Plant Asset Management (PAM)

Plant Asset Management
 

Plant Asset Management (PAM) has been used in operations for years, but recent industry trends and technological advancements make effective PAM strategies more critical than ever.

Plant personnel today face a transformative business environment filled with numerous challenges and demands.

Expectations of continuous improvement: 

• Save time, reduce costs, reduce downtime, improve product quality
• Loss of expertise through employee turnover or retirement
• Pressure to do more with fewer resources
• Desire to implement strategies associated with Industry 4.0, IIoT, Machine Learning, and Artificial Intelligence

Condition Based Maintenance (CBM) strategies improve efficiency

In order to keep operations running smoothly, manufacturing companies need a plan to keep equipment functioning at peak performance. Preventive or time-based maintenance once was the preferred solution for teams to maintain equipment health. However, this leads to added, and in many cases unnecessary, costs, due to performing maintenance on a piece of equipment before it really needs attention.

An alternative strategy used by some is “run-to-failure”, especially if a piece of equipment is deemed as “non-critical”. But this too leads to additional downtime and surprise equipment failures, which can be extremely costly and frustrating.

Condition-based maintenance (CBM) strategies use real data collected by sensors about the equipment to determine whether or not and when corrective action needs to be taken on that piece of equipment. CBM enables maintenance teams to identify the piece of equipment that is “most at risk” and prioritize work on that equipment before others. CBM also improves the balance of production schedules with equipment maintenance needs, ensuring product quality and production stability.

Predictive maintenance — using data and analysis to predict when issues will arise — has been found to save maintenance resources while avoiding equipment issues. Rather than sending technicians out on a schedule to review equipment that may or may not have issues, predictive maintenance combines sensor data with machine learning and diagnostics to determine when conditions have changed and require attention.

Intelligent devices – more data for better decision making

With the increasing availability of edge devices and smart sensors comes to the increasing amount of data and information at hand. For mission-critical equipment, this information has been available for some time at the device level, but smart networks have enabled decision-makers to access this important data more easily.

Traditionally, non-mission-critical equipment has been monitored by periodic operator rounds (once per day or less) or is unmonitored altogether. This method brings concerns of data accuracy, operator time and cost to conduct the rounds and slow reaction times in case of a failure. But industry innovations can improve the monitoring and plant asset management of this type of equipment as well.

Yokogawa’s Sushi sensor is a small, wireless device that comes in pressure, vibration or temperature varieties that monitor conditions continuously and accurately over vast distances of six miles or more. Small sensors deliver data from tight-fitting, remote/hard-to-reach, or hazardous locations to a central hub so that teams can track trends, detect abnormal conditions early and help direct troubleshooting activities efficiently.

Smart sensors, Powerful solutions

Yokogawa’s IIoT Sushi sensor PAM solution automates the manual operator round process and improves accuracy by collecting and digitizing precise data on a configurable interval (typically every hour) from hundreds of machines simultaneously. Where traditional operator rounds are reactive in nature, Yokogawa Sushi PAM takes a proactive approach to predict equipment abnormalities. This enables the plant maintenance manager to schedule preventative maintenance before equipment breaks down, thus eliminating the cost of unforeseen equipment downtime. With data collection now automated through IIoT PAM, operators previously spending hours on manual rounds are now available for higher-value assignments.

IIoT Sushi Sensor PAM solution ultimately improves plant efficiency by enabling equipment managers to utilize their resources more effectively and make more informed decisions. Robust sensors automatically collect hundreds of data points simultaneously from throughout the plant and transmit them via a single gateway to be digitized, stored, and analyzed on-premise, in the cloud, or both. 

Artificial Intelligence (AI) and Machine Learning (ML) algorithms can also improve Plant Asset Management strategies. These AI algorithms can learn the normal operating conditions of each unique piece of equipment, then detect abnormal conditions and predict failures in advance, allowing maintenance teams to prioritize jobs and keep the equipment healthy and running optimally.

Role of Smart Analyzers in Plant Asset Management

Yokogawa’s smart analyzer portfolio consists of liquid measurements, gas chromatographs, and tuneable diode laser analyzers. All of these devices have built-in self-diagnostic capabilities that can predict their own maintenance requirements.

Self-diagnostic capability is nothing new, this information has been available within the analyzer for a long time. However, IIoT has enabled this data and diagnostic information to be readily available to plant personnel and decision makers when and where they need it, rather than being isolated at only the device level. 

Consider the common industry occurrence of a pH sensor that has aged or broken and no longer works properly. This causes the analyzer to behave in a particular way. If equipped with self-diagnostics the outputs may drive high or low. However, the operator will not know why the outputs are behaving this way, only assuming something is wrong with either the analyzer or the process. 

Not all analyzers have diagnostics onboard. This may result in a default of pH  7 which may be a desire to some, while others may increase chemical dosing to try to achieve their pH set point.

A clever analyzer will pick up these anomalies, however, an intelligent analyzer will also pass this information on. This can then be incorporated into the Plant Asset Management system to help planning and operations of the entire plant.

Data you can trust for decisions that matter

Making informed decisions based on instrumentation data and equipment conditions can have a profound impact on plant profitability and performance. However, the outcome of these decisions can only be as good as the quality of data being used in the process. This is why high-quality measurements and smart sensor technologies are the backbone of any Plant Asset Management system.