Driven by AI technology, modern software provides an advance warning of imminent failures
Article By Fabio Tiviti
Vice President, ASEAN, Infor
Cities, large and small, are struggling to keep pace with the increasing number of infrastructure repairs needed today. Aging structures, crumbling bridges, patched transit systems and outdated utility networks are among the assets requiring attention. “State of Good Repair” is the goal for all, but cash-strapped municipalities are often forced to prioritize and focus on the most critical assets first. But how can engineers and officials predict which physical assets are most likely to fail — or when? Where will be the greatest safety risks, or the most disruptive occurrences, impacting commerce and constituents?
Fortunately, modern software solutions can help. Artificial intelligence (AI) and machine learning (ML) software tools can now predict likely occurrences, based on data patterns and driving influences. Reporting tools help identify early warning signs and anticipate probable outcomes — while there is still time to take proactive measures and intervene. Scheduling preventive maintenance or replacing aging parts before they fail can prevent high-impact disruption. The agency can stop “fighting fires” and move toward a more strategic approach for monitoring and managing asset wellness.
Predictive Science Not Science Fiction
Using AI technology to predict the future may sound like science fiction. But, predictive science is a capability that today’s advanced enterprise asset management EAM) solutions provide. Data from inspections and collected through embedded sensors and Internet of Things (IoT) technology can be analyzed to find anomalies or data points that fall outside of predefined acceptable limits.
These early warning signs can point to future breaches or failures, just as sniffles may indicate a cold coming on. The outlying data can trigger automatic responses, such as shutting down equipment, which may be unsafe. Early intervention, like dispatching a technician, ordering back-up parts, or rerouting activities, can change the likely outcome. Proactive asset maintenance can prevent catastrophic shut-downs, closures, or interruptions to service, saving headaches — and funds. But, most importantly, strategic intervention can control risks to safety or community well-being.
How Does it Work?
Advanced analytics are now easier to use, giving business users tools that step them through applying appropriate algorithms predictive science to specific use cases. With an intuitive user interfaces on the front and sophisticated technology behind the scenes, managers, including those without coding capabilities, can design and deploy projects to monitor infrastructure assets, from bridges and overpasses to public transportation, traffic lights, and communication systems.
This type of tool creates “citizen data scientists,” who can take advantage of advanced technology without requiring extensive expertise or help from third parties. Such easy-to-deploy tools are necessary to evolve from proof-of-concept projects that can take months or years to deploy. Organizations need solutions that can scale reliably, so they can be used in multiple applications and yield meaningful impact. This type of user-driven roll-out is necessary for municipalities that are overwhelmed with aging assets and seeking tools to help establish priorities.
Defining the Problems
International Standardization Organization (ISO) standards, developed around achieving State of Good Repair, give agencies a step-by-step approach for improving asset reliability. But, often, obstacles get in the way, from lack of funds to lack of staff resources for defining condition-assessments criteria or conducting audits. Numerous asset “emergencies” can put maintenance technicians in reactive mode, jumping from one high-profile issue to the next, making it difficult to be strategic. Predictive analytics can help the maintenance team better manage the numerous demands for attention, focus on the priorities, and make time to enact holistic strategies.
Combine with ISO 55000
ISO 55000 was developed and put into effect to help agencies follow best practices for achieving State of Good Repair. Federal legislation was passed mandating agencies ramp up new processes and meet State of Good Repair targets, including transit asset management plans.
ISO 55000 provides an overview of best practices for asset management, with ISO 55001 specifying the requirements and ISO 55002 providing guidelines for implementation. The goal is to help organizations achieve highly efficient maintenance programs and ensure infrastructure assets meet safety standards. To receive federal funding, local programs must be compliant—creating added urgency.
Knowing where to start can be the biggest hurdle. Business intelligence (BI) solutions provide objective views of the issues to help agencies launch critical first steps, moving in the right direction. Teams can look at what-if scenarios, analyze financial impacts, and forecast the parts, tools, and technicians needed to reach objectives.
Creating Long-term Plans
Data insights can be used to apply for funding, persuade stakeholders, plan major initiatives, and educate constituents on the facts, whether reassuring or alarming. When budgets are tight, data speaks louder than vague requests for capital. Self-service reporting tools help managers set realistic goals and monitor progress toward those goals. Data insights, derived from AI and ML, help keep the dialogue grounded in reliable facts and well-informed projections. With proven software in place, even the forward-looking predictions can be trusted, essential for planning today.
Prioritizing asset repairs will help the agency start on the path to long-term asset health. Complying with federal mandates, like ISO 55000, will promote good asset management processes and help agencies budget appropriate resources to support the needs of their community. Advanced BI tools improve visibility and help align the multiple stakeholders, from state legislatures to local branches, from managers who schedule maintenance to technicians dispatched to inspect or repair an asset. Data is the one common language all stakeholders speak.
Use Cases for AI-Driven Analytics
BI tools can help the agency assess the repair backlog and determine the investment needed to achieve compliance. An asset’s condition, based on inspection, age, criticality and risk, will determine its priority for repair or replacement. First, rating scales are assigned to each asset. Then, BI tools help assess the probability of failure, when and where. Algorithms provide the science. Sophisticated machine-learning tools use historical facts, incorporate proven outside influencers, such as weather or usage demands, and extrapolate likely outcomes. The application also can provide insights about the consequence of asset failure, such as cost to replace, lost revenue, or short-term inconvenience. Data analysis can also help determine when it makes sense to repair an asset, upgrade to a new version, or replace entirely.
The Final Take Away
With reliable asset data analysis, agencies and organizations can set priorities and formulate a strong capital improvement plan, based on predictive science, assessment of risk, and timelines for when assets are likely to need repairs or replacement. The plan can consider available capital and grants or other revenue sources. The plan can be shared with stakeholders, showing the data involved in decisions and reassuring constituents that resources are being optimized for their best interests. Data-driven insights will help cities and states upgrade the deteriorating infrastructure and return it to a reliable condition. Software technology is an important tool for rebuilding assets—and trust.