According to the latest figures from the National Safety Council, more than 4,500,000 workplace injuries occur annually. That’s one injury every seven seconds. At this rate, that equates to $161.5 billion in costs each year.
And while the organizations often implement extensive workplace safety rules, accidents still happen. But help is coming in the form of the Internet of Things (IoT), which can bring about significant improvements in workplace safety.
A subset of IoT is the Industrial Internet of Things (IIoT), which refers to the interconnectedness of industrial equipment, facilities, personnel
The Collaboration of IoT and Advanced “Accessories”
In today’s world, chest bands, wrist watches, implants and electrodes are doing the job of data collection. But change is coming. For example, the firm Karlsson Robotics has developed textile fabrics (EeonTex Conductive Fabric) built with fibers able to conduct electrical charges. These fabrics, many using silver-based fibers, can be used with sensors to gather personnel’s physical conditions and predict potential workplace safety issues.
They also offer optical fiber fabrics capable of generating images on fabrics, such as on the backs or sleeves of work shirts. Work instructions, text messaging, emails and parts images look to be only a few short steps away.
Using these sorts of collection methods, exoskeleton vests were recently unveiled by US automaker Ford to be used to reduce worker injury and fatigue. E-textiles with embedded nano-sensors, conductive polymers, inks
The Best Examples Come from the Construction Industry
As an industry that accounts for most workplace injuries, it is not surprising that progress is being made in the construction industry as well. Hard hats containing sensors that monitor workers’ physical conditions such as heart-rates, fatigue, temperature, oxygen levels and stresses are currently available.
These “smart hats” also gather data on working conditions such as equipment temperatures, dust, toxic conditions, and sudden accelerations (as might be experienced in a fall). Sensors in the hat are interconnected to a communication network which transmits this data to analytical software able to predict unsafe conditions before they become critical. Improved workplace safety on construction sites is the result.
Within IIoT, several important technologies are coming together to collect and analyze the mass of personnel and equipment data used to predict unsafe working conditions or production information such as out of spec processes.
The combinations of five converging technologies work together to process and identify trends not apparent to ordinary human review. These five important developments include:
- Interconnected devices
- Artificial intelligence
- The cloud storage
- Big data processing
- Deep dive analytics
The type and amount of data collected via interconnected devices are potentially so large that, at present, complete analysis to identify patterns and forecast trends is difficult and is a limiting factor in its use. Nevertheless, as data analytics improve, a greater u
Improving Safety Through Predictive Maintenance
Monitoring workers and working conditions are not the only areas where IIoT is improving workplace safety. Forward-thinking companies are applying IIoT to improve equipment performance and uptime through predictive maintenance.
It is not hard to imagine how potential machine malfunction can generate unsafe working conditions. If a part suddenly fails and a machine abruptly stops, the equipment operator may face a hazardous situation. Part breakage may result in loose equipment pieces sent airborne, as an example.
In other cases, if equipment deviates from the specified process, unsafe conditions can also occur. As collected data is analyzed, failure conditions can be predicted and maintenance personnel is alerted to perform the needed maintenance. If you have machines that operate in peak conditions, you don’t have to be afraid that they will be the reason for any safety issues at your facility.
In the future, predictive maintenance will involve replacing critical parts based on the analysis of machine operating conditions. This approach recognizes the fact that every part’s failure mode can change with changing conditions. For example, a bearing’s actual failure patterns may be dependent on operating characteristics such as speed, temperatures, and stresses. The same bearing on two different machines may fail in different ways and at different times due to variations in operating conditions.
With artificial intelligence (AI) and interconnected machines, failure modes are identified, parts failure predicted, and maintenance scheduled. Predictive maintenance is driven by analysis of actual equipment operating data which eliminates unnecessary maintenance, improves uptime
Safety and predictive maintenance go hand-in-hand. The ability of IIoT to identify and predict unsafe machine conditions in advance is essential to reducing the number of workplace injuries.
A solid predictive maintenance program based on the identification of failure patterns helps reduce both equipment downtime and unplanned repairs. The associated improvements in productivity, improved worker safety, increased capacity and reduced costs are only a few of the many benefits the future holds for IIoT.
Written by Bryan Christiansen, Founder and CEO of Limble CMMS.