Blockchain And Machine Learning-Based Real-Time Analysis of Smart Manufacturing

System to emerge as a foundational idea in administrative and deliberative contexts. Recent high-powered technologies, including the sensor-based Internet of Things (IoT), can provide enough means to keep tabs on the production process. This study proposes a method for keeping tabs on factories by combining the IoT, Machine Learning (ML), and other knowledges. Sensors connected to the Internet of Things record data about the surrounding environment. Sensors provide vast amounts of unstructured data that are updated in real time. The data is processed further using a variety of significant data methods. Fault detection in the production system is supported by a hybrid prediction model that employs the Random Forest organization method to filter out anomalies in the sensor data. The suggested technology was tested at South Korean automobile assembly plants. This system employs a strategy for securing and improving data trust to prevent the replacement of genuine data with dummy data and system transactions. In the results area, we show how our system performs compared to others. Associated to other inputs, the hybrid estimate model produces satisfactory fault predictions. Improvements in decision-making and reduced production errors are anticipated outcomes of the suggested approach.