Prior to 2016, construction workers at Skanska USA job sites could end up walking an average of 6 miles during a single day simply to get the right building materials, tools and equipment to the right location at the right time. By tracking worker location and movement data against worker activity data, the company has been able to optimize the positioning of workers, tools and resources to reduce worker time-in-motion by one-third, cutting the daily trudge by 2 miles and boosting productivity by roughly an hour per worker per day.
Tony Colonna is Skanska USA’s senior vice president for innovation and construction solutions and a 20-year veteran of manufacturing operations management for firms including Ford Motor Company and Bell Labs Lucent Technologies. “It’s a lot easier to study where we waste time moving material, people and tools around in a static manufacturing environment,” Colonna said. “Construction work is much more dynamic. The work today is different from the work tomorrow, the people and the trades are constantly in flux, and it can be incredibly hard to get your arms around the data.”
Like many AEC firms, Skanska USA is engaged in several simultaneous pilots of technologies designed to capture and analyze worker and equipment data. Delivered via wearables, smartphones and sensors and collected by BIM and project management software platforms, big data offers the promise of enhanced job site productivity, efficiency and safety and is an antecedent to real-time augmented reality deployment. However, it still faces adoption hurdles that include perceived value, worker privacy concerns and questions regarding data management and overall job site connectivity.
From paper to predictive analytics
For an industry that isn’t necessarily known for its quick embrace of technology, the adoption of systems designed to remove paper-based workflows has both enabled and stymied broader data analytics in construction. While firms have gained efficiencies from using digital collaboration tools, the amount of job site and work process data generated by those tools threatens to overwhelm construction professionals who aren’t specialized in data management or analysis.
Rich Humphrey is the vice president of marketing for Portsmouth, NH-based B2W Software, which provides a platform as a service (PaaS) solution designed to unify scheduling, dispatch, estimating and bidding with field data collection and equipment telematics and maintenance data to provide actionable business intelligence to heavy civil construction GCs and project managers.
“As with any technology, you need to convince the supervisor and project manager and workers that [a solution] will create value” – Michael Myers, Rhumbix director of data science
“All of the recent applications from safety programs to operations to equipment inspection had been geared towards replacing paper forms with digital processes,” Humphrey said. “Technologies are striving to cut across different workflows, and in the field, that manifests itself by applications that collect data, make data accessible to everyone and create new business decisions based on the data.”
Creating new, profitable and actionable decisions based on predictive analytics is a primary value-add of big data systems and services, without which the job site is merely cranking out gigs of data leading to zero business intelligence.
Guy Skillett, the head of construction analytics for San Francisco, CA-based workforce telematics and performance analytics firm Rhumbix, also spent the better part of a decade with San Francisco-based Bechtel as a project lead and senior cost engineer, and he has seen firsthand the impact of data overload on the job site.
“Unless it is a push notification regarding safety or exposure that requires immediate action and intervention, the extent of wearables, hardware, sensor-enabled networks and the deployment of IoT to the job site has the possibility of completely burying the foreman with data,” Skillett said.
As a result, Rhumbix and other project management and data analytics platforms are striving to organize data collected from both workers and machines to gain better access to performance and productivity insights for decision influencing at the operations level, presenting foremen and supervisors not with reams of data, but with directions informed by that data.
“There needs to be an analytics, artificial intelligence or machine learning layer that can take all of the data, interpret it, and then present it back to the project manager or foreman in the form of actionable information,” Colonna said.
AR as the future action-analytics platform
Disparate, purpose-built data collection and solution systems also have the propensity to overwhelm both site teams and back-office analysts with large volumes of raw data.
At Skanska USA, job sites across the country have implemented technologies that collect biometric data, catalog and tag job site photography and video, compare worker movement to some 200 to 300 OSHA-identified safe job site motions, use wearables to track worker proximity to rolling safety exclusionary zones, and monitor job site ingress and egress — not to mention machine and equipment tracking and telematics.
Even file access has become its own predictive analytics arena, with firms like Mountain View, CA-based Egntye providing content intelligence to firms like Balfour Beatty to collect and analyze all of the action-based data associated with construction files.
Analysis of information within contracts, blueprints, RFPs, work orders, and training and safety documents — along with documentation of who accesses those documents and when — provides document management efficiency along with competitive advantage to users, according to Egnyte chief strategy officer Isabelle Guis.
“You can see which documents are accessed the most, the amount of time accessed, and the applications used to access them,” Guis said.
File access data can provide analytics for how subcontractors bid, the kinds of projects they like to bid on, and the historical prices and hours they’ve identified for specific jobs and projects. Guis said the result is accelerated contract negotiation and streamlined administrative processes by prepopulating documents with known information and suggesting who should have ownership and access to a document, and when.
While enterprise BIM and project management systems have emerged as collaboration platforms of choice for a majority of AEC professionals, data experts are unsure if those systems are currently equipped to handle data storage, management and transmission, particularly as first-movers seek to provide real-time job site data via Google Glass or some other augmented reality interface.
Colonna said that while Skanska USA is pursuing real-time data and actionable analytics delivery through an AR interface from a research and development perspective, there are still challenges on a number of different levels.
In addition to data warehousing bogging down BIM systems, Skanska USA has several technologies with different communication protocols and data compression standards. “I think we’ll end up seeing a convergence of all of these technologies that will make AR interpretation of the data possible in real-time,” Colonna said. “That’s when the fully connected job site becomes real.”
Privacy, morale and connectivity
Simply from an IT infrastructure and worker comfort point of view, there needs to be some level of convergence of job site data collection technologies, according to Rhumbix director of data science Michael Myers. Wearables offer a clear example of the disparate tech challenge: With so many bracelet, belt-clip, necklace badge and hard-hat sensors developed for use-specific data collection, workers are becoming bogged down with gadgetry that they are often suspicious of to begin with. “As with any technology, you need to convince the supervisor and project manager and workers that [a solution] will create value,” Myers said.
“You can collect the data and protect the privacy of the worker”-Tony Colonna, Skanksa USA senior vice president for innovation and construction solutions
At Skanska USA, reception to collection of worker data has been mixed from one privacy extreme to another. “We had an instance where the workers refused to participate at all, and we’ve had instances where they were very enthusiastic,” Colonna said.
He added that one of the primary underlying fears with data collection in the construction industry has to do with concerns around discipline. “Once we take discipline off the table, that alleviates a lot of fears, and an easy way to do that is to remove names and personal identifiable information associated with the data,” Colonna said. “We are looking at data in the aggregate to improve productivity, not study how much time carpenter number three spent in the restroom. You can collect the data and protect the privacy of the worker.”
Ultimately, connectivity will also drive data collection and management capabilities on the job site. While local area network and mesh network technologies can bring broadband levels of connectivity to projects, the reality is that many heavy industrial and infrastructure projects are too remote for an IoT-enabled jobsite. “If you are doing a tunnel project, you don’t have GPS at all unless you set up your own network,” Humphrey said. “So connectivity, and not data volume or warehousing, becomes the biggest problem.”
Smartphones are quickly emerging as a device of choice to manage both the connectivity and device consolidation challenges facing job site data experts. With 3G, LTE and Wi-Fi transmission capabilities, phones equipped with app-driven biometric, geolocation and telematics sensors reduce the burden on workers to provide reporting and information and also eliminate the need for multiple wearables.
“Construction workers don’t want new processes, and mobile applications are the easiest way to empower them to deliver data back to the company in a much faster way and get on with their actual job,” Humphrey said. “That’s the simplicity that can make big data work, when worker morale is higher and everyone is making better decisions based on the gravitation towards devices that can capture information in the field and automatically turn it into action.”
- December 2020(10)
- November 2020(59)
- October 2020(79)
- September 2020(72)
- August 2020(64)
- July 2020(71)
- June 2020(74)
- May 2020(50)
- April 2020(71)
- March 2020(71)
- February 2020(58)
- January 2020(62)
- December 2019(57)
- November 2019(64)
- October 2019(26)
- September 2019(24)
- August 2019(15)
- July 2019(24)
- June 2019(55)
- May 2019(82)
- April 2019(77)
- March 2019(71)
- February 2019(67)
- January 2019(77)
- December 2018(46)
- November 2018(48)
- October 2018(76)
- September 2018(55)
- August 2018(63)
- July 2018(74)
- June 2018(64)
- May 2018(65)
- April 2018(76)
- March 2018(82)
- February 2018(65)
- January 2018(80)
- December 2017(71)
- November 2017(72)
- October 2017(75)
- September 2017(65)
- August 2017(97)
- July 2017(111)
- June 2017(87)
- May 2017(105)
- April 2017(113)
- March 2017(108)
- February 2017(112)
- January 2017(109)
- December 2016(110)
- November 2016(121)
- October 2016(111)
- September 2016(123)
- August 2016(169)
- July 2016(142)
- June 2016(152)
- May 2016(118)
- April 2016(60)
- March 2016(86)
- February 2016(154)
- January 2016(3)
- December 2015(150)