INSIGHTS ARTICLE: Digitiqs - Predictive Asset Management — A viable solution to the challenges brought by the "New Normal"

BLOGS COMPANY LOGO - 2022-10-17T130338.566 pillar%20page%20line%201

Predictive Asset Management — A viable solution to the challenges brought by the "New Normal"

Introduction

In 2019, the world was faced with a pandemic that severely disrupted economic activity and inflicted significant damage to economies all across the globe, thereby transforming the entire business landscape. During this period of deep uncertainty and rapid transformation, businesses have to make critical decisions that are going to have long-lasting impacts on their bottom lines. In order to steer in the right direction, they need answers to some very critical questions:

How can we make a precise prediction of asset failure beforehand?
How can we watch the health of critical assets in an effective way?
How do we optimize asset performance and maintenance to prevent failures?
How do we improve labor and asset utilization to increase productivity and uptime?
How do we optimize energy consumption in the facility and remote operations?

A lot more inquiries like these pose a potential threat to critical asset-intensive and energy-driven enterprises after the pandemic.

The world after the pandemic is not the same and given the limitations brought upon by this situation, companies must sketch out more crisis-resilient, cost-effective, and operationally efficient yet environmentally friendly methods to maintain their competency. A few examples of these include digitization, effective data management, efficient decision-making, enhanced asset utilization, smart energy management, automation, and so on.

Benefiting from data-driven analytics and powered by AI algorithms, Predictive Asset Management significantly helps to keep this ‘competency’ intact and gives you options to improve productivity. In this article, we are outlining 23 key outcomes with respect to Predictive Asset Management that can improve operational efficiency and hence global competitiveness.

Why Manage Assets?

Without doubts, businesses in today’s world have to manage a huge number of assets in multiple locations. This scenario has changed in the few last years, dramatically. With the inclusion of technology and highly-automated processes and high-tech equipment, which surely has helped us speed up the whole operations cycle, it has posed new challenges as well. In this conjuncture, if you don’t have data-driven asset management tools and systems, you can’t develop insights and an effective decision-making process for your variating asset base. Developing, operating, maintaining, upgrading, and disposing of assets is a systematic process that needs to be done continually and more importantly in a cost-effective manner.

Management of assets is a challenge that grows exponentially as your company grows. To stay on top of things, asset management requires the best tools, systems, and practices in place. If the organization is not structured to manage and maintain assets properly, it is quite likely that you will have no visibility and control over the assets. As a result, you may experience:

Huge opportunity as well as reputation losses subsequent to recurrent breakdowns/downtimes due to equipment failures.
Unavailability of a key asset (machine part, ), which may cause a long-term production halt.
Inadequate availabilities of assets, thereby causing the untimely stock issues.
Unnecessary stoppages for overhauling/servicing/maintenance, when it is not really Inability to identify when assets are not in use.
Inability to remotely manage your inventory.
Inappropriate capital investment, investing in parts/spares that are not used for long.
Loss of assets through misplacement or theft, resulting in monetary losses.
Legal issues/complexities
Poor ROI

and many other issues at your organization. Without effective and, more importantly, predictive data management of assets that enables accurate and timely decision making and reduces financial processes, it is highly unlikely for organizations to be crisis resilient and competitive or even survive the new normal.

The Pandemic Effect

The highly unforeseen challenges that most people and businesses face today due COVID-19 pandemic have had significant impacts. It is estimated that economies will lose at least 2.4 percent of the value of their gross domestic product (GDP) over 2020 alone (source from www.statista.com). To put this number into perspective, global GDP is estimated at around 86.6 Trillion USD in 2019 — meaning that just a 0.4 percent drop in economic growth amounts to almost 3.5 Trillion USD in lost economic output. That’s humungous and calls for action. It is imperative that the companies adapt to this new regime and take appropriate steps to manage these challenging times.

The current pandemic has redefined our daily lives, and businesses all across have been severely jolted. The compulsions, imposed regularities, and the emergence of a “new normal” is a strong wake-up call for all business sectors to not only adapt to the changing paradigm but also to develop innovative solutions and sustainable strategies in order to manage the upcoming challenges.

Being faced with this pandemic situation is a challenge that lurks over all enterprises, large or small, including but not limited to industrial units, banks, retails, Oil & Gas, Vehicle manufacturers and operators, etc. To manage it well, all sectors must prioritize implementing improvised methods that revolve around factors such as cost-effectiveness, productivity, maximum energy optimization, and the use of assets in a more responsible, mindful way. The effective development of all these mentioned elements can pave way for a more resilient and crisis-tolerant organization.

The Concept of Predictive Assets Management (PAM)?

Simply put, Predictive Analytics is a way of using historical and real-time but relevant data to predict future outcomes. It applies powerful statistical modeling techniques & algorithms and generates ‘strategic actionable insights from data through artificial intelligence. Additionally, it is capable of providing real-time ‘decision support insights' on specific equipment.

In the graph below, the 23 critical outcomes are provided if a well-structured Predictive Asset Management is implemented in enterprises. These are grouped into two main categories:

Bottom line Outcomes and Business Impacts. Each outcome has significant business effects that need to be carefully managed. In the following paragraphs, it is explained how you could reach out to these outcomes through Predictive Asset Management.

Properly implemented Predictive Analytics can be a lifesaver for all asset-intensive industries like Energy, Banks, Oil & Gas, Manufacturing Industries, etc., that have common challenges, i.e., avoiding downtimes, managing and mitigating the risk of equipment failure, avoiding unplanned costs, impacts on production, safety, and environmental implications, etc. In a constant encounter to balance the cost of preventative maintenance measures against the risk of equipment failures, digitized predictive asset management tends to be a game-changer.

Data acquisition is a key factor for precise predictions. Unless data is gathered from authenticated resources and is maintained properly, the efficacy of the predictive algorithms is not assured at optimum levels. Highly variating data sources exist in the organization and all are equally important. Data sources include user logs from software (any software in use), error or failure reports from the equipment, data reported by sensors, or other data manually recorded by your workforce in any structure or format.

If applied carefully and effectively, companies can have the following benefits summarized in the chart above:

Bottom Line Outcomes

Increased Asset Lifetime: As the system provides early detection and prevents anomalies, the system health will be improved and the asset lifetime will be longer based on real data analytics.
Decreased Maintenance Costs: Scheduled maintenance can be adjusted and optimized dynamically.
Decreased Inventories: Improved inventory management (especially for spare parts) and no unnecessary or too much spare parts usage.
Decreased Labor: Optimized usage of technical and maintenance personnel, eventually saving on salaries and utilizing resources efficiently.
Decreased Incident Impacts: Following the reduction of failures, the impacts will be less on business.
Increased Uptime: Prevent outages and failure by predicting (based on statistical data) what parts are likely to fail in the near Identify parts that haven’t yet failed but are ‘about’ to fail, so that they can be replaced just in time to avoid unscheduled downtime.
Improved environmental compliance: The data-driven process will be providing in-depth compliant information and will further help to discover the improvement areas.
SLA optimization: In the case of an SLA, the true performance and availability of the assets will help to improve SLA performance which means isolating the business from any fine or legal binding.
Calibration Management: Early detection of calibration needs.
Improved Service/Production Quality: As the asset performance improves, the quality of the outputs and services will improve accordingly.
Reduced Downtime: Critical faults predicted by the system can be detected before the system stop and problems can be fixed.

Business Impacts

Energy Optimization: Discover areas for improvements as well as enhance energy efficiency for more profitability. Significant energy savings when assets are operating at optimal performance.
Data-Driven Asset Optimization: Mine big data (multiple thousands of text-based logs, etc.) that describe the maintenance performed on systems and equipment. These important observations are key for the improvement of operations, machines, and equipment.
Increased Safety: Safety increases for both people and assets.
Improved Customer Experience: The overall improvements will help businesses to serve competitive solutions to their customers in a faster way and with high quality.
Capital Project Avoidance: As the life span of assets increases and the operational efficiencies improved, the overall CapEx investments will be optimized.
Improved OEE: The maintenance operations and data-based tracking will help to improve OEE as the anomalies are under control and asset health is improved.
Cyber Secure Operations: The data management and operations will be under control through digitized operations.
Asset Visibility: Maximize equipment availability and avoid equipment failure.
Digital Transformation: The facility operations will be managed based on data and will have integration capabilities with other enterprise systems to digitize the overall business and technical processes.
Improved Asset Utilization: Avoid unnecessary maintenance and save time and money. Fixing the problem with minor maintenance or repair of the original problem source.
Management Reporting: Due to the accumulated historical and real-time data, the reporting capabilities will be improved and hence provide a smart decision-making process for management.
Minimized MC/RAV: The ratio will be improved to the ideal rate of around 2.5%, which is the level of the organization’s operational excellence.

Quantifying the Concept

Speaking from a more practical and concrete approach, it is very important to take real-time data from assets. It is critical for a business to gather data and then store it properly (in proper structures) so that it can be later analyzed by Artificial Intelligence algorithms, thereby leading you to take appropriate business-related decisions and actions.

So now, decisions that businesses make are not just based on experiences or hunchs but are backed by solid statistics gathered over a period of time. The strength of using these algorithms and analysis for predictiveness is the ever-changing data which refines the algorithmic predictiveness and ensures further optimizations and efficiencies.

Asset-intensive, process-oriented businesses and industries, such as Manufacturing, Oil & Gas, Mining, Healthcare, Airports, Banks, Retail, Data Centers, Hotels, Logistics, and others, have high-value, business-critical assets that are to be managed very critically. These assets may include production robots, CNC machines, forklifts, presses, vehicles, heating/cooling equipment, compressors, generators, welding machines, heavy vehicles, buses or trucks, and so on. It is vital to ensure these are monitored and maintained in order to keep them up and running efficiently.

Periodic maintenance is not the best remedy in this case as it will fail to detect the failures at the exact time they occur and consequently increase the downtime. Predictive Asset Management helps in this regard as it monitors assets with real-time data and analyzes them with Al algorithms and intimates the operations team to engage the Preventive maintenance (which is aimed at catching and fixing problems before they happen) measures, eventually saving a lot of time, revenue, and production costs.

Article Image (2)

The competency of many industries is scaled by the ratio of maintenance costs to asset renewal value. Statistics show this ratio is between 2.5% and 5%, on a global scale, which shows that maintenance processes and operational activities are fairly successful (see the graph). Many companies or institutions cannot, however, adequately analyze this performance owing to the lack of data. There are situations where the ratio rises to an alarming

20%, which could pose a significant threat to the global competitiveness of firms if there is not sufficient data to measure this ratio. Studies show that the optimum operational excellence “Sweet Spot” appears around the level of 2.5% MC as of the percentage of RAV (Replacement Asset Value) for an operational efficiency close to 100%. However, these levels of maturity can only be reached along with advanced organizational behavior, aligned processes & technology-driven culture.

Implementation of PAM (Predictive Assets Management)

Being already accustomed to the jargon, knowing the basic concepts, and having a brief understanding of PAMS, listed below are some of the important parameters for implementing predictive asset

management system. The process of implementation may seem demanding, but with the right combination of knowledgeable resources, the right tools, and effective technologies, miles can be covered within a short time and concrete output can be seen, almost instantly.

Article Image (3) As the picture above demonstrates, the whole process from an unmanaged to a highly managed assets system is achieved in four phases.

Phase-1: The Audit & Analysis Phase:

The AS-IS analysis is executed here. As the name states, thorough insight into the existing processes, systems, equipment, data, operational standards, and output is gathered, discussed, documented, and later on analyzed to find out key attributes for later phases.

Phase-2: The Feasibility Phase:

The feasibility phase carries out detailed work to maximize the whole project’s ROI and prioritizes areas to be worked on. This phase takes input from phase-1 and analyzes the whole paradigm in detail to clearly mark areas of improvement.

Phase-3: The Proof of Concept (POC) Phase:

Once we figure out the target area(s), end-to-end implementation of the PAM is carried out as a pilot project of sorts. The POC gives detailed insight and is a litmus test for the upcoming days where full-blown implementation will be carried out all across the organization. Problems identified during this sprint are analyzed, amended, and improved wherever needed.

Phase-4: The Implementation Phase:

Now is the time for across-the-board, down-the-stream implementation of the model. Key areas identified during previous phases are carefully articulated and implemented. Step-by-step implementation of each area will eventually lead you toward fully integrated, efficient, and seamless processes. Benefits from the newly implemented system are there to be had, now.

Key Parameters of Implementation of PAM (Predictive Assets Management)

In the implementation phases defined earlier, key factors mentioned below are rigorously covered in thorough detail. This is important because subsequent steps take input from the predecessors and thus completing the predecessor in adequate detail that generates quantifiable output is necessary.

Each factor and its key characteristics are listed below:

Connectivity
• A feasibility study will be conducted to gather key insight into all equipment.
• The system can connect to different types of assets to communicate data.
• Connectivity on new aged devices is very successful, and efficient results can be obtained quickly by retrieving data efficiently.
• Even though it is slightly more limited in middle-aged equipment, reverse engineering can be used to access and analyze data.
• Depending on the criticality of old and non-communicating devices, it will be possible to implement a new PLC or replace the device.

Data Acquisition
• Connections for GSM, Wi-Fi, etc. (data connections) will be made and the data will be collected.
• Data is collected and the analyzed data is fed to machine learning algorithms for further analysis.
• The AI (Artificial Intelligence) will evaluate scenarios and KPIs.
• Based on carefully articulated KPIs, artificial intelligence algorithms will start processing attributes like data, alarms, and reports for decisions/predictions.

Predictive Analysis
• Analytics and AI algorithms in the cloud-based system will analyze the data obtained to make calculated predictions.
• If needed, the system can be configured to work in a local-cloud environment as well.
• The system’s predictions are shared in a well-formatted annotated report.
• The system provides RCA (root cause analysis), and the analysis made by the system can be provided in the form of an annotation report together with the root cause and cons relationship.
• Actionable insight prompts to take immediate measures to avoid instant failure(s).
• Clear and unambiguous guidance is provided by the system to take measures to avoid and devise a maintenance plan for assets that don’t have alarms.

Reporting / Dashboards

Visually intuitive, clear, and data-driven dashboards show a deep insight into your whole asset
Evaluate and view key decision-altering factors like
- Efficiency analysis of assets
- Tracking MC/RAV ratio on asset and/or plant-by-plant
- Cost based on number of failures and critical impact rate on business
- Efficiency or cost per part of the production
- Asset utilization and maintenance performance analyses of multi-branch structures such as retail, banking, industrial, logistics, warehouses, mining, etc.
- Total labor times and spare parts usage
- Maintenance activity performance
- Analysis of increased uptime and energy performance
- Determining the assets that can be improved by data-driven analysis
- Effective maintenance performance, monitoring, and analysis can be achieved by a workflow as data can also flow mobile
- Detecting assets that have difficulty lowering the MC/RAV ratio
- Optimum performance with calibration management
- Analyzing supplier's asset performance and selecting the most reliable products for future needs

Calculations

The MC/RAV ratio is calculated as:
(Annual Maintenance Cost X 100) / Replacement Asset Value

Studies and experience measurements show that the MC/RAV ratio, which can reach 2.5%, will achieve an operational excellence target level of 100%. Of course, this degree of excellence will only be possible with inter-unit coordination and improved corporate culture. Therefore, digitization is one of the most important factors that will allow this whole structure to form. Thanks to the big data that the system will provide, decision-making mechanisms will be able to make much more effective and scientific decisions. This powerful capability will lead to much more efficient results and operational excellence.

Overall Equipment Effectiveness (OEE)

Depending on this structure, when we look at the application areas in industrial facilities, we look for key attributes and features for assets. In order to identify losses, benchmark progress, and improve the productivity of manufacturing equipment, OEE (Overall Equipment Effectiveness) is the gold standard for measuring manufacturing productivity.

Simply put – it identifies the “truly-productive” percentage of your total manufacturing time. Measuring OEE gives you important insights and unearths the invisible losses you are incurring. With these clear and precisely directed insights, you can take necessary actions to improve your processes. Well, everyone desires to have a 100% score, but that is not possible in the real world. Breakages in the production line, uncalled-for stoppages, power outages, and other issues do happen during the production cycle. Gauging these three factors, i.e., quality, performance, and availability gives key insight into industrial plants and serves as a standard for productivity efficiency. Globally, this ratio stands around 60% (typically), giving good margins for improvements. This is where Predictive Asset Management comes in and can easily improve the efficiency of operations.

Total Effective Equipment Performance (TEEP)

Another metric that is used for gauging asset performances is TEEP. For a generalist understanding, TEEP is calculated by multiplying four factors: Availability, Performance, Quality, and Utilization.

TEEP (Total Effective Equipment Performance) shows the actual capacity of the manufacturing process. This used the values from OEE and applies another metric, i.e., utilization, to generate this key performance indicator.

TEEP = A x P x Q x U OR TEEP = OEE × Utilization
Utilization = Planned Production Time / All Time

Using this metric effectively, businesses can utilize the existing equipment in a highly efficient manner and can increase their output. This way, with minimum expense, in the fastest manner, performances can be improved without purchasing any new equipment.
This seems by many as a potential sales-enhancing attribute as the same equipment or infrastructure is capable enough to serve more clients if managed properly. It is important to note that there is no 100% efficiency equipment. Even the best systems can click a maximum of 90% utilization of their installed capacity.

Showcasing the Benefits

Fleet Operating Business

By applying predictive methods, fleet operating businesses can save millions of $ per annum. With reduced maintenance costs, fewer failures, and timely uninterrupted operations, corporations not only cut their operational losses but also gain on their operating profits.

For small vehicles under mid-sized organizations, the average per-vehicle cost saving is $850 per
- For 500 such vehicles, this turns out to be half a million dollars per
For companies running large vehicles (Buses, trucks, .), the average cost saving per vehicle is $2500.
- For 1000 such vehicles or more, this number crosses two million dollars per
Less than a Year, for
- This is huge; meaning that after the year, all the savings will be your net

NOTE:

The name of the enterprise is kept Anonymous due to confidentiality

If detailed insight into the numbers is desired, please contact us. Followed by an NDA, we will share all the relevant details. Or may even be able to experience them in person with POCs.
This covers fleets operated by all industries, including but not limited to, Mining, Industrial, Banks, Car Rental companies, Insurance companies, etc.

A Retail Store Company

Key factors affecting these companies are Energy and Asset maintenance costs. Not only it is the case that these companies are unaware of the maintenance details, but they also can’t control their maintenance costs. The results are really problematic and call for immediate action. No visibility on maintenance details or logs means total ignorance regarding what spares were changed on time, or late or even done correctly or otherwise.

Operating with 10,000 or more branches with a humungous asset
Operating with marginal profits and working in a highly competitive
Little optimization means huge
Maintenance and energy costs can be saved between 8% and 20% on average, by applying
Return on Investment is merely 2 years
Improves the decision-making process and enhances safety, compliance, and even saves labor costs.

A Waste Water Treatment Company

A highly challenging arena where measuring and classifying technological parameters (COT and suspended particles, debits, etc. in the fluids flowing from the factory to the plant) and acquisition of data from the devices in a timely and accurate manner was very difficult. This is the segment that sometimes results in penalties up to $100K or more, when SLAs between the factories and the treatment plants are breached. Legal and commercial challenges emerge due to the non-availability of correct data.

Immense benefits for factories and plants with accurate, precise, and timely availability of data.
ROI in 1 year approx.
Effective analysis and correct recharge of wastewater from factories.
Real-time maintenance and predictive management of analysis systems.
Effective SLA management saves penalties and legal complications
Increases plant lifetime and prevents sudden
Legal and economically fair solution for both parties
Accurate data and analysis with calibration management
Loss & fugitive management for Industrial Zone Managers
Fast-tracking and reporting for management

Conclusion

We believe that technological innovations should benefit people's lives. Businesses under the ‘new normal’ have to adapt to the products that make lives easy and are genuine results driven. The ability to have a real-time, uninterrupted, and accurate picture of their whole asset base is an advantage no one can ignore. The preemptive capabilities showcased by PAM produce immediate results and improve operations, enhance business immunity to a crisis, increase business efficiency and profitability, as well as have great turnaround times and awesome returns on investment.

I’m happy to discuss any of your needs in your organization to implement digitization and PAM kind of solutions to improve your operational efficiency and bottom-line growth and hence the global competitiveness and sustainability of your company.

Sonat Ciftcioglu

Electronics Engineer.

*Maintenance Cost/Replacement Asset Value

** Overall Equipment Effectiveness

pillar%20page%20line%201