Asset management is a critical component of overall equipment effectiveness (OEE). Two experts from weigh in.
Asset Management Insights
- Industry 4.0 and artificial intelligence (AI) analytics have shifted towards more predictive maintenance, data-driven reporting and dashboards.
- Manufacturing execution systems (MES) accelerators can reduce data collection deployment time by up to 70%.
- AI is crucial in predictive maintenance, involving data analytics and machine learning to predict when equipment might fail.
Everyone in the industrial space wants to know how to optimize uptime and limit downtime, so asset management is a hot-button topic right now. In this Ask Me Anything special feature from Plant Engineering, Cody Bann, vice president of engineering and John Oskin, senior vice president, with SmartSights offer their advice for maximizing efficiency.
Q: What’s the current trend in asset management for industrial and manufacturing facilities?
A: Driven by Industry 4.0 and artificial intelligence (AI) analytics, current trends include a shift towards more predictive maintenance, data-driven reporting and dashboards, real-time notification of more predictive alarm conditions and improved alarm management to help teams maximize asset efficiency. Adding to that, there is growing concern over energy efficiency. Additionally, more cloud-based software solutions and the information technology/operational technology (IT/OT) convergence continue.
Q: What future trends should engineers, plant managers and designers expect for asset management?
Future trends include tighter integration between plant software systems, wider adoption of digital twin technology and more AI suggestions for operators. By managing assets through the integration of additional technology like remote alarm notification software and reporting software and then leveraging this data and analytics, manufacturers can increase overall productivity, meet industry challenges and compliance regulations.
Q: Describe your successes from using programs and systems that incorporate asset management. This may include industrial internet of things (IIoT)-based systems, Industry 4.0, etc.
A: By incorporating asset management, organizations will have decreased downtime, increased overall equipment effectiveness (OEE), reduced response time, fewer false alarms and increased regulatory compliance.
The advent of smart machines equipped with IIoT capabilities has revolutionized manufacturing and production processes. This fusion of machine monitoring with IIoT has overcome traditional limitations in data collection, offering a comprehensive solution for modern factories to enhance operational efficiency.
Tracking the performance and condition of machinery in real time enables manufacturers to make informed decisions that boost productivity and reduce costs. Additionally, real-time data empowers manufacturers to make data-driven decisions, detect anomalies and optimize asset utilization. By leveraging these insights, manufacturers can identify inefficiencies, optimize production workflows and proactively address maintenance needs.
Real-time systems have thousands of components and sensors, each gathers data and helps ensure that every part of a facility is running effectively; these can also be controlled remotely.
Q: What types of computer applications are in use to support your asset management functions?
A: Manufacturing execution systems (MES), MES accelerators, Supervisory Control and Data Acquisition (SCADA), alarm notification, reporting, enterprise asset management (EAM) and computerized maintenance management system (CMMS). MES accelerators can reduce data collection deployment time by up to 70%. When issue management applications such as next-generation Andon technologies are coupled with CMMS, issue response time can be decreased by up to 50% and resolution time by up to 20%.
Q: Tell us about a recent asset management project you’ve worked on that’s innovative, large-scale or otherwise noteworthy.
A: We are currently involved in a three-plant rollout utilizing our issue management accelerator, Peer. This is a next-generation Andon solution for issue management, tracking and resolution that will integrate easily with the end user’s existing systems and CMMS application. The initial challenge with this project was to modernize maintenance communication and the objective is to eliminate radio communication and replace it with Andon machine and operator calls for help. The integrated solution provides a holistic view from alarm and alert detection through resolution, keeping workers and managers in the know.
Q: When considering your most effective asset management strategies, what are the advantages?
The most effective asset management strategies tie CMMS data to performance data such as OEE, mean time between failures (MBTR) and mean time to repair (MTTR). While accurate, real-time data is pivotal to operations, harnessing this data effectively requires advanced technology and analytical capabilities. Vast amounts of data are collected for industry reporting, predictive maintenance and safety enhancements, for example, but organizations may be challenged to effectively manage and analyze the data. Automated third-party reporting software, however, tracks all areas in a production facility. The finished reports are then distributed directly to preferred destinations, which streamlines the decision-making process and enhances operational efficiency. The ability to harness this data effectively can lead to smarter decision-making, improved processes and a competitive edge.
Integrating additional software accelerates digital transformation with advanced data collection for OEE and manufacturing execution systems (MES), enabling plant personnel to have valuable insights into the operations and helping them make better and more informed decisions.
Q: Describe how you use enterprise resource planning (ERP) and other systems to provide better data and information flow throughout the company.
Our accelerator apps can feed level three through five systems, including enterprise resource planning (ERP). ERP systems have context data that can be associated with machine performance data, enabling comparisons by production order, SKU and shift for example.
Q: What new or advanced technologies do you plan to implement at your partners’ facilities?
New technologies include advanced data collection software that track OEE at every point on a production lines, not just constraints. These include technologies for fault learning to rationalize and prioritize repetitive machine faults.
Plant personnel often use manual data collection to capture losses and generate efficiency metrics or, if they have embarked on an OEE journey, are using line-level data collection. But this information is often grossly inaccurate. Incorporating advanced software technologies in manufacturing plants can accelerate and drive OEE uplift, avoid problems before they occur and reduce engineering time by up to 70%. For a $1 billion company, every 1% improvement in OEE –– like integrating advanced software that reduces equipment downtime –– is worth approximately $7 million annually, further lessening costs and improving operational efficiencies.
The growing array of manufacturing regulations becomes more challenging to meet due to the increasing role of governmental regulatory bodies in certain industry sectors, along with the emergence of global manufacturing compliance standards to address the increasing global nature of manufacturing. Incorporating automated reporting solutions streamlines regulatory compliance by consolidating data from disparate sources like instrumentation readings, program or recipe setpoints, HMI audit trails, alarm history and others. As the data is collected, it’s summarized as key metrics, and the final output is published into a formatted document representing a detailed performance audit of the process execution. Additionally, this third-party software produces monthly regulatory reports, which can be automated with government forms.
Q: What tips would you offer to someone newly tasked with asset management duties?
A: Develop a deeper understanding of your assets; not just an inventory but how they fit into the larger picture, what impact they have on production and safety and compliance, as well as the assets’ historical trends.
The importance of improved alarm management, which greatly benefits the team when they are focused on the most impactful tasks.
Build relationships with the operators and maintenance technicians and seek their feedback and observations.
Learn and leverage the existing technology to improve asset management and what additional tools could be integrated to further drive efficiencies and complement [the existing technology].
Q: How has the integration of artificial intelligence (AI) and machine learning (ML) impacted traditional asset management strategies?
A: The subject most talked about is the shift from a reactive response to failures to a more preventative and prescriptive maintenance strategy. While this is a significant way that AI and ML are impacting asset management, it’s important to also recognize that the contributions don’t end there. For example, speech recognition helps operators respond to alarm conditions from their vehicle, chatbots assist operators to gain knowledge about less familiar systems and anomaly detection helps highlight reporting data for critical decisions. These small aggregate improvements are extremely transformative and effective to manufacturers.
Q: Can you share specific examples of successful applications of AI/ML in optimizing asset allocation and portfolio management?
A: Implementing novel machine learning algorithms to detect faults in real time mitigates the risk of downtime. As the industry continues to move toward greater efficiency, the integration of AI in MES is revolutionizing how manufacturers operate, bringing unprecedented levels of automation, predictive analytics and decision-making. It can leverage root cause analysis to predict failures and reduce defects; draft easy-to-follow dynamic work instructions; and augment operator stations by offering live, AI-supported troubleshooting and operating guidelines, helping companies be more flexible, efficient and intuitive in meeting end-users’ needs. In addition, technologies associated with fault learning can rationalize and prioritize repetitive machine faults.
Q: What challenges and risks do you see in implementing AI-driven asset management solutions and how can these be mitigated?
A: Manufacturers have started to recognize the benefits of embedding AI into business operations –– integrating the latest techniques with existing, widely used automation systems to enhance productivity. However, AI presents companies with privacy and data security risks. To mitigate this, it’s important for organizations to review how their data might be used by third-party vendors.
While AI helps improve operational efficiencies and innovation, ensuring the data quality is a big concern. Effective data collection requires embracing advanced solutions that go beyond traditional methodology. These algorithms can analyze large amounts of data and identify patterns and trends that humans may not be able to detect. By leveraging machine learning, asset managers can make more informed decisions.
Integrating AI can also be quite costly because many manufacturing plants have legacy systems that aren’t always compatible, further complicating adoption.
It’s important to prioritize AI systems that improve plant floor operations for workers. The first step is to get buy-in from employees who may be unfamiliar with this technology. Through employee training and careful planning, AI can be an effective tool to increasing operational efficiencies.
Q: How do you assess the ethical considerations surrounding the use of AI in asset management, particularly in terms of decision-making and bias?
A: AI is crucial in predictive maintenance, involving data analytics and machine learning to predict when equipment might fail. AI algorithms can anticipate maintenance needs by analyzing real-time data from sensors embedded in machines, minimizing unplanned downtime and optimizing maintenance schedules.
While employees are concerned about being replaced by AI, the technology will complement workers, helping them make better decisions and enhancing productivity. Just as automation in manufacturing has increased production, so too can AI. That said, companies must balance adopting AI with strategies to retain and upskill employees. For example, as AI-powered robots take over repetitive and manual tasks, workers may need to transition to roles that require more complex problem solving and technical skills.
AI is revolutionizing asset management and, for companies that embrace the technology, it provides competitive advantages. However, AI algorithms can unintentionally perpetuate biases in the training data, leading to unfair outcomes. To counter this, management must implement measures to identify and mitigate these biases. Specifically, companies can implement fairness-aware algorithms and conduct regular audits.
Q: How do you see the role of human expertise evolving in conjunction with the increasing use of AI in asset management?
A: AI raises concerns about potential job displacement due to automation. However, implementing proactive efforts to upskill and reskill the workforce through investments in job training programs will help ensure a smoother transition to new job roles.
Even as we integrate AI into our business processes, the value of human expertise is irreplaceable. In a recent report, The Blueprint to Total Expertise, 62% of leading firms plan to use AI to automate routine and repetitive tasks by 2027, freeing up time for critical and strategic thinking.
Q: How does effective asset management contribute to improved maintenance practices?
A: Effective asset management reduces downtime by scheduling maintenance optimally, improving team response times, optimizing resource allocation and new investment opportunities and increasing asset lifetime and reliability.
Q: Can you share examples of successful asset management strategies that have directly led to enhanced maintenance outcomes?
The use of Andon technologies has led to 50% reduction in issue response time and 20% reduction in issue resolution time. The use of multi-point advanced data collection for OEE has led to 20% improvement in OEE.
Q: In your experience, what are the key challenges organizations face when trying to align asset management with maintenance goals?
Data quality is one of the biggest challenges when aligning asset management with maintenance goals because inconsistent or fragmented data leads to inaccurate condition assessments. However, by integrating maintenance strategies into an overall asset management system, organizations can optimize resources minimize operational downtime and reduce costs.
As with so many objectives, it’s critical that organizations communicate and avoid silos. Maintenance teams need to understand the operational priorities of asset managers and vice versa. It’s important for organizations to solicit feedback from maintenance staff. Do they agree that the decision regarding whether to carry out a maintenance operation? And, if not, what variables might not be captured well?
This dialogue is also how organizations can identify training needs –– where the maintenance team may be lacking specialized skill or knowledge or may be relying too heavily on key individuals.
Q: What metrics or key performance indicators (KPIs) are most relevant for assessing the success of asset management in maintenance?
A: While people are familiar with OEE, modern systems now track OEE at every point on a production line not just bottleneck points. Mean-time-between-failure (MTBF) and mean- time-to-repair (MTTR) are important metrics for maintenance professionals as secondary metrics to OEE.
Q: How does real-time asset monitoring contribute to proactive decision-making in an automated environment?
A: Real-time asset monitoring provides increased responsiveness to issues and enables richer data collection for predictive analysis and problem solving. An excellent example of this is with Cincinnati-based G&J Pepsi, a Cincinnati-based Pepsi franchise bottler producing, selling and distributing over 30 beverage brands and roughly 700 products throughout Ohio and northern Kentucky. In 2023, G&J Pepsi’s processes included manual data collection in an Excel spreadsheet with a power BI tool used to capture losses and generate efficiency metrics. Initially, they were measuring the number of production stops and found the data was inaccurate. For example, reports would state there were five stops during the week on a line, when there were more than 75 stops a day, or about 375 stops a week. In addition, the lack of real-time data meant they would receive information the next day for how well they performed the previous day.
Looking at G&J Pepsi’s mean-time-between-failure (MTBF) numbers, which were as frequent as every three minutes, the company knew there was much room for improvement. If they could increase the MTBF, then production lines would be more stable, stop less frequently and potentially improve OEE, efficiencies, production yield, employee morale and safety.
By integrating a cloud-based Internet of Things (IoT) solution that provides real-time root cause analysis for manufacturing operations and extends the capabilities already offered by EMI and MES systems.
The work environment changed from a reactive to a proactive one. G&J Pepsi utilized the visibility from their real-time data to change how they perform their daily work to more on-the-floor troubleshooting, validating that their auto-tagging is accurate and reflects the loss. Specifically, they achieved:
- 15% improvement in production within six months
- 70% reduction in engineering time
- 5 times improvement in data fidelity
