Multimode process identification and monitoring based on hierarchical fluctuation window strategy

Hidden Markov model-based approach for multimode process monitoring

Usually, industrial processes have multiple operational modes due to different production strategies, external environmental variability, or changes in product specifications. Monitoring of multimode processes constitutes a challenging problem considering multiple steady-state operational regions and dynamic transitions. This paper proposes a novel method for the offline identification of stable modes and transitions based on a local kernel density estimation algorithm. The online monitoring scheme is based on mode identification and transition tracking. The Tennessee Eastman (TE) benchmark process is used as a case study to evaluate the performance of the proposal. As a result, stable modes are successfully isolated from transitions, even when these involve complex changes in the production mode. The results also demonstrate that the proposed scheme is capable of tracking mode changes, and finally, results monitored during transitions confirm the validity and efficacy of the new approach compared with pr...

Key principal components with recursive local outlier factor for multimode chemical process monitoring

Industrial processes generally have various operation modes, and fault detection for such processes is important. This paper proposes a method that integrates a variational Bayesian Gaussian mixture model with canonical correlation analysis (VBGMM-CCA) for efficient multimode process monitoring. The proposed VBGMM-CCA method maximizes the advantage of VBGMM in automatic mode identification and the superiority of CCA in local fault detection. First, VBGMM is applied to unlabeled historical process data to determine the number of operation modes and cluster the data in each mode. Second, local CCA models that explore input and output relationships are established. Fault detection residuals are generated in each local CCA model, and monitoring statistics are derived. Finally, a Bayesian inference probability index that integrates monitoring results from all local models is developed to increase the monitoring robustness. The effectiveness of the proposed monitoring scheme is verified through experimental studies on a numerical example and the multiphase batch-fed penicillin fermentation process. Note to Practitioners —Process monitoring is important in guaranteeing process safety and improving product quality. Large amounts of unlabeled process data with multiple operation modes generally exist in industrial processes. Labeling these data is difficult or costly. Hence, this paper presents a VBGMM-CCA method for monitoring multimode processes. The key advantage of the proposed method is that it automatically identifies the number of operation modes in historical data and clusters the data. Then, local CCA monitors are established to model the process input and output relationships. During online monitoring, the running-on operation mode is identified through a density function, and the process status is evaluated by the corresponding CCA monitor. A probabilistic monitoring index is also developed to increase the robustness of the monitoring. In comparison with the results of conventional methods, the monitoring results of the proposed approach are more reliable and informative because the process status and the type of the detected fault are presented.

Due to the existence of multiple operating modes, traditional fault detection techniques are ill-suited for complex industrial processes. Although there are more and more literature studies concerning this problem, only a few of them are based on the hidden Markov model (HMM). However, there is no exploration to concern the unknown mode in the industrial process based on it. This article proposes a novel process monitoring approach based on moving window HMM (MVHMM) for real-time multimode process monitoring with unknown mode. First, a hidden Markov model is built by training set. Instead of just considering the posterior probability of one single sample, the moving window is introduced to utilize the independence of samples for improving the accuracy of online mode identification. In addition, an MVHMM-based threshold statistic is defined to identify the unknown mode. Also, various known modes which include stable modes and transitions are separated on the basis of the Viterbi algorithm. Second, a new mo...

A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes

In this paper, a multimode process monitoring strategy based on improved just‐in‐time‐learning associated with locality preserving projections (IJITL‐LPP) is proposed. First, raw data are projected into the feature space using locality preserving projections (LPP). Second, IJITL searches for similar samples of the query sample in the feature space by introducing a variational inference Gaussian mixture model (VIGMM). Finally, the new statistic named average distance is created to complete process monitoring. In the IJITL, the introduced VI can automatically determine the number of modes, thereby accelerating the efficiency of selecting similar samples. In the process monitoring phase, the average distance can reduce the impact of different mode dispersion on fault detection. In addition, LPP can render the model less sensitive to outliers. Compared with principal component analysis (PCA), LPP, K nearest neighbour rules, Gaussian mixture model (GMM), K‐means based‐PCA, and just‐in‐time‐learning (JITL)‐based LPP, the proposed method has better performance in a numerical case, the Tennessee Eastman process, and the semiconductor etching process.

Modern industrial processes increasingly prioritize demands for safety and reliability, spurring substantial research on process monitoring models. Among existing research subjects, concurrent multimode operating conditions are vital for effective process monitoring. This work proposes an efficient dimensionality‐reducing Gaussian mixture‐based reconstruction approach for multimode industrial process monitoring. The t‐SNE method is first employed to transform high‐dimensional data into a lower‐dimensional space that retains critical operational information. Using these reduced dimensions, a robust Gaussian mixture model is established to partition the operation data into different modes. Furthermore, the original data are assigned to the corresponding operating modes, and local variational autoencoder (VAE) reconstruction models are established, respectively. For each VAE model, two statistics are designed, termed and , to detect abnormalities. The proposed method is applied to a three‐phase flow facility, and the superiority over the comparison methods is proved.

The LLC resonant converter, as an isolated DC-DC conversion topology, has been widely adopted in industrial applications. However, when operating under wide input/output voltage ranges, a broad switching frequency range is required to achieve the desired voltage gain. This wide frequency variation complicates the design of magnetic components, causes loss of soft-switching characteristics, and deteriorates electromagnetic interference (EMI) performance. To address these challenges, this paper presents a detailed analysis of the L-LCLC resonant converter. By controlling the connection/disconnection of additional inductors and capacitors through switching devices, the topology achieves structural reconfiguration to enhance the voltage gain range. Optimal mode transition points are selected to ensure stable operation during mode transitions, thereby reducing design complexity, minimizing transition losses, and suppressing voltage/current stress. The parameter design methodology for the additional reactive components is systematically developed. The converter’s performance is validated with Simulink, and the experimental prototype is established with 100 W. Both simulation and experimental results confirm that the L-LCLC resonant converter achieves a wide voltage gain range within a narrow frequency band while maintaining stable mode transitions.

Modern industrial systems typically operate in a multimode environment due to continuous changes in raw materials and production schedules. Traditional static monitoring methods often struggle to accurately capture the intricate relationships between different modes, leading to model mismatches and a significant decline in monitoring performance. On the other hand, emergence of a new mode often prompts model updates that focus on the new data, potentially causing the model to forget historical knowledge, which is a phenomenon known as catastrophic forgetting. To address these issues, we propose a zero forgetting lifelong dictionary learning (ZFLDL) method for multimode process monitoring. ZFLDL integrates a low-rank basis matrix growth mechanism with an adaptive basis matrix selector, enabling effective representation of knowledge across both new and historical modes. Specifically, a novel low-rank decomposition method is first proposed to address feature redundancy in data representation with an overcomplete dictionary. This method utilizes a low-rank matrix, i.e. a “basis matrix”, as the fundamental representation unit, which can accurately capture the core data features and enhance the dictionary's representation capability. Then, to address the emergence of new modes, a zero forgetting continual learning framework based on low-rank basis matrix growth is proposed. By adaptively adding basis matrices for each new mode while freezing those associated with historical modes, the dictionary efficiently assimilates new knowledge while ensuring zero forgetting of historical knowledge. Additionally, since only the basis matrices related to the new mode are updated, this approach significantly reduces the number of parameters requiring training, thus enhancing the model's learning efficiency. Finally, an adaptive basis matrix selector is proposed. By evaluating the contribution of each basis matrix to different modes, it dynamically selects the basis matrices that best match the specific mode, ensuring accurate mode recognition and reliable process monitoring. Extensive experiments have demonstrated that the proposed method outperforms several state-of-the-art methods, exhibiting superior continual learning capability and enhanced process monitoring performance.

New embedded systems offer rich power management features in the form of multiple operational and nonoperational power modes. While they offer mechanisms for better energy efficiency, they also complicate power management decisions in the presence of realtime constraints. A traditional dynamic power management techniques based on localized break-even-time analysis with simple on/off power controls often yield suboptimal if not incorrect results globally. To address these problems, This work presents two core algorithms for reducing idle energy consumption at the component level and system level. The first algorithm discovers the optimal sequence for mode transition over multiple power modes under timing constraints. It assists the second algorithm that performs a sophisticated global search strategy to aggressively explore system-wide energy savings by correctly interpreting the constraints across all subsystems. Experimental results show that in an embedded radio system where idle energy cost matches or exceeds the active energy consumption, our technique can further reduce the idle energy by 50-70%, which translates into 30-50% of overall system energy compared to existing techniques.

Industrial processes typically have multiple operating modes with complex data distribution and locality faults, which challenges the traditional multivariate statistical process monitoring methods. To address this problem, a double‐level local information‐based local outlier factor (LOF) method is proposed in this work for multimode complex process monitoring. First, to handle the multimodality, the local neighborhood standardization strategy is adopted to utilize the statistical information of local data structure. Second, the variable LOF method is proposed to determine reasonable boundary for complex data distribution and simultaneously reflect local variable behaviors. For better online monitoring, a weighting strategy is applied to emphasize the local variable information, and the Bayesian inference is employed to integrate the LOF value of each variable. To isolate the fault variables, a contribution plot is designed. Finally, a numerical example and the benchmark Tennessee Eastman process are used to demonstrate the effectiveness and superiority of the proposed method.

Enhanced robust multimode process monitoring under dirty data via difference-based decomposition of matrix

To meet the demand for diversified products, industrial processes typically have multiple operating modes. In this article, a novel scheme based on aligned mixture factor analysis (AMFA) is proposed for multimode process monitoring. First, mixture factor analysis (MFA) is applied to produce a statistical fingerprint of the training data that gives a detailed description of the multiple operating modes. Then, unlike conventional multimodal algorithms in which multiple models are constructed and monitoring results are softly combined, the proposed method aims at aligning the separated local models together and performing the monitoring behaviors based on the global model. Through this approach of dividing and integrating, both the within-mode and cross-mode correlations can be greatly preserved in the global model. Finally, the utility and feasibility of the proposed method are demonstrated through a numerical example, a nonisothermal continuous stirred-tank reactor (CSTR) model, and the Tennessee Eastman benchmark process.

Heat and mass transfer in electron beam additive manufacturing