<abstract>
<p>The proposed research addresses the optimization challenges in servo motor control for pipe-cutting machines, aiming to enhance performance and efficiency. Recognizing the existing limitations in parameter optimization and system behavior prediction, a novel hybrid approach is introduced. The methodology combines a Dandelion optimizer algorithm (DOA) for servo motor parameter optimization and an Attention pyramid convolution neural network (APCNN) (APCNN) for system behavior prediction. Integrated with a Programmable Logic Controller (PLC) and human-machine interface (HMI), this approach offers a comprehensive solution. Our research identifies a significant research gap in the efficiency of existing methods, emphasizing the need for improved control parameter optimization and system behavior prediction for cost reduction and enhanced efficiency. Through implementation on the MATLAB platform, the proposed DOA-APCNN approach demonstrates a noteworthy 30% reduction in computation time compared to existing methods such as Heap-based optimizer (HBO), Cuckoo Search Algorithm (CSA), and Salp Swarm Algorithm (SSA). These findings pave the way for faster and more efficient pipe-cutting operations, contributing to advancements in industrial automation and control systems.</p>
</abstract>