Leveraging Lean Methodologies to Define Objectives and Scope for AI-Driven Predictive Maintenance

BY: JERED TYACK

Integrating AI into predictive maintenance can revolutionize Lean manufacturing, offering significant benefits such as reduced downtime, increased equipment lifespan, and enhanced operational efficiency. To ensure a successful implementation, it is important to use Lean methodologies from the start to define objectives and scope. This approach ensures that the entire AI integration launches with a Lean focus on elements like value creation, waste reduction, and continuous improvement. Below, we discuss one approach to using AI to improve Lean manufacturing operations.

Identify Goals Aligned with Lean Principles

A critical goal of most operations is enhancing the utilization rate of machinery to ensure they operate efficiently without unexpected breakdowns. To do this, first, create a current-state Value Stream Map to identify both value-added and non-value-added processes. Assess the current state by going to the manufacturing floor to observe equipment, maintenance activities, and workflows. Be sure to engage with maintenance personnel and machine operators to understand their challenges and insights. Then, collect and analyze data by gathering historical maintenance records on past equipment failures, repair times, and maintenance activities. 

During this process, be sure to assess current key performance indicators (KPIs), including the mean time between failures (MTBF) and the mean time to repair (MTTR), to get a comprehensive view of your current performance. Before using AI, it’s important to fix the process to make sure it’s working well. Without this step, AI won’t help—and could even complicate your operations. Using a future state Value-Stream Map, describe the value stream after Lean manufacturing principles and practices have been applied. Set specific objectives using a deployment plan with the aim to minimize equipment downtime through early fault detection and proactive maintenance. 

Identify Key Areas for AI Integration

Many types of sensors are used to acquire data from machines, including accelerometers, temperature sensors, and current sensors. These sensors convert the physical conditions into data streams that AI can analyze to make decisions or issue warnings when readings begin to approach unsafe levels. AI can foresee mechanical issues like component wear, lubrication problems, and electrical failures such as motor overheating and power supply irregularities. It can also monitor environmental factors like extreme temperatures, humidity, and contamination that affect machinery performance. AI can identify tooling wear and deviations from optimal process parameters to facilitate timely replacements. Additionally, AI can predict network and communication failures to prevent disruptions. This predictive capability helps in planning proactive maintenance, ensuring smoother and more efficient operations. When planning an AI integration, prioritize the areas where AI can provide the highest return on investment (ROI) by reducing costly downtimes and extending equipment lifespan.

Appoint a Project Lead

A project leader is key to successfully implementing AI in a project. They ensure that AI solutions fit the project’s goals and work well with current processes. The leader helps the team navigate the challenges of adopting AI, chooses the right technologies, and manages any risks. They also make sure everyone involved understands how AI can help and what its limits are. By guiding the team and supporting them, the project leader makes sure AI improves productivity and contributes to the project’s success.

Define the Scope of the Implementation

Selecting a pilot project is a strategic step to test the feasibility and impact of AI-driven predictive maintenance. Choose a specific production line or set of equipment to focus on. Define the scope of the pilot clearly, including the equipment to be monitored, data to be collected, and metrics to be evaluated. Define what and how you aim to achieve with the AI implementation, such as reducing downtime by a specific percentage. Establish quantifiable metrics specific to yield, uptime, and throughput to track progress. You can also use maintenance-specific metrics such as reduction in MTBF and MTTR. Ensure goals are realistic and attainable within the pilot scope, aligning them with overall business objectives and lean manufacturing principles. Finally, set a timeline for achieving the objectives and assessing the pilot project’s success.

Engage Stakeholders

Forming a cross-functional team is essential to ensure a holistic approach and garner buy-in from all relevant parties. Involve representatives from maintenance, operations, IT, and management. Clearly define the roles and responsibilities of each team member in the implementation process. Establish a communication plan to provide regular updates on progress, challenges, and successes to all stakeholders. Implement feedback loops to gather input from maintenance teams and operators, ensuring their insights are considered in the AI implementation.

By defining objectives and scope using Lean methodologies, you can ensure that the integration of AI in predictive maintenance is strategically aligned with Lean manufacturing principles. This alignment drives value creation and continuous improvement throughout the organization, ultimately leading to a more efficient and effective maintenance process. Embrace the power of AI and Lean methodologies to transform your predictive maintenance practices, enhancing your manufacturing operations and delivering sustained value.

For personalized guidance and insights on integrating AI in Lean manufacturing, connect with a Business Solutions Manager today. Or, enhance your Lean knowledge with an upcoming training session. We are committed to your company’s growth and success!

MEET OUR EXPERT: Jered Tyack, Lean Program Manager
Jered Tyack is a Lean Program Manager at The Center. In his role, Jered provides custom training and mentoring to Michigan manufacturers on Lean principles and tools, helping them to reduce waste, increase efficiency and improve workplace culture. His areas of expertise include continuous improvement, Lean, efficiency and organization. Drawing from his wealth of experience and passion for continuous improvement, Jered guides manufacturers through their strategic improvement projects.

Since 1991, the Michigan Manufacturing Technology Center has assisted Michigan’s small and medium-sized businesses to successfully compete and grow. Through personalized services designed to meet the needs of clients, we develop more effective business leaders, drive product and process innovation, promote company-wide operational excellence and foster creative strategies for business growth and greater profitability. Find us at www.the-center.org.