An inland river container operation state monitoring system

Abstract

The utility model discloses an inland river container operation state monitoring system relates to inland river container technical field, include: cloud end server and with the edge calculation module of cloud end server information interaction, the cloud end server is inlayed 3D modeling engine, and edge calculation module is configured in container, and container is also equipped with: the box door monitoring module is used for real -time acquisition box door operation state and is transmitted to edge calculation module. Advantageous effect: through cloud end server built -in 3D modeling engine generation goods stereoscopic grid model, in the web end dynamic display goods contour change, solve traditional two -dimensional image and can not visually present goods deformation problem, be convenient for the owner real -time grasp goods stacking state, and simultaneously box door monitoring module real -time acquisition box door opening and closing state, can effectively prevent goods theft and illegal tampering, movement monitoring module accurate perception container vibration, tilt and other motion parameters, identify the risk of rollover in advance.

Description

Technical Field

[0001] This utility model relates to the field of inland waterway container technology, and more specifically, to an inland waterway container operation status monitoring system. Background Technology

[0002] In the inland waterway container shipping sector, containers serve as the core carrier of cargo transportation, and real-time monitoring of their operational status is crucial for ensuring cargo safety, improving transportation efficiency, and optimizing dispatch management. However, existing monitoring methods for inland waterway containers have significant shortcomings:

[0003] On the one hand, traditional monitoring systems have limited functionality, only able to monitor basic positioning or environmental parameters (such as temperature and humidity), and cannot comprehensively monitor the three-dimensional outline of goods inside containers, the opening and closing status of container doors, and the movement posture (such as vibration and tilt) during transportation. This makes it difficult to meet the needs of high-value goods (such as precision instruments and fresh products) for transportation safety and visual management.

[0004] On the other hand, data processing and early warning mechanisms are lagging behind. Existing systems mostly use single sensors to collect data, lacking the ability to fuse and process multi-source data, and rely on manual analysis to judge abnormal states. This makes it difficult to detect potential risks such as unauthorized opening of container doors or severe vibrations during transportation in a timely manner, which can easily lead to problems such as cargo damage, loss, or environmental anomalies. In addition, the cargo status display in traditional solutions is mostly two-dimensional planar images, which cannot intuitively present the real-time three-dimensional distribution and deformation of cargo inside the container, making it difficult for cargo owners or regulatory authorities to quickly grasp the dynamics of the cargo.

[0005] No effective solutions have yet been proposed to address the problems in the relevant technologies. Utility Model Content

[0006] In view of the problems in related technologies, the purpose of this utility model is to propose an inland waterway container operation status monitoring system to overcome the above-mentioned technical problems existing in the existing related technologies.

[0007] The technical solution of this utility model is implemented as follows:

[0008] An inland waterway container operation status monitoring system includes: a cloud server and an edge computing module that interacts with the cloud server; the cloud server has an embedded 3D modeling engine, and the edge computing module is configured inside the container; the container also contains:

[0009] The door monitoring module is used to collect the door's operating status in real time and transmit it to the edge computing module;

[0010] The motion monitoring module is used to monitor the motion status of the container in real time and transmit it to the edge computing module;

[0011] The visual perception module includes several ultra-wide-angle miniature cameras and a ToF depth sensor configured inside the container. The ultra-wide-angle miniature cameras are evenly deployed at preset positions on the top of the container to collect multi-view images of the cargo and transmit them to the edge computing module. The ToF depth sensor is deployed at symmetrical positions on the top and bottom of the container to measure the distance between various points on the cargo surface to obtain three-dimensional coordinate data and transmit it to the edge computing module.

[0012] The door monitoring module, the motion monitoring module, and the visual perception module are electrically connected to the edge computing module. The edge computing module is used to process data and transmit it to the cloud server. The cloud server is used to generate a three-dimensional mesh model of the cargo based on the data and realize dynamic display, while setting a preset threshold for status warning.

[0013] Furthermore, the container is also equipped with an environmental monitoring module, which is used to collect environmental information inside the container in real time and transmit it to the edge computing module. The environmental monitoring module includes a temperature sensor, a humidity sensor, and an oxygen content sensor.

[0014] Furthermore, the temperature sensor and humidity sensor are SHT31-D integrated temperature and humidity sensors, and the oxygen content sensor is a MembraporO2-A4 oxygen sensor.

[0015] Furthermore, a positioning module is also installed inside the container to collect real-time location information inside the container and transmit it to the edge computing module.

[0016] Furthermore, the container is also equipped with a power supply, which supplies power to the edge computing module, the container door monitoring module, the motion monitoring module, the visual perception module, the environmental monitoring module, and the positioning module.

[0017] Furthermore, the power source includes a 12V / 20Ah rechargeable lithium battery pack and a solar charging panel.

[0018] Furthermore, the door monitoring module is an OMROND4GL-4C magnetic switch with an operating distance of 15mm.

[0019] The beneficial effects of this utility model are:

[0020] This invention utilizes a door monitoring module to collect real-time data on the opening and closing status of container doors, effectively preventing cargo theft and unauthorized alteration. A motion monitoring module accurately senses container vibration, tilt, and other motion parameters, triggering a cloud server motion warning when acceleration exceeds 3g or tilt angle exceeds 15°, thus identifying the risk of tipping over in advance. An environmental monitoring module monitors temperature, humidity, and oxygen content in real time, and when thresholds are exceeded, it links with a dispatch system to plan emergency routes, ensuring the safe transport of sensitive goods such as pharmaceuticals and fresh produce. Simultaneously, a visual perception module collects multi-view images using ultra-wide-angle miniature cameras evenly deployed on the top, combined with ToF depth sensors symmetrically installed on the top and bottom to obtain three-dimensional coordinate data of the cargo surface. After preprocessing by an edge computing module, a 3D modeling engine built into the cloud server generates a three-dimensional mesh model of the cargo using a triangulation algorithm, dynamically displaying the cargo outline changes on the web, solving the problem that traditional two-dimensional images cannot intuitively present cargo deformation, and facilitating real-time monitoring of cargo stacking status by cargo owners.

[0021] In addition, to achieve multi-source data fusion and intelligent early warning, and improve the efficiency of anomaly response, the edge computing module integrates door status, motion parameters, environmental data and visual information through the central data bus. After performing lightweight preprocessing, it is encapsulated into TCP / IP data packets in JSON format and transmitted to the cloud server via TLS / SSL encryption. The cloud has preset multiple threshold rules to trigger audible and visual alarms and mark abnormal locations on the map in a short time, distinguishing between legitimate inspections and illegal intrusions, and reducing the cost of manual verification.

[0022] Other features and advantages of this invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objectives and other advantages of this invention are realized and obtained through the structures particularly pointed out in the description and the accompanying drawings.

[0023] To make the above-mentioned objectives, features and advantages of this utility model more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this utility model or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this utility model. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the inland waterway container operation status monitoring system according to an embodiment of the present utility model.

[0026] In the picture:

[0027] 1. Cloud server; 2. Edge computing module; 3. Door monitoring module; 4. Motion monitoring module; 5. Visual perception module; 6. Environmental monitoring module; 7. Positioning module; 8. Power supply;

[0028] 51. Ultra-wide-angle miniature camera; 52. ToF depth sensor. Detailed Implementation

[0029] The technical solutions of the present utility model will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present utility model, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present utility model are within the protection scope of the present utility model.

[0030] According to an embodiment of the present invention, an inland waterway container operation status monitoring system is provided.

[0031] like Figure 1 As shown, an inland waterway container operation status monitoring system includes: a cloud server 1 and an edge computing module 2 that interacts with the cloud server 1. The cloud server 1 has an embedded 3D modeling engine, and the edge computing module 2 is configured inside the container. The container is also equipped with a door monitoring module 3, a motion monitoring module 4, and a visual perception module 5. The door monitoring module 3, the motion monitoring module 4, and the visual perception module 5 are electrically connected to the edge computing module 2. The visual perception module 5 includes several ultra-wide-angle miniature cameras 51 and a ToF depth sensor 52 configured inside the container.

[0032] The door monitoring module 3 is used to collect the door's operating status in real time and transmit it to the edge computing module 2;

[0033] Among them, the door monitoring module 3 can use the OMROND4GL-4C magnetic switch, which has high reliability and long life, and the action distance can reach 15mm. It can stably detect the opening and closing status of the door and effectively prevent theft and illegal tampering of goods.

[0034] Motion monitoring module 4 is used to monitor the motion status of the container in real time and transmit it to edge computing module 2;

[0035] Among them, the motion monitoring module 4 can use a combination of MPU6050 six-axis accelerometer and gyroscope sensor. The acceleration measurement range can be selected as ±2g, ±4g, ±8g, ±16g, and the gyroscope measurement range can be selected as ±250dps, ±500dps, ±1000dps, ±2000dps. It can accurately sense the motion status of the container and assist in the analysis of transportation stability.

[0036] Several ultra-wide-angle miniature cameras 51 are evenly deployed at preset positions on the top of the container to collect multi-view images of the goods inside the container and transmit them to the edge computing module 2;

[0037] Several ToF depth sensors 52 are deployed symmetrically on the top and bottom of the container to measure the distance between each point on the cargo surface and the sensor, acquire three-dimensional coordinate data and transmit it to the edge computing module 2;

[0038] Specifically, the ultra-wide-angle miniature camera 51 can be equipped with a Hikvision DS-2CD3T47WD-L camera, which features 1080P resolution, a 180° ultra-wide-angle fisheye lens, and infrared fill light function. It can meet the monitoring needs of 95% of the space inside the container and can also provide clear imaging in low light conditions.

[0039] Meanwhile, the ToF depth sensor 52 can use an Intel RealSense D435i depth camera, with a measurement accuracy of up to 1mm at close range and maintaining high accuracy at long range. It is equipped with 4 depth sensors to meet the needs of acquiring three-dimensional coordinate data of cargo.

[0040] Edge computing module 2 is used to process the collected data and transmit it to cloud server 1;

[0041] The edge computing module 2 utilizes the NVIDIA Jetson Nano development kit, equipped with an NVIDIA Maxwell architecture GPU featuring 128 CUDA cores and 4GB of LPDDR4 memory. It can efficiently run Gaussian filtering, SIFT feature extraction, and binocular stereo vision algorithms, enabling real-time preprocessing of image and depth data. Simultaneously, it receives raw data in real-time from the environmental monitoring module (temperature / humidity / oxygen content), the door monitoring module (open / closed status), and the motion monitoring module (acceleration data) via a central data bus. This raw data undergoes lightweight preprocessing, and the preprocessed structured data (.JSON format) is encapsulated into TCP / IP packets and transmitted to the cloud server via a TLS / SSL encrypted channel, ensuring secure data transmission.

[0042] Cloud server 1 is used to receive data from edge computing module 2 and generate a three-dimensional mesh model of the cargo based on the 3D modeling engine to realize the dynamic display of the cargo's three-dimensional outline. It also presets thresholds and provides status warnings based on the data collected by the door monitoring module 3 and motion monitoring module 4.

[0043] The container is also equipped with an environmental monitoring module 6, which is used to collect environmental information inside the container in real time and transmit it to the edge computing module 2. The environmental monitoring module 6 includes a temperature sensor, a humidity sensor and an oxygen content sensor.

[0044] Specifically, in application, the SHT31-D integrated temperature and humidity sensor can be used for both temperature and humidity. It offers a temperature measurement accuracy of ±0.3℃ within the range of -40℃ to 125℃, and a humidity measurement accuracy of ±2%RH within the range of 20% to 80%RH. It features fast response, strong anti-interference capabilities, and is suitable for monitoring changes in temperature and humidity within containers. The MembraporO2-A4 oxygen sensor can be used for oxygen content measurement, with a measurement range of 0-25% VOL and an accuracy of ±0.1%. Utilizing electrochemical principles, it accurately detects the oxygen content within containers, ensuring the safe storage of goods.

[0045] The container is also equipped with a positioning module 7, which is used to collect the location information inside the container in real time and transmit it to the edge computing module 2.

[0046] Specifically, the positioning module 7 can be a u-bloxNEO-M8N, which has high-sensitivity GPS receiving capability, positioning accuracy of up to 2.5 meters CEP, supports multi-constellation positioning such as GPS, GLONASS, Galileo, and Beidou, and can adapt to complex inland waterway environments to stably obtain the geographical location and driving trajectory of containers.

[0047] In addition, the container is equipped with a power supply 8, which supplies power to the edge computing module 2, the door monitoring module 3, the motion monitoring module 4, the visual perception module 5, the environmental monitoring module 6, and the positioning module 7.

[0048] In this technical solution, the power supply 8 uses a 12V / 20Ah rechargeable lithium battery pack combined with a solar charging panel to provide continuous power to each module. When there is sufficient sunlight, the solar panel prioritizes power supply and charges the battery; in low-light conditions, the lithium battery pack automatically switches power supply to ensure the system can operate stably for ≥72 hours without an external power source.

[0049] Specifically, for the aforementioned cloud server 1, a built-in 3D modeling engine generates a 3D mesh model of the cargo based on the received point cloud data and multi-view images using a triangulation algorithm. The changes in the cargo's outline are then dynamically visualized on the web interface. Multiple preset threshold rules are also included, as follows:

[0050] Among them, motion warning: when the acceleration is greater than 3g or the tilt angle is greater than 15°, it is judged as a risk of severe vibration or rollover, triggering an audible and visual alarm and marking the abnormal location on the map.

[0051] Among them, environmental early warning: when the temperature, humidity and oxygen content exceed the threshold, an alarm message is immediately pushed to the administrator terminal, and the dispatch system is linked to plan an emergency route.

[0052] Among them, abnormal door tracing: storage cabinet door opening and closing logs, combined with camera-captured images and location data, generate an opening event timeline for suppliers or regulatory authorities to verify, such as distinguishing between legitimate inspections and illegal intrusions.

[0053] In application, if an abnormal temperature and humidity alarm is triggered, the environmental monitoring module detects that the temperature inside the container exceeds a preset threshold of 30°C for pharmaceutical transportation. The edge computing unit immediately packages and transmits the real-time temperature data and sensor location information to the cloud server 1. After receiving the data, the cloud server 1 triggers a push alarm within 3 seconds and marks the location of the abnormal container on the web interface. At the same time, it coordinates with the dispatch system to arrange for the nearest vehicle to handle the situation.

[0054] In addition, if the container door is abnormally opened, the container door monitoring module detects the opening event, such as when the OMROND4GL-4C magnetic switch changes from "closed" to "open". The edge computing unit records the opening time and duration and transmits it to the cloud server 1 for storage. The cargo owner or customs can query the container door operation log through the web interface and combine it with the historical image data of the visual perception module to verify whether it is a legitimate opening, such as customs inspection records, thus reducing the cost of manual inspection.

[0055] In summary, the following effects can be achieved by utilizing the above-described technical solution of this utility model:

[0056] This invention utilizes a door monitoring module 3 to collect real-time data on the opening and closing status of the container doors, effectively preventing cargo theft and illegal tampering. A motion monitoring module 4 accurately senses container vibration, tilt, and other motion parameters. When acceleration exceeds 3g or tilt angle exceeds 15°, a motion warning is triggered on the cloud server 1, identifying the risk of tipping over in advance. An environmental monitoring module 6 monitors temperature, humidity, and oxygen content in real time. When thresholds are exceeded, it links with a scheduling system to plan emergency routes, ensuring the safe transport of sensitive goods such as medicines and fresh produce. Simultaneously, a visual perception module 5 collects multi-view images using ultra-wide-angle miniature cameras 51 evenly deployed on the top, combined with ToF depth sensors 52 symmetrically installed on the top and bottom to obtain three-dimensional coordinate data of the cargo surface. After preprocessing by the edge computing module 2, the cloud server 1's built-in 3D modeling engine generates a three-dimensional mesh model of the cargo using a triangulation algorithm, dynamically displaying the cargo outline changes on the web, solving the problem that traditional two-dimensional images cannot intuitively present cargo deformation, and facilitating real-time monitoring of cargo stacking status by cargo owners.

[0057] In addition, to achieve multi-source data fusion and intelligent early warning, and improve the efficiency of anomaly response, the edge computing module 2 integrates the door status, motion parameters, environmental data and visual information through the central data bus. After performing lightweight preprocessing, it is encapsulated into TCP / IP data packets in JSON format and transmitted to the cloud server 1 through TLS / SSL encryption. The cloud has preset multiple threshold rules to trigger audible and visual alarms and mark the abnormal locations on the map in a short time, distinguishing between legitimate inspections and illegal intrusions, and reducing the cost of manual verification.

[0058] The above are merely preferred embodiments of the present utility model and are not intended to limit the present utility model. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present utility model shall be included within the protection scope of the present utility model.

Claims

1. An inland waterway container operation status monitoring system, comprising: A cloud server (1) and an edge computing module (2) that interacts with the cloud server (1), wherein the cloud server (1) has an embedded 3D modeling engine, and the edge computing module (2) is configured inside the container, characterized in that the container is further provided with: The door monitoring module (3) is used to collect the door operating status in real time and transmit it to the edge computing module (2); The motion monitoring module (4) is used to monitor the motion status of the container in real time and transmit it to the edge computing module (2); The visual perception module (5) includes several ultra-wide-angle miniature cameras (51) and ToF depth sensors (52) configured inside the container. The ultra-wide-angle miniature cameras (51) are evenly deployed at preset positions on the top of the container to collect multi-view images of the cargo and transmit them to the edge computing module (2). The ToF depth sensors (52) are deployed at symmetrical positions on the top and bottom of the container to measure the distance between points on the surface of the cargo to obtain three-dimensional coordinate data and transmit it to the edge computing module (2). The door monitoring module (3), the motion monitoring module (4) and the visual perception module (5) are electrically connected to the edge computing module (2) respectively. The edge computing module (2) is used to process data and transmit it to the cloud server (1). The cloud server (1) is used to generate a three-dimensional mesh model of the cargo based on the data and realize dynamic display, while setting a threshold for status warning.

2. The inland waterway container operation status monitoring system according to claim 1, characterized in that, The container is also equipped with an environmental monitoring module (6) for collecting environmental information inside the container in real time and transmitting it to the edge computing module (2). The environmental monitoring module (6) includes a temperature sensor, a humidity sensor and an oxygen content sensor.

3. The inland waterway container operation status monitoring system according to claim 2, characterized in that, The temperature sensor and humidity sensor are SHT31-D integrated temperature and humidity sensors, and the oxygen content sensor is a MembraporO2-A4 oxygen sensor.

4. The inland waterway container operation status monitoring system according to claim 2, characterized in that, The container is also equipped with a positioning module (7) for collecting real-time location information inside the container and transmitting it to the edge computing module (2).

5. The inland waterway container operation status monitoring system according to claim 4, characterized in that, The container is also equipped with a power supply (8), which is used to supply power to the edge computing module (2), the door monitoring module (3), the motion monitoring module (4), the visual perception module (5), the environmental monitoring module (6) and the positioning module (7).

6. The inland waterway container operation status monitoring system according to claim 5, characterized in that, The power source (8) includes a 12V / 20Ah rechargeable lithium battery pack and a solar charging panel.

7. The inland waterway container operation status monitoring system according to claim 1, characterized in that, The door monitoring module (3) is an OMROND4GL-4C magnetic switch with an operating distance of 15mm.

Images