Excessive-mix manufacturing poses many challenges for robotic automation. We now have seen many spectacular demonstrations of robotic automation in high-mix functions during the last 10 years. Typically these demonstrations are at expertise readiness degree (TRL) 5 or 6 degree. These demonstrations generate a substantial amount of curiosity in expertise and folks begin anticipating fast expertise transition.
Nevertheless, expertise 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 totally 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 expertise demonstration initiatives concentrate on growth 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 concentrate on exhibiting that acceptable course of high quality will be achieved utilizing a small variety of consultant components.
Listed below are explanation 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 sexy choice to complement conventional machine imaginative and prescient approaches. Solely a restricted quantity of knowledge will be collected in the course of the demonstration venture to coach a mannequin to carry out notion operate. Sensor noise is rigorously managed throughout demonstrations to make sure success. Area deployments inherently have a excessive quantity of sensor noise that breaks the notion system educated on restricted knowledge.
Creating a sturdy system able to functioning effectively within the discipline requires coaching the notion system with a considerable amount of knowledge and deciding on an structure that may successfully take care of the sensor noise. Constructing a sturdy notion system able to performing effectively within the discipline requires accessing many robotic cells and accumulating knowledge from these cells below all kinds of situations.
This isn’t possible in the course of the proof-of-concept demonstration methods. Utilizing artificial knowledge is a viable method, Nevertheless, artificial knowledge is just helpful if it matches actuality. So, constructing an artificial knowledge technology pipeline just isn’t helpful throughout demonstration levels. Due to this fact, the notion system developed throughout demonstrations typically requires important redesign. This takes important time and sources.
2. Restricted half variety makes it troublesome to design sturdy algorithms
Demonstrations are carried out on a restricted variety of half geometries. Which means the planning and management capabilities are usually 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 just isn’t attainable in the course of the demonstration part. Due to this fact, conclusions drawn concerning the feasibility of planning and management approaches don’t generalize throughout deployment.
3. Processes are usually not optimized for robots
Many handbook processes are designed based mostly on human capabilities. Robots have basically totally different capabilities. Demonstrations that concentrate on robotic methods which can be 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 subsequently can use cheaper abrasives and dramatically scale back abrasive prices.
Robots are very constant and, subsequently, can use aggressive course of parameters with out the danger of inflicting half harm. This has the potential to dramatically scale back the cycle time. Automation may also use device motions that will not be possible for people to execute on account of pace or vibration issues. Most demonstration initiatives concentrate on automation and should not have sources to appreciate course of innovation wanted for profitable deployment. It’s typically attainable to attain superhuman efficiency by investing enough sources in course of innovation for robotic automation and creating pathways to favorable ROI for profitable deployment.
4. Human-system interplay points are usually not thought-about
In lots of functions, full automation just isn’t possible. Typically, we will notice important advantages if we will automate 90% or 95% of the duty. This ensures that the automation answer doesn’t grow to be 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 process is carried out by people.
This mannequin works in precept. Nevertheless, most demonstration initiatives ignore points associated to human integration with robotic cells. For instance, it is very important 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 will be saved very excessive, it’s troublesome to justify robotic automation value. For instance, if a human employee can assist a number of cells, then human employee utilization will be excessive and automation will be justified.
Alternatively, a robotic cell will be designed to maintain the robotic busy for half-hour or extra and subsequently giving the human operator enough time to work on different duties Most demonstration initiatives concentrate on the design of a single cell. Due to this fact, human integration subjects are ignored. This results in design of methods that can not be justified as a result of they result in a number of idle time for human employees.
5. Workforce readiness points are usually not addressed
Workforce associated points are sometimes not addressed throughout demonstration initiatives. Good automation is usually offered as an answer to labor scarcity. Nevertheless, people are an integral a part of the manufacturing course of. To get the total worth of automation, we’d like employees with the fitting ability units. For instance, human operators could must work together with automated machines and robotic cells by feeding components into them or eradicating components from them. If human employees can’t successfully make the most of the automated tools, it can’t ship worth.
For present employees to carry out successfully, the interface to the automation system should 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 keep up 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 can be deployed in high-mix functions are advanced cyber-physical methods working in dynamic environments. Due to this fact, there’s important potential for the onset of adversarial situations that if not dealt with promptly can function a precursor to failure. Beneath are just a few consultant examples. Stress within the airline can fluctuate and might 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 severe failure and trigger harm. For instance, if the sensing system is performing suboptimally, then it could result in a collision that will break a cable or the device.
Recovering from severe failures requires appreciable human experience and important 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 enough quantities of coaching knowledge to implement a PHM system to ship an enough degree of system availability. Due to this fact, PHM associated points are usually not addressed throughout demonstration. Growing a PHM system wanted for profitable deployment requires a considerable quantity of extra sources.
7. Lack of service infrastructure
A PHM system can difficulty alerts and produce 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 almost certainly want an outdoor firm to service the robotic cells. These service associated points are usually not addressed in the course of the demonstration initiatives. With out addressing this difficulty, it’s not attainable to deploy robotic options in high-mix manufacturing functions.
8. Robotic cells are usually not optimized to ship acceptable efficiency
For a robotic cell to carry out effectively, the general cycle time must be optimized. This requires addressing automation of a number of auxiliary features comparable to device change, particles assortment, calibration and so forth. This typically requires including extra {hardware} and software program capabilities. This in flip can enhance prices. Deploying a system requires a trade-off between cycle time and value and discovering a system design idea that delivers helpful worth. Demonstration initiatives typically ignore all these system design points and narrowly concentrate on the method automation. Due to this fact, a number of new technological growth must happen to automate auxiliary features earlier than a system will be efficiently deployed.
9. The general manufacturing system just isn’t streamlined to allow the automation answer to ship its true worth
Demonstration initiatives take 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 will be efficiently automated, its general efficacy will be restricted by downstream processing steps. For instance, if a downstream course of is inefficient, it should grow to be 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’t ship its full worth.
Moreover, if the downstream course of is handbook, then it’d neutralize the top quality produced by the automated course of. However, if an upstream course of is handbook and displays important variability in high quality, it could pose a problem for the automated course of. Variability could drive the automated course of to carry out extra work, slowing it down, or lead to decrease high quality outputs. Automation typically can’t repair high quality issues originating from upstream processes. Due to this fact, when deploying an automatic course of step, it’s essential to contemplate the complete workflow. This will likely require adjustments within the general course of circulate and system-level optimization to make sure the automated course of step can ship the anticipated worth. This step can take important time and sources 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 will 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 indication system right into a manufacturing system, the associated fee will increase quickly due to all the components talked about above. Due to this fact, ROI turns into onerous to justify purely based mostly on the labor financial savings. ROI can grow to be extra favorable if extra values are delivered. For instance, automated options can scale back use of consumables and supply important course of innovation. These components are usually not thought-about throughout demonstration initiatives and integrating these throughout deployment requires important time and sources.
Most pilot demonstration initiatives primarily concentrate on demonstrating the feasibility of automating a course of step. We now have seen a number of reinvention of recognized applied sciences/ideas throughout demonstrations initiatives. These kinds of demonstration initiatives don’t add a lot worth to expertise deployment. Efficiently, deploying robotic automation in high-mix manufacturing functions requires a number of supporting expertise growth, system design, and consideration of workforce points. All of those require substantial sources and time. And not using a correct answer 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 economic system of scale crucial to achieve success in deployment. Due to this fact, a company thinking about deploying robotic automation in high-mix manufacturing both must have calls for for a lot of robotic cells to create the economic system of scale internally or associate with an exterior group that has already addressed the scaling difficulty.
In regards to the writer
Dr. Satyandra Okay. 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 Middle 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 printed 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), Strong Modeling Affiliation (SMA), and Society of Manufacturing Engineers (SME). He has obtained 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 Yr Award on the College of
