Edge computing terminal of hydrogen fuel cell system

Abstract

The utility model discloses an edge computing terminal of a hydrogen fuel cell system, which comprises a heterogeneous core processor, a data acquisition module and a network communication module, and is characterized in that the heterogeneous core processor is respectively connected with the data acquisition module and the network communication module; the signal input end of the data acquisition module is connected with the hydrogen fuel cell system, and target data of the hydrogen fuel cell system are acquired in a multi-path parallel mode. The heterogeneous core processor comprises a central processing unit, an embedded neural network processor and a graphics processor which are connected with one another, the central processing unit is configured to execute data processing and analysis tasks, and the embedded neural network processor and the graphics processor are configured to realize hardware algorithm acceleration and run a neural network model; and the network communication module is configured to upload the hydrogen fuel cell system target data processed by the heterogeneous core processor in a wireless or wired manner. The number of system modules can be reduced, the cost and the failure rate are reduced, and later maintenance is facilitated.

Description

Technical Field

[0001] The utility model relates to the technical field of hydrogen fuel cells, and in particular to an edge computing terminal of a hydrogen fuel cell system. Background Art

[0002] The current hydrogen fuel cell system needs to be connected to the TBOX terminal for the collection of various parameters of the fuel cell system. Since there are many parameters to be collected, and a single TBOX terminal cannot achieve parallel access to all data, a hydrogen fuel cell system needs to be equipped with multiple TBOXs, resulting in overall system redundancy, high cost, and inconvenient maintenance. Utility Model Content

[0003] In view of the problems of redundant hydrogen fuel cell system architecture, high cost and inconvenient maintenance caused by the low data collection and computing power levels of current TBOX terminals, the utility model proposes an edge computing terminal for a hydrogen fuel cell system, which can reduce the number of system modules, reduce costs and failure rates, and facilitate later maintenance.

[0004] The technical solution adopted by the utility model is as follows:

[0005] An edge computing terminal for a hydrogen fuel cell system comprises a heterogeneous core processor, a data acquisition module and a network communication module, wherein the heterogeneous core processor is respectively connected to the data acquisition module and the network communication module; the signal input end of the data acquisition module is connected to the hydrogen fuel cell system, and multiple channels of parallel acquisition of target data of the hydrogen fuel cell system are performed; the heterogeneous core processor comprises a central processing unit, an embedded neural network processor and a graphics processor which are connected to each other, wherein the central processing unit is configured to perform data processing and analysis tasks, and the embedded neural network processor and the graphics processor are configured to implement hardware algorithm acceleration and run a neural network model; the network communication module is configured to upload the target data of the hydrogen fuel cell system processed by the heterogeneous core processor in a wireless or wired manner.

[0006] Furthermore, the data acquisition module includes a plurality of CAN interfaces, which are connected to the hydrogen fuel cell system via a CAN bus.

[0007] Furthermore, different computing cores, namely the central processing unit, embedded neural network processor and graphics processor, are packaged in one chip to simultaneously perform multiple computing tasks.

[0008] Furthermore, the network communication module includes a 4G module, a 5G module, a Bluetooth module and an Ethernet module, and the 4G module, the 5G module, the Bluetooth module and the Ethernet module are respectively connected to the heterogeneous core processors.

[0009] Furthermore, it also includes a storage module, which is connected to the heterogeneous core processor and stores the collected data and algorithm code. Furthermore, the storage module includes an SD card, a FLASH memory and a hard disk.

[0010] Furthermore, it also includes an internal memory, which is connected to the heterogeneous core processor and supports complex algorithm operations. Furthermore, the internal memory includes memory bars of DDR3 and DDR4 specifications and supports a capacity of 32GB.

[0011] Furthermore, it also includes a power module, which is connected to the heterogeneous core processor and provides power for the entire edge computing terminal.

[0012] Furthermore, the edge computing terminal adopts a fanless, passive heat dissipation structure for heat dissipation.

[0013] The beneficial effects of the utility model are:

[0014] 1) The edge computing terminal replaces the TBOX terminal in the traditional hydrogen fuel cell system, which simplifies the system hardware architecture, reduces the power consumption of the whole system and improves reliability;

[0015] 2) Using heterogeneous multi-core processors, different computing cores are encapsulated in one chip, which can simultaneously perform multiple computing tasks with lower energy consumption;

[0016] 3) The edge computing terminal can simultaneously realize data collection, analysis and transmission of the fuel cell system, which facilitates the unified management of software and hardware and reduces the difficulty of operation and maintenance;

[0017] 4) The edge computing terminal is equipped with NPU and GPU computing units, which can run neural network models, greatly improving the intelligence level of the hydrogen fuel cell system.

[0018] 5) The edge computing terminal adopts a fanless, passive heat dissipation structure design, which is effectively dust-proof and waterproof, and is more suitable for the complex working environment of the fuel cell system.

[0019] In summary, the utility model uses edge computing terminals to replace the original TBOX terminals, making the system architecture more streamlined, the hardware cost lower, and effectively reducing the failure rate of the whole machine. Compared with the original TBOX terminals, edge computing terminals have higher computing power and stronger data collection and processing capabilities; the NPU and GPU cores have AI computing capabilities and can run neural network models, making the fuel cell system more intelligent. In addition, the edge computing terminal adopts a fanless, passive heat dissipation structure design, which can effectively prevent dust and water, and is more suitable for the complex environment in which the fuel cell system operates. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1This is a schematic diagram of the hardware architecture of an edge computing terminal of a hydrogen fuel cell system of the utility model. DETAILED DESCRIPTION

[0021] In order to have a clearer understanding of the technical features, purposes and effects of the utility model, the specific implementation methods of the utility model are now described. It should be understood that the specific embodiments described herein are only used to explain the utility model, and are not used to limit the utility model, that is, the embodiments described are only part of the embodiments of the utility model, rather than all the embodiments. Based on the embodiments of the utility model, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the utility model.

[0022] like Figure 1 As shown, this embodiment provides an edge computing terminal of a hydrogen fuel cell system, including a heterogeneous core processor, a data acquisition module and a network communication module, wherein the heterogeneous core processor is connected to the data acquisition module and the network communication module respectively, wherein:

[0023] The signal input end of the data acquisition module is connected to the hydrogen fuel cell system, so that multi-channel parallel acquisition of target data of the hydrogen fuel cell system can be realized. Preferably, the data acquisition module includes multiple CAN interfaces, which are connected to the hydrogen fuel cell system via a CAN bus.

[0024] The heterogeneous core processor includes a central processing unit (CPU), an embedded neural network processor (NPU) and a graphics processing unit (GPU) connected to each other. The central processing unit is configured to perform data processing and analysis tasks, and the embedded neural network processor and the graphics processing unit are configured to implement hardware algorithm acceleration and run neural network models. Different computing cores, namely the central processing unit, the embedded neural network processor and the graphics processing unit are encapsulated in one chip to implement multiple computing tasks at the same time. Preferably, the central processing unit can adopt an 8-core ARM 64-bit Cortex-A architecture and run the Linux operating system.

[0025] The network communication module is configured to upload the target data of the hydrogen fuel cell system processed by the heterogeneous core processor wirelessly or wiredly. Preferably, the network communication module includes a 4G module, a 5G module, a Bluetooth module and an Ethernet module, and the 4G module, the 5G module, the Bluetooth module and the Ethernet module are respectively connected to the heterogeneous core processor for collecting data upload and code update of the edge computing terminal.

[0026] Preferably, the edge computing terminal of this embodiment further includes a storage module, which is connected to the heterogeneous core processor and stores the collected data and algorithm code. More preferably, the storage module includes storage media such as an SD card, a FLASH memory, and a hard disk.

[0027] Preferably, the edge computing terminal of this embodiment also includes an internal memory, which is connected to the heterogeneous core processor and supports complex algorithm operations. More preferably, the internal memory includes a memory bar of DDR3 and DDR4 specifications, supporting a capacity of 32GB.

[0028] Preferably, the edge computing terminal of this embodiment also includes a power module, which is connected to the heterogeneous core processor and provides power for the entire edge computing terminal.

[0029] Preferably, the edge computing terminal of this embodiment adopts a fanless, passive heat dissipation structure design, which is effectively dustproof and waterproof, and is suitable for the complex working environment of the hydrogen fuel cell system.

[0030] The above is only a preferred embodiment of the utility model. It should be understood that the utility model is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art do not deviate from the spirit and scope of the utility model, and should be within the scope of protection of the claims attached to the utility model.

Claims

1. An edge computing terminal for a hydrogen fuel cell system, characterized in that: It includes a heterogeneous core processor, a data acquisition module and a network communication module, wherein the heterogeneous core processor is connected to the data acquisition module and the network communication module respectively; the signal input end of the data acquisition module is connected to the hydrogen fuel cell system, and multiple channels of parallel acquisition of target data of the hydrogen fuel cell system are performed; the heterogeneous core processor includes a central processing unit, an embedded neural network processor and a graphics processor which are connected to each other, wherein the central processing unit is configured to perform data processing and analysis tasks, and the embedded neural network processor and the graphics processor are configured to implement hardware algorithm acceleration and run a neural network model; the network communication module is configured to upload the target data of the hydrogen fuel cell system processed by the heterogeneous core processor by wireless or wired means.

2. The edge computing terminal of a hydrogen fuel cell system according to claim 1, characterized in that: The data acquisition module includes a plurality of CAN interfaces and is connected to the hydrogen fuel cell system via a CAN bus.

3. The edge computing terminal of a hydrogen fuel cell system according to claim 1, characterized in that: Different computing cores, namely the central processing unit, embedded neural network processor and graphics processor, are packaged in one chip to simultaneously perform multiple computing tasks.

4. The edge computing terminal of a hydrogen fuel cell system according to claim 1, characterized in that: The network communication module includes a 4G module, a 5G module, a Bluetooth module and an Ethernet module, and the 4G module, the 5G module, the Bluetooth module and the Ethernet module are respectively connected to heterogeneous core processors.

5. The edge computing terminal of a hydrogen fuel cell system according to claim 1, characterized in that: It also includes a storage module, which is connected to the heterogeneous core processor and stores the collected data and algorithm codes.

6. The edge computing terminal of a hydrogen fuel cell system according to claim 5, characterized in that: The storage module includes an SD card, a FLASH memory and a hard disk.

7. The edge computing terminal of a hydrogen fuel cell system according to claim 1, characterized in that: The system also includes an internal memory, which is connected to the heterogeneous core processor and supports complex algorithm operations.

8. The edge computing terminal of a hydrogen fuel cell system according to claim 7, characterized in that: The internal memory includes memory sticks of DDR3 and DDR4 specifications, supporting a capacity of 32GB.

9. The edge computing terminal of a hydrogen fuel cell system according to claim 1, characterized in that: It also includes a power module, which is connected to the heterogeneous core processor and provides power to the entire edge computing terminal.

10. The edge computing terminal of a hydrogen fuel cell system according to claim 1, characterized in that: The edge computing terminal adopts a fanless, passive heat dissipation structure for heat dissipation.

Images