Accuracy Of Soft Sensor Models Research Articles

An adaptive soft sensor method of D-vine copula quantile regression for complex chemical processes

Non-linear and non-Gaussian properties are challenging topics in the soft sensor modeling of chemical processes, and fluctuations in the environmental conditions of chemical plants will also affect the accuracy of soft sensor models. This paper proposes an adaptive soft sensor method of D-vine copula quantile regression (aDVQR). In the modeling process, a sparse vine model is established using the Bayesian information criterion. Then, the conditional quantile function value of the specified quantile can be obtained via the recursive nesting method by the h function. An online model updating system based on the aDVQR model is also proposed, and an adaptive soft sensor model is established. The proposed adaptive soft sensor method can successfully approximate the non-linear and non-Gaussian relationships between variables and adapt to unstable environments. Finally, a numerical example and an example of the ethylene industry are used to verify the effectiveness of the proposed method.

Novel manifold learning based virtual sample generation for optimizing soft sensor with small data

Due to the extremely complex mechanism and strong non-linear characteristics of industrial processes, data-driven soft sensor technologies play a key role in the intelligent measurement of process industries. However, the information of the collected process data in the steady stage is quite limited and unreliable, causing the small sample problem. As a result, it becomes an intractable challenge to catch the nature of the process and build accurate soft sensor models. To solve this problem, this paper proposes a novel manifold learning based virtual sample generation method (Isomap-VSG) to generate feasible virtual samples in the information gaps for supplementing the original small sample space. To find data sparse regions reasonably, one kind of manifold learning methods called Isomap is used to visualize process data with high dimension. Then virtual samples can be generated by the interpolation method and extreme learning machine. The simulation results on a standard dataset and a real-world application demonstrate that, compared with other advanced methods, the proposed Isomap-VSG method can achieve better performance in terms of generating feasible virtual samples and improving the accuracy of soft sensor models using limited samples.

Soft Sensor Model Derived from Wiener Model Structure: Modeling and Identification

The processes of building dynamic and static relationships between secondary and primary variables are usually integrated in most of nonlinear dynamic soft sensor models. However, such integration limits the estimation accuracy of soft sensor models. Wiener model effectively describes dynamic and static characteristics of a system with the structure of dynamic and static submodels in cascade. We propose a soft sensor model derived from Wiener model structure, which is an extension of Wiener model. Dynamic and static relationships between secondary and primary variables are built respectively to describe the dynamic and static characteristics of system. The feasibility of this model is verified. Then the expression of discrete model is derived for soft sensor system. Conjugate gradient algorithm is applied to identify the dynamic and static model parameters alternately. Corresponding update method for soft sensor system is also given. Case studies confirm the effectiveness of the proposed model, alternate identification algorithm, and update method.

Estimation of predictive accuracy of soft sensor models based on data density

Soft sensors are widely used to predict process variables that are difficult to measure online. By using soft sensors, analyzer faults can be detected when the difference between a measured value and a predicted value is large. However, it is difficult to detect abnormal data and determine the reasons for the abnormality because prediction errors increase not only because of analyzer faults but also because of variations caused by changes in the state of the chemical plants. To separate these factors, we previously applied applicability domains to the soft sensors and proposed construction of the relationships between the distances to soft sensor models (DMs) and the prediction accuracy of the models quantitatively, and estimated the prediction accuracy, i.e. the error bar, for new data online. In this paper, we use k-nearest-neighbor method and a one-class support vector machine (OCSVM) to estimate the data density and use the average of the distances from the k nearest data and the output of an OCSVM as DMs, respectively. The proposed method was applied to both simulation data and real industrial data, and the superiority of the proposed DMs compared with the traditional models was demonstrated by comparison of their results.

Outlier Detection for Soft-Sensor Modeling Data Based on <i>k</i>-Nearest Neighbor

The on-line estimation of some key hard-to-measure process variables by using soft-sensor technique has received extensive concern in industrial production process. The precision of on-line estimation is closely related to the accuracy of soft-sensor model, while the accuracy of soft-sensor model depends strongly on the accuracy of modeling data. Aiming at the special character of the definition for outliers in soft-sensor modeling process, an outlier detection method based on k-nearest neighbor (k-NN) is proposed in this paper. The proposed method can be realized conveniently from data without priori knowledge and assumption of the process. The simulation result and practical application show that the proposed outlier detection method based on k-NN has good detection effect and high application value.