Tower crane jacking safety state online evaluation system based on edge calculation
By using Kalman filtering and fuzzy logic algorithms in the edge computing layer to assess the safety status of tower crane lifting, the problem of insufficient real-time performance in existing technologies is solved. This enables low-latency safety monitoring and highly reliable tower crane lifting operations. Combined with deep learning analysis on the cloud platform, it provides comprehensive safety management support for tower crane lifting.
Patent Information
- Application Number
- CN202511496384.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-20
- Publication Date
- 2026-02-10
AI Technical Summary
Existing tower crane jacking safety monitoring systems rely on manual experience or remote cloud platforms, which suffer from problems such as large data transmission delays, insufficient real-time performance, and high network stability requirements, making it difficult to meet the high reliability and low latency requirements of jacking operations.
The tower crane jacking safety status online assessment system based on edge computing includes a terminal perception layer, an edge computing layer, and a cloud platform layer. The terminal perception layer collects data through multiple sensors, the edge computing layer performs local real-time processing and safety status assessment, and the cloud platform layer stores historical data and performs remote monitoring. The system uses Kalman filtering algorithm, multi-source information fusion technology, and fuzzy logic algorithm to assess safety status and communicates with the cloud platform through 4G/5G network.
It enables low-latency local real-time safety assessment, reduces reliance on network stability, minimizes false alarms and missed alarms, enhances real-time safety assurance capabilities for jacking operations, and provides comprehensive remote monitoring support through a cloud platform.
Smart Images

Figure CN121493812A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of tower crane safety monitoring technology, and in particular to an online assessment system for the safety status of tower crane jacking based on edge computing. Background Technology
[0002] Tower cranes are indispensable key equipment in modern construction, and the safety status of their lifting operations directly affects construction safety and project progress. The lifting process involves changes in various physical parameters, including hydraulic system pressure, tower tilt angle, and structural vibration. Failure to detect abnormalities in a timely manner can easily lead to structural instability or even safety accidents. Therefore, achieving real-time and accurate online assessment of the safety status during the lifting process is of great significance for ensuring the safe operation of tower cranes.
[0003] Currently, in the field of tower crane jacking safety monitoring, common practices still rely on manual experience or monitoring systems based on remote cloud platforms. Manual monitoring is limited by personnel experience and attention, making it difficult to achieve continuous and accurate judgment of multi-source data. While cloud-based systems possess some data processing capabilities, they suffer from problems such as large data transmission delays, insufficient real-time performance, and high requirements for network stability because they rely on transmitting all raw data to the cloud for processing. Especially when network conditions at the construction site are poor, the system response is slow, making it difficult to issue timely warnings and failing to meet the stringent requirements of high reliability and low latency for jacking operations. Summary of the Invention
[0004] This invention provides a tower crane jacking safety status assessment system that can achieve local real-time processing, low-latency response, and high reliability.
[0005] The technical solution adopted in this invention is as follows: an online assessment system for the safety status of tower crane jacking based on edge computing, comprising a terminal sensing layer, an edge computing layer, and a cloud platform layer. The terminal sensing layer includes multiple sensors arranged in key parts of the tower crane for collecting physical parameters during the jacking process. The edge computing layer is connected to the terminal sensing layer through an industrial embedded device for local real-time processing and safety status assessment of the sensor data. The cloud platform layer is used to receive data uploaded by the edge computing layer and perform historical data storage, trend prediction, and remote monitoring.
[0006] As a further improvement of the present invention, the terminal sensing layer includes at least three of the following: a hydraulic cylinder pressure sensor, a dual-axis tilt sensor, a triaxial vibration acceleration sensor, and a laser displacement sensor. Each sensor has an IP67 protection rating, a sampling frequency of not less than 1 kHz, and communicates with the edge computing layer via a CAN bus.
[0007] As a further improvement of the present invention, the edge computing layer includes a data preprocessing module, a security assessment module, and a local early warning module. The data preprocessing module uses a Kalman filter algorithm to denoise and smooth the sensor data. The security assessment module constructs a security coefficient model based on multi-source information fusion technology and combines a fuzzy logic algorithm to perform hierarchical assessment of the security status. The local early warning module triggers a local alarm and uploads abnormal information to the cloud platform when the security coefficient exceeds a preset threshold.
[0008] As a further improvement of the present invention, the safety factor model is defined as follows:
[0009] Where P, θ, and a are the real-time pressure, tilt angle, and vibration acceleration, respectively. max θ lim a lim For the corresponding threshold, α, β, and γ are weight coefficients determined by the analytic hierarchy process, and satisfy α + β + γ = 1.
[0010] As a further improvement of the present invention, the fuzzy logic algorithm divides the security status into three levels: "low risk", "medium risk" and "high risk", uses the triangular membership function and Mamdani reasoning method to determine the status, and uses the centroid method to defuzzify the output.
[0011] As a further improvement of the present invention, the edge computing layer has data compression and local caching functions, storing critical data when the network is abnormal and uploading it to the cloud platform after the network is restored.
[0012] As a further improvement of the present invention, the edge computing layer and the cloud platform layer establish a VPN connection through a 4G / 5G network, use the TLS1.3 protocol to encrypt communication, and use the MQTT protocol to transmit data, supporting QoS1 level message guarantee.
[0013] As a further improvement of the present invention, the total system delay satisfies: t d =t s +t f +t e +t c <50ms,
[0014] Among them, t s t is the sampling time. f t is the filtering time. e To evaluate time, t c This refers to the communication time.
[0015] As a further improvement of the present invention, the cloud platform layer adopts a microservice architecture, including data receiving services, real-time computing services and web application services, and supports time-series database storage and deep learning frameworks for anomaly diagnosis and trend prediction.
[0016] A method for online assessment of the safety status of tower crane jacking, based on the above-mentioned system implementation, includes the following steps:
[0017] S1, Multi-source data acquisition: Through multiple sensors deployed at key parts of the tower crane, the hydraulic cylinder pressure, tower tilt angle, structural vibration acceleration and physical parameters of lifting displacement during the jacking process are collected in real time;
[0018] S2, edge-side data preprocessing and fusion: Multi-source sensor data is received at the edge computing layer, and Kalman filtering algorithm is used to denoise and smooth the data to filter out process noise and observation noise, and obtain fused high signal-to-noise ratio state data.
[0019] S3, Real-time safety status assessment: Based on the fused status data, the safety factor S of the current lifting process is calculated according to the predefined safety factor model. Then, the calculated safety factor S is input into the fuzzy logic system. Using the triangular membership function and the fuzzy rule base pre-built by expert knowledge, the system performs comprehensive inference through the Mamdani reasoning method and uses the centroid method for defuzzification, outputting three levels of safety status: "low risk", "medium risk" and "high risk".
[0020] S4, Local Early Warning and Decision Execution: The security status is compared with the preset threshold in real time. If the status is "low risk", the system is determined to be operating normally. If the status is "medium risk" or "high risk", the local sound and light alarm of the edge computing layer is immediately triggered and a warning is issued to the operator. At the same time, the abnormal status event and related data are formed into a summary information package.
[0021] S5, Cloud Data Synchronization and Remote Monitoring: The summary information packet is transmitted via 4G / 5G network, encrypted through a VPN tunnel using the TLS1.3 protocol, and then uploaded to the cloud platform layer using the MQTT protocol. After receiving the data, the cloud platform layer stores it in a time-series database and uses a deep learning framework to perform historical trend analysis, anomaly diagnosis and prediction. A monitoring interface is then provided to remote administrators through a web application service.
[0022] The beneficial effects of the present invention are as follows: (1) The present invention constructs a three-level collaborative architecture of "terminal perception-edge computing-cloud platform", sinks the core data processing and security assessment tasks to the edge layer, completes Kalman filtering, multi-source information fusion and fuzzy logic judgment at the near end of the data source, and controls the total system latency to within 50ms, which is far superior to the traditional cloud processing mode. It can identify risks in a timely manner and trigger local alarms, which greatly improves the real-time safety assurance capability of jacking operations.
[0023] (2) The localized processing of the edge computing layer in this invention reduces the dependence on network stability. Combined with data compression and caching mechanisms, it ensures that critical data is not lost when the network is abnormal. At the same time, the security assessment model that integrates fuzzy logic can handle data fluctuations and uncertainties more accurately than the traditional fixed threshold method, effectively reducing false alarms and false negatives, and making the system more robust and rational in the face of changing operating conditions.
[0024] (3) The system of the present invention not only realizes rapid response at the edge, but also performs historical data storage, deep learning analysis and trend prediction through the cloud platform, providing managers with a comprehensive remote monitoring interface and decision support. This division of labor mode of "real-time edge processing + deep mining in the cloud" realizes the organic combination of short-cycle response and long-cycle optimization of safety monitoring, and systematically improves the safety management level of tower crane jacking operations. Attached Figure Description
[0025] Figure 1 This is the overall architecture diagram of an online assessment system for the safety status of tower crane jacking based on edge computing, according to the present invention. Detailed Implementation
[0026] To make the technical problems, technical solutions, and beneficial effects to be solved by this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the embodiments described herein are merely illustrative and are not intended to limit the scope of this application.
[0027] This invention provides an online safety status assessment system for tower crane jacking based on edge computing, comprising a terminal sensing layer, an edge computing layer, and a cloud platform layer. The terminal sensing layer includes multiple sensors deployed at key parts of the tower crane to collect physical parameters during the jacking process. The edge computing layer is connected to the terminal sensing layer through industrial embedded devices to perform local real-time processing and safety status assessment of the sensor data. The cloud platform layer receives data uploaded by the edge computing layer and performs historical data storage, trend prediction, and remote monitoring.
[0028] In this invention, the terminal sensing layer includes at least three of the following: a hydraulic cylinder pressure sensor, a dual-axis tilt sensor, a triaxial vibration acceleration sensor, and a laser displacement sensor. Each sensor has an IP67 protection rating, a sampling frequency of not less than 1 kHz, and communicates with the edge computing layer via a CAN bus.
[0029] In this invention, the edge computing layer includes a data preprocessing module, a security assessment module, and a local early warning module. The data preprocessing module uses a Kalman filter algorithm to denoise and smooth sensor data. The security assessment module constructs a security coefficient model based on multi-source information fusion technology and combines a fuzzy logic algorithm to perform hierarchical assessment of the security status. The local early warning module triggers a local alarm and uploads abnormal information to the cloud platform when the security coefficient exceeds a preset threshold.
[0030] In this invention, the safety factor model is defined as follows:
[0031] Where P, θ, and a are the real-time pressure, tilt angle, and vibration acceleration, respectively. max θ lim a lim For the corresponding threshold, α, β, and γ are weight coefficients determined by the analytic hierarchy process, and satisfy α + β + γ = 1.
[0032] In this invention, the fuzzy logic algorithm divides the security state into three levels: "low risk", "medium risk" and "high risk". It uses the triangular membership function and Mamdani inference method to determine the state and uses the centroid method to defuzzify the output.
[0033] In this invention, the edge computing layer has data compression and local caching functions, storing critical data when the network is abnormal and uploading it to the cloud platform after the network is restored.
[0034] In this invention, the edge computing layer and the cloud platform layer establish a VPN connection through a 4G / 5G network, use the TLS1.3 protocol to encrypt communication, and use the MQTT protocol to transmit data, supporting QoS1 level message guarantee.
[0035] In this invention, the total system delay satisfies: t d =t s +t f +t e +t c <50ms,
[0036] Among them, t s t is the sampling time. f t is the filtering time. e To evaluate time, t c This refers to the communication time.
[0037] In this invention, the cloud platform layer adopts a microservice architecture, including data receiving services, real-time computing services, and web application services, and supports time-series database storage and deep learning frameworks for anomaly diagnosis and trend prediction.
[0038] A method for online assessment of the safety status of tower crane jacking, based on the above-mentioned system implementation, includes the following steps:
[0039] S1, Multi-source data acquisition: Through multiple sensors deployed at key parts of the tower crane, the hydraulic cylinder pressure, tower tilt angle, structural vibration acceleration and physical parameters of lifting displacement during the jacking process are collected in real time;
[0040] S2, edge-side data preprocessing and fusion: Multi-source sensor data is received at the edge computing layer, and Kalman filtering algorithm is used to denoise and smooth the data to filter out process noise and observation noise, and obtain fused high signal-to-noise ratio state data.
[0041] S3, Real-time Safety Status Assessment: Based on the fused status data, the safety factor S of the current lifting process is calculated according to the predefined safety factor model. The calculated safety factor S is then input into the fuzzy logic system. Using the triangular membership function and the fuzzy rule base pre-built by expert knowledge, the system performs comprehensive inference through the Mamdani inference method and defuzzifies using the centroid method, outputting three levels of safety status: "low risk", "medium risk" and "high risk".
[0042] S4, Local Early Warning and Decision Execution: The security status is compared with the preset threshold in real time. If the status is "low risk", the system is determined to be operating normally. If the status is "medium risk" or "high risk", the local audible and visual alarm of the edge computing layer is immediately triggered and the operator is alerted. At the same time, the abnormal status event and related data are formed into a summary information package.
[0043] S5, Cloud Data Synchronization and Remote Monitoring: The summary information packet is transmitted via 4G / 5G network, encrypted through VPN tunnel and using TLS 1.3 protocol, and then uploaded to the cloud platform layer via MQTT protocol. After receiving the data, the cloud platform layer stores it in time series database and uses deep learning framework to perform historical trend analysis, anomaly diagnosis and prediction. The monitoring interface is provided to remote management personnel through Web application service.
[0044] Example:
[0045] This embodiment uses a QTZ80 tower crane used in a typical high-rise building construction project as an example to illustrate the specific implementation of the system of the present invention.
[0046] (I) System Hardware Configuration and Deployment
[0047] Terminal sensing layer sensors are deployed in key areas of the QTZ80 tower crane, such as the lifting frame, near the hydraulic cylinders, and in the standard sections of the tower body.
[0048] (1) Install a hydraulic cylinder pressure sensor (model: HYD-PT501, range 0-40MPa, accuracy ±0.5%FS) in the oil inlet circuit of the lifting hydraulic cylinder to monitor the lifting force.
[0049] (2) Install dual-axis tilt sensors (model: SST300, measurement range ±15°, accuracy ±0.1°) on the top of the tower body and the crossbeam of the frame respectively to monitor the verticality of the tower body and the horizontality of the frame.
[0050] (3) Install a triaxial vibration acceleration sensor (model: CA-YD-180, frequency response 0-500Hz) at the connecting pin between the jacking frame and the tower body to monitor abnormal vibrations during the jacking process.
[0051] (4) Install a laser displacement sensor (model: ZLDS100, resolution 0.1mm) between the sleeve and the standard section to accurately measure the lifting displacement and check the lifting synchronization.
[0052] All of the above sensors have an IP67 protection rating and are connected to the edge computing node located in the control cabinet of the tower crane operating platform via a CAN bus (communication rate 1Mbps).
[0053] The edge computing layer uses an industrial-grade embedded computer (model: Advantech UNO-2484G, equipped with an Intel Core i7 multi-core processor). This device integrates a CAN bus interface and is responsible for running data preprocessing, security assessment, and early warning modules.
[0054] The cloud platform layer is deployed on a public cloud (such as Alibaba Cloud), using its elastic computing service to build a microservice cluster, and using time-series databases (such as InfluxDB) and deep learning frameworks (such as TensorFlow Serving).
[0055] (II) System Software Implementation and Parameter Setting
[0056] Step 1, Data Preprocessing:
[0057] Edge computing nodes read raw sensor data from the CAN bus at a frequency of 100Hz. The data preprocessing module uses a Kalman filter algorithm to perform real-time noise reduction and smoothing of the data. The state vector is selected as x = [P, θ, a]. T(i.e., pressure, tilt angle, and vibration acceleration), with the observation matrix H being an identity matrix. By adjusting the process noise covariance matrix Q and the observation noise covariance matrix R, the filter can effectively remove random interference caused by hydraulic pulsation and wind force, improving the signal-to-noise ratio of the processed data from approximately 15 dB to over 32 dB.
[0058] Step 2, Safety Status Assessment:
[0059] The security assessment module calculates the security factor S based on the preprocessed data.
[0060] In this embodiment, based on the performance and safety specifications of the QTZ80 tower crane, a threshold value is set as: P max =32MPa, θ lim =2°, a lim =5m / s 2 The judgment matrix is constructed using the Analytic Hierarchy Process (AHP), and the weight coefficients are calculated to be α = 0.5, β = 0.3, and γ = 0.2. Therefore, the specific safety factor model is as follows:
[0061] The calculated safety factor S (range 0-1) is then input into the fuzzy logic system. This system defines three linguistic variables: "low risk," "medium risk," and "high risk," all with triangular membership functions and a universe of discourse [0,1]. For example, the membership function for "medium risk" can be defined as having a membership of 0 when S=0.3, 1 when S=0.5, and 0 when S=0.7. The fuzzy rule base, built based on expert experience, contains nine rules, for example:
[0062] Rule 1: If P is normal, θ is normal, and a is normal, then the state is low risk.
[0063] Rule 5: If P is high, θ is large, and a is normal, then the state is medium risk.
[0064] Rule 9: If P is too high, θ is too large, and a is too large, then the state is high risk.
[0065] The system uses the Mamdani inference method for fuzzy reasoning and the centroid method for defuzzification, ultimately outputting an accurate security status level.
[0066] Step 3, Early Warning and Communication:
[0067] Local early warning module settings: When the output status is "low risk" (S>0.7), the system operates normally; when the status is "medium risk" (0.4≤S≤0.7), the yellow warning light flashes; when the status is "high risk" (S<0.4), the local audible and visual alarm (model: AD-2410) is immediately triggered and the lifting action is locked.
[0068] Meanwhile, the edge node compresses the abnormal events and related data (timestamp, device ID, security factor S, key sensor readings) into a Protocol Buffers format data packet of approximately 200 bytes. This packet is then uploaded to the cloud platform via a VPN tunnel established through the 4G network (in this embodiment, a China Mobile 4G IoT card) using TLS 1.3 encryption and the MQTT protocol (QoS level 1).
[0069] (III) Verification of Implementation Results
[0070] During the three-month jacking operation of this project, the system completed 12 standard section jackings. Actual measurements showed the following delays in each component of the system: sensor sampling and AD conversion time t s ≈8ms, Kalman filter processing time t f = 4ms, execution time t of the security assessment algorithm e ≈12ms, communication time t from edge to cloud c ≈3ms. Total system latency t d ≈27ms < 50ms, which meets the real-time requirements.
[0071] The system successfully issued warnings for two "medium-risk" events (one due to a brief exceedance of the tilt angle caused by excessive instantaneous wind speed, and the other due to a slight fluctuation in the hydraulic system), neither of which developed into an accident. During the two brief network outages, the local caching function of the edge nodes preserved complete warning event data, which was successfully retransmitted to the cloud platform after network recovery. The cloud platform utilized the accumulated historical data and an LSTM neural network model to predict hydraulic pressure trends with an accuracy rate of 92%, providing data support for preventative maintenance.
[0072] As can be seen from the above embodiments, the online safety assessment system for tower crane jacking based on edge computing of the present invention collects physical parameters of key parts of the tower crane in real time through multi-source sensors. The parameters are then processed by Kalman filtering algorithm in the edge computing layer for noise reduction and smoothing, and a safety factor model is constructed using weight coefficients determined by the analytic hierarchy process. Finally, a fuzzy logic algorithm is used to classify the safety status levels, achieving real-time safety assessment of the jacking process. Simultaneously, the edge computing layer has local caching and encrypted communication functions to ensure that critical data is not lost and transmission is secure in the event of network anomalies. The microservice architecture of the cloud platform layer supports data storage, deep learning analysis, and remote monitoring, forming a complete closed loop from data acquisition and edge processing to cloud management, effectively improving the safety and intelligence level of the tower crane during jacking operations.
[0073] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. An online safety status assessment system for tower crane jacking based on edge computing, comprising a terminal sensing layer, an edge computing layer, and a cloud platform layer, characterized in that: The terminal sensing layer includes multiple sensors deployed at key parts of the tower crane to collect physical parameters during the lifting process; the edge computing layer is connected to the terminal sensing layer through industrial embedded devices to perform local real-time processing and safety status assessment of sensor data; the cloud platform layer is used to receive data uploaded by the edge computing layer and perform historical data storage, trend prediction, and remote monitoring.
2. The online safety status assessment system for tower crane jacking based on edge computing according to claim 1, characterized in that: The terminal sensing layer includes at least three of the following: hydraulic cylinder pressure sensor, dual-axis tilt sensor, triaxial vibration acceleration sensor, and laser displacement sensor. Each sensor has an IP67 protection rating, a sampling frequency of not less than 1kHz, and communicates with the edge computing layer via a CAN bus.
3. The online safety status assessment system for tower crane jacking based on edge computing according to claim 1, characterized in that: The edge computing layer includes a data preprocessing module, a security assessment module, and a local early warning module. The data preprocessing module uses a Kalman filter algorithm to denoise and smooth the sensor data. The security assessment module constructs a security coefficient model based on multi-source information fusion technology and combines a fuzzy logic algorithm to perform graded assessment of the security status. The local early warning module triggers a local alarm and uploads abnormal information to the cloud platform when the security coefficient exceeds a preset threshold.
4. The online safety status assessment system for tower crane jacking based on edge computing according to claim 3, characterized in that: The safety factor model is defined as follows: Where P, θ, and a are the real-time pressure, tilt angle, and vibration acceleration, respectively. max θ lim a lim For the corresponding threshold, α, β, and γ are weight coefficients determined by the analytic hierarchy process, and satisfy α + β + γ = 1.
5. The online safety status assessment system for tower crane jacking based on edge computing according to claim 3, characterized in that: The fuzzy logic algorithm divides the security status into three levels: "low risk", "medium risk" and "high risk". It uses the triangular membership function and Mamdani inference method to determine the status and uses the centroid method to defuzzify the output.
6. The online safety status assessment system for tower crane jacking based on edge computing according to claim 1, characterized in that: The edge computing layer has data compression and local caching functions, storing critical data when the network is abnormal and uploading it to the cloud platform after the network is restored.
7. The online safety status assessment system for tower crane jacking based on edge computing according to claim 1, characterized in that: The edge computing layer and the cloud platform layer establish a VPN connection through a 4G / 5G network, use the TLS1.3 protocol for encrypted communication, and use the MQTT protocol to transmit data, supporting QoS1 level message guarantee.
8. The online safety status assessment system for tower crane jacking based on edge computing according to claim 1, characterized in that: The total system delay satisfies: t d =t s +t f +t e +t c <50ms, Among them, t s t is the sampling time. f t is the filtering time. e To evaluate time, t c This refers to the communication time.
9. The online safety status assessment system for tower crane jacking based on edge computing according to claim 1, characterized in that: The cloud platform layer adopts a microservice architecture, including data receiving services, real-time computing services, and web application services, and supports time-series database storage and deep learning frameworks for anomaly diagnosis and trend prediction.
10. A method for online assessment of the safety status of tower crane jacking, characterized in that: The system implementation based on any one of claims 1-9 includes the following steps: S1, Multi-source data acquisition: Through multiple sensors deployed at key parts of the tower crane, the hydraulic cylinder pressure, tower tilt angle, structural vibration acceleration and physical parameters of lifting displacement during the jacking process are collected in real time; S2, edge-side data preprocessing and fusion: Multi-source sensor data is received at the edge computing layer, and Kalman filtering algorithm is used to denoise and smooth the data to filter out process noise and observation noise, and obtain fused high signal-to-noise ratio state data. S3, Real-time safety status assessment: Based on the fused status data, the safety factor S of the current lifting process is calculated according to the predefined safety factor model. Then, the calculated safety factor S is input into the fuzzy logic system. Using the triangular membership function and the fuzzy rule base pre-built by expert knowledge, the system performs comprehensive inference through the Mamdani reasoning method and uses the centroid method for defuzzification, outputting three levels of safety status: "low risk", "medium risk" and "high risk". S4, Local Early Warning and Decision Execution: The security status is compared with the preset threshold in real time. If the status is "low risk", the system is determined to be operating normally. If the status is "medium risk" or "high risk", the local sound and light alarm of the edge computing layer is immediately triggered and a warning is issued to the operator. At the same time, the abnormal status event and related data are formed into a summary information package. S5, Cloud Data Synchronization and Remote Monitoring: The summary information packet is transmitted via 4G / 5G network, encrypted through a VPN tunnel using the TLS1.3 protocol, and then uploaded to the cloud platform layer using the MQTT protocol. After receiving the data, the cloud platform layer stores it in a time-series database and uses a deep learning framework to perform historical trend analysis, anomaly diagnosis and prediction. A monitoring interface is then provided to remote administrators through a web application service.
Citation Information
Cited By
Hoisting equipment fault pre-diagnosis system and method based on multi-source sensor
CN122144609A
