintenance decisions based on equipment status and historical data. Training is conducted based on these input data and output decisions, enabling the model to continuously optimize equipment status analysis and maintenance recommendations. Setting the model's learning environment involves providing suitable computational conditions and data processing methods. The model learning environment refers to the conditions that influence the model's learning process, such as the training method.

[0034] Equipment safety constraints refer to the limitations set to ensure the safe operation of equipment, such as preventing overloading, avoiding data leakage, and preventing malicious attacks. Using equipment safety constraints as constraints for model learning ensures that the model adheres to safety standards during training. Equipment safety constraints include hardware safety, data security, network security, operational safety, and environmental safety, each involving different safety protection requirements. Hardware safety refers to ensuring that the physical structure and critical components of the equipment are not damaged. For example, in tower crane operation monitoring, the tension of the steel cables must be kept within limits to prevent breakage and lifting accidents. Data security refers to preventing the tampering or loss of equipment operating data. For example, in construction site equipment monitoring systems, all sensor data should be stored and transmitted encrypted to prevent malicious tampering and erroneous decisions. Network security refers to preventing hacker attacks or unauthorized access. For example, if an equipment monitoring system uses wireless communication, firewalls and authentication mechanisms are required to prevent unauthorized intrusion. Operational safety refers to ensuring that the equipment does not encounter danger during operation. For example, if the tilt angle of an excavator exceeds the safe range, it should automatically stop to prevent rollover accidents. Environmental safety refers to ensuring that equipment operation does not harm the surrounding environment. For example, equipment operating in high-temperature environments needs to ensure that the cooling system is working properly to prevent overheating from causing equipment damage or fire. Table 3 shows the implementation plan for equipment safety constraints.

[0035] Table 3: Record of Implementation Plans for Equipment Safety Constraints

[0036] Under the premise of meeting safety requirements and computational conditions, the model is trained so that it can accurately identify the operating status of the equipment and generate reasonable maintenance suggestions, thus obtaining a life monitoring model.

[0037] Furthermore, this application also includes: constructing a maintenance space based on the equipment maintenance decisions, and correcting the maintenance space boundary by combining the model learning constraints, wherein the equipment maintenance decisions include passive maintenance, periodic maintenance, and predictive maintenance; establishing an operation space based on the life operation parameters; connecting the life operation parameters with the equipment maintenance decisions to generate a maintenance guidance relationship; actively adjusting the maintenance vector in the maintenance space according to the maintenance guidance relationship, and actively adjusting the boundary based on the maintenance space boundary constraints to obtain a passively adjusted operation vector in the operation space; and actively adjusting and training the life monitoring model based on the bias of the operation vector as a guide.

[0038] Specifically, equipment maintenance decisions refer to different maintenance strategies adopted for potential equipment failures or aging, mainly including reactive maintenance, periodic maintenance, and predictive maintenance. Reactive maintenance refers to repairing equipment only after a failure occurs, such as replacing the seals on an excavator only after a leak in the hydraulic system. This approach can easily lead to production stoppages and high repair costs. Periodic maintenance refers to maintenance performed at fixed time intervals or according to equipment usage duration, such as changing the lubricating oil of a generator every 500 hours of operation to reduce wear. Maintenance is performed even when there are no obvious faults, thus reducing the risk of sudden failures. Predictive maintenance refers to predicting potential failures based on real-time monitoring data and historical failure trends, combined with big data and artificial intelligence technologies, and taking preventative measures in advance. For example, if the main shaft vibration amplitude of a tower crane has increased by 20% in the past three months, and the steel structure stress exceeds the safety threshold, it can be predicted that bearing failure may occur within the next two months, and replacement can be recommended in advance. A maintenance space is established based on maintenance decisions. The maintenance space refers to a mathematical model or computational framework used to optimize equipment maintenance strategies, containing information such as equipment operating data, maintenance methods, and repair costs. Model learning constraints refer to the limitations on safety, stability, and computational power that need to be met during model training. By learning constraints through the model, the maintenance space boundary is corrected to better meet actual needs, making the maintenance strategy more accurate and reasonable. Table 4 shows a comparison of the three maintenance methods.

[0039] Table 4: Comparison Record of Three Maintenance Methods

[0040] An operating space is established using key operational data from each stage of the equipment's lifecycle, such as energy consumption, failure rate, temperature, and vibration amplitude. The operating space refers to a data state constructed based on equipment status data, used to describe the equipment's behavior under different operating conditions. For example, if a generator's energy consumption, temperature, and vibration signals are all within normal ranges, its operating state is considered healthy.

[0041] This involves linking operational parameters with equipment maintenance decisions to form a logical relationship that serves as a maintenance guidance relationship. This relationship refers to determining appropriate maintenance strategies based on the equipment's operational status. For example, if the cable tension of a tower crane is consistently close to its safety limit and minor wire breaks have occurred, it can be recommended to shift from periodic maintenance to predictive maintenance—that is, replacing the cable in advance, rather than waiting until it is severely worn.

[0042] The maintenance space represents the optimization range of a maintenance strategy. Within this range, different maintenance methods can be adjusted to achieve the optimal maintenance effect. Based on the maintenance guidance relationship, the maintenance vector is actively adjusted within the maintenance space. The maintenance vector represents the mathematical variables describing the maintenance strategy; for example, a maintenance vector might include information such as maintenance frequency, maintenance method, and maintenance cost. Active adjustment means that, according to the maintenance guidance relationship, the running vector is passively adjusted within the running space because the maintenance vector is adjusted within the maintenance space.

[0043] Actively adjusting the boundary based on maintenance space boundary constraints. Maintenance space boundary constraints refer to safety and economic constraints used to limit the range of maintenance strategy adjustments. Actively adjusting the boundary means that adjustments to the maintenance vector must be made within a reasonable range. Passively adjusted operating vectors refer to the equipment operating parameters obtained after optimization based on equipment status and maintenance strategies.

[0044] Optimization is performed with the goal of achieving biased operational vectors. Biased operational vectors refer to selecting the most beneficial operating state for the equipment among multiple optimization objectives, such as finding the optimal balance between energy consumption, maintenance costs, and equipment lifespan, to guide training. By continuously adjusting and optimizing model parameters, the model can adaptively adjust maintenance strategies, resulting in a life monitoring model used to predict equipment failures, optimize maintenance strategies, and ensure safe equipment operation.

[0045] Furthermore, this application also includes: classifying the target site equipment by fault impact to obtain classified equipment, wherein the classified equipment includes low-impact equipment, medium-impact equipment, and high-impact equipment; performing an optimization vector search in the operating space based on the classified equipment to obtain a matching operating vector; responding to the maintenance vector according to the matching operating vector to obtain an optimized maintenance vector; and training the optimized operating vector obtained by active adjustment of the optimized maintenance vector and the optimized maintenance vector to obtain a life monitoring model.

[0046] Specifically, the impact of a malfunction refers to the degree to which equipment failure affects on-site operations. On-site equipment is categorized and managed according to the degree of impact. Target on-site equipment refers to construction equipment that requires management and monitoring. Classified equipment refers to equipment categorized into different levels based on the degree of impact. For example, if a tower crane malfunctions, it may affect the construction of the entire building structure, classifying it as high-impact equipment, while a malfunction of an on-site air quality monitor may only affect environmental data collection, classifying it as low-impact equipment. The term "high-impact equipment" refers to the equipment classifications mentioned above: low-impact, medium-impact, and high-impact equipment. Low-impact equipment refers to equipment that, even if it malfunctions, will not have a significant impact on the overall construction progress and safety of the site, such as small power tools or portable lighting devices. Medium-impact equipment refers to equipment whose malfunction may have a significant impact on local construction tasks or specific stages, but will not cause the entire construction site to stop, such as concrete mixers or small generators. High-impact equipment refers to equipment that, once it malfunctions, will have a significant impact on the overall construction progress or personnel safety of the site, such as tower cranes, cranes, or large excavators.

[0047] The classifying equipment searches for optimization vectors within its operating space. The operating space refers to a mathematical model comprised of the equipment's operating state data, used to analyze the equipment's health status. An optimization vector is a set of mathematical variables describing the optimal operating state. The search involves finding the best-matching operating parameters and ultimately, a matching operating vector. A matching operating vector is the parameter found within the operating space that best reflects the equipment's optimal operating state.

[0048] The maintenance strategy is optimized based on the matching operational vector. A response represents an adjustment or feedback to a certain input, i.e., optimizing the maintenance vector based on the matching operational vector. The maintenance vector refers to the parameters that affect the equipment maintenance method. The optimized maintenance vector refers to the maintenance strategy adjusted under the guidance of the matching operational vector. Active adjustment is performed using the optimized maintenance vector, and the optimized data is used to train the life monitoring model, resulting in the life monitoring model.

[0049] Furthermore, this application also includes: performing a maintenance decision transition from static maintenance to dynamic maintenance on the maintenance space to obtain a transition decision space; matching the class division device based on the transition decision space to obtain a coarse matching operation vector; extracting the scene criticality of the class division device, and adjusting the coarse matching operation vector in the transition decision space to obtain a matching operation vector.

[0050] Specifically, this involves adjusting and optimizing the maintenance space. The maintenance space includes transitional decisions from static to dynamic maintenance. Static maintenance refers to fixed, unchanging maintenance strategies, such as performing maintenance at fixed intervals regardless of whether the equipment actually needs it, like changing lubricating oil every three months even if the equipment is in good operating condition. Dynamic maintenance refers to dynamically adjusting maintenance plans based on the equipment's real-time operating status and historical data. For example, if an increase in equipment vibration is detected, maintenance can be scheduled in advance, while if the equipment is in good condition, the maintenance cycle can be appropriately extended. The transitional decision space refers to the space where multiple transitional decisions are made, merging and adjusting between static and dynamic maintenance.

[0051] Based on the transition decision space matching to classify devices by category, a coarse-matching operating vector is obtained, representing the operating parameters found to be suitable for the device category through matching. The coarse-matching operating vector refers to the set of operating parameters initially selected based on the device category. For example, for high-impact devices, a more stringent range of operating parameters may be selected.

[0052] Select key operational scenario factors from equipment categories. Scenario criticality refers to the critical operational factors of equipment under different usage scenarios. For example, for a tower crane, the key factors for operation in strong winds are wind speed and structural stability, while under normal weather conditions, the key factors might be load weight and lifting angle. Optimize the operational vector based on scenario criticality to better suit the actual operational needs of the equipment. For instance, if a concrete mixer operates in a high-humidity environment, its key parameters might be mixing time and motor power, while in a dry environment, the key parameter might be the cement-to-water ratio. Therefore, parameters need to be dynamically adjusted to adapt to different scenarios.

[0053] Furthermore, this application also includes: determining whether the optimized maintenance vector is completely within the maintenance space; pruning maintenance vectors outside the maintenance space according to the boundary of the maintenance space to generate a fragmented maintenance vector; pixelating the maintenance space to obtain the corresponding pixel space of the maintenance space; measuring the optimized maintenance vector in the corresponding pixel space to obtain the optimized maintenance pixel size; selecting adjacent pixels of the fragmented maintenance vector in the corresponding pixel space based on the optimized maintenance pixel size to obtain pixels to be smeared; smearing pixels on the pixels to be smeared to obtain a complete maintenance vector; and training a life monitoring model using an optimized adjustment running vector obtained by actively adjusting the complete maintenance vector and the complete maintenance vector.

[0054] Specifically, the process checks whether the optimized maintenance vectors conform to the maintenance space, determining if all optimized maintenance vectors fall within the maintenance space's range. If an optimized maintenance vector exceeds the maintenance space's range—for example, if an excavator's engine maintenance cycle is originally adjusted to 1200 working hours, but the maintenance space's upper limit is 1000 working hours, thus exceeding the allowable range—then maintenance vectors outside the maintenance space are pruned according to the maintenance space boundaries. Pruning means adjusting maintenance vectors exceeding the maintenance space into the allowable range, forming new maintenance vectors. Incomplete maintenance vectors refer to maintenance vectors whose parameters have been modified after pruning.

[0055] Pixelation refers to converting continuous data into discrete pixel form; that is, discretizing the maintenance space so that it can be computed in pixel space, generating a corresponding pixel space. There is a one-to-one correspondence between the corresponding pixel space and the maintenance space.

[0056] The measurement task is performed in the corresponding pixel space. The measuring scale represents the measurement dimension. The size of the optimized maintenance vector in the pixel space is calculated. The optimized maintenance pixel size refers to the area occupied by the optimized maintenance vector within the pixel space.

[0057] In the pixelated data space, neighboring pixels of the incomplete maintenance vector are processed. Neighboring pixels represent pixel units that are in contact with each other in the pixel space, and are the pixel regions associated with the incomplete maintenance vector. Pixel selection means selecting neighboring pixels around the incomplete maintenance vector to obtain the pixel region to be adjusted. Pixels to be painted refer to the pixel region that needs adjustment.

[0058] Pixel smearing performs a pixel filling operation on the pixels to be smeared. Pixel smearing means filling in the selected area in pixel space, adjusting the pixel values ​​of the incomplete maintenance vector by optimizing the maintenance pixel size to better meet the requirements of the maintenance space.

[0059] The operational vector is optimized and adjusted using the complete maintenance vector. Active adjustment refers to optimizing the equipment's operating state based on the complete maintenance vector to obtain the adjusted optimized operational vector. The optimized operational vector refers to the operational parameters obtained through active optimization based on the complete maintenance vector. The optimized operational vector is then used to train the life monitoring model, ultimately establishing the life monitoring model.

[0060] Furthermore, this application also includes: obtaining the real-time equipment life stage of the target construction site equipment; determining whether the real-time equipment life stage is in a transitional operation stage; if so, executing maintenance start / stop based on the next real-time operation stage to obtain a maintenance decision to be executed; and performing equipment maintenance management based on the maintenance decision to be executed.

[0061] Specifically, sensors and monitoring systems are used to collect data on the current lifecycle stage of equipment at the target construction site. For example, the lifecycle data of a tower crane may include its status during installation and commissioning, normal operation, minor maintenance, major maintenance, and eventual scrapping.

[0062] Assess the current lifecycle stage of the equipment and determine if it has entered a transitional operation phase. For example, a tower crane may have just completed a major overhaul and is in the recovery phase, or the equipment at the target construction site may be too old to be maintained and put back into use, thus entering the scrapping phase. If in the transitional operation phase, subsequent maintenance measures will be implemented, i.e., appropriate equipment management based on the assessment results, such as suspending equipment operation or scheduling maintenance. The next operation phase represents the next state of the equipment's lifecycle. Start-up and shutdown indicate a switch in the equipment's operating state. Based on the equipment's state, a decision is made on whether to suspend use or restart, generating a specific maintenance decision plan. Equipment management is then carried out based on the generated maintenance decisions, such as replacing aging parts in advance and optimizing equipment load.

[0063] In summary, the IoT-based smart construction site equipment remote monitoring and management method provided in this application has the following technical effects: by achieving the technical goal of intelligent monitoring and optimized management of the entire equipment lifecycle, it can improve equipment operating efficiency and ensure the timely completion of projects.

[0064] Example 2: Based on the same inventive concept as the IoT-based smart construction site equipment remote monitoring and management method described in the previous examples, this application also provides an IoT-based smart construction site equipment remote monitoring and management system. Please refer to the appendix. Figure 2 The system includes: a parameter acquisition module 11, used to acquire operating parameters of the target construction site equipment through IoT sensors; a model building module 12, used to divide the equipment life stages, match the operating parameters according to the equipment life stages to obtain life operation parameters, build an intelligent learning framework in the equipment life stages, train the intelligent learning framework through the life operation parameters to obtain a life monitoring model, wherein the equipment life stages include the procurement stage, installation stage, usage stage, maintenance stage and scrapping stage; an equipment monitoring module 13, used to remotely monitor the target construction site equipment based on the life monitoring model to obtain the equipment operating status; and a maintenance management module 14, used to perform equipment maintenance management according to the equipment operating status.

[0065] Furthermore, the IoT-based smart construction site equipment remote monitoring and management system is also used for: collecting and acquiring the operating status, energy consumption data, location data, environmental data, and fault information of the target construction site equipment based on the IoT sensors, wherein the IoT sensors include smart sensors and smart terminal devices; performing data cleaning on the operating status, energy consumption data, location data, environmental data, and fault information, and combining them using time series data to obtain the operating parameters.

[0066] Furthermore, the IoT-based smart construction site equipment remote monitoring and management system is also used for: taking the life operation parameters as input and combining equipment maintenance decisions as output to perform monitoring learning and setting a model learning environment; setting equipment safety constraints as model learning constraints, wherein the equipment safety constraints include hardware security, data security, network security, operational security and environmental security; and training the life monitoring model by combining the model learning constraints and the model learning environment.

[0067] Furthermore, the IoT-based smart construction site equipment remote monitoring and management system is also used for: constructing a maintenance space based on the equipment maintenance decisions, and correcting the maintenance space boundary by combining the model learning constraints, wherein the equipment maintenance decisions include passive maintenance, periodic maintenance, and predictive maintenance; establishing an operation space based on the life operation parameters; connecting the life operation parameters with the equipment maintenance decisions to generate a maintenance guidance relationship; actively adjusting the maintenance vector in the maintenance space according to the maintenance guidance relationship, and actively adjusting the boundary based on the maintenance space boundary constraints to obtain the passively adjusted operation vector in the operation space; and actively adjusting and training the life monitoring model based on the bias of the operation vector as a guide.

[0068] Furthermore, the IoT-based smart construction site equipment remote monitoring and management system is also used for: classifying the target construction site equipment by fault impact to obtain class-based equipment, wherein the class-based equipment includes low-impact equipment, medium-impact equipment, and high-impact equipment; performing an optimization vector search in the operating space based on the class-based equipment to obtain a matching operating vector; responding to the maintenance vector according to the matching operating vector to obtain an optimized maintenance vector; and training the optimized operating vector obtained by actively adjusting the optimized maintenance vector and the optimized maintenance vector to obtain a life monitoring model.

[0069] Furthermore, the IoT-based smart construction site equipment remote monitoring and management system is also used for: transitioning maintenance decisions from static maintenance to dynamic maintenance in the maintenance space to obtain a transition decision space; matching the class-divided equipment based on the transition decision space to obtain a coarse matching operation vector; extracting the scene criticality of the class-divided equipment, and adjusting the coarse matching operation vector in the transition decision space to obtain a matching operation vector.

[0070] Furthermore, the IoT-based smart construction site equipment remote monitoring and management system is also used for: determining whether the optimized maintenance vector is completely within the maintenance space; trimming maintenance vectors outside the maintenance space according to the boundary of the maintenance space to generate incomplete maintenance vectors; pixelating the maintenance space to obtain the corresponding pixel space of the maintenance space; measuring the optimized maintenance vector in the corresponding pixel space to obtain the optimized maintenance pixel size; selecting adjacent pixels of the incomplete maintenance vector in the corresponding pixel space based on the pixel size of the optimized maintenance vector to obtain pixels to be smeared; smearing pixels on the pixels to be smeared to obtain a complete maintenance vector; and training a life monitoring model using the optimized adjustment operation vector obtained by actively adjusting the complete maintenance vector and the complete maintenance vector.

[0071] Furthermore, the IoT-based smart construction site equipment remote monitoring and management system is also used to: obtain the real-time equipment life stage of the target construction site equipment; determine whether the real-time equipment life stage is in a transitional operation stage; if so, execute maintenance start / stop based on the next real-time operation stage to obtain a maintenance decision to be executed; and perform equipment maintenance management based on the maintenance decision to be executed.

[0072] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The IoT-based smart construction site equipment remote monitoring and management method and specific examples in the aforementioned Embodiment 1 are also applicable to the IoT-based smart construction site equipment remote monitoring and management system of this embodiment. Through the foregoing detailed description of the IoT-based smart construction site equipment remote monitoring and management method, those skilled in the art can clearly understand the IoT-based smart construction site equipment remote monitoring and management system of this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0073] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0074] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for remote monitoring and management of smart construction site equipment based on the Internet of Things, characterized in that, include: Collect operating parameters of equipment at the target construction site using IoT sensors; The equipment life cycle is divided into stages, and operating parameters are matched according to the equipment life cycle to obtain life cycle operating parameters. An intelligent learning framework is constructed in the equipment life cycle, and the intelligent learning framework is trained through the life cycle operating parameters to obtain a life cycle monitoring model. The equipment life cycle includes the procurement stage, installation stage, usage stage, maintenance stage, and scrapping stage. Based on the life monitoring model, remote monitoring of the equipment at the target construction site is performed to obtain the equipment operating status; Equipment maintenance and management shall be carried out based on the equipment's operating status.

2. The method for remote monitoring and management of smart construction site equipment based on the Internet of Things as described in claim 1, characterized in that, The operating parameters of equipment at the target construction site are collected through IoT sensors, including: The IoT sensors are used to collect and acquire the operating status, energy consumption data, location data, environmental data and fault information of the equipment at the target construction site. The IoT sensors include smart sensors and smart terminal devices. The operating status, energy consumption data, location data, environmental data, and fault information are cleaned and combined using time series analysis to obtain the operating parameters.

3. The method for remote monitoring and management of smart construction site equipment based on the Internet of Things as described in claim 1, characterized in that, The life monitoring model is obtained by: Using the aforementioned life operation parameters as input and combining them with equipment maintenance decisions as output, monitoring and learning are performed, and a model learning environment is set up. Device security constraints are set as model learning constraints, wherein the device security constraints include hardware security, data security, network security, operational security, and environmental security; The life monitoring model is obtained by training the model by combining the model learning constraints and the model learning environment.

4. The method for remote monitoring and management of smart construction site equipment based on the Internet of Things as described in claim 3, characterized in that, The life monitoring model is obtained by training the model using the model learning constraints and the model learning environment, including: A maintenance space is constructed based on the equipment maintenance decisions, and the boundary of the maintenance space is corrected by combining the model learning constraints. The equipment maintenance decisions include passive maintenance, periodic maintenance, and predictive maintenance. The operating space is established based on the aforementioned life operation parameters; The life cycle parameters are linked with the equipment maintenance decisions to generate maintenance guidance relationships; Based on the maintenance guidance relationship, the maintenance vector is actively adjusted in the maintenance space, and the boundary is actively adjusted based on the boundary constraints of the maintenance space to obtain the passively adjusted operating vector in the operating space. Guided by the bias in the running vector, the life monitoring model is obtained by actively adjusting the training.

5. The method for remote monitoring and management of smart construction site equipment based on the Internet of Things as described in claim 4, characterized in that, The life monitoring model is obtained through active training and adjustment, including: The target site equipment is classified by fault impact to obtain classified equipment, wherein the classified equipment includes low-impact equipment, medium-impact equipment and high-impact equipment; Based on the class division device, an optimized vector search is performed in the operating space to obtain a matching operating vector; Based on the matching running vector, the maintenance vector is responded to to obtain the optimized maintenance vector; The life monitoring model is obtained by actively adjusting the optimized operation vector through the optimized maintenance vector and training the optimized operation vector.

6. The method for remote monitoring and management of smart construction site equipment based on the Internet of Things as described in claim 5, characterized in that, Based on the class division device, an optimized vector search is performed in the operating space to obtain a matching operating vector, including: The maintenance space is transitioned from static maintenance to dynamic maintenance, resulting in a transitional decision space; Based on the transition decision space, the class division device is matched to obtain a coarse matching running vector; Extract the scene key of the class division device, adjust the coarse matching running vector in the transition decision space, and obtain the matching running vector.

7. The method for remote monitoring and management of smart construction site equipment based on the Internet of Things as described in claim 5, characterized in that, The life monitoring model is obtained by actively adjusting the optimized operation vector through the optimized maintenance vector and training the optimized maintenance vector, including: Determine whether the optimized maintenance vector is completely within the maintenance space, and prune the maintenance vector outside the maintenance space according to the boundary of the maintenance space to generate a fragmented maintenance vector; The maintenance space is pixelated to obtain the corresponding pixel space of the maintenance space; The optimized maintenance vector is measured in the corresponding pixel space to obtain the optimized maintenance pixel size; In the corresponding pixel space, the adjacent pixels of the incomplete maintenance vector are selected based on the optimized maintenance pixel size to obtain the pixel to be painted; Pixel smearing is performed on the pixels to be smeared to obtain a complete maintenance vector; The life monitoring model is obtained by actively adjusting the optimized adjustment operation vector obtained by the complete maintenance vector and training the complete maintenance vector.

8. The method for remote monitoring and management of smart construction site equipment based on the Internet of Things as described in claim 1, characterized in that, Equipment maintenance and management are performed based on the equipment's operating status, including: Obtain the real-time equipment lifecycle stage of the target construction site equipment; Determine whether the real-time device is in a transitional operation phase. If it is, execute maintenance start / stop based on the next real-time operation phase to obtain the maintenance decision to be executed. Equipment maintenance management is performed based on the maintenance decisions to be executed.

9. A smart construction site equipment remote monitoring and management system based on the Internet of Things, characterized in that, The steps for implementing the IoT-based smart construction site equipment remote monitoring and management method according to any one of claims 1 to 8 include: The parameter acquisition module is used to collect the operating parameters of the equipment at the target construction site through IoT sensors; The model building module is used to divide the equipment life stage, match the operating parameters according to the equipment life stage to obtain life operation parameters, build an intelligent learning framework in the equipment life stage, train the intelligent learning framework through the life operation parameters to obtain a life monitoring model. The equipment life stage includes the procurement stage, installation stage, use stage, maintenance stage and scrapping stage. The equipment monitoring module is used to remotely monitor the equipment at the target construction site based on the life monitoring model, and obtain the equipment operating status. The maintenance management module is used to perform equipment maintenance management based on the operating status of the equipment.

Images