Parameter change detection

An alternative SPM framework for autocorrelated data is developed by monitoring variations in time series model parameters that are updated at each new measurement instant. Parameter change detection with recursive weighted least squares was used to detect changes in the parameters and the order of a time series model that describes stock prices in financial markets [263]. Here, the recursive least squares is extended with adaptive forgetting. 

T Sastri. A recursive estimation algorithm for adaptive estimation and parameter change detection of time series models. J. Op. Res. Soc., 37 987-999, 1986. 

Parameter change detection, 27 Partial least squares, 42, 79 convergence, 81 inner relations, 81 multi-block, 113 multipass PLS for sensor auditing, 204... 

Forced expiration is commonly used to assess pulmonary function in both healthy and impaired individuals. Static measures of lung volumes (TLC, Vj, FRC) fail to detect dynamic changes in pulmonary function that are attributable to disease (e.g., asthmatic airway constriction). Obtaining maximum expiratory flow-volume (MEFV) curves (Fig. 5.21) permits derivation of key parameters in detecting changes in lung function. 

In contrast, inactivity of muscle gene expression and elevated DNA content of infected cell nuclei did not change detectably with MBZ treatment, which may indicate that these host cell parameters are not chronically regulated by the parasite. 

Bank and co-workers [19] have proposed using thermal analysis to measure other parameters for detecting local moisture content, changes in modulus and damping, and crystallinity in composite materials. 

Several related problems have been previously considered in the literature. In addition to the afore mentioned statistical approaches for structural change detection in data sets and their application for linear system identification [7], the joint problem of model structure determination and parameter estimation was addressed by [8-10]. A related approach was used by [11-13] in the context of data reconciliation. Additional aspects of model selection in chemical engineering are covered in [14]. Although the present problem shares common features with the all of the previous applications, it also presents unique characteristics that require a specific formulation. 

Due to the length of the production lines (up to 250 m), the time needed for vulcanization and thus, the slow speed of extrusion, the produced profile takes a long time to reach the inspection zone (up to 30 minutes). Thus, the results of operating parameter changes can only be accurately detected after this time. 

The modulation technique resolves the main technical difficulties of the constant potential spectral measurement at the electrode surface. Basically, in the modulation spectroscopic measurement, only the change associated with the change of the modulated parameter is detected. Thanks to lock-in ampHfication, we can significantly increase the sensitivity of the optical signal detection. It must be noted that what we can obtain is the change of the spectrum with respect to the modulated parameter but not the absolute reflection spectrum. In other words, modulation methods give the difference or differential spectrum. From the modulation spectrum, we cannot obtain explicitly the absolute spectrum at a unique condition unless a perfect reference absolute reflection spectrum is already in our hands. One should be careful in the interpretation of the spectral curves at this point. 

There are two main purposes of model updating or system identification. One common goal is to identify physical parameters, e.g., stiffness of a structural element or the diffusion rate of an air pollutant. These identified parameters can be further used as indicator for the status of the system or phenomenon. For example, the stiffness parameter of a structural member can be monitored from time to time and an abnormal reduction indicates possible damage of the member. However, reduction may be simply due to statistical uncertainty. Therefore, it is necessary to quantify the uncertainty of the estimation so that one can distinguish whether the parameter change is due to deterioration of the structural member. In this case, it is desirable to obtain a narrow distribution of the parameter so that small changes can be detected with a high level of confidence. 

For the Phase 1 study, sii le doses of Serp-1 protein were infused in normal volunteers as mandated by the FDA. This was the first trial in man with a new class of virus-derived native protein therapeutic No changes in cardiac, renal or hepatic function, as well as no chaises in clotting parameters were detected in this study. This Phase 1 safety study demonstrated that Serp-1 infusion was safe with no adverse events detected or reported. A Phase Ila study is currently ongoii in which the effects of a Serp-1 infusion is given for three days startup immediately after balloon ai oplasty and stent implant in patients with acute unstable angina and non-ST elevation myocardial infarction (NSTEMl). This trial is still ongoing at 7 sites in Canada and the US. The... 

Fouladirad, M. and M. Nikiforov (2006). On line change detection with nuisance parameters. In Safeprocess, Bei-jin, China, CD ROM. 

Lai, T. L. (1998). Information bounds and quick detection of parameter changes in stochastic systems. IEEE Transactions on Information Theory 44, 2917-2929. 

The method is particulary suited for the detection of incipient faults as it can pinpoint small parameter changes. In Chap. 6, least squares parameter estimation is considered with to regard to the isolation of multiple parametric faults. 

---