Tech Advances Safety/Ergonomics

Today’s advanced technologies, applied carefully, can help reverse the trend of increasing industrial safety incidents.

The Industry 4.0 evolution (versus revolution) began about 2010 and is finally getting more widespread application in industry.

Augmented and virtual reality, more connected devices, better data historians, more practicable wearables, with machine learning can all assist in improved training concepts and prescriptive safety and ergonomics guidance from automated and ongoing data collection and analysis.

IIoT seems to be a reasonable next step to collect and sort out the mix of data from health monitoring, ergonomic stressors, and plant-floor daily activities to generate improvement recommendations. Just as your CMMS tracks asset data to help find root causes of symptoms to avoid repeat asset failures, the same can be done for safety and ergonomics. An example of two safety/ergonomic technologies that we use in our RMC training factory are Soter and MakUsafe.

SoterCoach, Wilmington, DE (soteranalytics.com), is a small wearable that monitors and collects data used to train muscle memory for better body postures during work activities. SoterTask is a cloud-based AI-driven ergonomic risk analysis using video of movements captured on a mobile application. The video and data and workplace tasks are available on the online dashboard.

MākuSafe, West Des Moines, IA (makusafe.com), is a wearable system that enables a safety, data, and analytics solution to improve worker health and safety by tracking workplace hazards and risk exposure, such as noise, temperature, lighting, and humidity. The AI-driven system combines a safety-management software platform with wearable technology that provides immediate access to real-time EHS data with predictive value. MākuSafe Motion Explorer addresses exertion risk, strains, MSDs, and cumulative ergonomic hazards.

Recently, workplace injuries are on the rise. This is true for fatal and non-fatal injuries. According to the U. S. Bureau of Labor Statistics (Census of Fatal Occupational Injuries Summary, 2022 (bls.gov)):

A worker died every 96 min. from a work-related injury in 2022 compared to 101 min. in 2021. There were 5,486 fatal work injuries recorded in the U. S. in 2022, a 5.7% increase from 5,190 in 2021. The fatal-work injury rate was 3.7 fatalities per 100,000 full-time equivalent (FTE) workers, up from 3.6 per 100,000 FTE in 2021. 

Private-industry employers reported 2.8-million nonfatal workplace injuries and illnesses in 2022, up 7.5% from 2021. This increase is driven by the rise in injuries, up 4.5% to 2.3 million cases, and illnesses, up 26.1% to 460,700 cases. The increase in illnesses is driven by the rise in respiratory illness cases, up 35.4% to 365,000 cases in 2022. This comes after a decrease in respiratory illnesses in 2021, compared to 2020.

Some average cost/work injuries (2023), that reflect the most-expensive injuries for workers include:

• Amputation: $118,837
• Fracture or dislocation: $60,934
• Burns: $48,671
• Infection or inflammation: $37,498
• Sprain or strain: $33,589
• Carpal tunnel syndrome: $33,477
• Lacerations, punctures, and ruptures: $33,348
• Concussions: $33,151

Industry 4.0 has significant possibilities for occupational health and safety. However, the path to full implementation has numerous opportunities and challenges. Examples of opportunities include:

• AI can look at large amounts of data quickly and prescribe focused training. It could even create training. Some companies have already been doing this with extensions of their CMMS system going to the training department for immediate needs. With the wholistic vantage point that AI offers, correlations could be quickly found and algorithms developed to track and minimize situations that led to injury.

• Monitoring health and safety (H&S) regulations in real time and prescribing interventions to reduce risk as the boundaries of limits are approached can be accomplished using smart technologies such as Soteranalytics and MākuSafe.

• AI works 24/7, can create more interest/enthusiasm, is faster and more accurate (if algorithms are correct), and has the potential for great revenue streams.

• Newly developed robots, cobots, mobile apps, augmented reality, and greater interconnectivity will all enhance what’s possible.

Examples of challenges include:

• Just as too many companies don’t trust their CMMS data to make the tough decisions, are you going to let AI control H&S and regulatory compliance with all the potential legal implications?

• AI is not necessarily fair, unbiased, ethical, or moral. Who decides on the programming/algorithms? What about data security?

• AI optimizes (versus reaching team-engaging consensus), can spread misinformation, generate errors with significant consequence, and can be wrong (especially in the early stages). Your AI applications should be monitored for accuracy of results and potential liabilities. If risk is too high, always have an off switch (regardless of how autonomous AI becomes).

As stated in “AI: Good or Bad?” Efficient Plant, Oct. 2023 (efficientplantmag.com), it appears that we are divided with curiosity, high hopes, and expectations. At the same time, there are deep concerns about ethics, misuse, and all the things that can go wrong with an intelligence that will eventually surpass humanity.

In an in-depth research report (“Assessing the influence of industry 4.0 technologies on occupational health and safety,” nih.gov), the findings highlight that, “the analyzed technologies (additive manufacturing, artificial intelligence, artificial vision, big data and/or advanced analytics, cybersecurity, internet of things, robotics, and virtual and augmented reality) help to reduce occupational health and safety risks (physical and mechanical). However, its impact depends on the type of technology and the method of application. Influences in new emerging risks, mainly psychosocial and mechanical, have been detected in all technologies except in internet of things. In addition, additive manufacturing, artificial intelligence, machine vision, internet of things, robotics, and virtual and augmented reality help to reduce ergonomic risks and artificial intelligence, big data, and cybersecurity psychosocial risks.”

I remember a meeting many years ago when Dr. W. Edwards Deming said, “If you know what you know and also what you don’t know, that is true knowledge.” On the surface that statement may not appear that profound, but the deeper interpretation is that you must always recognize what you don’t know before acting. AI will open many doors toward attaining immense knowledge, bringing us closer to true knowledge.

Although the use of these technologies (to be predictive, prescriptive, and proactive) in safety and ergonomics is still in the early adoption stage, as is machine learning/AI in North America, the learning curve is quickly accelerating. AI in safety and ergonomics/human factors has the potential to enable a next level of improvement opportunity. EP

Based in Knoxville, Dr. Klaus M. Blache is director of the Reliability & Maintainability Center at the Univ. of Tennessee, and a research professor in the College of Engineering. Contact him at kblache@utk.edu.