Liquid ammonia loading and unloading management and control system, method and equipment based on AI identification and man-vehicle positioning

Abstract

The invention relates to a liquid ammonia loading and unloading management and control system, method and equipment based on AI identification and man-vehicle positioning. The system comprises: an AI visual identification module used for constructing a face identification model by using a deep learning algorithm and a man-vehicle positioning technology, collecting authentication information and position information of a safety officer by using the AI face identification model, and collecting an operation state of liquid ammonia loading and unloading and position information of each device by using a video capture device; the data fusion module is used for uniformly labeling the position information with the equipment position information and the operation state to generate a management and control data set; and the decision early warning module is used for carrying out potential safety hazard training on the management and control data set according to the operation state and the safety operation mechanism, outputting a safety prediction result, generating an early warning scheme and uploading the early warning scheme to the central server. And the monitoring module is used for calling the security officer closest to the position of the security problem. By adopting the method, the safety and hidden danger elimination efficiency in the liquid ammonia loading and unloading operation process can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of liquid ammonia loading and unloading control, and in particular to a liquid ammonia loading and unloading control system, method and equipment based on AI recognition and human-vehicle positioning. Background Art

[0002] Liquid ammonia is an important industrial raw material and is widely used in chemical, agricultural and other fields. However, due to the corrosive and volatile characteristics of liquid ammonia, its transportation and storage process must strictly follow safety regulations to prevent accidents such as leakage, fire and explosion. Therefore, liquid ammonia unloading is a complex process involving multiple safety links.

[0003] At present, most liquid ammonia unloading operations still rely on manual operation and management, which has many problems: 1. Irregular operation process: There are no specific laws and regulations to constrain the liquid ammonia unloading process, resulting in a high probability of accidents. 2. Safety hazards: There is a possibility of omissions in manual inspection, especially for some hidden safety hazards, such as small cracks in the pipeline, valves not completely closed, etc., manual inspection is difficult to be 100% accurate. 3. Inefficiency: Each step requires manual confirmation, which is not only time-consuming, but also increases the workload of operators. 4. Human error: Operators are prone to fatigue during long hours of work, and may make operational errors due to negligence. 5. Lack of real-time monitoring: Traditional operation modes are difficult to achieve real-time monitoring. Once an abnormal situation occurs, it is often not discovered and handled in time. With the development of artificial intelligence (AI) and Internet of Things (IoT) technologies, more and more companies are beginning to explore the use of new technologies to improve the safety and efficiency of operations. AI visual recognition technology can be used to automatically detect various safety factors, such as personnel identity verification, equipment status inspection, etc.; human and vehicle positioning technology can optimize the operation process and prevent accidents through precise location information.

[0004] Although AI visual recognition and human-vehicle positioning technologies have been applied in many fields, in the specific scenario of liquid ammonia unloading, it is still necessary to specially design a model with strong adaptability and high precision to meet the special requirements of liquid ammonia unloading operations and improve the safety and efficiency of operations. Summary of the invention

[0005] Based on this, it is necessary to provide a liquid ammonia loading and unloading control system, method and equipment based on AI recognition and human and vehicle positioning, which can improve the safety and early warning efficiency of liquid ammonia loading and unloading operations in response to the above-mentioned technical problems.

[0006] A liquid ammonia loading and unloading control system based on AI recognition and human-vehicle positioning, the system comprising: a central server, a liquid ammonia loading and unloading control subsystem and a safety officer terminal; wherein the liquid ammonia loading and unloading control subsystem comprises: an AI visual recognition module, a data fusion module, a decision-making and early warning module and a monitoring module;

[0007] The AI ​​visual recognition module is used to build a face recognition model using a deep learning algorithm and human-vehicle positioning technology, collect the authentication information and location information of the safety officer using the AI ​​face recognition model, and collect the operation status of liquid ammonia loading and unloading and the device location information of the relevant operating equipment corresponding to each operation status using a video capture device;

[0008] The data fusion module is used to perform unified data annotation and fusion on the location information, the equipment location information and the operation status according to the authentication information to generate a control data set, and to process the control data set within a preset safety range corresponding to the relevant operating equipment according to the data transmitted by the AI ​​visual recognition module and the monitoring module, so that the decision-making and early warning module performs safety hazard training according to the received control data set;

[0009] The decision-making and early warning module is used to perform safety hazard training on the received control data set according to the operation status and the safe operation mechanism, output a safety prediction result, generate an early warning plan according to the safety prediction result, and upload the early warning plan to the central server;

[0010] The monitoring module is used to call the nearest safety officer to the location of the safety problem to handle the fault according to the early warning scheme and the authentication information collected by the AI ​​visual recognition module, the location information, the device location information, and the safety range corresponding to the device location information;

[0011] The liquid ammonia loading and unloading control subsystem is communicated with the safety officer terminal through the central server.

[0012] A liquid ammonia loading and unloading control method based on AI recognition and human-vehicle positioning, the method comprising:

[0013] Based on AI recognition and human-vehicle positioning technology, the operation status information and safety officer authentication information of the liquid ammonia loading and unloading operation are obtained; wherein the operation status information includes the equipment safety status information corresponding to each operating device during the liquid ammonia loading and unloading operation, and the authentication information includes the location information and work authority information of the safety officer;

[0014] In the preparation stage for unloading the liquid ammonia tank, the relative position relationship between the safe operation area corresponding to the operating equipment and the position information is verified according to the work authority information, so that the safety officer can perform the liquid ammonia tank unloading operation on the operating equipment within the relative position relationship;

[0015] During the liquid ammonia tank unloading operation phase, a data fusion module is used to perform safety prediction analysis on the operation process of each of the operating devices according to the equipment safety status information and the relative position relationship to obtain a safety hazard data set, and the safety hazard data set is uploaded to the central server;

[0016] When the unloading of the liquid ammonia tank is completed, the monitoring and early warning module performs a safety check on the safety hazard data set transmitted by the central server according to the safety measures mechanism, obtains the inspection result and the equipment problem status information corresponding to the inspection result, and calls the safety officer to correct the safety hazard according to the relative position relationship between the equipment problem status information and the location information.

[0017] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0018] Based on AI recognition and human-vehicle positioning technology, the operation status information and safety officer authentication information of the liquid ammonia loading and unloading operation are obtained; wherein the operation status information includes the equipment safety status information corresponding to each operating device during the liquid ammonia loading and unloading operation, and the authentication information includes the location information and work authority information of the safety officer;

[0019] In the preparation stage for unloading the liquid ammonia tank, the relative position relationship between the safe operation area corresponding to the operating equipment and the position information is verified according to the work authority information, so that the safety officer can perform the liquid ammonia tank unloading operation on the operating equipment within the relative position relationship;

[0020] During the liquid ammonia tank unloading operation phase, a data fusion module is used to perform safety prediction analysis on the operation process of each of the operating devices according to the equipment safety status information and the relative position relationship to obtain a safety hazard data set, and the safety hazard data set is uploaded to the central server;

[0021] When the unloading of the liquid ammonia tank is completed, the monitoring and early warning module performs a safety check on the safety hazard data set transmitted by the central server according to the safety measures mechanism, obtains the inspection result and the equipment problem status information corresponding to the inspection result, and calls the safety officer to correct the safety hazard according to the relative position relationship between the equipment problem status information and the location information.

[0022] The above-mentioned liquid ammonia loading and unloading control system, method and equipment based on AI recognition and human-vehicle positioning automatically detect and verify various operations through AI visual analysis technology, reducing safety hazards caused by human factors. Human-vehicle positioning technology is used to track the location of operators and vehicles in real time to ensure the accuracy and safety of the location during the operation. The system can summarize the data of each operation link, automatically identify potential safety hazards, and issue corresponding warnings at different times to prevent accidents. Through automation technology, it reduces dependence on human resources and reduces labor costs. Through preventive measures, the possibility of accidents is reduced, and the direct and indirect economic losses caused by accidents are reduced. The system automatically records various data during the operation, including the behavior of operators, equipment status, environmental conditions, etc. Use big data analysis technology to deeply mine historical data, provide a reference basis for future operations, and continuously optimize system performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the framework of a liquid ammonia loading and unloading control system based on AI recognition and human and vehicle positioning in one embodiment;

[0024] Figure 2 It is a flow chart of a liquid ammonia loading and unloading control method based on AI recognition and human-vehicle positioning in one embodiment;

[0025] Figure 3 A schematic diagram of a process of liquid ammonia unloading operation based on AI recognition and human-vehicle positioning in one embodiment;

[0026] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0028] In one embodiment, Figure 1 As shown, a liquid ammonia loading and unloading control system based on AI recognition and human-vehicle positioning is provided, including: a central server 102, a liquid ammonia loading and unloading control subsystem 104 and a safety officer terminal 106. Among them, the liquid ammonia loading and unloading control subsystem 104 includes: an AI visual recognition module 10402, a data fusion module 10404, a decision warning module 10406 ​​and a monitoring module 10408.

[0029] The AI ​​visual recognition module 10402 is used to build a face recognition model using deep learning algorithms and human-vehicle positioning technology, use the AI ​​face recognition model to collect the authentication information and location information of the safety officer, and use the video capture device to collect the operating status of liquid ammonia loading and unloading and the equipment location information of the relevant operating equipment corresponding to each operating status.

[0030] The data fusion module 10404 is used to unify the data annotation and integration of the location information with the equipment location information and the operation status according to the authentication information to generate a control data set, and to process the control data set within a preset safety range corresponding to the relevant operating equipment according to the data transmitted by the AI ​​visual recognition module and the monitoring module, so that the decision-making and early warning module can perform safety hazard training according to the received control data set.

[0031] The decision-making and early warning module 10406 ​​is used to perform safety hazard training on the received control data set according to the operation status and safe operation mechanism, output the safety prediction results, generate an early warning plan according to the safety prediction results, and upload the early warning plan to the central server.

[0032] The monitoring module 10408 is used to call the safety officer closest to the location of the safety problem to handle the fault according to the authentication information, location information, device location information collected by the early warning plan and the AI ​​visual recognition module, and the safety range corresponding to the device location information.

[0033] The liquid ammonia loading and unloading control subsystem 104 is linked to the safety officer terminal 106 through the central server 102 for communication.

[0034] In one of the embodiments, the AI ​​visual recognition module 10402 is also used to achieve real-time monitoring and intelligent analysis of each link in the liquid ammonia unloading process through image processing and deep learning technology. For example, in order to determine the unity of person and certificate in operator identity authentication, it is necessary to capture the operator's facial image through a camera, and use facial recognition technology to verify his identity to ensure that only authorized personnel can enter the operation area; in the process of wearing personal protective equipment detection, image processing technology is used to identify whether the operator is wearing the prescribed personal protective equipment to ensure that he operates under safe conditions; when verifying the liquid level of the storage tank, AI visual analysis is used to use the camera to capture the image of the inside of the storage tank, and the image processing technology is used to identify the liquid level in the storage tank; when checking the vehicle's emergency shut-off valve, the camera is used to capture the image of the emergency shut-off valve, and its status (open or closed) is identified through image processing technology; during loading and unloading operations, the camera is used to capture the image of the vehicle's grounding wire, and the image processing technology is used to identify its status (open or closed); Image processing technology is used to identify whether the electrostatic clamp is connected to the vehicle (whether it is grounded); a camera is used to capture images of the crane connection, and its connection status (connected or not) is identified through computer vision using edge detection, template matching and other image processing technologies; a camera is used to capture images of the leak test site, and the state of the soap bubble is visually identified to determine whether there is a leak at the connection of the universal pipe; a camera is used to capture images of the on-site signboard, and image processing technology is used to identify whether a plate block, triangular cone, etc. is placed in front of the vehicle; a camera is used to capture images of the ground around the vehicle, and image processing technology is used to identify whether anti-slip pads are placed under the loading and unloading vehicle; after the loading and unloading operation, the liquid level is verified again, and combined with the personnel positioning information to ensure that the operator conducts on-site acceptance.

[0035] In one embodiment, the data fusion module 10404 is also used to integrate and process the AI ​​visual recognition results with the personnel positioning information. For example, when judging the unity of person and certificate, the face recognition result is associated with the positioning data to ensure that only authorized personnel can enter the designated area and record their location information; when verifying the tank level, the tank level data is combined with the operator's location information to ensure that the operator observes the tank level in a safe position; when checking the vehicle emergency shut-off valve, the location of the operator and the vehicle is confirmed by positioning technology, and combined with the AI ​​visual analysis results to ensure that the shut-off valve is correctly operated in the correct position; when judging whether the personnel wear personal protective equipment, the wearing of personal protective equipment is combined with the operator's location information to ensure that the operator wears personal protective equipment within the prescribed operating range; during the loading and unloading operation, when judging the vehicle's electrostatic grounding, crane pipe connection, leak test, inspection of no-entry signs, and inspection of anti-slip pads, the vehicle's location is confirmed by positioning technology, and combined with the AI ​​visual analysis results to ensure that the vehicle is parked in the correct position; after the loading and unloading operation, the personnel positioning and AI visual recognition are combined again to ensure that the operator wears the protective equipment correctly and conducts on-site acceptance.

[0036] In one of the embodiments, the decision-making warning module 10406 ​​is also used for comprehensive warning analysis, which comprehensively analyzes the data collected by the monitoring module to identify potential safety hazards; dynamic warning, dynamic warning based on real-time data to ensure that preventive measures are taken before an accident occurs. For example, when the liquid level is detected to be too high, the system will immediately issue a warning; multi-level warning, setting up a multi-level warning mechanism, and issuing different levels of warning signals according to the severity of the hidden danger, such as warnings, alarms, emergency alarms, etc.

[0037] In one of the embodiments, the monitoring module 10408 is also used to enable the high-definition camera to collect the video stream of the loading and unloading site in real time to ensure the visualization of the operation process; to collect the physical parameters of the equipment and environment in real time through various sensors (such as liquid level sensors, temperature sensors, pressure sensors, etc.); and to collect the location information of operators and vehicles in real time through GPS, RFID, Bluetooth beacons and other technologies.

[0038] In one of the embodiments, the safety officer terminal 106 is used to display the warning result after the personnel positioning information and AI warning information are integrated. The safety officer on duty receives the warning information, arranges personnel for on-site inspections, and takes corresponding emergency plans after confirming that it is consistent with the warning result. If it does not match the on-site inspection results, it is a model false alarm, and the information will be re-labeled for the corresponding model to learn. After the emergency measures are taken, if the alarm is not cancelled within the specified time, the development of the situation may become more serious. The system will report to the senior management of the enterprise, the district and county emergency management departments, the municipal emergency management departments, and the provincial emergency management departments respectively to urge the correct implementation of safety measures and prevent the situation from spreading. After the rectification is completed within the deadline, the on-site duty personnel will inspect and cancel the alarm, complete the closed loop of the warning processing, and form a warning ledger for traceability at the time.

[0039] For the specific limitations of the liquid ammonia loading and unloading control system based on AI recognition and human-vehicle positioning, please refer to the limitations of the liquid ammonia loading and unloading control method based on AI recognition and human-vehicle positioning above, which will not be repeated here. Each module in the above-mentioned liquid ammonia loading and unloading control system based on AI recognition and human-vehicle positioning can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0040] In one embodiment, Figure 2 As shown in the figure, a liquid ammonia loading and unloading control method based on AI recognition and human-vehicle positioning is provided. Figure 1 The system in is taken as an example to illustrate, including the following steps:

[0041] Step 202, based on AI recognition and human-vehicle positioning technology, obtain the operation status information and the safety officer's authentication information during the liquid ammonia loading and unloading operation.

[0042] The operation status information includes the equipment safety status information corresponding to each operating device during the liquid ammonia loading and unloading operation, and the authentication information includes the location information and work authority information of the safety officer.

[0043] Step 204, during the preparation stage for unloading the liquid ammonia tank, the relative position relationship between the safe operating area and the position information corresponding to the operating equipment is verified according to the work authority information, so that the safety officer can perform the liquid ammonia tank unloading operation on the operating equipment within the relative position relationship.

[0044] Step 206, during the liquid ammonia tank unloading operation stage, the data fusion module performs safety prediction analysis on the operation process of each operating device according to the equipment safety status information and relative position relationship, obtains a safety hazard data set, and uploads the safety hazard data set to the central server.

[0045] Step 208, when the unloading of the liquid ammonia tank is completed, the monitoring and early warning module performs a safety check on the safety hazard data set transmitted by the central server according to the safety measures mechanism, obtains the inspection result and the equipment problem status information corresponding to the inspection result, and calls the safety officer to correct the safety hazard according to the relative position relationship between the equipment problem status information and the position information.

[0046] In the above-mentioned liquid ammonia loading and unloading control method based on AI recognition and human-vehicle positioning, AI visual analysis technology is used to automatically detect and verify various operations, reducing safety hazards caused by human factors. Human-vehicle positioning technology is used to track the location of operators and vehicles in real time to ensure the accuracy and safety of the location during the operation. The system can summarize the data of each operation link, automatically identify potential safety hazards, and issue corresponding warnings at different times to prevent accidents. Through automation technology, the dependence on human resources is reduced and labor costs are reduced. Preventive measures are taken to reduce the possibility of accidents and reduce direct and indirect economic losses caused by accidents. The system automatically records various data during the operation, including operator behavior, equipment status, environmental conditions, etc. Big data analysis technology is used to deeply mine historical data to provide a reference for future operations and continuously optimize system performance.

[0047] In one embodiment, if Figure 3 As shown in the figure, a process of liquid ammonia unloading operation based on AI recognition and human-vehicle positioning is provided. The specific steps are as follows:

[0048] 1. Data Collection

[0049] Get the video streams of all cameras in the unloading scene.

[0050] 2. Verification of both person and evidence

[0051] Establish a database containing all authorized operator information, including name, photo, etc. Capture operator's facial image through camera and use face recognition technology to verify their identity.

[0052] Build a face recognition model based on deep learning algorithm (FaceNet, OpenFace, etc.) and train a high-precision face recognition model.

[0053] The operator's position can be located in real time through technologies such as GPS, RFID or Bluetooth beacons.

[0054] The facial recognition results are associated with the positioning data to ensure that only authorized personnel can enter the designated area and their location information is recorded.

[0055] Only after successful verification will the system allow it to enter the operating area and record its entry time and location information.

[0056] 3. Verify tank level

[0057] Use a camera to capture images of the interior of the tank and use image processing technology to identify the liquid level in the tank.

[0058] Positioning technology is used to ensure that operators can observe from a safe distance.

[0059] Combine tank level data with operator location information to ensure operators can observe tank levels from a safe location.

[0060] If the liquid level exceeds the safe range, the system will automatically issue an early warning and record the specific time and liquid level value.

[0061] 4. Check the vehicle emergency shut-off valve

[0062] A camera is used to capture images of the emergency shut-off valve, and its status (open or closed) is identified through image processing technology.

[0063] Use a camera to capture and annotate images of the vehicle's emergency shut-off valve.

[0064] Use the trained AI model to determine whether the shut-off valve is in the correct closed state.

[0065] The location information of operators and vehicles is confirmed through positioning technology.

[0066] Combining the status of the emergency shut-off valve with the operator's location information ensures that the operator is in the correct position to operate the shut-off valve.

[0067] The judgment results are fed back to the operator in real time and recorded in the system.

[0068] If it is detected that the shut-off valve is not closed, the system will immediately sound an alarm and prompt the operator to take action.

[0069] 5. Wear personal protective equipment

[0070] The camera collects the operator's image and uses image processing technology to identify whether the operator is wearing the required personal protective equipment, including a helmet, protective clothing, etc.

[0071] The operator's location information is confirmed through positioning technology.

[0072] Combine the wearing status of personal protective equipment with the location information of the operator to ensure that the operator wears personal protective equipment within the specified working scope.

[0073] Use the trained AI model to identify whether the operator is wearing the required protective equipment.

[0074] The recognition results are fed back to the operator and recorded in the system.

[0075] If it is detected that the equipment is not being worn, the system will sound an alarm and prompt the operator to put on the complete equipment.

[0076] 6. Vehicle static grounding identification

[0077] The image of the vehicle grounding wire is collected by a camera, and image processing technology is used to identify whether the electrostatic clamp is connected to the vehicle (whether it is grounded).

[0078] The location of the vehicle is confirmed through positioning technology to ensure that the vehicle is parked in the correct location.

[0079] The grounding status is combined with the vehicle position information to ensure that the vehicle is grounded at the correct position.

[0080] The control system monitors in real time whether the vehicle has been properly grounded.

[0081] If it is detected that the vehicle is not grounded, the system will issue a warning and record relevant information.

[0082] 7. Crane pipe connection identification

[0083] A camera is used to capture images of the crane pipe connection parts, and its connection status (connected or not connected) is identified by using image processing technologies such as edge detection and template matching.

[0084] The operator’s position is confirmed through positioning technology, and combined with AI visual analysis results, it ensures that the crane pipe is connected at the correct position.

[0085] Combine the crane connection status with the operator's location information to ensure that the operator operates the crane in the correct position.

[0086] Use the trained AI model to identify whether the crane pipe is correctly connected.

[0087] If a disconnection is detected, the system will sound an alarm and prompt the operator to check.

[0088] 8. Leak test

[0089] Use a camera to capture images of the leak test site, and determine whether there is a leak at the connection of the universal pipe by identifying the state of the soap bubbles.

[0090] The operator’s location is confirmed through positioning technology, and combined with AI visual analysis results, it is ensured that the operator performs leak inspection in the specified area.

[0091] The leak test results are combined with the operator's location information to ensure that the operator performs leak tests in the correct position. At the same time, a highly sensitive gas detector is used to detect pipeline connections. The detector collects gas concentration data and performs real-time monitoring and early warning.

[0092] If a leak is detected, the system will issue an alarm and record the leak location.

[0093] 9. Recognition of prohibited signs

[0094] The image of the on-site sign is collected by the camera, and image processing technology is used to identify and determine whether there are license plate blocks, triangular cones, etc. in front of the vehicle.

[0095] The operator's location is confirmed through positioning technology, and the vehicle's location information is obtained.

[0096] The content of the no-entry sign is combined with the operator's location information to ensure that the operator does not enter the no-entry area. And if the blocking plate does not move, the vehicle's location information shall not change.

[0097] If a mark that does not comply with regulations is identified, the system will sound an alarm and prompt the operator to make corrections.

[0098] 10. Anti-slip pad identification

[0099] The camera collects images of the ground around the vehicle, and uses image processing technology to identify whether anti-slip pads are placed under the loading and unloading vehicle.

[0100] The location of the vehicle is confirmed through positioning technology to ensure that the vehicle is parked in the correct location.

[0101] The presence of anti-skid pads is combined with the vehicle position information to ensure that the vehicle places the anti-skid pads in the correct parking area.

[0102] If the system detects a lack of anti-skid pads, it will sound an alarm and prompt the operator to replenish the pads.

[0103] 11. Check the personal protective equipment again to ensure that personnel do not remove the personal protective equipment during the unloading process.

[0104] 12. Verify the tank liquid level again to ensure that there is no liquid ammonia residue in the vehicle after unloading.

[0105] 13. After receiving the early warning information, the security officer will arrange personnel to conduct on-site inspections.

[0106] 14. After confirming that it is consistent with the warning result, take the corresponding emergency plan. If it is inconsistent with the on-site inspection result, it is a model false alarm, and the information will be re-labeled for the corresponding model to learn.

[0107] 15. After emergency measures are taken, if the alarm is not closed within the specified time, the situation may become more serious. The system will report to the company's senior management, district and county emergency management departments, municipal emergency management departments and provincial emergency management departments respectively to urge the correct implementation of safety measures and prevent the situation from spreading.

[0108] 16. After the rectification is completed within the deadline, the on-site duty personnel will inspect and cancel the alarm, completing the early warning processing closed loop and forming an early warning ledger for traceability at any time.

[0109] In one of the embodiments, a data fusion module performs safety prediction analysis on the operation process of each of the operating devices according to the equipment safety status information and the relative position relationship to obtain a safety hazard data set, and the safety hazard data set is uploaded to a central server, including: a face recognition data set, a liquid level monitoring identification data set, an emergency shut-off valve connection status data set, a safety helmet / reflective clothing identification data set, an electrostatic grounding connection status data set, a crane connection status data set, a leak detection location detection data set, a no-entry sign data set, an anti-slip pad status monitoring data set, etc.

[0110] In one of the embodiments, there are warnings before the loading and unloading process about the mismatch between personnel and credentials, warnings about exceeding the storage liquid level, warnings about the closure of the emergency shut-off valve, warnings about personnel not wearing the required safety helmets / protective clothing, warnings about the vehicle not being electrostatically grounded during unloading, warnings about not using a crane for filling operations, warnings about not placing signs, warnings about not placing anti-slip pads, warnings about acceptance personnel exceeding their position, warnings about the scope of operations exceeding the prescribed scope, etc.

[0111] It should be understood that although Figure 2-3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-3 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0112] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input system connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a liquid ammonia loading and unloading control method based on AI recognition and human-vehicle positioning is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0113] Those skilled in the art will understand that Figure 1 , 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0115] Based on AI recognition and human-vehicle positioning technology, the operation status information and safety officer authentication information of the liquid ammonia loading and unloading operation are obtained; wherein the operation status information includes the equipment safety status information corresponding to each operating device during the liquid ammonia loading and unloading operation, and the authentication information includes the location information and work authority information of the safety officer;

[0116] In the preparation stage for unloading the liquid ammonia tank, the relative position relationship between the safe operation area corresponding to the operating equipment and the position information is verified according to the work authority information, so that the safety officer can perform the liquid ammonia tank unloading operation on the operating equipment within the relative position relationship;

[0117] During the liquid ammonia tank unloading operation phase, a data fusion module is used to perform safety prediction analysis on the operation process of each of the operating devices according to the equipment safety status information and the relative position relationship to obtain a safety hazard data set, and the safety hazard data set is uploaded to the central server;

[0118] When the unloading of the liquid ammonia tank is completed, the monitoring and early warning module performs a safety check on the safety hazard data set transmitted by the central server according to the safety measures mechanism, obtains the inspection result and the equipment problem status information corresponding to the inspection result, and calls the safety officer to correct the safety hazard according to the relative position relationship between the equipment problem status information and the location information.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0120] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A liquid ammonia loading and unloading control system based on AI recognition and human-vehicle positioning, characterized in that: The system includes: a central server, a liquid ammonia loading and unloading control subsystem and a safety officer terminal; wherein the liquid ammonia loading and unloading control subsystem includes: an AI visual recognition module, a data fusion module, a decision-making and early warning module and a monitoring module; The AI ​​visual recognition module is used to build a face recognition model using a deep learning algorithm and human-vehicle positioning technology, collect the authentication information and location information of the safety officer using the AI ​​face recognition model, and collect the operation status of liquid ammonia loading and unloading and the device location information of the relevant operating equipment corresponding to each operation status using a video capture device; The data fusion module is used to perform unified data annotation and fusion on the location information, the equipment location information and the operation status according to the authentication information to generate a control data set, and to process the control data set within a preset safety range corresponding to the relevant operating equipment according to the data transmitted by the AI ​​visual recognition module and the monitoring module, so that the decision-making and early warning module performs safety hazard training according to the received control data set; The decision-making and early warning module is used to perform safety hazard training on the received control data set according to the operation status and the safe operation mechanism, output a safety prediction result, generate an early warning plan according to the safety prediction result, and upload the early warning plan to the central server; The monitoring module is used to call the nearest safety officer to the location of the safety problem to handle the fault according to the early warning scheme and the authentication information collected by the AI ​​visual recognition module, the location information, the device location information, and the safety range corresponding to the device location information; The liquid ammonia loading and unloading control subsystem is communicated with the safety officer terminal through the central server.

2. The system according to claim 1, characterized in that The AI ​​visual recognition module is also used to conduct real-time monitoring and intelligent analysis of each link in the liquid ammonia unloading process through image processing and deep learning technology. The specific steps include: in the operator identity verification, if the person and the certificate are consistent, the facial image of the operator is collected by the camera for face recognition technology verification. If the operator is an authorized person, the operator is authorized to enter the loading and unloading operation area; otherwise, an alarm signal is generated and sent to the emergency management system for alarm; in the process of wearing personal protective equipment detection, the operator's wear is identified by image processing technology, and an alarm is issued according to the matching degree between the wear and the prescribed personal protective equipment. If the matching degree is lower than the preset safety threshold, an alarm signal is generated and sent to the emergency management system for alarm; when verifying the liquid level of the storage tank, the liquid nitrogen image inside the storage tank collected by the camera is analyzed by AI vision, and the liquid level in the storage tank is identified by image processing technology; when checking the emergency shut-off valve of the vehicle, the image is used to identify the liquid nitrogen inside the storage tank. Image processing technology is used to identify the status image of the emergency shut-off valve collected by the camera; during the loading and unloading operation, the image of the vehicle grounding wire is collected by the camera, and image processing technology is used to identify whether the electrostatic clamp is connected to the vehicle; the image of the crane pipe connection part is collected by the camera, and image processing technology is used to identify the connection status of the crane pipe; the image of the leak test part is collected by the camera, and the state of the soap bubble is visually identified to determine whether there is a leak point at the connection of the universal pipe; the image of the on-site signboard is identified by image processing technology to determine whether a warning sign is placed in front of the vehicle; the image of the ground around the vehicle is identified by image processing technology to determine whether anti-slip pads are placed under the loading and unloading vehicle; after the loading and unloading operation, the liquid level in the storage tank is verified by image processing technology for the second time, and the verification result is uploaded to the enterprise management platform. The enterprise management platform selects the operator closest to the loading and unloading safety area according to the operator's positioning information to conduct on-site acceptance of the loaded and unloaded liquid ammonia.

3. The system according to claim 1, characterized in that The data fusion module is also used to integrate and process the AI ​​visual recognition results and positioning information. The specific steps include: when judging the consistency between the person and the certificate, the face recognition result is associated with the positioning data to ensure that the authorized operator enters the designated area, and the location information of the operator who has entered the designated area is recorded; when verifying the tank level, the tank level data is aggregated with the operator's location information to enable the operator to monitor the tank level in a safe position; when checking the vehicle emergency shut-off valve, the relative position of the operator and the vehicle is confirmed by positioning technology, and the shut-off valve is correctly located in the correct position according to AI visual analysis. operation; when warning the operator to wear personal protective equipment, the wearing status of the personal protective equipment is combined with the location information of the operator, so that the operator can correctly wear the personal protective equipment within the specified working range; during the loading and unloading operation, when judging the vehicle's electrostatic grounding, crane pipe connection status, leak testing, inspection of no-entry signs, and inspection of anti-slip pads, the position of the vehicle is confirmed by positioning technology, and combined with the analysis results of the AI ​​vision, the vehicle is parked in the correct position; after the loading and unloading operation, the recognition results of the AI ​​vision are aggregated according to the operator's location information, so that the operator can correctly wear protective equipment for on-site acceptance.

4. The system according to claim 3, characterized in that The decision-making warning module is also used for comprehensive warning analysis, which comprehensively analyzes the data collected by the monitoring module, identifies potential safety hazards, and issues dynamic warnings based on real-time data.

5. The system according to claim 4, characterized in that The monitoring module is also used to use a high-definition camera to collect real-time video streams of the loading and unloading site to visualize the operation process; and to collect real-time physical parameters of the equipment and the environment through various sensors; and to collect location information of the operator and the vehicle through positioning technology.

6. The system according to claim 4, characterized in that The safety officer terminal is used to display the warning results that integrate the operator's positioning information and AI warning information, and transmit them to the mobile device of the safety officer on duty through the emergency management system. If the on-site investigation result of the safety officer on duty is consistent with the warning result, the emergency plan corresponding to the warning result is adopted; if the investigation result is inconsistent with the warning result, the model false alarm information is reported to the emergency management system, so that the emergency management system re-labels the model false alarm information and then inputs the labeled model false alarm information into the model corresponding to the model false alarm information for training and learning.

7. A liquid ammonia loading and unloading control method based on AI recognition and human-vehicle positioning, characterized in that: The method comprises: Based on AI recognition and human-vehicle positioning technology, the operation status information and safety officer authentication information of the liquid ammonia loading and unloading operation are obtained; wherein the operation status information includes the equipment safety status information corresponding to each operating device during the liquid ammonia loading and unloading operation, and the authentication information includes the location information and work authority information of the safety officer; In the preparation stage for unloading the liquid ammonia tank, the relative position relationship between the safe operation area corresponding to the operating equipment and the position information is verified according to the work authority information, so that the safety officer can perform the liquid ammonia tank unloading operation on the operating equipment within the relative position relationship; During the liquid ammonia tank unloading operation phase, a data fusion module is used to perform safety prediction analysis on the operation process of each of the operating devices according to the equipment safety status information and the relative position relationship to obtain a safety hazard data set, and the safety hazard data set is uploaded to the central server; When the unloading of the liquid ammonia tank is completed, the monitoring and early warning module performs a safety check on the safety hazard data set transmitted by the central server according to the safety measures mechanism, obtains the inspection result and the equipment problem status information corresponding to the inspection result, and calls the safety officer to correct the safety hazard according to the relative position relationship between the equipment problem status information and the location information.

8. The method according to claim 7, characterized in that The safety hazard data set includes: face recognition data set, liquid level monitoring recognition data set, emergency shut-off valve connection status data set, safety helmet or reflective clothing recognition data set, electrostatic grounding connection status data set, crane pipe connection status data set, leak detection location detection data set, no-entry sign data set and anti-slip pad status monitoring data set.

9. The method according to claim 8, characterized in that The safety measures mechanism includes: warning of mismatch between the operator and the authorized certificate before the loading and unloading process, warning of exceeding the storage liquid level, warning of emergency shut-off valve closure, warning of personnel not wearing the required safety helmets or protective clothing, warning of vehicle not being electrostatically grounded during unloading, warning of not using a crane for filling operations, warning of not placing signs, warning of not placing anti-slip pads, warning of acceptance personnel exceeding the position, and warning of the operation scope exceeding the prescribed scope.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 7 to 9 are implemented.

Images