Heading machine intelligent control method based on mixed heterogeneous calculation

Abstract

The invention relates to a heading machine intelligent control method based on hybrid heterogeneous calculation, which comprises the following steps: an edge controller obtains heading machine task information, and obtains task scheduling information according to the heading machine task information and a preset resource scheduling strategy; the edge controller receives a task execution starting instruction sent by the upper computer, and obtains a task scheduling sequence according to the instruction and the task scheduling information; according to the task scheduling sequence, the edge controller sends an instruction for collecting data information to data collection equipment and receives the data information fed back by the data collection equipment; and according to the data information fed back by the data acquisition device, the edge controller performs data processing by using the model optimized in advance to obtain a model calculation result, and sends the model calculation result to the upper computer platform. According to the invention, cooperative control of real-time tasks such as logic control and motion control of the heading machine and non-real-time tasks of intelligent applications can be realized, and the execution efficiency of the tasks and the efficiency of data interaction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and in particular to an intelligent control method for a tunnel boring machine based on hybrid heterogeneous computing. Background Art

[0002] With the rise of technologies like artificial intelligence and big data, and the advancement of digital engineering, intelligent technology is gradually penetrating the tunneling industry. However, due to the large scale, numerous units, and complex structure of shield equipment, as well as the complex geological environment in which construction takes place, intelligent tunneling still requires continuous development and improvement to ensure efficient and safe tunneling operations.

[0003] With the growing demand for intelligent tunneling, an increasing number of intelligent systems are being deployed on tunneling equipment, such as conveyor slag volume flow monitoring, rock slag analysis, automatic shield tail gap measurement, and automatic spray mixing. A common approach is to directly execute intelligent control computing tasks on industrial controllers. However, due to limited industrial controller resources, this approach cannot guarantee algorithm execution efficiency. To better complete intelligent tasks and achieve the desired results, another approach is to configure additional hardware support on top of the industrial control system. This results in the tunneling equipment being equipped with multiple controller hardware sets of different manufacturers and models. This not only wastes controller resources, but also complicates data exchange and communication between multiple hardware systems, making resource sharing and coordinated multi-task control difficult.

[0004] Therefore, there is an urgent need for an intelligent control method for tunnel boring machines based on hybrid heterogeneous computing. Summary of the Invention

[0005] (1) Technical issues to be resolved

[0006] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides an intelligent control method for a tunnel boring machine based on hybrid heterogeneous computing, which solves the technical problems in the prior art of low execution efficiency, waste of controller resources, complex data interaction and communication between multiple hardware systems, and difficulty in achieving resource sharing and coordinated control of multiple tasks in order to meet the intelligent requirements of the tunnel boring machine.

[0007] (2) Technical solution

[0008] In order to achieve the above objectives, the main technical solutions adopted by the present invention include:

[0009] An embodiment of the present invention provides an intelligent control method for a roadheader based on hybrid heterogeneous computing. The intelligent control method is applied to an intelligent control system for a roadheader. The system includes: a host computer platform for sending task execution instructions to an edge controller and displaying model calculation results; a cloud for optimizing the algorithm model; a data acquisition device for collecting data information; and an edge controller. The intelligent control method for a roadheader includes:

[0010] S1. The edge controller obtains the task information of the tunnel boring machine and obtains the task scheduling information according to the task information of the tunnel boring machine and the resource scheduling strategy set in advance;

[0011] S2. The edge controller receives an instruction from the host computer to start executing a task, and obtains the task scheduling order according to the instruction and task scheduling information;

[0012] S3. According to the task scheduling sequence, the edge controller sends a data collection instruction to the data collection device and receives data information fed back by the data collection device;

[0013] S4. Based on the data information fed back by the data acquisition device, the edge controller uses the pre-optimized algorithm model to process the data, obtain the model calculation results, and send the model calculation results to the host computer platform.

[0014] Optionally, the edge controller includes: a virtual controller control module, K CPU virtual controllers, M NPU virtual controllers, and N FPGA virtual controllers;

[0015] The virtual controller control module controls the K CPU virtual controllers, the M NPU virtual controllers, and the N FPGA virtual controllers for allocation.

[0016] Optionally, in S1, the roadheader task information includes:

[0017] The task type, the controller resource size required by the task, and the controller real-time performance required by the task.

[0018] Optionally, in S1, the resource scheduling strategy set in advance includes:

[0019] When the task requires the controller to be as fast as 50ms in real time, it is assigned to the CPU virtual controller for execution.

[0020] When the task requires the controller to be real-time at the level of 1 to 10 ms, it is divided into the FPGA virtual controller or the CPU virtual controller for execution;

[0021] When the task is an image processing task, it is divided into the NPU virtual controller for execution.

[0022] Optionally, in S1, the task scheduling information includes:

[0023] The virtual controllers corresponding to different tasks and the scheduling priority and time slice information of the virtual controllers.

[0024] Optionally, in S2, generating a task scheduling sequence according to the instruction and the task scheduling information includes:

[0025] For virtual controllers that are not at the same priority level, the task scheduling order is determined according to the priority order;

[0026] For virtual controllers with the same priority, a time slice round-robin algorithm is used to determine the task scheduling order based on the time slice information of the virtual controller.

[0027] Optionally, before S1, the step further includes:

[0028] S0, the edge controller receives the optimized algorithm model sent by the cloud;

[0029] The algorithm model includes: a shield tail gap measurement algorithm, a rock slag identification model, and an automatic spray-mixing trajectory planning model.

[0030] Optionally, the system further comprises: an actuator;

[0031] The executor is in communication with the edge controller, and is configured to receive the model calculation results sent by the edge controller and perform corresponding actions according to the model calculation results.

[0032] Optionally, the system further comprises: a plurality of PLC substations;

[0033] The PLC substation is connected between the edge controller and the data acquisition device and between the edge controller and the actuator, and is used to transmit data information and model calculation results.

[0034] Optionally, the method further includes:

[0035] The edge controller saves the task scheduling information to the local end and generates a local end configuration file.

[0036] (3) Beneficial effects

[0037] The beneficial effects of the present invention are: a tunnel boring machine intelligent control method based on hybrid heterogeneous computing of the present invention, due to the use of a multi-core CPU + FPGA + NPU hybrid heterogeneous architecture edge computing controller, can centrally deploy the tunnel boring machine intelligent system on a single controller, reducing the redundancy of the controller hardware; at the same time, hybrid heterogeneous computing is used to realize the coordinated control of multi-system tasks of tunnel boring machine logic control and intelligent control, ensuring the actual effect of multiple intelligent systems carried by the tunnel boring machine; in addition, this application realizes the interconnection and interoperability of underlying data by uniformly storing and managing the data collected by on-site terminal equipment and the processing results of each task, so that the application layer can easily call terminal data, greatly improving the data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Schematic diagram of a flow chart of an intelligent control method for a roadheader based on hybrid heterogeneous computing according to an embodiment of the present invention;

[0039] Figure 2 This is a system architecture diagram of the intelligent control system for a roadheader based on hybrid heterogeneous computing in Example 2 of the present invention;

[0040] Figure 3 This is a schematic diagram of the configuration of the edge controller in Example 2 of the present invention. DETAILED DESCRIPTION

[0041] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0042] An embodiment of the present invention proposes an intelligent control method for a tunnel boring machine based on hybrid heterogeneous computing. The method adopts an edge controller with a hybrid heterogeneous architecture of multi-core CPU+FPGA+NPU to determine the scheduling information of each task based on the task information and resource scheduling strategy of different tasks. The method solves the technical problems in the prior art of low execution efficiency, waste of controller resources, complex data interaction and communication of multiple hardware systems, and difficulty in achieving resource sharing and coordinated control of multiple tasks in order to meet the intelligent requirements of the tunnel boring machine. The method realizes the coordinated control of real-time tasks such as logic control and motion control of the tunnel boring machine and non-real-time tasks of intelligent applications, thereby improving the efficiency of resource scheduling, task execution and data interaction.

[0043] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0044] Specific embodiment description part

[0045] Example 1

[0046] See also Figure 1 This embodiment provides a method for intelligent control of a roadheader based on hybrid heterogeneous computing. The method is applied to an intelligent control system of the roadheader. The system includes: a host computer platform for sending task execution instructions to an edge controller and displaying model calculation results; a cloud for optimizing the algorithm model; a data acquisition device for collecting data information; and an edge controller. The method includes:

[0047] Step S1: The edge controller obtains task information of the roadheader, and obtains task scheduling information based on the task information and a pre-set resource scheduling strategy;

[0048] Step S2: The edge controller receives an instruction from the host computer to start executing the task, and obtains the task scheduling order according to the instruction and the task scheduling information;

[0049] Step S3: According to the task scheduling sequence, the edge controller sends a data collection instruction to the data collection device and receives data information fed back by the data collection device;

[0050] Step S4: Based on the data information fed back by the data acquisition device, the edge controller uses the pre-optimized algorithm model to process the data, obtain the model calculation results, and send the model calculation results to the host computer platform.

[0051] The present embodiment provides an intelligent control method for a tunnel boring machine based on hybrid heterogeneous computing, which can deploy an intelligent system for the tunnel boring machine on a single edge controller, reducing the redundancy of the controller hardware. At the same time, through hybrid heterogeneous computing, the coordinated control of multiple system tasks such as logical control and intelligent control of the tunnel boring machine is achieved, ensuring the actual effects of the multiple intelligent systems carried by the tunnel boring machine. In addition, in the present embodiment, the data information collected by the data acquisition device is fed back to the edge controller, realizing the interconnection and interoperability of the underlying data, enabling the upper function to easily call the data information, and greatly improving the data processing efficiency.

[0052] Example 2

[0053] In this embodiment, a method for intelligent control of a roadheader based on hybrid heterogeneous computing is provided. The method is applied to an intelligent control system of the roadheader. The system includes: a host computer platform for sending task execution instructions to an edge controller and displaying model calculation results; a cloud for optimizing the algorithm model; a data acquisition device for collecting data information; and an edge controller. The method for intelligent control of the roadheader includes:

[0054] Step S1: The edge controller obtains the task information of the roadheader, and obtains the task scheduling information based on the task information of the roadheader and the resource scheduling strategy set in advance;

[0055] Step S2: The edge controller receives the instruction to start executing the task from the host computer, and obtains the task scheduling order according to the instruction and task scheduling information;

[0056] Step S3: According to the task scheduling order, the edge controller sends a data collection instruction to the data collection device and receives data information fed back by the data collection device;

[0057] Step S4: Based on the data information fed back by the data acquisition device, the edge controller uses the pre-optimized algorithm model to process the data, obtain the model calculation results, and send the model calculation results to the host computer platform.

[0058] In the specific implementation process, see Figure 2 The data acquisition equipment consists of various sensors, including temperature sensors, pressure sensors, distance sensors, and cameras. Each system of the tunnel boring machine incorporates data acquisition equipment based on its functional requirements and design. For example, the rock slag analysis system's data acquisition equipment includes a camera, the shield tail gap measurement system's data acquisition module consists of multiple cameras, and the automatic spray mixing system's data acquisition module comprises distance sensors, inclination sensors, and travel sensors.

[0059] The edge controller includes: a virtual controller control module, K CPU virtual controllers, M NPU virtual controllers, and N FPGA virtual controllers;

[0060] The virtual controller control module controls K CPU virtual controllers, M NPU virtual controllers, and N FPGA virtual controllers for allocation.

[0061] During the specific implementation process, the virtual controller module can run and control multiple virtual controllers configured with virtual CPUs, NPUs, and FPGAs. The physical controller resources corresponding to the virtual controllers are determined through the mapping relationship between the physical controller resources of the tunnel boring machine and the virtual controllers. In addition, control modules for various tasks of the tunnel boring machine are deployed on each virtual device.

[0062] Control modules related to the tunnel boring machine tasks are deployed on each virtual controller. These modules are responsible for executing specific control logic. By deploying these control modules on the virtual controller, parallel processing of tasks can be achieved, thereby improving overall efficiency.

[0063] In this embodiment, each virtual controller uses virtualization technology to isolate interference between tasks, thereby ensuring stability and security.

[0064] In this embodiment, the roadheader task information in step S1 includes:

[0065] The task type, the controller resource size required by the task, and the controller real-time performance required by the task.

[0066] Optionally, in step S1, the resource scheduling strategy set in advance includes:

[0067] When the task requires the controller to be as fast as 50ms in real time, it is assigned to the CPU virtual controller for execution.

[0068] When the task requires the controller to be real-time at the level of 1 to 10 ms, it is divided into the FPGA virtual controller or the CPU virtual controller for execution;

[0069] When the task is an image processing task, it is divided into the NPU virtual controller for execution.

[0070] In this embodiment, tasks with low real-time requirements in logic control and process control are divided into the CPU virtual controller for execution to achieve medium and low latency (50ms level) control requirements; tasks such as the automatic spray mixing system that require the robotic arm to perform trajectory planning are divided into the FPGA virtual controller or the CPU virtual controller for execution to meet the low latency (between 1ms and 10ms) processing requirements; image processing tasks that require large computing resources, such as the shield tail gap measurement system, rock slag analysis system, and belt conveyor slag volume flow monitoring system that use image processing technology, are divided into the NPU virtual controller for execution.

[0071] In step S1, the task scheduling information includes:

[0072] The virtual controllers corresponding to different tasks and the scheduling priority and time slice information of the virtual controllers.

[0073] Optionally, in step S2, generating a task scheduling sequence according to the instruction and the task scheduling information includes:

[0074] For virtual controllers that are not at the same priority level, the task scheduling order is determined according to the priority order;

[0075] For virtual controllers with the same priority, a time slice round-robin algorithm is used to determine the task scheduling order based on the time slice information of the virtual controller.

[0076] In this embodiment, the time slice wheel algorithm is a classic algorithm for scheduling multiple tasks, which divides events into several time slices. Each task runs for a period of time in a time slice and then switches to the next model.

[0077] For example, see Figure 3 Assume that the rock slag analysis task is matched to virtual NPU0, with a priority of 11 and a time slice of 10, and the shield tail gap measurement task is matched to virtual NPU1, with a priority of 10 and a time slice of 8. That is, the priority of virtual NPU0 is higher than that of virtual NPU1. Therefore, the task scheduling order is determined based on the priority order, that is, the rock slag analysis task is performed first.

[0078] Assume that logical control task 1 is matched to virtual CPU0 in physical CPU0, with a priority of 6 and a time slice of 5. Logic control task 2 is assigned to virtual CPU1 in physical CPU0, with a priority of 6 and a time slice of 5. That is, virtual CPU0 and CPU1 have the same priority. In this case, the time slice rotation algorithm is adopted. Logic control task 1 runs for one time slice first, and then logic control task 2 runs for one time slice, alternating until the time slice ends.

[0079] In this embodiment, before step S1, the following steps are further included:

[0080] Step S0: The edge controller receives the optimized algorithm model sent by the cloud;

[0081] The algorithm model includes: a shield tail gap measurement algorithm, a rock slag identification model, and an automatic spray-mixing trajectory planning model.

[0082] When optimizing the algorithm model, the cloud-based system inputs the training dataset into the initialized algorithm model. Using the cross-entropy function and the Adam optimizer with a learning rate of 0.001, the algorithm is trained until the cross-entropy regression loss function is minimized, resulting in an optimized rock slag analysis model. The training dataset consists of historical data; for example, when optimizing the rock slag analysis model, the training dataset includes historical rock slag images, the rock slag classification results corresponding to these images, and the surrounding rock grade identification results.

[0083] The intelligent control system of the roadheader in this embodiment further includes: an actuator;

[0084] The executor is connected to the edge controller to receive the model calculation results sent by the edge controller and perform corresponding actions based on the model calculation results.

[0085] The intelligent control system of the roadheader in this embodiment further includes: a plurality of PLC substations;

[0086] The PLC substation is connected between the edge controller and the data acquisition device, and between the edge controller and the actuator, and is used to transmit data information and model calculation results.

[0087] For example, see Figure 2,Temperature sensors, pressure sensors, distance sensors and other sensors are responsible for collecting data information, which are connected to the edge controller through the PLC substation to transmit data signals, such as Figure 2 shown.

[0088] When the data acquisition device is a camera, a PLC substation may not be set up, and it can be directly connected to the edge controller to transmit rock slag images, shield tail gap images, and video data.

[0089] In addition, when the data acquisition device is a camera, a switch can be set up between the camera and the edge controller to manage and optimize network communications, thereby ensuring smooth transmission of image or video data and avoiding delays and packet loss.

[0090] In this embodiment, the roadheader intelligent control method further includes:

[0091] The edge controller saves the task scheduling information to the local end and generates a local configuration file.

[0092] The intelligent control method of a tunnel boring machine based on hybrid heterogeneous computing of the present invention can also be equipped with risk identification systems, intelligent tunneling systems and other systems for intelligent control of tunnel boring machines.

[0093] The present invention provides an intelligent control method for a tunnel boring machine based on hybrid heterogeneous computing. Due to the use of an edge computing controller with a multi-core CPU+FPGA+NPU hybrid heterogeneous architecture, the intelligent system of the tunnel boring machine can be centrally deployed on a single controller, reducing the redundancy of the controller hardware. At the same time, hybrid heterogeneous computing is used to realize the coordinated control of multiple system tasks of the tunnel boring machine's logical control and intelligent control, thereby ensuring the actual effect of multiple intelligent systems carried by the tunnel boring machine. In addition, this application realizes the interconnection and interoperability of the underlying data by uniformly storing and managing the data collected by the on-site terminal equipment and the processing results of each task, so that the application layer can easily call the terminal data, thereby greatly improving the data processing efficiency.

[0094] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0095] In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connect," "fixed," etc. should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; and internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0096] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0097] In the description of this specification, the terms "one embodiment", "some embodiments", "embodiments", "examples", "specific examples" or "some examples" refer to the specific features, structures, materials or characteristics described in conjunction with the embodiment or example and included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and features of different embodiments or examples, unless they are mutually inconsistent.

[0098] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may alter, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. An intelligent control method for roadheader based on hybrid heterogeneous computing, It is characterized in that The intelligent control method is applied to the intelligent control system of the roadheader. The system includes: a host computer platform for sending instructions to the edge controller to execute tasks and display model calculation results, a cloud for optimizing the algorithm model, a data acquisition device for collecting data information, and an edge controller. The intelligent control method of the roadheader includes: S1. The edge controller obtains the task information of the tunnel boring machine, and obtains the task scheduling information according to the task information of the tunnel boring machine and the resource scheduling strategy set in advance; S2. The edge controller receives an instruction from the host computer to start executing a task, and obtains a task scheduling order according to the instruction and task scheduling information; S3. According to the task scheduling sequence, the edge controller sends an instruction to collect data information to the data acquisition device, and receives data information fed back by the data acquisition device; S4. According to the data information fed back by the data acquisition device, the edge controller uses the algorithm model optimized in advance to process the data, obtain the model calculation results, and send the model calculation results to the host computer platform.

2. According to claim 1, the intelligent control method for a roadheader based on hybrid heterogeneous computing, It is characterized in that The edge controller includes: a virtual controller control module, K CPU virtual controllers, M NPU virtual controllers, and N FPGA virtual controllers; The virtual controller control module controls the K CPU virtual controllers, the M NPU virtual controllers, and the N FPGA virtual controllers for allocation.

3. According to claim 1, the intelligent control method for a roadheader based on hybrid heterogeneous computing, It is characterized in that In S1, the tunnel boring machine task information includes: The task type, the task's requirements for the controller's resource size, and the task's requirements for the controller's real-time performance.

4. The intelligent control method for a roadheader based on hybrid heterogeneous computing according to claim 2, It is characterized in that In S1, the resource scheduling strategy set in advance includes: When the task requires the controller to be as real-time as 50ms, it is assigned to the CPU virtual controller for execution. When the task has a real-time requirement of 1 to 10 ms for the controller, it is divided into FPGA virtual controller or CPU virtual controller for execution; When the task is an image processing task, it is divided into the NPU virtual controller for execution.

5. According to claim 2, the intelligent control method for a roadheader based on hybrid heterogeneous computing, It is characterized in that In S1, the task scheduling information includes: The virtual controllers corresponding to different tasks and the scheduling priority and time slice information of the virtual controllers.

6. The intelligent control method for a roadheader based on hybrid heterogeneous computing according to claim 2, It is characterized in that In S2, generating a task scheduling sequence according to the instruction and the task scheduling information includes: For virtual controllers that are not at the same priority level, the task scheduling order is determined according to the priority order; For virtual controllers with the same priority, a time slice round-robin algorithm is used to determine the task scheduling order based on the time slice information of the virtual controller.

7. The intelligent control method for a roadheader based on hybrid heterogeneous computing according to claim 1, It is characterized in that The S1 also includes: S0, the edge controller receives the optimized algorithm model sent by the cloud; The algorithm model includes: a shield tail gap measurement algorithm, a rock slag identification model, and an automatic spray-mixing trajectory planning model.

8. The intelligent control method for a roadheader based on hybrid heterogeneous computing according to claim 1, It is characterized in that The system further comprises: an actuator; The executor is communicatively connected to the edge controller, and is used for receiving the model calculation result sent by the edge controller, and performing corresponding actions according to the model calculation result.

9. The intelligent control method for a roadheader based on hybrid heterogeneous computing according to claim 8, It is characterized in that The system further comprises: a plurality of PLC substations; The PLC substation is connected between the edge controller and the data acquisition device and between the edge controller and the actuator, and is used to transmit data information and model calculation results.

10. The intelligent control method for a roadheader based on hybrid heterogeneous computing according to claim 1, It is characterized in that The method further comprises: The edge controller saves the task scheduling information to the local end and generates a local end configuration file.

Images