The rapid growth of industrial wireless sensor networks (IWSNs) is due to their improved scalability and low cost of positioning cluster nodes. However, the existing machine learning (ML) approaches failed to solve the challenges like energy optimization in cluster routing, which industrial users must consider to improve energy efficiency-based routing in IWSN. To overcome this problem, an Improved Bald Eagle Search (IBES) optimization algorithm is proposed for energy-efficient clustering routing by an exploring strategy that helps to find cluster heads effectively. Initially, the network of the model was assumed based on three things. Then, in the communication and transmission model of IWSN, the energy consumption of receiving and transmitting nodes is considered. After that, the IBES clustering approach reduces energy efficiently by searching optimal cluster head in IWSN. The experimental analysis indicates promising results for energy optimization in IWSN with residual energy, dead nodes, and energy consumption for nodes of 100, 150, 200, 250, and 300 are 0.9, 1.2, 1.4, 1.8, and 2.2 J which is lesser than other existing methods like Quantum Elite Grey Wolf Optimization (QEGWO), Angle-Based Critical Node Detection (ABCND), and Multi-Objective Binary Grey Wolf Optimizer (MOBGWO).