Intelligent hanging basket monitoring system based on AI and Internet of Things

Abstract

The invention discloses an intelligent hanging basket monitoring system based on AI and Internet of Things, which belongs to the technical field of high-altitude operation safety monitoring and comprises a hanging basket monitor, a suspension device monitor, a personnel monitor and ground service equipment. Through three-in-one of environment, equipment and people, a gyroscope, an air pressure / temperature and humidity / wind speed / current sensor, a cardiotachometer, a camera, an LoRa / Bluetooth / 4G gateway and other equipment are fused, and end side AI and deep learning technologies are combined, so that the state of a hanging basket system, the behaviors of operating personnel and environmental parameters are monitored in real time, and the safety and reliability of high-altitude operation are ensured. According to the invention, the occurrence rate of safety accidents can be effectively reduced, and the safety consciousness and working efficiency of operators are improved. And meanwhile, the black box function also provides data support for accident tracing.

Description

Technical Field

[0001] The present invention belongs to the technical field of high-altitude operation safety monitoring, and in particular relates to an AI and Internet of Things-based hanging basket intelligent monitoring system for real-time monitoring of the hanging basket status, operator behavior and environmental parameters to ensure the safety of high-altitude operations. Background Art

[0002] The high-altitude working basket has the advantages of high working height, easy erection and low construction cost. It has been widely used in the exterior wall construction and decoration of high-rise buildings. With the increasing use of the hanging basket, the safety supervision of the construction hanging basket for high-altitude operations is the guarantee of the life and health of employees working at heights. Therefore, a comprehensive, accurate and reliable construction hanging basket intelligent monitoring system is needed. The monitoring system can improve the safety factor of high-altitude operations, increase the control over construction personnel, effectively regulate their behavior and improve their safety awareness.

[0003] Some invention patents in the field of intelligent management technology of suspended baskets are disclosed in the prior art, among which the invention patent with publication number CN105608641A discloses an intelligent suspended basket management system, which is composed of equipment management, service platform system, data processing unit and data presentation unit. The equipment management is composed of module equipment and suspended basket equipment, the service platform system is composed of basic parameter management, suspended basket management, positioning monitoring system and system management, the data processing unit is composed of data acquisition and data push, and the data presentation unit is mainly implemented by a mobile client. This technical solution can manage and view the suspended basket equipment well to solve the problem of chaotic management in the suspended basket industry, and bring the intelligent suspended basket management system into the suspended basket industry, so that it can manage the suspended basket equipment very simply and conveniently. However, this technical solution still has some shortcomings in the process of application. Most of the suspended baskets on the market are only electromechanical structures, lacking real-time monitoring of the suspended basket status, operator behavior and environmental parameters, and cannot be intelligently analyzed through AI, resulting in frequent safety accidents and difficulty in tracing the causes of accidents. With the increase in high-rise buildings, the safety issues of suspended basket operations have become increasingly prominent. The existing suspended basket management system cannot meet the safety needs of modern high-altitude operations, and an intelligent and comprehensive monitoring system is urgently needed.

[0004] Based on this, the present invention designs a hanging basket intelligent monitoring system to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a trinity intelligent monitoring system for a hanging basket based on AI and the Internet of Things. The so-called trinity is a system that integrates the environment, equipment and people. It monitors the status of the hanging basket system, the behavior of the operators and environmental parameters in real time through a variety of sensors, and combines AI intelligent analysis to ensure the safety and reliability of high-altitude operations. By integrating six-axis accelerometers, air pressure sensors, cameras, heart rate monitors, LoRa gateways and other equipment, combined with end-side AI and deep learning technology, it can identify the tilt, shake, weight change of the hanging basket, the physical signs, behavior and other states of the operators in real time, and provide early warnings and operational suggestions through cloud data analysis, effectively reducing the incidence of safety accidents.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An intelligent monitoring system for a hanging basket, comprising a hanging basket monitor, a suspension device monitor, a personnel monitor and ground handling equipment;

[0008] The hanging basket monitor detects the posture and shaking of the hanging basket through an acceleration sensor / gyroscope, the lifting motor current sensor detects the phase current, leakage current and power consumption, the air pressure sensor detects the altitude and up and down speeds, the camera records and confirms the operator, and there are also lifting, emergency stop and SOS buttons, lifting limit, voice operation and early warning reminders. The terminal side AI recognizes the status of the hanging basket, and integrates the real-time operating system RTOS and the file system FS to realize the solidification and preservation of black box data. It also integrates LoRa / Bluetooth / Star Flash gateway and cellular mobile network IoT functions, real-time LAN networking and uploading system data to the IoT platform for cloud data storage and analysis and large-screen display;

[0009] The suspension device monitor can detect the stacking mode and quantity of counterweights, the straightness of the front, middle and rear beams, and the identification and sound and light warning of changes during operation by installing a camera. The weight sensor can detect the weight of the hanging basket, and the wind speed sensor A and wind direction sensor A can detect the wind speed and wind direction on the roof. The hanging basket controller can be communicated with by wireless methods such as LoRa.

[0010] The personnel monitor uses a smart bracelet to monitor the heart rate and body temperature of the operator in real time; uses a smart belt to check whether the safety rope is worn, whether the body is tilted, weightless, etc.; uses a smart helmet to ensure that the operator wears the helmet correctly; and communicates with the hanging basket controller through wireless methods such as Bluetooth / Star Flash;

[0011] The ground handling equipment uses human body detection sensors to provide voice prompts when ground personnel approach the operating area, and communicates with the hanging basket controller via wireless methods such as LoRa.

[0012] As a further description of the above technical solution:

[0013] The Hanging basket monitor built-in LoRa gateway function enables data interaction between the suspension device monitor, personnel monitor, and ground support equipment; it also has an IoT function to achieve data interaction with the platform / App / miniprogram through the cellular mobile network.

[0014] As a further description of the above technical solution:

[0015] Hanging basket monitor The controller is built with a wide-angle camera that can monitor the entire hanging basket operation area and identify human forms, status, quantity, and whether a safety belt and safety helmet are worn through AI to comply with the technical specifications of hanging basket operations.

[0016] As a further description of the above technical solution:

[0017] The personnel monitor uses a smart bracelet to real-time monitor the heart rate and body temperature of the operating personnel; uses a smart waistband to detect whether the safety rope is worn, whether the body is tilted, in a weightless state, and the working hours; uses a smart helmet to detect whether the safety helmet is worn correctly; and communicates with the hanging basket controller through wireless methods such as Bluetooth / StarFlash.

[0018] As a further description of the above technical solution:

[0019] The suspension device monitor is built with an edge AI image recognition module and integrates a rope weight sensor, wind speed sensor A, and wind direction sensor A through wired communication methods such as RS485; the detector communicates with the hanging basket monitor through wireless communication methods such as LoRa;

[0020] As a further description of the above technical solution:

[0021] The image recognition module of the suspension device monitor uses a convolutional neural network (CNN) to detect and identify the stacking method, quantity, bundling method, etc. of the counterweight and upload the converted results to the LoRa gateway.

[0022] As a further description of the above technical solution:

[0023] The ground support equipment can detect pedestrians and give a voice reminder for high-altitude operations; when an abnormality occurs in the system, it can give an immediate audible and visual alarm to attract the attention of ground support personnel or pedestrians.

[0024] As a further description of the above technical solution:

[0025] The hanging basket controller also includes a data acquisition module, an image data preprocessing module, a video data preprocessing module, a data annotation module, a deep learning model and a model training and optimization module. The output end of the data acquisition module is electrically connected to the input end of the image data preprocessing module and the video data preprocessing module, respectively. The output ends of the image data preprocessing module and the video data preprocessing module are both electrically connected to the input end of the data annotation module. The output end of the data annotation module is electrically connected to the input end of the deep learning model. The deep learning model is bidirectionally connected to the model training and optimization module.

[0026] As a further description of the above technical solution:

[0027] The data acquisition module, based on local AI recognition technology, collects environmental parameters, including wind speed, basket elevation / weight, rotation / shake / tilt, and captures the operation process of the operators, including the operators' movements, postures, and the wearing of safety equipment.

[0028] As a further description of the above technical solution:

[0029] The image data preprocessing module denoises the image data acquired by the local AI recognition technology and removes interference signals caused by environmental noise during the image acquisition process. The image data preprocessing module enhances the contrast and clarity of the denoised image based on image enhancement technology, making the details in the image content more obvious.

[0030] As a further description of the above technical solution:

[0031] The video data preprocessing module decomposes the video into a series of separate image frames and samples the frame memory as needed to balance the data training amount and training efficiency of the model. The data annotation module is used to annotate the violations of the operators so that the deep learning module can identify different situations and facilitate the deep learning model to understand and learn different safety behavior patterns. The model training and optimization module uses the annotated data to train the deep learning model and continuously optimizes the parameters of the deep learning model to improve its performance.

[0032] The overall structure of the deep learning model organizes the data into input layers, hidden layers, and output layers;

[0033] The input layer is responsible for receiving the collected data and standardizing it according to the following formula;

[0034]

[0035] In the formula, x′ i is the standardized data, x i is the input time series data, is the average value of the input time series data, n is the length of the time series data, and Excel is used to organize the received environment / basket / human data into a time series y according to the 30-min time interval monitored by the sensor. 1 and 2 , after normalization, participate in the operation of the fully connected layer;

[0036] The hidden layer includes three sub-layers: long short-term memory, full connection, and regression. The long short-term memory layer is used to enhance the interaction of long-sequence gradient flows by analyzing the connections between time series data. This layer consists of cell state a, hidden state b, input gate i, forget gate c, candidate gate d, and output gate e.

[0037] The cell state a carries the information learned from the previous time point and is adjusted in each step of the long short-term memory layer to ensure the accuracy of the information. The implicit state b of each step retains the output information of the step to ensure the accuracy of data updates. The input gate i adjusts the update progress of the cell state, the forget gate c manages the amount of cell information retained, the candidate gate d is responsible for adding new data information to the cell, and the output gate e controls the proportion of cell information passed to the next step.

[0038] The cell state and implicit state at each step are calculated by the following formula:

[0039]

[0040] In the formula, o is the vector element multiplication symbol, σ is the state function;

[0041] And in each time step, the input gate, forget gate, candidate gate and output gate are expressed as:

[0042] i t =σ g (z i x t +R i b t-1 +m i )

[0043] f t =σ g (z f x t +R f b t-1 +m f )

[0044] g t =σ t (z g x t +R g b t-1+m g )

[0045] o t =σ g (z o x t +R o b t-1 +m o )

[0046] In the formula, σ t is the state activation function, σ g is the gate state function, z represents the current input x t The relevant weight matrices are used for the input gate, forget gate, candidate gate, and output gate, respectively. R represents the implicit state of the previous time step, and b t-1 The relevant weight matrices are used for the input gate, forget gate, candidate gate and output gate respectively. m represents the bias term of each gate, which is used for the input gate, forget gate, candidate gate and output gate respectively.

[0047] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0048] 1. In the present invention, by installing a variety of special sensors, various states are monitored and recorded in real time. At the same time, through intelligent analysis and judgment, correct operations are given or wrong instructions are rejected, thereby achieving safe protection of the hanging basket.

[0049] 2. In the present invention, the high-altitude worker safety behavior identification technology based on deep learning provides a more comprehensive, accurate and real-time safety monitoring solution for high-risk high-altitude working environments. By adopting a deep learning model, combined with key steps such as data collection, data annotation, model training and real-time monitoring, it can effectively identify environmental risks, the safe behavior of workers in high-altitude operations, and possible unsafe behaviors, which not only helps to reduce the risk of high-altitude working accidents, but also improves the life safety and work efficiency of workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a schematic diagram of equipment installation of a hanging basket intelligent monitoring system proposed by the present invention;

[0051] Figure 2 A software framework and functional implementation diagram of a hanging basket intelligent monitoring system proposed by the present invention;

[0052] Figure 3 A hardware framework and data interaction diagram of a hanging basket intelligent monitoring system proposed by the present invention;

[0053] Figure 4 This is a schematic diagram of the safety behavior identification of operators in the hanging basket intelligent monitoring system proposed by the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] Please see attached Figure 1 -Attached Figure 4 ,The present invention provides a technical solution: an intelligent monitoring system for a hanging basket, including a hanging basket monitor, a suspension device monitor, a personnel monitor and ground handling equipment;

[0056] The hanging basket monitor detects the posture and shaking of the hanging basket through an acceleration sensor / gyroscope, a current sensor detects the phase current, leakage current and power consumption of the lifting motor, an air pressure sensor detects the altitude and speed, and a camera records and confirms the operator. It also has lifting, emergency stop and SOS buttons, lifting limit, voice operation and early warning reminders. It combines the end-side AI to identify the status of the hanging basket, and integrates the real-time operating system RTOS and the file system FS to realize the solidification and preservation of black box data. It also integrates the LoRa gateway and the Internet of Things function, and uploads the system data to the IoT platform in real time through cellular mobile networks such as 4G, so that the data can be stored, analyzed and displayed on the cloud.

[0057] The suspension device monitor can detect the stacking mode and quantity of counterweights, the straightness of the front, middle and rear beams, and the identification and sound and light warning of changes during operation by installing a camera. The weight sensor can detect the weight of the hanging basket, and the wind speed sensor A and wind direction sensor A can detect the wind speed and wind direction on the roof. The hanging basket controller can be communicated with by wireless methods such as LoRa.

[0058] The personnel monitor uses a smart bracelet to monitor the heart rate and body temperature of the operator in real time; uses a smart belt to detect whether the safety rope is worn, whether the body is tilted, weightless, and the working time; uses a smart helmet to detect whether the helmet is worn correctly; and communicates with the hanging basket controller through wireless methods such as Bluetooth / Star Flash;

[0059] The ground handling equipment uses human body detection sensors to provide voice prompts when ground personnel approach the operating area, and communicates with the hanging basket controller via wireless methods such as LoRa.

[0060] Specifically, the hanging basket controller also includes a data acquisition module, an image data preprocessing module, a video data preprocessing module, a data annotation module, a deep learning model and a model training and optimization module. The output end of the data acquisition module is electrically connected to the input end of the image data preprocessing module and the video data preprocessing module, respectively. The output ends of the image data preprocessing module and the video data preprocessing module are both electrically connected to the input end of the data annotation module. The output end of the data annotation module is electrically connected to the input end of the deep learning model. The deep learning model is bidirectionally connected to the model training and optimization module.

[0061] Specifically, the data acquisition module, based on local AI recognition technology, collects environmental parameters, including wind speed, basket elevation / weight, rotation / shake / tilt, and captures the operation process of the operators, including the operators' movements, postures, and the wearing of safety equipment.

[0062] Specifically, the image data preprocessing module denoises the image data acquired by the local AI recognition technology to remove interference signals caused by environmental noise during the image acquisition process. The image data preprocessing module enhances the contrast and clarity of the denoised image based on image enhancement technology, making the details in the image content more obvious.

[0063] Specifically, the video data preprocessing module decomposes the video into a series of separate image frames and samples the frame memory as needed to balance the data training volume and training efficiency of the model. The data annotation module is used to annotate the violations of the operators so that the deep learning module can identify different situations and facilitate the deep learning model to understand and learn different safety behavior patterns. The model training and optimization module uses the annotated data to train the deep learning model, and continuously optimizes the parameters of the deep learning model to improve its performance.

[0064] Working principle, when using:

[0065] The hanging basket monitor uses a six-axis acceleration sensor to detect the posture and shaking of the hanging basket, a current sensor to detect the phase current, leakage current and power consumption of the lifting motor, an air pressure sensor to detect the altitude and speed, and a camera to record and confirm the operator and monitor the operator's behavior. It also has lifting, emergency stop and SOS buttons, lifting limit, voice operation and early warning reminders. The end-side AI recognizes the status of the hanging basket, and integrates the real-time operating system RTOS and the file system FS to realize the solidification and preservation of black box data. It also integrates the Internet of Things function to upload system data to the IoT platform in real time for data cloud storage and analysis and large-screen display;

[0066] The suspension device monitor can detect the stacking method and quantity of counterweights, the straightness of the front, middle and rear beams, and the identification and sound and light warning of changes during operation by adding cameras. The weight sensor detects the weight of the hanging basket, and the wind speed sensor A and wind direction sensor A detect the wind speed and direction on the roof. It communicates with the hanging basket controller through wireless methods such as LoRa.

[0067] Personnel monitor, using smart bracelets to monitor the heart rate, body temperature and working hours of workers in real time; using smart belts to check whether the safety rope is worn, whether the body is tilted, weightless, etc.; using smart helmets to ensure that workers wear safety helmets correctly; communicating with the hanging basket controller through wireless methods such as Bluetooth / Star Flash;

[0068] The hanging basket monitor also includes a data acquisition module, an image data preprocessing module, a video data preprocessing module, a data annotation module, a deep learning model and a model training and optimization module. The output end of the data acquisition module is electrically connected to the input end of the image data preprocessing module and the video data preprocessing module respectively. The output ends of the image data preprocessing module and the video data preprocessing module are both electrically connected to the input end of the data annotation module. The output end of the data annotation module is electrically connected to the input end of the deep learning model. The deep learning model is bidirectionally connected to the model training and optimization module.

[0069] The data acquisition module, based on local AI recognition technology, collects environmental parameters, including wind speed, basket elevation / weight, rotation / shake / tilt, etc.; captures the operation process of the operator, including the operator's movements, postures, and wearing of safety equipment;

[0070] The image data preprocessing module denoises the image data acquired by the local AI recognition technology to remove interference signals caused by environmental noise during the image acquisition process. The image data preprocessing module enhances the contrast and clarity of the denoised image based on the image enhancement technology to make the details in the image content more obvious;

[0071] The video data preprocessing module decomposes the video into a series of separate image frames and samples the frame memory as needed to balance the data training amount and training efficiency of the model. The data annotation module is used to annotate the violations of the operators so that the deep learning module can identify different situations and facilitate the deep learning model to understand and learn different safety behavior patterns. The model training and optimization module uses the annotated data to train the deep learning model and continuously optimizes the parameters of the deep learning model to improve its performance.

[0072] The overall structure of the deep learning model organizes the data into input layers, hidden layers, and output layers;

[0073] The input layer is responsible for receiving the collected data and standardizing it according to the following formula;

[0074]

[0075] In the formula, x′ i is the standardized data, x i is the input time series data, is the average value of the input time series data, n is the length of the time series data, and Excel is used to organize the received environment / basket / human body data into a time series y according to the 30-minute time interval monitored by the sensor. i , after normalization, participate in the operation of the fully connected layer;

[0076] The hidden layer includes three sub-layers: long short-term memory, full connection, and regression. The long short-term memory layer is used to enhance the interaction of long-sequence gradient flows by analyzing the connections between time series data. This layer consists of cell state a, hidden state b, input gate i, forget gate c, candidate gate d, and output gate e.

[0077] The cell state a carries the information learned from the previous time point and is adjusted in each step of the long short-term memory layer to ensure the accuracy of the information. The implicit state b of each step retains the output information of the step to ensure the accuracy of data updates. The input gate i adjusts the update progress of the cell state, the forget gate c manages the amount of cell information retained, the candidate gate d is responsible for adding new data information to the cell, and the output gate e controls the proportion of cell information passed to the next step.

[0078] The cell state and implicit state at each step are calculated by the following formula:

[0079]

[0080] In the formula, o is the vector element multiplication symbol, σ is the state function;

[0081] And in each time step, the input gate, forget gate, candidate gate and output gate are expressed as:

[0082] i t =σ g (z i x t +R i b t-1 +m i )

[0083] f t =σ g (z f x t +R f bt-1 +m f )

[0084] g t =σ t (z g x t +R g b t-1 +m g )

[0085] o t =σ g (z o x t +R o b t-1 +m o )

[0086] In the formula, σ t is the state activation function, σ g is the gate state function, z represents the current input x t The relevant weight matrices are used for the input gate, forget gate, candidate gate, and output gate, respectively. R represents the implicit state of the previous time step, and b t-1 The relevant weight matrices are used for the input gate, forget gate, candidate gate and output gate respectively. m represents the bias term of each gate, which is used for the input gate, forget gate, candidate gate and output gate respectively.

[0087] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A hanging basket intelligent monitoring system, characterized in that: Includes basket monitors, suspension device monitors, personnel monitors and ground handling equipment; Said Hanging basket monitor , the six-axis acceleration sensor is used to detect the posture and shaking of the hanging basket, the three-phase lifting motor current sensor detects the phase current, leakage current and power consumption, the air pressure sensor detects the altitude and speed, the camera records and confirms the operator, and there are lifting, emergency stop and SOS buttons, lifting limit, voice operation and early warning reminders. Combined with the end-side AI capabilities to identify the status of the hanging basket, the real-time operating system RTOS and the file system FS are integrated to realize the solidification and preservation of black box data. It also integrates LoRa gateway and IoT functions, real-time LoRa networking and uploading system data to the IoT platform for cloud data storage and analysis and large-screen display; Said Suspension monitor , by installing cameras, the stacking method and quantity of counterweights, the straightness of the front, middle and rear beams, and the identification and sound and light warning of changes during operation can be realized. The weight of the hanging basket is detected by the weight sensor, and the wind speed sensor A and wind direction sensor A detect the wind speed and wind direction on the roof. The wireless communication with the hanging basket controller is realized through LoRa and other wireless methods; Said Personnel monitor , use smart bracelets to monitor the heart rate and body temperature of workers in real time; use smart waists to detect whether the safety rope is worn, whether the body is tilted, weightless, and working hours; use smart helmets to detect whether the helmet is worn correctly; communicate with the hanging basket controller through wireless methods such as Bluetooth / Star Flash; Said Ground support equipment , through human detection sensors, it can detect the ground personnel approaching the operation area and issue voice warnings, and communicate with the hanging basket controller through wireless methods such as LoRa.

2. The intelligent monitoring system for a hanging basket according to claim 1 is characterized in that: The hanging basket monitor has a built-in LoRa gateway function to realize data interaction between the suspension device monitor, personnel monitor and ground equipment; it also has the Internet of Things function, which can upload data through cellular mobile networks such as 4G, and receive requests issued by the platform to realize data interaction with the platform / App / mini program.

3. The intelligent monitoring system for a hanging basket according to claim 1 is characterized in that: The hanging basket monitor has a built-in wide-angle camera that can monitor the entire hanging basket operation area and use AI to identify human shape, status, number, and whether they are wearing belts and helmets, so as to comply with the technical specifications for hanging basket operations.

4. The intelligent monitoring system for a hanging basket according to claim 1 is characterized in that: Said Suspension monitor It has a built-in end-side AI image recognition module, and integrates the rope weight sensor, wind speed sensor A and wind direction sensor A through RS485 and other methods; the detector communicates with the hanging basket monitor through wireless communication methods such as LoRa.

5. The intelligent monitoring system for a hanging basket according to claim 1 is characterized in that: Said Suspension monitor The image recognition module detects and identifies the stacking method, quantity, bundling method, etc. of the counterweights through a convolutional neural network (CNN), and uploads the converted results to the LoRa gateway.

6. The suspension device monitor according to claim 5 has a built-in end-side AI image recognition module, which can determine whether the height, length and counterweight of the suspension meet the relevant national hanging basket installation technical specifications, and can make real-time judgments and comparisons so that it will not be changed arbitrarily during construction to prevent accidents.

7. The intelligent monitoring system for a hanging basket according to claim 1, characterized in that: The personnel monitor integrates local AI-based recognition capabilities. Through wristband, belt and helmet data, it can identify abnormal conditions, output results in a timely manner, and nip risks in the bud.

8. The intelligent monitoring system for a hanging basket according to claim 1, characterized in that: Said Ground support equipment , can detect pedestrians and give voice reminders for aerial work; when the system is abnormal, it can promptly give sound and light alarms so that ground staff or pedestrians can pay attention. And through communication technologies such as LoRa and other communication technologies with the hanging basket intelligent monitoring system to achieve data upload and sharing.

9. According to the intelligent monitoring system of a hanging basket as described in claim 1, the hanging basket monitor also includes a data storage module and a fatigue monitoring module. The data storage module is used to store black box data to ensure that the cause of the accident can be traced after the accident occurs. The fatigue monitoring module is used to monitor the fatigue status of the operators in real time and remind the operators to rest through voice prompts.

10. According to the intelligent monitoring system of the hanging basket of claim 1, the suspension device monitor further comprises an environmental monitoring module for real-time monitoring of parameters such as temperature, humidity, ultraviolet rays, etc. of the working environment to ensure the safety of the working environment, which comprises the following contents: Data collection, through a variety of sensors arranged in the monitoring area, collects different types of environmental data in real time. Data transmission: the collected data is transmitted to the central data processing platform via wireless or wired networks; Data processing: Data transmitted to the central data processing platform will be stored in the database and pre-processed, including noise removal, smoothing, missing value filling and outlier detection, to ensure the accuracy and consistency of the data; Data analysis uses statistical methods, data mining, and machine learning algorithms to conduct in-depth analysis of data, revealing the inherent laws and trends of environmental changes and providing a scientific basis for the formulation of environmental protection policies.

Images