Software improves AI, automation flexibility
Software-based artificial intelligence (AI) can be used to give robots abilities that allow them to straddle the flexibility gap between small batch manufacturing and high-volume automation.
- Manufacturers are dealing with a flexibility gap, which is the range between viable small batch manufacturing and high-volume automation. Many companies are having a hard time finding workers and usable automation.
- Software-based artificial intelligence (AI) can enhance existing robots to deal with variances in real-time and give them needed flexibility on the plant floor.
Artificial Intelligence Insights
- Artificial intelligence (AI) being used to make robots smarter has been growing in popularity as both technologies get better.
- Robots are being used to fill roles on the plant floor because there aren’t enough people.
- Robots won’t completely replace humans, but AI advances are making it so they will replace the dull, dirty and dangerous jobs.
Industrial automation continues to enable manufacturers to improve agility in adapting production processes to address rapidly changing markets, increase innovation, produce more cost effectively and shrink product delivery times. Automation also relieves human workers of the need to perform repetitious tasks that are monotonous and sometimes even dangerous.
Automating has been primarily a hardware-based process, with purpose-built machines that can provide substantial production savings for high-volume applications with long product lifecycles. However, conventional automation is becoming a less suitable solution these days. Manually programming, reconfiguring and maintaining hardware-based control systems is time-consuming. In high-mix, low-volume manufacturing, for example, deploying industrial robots is often not profitable. This is increasingly the case for markets where the trend is greater demand for high quality, individual products. Because the number of production steps varies between products, conventional robots in some industries have already reached their limit, and that trend will continue.
The flexibility gap hampers modern automation
Modern automation is hampered by what is called the “flexibility gap.” The more flexibility required in a manufacturing process, the more complex the automation required to accommodate it. When this complexity is implemented in hardware, the cost only can be justified by high volumes and long product lifecycles. In addition, this type of automation is not easy to repurpose as products continue to evolve in faster cycles.
When volumes are not high enough or a product has too many variances, people can take on those production tasks for which robots are too inflexible or too expensive to justify. However, manufacturing has been impacted by the ongoing global labor shortage. Even where manual manufacturing processes account for variances, lack of available workers willing to perform repetitious and monotonous tasks is halting productions lines.
With more manufacturing falling into the flexibility gap – the range between viable small batch manufacturing and high-volume automation – manufacturers need a new approach to meet product demand.
Software-based AI can narrow the automation flexibility gap
Manufacturers can overcome the automation flexibility gap with software-based artificial intelligence (AI). Rather than relying on specific, purpose-built hardware, manufacturers need a way to carry the flexibility of a person into robot-based processes. With AI, manufacturers can enhance existing robots to deal with variances in real-time. In this way, processes can be planned, optimized and automated with agility and efficiency.
Rather than continuing to invest in increasingly complex and expensive hardware with a shorter viable lifecycle, manufacturers can extend the capabilities and lifespan of robots with smart software. Advances in AI, especially in the subfield of machine learning (ML), offer companies ways to plan and improve manufacturing processes. For example, ML is already being used to substantially improve monitoring and maintenance of production facilities.
Software closes the flexibility gap by combining robotics with AI to enable the automation of manual workstations. With the help of AI-driven controls connected to a camera, robots gain hand-eye coordination and human-like flexibility. These robotic systems can be trained by a human to understand the general task to complete. Using AI, the system can then generalize the training across new situations and comparable variances in the manufacturing process, including differently shaped or positioned workpieces. The robot now can accommodate variances by independently adjusting its movements in real time.
A robot combined with an AI controller can be trained in a few hours through human demonstration. Numerous activities such as picking individual parts, in-feed movements, joining and tracking can be implemented with a special robot controller and one small camera mounted on the robot’s wrist.
The robot is taught what to do by demonstrating the required activity with typically occurring variances. During training, all necessary data is aggregated to build out a neural network in the cloud that can perform the task and variances. To assure operation reliability and safety, all cloud activities have to meet the highest safety standards.
Automotive supplier automates workpiece pickup with AI control
German-based company ZF, an automotive supplier, was faced with the challenge of reconciling flexibility and precision when automating the workpiece feed of a large-volume milling station where gears are produced.
In the work process, metal rings are removed from a crate and placed on a conveyor belt to later flow into the production of the gears. Several factors made this process difficult to automate. First, the production step is variable, as the rings shift in the delivered mesh box and are randomly arranged. The placement and shape of the box also could vary. Changing light conditions posed an additional challenge, and the surface of the rings could be shiny metallic, sometimes oil-smeared, or even corroded, making classic automation impossible.
ZF used an AI controller and a collaborative robot (cobot) in an automated workpiece fixture. Using its own controller, the cobot positions itself over the rings in the crate. The system then takes control, moving the robot independently to the next ring to bring the gripper into the correct three-dimensional gripping position. The robot resumes control, picking up the ring and moving it to the conveyor belt for placement. The robot with added AI setu took only a few days.
Reliable quality control management: AI checks for coolant leaks
Another premise for success in manufacturing is a constantly high level in product quality, which is why accurate quality management is so important. On the other hand, it is equally important to notice the overriding goal of automation is to reduce the workload of humans. As the example of BSH Hausgeräte GmbH proves, it is possible to find a feasible and intuitive solution resolving quality while reducing human workloads.
In this case, the Spanish production site of a major European white goods manufacturer relied on automation for checking coolant leaks on refrigerators. The so-called fridge sniffing is a monotonous, error-prone activity. In this application, refrigerator manufacturers use hand-held probes to search for cooling leaks in solder joints of compressors and copper piping. When a leak goes undetected, harmful substances can escape, so this is an important safety test.
To ensure the pipes are leak-proof, a probe is brought to within a millimeter of a solder joint, which can vary in position. The AI control system guides the robot to the joint to detect possible leaks. In this way, the robot can perform a tedious task with repeatable precision and consistent quality.
Software-based AI enables more automation for manufacturing
Enhancing a robot’s ability to accommodate variances is one example of how AI can bridge the flexibility gap. With AI, production efficiency, reliability, and quality can be improved and maintained. However, the benefits of AI can extend beyond automating manufacturing processes.
For example, through AI/ML, decision-makers can have faster access to real-time information about production lines, supply chains and product operations. This will enable them to better evaluate future product development, new business models, and overall strategic decisions.
This information also can be used by robots to improve their own operation. Predictive maintenance, for example, is a technology where AI can track robotic operations across a factory floor. Over time, the AI can predict when various equipment will need maintenance. Rather than shut down production when equipment fails, such maintenance can be scheduled so the impact on production is minimized.
AI in automation is the key factor for future success for manufacturers from all industries. Instead of relying on complex and expensive hardware solutions or manual workstations, AI software can extend the necessary agility for robotic equipment to overcome the flexibility gap. AI not only accelerates automation and the training of robots, but it also changes how developers and designers can plan production to be more economical as products become more complex.
Companies that adopt AI-based software to augment automated processes will have the agility to adapt to changing market conditions, shifts in customer requirements and shorter product lifecycles.
Keywords: artificial intelligence, robotics, automation
See additional robotics stories at https://www.controleng.com/discrete-manufacturing/robotics/
How are you working to close the flexibility gap?
Original content can be found at Control Engineering.