Chemical process systems are susceptible to disruptions that can affect production efficiency and even turn into accident with casualties. To reduce the impact of disruptions on chemical process systems, this study presents a data-driven methodology for evaluating and forecasting system resilience. Critical process parameters (CPPs) governing system performance are first identified, considering both safety constraints and production efficiency. Subsequently, potential disruptive events are systematically identified and generated. Then, dynamic simulations are performed to generate transient response data. Finally, a resilience assessment method considering the CPPs is proposed, and an attention Bi-LSTM model is developed to learn the temporal dependencies between disruptions characteristics and system resilience, thereby allowing the prediction of the system resilience. The results indicate that the proposed methodology can accurately predict the variation over time of system performance and resilience under disruptive scenarios, with a root mean square error (RMSE) of 0.0035 and a mean absolute error (MAE) of 0.0032. The error between the predicted value and the actual value of resilience does not exceed 0.005. The proposed methodology demonstrates robust capability in predicting resilience of chemical process systems under diverse disturbance scenarios. It provides a systematic approach for proactive resilience management in chemical process systems, with implications for enhancing operational safety and informing maintenance strategies.

Deviations of process parameters from their normal ranges are the primary causes of accidents in chemical process systems. Traditional risk assessment methods largely rely on static probability analysis based on historical data, which struggles to capture the dynamic influence of real-time parameter variations on risk and lacks the capability to predict risk evolution trends. This paper proposes a dynamic risk prediction method for chemical process systems based on enhanced feature engineering and XGBoost. First, key process parameters (KPPs), including temperature, liquid level and flow rate are identified through process analysis. A comprehensive risk indicator is then constructed using Dempster-Shafer (D-S) evidence theory to achieve dynamic quantification of system risk. Second, a dynamic simulation model is established using Aspen Plus, simulating operations under normal, disturbed, and extreme conditions to generate time-series data of KPPs. On this basis, multi-scale sliding window techniques are employed to extract enhanced features, including temporal, statistical, trend, and disturbance features. Finally, an XGBoost-based risk prediction model is developed. A continuous stirred-tank reactor (CSTR) is employed to demonstrate the proposed methodology. The results indicate that the proposed methodology achieves an RMSE of 0.159, MAE of 0.122 and an R² of 0.7237, outperforming traditional methods by significant margins. The results validate the effectiveness of combining enhanced feature engineering with XGBoost for risk prediction in chemical processes.

In the post-disruption phase, the resilience of LNG terminal system largely depends on maintenance resources—the more maintenance resources there are, the stronger the system's restoration capability and resilience. However, as maintenance resources increase, so do the associated maintenance costs. To enhance system resilience while controlling costs, a well-formulated optimization methodology is crucial. A process parameter-driven resilience optimization method for LNG terminal system considering the resilience enhancement rate (RER), cost and the maximum acceptable restoration time (MART) is proposed. The system resilience and RER are assessed by system performance curve, which is determined by time-dependent process parameters obtained from process simulations. The maintenance resources are represented by the number of maintenance team, including human resources, necessary equipment and materials, etc. A cost function model considering inherent cost, the cost of maintenance resources secondment and operating costs is established to represent the cost factors involved in the entire maintenance activity. According to derived results of the resilience assessment and cost analysis, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) is employed to solve the multi-objective optimization model developed in this study. The resilience enhancement optimization for the LNG terminal system is utilized to demonstrate the proposed methodology.

Chemical Process Systems (CPSs) exhibit complex characteristics and inherent dangers that can lead to serious accidents when disrupted. Accurate quantification and assessment of system resilience are crucial for effectively responding to potential undesired events. To address this, we propose a multiparametric resilience assessment methodology for CPSs that considers system dynamics and Independent Protection Layers (IPLs). This method integrates multiple CPS parameters using the Best Worst Method (BWM) to establish a comprehensive performance indicator. A dynamic simulation model incorporating IPLs is developed to monitor real-time changes in system parameters under disruptive influences. Additionally, a resilience metric is introduced, utilizing time-varying parameters to quantify system resilience under various disruptions. A case study involving a two-column pressure-swing distillation process with top recycling, designed to separate a minimum-boiling azeotrope of tetrahydrofuran and water, demonstrates the applicability of this method to complex CPSs. The results indicate that, compared to traditional resilience assessment methods based on reliability, the proposed approach provides time-dependent process parameters, reducing the uncertainty of reliability data. Furthermore, by considering IPLs, this method offers valuable decision support for the design and optimization of these protective layers.