Intelligent manufacturing is becoming increasingly important due to the growing demand for maximizing productivity and flexibility while minimizing waste and lead times. This work investigates automated secondary robotic food packaging solutions that transfer food products from the conveyor belt into containers. A major problem in these solutions is varying product supply which can cause drastic productivity drops. Conventional rule-based approaches, used to address this issue, are often inadequate, leading to violation of the industry's requirements. Reinforcement learning, on the other hand, has the potential of solving this problem by learning responsive and predictive policy, based on experience. However, it is challenging to utilize it in highly complex control schemes. In this paper, we propose a reinforcement learning framework, designed to optimize the conveyor belt speed while minimizing interference with the rest of the control system. When tested on real-world data, the framework exceeds the performance requirements (99.8% packed products) and maintains quality (100% filled boxes). Compared to the existing solution, our proposed framework improves productivity, has smoother control, and reduces computation time.

While not a magic bullet, artificial intelligence (AI) is changing the game for manufacturers faced with ongoing labor shortages, decreased productivity and quality control, and an unpredictable supply chain exacerbated by growing consumer demands. Increasingly sophisticated AI is already being used in nearly every industry--from automotive and food & beverage to metal fabrication and plastic molding--to power predictive systems, increase robot capabilities, improve the precision of machine vision and help businesses optimize their processes to improve quality and reduce waste. The future is here--and we're just getting started. As AI becomes more powerful, robots and other machines can quickly learn what they need to do to perform given tasks without expensive and difficult-to-find AI experts. When coupled with decreasing hardware costs and clearer use cases demonstrating the benefits, deploying AI is an obvious choice for small and large companies alike.

In today's world, artificial intelligence (AI) is transforming several industries, and many of us interact with AI on regular basis in some form or another. From banking and manufacturing to e-commerce and personalized advertisements, AI is becoming imperative in almost every business. Business experts believe that it is an essential tool for data analytics, predictive suggestions, chatbots, and so on. AI can be defined as any software algorithm which possesses human-like features, such as an ability to learn, plan, and solve problems. These attributes can be groomed, and the system made more intelligent depending upon the type of industry where it is going to be used.

In this paper we propose a new method to assist in labeling data arriving from fast running processes using anomaly detection. A result is the possibility to manually classify data arriving at a high rates to train machine learning models. To circumvent the problem of not having a real ground truth we propose specific metrics for model selection and validation of the results. The use case is taken from the food packaging industry, where processes are affected by regular but short breakdowns causing interruptions in the production process. Fast production rates make it hard for machine operators to identify the source and thus the cause of the breakdown. Self learning assistance systems can help them finding the root cause of the problem and assist the machine operator in applying lasting solutions. These learning systems need to be trained to identify reoccurring problems using data analytics. Training is not easy as the process is too fast to be manually monitored to add specific classifications on the single data points.

In this paper, we investigate a novel application of online planning and scheduling:controlling an automated infeeder for a packaging line of foodand consumer packaged goods. In this system, products arrive continuously at high-speedfrom the end of the production line and need to be arranged into a specific configurationfor downstream primary and secondary packaging machines.In collaboration with a domain expert from the packaging industry,we developed an innovative design for a reconfigurable parallel infeed system usinga matrix of interchangeable smart belts. We also adapted our online model-basedPlantrol planner to this domain. Our planner can control various configurations ofthe new infeed system through simulation both in nominal planning and when runtimefailures occur. We are also building a small physical prototype to validate the newdesign and our software framework.