Excessive-mix manufacturing poses many challenges for robotic automation. We have now seen many spectacular demonstrations of robotic automation in high-mix functions over the past 10 years. Typically these demonstrations are at know-how readiness stage (TRL) 5 or 6 stage. These demonstrations generate a substantial amount of curiosity in know-how and folks begin anticipating speedy know-how transition.
Nonetheless, know-how maturation on this space has been very gradual. Only a few robotics applied sciences have been really deployed in high-mix functions. This text explores the explanations behind this gradual transition.
Robotic automation for high-mix functions requires a basically completely different method. Parts of this method embrace:
- 1. Sensor-based methods for constructing half and workspace fashions
- 2. Automated robotic trajectory technology based mostly on half fashions constructed from sensing
- 3. Management system to deal with sensor uncertainties
Most know-how demonstration initiatives give attention to improvement of notion, planning, and management capabilities to automate the duty. Generally, novel human-robot interplay capabilities are developed as a part of these demonstration efforts. Success metrics throughout demonstration typically give attention to exhibiting that acceptable course of high quality may be achieved utilizing a small variety of consultant components.
Listed below are the reason why robotics demonstrations fail to transition to deployments in high-mix manufacturing environments.
1. Lack of knowledge to successfully use AI-based approaches
Excessive-mix manufacturing requires use of sensors to localize components and assess high quality. So, utilizing an AI-based notion system turns into a beautiful choice to complement conventional machine imaginative and prescient approaches. Solely a restricted quantity of knowledge may be collected throughout the demonstration challenge to coach a mannequin to carry out notion operate. Sensor noise is fastidiously managed throughout demonstrations to make sure success. Subject deployments inherently have a excessive quantity of sensor noise that breaks the notion system skilled on restricted knowledge.
Creating a strong system able to functioning nicely within the subject requires coaching the notion system with a considerable amount of knowledge and choosing an structure that may successfully cope with the sensor noise. Constructing a strong notion system able to performing nicely within the subject requires accessing many robotic cells and gathering knowledge from these cells underneath all kinds of circumstances.
This isn’t possible throughout the proof-of-concept demonstration methods. Utilizing artificial knowledge is a viable method, Nonetheless, artificial knowledge is barely helpful if it matches actuality. So, constructing an artificial knowledge technology pipeline isn’t helpful throughout demonstration phases. Due to this fact, the notion system developed throughout demonstrations typically requires vital redesign. This takes vital time and assets.
2. Restricted half range makes it tough to design sturdy algorithms
Demonstrations are carried out on a restricted variety of half geometries. Because of this the planning and management capabilities should not examined rigorously. New half geometries encountered throughout deployment pose challenges for planning and management algorithms, typically requiring main upgrades to the method that may take a very long time to finish. Correctly validating planning and management capabilities requires testing with a number of hundred half geometries. This scale of testing isn’t doable throughout the demonstration part. Due to this fact, conclusions drawn relating to the feasibility of planning and management approaches don’t generalize throughout deployment.
3. Processes should not optimized for robots
Many handbook processes are designed based mostly on human capabilities. Robots have basically completely different capabilities. Demonstrations that concentrate on robotic methods which are human-competitive when it comes to pace are sometimes removed from being cost-effective throughout deployment. Efficiently integrating robotic automation requires course of improvements by creating new course of recipes. For instance, robots can apply a lot increased forces and due to this fact can use cheaper abrasives and dramatically scale back abrasive prices.
Robots are very constant and, due to this fact, can use aggressive course of parameters with out the danger of inflicting half injury. This has the potential to dramatically scale back the cycle time. Automation also can use device motions that will not be possible for people to execute on account of pace or vibration concerns. Most demonstration initiatives give attention to automation and don’t have assets to appreciate course of innovation wanted for profitable deployment. It’s typically doable to attain superhuman efficiency by investing sufficient assets in course of innovation for robotic automation and creating pathways to favorable ROI for profitable deployment.
4. Human-system interplay points should not thought of
In lots of functions, full automation isn’t possible. Typically, we will understand vital advantages if we will automate 90% or 95% of the duty. This ensures that the automation resolution doesn’t turn into overly costly to automate the toughest a part of the job. Due to this fact, many demonstration initiatives goal automation of 90% or 95% of the duty. The remaining activity is carried out by people.
This mannequin works in precept. Nonetheless, most demonstration initiatives ignore points associated to human integration with robotic cells. For instance, you will need to determine what work a human employee would do when the robotic is engaged on the half. They can’t be merely watching the robotic and ready for his or her flip to do the work. Until the human employee utilization may be stored very excessive, it’s tough to justify robotic automation value. For instance, if a human employee can assist a number of cells, then human employee utilization may be excessive and automation may be justified.
Alternatively, a robotic cell may be designed to maintain the robotic busy for half-hour or extra and due to this fact giving the human operator enough time to work on different duties Most demonstration initiatives give attention to the design of a single cell. Due to this fact, human integration matters are ignored. This results in design of methods that can’t be justified as a result of they result in a whole lot of idle time for human staff.
5. Workforce readiness points should not addressed
Workforce associated points are sometimes not addressed throughout demonstration initiatives. Good automation is usually offered as an answer to labor scarcity. Nonetheless, people are an integral a part of the manufacturing course of. To get the total worth of automation, we’d like staff with the fitting ability units. For instance, human operators could have to work together with automated machines and robotic cells by feeding components into them or eradicating components from them. If human staff can not successfully make the most of the automated tools, it can not ship worth.
For current staff to carry out successfully, the interface to the automation system have to be intuitive and easy to make use of. Ease of person interface and coaching is a key to getting buy-in from the workforce. One other problem is the upkeep and servicing of automation applied sciences. Typically creating in-house expertise to take care of automation tools turns into cost-prohibitive and the methods fail to transition on account of lack of workforce readiness.
6. Low system availability on account of failures and time wanted to restore
Robotic cells which are deployed in high-mix functions are complicated cyber-physical methods working in dynamic environments. Due to this fact, there may be vital potential for the onset of adversarial circumstances that if not dealt with promptly can function a precursor to failure. Under are just a few consultant examples. Strain within the airline can fluctuate and may result in the malfunction of pneumatic elements; Suboptimal particles removing can result in issues with imaging methods; Elevated friction within the rail drive system can result in overheating of motors; Human errors can result in the loading of improper instruments or inadequate clamping of components. Any of those errors can result in critical failure and trigger injury. For instance, if the sensing system is performing suboptimally, then it might result in a collision that will break a cable or the device.
Recovering from critical failures requires appreciable human experience and vital downtime. This limits system availability. Delivering excessive system availability requires creating and deploying an AI-based Prognostics and Well being Administration (PHM) system. A single robotic cell implementation throughout demonstration will be unable to provide sufficient quantities of coaching knowledge to implement a PHM system to ship an sufficient stage of system availability. Due to this fact, PHM associated points should not addressed throughout demonstration. Creating a PHM system wanted for profitable deployment requires a considerable quantity of further assets.
7. Lack of service infrastructure
A PHM system can problem alerts and convey the system to a secure state. Generally, recovering from adversarial occasions detected by the PHM system requires service. Due to this fact, the PHM system must be complemented by a service infrastructure. This requires fielding a service staff to assist robotic cells. If a company has deployed only a few cells, then it’s economically infeasible for them to develop an in-house service staff. They may probably want an out of doors firm to service the robotic cells. These service associated points should not addressed throughout the demonstration initiatives. With out addressing this problem, it’s not doable to deploy robotic options in high-mix manufacturing functions.
8. Robotic cells should not optimized to ship acceptable efficiency
For a robotic cell to carry out nicely, the general cycle time must be optimized. This requires addressing automation of a whole lot of auxiliary features corresponding to device change, particles assortment, calibration and many others. This typically requires including further {hardware} and software program capabilities. This in flip can improve prices. Deploying a system requires a trade-off between cycle time and price and discovering a system design idea that delivers helpful worth. Demonstration initiatives typically ignore a majority of these system design points and narrowly give attention to the method automation. Due to this fact, a whole lot of new technological improvement must happen to automate auxiliary features earlier than a system may be efficiently deployed.
9. The general manufacturing system isn’t streamlined to allow the automation resolution to ship its true worth
Demonstration initiatives have a look at the method automation in insolation with out contemplating upstream or downstream steps. Sometimes, a course of step that faces high quality points or is difficult from an ergonomic perspective is focused for automation. Even when this course of step may be efficiently automated, its general efficacy may be restricted by downstream processing steps. For instance, if a downstream course of is inefficient, it’ll turn into a bottleneck. Even when the automated course of operates at excessive pace, it is not going to be absolutely utilized on account of downstream bottlenecks and therefore it can not ship its full worth.
Moreover, if the downstream course of is handbook, then it would neutralize the top quality produced by the automated course of. Then again, if an upstream course of is handbook and displays vital variability in high quality, it might probably pose a problem for the automated course of. Variability could power the automated course of to carry out further work, slowing it down, or end in decrease high quality outputs. Automation typically can not repair high quality issues originating from upstream processes. Due to this fact, when deploying an automatic course of step, it’s essential to think about your entire workflow. This will require modifications within the general course of circulation and system-level optimization to make sure the automated course of step can ship the anticipated worth. This step can take vital time and assets and therefore delay deployment.
10. Infrastructure to replace/improve software program doesn’t exist
Automation in high-mix functions makes use of a major quantity of software program. This software program must be maintained and up to date at common intervals. Demonstration initiatives don’t account for these wants. Constructing infrastructure for steady upgrades may be costly for particular person websites. However sadly, automation in high-mix functions can’t be deployed with out this infrastructure.
11. ROI can’t be justified based mostly on labor saving alone
Typically, when efforts are made to mature an illustration system right into a manufacturing system, the fee will increase quickly due to the entire elements talked about above. Due to this fact, ROI turns into arduous to justify purely based mostly on the labor financial savings. ROI can turn into extra favorable if further values are delivered. For instance, automated options can scale back use of consumables and supply vital course of innovation. These elements should not thought of throughout demonstration initiatives and integrating these throughout deployment requires vital time and assets.
Most pilot demonstration initiatives primarily give attention to demonstrating the feasibility of automating a course of step. We have now seen a whole lot of reinvention of recognized applied sciences/ideas throughout demonstrations initiatives. A majority of these demonstration initiatives don’t add a lot worth to know-how deployment. Efficiently, deploying robotic automation in high-mix manufacturing functions requires a whole lot of supporting know-how improvement, system design, and consideration of workforce points. All of those require substantial assets and time. With no correct resolution deployment roadmap, demonstration initiatives are prone to be shelved.
It’s extremely unlikely that the event of some robotic cells will allow a company to create the financial system of scale essential to achieve success in deployment. Due to this fact, a company occupied with deploying robotic automation in high-mix manufacturing both must have calls for for numerous robotic cells to create the financial system of scale internally or associate with an exterior group that has already addressed the scaling problem.
Concerning the writer
Dr. Satyandra Ok. Gupta is co-founder and chief scientist at GrayMatter Robotics. He additionally holds Smith Worldwide Professorship within the Viterbi Faculty of Engineering on the College of Southern California and serves because the Director of the Heart for Superior Manufacturing. His analysis pursuits are physics-informed synthetic intelligence, computational foundations for decision-making, and human-centered automation. He works on functions associated to Manufacturing Automation and Robotics.
He has revealed greater than 5 hundred technical articles in journals, convention proceedings, and edited books. He additionally holds twenty one patents. He’s a fellow of the American Society of Mechanical Engineers (ASME), Institute of Electrical and Electronics Engineers (IEEE), Stable Modeling Affiliation (SMA), and Society of Manufacturing Engineers (SME). He has acquired quite a few honors and awards for his scholarly contributions. Consultant examples embrace a Presidential Early Profession Award for Scientists and Engineers (PECASE) in 2001, Invention of the 12 months Award on the College of
