Cloud computing bridge swing early warning equipment

Abstract

The invention discloses cloud computing bridge swing early warning equipment in the technical field of bridge monitoring. The cloud computing bridge swing early warning equipment comprises a sensor layer, a data acquisition layer, a communication layer, a cloud computing layer and an early warning layer. According to the embodiment of the invention, through the multi-source high-precision sensor network, edge-cloud cooperative computing and an adaptive early warning algorithm, real-time monitoring and accurate early warning of bridge swing are realized. The system adopts a modular design, supports multi-protocol communication and elastic expansion, and can be widely applied to structural health monitoring of various bridges.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge monitoring, and in particular to a cloud computing bridge swing early warning device. Background Art

[0002] With the acceleration of urbanization, bridges, as an important part of transportation infrastructure, are receiving increasing attention for their safety. Traditional bridge monitoring methods rely primarily on manual inspections and fixed sensor networks, but these methods suffer from problems such as low monitoring frequency, incomplete data collection, and slow response speed.

[0003] In the existing technology, the commonly used technical means in the field of bridge monitoring include: (1) static monitoring systems based on fixed sensors, which collect data through sensors installed at key parts of the bridge, but the data update frequency is low; (2) visual monitoring systems based on video surveillance, which can intuitively reflect the status of the bridge, but are easily affected by ambient light and weather. Summary of the Invention

[0004] To solve the problem in the prior art that the monitoring results of bridge sway are unstable and easily affected by external environmental and weather factors, the present invention provides a technical solution: a cloud computing bridge sway early warning device, comprising:

[0005] Sensor layer: The sensor layer includes core sensors and auxiliary sensors. The core sensor is a MEMS accelerometer used to collect three-dimensional bridge swing data. The MEMS accelerometer has a range of ±2g and a resolution of 0.001g. The auxiliary sensors include a temperature and humidity sensor with an accuracy of ±2%RH and a wind speed sensor with a range of 0-60m / s for environmental parameter compensation. The sensor layer is installed on both sides of the bridge tower, on both sides of the bridge deck, and at the intersection of the suspension cables and main cables for redundant deployment to ensure data reliability.

[0006] Data acquisition layer: The data acquisition layer receives the current or voltage signal from the sensor layer. The data acquisition layer includes an analog-to-digital conversion module, a digital filtering module, and an edge computing module. The analog-to-digital conversion module is set to a 16-bit ADC with a sampling frequency of 200Hz. The digital filtering module uses Kalman filtering and wavelet denoising algorithms to eliminate environmental noise interference. The edge computing module integrates Kalman filtering and wavelet denoising algorithms to pre-screen valid data and compress transmission to reduce cloud load;

[0007] Communication layer: The communication layer is configured as a wireless transmission module using a multi-mode transmission protocol that supports 4G / 5G and LoRaWAN dual-mode switching, where 4G / 5G is used in real-time mode and LoRaWAN is used in low-power mode;

[0008] Power supply unit: The power supply unit adopts a solar panel with an output power of 20W and a super capacitor with a capacity of 100F to achieve long-term maintenance-free operation;

[0009] Cloud computing layer: This layer adopts a distributed architecture and includes a data processing engine and intelligent analysis model. The data processing engine uses the Apache Kafka real-time stream processing framework and Spark distributed computing cluster. The intelligent analysis model uses an LSTM neural network to dynamically learn bridge swing patterns and set adaptive warning thresholds based on historical data.

[0010] Early warning layer: The pre-tensioning layer is set as a multi-level early warning mechanism, triggering yellow, orange, and red level warnings according to the swing amplitude. It supports SMS, email, and mobile push notifications, integrates GIS maps to locate abnormal locations, and can generate PDF reports containing abnormal frequencies and recommended maintenance measures;

[0011] Housing: The MEMS accelerometer, temperature and humidity compensation sensor, and wind speed sensor are fixed in the housing.

[0012] The beneficial effects achieved by the present invention using the above structure are as follows:

[0013] 1: Multi-source data fusion: Acceleration data is weightedly integrated with temperature, humidity, and wind speed data to eliminate environmental interference (such as false swings caused by wind vibration);

[0014] 2: Adaptive threshold algorithm: Dynamically adjusts the warning threshold based on the prediction results of the LSTM model to avoid false alarms caused by fixed thresholds;

[0015] 3. Modular expansion: sensor nodes support plug-and-play, and the communication protocol is compatible with standards such as MQTT and CoAP, adapting to different bridge requirements;

[0016] 3: Edge-cloud collaboration: Local preprocessing reduces bandwidth usage, and deep analysis on the cloud improves processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 : Logical connection diagram of sensor layer, data acquisition layer, communication layer, cloud computing layer and early warning layer;

[0018] Figure 2 : Schematic diagram of sensor node deployment;

[0019] Figure 3 : Data processing flow chart.

[0020] Description of reference numerals:

[0021] 1: Bridge tower, 2. Bridge deck, 3. Main cable, 301. Suspension cable, 4. Installation point. DETAILED DESCRIPTION

[0022] A cloud computing bridge swing warning device, comprising:

[0023] Sensor layer: The sensor layer includes core sensors and auxiliary sensors. The core sensor is a MEMS accelerometer used to collect three-dimensional bridge swing data. The MEMS accelerometer has a range of ±2g and a resolution of 0.001g. The auxiliary sensors include a temperature and humidity sensor with an accuracy of ±2%RH and a wind speed sensor with a range of 0-60m / s for environmental parameter compensation. The sensor layer is installed on both sides of the bridge tower, on both sides of the bridge deck, and at the intersection of the suspension cables and main cables for redundant deployment to ensure data reliability.

[0024] Data acquisition layer: The data acquisition layer includes an analog-to-digital conversion module, a digital filtering module, and an edge computing module. The analog-to-digital conversion module is set to a 16-bit ADC with a sampling frequency of 200Hz. The digital filtering module uses Kalman filtering and wavelet denoising algorithms to eliminate environmental noise interference. The edge computing module integrates Kalman filtering and wavelet denoising algorithms to pre-screen valid data and compress transmission to reduce cloud load;

[0025] Communication layer: The communication layer adopts a multi-mode transmission protocol that supports 4G / 5G and LoRaWAN dual-mode switching, where 4G / 5G is used in real-time mode and LoRaWAN is used in low-power mode;

[0026] Power supply unit: The power supply unit adopts a solar panel with an output power of 20W and a super capacitor with a capacity of 100F to achieve long-term maintenance-free operation;

[0027] Cloud computing layer: This layer adopts a distributed architecture and includes a data processing engine and intelligent analysis model. The data processing engine uses the Apache Kafka real-time stream processing framework and Spark distributed computing cluster. The intelligent analysis model uses an LSTM neural network to dynamically learn bridge swing patterns and set adaptive warning thresholds based on historical data.

[0028] Early warning layer: The pre-tensioning layer is set as a multi-level early warning mechanism, which triggers yellow, orange and red level warnings according to the swing amplitude, supports SMS, email and mobile push, integrates GIS map to locate the abnormal position, and can generate a PDF report containing abnormal frequency and recommended maintenance measures.

[0029] When the present invention is used

[0030] 1. Hardware deployment

[0031] Sensor clusters are installed on both sides of the bridge tower, on both sides of the bridge deck, and at the intersection of the suspension cables and the main cables. Each node contains a MEMS accelerometer, a temperature and humidity sensor, and a wind speed sensor.

[0032] The sensor housing adopts IP67 protection grade, and integrates solar power supply module and super capacitor inside, which can adapt to the working environment of -40℃ to 85℃.

[0033] 2. Data processing flow

[0034] Step 1: Sensor data is converted by a 16-bit ADC and uploaded to the edge gateway via LoRaWAN.

[0035] Step 2: The edge gateway performs Kalman filtering (to eliminate random noise) and wavelet denoising (to suppress high-frequency interference), extracts valid data, and compresses it into JSON format.

[0036] Step 3: After receiving the data stream, the cloud platform uses FFT frequency domain analysis to extract the main frequency of the swing and combines it with time domain integration to calculate the displacement amplitude;

[0037] Step 4: The LSTM model predicts the swing trend based on historical data and dynamically adjusts the warning threshold;

[0038] Step 5: When real-time data exceeds the threshold, a multi-level warning is triggered and a diagnostic report is generated.

[0039] 3. System compatibility

[0040] Provides a RESTful API interface to support data exchange with third-party monitoring platforms (such as bridge management systems and emergency command platforms);

[0041] The cloud computing platform adopts the Kubernetes containerized architecture, supports elastic expansion on demand, and can monitor more than 1,000 bridges simultaneously.

[0042] The above description of the present invention and its embodiments is non-limiting. In short, if a person skilled in the art is inspired by the above description and designs a similar structure and embodiment to the technical solution without departing from the purpose of the present invention, they should fall within the scope of protection of the present invention.

Claims

1. A cloud computing bridge swing warning device, characterized in that: include: Sensor layer: composed of multiple types of high-precision sensors, including MEMS accelerometers, temperature and humidity compensation sensors, and wind speed sensors, used to collect bridge swing data and environmental parameters; Data acquisition layer: includes analog-to-digital conversion module and digital filtering module, which are used to receive current or voltage signals from the sensor layer. The digital filtering module uses Kalman filtering and wavelet denoising algorithm to eliminate environmental noise interference; Communication layer: supports multi-mode wireless transmission protocols (4G / 5G / LoRaWAN) and integrates a dynamic power management module to extend device battery life; Cloud computing layer: This layer uses a distributed architecture, including a real-time stream processing unit (Apache Kafka) and a data analysis engine (Spark). It also deploys an LSTM neural network model for bridge sway trend prediction. Early warning layer: Generates multi-level early warning signals based on dynamic threshold algorithms, supports SMS, email, and mobile push, and integrates GIS maps to locate abnormal locations; Housing: The MEMS accelerometer, temperature and humidity compensation sensor, and wind speed sensor are fixed in the housing.

2. The device according to claim 1, characterized in that The MEMS accelerometer range of the sensor layer is ±2g and the resolution is 0.001g. The sensor nodes are deployed redundantly and are distributed on the upper and lower sides of the bridge tower, on both sides of the bridge deck, and at the intersection of the suspension cables and main cables.

3. The device according to claim 1, characterized in that The data collection layer further includes an edge computing module for pre-screening key data locally and compressing transmission to reduce the cloud load.

4. The device according to claim 1, characterized in that The dynamic threshold algorithm of the cloud computing layer adaptively adjusts the warning threshold through historical data training and real-time analysis, and cross-checks with multi-sensor data to reduce the false alarm rate.

5. The device according to claim 1, characterized in that The wireless transmission module of the communication layer supports LoRaWAN and 5G dual-mode switching, and has a built-in solar power supply unit and supercapacitor energy storage module to achieve long-term maintenance-free operation.

6. The device according to claim 1, characterized in that The early warning module further generates a diagnostic report, including swing amplitude, frequency anomalies and recommended treatment measures, and communicates with a third-party monitoring platform through a standardized API interface.

7. The device according to claim 1, characterized in that The sensor node adopts a modular design, supports plug-and-play expansion, and has an IP67 packaging protection level, making it suitable for deployment in harsh environments.

8. The device according to claim 1, characterized in that The cloud computing platform adopts a containerized microservice architecture, supports elastic expansion and distributed storage, and can adapt to the monitoring needs of bridges of different sizes.

Images