Smart construction site online monitoring method and system based on Internet of Things and AI algorithm

Abstract

The present invention discloses an online monitoring method and system for a smart construction site based on the Internet of Things and an AI algorithm, and relates to the field of online monitoring technology. The online monitoring method for a smart construction site based on the Internet of Things and an AI algorithm includes judging whether the power supply equipment is abnormal, judging whether the communication equipment is abnormal, and if the communication equipment is abnormal, an alarm prompt is issued; when the power supply equipment and the communication equipment are normal, judging whether the construction site personnel are wearing helmets normally, judging whether street events occur, and judging whether the muck truck is operating in violation of regulations, by automatically detecting the wearing of helmets by construction site personnel, the gathering and flow status of personnel, the operation specifications of muck trucks, etc., safety hazards can be effectively prevented, and emergencies can be responded to quickly to ensure the safety of the construction site, and data such as communication equipment, power supply equipment, personnel density, personnel movement, and license plate recognition can be collected and analyzed in real time, and whether abnormal situations or violations occur can be automatically judged to improve management efficiency.

Description

Technical Field

[0001] Smart construction sites are engineering construction sites that use the Internet of Things (IoT) as the core and make comprehensive use of modern information technology means such as "cloud, big data, Internet of Things, mobile, and intelligence" to perceive, collect, process, and analyze information and data during the construction process, ultimately achieving data sharing, interconnection, safe operation, intelligent production, efficient collaboration, intelligent decision-making, and scientific management. It is an implementation model for construction projects that supports comprehensive perception of people and objects, comprehensive intelligent construction technology, interconnected work, collaborative information sharing, scientific decision-making analysis, and intelligent risk pre-control based on a high degree of informatization.

[0002] However, existing technologies make it difficult to conduct real-time monitoring and analysis of construction site power supply equipment, communication equipment, personnel helmet wearing, personnel flow and dump truck operation, which makes it difficult to promptly detect and handle equipment failures, personnel violations and vehicle illegal operation problems. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a smart construction site online monitoring method and system based on the Internet of Things and AI algorithms, which solves the problem that the prior art is difficult to monitor and analyze the construction site power supply equipment, communication equipment, personnel helmet wearing, personnel flow and dump truck operation in real time, resulting in inconvenience in timely detection and handling of equipment failures, personnel violations and vehicle illegal operations.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: an online monitoring method for a smart construction site based on the Internet of Things and an AI algorithm, comprising the following steps: monitoring the power supply equipment and communication equipment in the smart construction site to determine whether the power supply equipment is abnormal, and if the power supply equipment is abnormal, an alarm is issued, and determining whether the communication equipment is abnormal, and if the communication equipment is abnormal, an alarm is issued; when the power supply equipment and the communication equipment are normal, obtaining the video data at the entrance of the smart construction site, uploading the video data to the AI ​​data processing center, determining whether the construction site personnel are wearing safety helmets normally, and if they are not wearing safety helmets normally, an alarm is issued; monitoring the flow of construction site personnel who are wearing safety helmets normally in the smart construction site, uploading the personnel flow data to the AI ​​data processing center, determining whether street events occur, and if street events occur, an alarm is issued; real-time monitoring of dump trucks, uploading the operation data of the dump trucks to the AI ​​data processing center, determining whether the dump trucks are operating in violation of regulations, and if they are operating in violation of regulations, an alarm is issued.

[0005] Furthermore, the determination of whether the power supply equipment is abnormal includes the following steps: obtaining the power supply equipment operation data, the power supply equipment operation data including current stability, electric energy consumption within a set time, and power supply equipment temperature; obtaining the power supply equipment operation parameter data stored in a database, the power supply equipment operation parameter data including current parameter stability, electric energy parameter consumption within a set time, and power supply equipment parameter temperature; combining the power supply equipment operation data with the power supply equipment operation parameter data to obtain a power supply equipment abnormality judgment index; comparing the power supply equipment abnormality judgment index with a power supply equipment abnormality judgment threshold stored in the database: if the power supply equipment abnormality judgment index is greater than the power supply equipment abnormality judgment threshold stored in the database, the power supply equipment is abnormal; if the power supply equipment abnormality judgment index is not greater than the power supply equipment abnormality judgment threshold stored in the database, the power supply equipment is normal.

[0006] Furthermore, the calculation formula of the power supply equipment abnormality judgment index is:

[0007] ;

[0008] In the formula, It is the power supply equipment abnormality judgment index. is the current stability, It is the power consumption within the set time. is the power supply equipment temperature, is the current parameter stability, The power consumption is determined for the set time. Set the temperature for the power supply equipment. is a natural constant.

[0009] Furthermore, the determination of whether the communication device is abnormal includes the following steps: obtaining operation data of the communication device, wherein the operation data of the communication device includes a data transmission rate and a data compression rate; obtaining operation parameter data of the communication device stored in a database, wherein the operation parameter data of the communication device includes a data transmission parameter rate and a data compression parameter rate; matching the operation allowable deviation data of the communication device based on the operation environment data of the communication device in the smart construction site, wherein the operation allowable deviation data of the communication device includes an allowable deviation value of the data transmission rate and an allowable deviation value of the data compression rate, and the operation environment data of the communication device includes the operation environment temperature and the number of terminals within the communication coverage range; integrating the operation data of the communication device, the operation parameter data of the communication device and the operation allowable deviation data of the communication device to obtain an abnormal judgment index of the communication device; comparing the abnormal judgment index of the communication device with the abnormal judgment threshold of the communication device stored in the database: if the abnormal judgment index of the communication device is greater than the abnormal judgment threshold of the communication device stored in the database, the communication device is abnormal; if the abnormal judgment index of the communication device is not greater than the abnormal judgment threshold of the communication device stored in the database, the communication device is normal.

[0010] Furthermore, the matching of communication equipment operation allowable deviation data based on communication equipment operation environment data in the smart construction site includes the following steps: using a similarity function to compare the communication equipment operation environment data with the communication equipment operation environment matching data stored in the database one by one; determining the communication equipment operation environment matching data that is most similar to the communication equipment operation environment data; and obtaining the communication equipment operation allowable deviation data stored in the database corresponding to the most similar communication equipment operation environment matching data.

[0011] Furthermore, the calculation formula of the communication device abnormality judgment index is:

[0012] ;

[0013] In the formula, is the communication equipment abnormality judgment index, is the data transmission rate, is the data compression rate, To set the data transmission rate, is the data compression parameter rate, is the permissible deviation value of the data transmission rate, The permissible deviation value for the data compression rate.

[0014] Furthermore, the method of judging whether the construction site personnel are wearing safety helmets normally comprises the following steps: extracting facial features from the video data, judging whether the current personnel is a registered personnel on the construction site based on the facial features, and issuing an alarm if not; if the personnel is a registered personnel on the construction site, obtaining whether the registered personnel on the construction site are wearing a hat; if the personnel are not wearing a hat, issuing an alarm; if the personnel are wearing a hat, judging whether the shape of the hat is qualified; if the shape of the hat is unqualified, issuing an alarm; if the shape of the hat is qualified, determining a designated color of the hat based on the registered personnel on the construction site; judging the designated color of the hat and comparing it with the actual color of the hat worn by the registered personnel on the construction site, and issuing an alarm if the colors do not match; if the colors match, the construction site personnel are wearing safety helmets normally.

[0015] Furthermore, the determination of whether a street incident occurs comprises the following steps: obtaining a density of people in a gathering area, and determining whether the density of people is greater than a threshold value of people density set in a database: if the density of people is greater than the threshold value of people density set in a database, determining that a street incident occurs; if the density of people is not greater than the threshold value of people density set in a database, determining the moving speed of people; if the number of people whose moving speed is greater than the moving speed threshold value set in a database is greater than the number threshold value set in a database, determining that a street incident occurs; if the moving speed of people is not greater than the moving speed threshold value set in a database, determining whether anyone falls to the ground; if anyone falls to the ground, determining that a street incident occurs; if no one falls to the ground, determining that no street incident occurs.

[0016] Furthermore, the determination of whether a dump truck is operating in violation of regulations comprises the following steps: determining whether the license plate of the dump truck is blocked; if so, determining that the dump truck is operating in violation of regulations; if the license plate of the dump truck is not blocked, determining whether the sludge coverage area of ​​the dump truck body is greater than the sludge coverage area threshold set in the database; if the sludge coverage area of ​​the dump truck body is greater than the sludge coverage area threshold set in the database, determining that the dump truck is operating in violation of regulations; if the sludge coverage area of ​​the dump truck body is not greater than the sludge coverage area threshold set in the database, determining whether the roof of the dump truck is covered; if the roof of the dump truck is not covered, determining that the dump truck is operating in violation of regulations; if the roof of the dump truck is covered, determining that the dump truck is operating normally.

[0017] The online monitoring system for smart construction sites based on the Internet of Things and AI algorithms includes a hardware equipment abnormality monitoring module, a safety helmet abnormal wearing monitoring module, a street event monitoring module and a muck truck monitoring module, wherein: the hardware equipment abnormality monitoring module is used to monitor the power supply equipment and communication equipment in the smart construction site, determine whether the power supply equipment is abnormal, and if so, issue an alarm prompt, determine whether the communication equipment is abnormal, and if so, issue an alarm prompt; the safety helmet abnormal wearing monitoring module is used to obtain video data at the entrance of the smart construction site when the power supply equipment and the communication equipment are normal. The video data is uploaded to the AI ​​data processing center to determine whether the construction site personnel are wearing safety helmets normally. If they are not wearing safety helmets normally, an alarm prompt is issued; the street event monitoring module is used to monitor the flow of construction site personnel who are wearing safety helmets normally in the smart construction site, and upload the personnel flow data to the AI ​​data processing center to determine whether street events occur. If street events occur, an alarm prompt is issued; the dump truck monitoring module is used to monitor the dump truck in real time, upload the dump truck operation data to the AI ​​data processing center, and determine whether the dump truck is operating in violation of regulations. If it is operating in violation of regulations, an alarm prompt is issued.

[0018] The present invention has the following beneficial effects:

[0019] This smart construction site online monitoring method and system based on the Internet of Things and AI algorithms can effectively prevent safety hazards and quickly respond to emergencies to ensure safety within the construction site by automatically detecting the wearing of safety helmets by construction site personnel, the gathering and flow status of personnel, and the operation specifications of dump trucks. It can also collect and analyze data such as communication equipment, power supply equipment, personnel density, personnel movement, and license plate recognition in real time, and automatically determine whether abnormal situations or violations occur, thereby reducing the workload of manual inspections and interventions and improving management efficiency.

[0020] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of the online monitoring method for smart construction sites based on the Internet of Things and AI algorithms of the present invention.

[0022] Figure 2 This is a flowchart of the smart construction site online monitoring system based on the Internet of Things and AI algorithm of the present invention.

[0023] Figure 3 This is a logical framework diagram of the smart construction site online monitoring method based on the Internet of Things and AI algorithm of the present invention. DETAILED DESCRIPTION

[0024] The embodiment of the present application realizes real-time monitoring and analysis of the construction site power supply equipment, communication equipment, personnel helmet wearing, personnel flow and dump truck operation through a smart construction site online monitoring method and system based on the Internet of Things and AI algorithms. It can promptly discover and handle problems such as equipment failures, personnel violations and vehicle illegal operations, effectively improve the level of construction site safety management, reduce potential accidents, and ensure the safety and standardized operation of construction site operations.

[0025] See also Figure 1 The embodiment of the present invention provides a technical solution: an online monitoring method for a smart construction site based on the Internet of Things and an AI algorithm, comprising the following steps: monitoring power supply equipment and communication equipment in the smart construction site, determining whether the power supply equipment is abnormal, and if so, issuing an alarm; determining whether the communication equipment is abnormal, and if so, issuing an alarm; when both the power supply equipment and the communication equipment are normal, obtaining video data at the entrance of the smart construction site, uploading the video data to an AI data processing center, determining whether construction site personnel are wearing safety helmets normally, and if not, issuing an alarm; monitoring the flow of construction site personnel who are wearing safety helmets normally in the smart construction site, uploading personnel flow data to an AI data processing center, determining whether street events occur, and if so, issuing an alarm; real-time monitoring of dump trucks, uploading dump truck operation data to an AI data processing center, determining whether the dump trucks are operating in violation of regulations, and if so, issuing an alarm.

[0026] First, the power supply equipment and communication equipment are monitored to ensure the normal operation of the core system, because these devices are the basis of the monitoring system. If any equipment is abnormal, the system will issue an alarm to prevent subsequent operations from being affected. When the equipment is normal, through video data analysis, it is identified whether the construction site personnel are wearing safety helmets correctly. If not, an alarm will be issued to ensure the safety of personnel. For construction site personnel who wear safety helmets correctly, the system continues to monitor their flow, determine whether abnormal events occur, and prevent possible safety accidents in time. The operating status of the muck truck is also monitored. If illegal operation is found, the system will issue an alarm to ensure that the vehicle is operated in accordance with regulations to avoid chaos in traffic and work order.

[0027] Through real-time monitoring of equipment and personnel, potential dangerous situations can be discovered in time, the probability of accidents on the construction site can be reduced, and the safety of construction site personnel can be ensured. Strict monitoring of personnel wearing safety helmets and vehicle operation can be carried out to standardize construction site operation processes and improve the standardization and compliance of construction site management. AI algorithms can quickly determine abnormal situations, automatically issue alarms, and help managers take timely actions to reduce the impact and losses of accidents.

[0028] like Figure 3As shown in the figure, the helmet inspection instrument in the smart construction site is connected to the local cloud gateway NVR storage through the 4G network. In addition, the camera is connected to the local cloud gateway NVR storage through the smart construction site private network. The local platform can view the content in the cloud gateway NVR storage. The detection equipment of the power supply equipment and communication equipment is also connected to the smart construction site platform through the operator's 4G network, and the real-time detection data can be transmitted to the smart construction site platform. The local cloud gateway NVR storage sends the content in the local cloud gateway NVR storage to the AI ​​host through the operator network (dedicated line / 4G), and the AI ​​host analyzes and judges the uploaded content. If there is no violation, it is sent to the provincial company's centralized storage platform for storage; if there is a violation, it is sent to the provincial company's smart construction site platform, and after the work order is formed, the relevant personnel are notified to handle it. At the same time, the smart construction site platform provides on-site voice and image prompts; in addition, the provincial company's smart construction site platform sends the violation event signal to the smart construction site platform in the smart construction site through the operator network (dedicated line / 4G), and the smart construction site provides on-site voice and image prompts.

[0029] Specifically, the determination of whether the power supply equipment is abnormal includes the following steps: obtaining the power supply equipment operation data, the power supply equipment operation data including current stability, electric energy consumption within a set time, and power supply equipment temperature; obtaining the power supply equipment operation parameter data stored in a database, the power supply equipment operation parameter data including current parameter stability, electric energy parameter consumption within a set time, and power supply equipment parameter temperature; combining the power supply equipment operation data with the power supply equipment operation parameter data to obtain a power supply equipment abnormality judgment index; comparing the power supply equipment abnormality judgment index with the power supply equipment abnormality judgment threshold stored in the database: if the power supply equipment abnormality judgment index is greater than the power supply equipment abnormality judgment threshold stored in the database, the power supply equipment is abnormal; if the power supply equipment abnormality judgment index is not greater than the power supply equipment abnormality judgment threshold stored in the database, the power supply equipment is normal.

[0030] First, the actual operation data of the power supply equipment is obtained, including current stability (using current sensors or current transformers (CT) to monitor the current fluctuation of the power supply equipment in real time. Current stability is usually calculated by calculating the volatility of current data in a short period of time. The stability of current can be measured by methods such as standard deviation or coefficient of variation. For example, within a set time, multiple sampling values ​​of the current signal are taken, and its variance or deviation is calculated to determine the stability of the current), power consumption (obtained through an electric energy meter or smart meter installed on the power supply equipment. Within a set time period, the electric energy meter records the power consumption of the equipment (in kilowatt-hours kWh), and these data can be transmitted to the monitoring system at regular intervals through the Internet of Things device) and equipment temperature (through temperature sensors (such as thermocouples, thermistors, infrared temperature sensors, etc.) installed on key components of the power supply equipment for real-time monitoring. The temperature sensor directly senses the surface or internal temperature of the equipment and transmits the data to the monitoring system). As a reflection of the current status, the stored power supply equipment parameter data (i.e., the reference value of the equipment under normal conditions) is extracted from the database, including current stability, power consumption and temperature. By comparing the actual operation data with the parameter data, the abnormal judgment index of the power supply equipment is calculated to quantify the deviation of the equipment's operating status. The abnormal judgment index is compared with the abnormal judgment threshold in the database. If the index exceeds the threshold, it indicates that the equipment is abnormal, otherwise the equipment is normal.

[0031] By comparing the reference data with the actual data, the operating status of the equipment can be judged more accurately, avoiding false alarms or missed alarms, and improving the accuracy of judgment. Before the problem affects the operation of the equipment, the index can be used to judge potential abnormalities, and the problem can be handled in a timely manner to avoid downtime and losses caused by equipment failure. Relying on historical data and threshold standards, equipment status analysis can be automated to reduce manual intervention and improve monitoring efficiency and response speed. By real-time monitoring of key parameters such as current and temperature of the equipment, abnormalities can be discovered and maintenance can be performed in a timely manner, thereby extending the service life of the equipment.

[0032] The calculation formula of the power supply equipment abnormality judgment index is:

[0033] ;

[0034] In the formula, It is the power supply equipment abnormality judgment index. is the current stability, It is the power consumption within the set time. is the power supply equipment temperature, is the current parameter stability, The power consumption is determined for the set time. Set the temperature for the power supply equipment. is a natural constant.

[0035] In this implementation, the absolute difference between the actual current stability (Sdw) and the specified current stability (Cdw), as well as the actual power consumption (Sdn) and the specified power consumption (Cdn) is calculated to reflect the deviation of the current and power consumption during the operation of the equipment. A larger difference will significantly increase the index value. By calculating the difference between the actual equipment temperature (Sw) and the specified temperature (Cw), the temperature deviation is processed through logarithmic functions and square root functions to smooth the impact of temperature changes and respond to temperature anomalies. The combination of the natural constant e and the logarithm ln in the formula can balance the impact of different variables and ensure the sensitivity and accuracy of the abnormal judgment index to key deviations.

[0036] By combining exponential and logarithmic functions, it is possible to respond sensitively to subtle changes in current, power consumption, and temperature, and effectively identify potential anomalies in the operation of power supply equipment. Current is the core indicator of the operation of power supply equipment and reflects the load condition of the equipment. If the current fluctuates greatly, it may mean that the equipment load is abnormal, short-circuited, or has other problems. Therefore, monitoring the current stability can directly detect whether the equipment has abnormal operation. Power consumption is an important indicator of the efficiency of power supply equipment. An abnormal increase or decrease in the amount of power consumed by the equipment may indicate that the operating status of the equipment has changed, or there are problems such as loss or failure. By comparing the actual value of power consumption with the parameter value, it can be determined whether the equipment is operating normally within the set power range. The temperature of the equipment is a direct reflection of the health status of the equipment. Too high a temperature may indicate that the equipment is overloaded, has poor heat dissipation, or has internal component failures; too low a temperature may mean that the equipment is not operating normally. Therefore, temperature is one of the important parameters for the safe operation of power supply equipment.

[0037] Current and power consumption are closely related, and the stability of current affects the power consumption of the device. If the current fluctuates greatly, the power consumption of the device may increase or decrease abnormally, indicating that the device load may be unstable. Therefore, the fluctuation of current will directly affect the change of power consumption, and abnormal power consumption may in turn affect the stability of current. Excessive or unstable current may cause the internal components of the device to heat up, which in turn causes the temperature to rise. If the current is abnormal and not handled in time, it may cause the device to overheat, which in turn accelerates the loss of the device or causes a malfunction. Therefore, the change of current can directly or indirectly affect the temperature of the device. The increase in power consumption of the device is usually accompanied by the conversion of part of the energy loss into heat energy, resulting in a temperature rise. If the device is in a high power consumption state for a long time, the temperature will also rise accordingly, so the abnormal power consumption will directly lead to a change in the temperature of the device. In addition, the increase in device temperature may also increase power consumption, further causing the instability of the device. Current, power consumption and temperature are inseparable. They affect each other and reflect the operating status of the device together. By monitoring the deviation of these three parameters, it is possible to comprehensively judge whether there is an abnormality in the power supply device: current fluctuation affects power consumption, changes in power consumption affect temperature, and temperature can provide feedback on whether the device is dissipating heat and operating normally. Selecting these three parameters as the basis for judging abnormalities in power supply equipment can ensure a comprehensive evaluation of equipment operation and rapid fault detection.

[0038] Specifically, the determination of whether the communication device is abnormal includes the following steps: obtaining the communication device operation data, the communication device operation data including the data transmission rate and the data compression rate; obtaining the communication device operation parameter data stored in the database, the communication device operation parameter data including the data transmission parameter rate and the data compression parameter rate; matching the communication device operation allowable deviation data based on the communication device operation environment data in the smart construction site, the communication device operation allowable deviation data including the data transmission rate allowable deviation value and the data compression rate allowable deviation value, and the communication device operation environment data including the operation environment temperature and the number of terminals within the communication coverage range; combining the communication device operation data, the communication device operation parameter data and the communication device operation allowable deviation data to obtain the communication device abnormality judgment index; comparing the communication device abnormality judgment index with the communication device abnormality judgment threshold stored in the database: if the communication device abnormality judgment index is greater than the communication device abnormality judgment threshold stored in the database, the communication device is abnormal; if the communication device abnormality judgment index is not greater than the communication device abnormality judgment threshold stored in the database, the communication device is normal.

[0039] First, the real-time operation data of the communication equipment is obtained through sensors and monitoring systems, including data transmission rate (communication equipment usually integrates a network monitoring module to measure and record the real-time data transmission rate of the equipment. This module calculates the average transmission rate by collecting the amount of data sent or received in a specific time period) and data compression rate (communication equipment (especially equipment involving large data transmission) usually has a data compression / decompression module. This module records the size of the data before and after compression each time the data is processed, and automatically calculates the compression ratio to obtain the compression rate) as a reflection of the current performance of the communication equipment. The parameter data of the communication equipment, including the historical data transmission rate and compression rate, are obtained from the database as reference values ​​under normal operating conditions. Combined with the communication environment data at the construction site, such as the ambient temperature and the number of terminals during operation, the allowable deviation range (such as the fluctuation range of the data transmission rate and the compression rate) is matched to ensure that the judgment criteria are reasonably adjusted under different environmental conditions.

[0040] Comprehensively analyze the operation data, parameter data and allowable deviation of the communication equipment, calculate the abnormal judgment index of the communication equipment, and quantify whether the equipment has abnormal fluctuations. Compare the abnormal judgment index with the abnormal judgment threshold stored in the database. If it exceeds the threshold, the equipment is judged to be abnormal, otherwise the equipment is normal.

[0041] By comparing actual data with parameter values ​​and making flexible adjustments based on the on-site environment, we can ensure that we can accurately judge whether the communication equipment is abnormal under different conditions to avoid false alarms and missed alarms. The influence of the operating environment (such as temperature and number of terminals) is balanced by the allowable deviation to ensure that the equipment status can still be effectively evaluated in a complex construction site environment and improve the robustness of judgment. It can calculate the abnormal index of communication equipment in real time, quickly detect equipment failures, and issue early warnings to prevent system paralysis caused by data transmission interruptions.

[0042] The method of matching the communication equipment operation allowable deviation data based on the communication equipment operation environment data in the smart construction site includes the following steps: using a similarity function (such as Euclidean distance, cosine similarity, etc.) to compare the communication equipment operation environment data with the communication equipment operation environment matching data stored in the database one by one; determining the communication equipment operation environment matching data that is most similar to the communication equipment operation environment data; and obtaining the communication equipment operation allowable deviation data stored in the database corresponding to the most similar communication equipment operation environment matching data.

[0043] The real-time communication equipment operating environment data (such as ambient temperature, number of terminals, etc.) is compared with the historical communication equipment environment data stored in the database one by one to quantify the similarity between the two. Based on the calculation results of the similarity function, the historical data most similar to the current communication equipment operating environment is determined to represent the state of the equipment under similar operating conditions. The communication equipment operation allowable deviation data corresponding to the most similar operating environment is extracted from the database to determine the reasonable fluctuation range of the equipment performance under the current environment.

[0044] By matching the most similar historical data, the system can adapt to changes in the construction site environment (such as temperature, number of terminals, etc.) and give accurate equipment performance judgment standards under different environmental conditions. Under different environmental conditions, the performance of the equipment may fluctuate. By matching the most similar environmental data, the allowable deviation range of equipment operation can be reasonably set to avoid unnecessary alarms. The complexity and diversity of the environment may lead to the variability of equipment behavior. Based on the data comparison of historical similar environments, the system is more adaptable and robust and can adapt to a variety of operating conditions.

[0045] The calculation formula of the communication equipment abnormality judgment index is:

[0046] ;

[0047] In the formula, is the communication equipment abnormality judgment index, is the data transmission rate, is the data compression rate, To set the data transmission rate, is the data compression parameter rate, is the permissible deviation value of the data transmission rate, The permissible deviation value for the data compression rate.

[0048] In this implementation scheme, the deviation between the current data transmission rate (SdL) and data compression rate (SYn) and the parameterized rates (CdL and CYn) is calculated to quantify the degree of deviation between the current operating state of the communication equipment and the normal state. The rate differences are divided by the corresponding allowable deviation values ​​(ΔdL and ΔYn) to standardize the influence between different variables, ensure that the fluctuations of each rate are handled within a reasonable range, and the deviations of different parameters can be fairly included in the calculation. By standardizing the differences in each rate, it is ensured that the influence of the data transmission rate and the compression rate can be balanced in the calculation, and the judgment will not be distorted due to a certain parameter being too large or too small.

[0049] By introducing the allowable deviation values ​​(ΔdL and ΔYn), the formula can be dynamically adjusted according to the actual environmental conditions, adapting to different operating environments and enhancing the accuracy of equipment abnormality judgment.

[0050] Data transmission rate is one of the core indicators of communication equipment, which directly reflects the bandwidth utilization of the communication link and the efficiency of the data flow. If the transmission rate is lower than expected, it may mean congestion of the communication link, equipment failure or network transmission problems. Therefore, monitoring the data transmission rate can ensure that the communication equipment is in a normal state and detect potential problems in time. Data compression rate is another important indicator, especially when processing large amounts of data. Compression technology can effectively reduce the size of transmitted data, thereby improving transmission efficiency and saving bandwidth. If the compression rate is abnormal (too low or too high), it may indicate that there is a problem with the compression algorithm or that the processing capacity of the device is limited. Therefore, the data compression rate can reflect the device's ability to process data and indirectly affect transmission performance.

[0051] The data transmission rate and compression rate are closely related. The increase in data compression rate will directly reduce the size of the data to be transmitted, thereby increasing the data transmission rate. Conversely, if the compression rate is reduced, the amount of data increases, and the transmission rate will also decrease accordingly. Therefore, these two parameters jointly affect the transmission efficiency of the communication device.

[0052] In communication equipment, when the transmission rate is limited, the increase in compression rate can compensate for the lack of bandwidth to a certain extent, and improve the actual transmission effect by reducing the amount of data through compression. On the contrary, if the transmission rate is stable and fast, the abnormality of compression rate may not directly affect the transmission, but it is still a key part of the performance of the communication equipment. Therefore, by monitoring both at the same time, the performance of the communication equipment can be fully evaluated.

[0053] The data compression rate and transmission rate affect each other. If the compression rate is too low, the amount of data transmitted will increase, which may lead to a decrease in the transmission rate, thus affecting the overall communication efficiency. Excessive compression may also cause data quality loss or decompression delay, thus affecting the stability of the transmission link. Therefore, a reasonable balance between data compression and transmission rate is needed to ensure the best performance of communication equipment.

[0054] Specifically, the method of judging whether the construction site personnel are wearing safety helmets normally includes the following steps: extracting facial features from video data, judging whether the current person is a registered person on the construction site based on the facial features, and issuing an alarm if not; if the person is a registered person on the construction site, obtaining whether the registered person on the construction site is wearing a hat; if the person is not wearing a hat, issuing an alarm; if the person is wearing a hat, judging whether the shape of the hat is qualified; if the shape of the hat is unqualified, issuing an alarm; if the shape of the hat is qualified, determining a designated color of the hat based on the registered person on the construction site; judging the designated color of the hat and comparing it with the actual color of the hat worn by the registered person on the construction site, and issuing an alarm if the colors do not match; if the colors match, the construction site personnel are wearing safety helmets normally.

[0055] In this implementation scheme, computer vision technology is used to extract features of faces in the video at the entrance of the construction site using deep learning models (such as convolutional neural networks, CNN). The extracted features are compared with the facial features of registered personnel in the database to verify the identity of the personnel. Facial recognition libraries such as OpenCV and Dlib can be used. Based on image analysis of the head area, it is detected whether there is a hat on the head of the construction site personnel. Deep learning models (such as YOLO or SSD) can be trained to recognize the presence of a hat, and a pre-trained helmet detection model can be used.

[0056] Use image processing algorithms or 3D shape recognition technology to analyze the detected cap contour to ensure that it meets the standard shape. If the cap is obviously deformed or damaged, the system will mark it as unqualified. You can use contour detection or other shape analysis models based on OpenCV. Use image processing technology to extract the cap color information. After extracting the color features, compare it with the reference color of the registered personnel on the construction site in the database to ensure color matching. Color matching is usually processed based on color space conversion (such as RGB to HSV), and the color analysis function in OpenCV can be used.

[0057] This process ensures that all construction site personnel wear helmets correctly, reduces potential safety hazards, and prevents unauthorized personnel from entering dangerous areas. Through real-time analysis of video data, incorrect wearing behavior can be quickly identified and an alarm can be issued to ensure efficient construction site safety management. By checking the shape and color of the helmet, it is ensured that the helmets of construction site personnel meet standardization requirements, which helps avoid safety problems caused by non-compliant equipment.

[0058] Specifically, the determination of whether a street incident occurs includes the following steps: obtaining a population density in a gathering area, and determining whether the population density is greater than a population density threshold value set in a database: if the population density is greater than the population density threshold value set in the database, determining that a street incident occurs; if the population density is not greater than the population density threshold value set in the database, determining the movement speed of the population; if the number of people whose movement speed is greater than the movement speed threshold value set in the database is greater than the number threshold value set in the database, determining that a street incident occurs; if the movement speed of the people is not greater than the movement speed threshold value set in the database, determining whether a person falls to the ground; if a person falls to the ground, determining that a street incident occurs; if no person falls to the ground, determining that no street incident occurs.

[0059] In this implementation scheme, the video is captured by the camera, and image processing technology (such as YOLO, OpenCV, etc.) is used to identify and count people in the scene. The density of people can be calculated based on the area of ​​the area, and image recognition tools such as YOLOv5, TensorFlow, and OpenCV can be used. Use the optical flow method, background difference method, or deep learning algorithm to track the moving target in the video and calculate its moving speed. Analyze the movement trajectory of the person and detect large-scale abnormal acceleration. The optical flow algorithm and deep learning tracking model in OpenCV can be used. Analyze the human posture through a deep learning model (such as a posture estimation algorithm or a convolutional neural network) to determine whether there is a person falling to the ground. Falling events are usually accompanied by significant changes in the human body structure, such as changes in the contact angle between the torso and the ground. OpenPose, posture estimation models, etc. can be used.

[0060] This process effectively avoids false alarms under a single condition through multi-dimensional analysis of density, movement speed, and fall situations, ensuring more accurate and reliable judgment of street events. It can quickly detect abnormal crowd behavior, make timely judgments and trigger alarms to prevent further deterioration of events, and improve safety management of construction sites and public areas. Different density, speed, and fall thresholds can be set according to different construction sites or areas to ensure effective identification of potential events in various environments, with strong adaptability.

[0061] Specifically, the determination of whether a dump truck is operating in violation of regulations comprises the following steps: determining whether the license plate of the dump truck is blocked; if so, determining that the dump truck is operating in violation of regulations; if the license plate of the dump truck is not blocked, determining whether the sludge coverage area of ​​the dump truck body is greater than the sludge coverage area threshold set in the database; if the sludge coverage area of ​​the dump truck body is greater than the sludge coverage area threshold set in the database, determining that the dump truck is operating in violation of regulations; if the sludge coverage area of ​​the dump truck body is not greater than the sludge coverage area threshold set in the database, determining whether the roof of the dump truck is covered; if the roof of the dump truck is not covered, determining that the dump truck is operating in violation of regulations; if the roof of the dump truck is covered, determining that the dump truck is operating normally.

[0062] In this implementation scheme, license plate recognition technology (such as OCR technology) is used to extract license plate information from videos or images. If the complete license plate number cannot be recognized, the license plate is considered to be obscured or defaced. Commonly used license plate recognition tools include OCR technologies such as OpenALPR and TensorFlow. The body area of ​​the muck truck is identified by image processing algorithms, and the sludge coverage area on the body is detected. Image segmentation technology can be used to distinguish the area between the body and the sludge, and then calculate the percentage of sludge coverage. Image segmentation technology such as U-Net and OpenCV's area detection algorithm can be used. The roof part of the muck truck is identified by a deep learning target detection model (such as YOLO, SSD) to detect whether the roof is covered. The coverage can be judged based on the outline and color of the roof in the image. Pre-trained deep learning target detection models such as YOLO and SSD can be used.

[0063] Through multi-level detection of license plate obstruction, sludge coverage and roof coverage, the system can automatically identify violations of muck trucks and improve supervision efficiency. Detecting sludge coverage and roof coverage ensures the cleanliness and safe transportation of muck trucks, reduces pollution to roads and the environment, and ensures driving safety. The automated monitoring and judgment process reduces the burden of manual inspections and improves the timeliness and accuracy of violation detection.

[0064] Smart construction site online monitoring system based on IoT and AI algorithm, such as Figure 2 As shown, it includes a hardware equipment abnormality monitoring module, a safety helmet abnormal wearing monitoring module, a street event monitoring module and a muck truck monitoring module, wherein: the hardware equipment abnormality monitoring module is used to monitor the power supply equipment and communication equipment in the smart construction site, determine whether the power supply equipment is abnormal, and if the power supply equipment is abnormal, an alarm prompt is issued, and determine whether the communication equipment is abnormal, and if the communication equipment is abnormal, an alarm prompt is issued; the safety helmet abnormal wearing monitoring module is used to obtain the video data at the entrance of the smart construction site when the power supply equipment and the communication equipment are normal, upload the video data to the AI ​​data processing center, determine whether the construction site personnel wear safety helmets normally, and if they do not wear safety helmets normally, an alarm prompt is issued; the street event monitoring module is used to monitor the flow of construction site personnel who wear safety helmets normally in the smart construction site, upload the personnel flow data to the AI ​​data processing center, determine whether street events occur, and if street events occur, an alarm prompt is issued; the muck truck monitoring module is used to monitor the muck truck in real time, upload the muck truck operation data to the AI ​​data processing center, determine whether the muck truck is running illegally, and if it is running illegally, an alarm prompt is issued.

[0065] An electronic device includes: a processor and a memory, wherein computer program instructions are stored in the memory, and when the computer program instructions are executed by the processor, the processor executes the above-mentioned smart construction site online monitoring method based on the Internet of Things and AI algorithm.

[0066] A computer-readable storage medium is used to store a program, which, when executed by a processor, implements the online monitoring method for smart construction sites based on the Internet of Things and AI algorithms as described above.

[0067] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0071] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0072] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A smart construction site online monitoring method based on the Internet of Things and AI algorithms, characterized in that: The following steps are involved: Monitor the power supply equipment and communication equipment in the smart construction site to determine whether the power supply equipment is abnormal. If so, issue an alarm. Determine whether the communication equipment is abnormal. If so, issue an alarm. The step of determining whether the power supply device is abnormal comprises the following steps: Acquiring power supply equipment operation data, wherein the power supply equipment operation data includes current stability, power consumption within a set time, and power supply equipment temperature; Acquire the power supply equipment operation parameter data stored in the database, wherein the power supply equipment operation parameter data includes current parameter stability, power parameter consumption within a set time, and power supply equipment parameter temperature; The power supply equipment operation data and the power supply equipment operation parameter data are combined to obtain the power supply equipment abnormality judgment index; Compare the power supply equipment abnormality judgment index with the power supply equipment abnormality judgment threshold stored in the database: If the power supply equipment abnormality judgment index is greater than the power supply equipment abnormality judgment threshold stored in the database, the power supply equipment is abnormal; If the power supply equipment abnormality judgment index is not greater than the power supply equipment abnormality judgment threshold stored in the database, the power supply equipment is normal; The calculation formula of the power supply equipment abnormality judgment index is: ； In the formula, It is the power supply equipment abnormality judgment index. is the current stability, It is the power consumption within the set time. is the power supply equipment temperature, is the current parameter stability, The power consumption is determined for the set time. Set the temperature for the power supply equipment. is a natural constant; When the power supply equipment and communication equipment are normal, obtain the video data at the entrance of the smart construction site, upload the video data to the AI ​​data processing center, and determine whether the construction site personnel are wearing safety helmets normally. If they are not wearing safety helmets normally, an alarm will be issued; Monitor the flow of construction personnel wearing helmets in smart construction sites, upload personnel flow data to the AI ​​data processing center, and determine whether street incidents occur. If street incidents occur, an alarm will be issued; Monitor the dump trucks in real time and upload their operating data to the AI ​​data processing center to determine whether they are operating in violation of regulations. If so, an alarm will be issued.

2. The method for online monitoring of smart construction sites based on the Internet of Things and AI algorithm according to claim 1 is characterized in that: The step of determining whether the communication device is abnormal comprises the following steps: Acquiring communication device operation data, wherein the communication device operation data includes a data transmission rate and a data compression rate; Acquire communication equipment operation parameter data stored in a database, wherein the communication equipment operation parameter data includes a data transmission parameter rate and a data compression parameter rate; Matching the communication equipment operation allowable deviation data based on the communication equipment operation environment data in the smart construction site, wherein the communication equipment operation allowable deviation data includes the data transmission rate allowable deviation value and the data compression rate allowable deviation value, and the communication equipment operation environment data includes the operation environment temperature and the number of terminals within the communication coverage range; The communication equipment operation data, the communication equipment operation parameter data and the communication equipment operation allowable deviation data are integrated to obtain the communication equipment abnormality judgment index; Compare the communication device abnormality judgment index with the communication device abnormality judgment threshold stored in the database: If the communication device abnormality judgment index is greater than the communication device abnormality judgment threshold stored in the database, the communication device is abnormal; If the communication device abnormality judgment index is not greater than the communication device abnormality judgment threshold stored in the database, the communication device is normal.

3. The method for online monitoring of smart construction sites based on the Internet of Things and AI algorithm according to claim 2 is characterized in that: The method of matching the communication equipment operation allowable deviation data based on the communication equipment operation environment data in the smart construction site includes the following steps: Using a similarity function, the communication device operating environment data is compared with the communication device operating environment matching data stored in the database one by one; Determine the communication device operating environment matching data that is most similar to the communication device operating environment data; The communication equipment operation allowable deviation data stored in the database corresponding to the most similar communication equipment operation environment matching data is obtained.

4. The method for online monitoring of smart construction sites based on the Internet of Things and AI algorithm according to claim 2 is characterized in that: The calculation formula of the communication equipment abnormality judgment index is: ； In the formula, is the communication equipment abnormality judgment index, is the data transmission rate, is the data compression rate, To set the data transmission rate, The data compression parameter rate is is the permissible deviation value of the data transmission rate, The permissible deviation value for the data compression rate.

5. The method for online monitoring of smart construction sites based on the Internet of Things and AI algorithm according to claim 1 is characterized in that: The method of judging whether the construction site personnel are wearing safety helmets normally comprises the following steps: Extract facial features from video data and determine whether the current person is a registered person on the construction site based on the facial features. If not, issue an alarm. If the person is a registered staff member at the construction site, then obtain whether the registered staff member at the construction site is wearing a hat; If the cap is not worn, an alarm will be given; If the cap body is worn, determine whether the cap body shape is qualified; If the cap shape is unqualified, an alarm will be given; If the cap shape is qualified, the cap color will be determined based on the site registration personnel; The determined color of the helmet body is compared with the actual color of the helmet body worn by the registered personnel on the construction site. If the colors do not match, an alarm is given. If the colors match, the personnel on the construction site are wearing the safety helmet normally.

6. The method for online monitoring of smart construction sites based on the Internet of Things and AI algorithm according to claim 1 is characterized in that: The step of determining whether a street event occurs comprises the following steps: Get the density of people in the gathering area and determine whether the density is greater than the threshold set in the database: If the population density is greater than the population density threshold set in the database, it is determined that a street incident has occurred; If the density of people is not greater than the threshold value of people density set in the database, the moving speed of people is determined; if the number of people whose moving speed is greater than the moving speed threshold value set in the database is greater than the number threshold value set in the database, it is determined that a street event has occurred; If the moving speed of the person is not greater than the moving speed threshold set in the database, it is determined whether a person has fallen to the ground; If someone falls to the ground, it is judged that a street incident has occurred; If no one falls to the ground, it is determined that no street incident has occurred.

7. The method for online monitoring of smart construction sites based on the Internet of Things and AI algorithm according to claim 1 is characterized in that: The method of judging whether the muck truck is operating in violation of regulations comprises the following steps: Determine whether the license plate of the muck truck is blocked. If it is blocked, it is determined that the muck truck is operating illegally; If the license plate of the muck truck is not blocked, determine whether the sludge coverage area of ​​the muck truck body is greater than the sludge coverage area threshold set in the database: If the sludge coverage area of ​​the muck truck body is greater than the sludge coverage area threshold set in the database, the muck truck is judged to be operating in violation of regulations; If the sludge coverage area of ​​the muck truck body is not greater than the sludge coverage area threshold set in the database, it is determined whether the roof of the muck truck is covered; If the roof of the muck truck is not covered, it is judged that the muck truck is operating illegally; If the roof of the dump truck is covered, it is judged that the dump truck is operating normally.

8. The smart construction site online monitoring system based on the Internet of Things and AI algorithms is characterized by: The smart construction site online monitoring system runs the smart construction site online monitoring method based on the Internet of Things and AI algorithm as described in any one of claims 1 to 7, and the smart construction site online monitoring system includes a hardware equipment abnormality monitoring module, a safety helmet abnormal wearing monitoring module, a street event monitoring module and a muck truck monitoring module, wherein: The hardware equipment abnormality monitoring module is used to monitor the power supply equipment and communication equipment in the smart construction site, determine whether the power supply equipment is abnormal, and if so, issue an alarm prompt, and determine whether the communication equipment is abnormal, and if so, issue an alarm prompt; The abnormal helmet wearing monitoring module is used to obtain video data at the entrance of the smart construction site when the power supply equipment and communication equipment are normal, upload the video data to the AI ​​data processing center, and determine whether the construction site personnel are wearing safety helmets normally. If they are not wearing safety helmets normally, an alarm prompt is issued; The street event monitoring module is used to monitor the flow of construction personnel who normally wear safety helmets in the smart construction site, upload the personnel flow data to the AI ​​data processing center, determine whether a street event occurs, and issue an alarm if a street event occurs; The muck truck monitoring module is used to monitor the muck truck in real time, upload the muck truck operation data to the AI ​​data processing center, and determine whether the muck truck is operating in violation of regulations. If it is operating in violation of regulations, an alarm prompt will be issued.

Images