A system for empirically diagnosing a condition of a monitored system. Estimates of monitored parameters from a model of the system provide residual values that can be analyzed for failure mode signature recognition. Residual values can also be tested for alert (non-zero) conditions, and patterns of alerts thus generated are analyzed for failure mode signature patterns. The system employs a similarity operator for signature recognition and also for parameter estimation. Failure modes are empirically determined, and precursor data is automatically analyzed to determine differentiable signatures for failure modes.

Diagnostic systems and methods for predictive condition monitoring

An improved empirical model-based surveillance or control system for monitoring or controlling a process or machine (105) provides adaptation of the empirical model (117) in response to new operational states that are deemed normal or non-exceptional for the process or machine. An adaptation decision module (125) differentiates process or sensor upset requiring alerts from new operational states not yet modeled. A retraining module (128) updates the empirical model (117) to incorporate the new states, and a pruning technique optionally maintains the empirical model by removing older states in favor of the added new states recognized by the model.

Adaptive modeling of changed states in predictive condition monitoring

A system and method for monitoring a condition of a monitored system. Estimates of monitored parameters from a model of the system provide residual values that can be analyzed using a sequential probability ratio test (“SPRT”). The invention employs empirically derived distributions in the SPRT to provide more accurate and sensitive alerts of impending faults, breakdowns and process deviations. The distributions can be generated from piecewise continuous approximation or spline functions based on the actual distribution of residual data to provide improved computational performance. The distributions can be provided before monitoring, or can be updated and determined during monitoring in an adaptive fashion.

Residual signal alert generation for condition monitoring using approximated SPRT distribution

A system (100), method and program product for monitoring a complex signal for ultrasensitive detection of state changes, or for signature recognition and classification is provided. A complex signal is decomposed periodically for empirical modeling (106). Wavelet analysis, frequency band filtering or other methods (102) may be used to decompose the complex signal into components. A library (104) of signature data may be referenced for selection of a recognized signature in the decomposed complex signal. The recognized signature may indicate data being carried in the complex signal. Estimated signal data may be generated for determination of an operational state of a monitored process or machine using a statistical hypothesis test (112) with reference to the decomposed input signal.

Complex signal decomposition and modeling

A method and apparatus are provided for diagnosing faults in a monitored system that is monitored by sensors. An empirical model is generated for a targeted component of the monitored system. The empirical model is trained with an historical data source that contains example observations of the sensors. Substantially real-time estimates are generated based on instrumented data corresponding to the targeted component. The substantially real-time estimates are compared and differenced with instrumented readings from the sensors to provide residual values. The residual values are analyzed to detect the faults and determine a location of the faults in the monitored system.

Kernel-based method for detecting boiler tube leaks

A process and a device for comprehensive control of a basic industry plant, such as a steel plant or an integrated iron works, which includes subprocesses that are critical with regard to continuous material flow, eg, casting processes The invention optimizes the material flow through the system and prevents the interruption of the material flow prior to the start of subprocesses that are critical with regard to continuous material flow The process sequence in a subprocess is subdivided into four steps, referred to as quarter cells with each quarter cell containing a point in time, a time range to describe possible process time fluctuations, the name of the previous quarter cell, ie, the name of the previous substep of a subprocess, as well as a marker of whether the process time fluctuation of this subcell is influenceable or non-influenceable

Ferd Hergert-Mueckusch

Papers

Process and system for time control of a basic industry plant