Manual intervention control system based on unmanned driving system of crane

Abstract

The invention provides a manual intervention control system based on a crane unmanned driving system. The manual intervention control system comprises the steps that S1, the unmanned system monitors the operation state of a portal crane in real time, and whether manual intervention is needed or not is judged when operation of one stage is finished; s2, the system display generates a manual intervention prompt according to the operation result, and prompts an operator whether intervention is needed or not; s3, an operator judges whether intervention is carried out or not according to the field condition, and if intervention is needed, the mode is switched to a manual control mode; s4, after the operator completes intervention, the automatic control mode is selected to be recovered, and the system is transited back to the automatic control state; s5, the system monitors and feeds back intervention operation in real time, and an operation log is generated. According to the control method, whether manual intervention is needed or not can be prompted in real time in the operation process of the unmanned system, whether intervention is needed or not is judged by an operator according to the actual site situation, the flexibility of the system and the response ability of the operator can be effectively improved, and risks are reduced.

Description

Technical Field

[0001] The present invention relates to the field of unmanned systems, and in particular, to an artificial intervention control system based on a crane unmanned driving system. Background Art

[0002] With the rapid development of automation technology, the unmanned driving system of gantry cranes has been widely applied in fields such as ports and warehousing to improve work efficiency and reduce labor costs. However, when a gantry crane operates in a complex environment, it may encounter various unforeseeable obstacles, faults or abnormal situations, and it is difficult for a simple automatic system to handle all emergencies.

[0003] Existing unmanned systems usually automatically pause or shut down when an abnormality occurs, or perform manual intervention remotely. However, this often relies on pre-set rules and monitoring devices and requires frequent regular inspections to ensure effectiveness. At the same time, there are still certain limitations in the real-time monitoring and emergency response of existing systems. Especially during the operation of an unmanned system, there is often no effective mechanism for reminding an operator at an appropriate time and making a judgmental intervention, so that preventive intervention cannot be achieved, and only processing can be carried out after an abnormal situation occurs, and it is difficult to achieve effective fault avoidance to reduce losses. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide an artificial intervention control system based on a crane unmanned driving system in view of the above technical status quo, which solves the problem in the prior art that risks during the operation of an unmanned system cannot be pre-controlled, resulting in only subsequent processing being possible.

[0005] The technical solution adopted by the present invention to solve the above problems is as follows: An artificial intervention control system based on a crane unmanned driving system includes the following steps:

[0006] S1: The unmanned system monitors the operation status of the gantry crane in real time, and at the end of one stage of operation, determines whether manual intervention is required according to a preset algorithm;

[0007] S2: The system displays an artificial intervention reminder generated according to the operation result, prompting the operator whether intervention is required;

[0008] S3: The operator determines whether to intervene according to the on-site situation. If intervention is required, switch to the manual control mode;

[0009] S4: After the operator completes the intervention, select to resume the automatic control mode, and the system transitions back to the automatic control state;

[0010] S5: The system monitors and feeds back the intervention operation in real time, and generates an operation log.

[0011] Further, in the step S1, the unmanned system monitors the operating state of the gantry crane in real time through sensors and a data processing unit, and determines whether the condition for manual intervention is met through a preset algorithm.

[0012] Further, the operating state of the gantry crane includes a load state, a position state, and a speed state.

[0013] Further, in the step S1, the judgment steps of the preset algorithm are as follows:

[0014] S1.1: Collect relevant data, including the operation records of users, system logs, and error logs, for subsequent analysis and processing;

[0015] S1.2: Use machine learning algorithms to perform anomaly detection on the collected data, and identify abnormal behaviors or data patterns by establishing a model;

[0016] S1.3: Set alarm rules according to the results of anomaly detection; based on the thresholds of monitoring metrics or abnormal patterns, define the conditions for triggering alarms through static or dynamic adaptive alarm rules to adapt to changes in the system environment;

[0017] S1.4: The system needs to monitor key metrics in real time. Once an abnormal situation is detected, the alarm mechanism is immediately triggered; the alarm mechanism notifies the operator by means of email, text message, or in-app notification;

[0018] S1.5: After the alarm is triggered, the system generates specific intervention suggestions. The intervention suggestions are based on historical data and an expert knowledge base, and provide specific operation steps or solutions to the user.

[0019] Further, in the step S2, the manual intervention reminder generated by the system according to the operation result includes sound, light, and screen display to ensure that the operator can receive the intervention reminder in time.

[0020] Further, in the step S3, the operator performs manual intervention through a console or a remote control device, and the system provides necessary operation interfaces and control instructions to support the operator to perform effective intervention.

[0021] Further, in the step S4, after the operator selects to resume the automatic control mode, the system ensures a smooth transition from the manual control mode back to the automatic control state through smooth control, avoiding operation instability caused by mode switching.

[0022] Further, in the step S5, the system monitors the intervention operation in real time and records the key information during the intervention process in the operation log for subsequent analysis and auditing.

[0023] Compared with the prior art, the advantages of the present invention are as follows:

[0024] 1. By combining the unmanned system with manual intervention, the present invention solves the complex or unexpected situations that may be faced by automatic control, and can effectively avoid safety accidents caused by the system's inability to handle abnormal situations. At the same time, the operator can intervene according to the actual on-site situation, improving the crane's response ability in complex environments. Secondly, the smooth switching and recovery of the manual intervention mode avoid conflicts in the control of the crane during the transition period, ensuring the stable operation of the automation system.

[0025] 2. The present invention can prompt in real time during the operation of the unmanned system whether manual intervention is required, and the control method for the operator to judge whether to intervene according to the actual on-site situation can effectively improve the flexibility of the system and the response ability of the operator, reducing risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0027] Figure 1 It is a schematic diagram of the method steps of an embodiment of the present invention;

[0028] Figure 2 It is a schematic diagram of the sub-steps in step S1 of an embodiment of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Usually, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0030] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application that is required to be protected, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0031] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the present invention.

[0032] In an exemplary embodiment, as Figure 1 shown, the present invention provides an artificial intervention control system based on a crane unmanned system, including:

[0033] S1: The unmanned system monitors the operating state of the gantry crane in real time, and at the end of one stage of operation, determines whether manual intervention is required;

[0034] S2: The system displays an artificial intervention reminder generated according to the operation result, prompting the operator whether intervention is required;

[0035] S3: The operator determines whether to intervene according to the on-site situation. If intervention is required, switch to the manual control mode;

[0036] S4: After the operator completes the intervention, select to resume the automatic control mode, and the system transitions back to the automatic control state;

[0037] S5: The system monitors and feeds back the intervention operation in real time, generating an operation log.

[0038] As Figure 1 shown, in a further exemplary solution, in the S1 step, the unmanned system monitors the operating state of the gantry crane in real time through sensors and a data processing unit, including but not limited to the load state, position state, speed state, etc., and determines whether the condition for manual intervention is met through a preset algorithm; in the S2 step, the artificial intervention reminder generated by the system according to the operation result includes but not limited to sound, light, screen display, etc., to ensure that the operator can receive the intervention reminder in time; in the S3 step, the operator performs manual intervention through a console or a remote control device, and the system provides necessary operation interfaces and control instructions to support the operator to perform effective intervention; in the S4 step, after the operator selects to resume the automatic control mode, the system ensures a smooth transition from the manual control mode back to the automatic control state through smooth control, avoiding unstable operation caused by mode switching; in the S5 step, the system monitors the intervention operation in real time and records the key information during the intervention process in the operation log for subsequent analysis and auditing.

[0039] As Figure 2 shown, in a further exemplary embodiment, in step 1, the preset algorithm judgment sub-step is as follows:

[0040] S1.1: Collect relevant data, including user operation records, system logs, error logs, etc., which are used for subsequent analysis and processing;

[0041] S1.2: Use machine learning algorithms to perform anomaly detection on the collected data, and establish a model to identify abnormal behaviors or data patterns;

[0042] S1.3: Set alarm rules according to the results of anomaly detection; these rules define the conditions for triggering an alarm, usually based on the thresholds of monitoring metrics or abnormal patterns; the rules can be static or dynamically adaptive to adapt to changes in the system environment;

[0043] S1.4: The system needs to monitor key metrics in real time. Once an abnormal situation is detected, the alarm mechanism is immediately triggered; the alarm mechanism can notify relevant personnel via email, text message, in-app notification, etc.;

[0044] S1.5: After triggering the alarm, the system can generate specific intervention suggestions, which can be based on historical data and expert knowledge bases, and provide users with specific operation steps or solutions.

[0045] Specifically, the method for the machine learning algorithm to perform anomaly detection on the collected data is as follows:

[0046] (1): Process the collected data into normal data and abnormal data, and combine these two types of data into a dataset X;

[0047] (2): Randomly extract a certain number of samples x from the entire dataset X, and construct isolation trees for each sub-dataset; after obtaining t isolation trees, the training of a single tree ends, and the generated isolation trees are used to evaluate the test data, that is, calculate the anomaly score s;

[0048] (3): Build the isolation trees into an isolation forest. For each sample x, it is necessary to comprehensively calculate the results of each tree, and calculate the anomaly score through the following formula:

[0049]

[0050] where h(x) is the height of x in each tree, E(h(x)) is the average path length of the data point x in all trees, n is the sample size of the training data, and c(n) is the average path length of the tree, which is used to standardize the path length h(x) of the sample x.

[0051] (4): Set a threshold value according to the calculated anomaly scores to determine which data points are anomalies.

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A manual intervention control system based on a crane unmanned driving system, characterized in that: The steps include: S1: The unmanned system monitors the operating status of the gantry crane in real time and determines whether manual intervention is required based on the preset algorithm at the end of one stage of operation; S2: The system displays a manual intervention reminder based on the operation results, prompting the operator whether intervention is required; S3: The operator determines whether to intervene based on the on-site situation. If intervention is required, the operator switches to manual control mode. S4: After the operator completes the intervention, he chooses to restore the automatic control mode, and the system transitions back to the automatic control state; S5: The system monitors and provides feedback on intervention operations in real time and generates operation logs.

2. The manual intervention control system based on the crane unmanned driving system according to claim 1, characterized in that: In the step S1, the unmanned system monitors the operating status of the gantry crane in real time through sensors and data processing units, and determines whether the conditions for manual intervention are met through a preset algorithm.

3. The manual intervention control system based on the crane unmanned driving system according to claim 2, characterized in that: The operating state of the gantry crane includes load state, position state and speed state.

4. The manual intervention control system based on the crane unmanned driving system according to claim 1, characterized in that: In step S1, the judgment steps of the preset algorithm are: S1.1: Collect relevant data, including user operation records, system logs, and error logs, for subsequent analysis and processing; S1.2: Use machine learning algorithms to perform anomaly detection on the collected data by building models to identify abnormal behaviors or data patterns; S1.3: Set alarm rules based on the results of anomaly detection; based on the thresholds or anomaly patterns of monitoring indicators, define the conditions for triggering alarms through static or dynamic adaptive alarm rules to adapt to changes in the system environment; S1.4: The system needs to monitor key indicators in real time and immediately trigger an alarm mechanism once an abnormal situation is detected; the alarm mechanism notifies the operator via email, SMS or in-app notification; S1.5: After the alarm is triggered, the system generates specific intervention suggestions. The intervention suggestions are based on historical data and expert knowledge base, and provide users with specific operation steps or solutions.

5. The manual intervention control system based on the crane unmanned driving system according to claim 1, characterized in that: In the step S2, the system generates a manual intervention reminder including sound, light, and screen display according to the operation result, to ensure that the operator can receive the intervention reminder in time.

6. The manual intervention control system based on the crane unmanned driving system according to claim 1, characterized in that: In the step S3, the operator performs manual intervention through a console or a remote control device, and the system provides necessary operation interfaces and control instructions to support the operator to perform effective intervention.

7. The manual intervention control system based on the crane unmanned driving system according to claim 1, characterized in that: In the step S4, after the operator chooses to restore the automatic control mode, the system ensures a smooth transition from the manual control mode back to the automatic control state through smooth control, thereby avoiding unstable operation caused by mode switching.

8. The manual intervention control system based on the crane unmanned driving system according to claim 1, characterized in that: In the step S5, the system monitors the intervention operation in real time and records key information during the intervention process in the operation log to facilitate subsequent analysis and auditing.

Images