MSET: An Early Warning System with Broad Industrial Application
The success of modern industries— especially those that are electricity-intensive—depends on complex engineering systems to ensure safe, productive and efficient operations. System breakdowns can result in millions of dollars in lost time and productivity—and even the loss of life and property. For example, in the utilities industry—where the continuous operation of coolant pumps is essential—the breakdown of a single pump can result in a loss of as much as $10 million in downtime.
Scientists at Argonne National Laboratory devised a unique early-warning system, called the Multivariate State Estimation Technique (MSET), that monitors the performance of sensors, equipment and plant processes in an industrial environment. A highly sensitive, highly accurate tool, MSET monitors the operation of any process that uses multiple sensors, detecting and alerting users of potentialDescription
MSET, the winner of a 1998 R&D 100 Award, consists of a unique, patented suite of statistically based pattern recognition modules. It detects and identifies malfunctions that may occur in process sensors, components or control systems; or changes in process operating conditions. The MSET modules interact to provide users with the information needed for the safe, reliable and economical operation of a process by detecting, locating and identifying very subtle changes that could lead to future problems well in advance of actual equipment degradation.
Since it provides continuous calibration validation for all sensors, MSET offers a technical basis for reducing burdensome instrument calibration requirements. It can also help users determine when it is appropriate to continue or extend operation of certain components, or to schedule corrective actions, such as sensor replacement or re-calibration, component adjustment.
MSET uses an ultra-sensitive Sequential Probability Ratio Test (SPRT, which was also developed and patented by the MSET inventors) to discern sensor or system anomalies at the earliest possible time. MSET’s unique capabilities make
it better than conventional approaches—including neural networks—in sensitivity, reliability and computational efficiency.
To use MSET, the user first collects sensor readings (via a digital acquisition system) to characterize the normal operating state of the system. MSET automatically selects an optimal subset of these data and uses it to "train" the system to recognize normal behavior. During monitoring, MSET generates an accurate estimate of what each signal should be based on the latest set of sensor readings and the previously learned correlations among them. Then, SPRT analyzes the difference between this state estimate and the measurement, and quickly detects and alerts the smallest developing faults. If an abnormal condition is detected, the initial diagnostic step identifies the cause as either a sensor degradation or an operational change in the process. When a sensor fault is identified, MSET uses the estimated value of the signal to provide an extremely precise "virtual sensor" that can be used to fully replace the function of the faulted sensor.Benefits
MSET’s benefits include:
- Diversity of application. MSET can be used in an exceptionally wide range of industries, from aerospace to utilities.
- Cost-saving. MSET saves money in industries where high value is placed on safety, reliability, quality and avoidance of production loss. It also cuts the cost of generating electricity.
- Enhancing safety. MSET enhances plant safety.
Superior performance. MSET has simultaneously enhanced both safety margins and operating efficiency for nearly all plant and process applications to which it has been applied. By comparison, in nearly all chemical, manufacturing, transportation and utility sectors, new safety technology or procedures almost always carry some “penalty” in reduced system availability or operating efficiency.
MSET is applicable to any industry in which continuous operation and safety are imperative. The suite was initially demonstrated at the U.S. Department of Energy’s EBR-II nuclear reactor, where it was shown to detect coolant pump abnormalities at extremely early stages of degradation (well in advance of actual damage) and to provide reliable "virtual" replacement signals for degraded and irreplaceable sensors (for example, coolant flow meter).
MSET has also been used for light water reactor signal validation applications at the Florida Power Corporation Crystal River 3 nuclear power station. During the testing, MSET detected and identified a number of sensor problems. For example, it identified a subtle discrepancy in a primary loop flow channel that could not be detected through visual examination of the data or by the existing monitoring systems. Upon further examination of the instrument string, a degrading component was revealed and subsequently replaced. Had this problem not been identified, the resulting failure would have necessitated replacing the entire instrument string, including the sensor, to avoid plant shutdown.
Other applications outside the power industry — some licensed and some in negotiation — include improved manufacturing, enhanced energy use for co-generation technology, sensor validation for commercial jet engines, improved pharmaceutical quality assurance, and aerospace applications.Technology Status
|Technology ID||Development Stage||Availability||Published||Last Updated|
|ANL-IN-89-043, ANL-IN-91-077, ANL-IN-91-078, -078b,and -078c, ANL-IN-92-099, ANL-IN-93-112, ANL-IN-93-128 and -128B, ANL-IN-94-081, ANL-IN-94-135 and -135b,ANL?IN-95-065, ANL-IN-96-136, ANL-IN-97-101,ANL?IN-98-082, ANL-IN-98-107||Exclusively Licensed||Licensed||07/16/2013||06/13/2013|