When vital industrial process decisions are bolstered by artificial intelligence (AI) and machine learning (ML), their timeliness, efficiency, and effectiveness improve. Work planning and scheduling processes are no exception.
Eliminating the complexity and lack of visibility that planners and schedulers face on a constant basis is the aim of AI/ML-based solutions. The technology provides the analytical foundation for dynamic planning and scheduling, a capability that is increasingly in demand considering the innumerable, rapidly changing variables needing to be weighed when making resource and timeline choices that affect operational effectiveness and the bottom line.
Goodbye status quo, hello PSO
Manufacturing plants and utilities ordinarily rely on dedicated teams or individuals to ensure that all maintenance, inspection, repair, and customer requests are strategically planned and efficiently scheduled. It is no easy feat when manual spreadsheets, paper maps, Gantt charts, or no-frills planning and scheduling software are used.
Planners determine the criticality and priority of all the proposed work, distinguishing between emergencies, high-risk conditions, advantageous activities, and those that can easily be deferred. They need to understand the work steps and safety clearances and anticipate which human resources and equipment, tools, parts, materials, and components must be on hand to complete the job. And they have to be ready and able to change plans on the fly.
Schedulers interpret the plans and determine when the work will be completed, by whom, and how long it should take. Scheduling efficiency is required to maximize wrench time, minimize asset downtime, and avoid impacting production while complying with regulatory requirements and service level agreements (SLAs). Readiness to change a schedule at a moment’s notice is essential.
Both roles are further challenged by aging industrial infrastructure, skilled talent shortages, rising maintenance costs, supply delays, high customer expectations, and ever-changing regulatory oversight.
Weaknesses in planning or scheduling processes introduce operational, safety, regulatory, and profitability risks. Flawed processes inhibit work initiation and completion, consume excess time for problem resolution, and detract time from other value-added tasks. Asset failures, overtime or contract labor charges, safety hazards, regulatory penalties, and breached SLAs may ensue. But fortunately, new opportunities for planning and scheduling optimization (PSO) are available.
Lately, process modernization enabled by industrial internet of things (IIoT) sensors and Industry 4.0 initiatives is giving planners and schedulers newfound access to massive amounts of formerly disparate data and creating the potential for more sophisticated decision-making. With AI/ML algorithms enabling the transition from manual to dynamic planning and scheduling, crucial insights are revealed in real time, helping to increase agility and efficiency, reduce overall costs, and drive operational excellence.
Imagine how real-time knowledge of a power outage, excessively vibrating pump, threatening weather forecast, traffic tie-up, field service vehicle fuel level, or even an employee’s health or safety status can be applied to work plans and schedules. Consider further how advanced data analytics can heighten responsiveness to macro challenges such as supply chain disruptions, global pandemics, and events tied to climate change. Replacing reactive approaches with enhanced predictions and improved PSO is the key to ensuring operational success.
Using today’s technologies, planners and schedulers can explore a richer variety of data and options to achieve better outcomes, and rapidly devise workarounds or alternative approaches to unexpected conditions. Instead of focusing primarily on completing work on time and within budget, attention can be paid to delivering better business value and customer service.
As an example, facilitating the interconnectivity of information between work planning, scheduling, dispatch, and execution heightens responsiveness and performance. For asset-intensive industries concerned with maintenance, repairs, overhauls, expanding service, or responding to customer service requests, this interconnectivity ensures their work plans and associated schedules are continually optimized in real time based on events in the field and beyond.
IFS recently augmented the PSO component of its Field Service Management (FSM) solution with bi-directional information flows by acquiring Clevest. IFS PSO’s dynamic scheduling engine, target-based scheduling, predictive analytics, advanced resource planning, capacity planning, and route optimization are now accompanied by Clevest’s utility-focused Mobile Workforce Management (MWM), location tracking, mobile GIS, and advanced network deployment solutions. The combination enables industrial organizations, especially energy and water utilities, to improve customer service, asset uptime, and workforce and community safety.
Dynamic scheduling stands out
Of all the desirable PSO capabilities, the most intriguing may be dynamic scheduling. Since change is constant, the capacity to continuously search for efficiencies, adapt accordingly, and solve even large and complex challenges in seconds, is set to revolutionize once-staid field service and work management processes.
Dynamic scheduling leverages AI/ML-powered algorithms to constantly reevaluate the optimal sequence of events and recommend the most efficient options. Any number of variables may be involved in the optimization, such as equipment or parts availability; labor skills, certifications, location, availability, travel time, or work shifts; regulatory constraints such as the EU’s Working Time Directive; business performance, productivity, or throughput goals; or customer contract or SLA considerations. Effectively applied, dynamic scheduling can reduce costs, increase profitability, improve compliance, and enhance customer satisfaction.
Central to IFS PSO is its Dynamic Scheduling Engine (DSE). It enables optimization windows to be extended as far as a year and commitment locks as short as two hours, providing greater flexibility than conventional planning and scheduling tools. When it “finds a schedule with a better service margin, it changes the part of the plan that has not been committed to reflect the improvement, reallocating work to resources in a just-in-time, decision-making approach.”
It also supports flexible modeling of business policies and objectives such as reliability as a competitive advantage; business models such as support for depot pick-ups and “late-as-possible” scheduling; and SLA allowances such as allowing overtime for certainly highly efficient workers when compliance is in jeopardy.
Assistance, not replacements
What-if scenarios are another advanced PSO capability buoyed by modern technologies and analytics. It simplifies how the cost-benefits of planning and scheduling changes are understood. Using against data such as hourly and overtime labor rates, potential regulatory penalties, planned outage schedules, and SLAs to test potential plans and schedules against a range of possible outcomes helps to inform how best to carry out the work. Computed recommendations can be presented for review and selection by the planner or scheduler.
Importantly, such PSO tools know their place. They are not designed to replace human planners and schedulers but rather to augment their knowledge, save them time, and simplify the process of weighing and making informed decisions to improve performance, safety, compliance, and the bottom line.
This story originally appeared in the September 2022 issue of Plant Services. Subscribe to Plant Services here.
About the Author: Sheila Kennedy
Sheila Kennedy, CMRP, is a professional freelance writer specializing in industrial and technical topics. She established Additive Communications in 2003 to serve software, technology, and service providers in industries such as manufacturing and utilities, and became a contributing editor and Technology Toolbox columnist for Plant Services in 2004. Prior to Additive Communications, she had 11 years of experience implementing industrial information systems. Kennedy earned her B.S. at Purdue University and her MBA at the University of Phoenix. She can be reached at [email protected].