Omron Corporation announced the development of a machine automation controller equipped with a machine learning artificial intelligence (AI) algorithm.
The first of its kind in the industry, this AI-equipped controller achieves real-time integration between the programmable logic controller function, which controls production lines and equipment changing in microseconds on factory floors, and the AI processing function. Using our extensive range of sensors to monitor the status of equipment and processes, the controller safely regulates them before an irregularity can occur. It predicts unusual movements of machinery based on the causal model that the built-in AI has been made to learn.
As recent years have seen an ever-increasing shift toward small-lot production for a wide array of products and flexible production at optimal locations around the globe, the need has continually risen for the introduction of AI and the internet of things (IoT) on manufacturing floors. It allows manufacturers to contain the impact of skilled worker shortages and surging labor costs, while simultaneously increasing equipment utilization and achieving stable production of quality products. To leverage data at manufacturing sites where control is performed in microseconds, high-speed and high-precision data gathering (e.g. position, vibration, and temperature data) and precisely associating them with time data is required.
Analyzing and utilizing combined data allows us to quickly predict possible machine errors and prevent equipment stoppage, as well as deterioration of product quality. Meanwhile, rapid diffusion of IoT has brought along with it a huge quantity of data, making it difficult to transmit all data to the cloud for analysis by AI, regardless of how far network bandwidth is extended. Another bottleneck in introducing IoT to manufacturing floors is caused by the response delay resulting from bilateral data transmission generated when data from sensors, motors, and other devices must be transmitted to and from the cloud, even though instantaneous response is crucial at such manufacturing sites.
In our search for solutions to such issues, we introduce “intelligence developed through ICT” to manufacturing floors. We incorporate the knowhow of skilled workers into the controls of equipment and processes. This is accomplished by utilizing a broad range of factory automation (FA) equipment that enables IoT-capable automated production or implements optimal AI algorithms in such equipment. Developed under this concept, the AI-equipped controller is meant to immediately detect signs of equipment irregularity. The machine automation controller’s AI algorithms allow it to learn the repeated movements of the equipment from precise sensing data, which enables feedback to status monitoring and real-time control of machines.
How the machine automation controller uses AI in production processes:
1. Gathers sensing data (e.g. vibration and temperature) and output data for motors from equipment and processes it chronologically in real-time
2. Generates characteristic quantities at regular or irregular times based on chronological data in real-time
3. Accumulates characteristic quantity data and generates model data of learning machine after causal analysis
4. Sends feedback to condition monitoring and controls based on such model data in real-time
In order to make AI technology a handy tool on manufacturing floors, we will advance the development of our controller, vision sensor, and other AI-equipped products. We will use AI and IoT to monitor the status of equipment and processes and assure product quality, thereby assisting its customers in realizing manufacturing processes that “produce no defects and do not stop”. Since sample shipments of the controller to some customers began in 2016, we have conducted demonstrations at our and customers’ factories. The demo's aimed to predict and analyze equipment irregularities and enhance knowledge of the cause-and-effect relationship involved in such irregularities, prior to the scheduled launch and service provision in 2018.
Having long developed and delivered FA equipment essential for very diverse manufacturing sites, we take pride in the fact that it continues to offer new advantages to its customers. Improvements that have been made possible through proactive use of the world’s most cutting-edge information technology, including EtherCAT®, IO-Link, and other open networks. Tapping into its wealth of knowhow in implementing AI algorithms into equipment, cultivated over more than two decades, we have been able to develop the table tennis robot FORPHEUS.
FORPHEUS is the epitome of Omron’s core technology of “Sensing & Control + Think”. The smart tutoring robot makes use of core technologies like OKAO Vision face/individual recognition technology and the world’s first on-board sensor equipped with “technology that senses the degree of driver concentration”. By combining automation knowhow for manufacturing floors, using a variety of FA equipment and robot technology with state-of-the-art AI algorithms, we support manufacturing businesses that are troubled by the shortage of human resources and rise of labor costs. We accelerate a transition to the “manufacturing floors of the future” in which “machines bring out human capabilities and creativity”.