Introduction

With the continuous advancement of the great trend of Artificial Intelligence (AI), more and more fields are leveraging AI to drive industrial upgrading and improve the efficiency of products or projects. In industrial control applications, the demand for automation is also increasing, and in many scenarios, there is an urgent desire for the introduction of AI technology to bring about product performance improvements. This is especially true in areas such as factory manufacturing lines and industrial robots, where AI technology is often needed to enhance the efficiency of image recognition and fault analysis [1~3]. On the other hand, industrial control emphasizes product stability and the convenience of product programming applications. How to simultaneously meet the application needs of both aspects is a direction the industry is currently striving for.

Currently, there are two common modes:

(1) Directly developing AI algorithms, performing AI computations, and programming industrial control logic on an AI computer.

This mode primarily presents three problems:

The entire system is relatively bulky and costly.
After all, an AI computer is not like an embedded system; its system stability cannot be guaranteed, which is fatal for industrial reliability requirements.
A problem that cannot be ignored is that programming industrial control on a computer has a high development threshold, and functional adjustments and changes are troublesome, making it unable to meet the needs of on-site application engineers.

(2) Using an embedded system with AI computing power in conjunction with a PLC for functional development [4]. This method can solve stability issues, but the overall cost is relatively high. Moreover, the combination of two systems requires data communication and instruction interaction, and the development and adaptation work involved has a high threshold and significant investment.

To address the above problems, this paper proposes a new type of PLC controller that can support AI functions, lower the technical barrier brought by AI technology applications, and meet the configuration programming development method that electrical engineers are proficient in.

1 PLC Functional Architecture

The PLC controller proposed in this paper adopts an integrated design of an AI computing core and PLC control. Its programming method is completely consistent with general PLCs, providing a configuration programming environment that supports the 5 programming languages of the IEC 61131-3 standard, including ST, LD, IL, FBD, and SFC languages. It supports common digital and analog input/output, and its built-in Modbus RTU/TCP and CANopen protocols are also applicable to most industrial control scenarios. For AI functions, this PLC provides multiple camera input interfaces, achieving AI image processing through function block configuration. The overall system functional block diagram is shown in Figure 1.

![](https://pub-048dcb96257f476697b113fcb5939cb9.r2.dev/blog/145