By {{Article.AuthorName}} | {{Article.PublicationDate.slice(6, -2) | date:'EEEE, MMMM d, y'}}
{{TotalFavorites}} Favorite{{TotalFavorites>1? 's' : ''}}
According to the Bureau of Labor Statistics (BLS) 4,836 American workers died on the job in 2015. Unfortunately, construction remained America’s deadliest industry with 937 deaths, representing 19.4 percent of overall workplace fatalities for that year.

Although on-site safety has improved tremendously over the years, the construction industry needs to continuously review and incorporate innovative technology and best practices to ensure occupational health and safety is strengthened.

“Industry 4.0” is a term used to describe the current trend of automation and data exchange in manufacturing technologies. Connected devices and intelligent machines are spearheading the rise of “Industry 4.0” and helping the construction industry push new boundaries. The Internet of Things (IoT), artificial intelligence (AI) and machine learning are allowing construction professionals to incorporate predictive maintenance capabilities into their on-site performance and safety procedures. These newly acquired capabilities are allowing construction companies to predict forthcoming maintenance needs and prevent unforeseen breakdowns, safety hazards and their resultant downtime. However, with connected sensors communicating equipment status to the cloud in real-time, there are many additional benefits to be gained.

Artificial intelligence allows organizations to continuously record a range of sensor readings, which allows the systems to identify the ‘normal’ operating baselines for different machinery. By monitoring the behaviors that fall outside of these parameters, the systems are able to create alerts and actions that not only improve the machinery’s performance, but also address hazardous conditions that may have been overlooked by their human operators.

Consider a piece of heavy equipment, such as a front end loader or a forklift. Over time, its core components deteriorate and mechanical faults inevitably develop, causing issues such as poor fuel efficiency and less power output, which subsequently slows the progress of projects. Or, as the machinery’s braking systems become increasingly worn, the operators ability to safely maneuver the vehicle is diminished leading to potentially dangerous work conditions. Issues such as these can be proactively detected, with the necessary actions triggered to mitigate the associated risks with advance warning (maintain, repair, replace, upgrade). Artificial intelligence and machine learning allows construction professionals to detect these sorts of breakdowns and reduce the chances of physical danger to the machinery’s operator, support crew and nearby workers.

Look at safety and causation factors for the same equipment. For example, if the vehicles generate a rapid, unexpected start/stop movement, this could indicate that it has crashed, overturned or some other irregular movement which may pose a threat to its human operator. Alternatively, if the front end loader or forklift regularly produces this kind of data, it may also indicate that its human operator could be executing duties in an unsafe manner (rapid acceleration/braking, working on unsafe grades, etc.). The resulting data generated from the vehicle would allow an organization to schedule additional training sessions or an on-site meeting with the employee to ensure they are complying with safety protocols.

With companies seeking to constantly improve safety and productivity, it makes sense to use the best technology available to monitor the data generated by an organization’s assets. Companies are now able to make practical use of IoT data across all their operations, and a specialized third party can help construction outfits create a machine learning strategy for their connected equipment. With such an approach, the modern construction organization can see immediate benefits today and future-proof itself for tomorrow.

 Comments ({{Comments.length}})

  • {{comment.Name}}


    {{comment.DateCreated.slice(6, -2) | date: 'MMM d, y h:mm:ss a'}}

Leave a comment

Required! Not valid email!