Implementation of Predictive Maintenance using Time-in-State® – Case Study
2020-01-09
Case Study: Predictive Maintenance
2020-01-10
Case Study: Pro-active decision-making
Implementing pro-active management of process and equipment performance using Time-in-State
What is Time-in-State®?
Time-in-State® identifies process and equipment issues causing inefficiency. It enables the design of solutions to improve performance.
Time-in-State® extracts information from process data. The methodology integrates process knowledge and experience with process data to deliver team learning and innovation.
The product consists of the following elements:
- Analytics
- Real-Time Monitoring
- MESA International endorsed methodology.
Implementation takes the format of a service level agreement. Change management and continuous improvement form an integral part of the implementation.
Time-in-State® is one of the most effective tools to describe process and equipment behavior, communicate process insight, and to establish a common understanding of issues affecting process performance.
The platform translates data into information that is useful to production, maintenance, financial, quality control and management.
Time-in-State® changes the way you think about and use production process data.
PROACTIVE DECISION-MAKING
Time-in-State® generates information from data to facilitate pro-active decision-making for the management of process and equipment.
For information to be useful for pro- active decision-making, the time- lapse between detecting changing behavior and the presence of conditions causing a loss should be long enough to implement corrective action.
The probability of incurring losses increases without early warning of deteriorating performance,
Aspects affecting plant performance include equipment condition, material variability, operator decision-making, and or plant configuration. When generating information for pro-active decision- making, it must be able to distinguish between these sources affecting performance.
Time-in-State® derives a performance baseline that takes process data, equipment data, and experiential knowledge into account.
By deriving a baseline at modular level provides insight into the root cause affecting performance. This baseline is referred to as the Optimum Operating Envelope (or OOE) of the module.
Time-in-State® takes process and equipment data into account when deriving a baseline.
PROCESS CAPABILITY MODEL
Process Capability Model breaks the production process down into production (and/or equipment) modules.
Time-in-State® Analytics characterizes each module’s behavior using process data.
Time-in-State® quantifies performance of each module – this approach delivers early warning of deteriorating performance.
Fuel Pulverization:
Background
Boilers in a coal power plant receive pulverized fuel from a bank of mills. The objective of the mills is to deliver the right quantity of fuel at the correct size distribution to the fuel burners in order to facilitate stable and complete combustion1:
-
An inability to deliver fuel at the correct rate could have a negative impact on boiler steam supply.
Size Distribution:
- Too fine pulverized fuel: Causes slagging in the furnace region which can disrupt the air/fuel ratio. It will also cause low NOx burners to become ineffective (at installations where these burners are used)
- Too coarse pulverized fuel: Causes the flame ball to burn higher; larger particles still burning at the super heater. These particles begin to stick to tubes forming clinker. Heat pick up through the tubes are reduced resulting in higher exhaust temperatures which can damage the bags in the Fabric Filter Plant.
Consequences of suboptimal mill performance may not always be visible immediately. Ensuring efficient and effective mill operation minimizes the probability of introducing variance into the furnace operation.
In an operation where multiple constraints apply, it is important to prioritize maintenance. This application illustrates how a common performance metric facilitates decision-making around the deployment/use of resources.
This case study shows how Time-in-State® translates available process measurements into actionable information to mitigate operational risk.
Considerations
The operation demands performance assessment of individual mills – six mills supply pulverized fuel to the boiler:
-
Quantify operational performance.
-
Sub-optimal mill efficiency and effectiveness don’t always manifest in immediate
losses e.g. sintering takes place over an extended time interval.
-
Poor operating conditions on one mill (out of five in operation) is not always apparent.
-
Provide early warning of deteriorating performance: It is necessary to pro-actively manage conditions that may later affect performance of downstream processes.
The need exists to quantify the effectiveness of maintenance actions (or other initiatives) for each of the mills.
Failure to monitor and track performance of individual modules masks inefficiency and degrades the quality of decision-making.
Analysis
Deriving the Optimum Operating Envelope (OOE):
-
Identify key influencing factors for the mills through consultation with plant
personnel. The aim is to capture knowledge, facilitate team learning and
establish alignment on issues that need to be considered.
-
Use historic process data, design information and plant personnel knowledge/experience to define the Optimum Operating Envelope (OOE) for the module.
Measuring Compliance with OOE:
The OOE definition provides a reference for measuring each mill’s performance. Evaluation of mill performance takes place by applying the OOE definition/model to the most recent process data.
The same control and operating philosophy are applied across all six mills. It is therefore possible to assess performance of all the mills using the same OOE definition.
Using the same OOE definition, it is possible to compare and rank mill performance on a specific generating unit. Applying the same approach, this method of measuring performance enables performance comparison across different units and stations.
Results- Mill D
Monthly Performance Assessment.
The graphs illustrate the performance of Mill D. The latest assessment is for July.
Each mill’s performance is reported using the common performance baseline or Optimum Operating Envelope (OOE) definition.
Compliance with OOE improved to a maximum in May. A slight degradation is visible during June and July.
This graph confirms that P5 was the main contributing factor causing non- compliance with OOE during Jan – April. During June and July, P2 and P4’s impact became more prominent.
The teams will discuss these trends with the aim of prioritizing initiatives.
Results - Mill F
Monthly Performance Assssment.
Compliance with OOE deteriorated after April .
P1 (hydraulic pressure) is the main contributing factor causing deteriorating performance during May, June and July. P1’s impact has been increasing since March, reaching a maximum in May.
Mill F is in a worse state than Mill D when comparing the respective mill’s compliance with OOE.
With this information, the team can generate informed decisions.
Pro-active Management of Process and Equipment Performance
Pro-active management of process and equipment performance demands a thorough understanding of issues affecting performance.
Time-in-State® delivers insight by integrating data and knowledge, stimulating innovation and team learning.
Time-in-State® extracts data patterns that associate with specific process and equipment conditions. Time-in-State® recognizes data patterns and translates data into actionable information.
Timely identification of abnormal equipment and process behavior is a prerequisite for pro-active management of process and equipment performance.
This application illustrates how existing process measurements can be converted into information to facilitate decision-making and prioritization of resources.
