Fault detection and diagnosis (FDD) has received considerable attention with the advent of big data. Many data-driven FDD procedures have been proposed, but most of them may not be accurate when data missing occurs. Therefore, this paper proposes an improved random forest (RF) based on decision paths, named DPRF, utilizing correction coefficients to compensate for the influence of incomplete data. In this DPRF model, intact training samples are firstly used to grow all the decision trees in the RF. Then, for each test sample that possibly contains missing values, the decision paths and the corresponding nodes importance scores are obtained, so that for each tree in the RF, the reliability score for the sample can be inferred. Thus, the prediction results of each decision tree for the sample will be assigned to certain reliability scores. The final prediction result is obtained according to the majority voting law, combining both the predicting results and the corresponding reliability scores. To prove the feasibility and effectiveness of the proposed method, the Tennessee Eastman (TE) process is tested. Compared with other FDD methods, the proposed DPRF model shows better performance on incomplete data.
In response to the escalating challenges of rapid load fluctuations and intricate operating environments, supercritical power units demand enhanced control efficiency and adaptability. To this end, this study introduces a novel model predictive hybrid PID control strategy that integrates PID with model predictive control (MPC), leveraging the operational characteristics of multi-loop systems. The proposed strategy adeptly marries the swift response of PID controllers with the foresight and optimization capabilities of MPC. A dynamic model of a supercritical unit is constructed using the subspace identification method. The model’s high precision is confirmed by its alignment with field data. Load change simulations demonstrate that the PID–MPC hybrid controller shows faster response times and more precise tracking capabilities compared to the feedforward-PID strategy. It achieves substantial improvements in the IAE index for three loops, with increases of 29.2%, 54.1%, and 57.3% over the feedforward-PID controller. An energy-saving performance analysis indicates that the proactive control actions of both the PID–MPC and MPC strategies lead to dynamic exergy efficiency and coal consumption rates with a broader range of dynamic process changes. The disturbance scenario simulation regarding the proposed controller achieves faster settling times and minimizes control deviation compared to the traditional controller.
Mutual information (MI) has been widely used for association mining in complex chemical processes, but how to precisely estimate MI between variables of different numerical types, discriminate their association relationships with targets and finally achieve compact and interpretable prediction has not been discussed in detail, which may limit MI in more complicated industrial applications. Therefore, this paper first reviews the existing information-based association measures and proposes a general framework, GIEF, to consistently detect associations and independence between different types of variables. Then, the study defines four mutually exclusive association relations of variables from an information-theoretic perspective to guide feature selection and compact prediction in high-dimensional processes. Based on GIEF and conditional mutual information maximization (CMIM), a new algorithm, CMIM-GIEF, is proposed and tested on a fluidized catalytic cracking (FCC) process with 217 variables, one which achieves significantly improved accuracies with fewer variables in predicting the yields of four crucial products. The compact variables identified are also consistent with the results of Shapley Additive exPlanations (SHAP) and industrial experience, proving good adaptivity of the method for chemical process data.
21 April 2025 in Chemical Engineering & Technology