Historical Operation Data Research Articles

A data-driven linear formulation of the optimal demand response scheduling problem for an industrial air separation unit

Demand response (DR) has become a key element in balancing the power grid as the contribution of time-varying renewable power generation increases. Chemical plants are appealing candidates for DR programs as they offer large, concentrated and flexible loads. DR participation calls for frequent production rate changes over time scales that overlap with the dominant dynamics of the plant. Production scheduling should therefore consider the process dynamics explicitly. We present a data-driven approach for modelling the scheduling-relevant dynamics based on historical closed-loop operating data using autoregressive with extra inputs (ARX) models. We introduce a new, linear scheduling problem formulation based on the ARX representation, and demonstrate its implementation on an industrial air separation unit.

Repair limit policy of aircraft component based on extended uncertain random renewal reward process

PurposeThe purpose of this paper is to focus on an optimizing maintenance policy with repair limit time for a new type of aircraft component, in which the lifetime is assumed to be an uncertain variable due to no historical operation data, and the repair time is a random variable that can be described by the experimental data.Design/methodology/approachTo describe this repair limit time policy over an infinite time horizon, an extended uncertain random renewal reward theorem is firstly proposed based on chance theory, involves uncertain random interarrival times and stochastic rewards. Accordingly, the uncertain random programming model, which minimized the expected maintenance cost rate, is formulated to find the optimal repair limit time.FindingsA numerical example with sensitivity analysis is provided to illustrate the utility of the proposed policy. It provides a useful reference and guidance for aircraft optimization. For maintainers, it plays an important guiding role in engineering practice.Originality/valueThe proposed uncertain random renewal reward process proved useful for the optimization of maintenance strategy with maintenance limited time for a new type of aircraft components, which provides scientific support for aircraft maintenance decision-making for civil aviation enterprises.

Stochastic Delay Cost Functions to Estimate Delay Propagation Under Uncertainty

We provide a mathematical formulation of flight-specific delay cost functions that enables a detailed tactical consideration of how a given flight delay will interact with all downstream constraints in the respective aircraft rotation. These functions are reformulated into stochastic delay cost functions to respect conditional probabilities and increasing uncertainty related to more distant operational constraints. Conditional probabilities are learned from historical operations data, such that typical delay propagation patterns can support the flight prioritization process as a part of tactical airline schedule recovery. A case study compares the impact of deterministic and stochastic cost functions on optimal recovery decisions during an airport constraint. We find that deterministic functions systematically overestimate potential disruption costs as well as optimal schedule recovery costs in high delay situations. Thus, an optimisation based on stochastic costs outperforms the deterministic approach by up to 15%, as it reveals ‘hidden’ downstream recovery potentials. This results in different slot allocations and in fewer passengers missing their connections.

A State Evaluation Method of Equipment Based on Safe Operation State Space Extraction with Zero-failure Data

For high reliability equipment and newly designed products, it is difficult to accurately evaluate the equipment status because almost no failure data will be generated during testing or using period. At present, the analysis of zero fault data mainly focuses on reliability estimation and unsupervised fault detection, and there is little research on the safe operation state of equipment to evaluate whether the equipment is in normal state. In this paper, we propose an equipment state evaluation method based on safe operation state space extraction, and verify the feasibility of this method through real data experiments. This method uses algorithms such as LOF (local outlier factor) and k-means algorithm to extract the parameter range of normal operation of the equipment from the historical zero-failure operation data, so as to judge whether the equipment is in a safe operation state. Compared with other methods, this method is simple and easy to use, and has wider applicability and stronger interpretability.

Construction and Application of Reservoir Flood Control Operation Rules Using the Decision Tree Algorithm

Current conventional and optimal reservoir flood control operation methods insufficiently utilize historical reservoir operation data, which include rainfall, runoff generation, and inflow from the watershed, as well as the operational experience of decision makers over many years. Therefore, this study proposed and evaluated a new method for extracting reservoir flood control operation rules from historical operation data using the C4.5 algorithm. Thus, in this paper, the C4.5 algorithm is first introduced; then, the generation of the flood control operation dataset, the construction of decision tree-based (DT-based) rules, and the subsequent design of a real-time operating scheme are detailed. A case study of the Rizhao Reservoir is then employed to demonstrate the feasibility and even superiority of the operating scheme formulated using DT-based rules. Compared with previously proposed conventional and optimal reservoir operation methods, the DT-based method has the advantages of strong and convenient adaptability, enabling decision makers to effectively guide real-time reservoir operation.

Thermal Runaway Prognosis of Battery Systems Using the Modified Multiscale Entropy in Real-World Electric Vehicles

The battery system is vital for the safety and durability of a real-world electric vehicle (EV), and the prognosis of battery thermal runaway trigged by various abuse conditions is critical for preventing security incidents, such as spontaneous combustion or explosion. This article presents a real-scenario-based thermal runaway prognosis on a Li(NiCoMn)O <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ternary battery in an actual electric bus, deriving historical operation data from the National Monitoring and Management Platform for Electric Vehicles of China. The multiscale detailed features of the fault signals before the accident are extracted using the modified multiscale entropy algorithm, avoiding entropy fluctuations and information redundancy due to the sliding averaging process, as well as overcoming the shortcomings of the single-scale coarse-graining and dimensional disaster. The results show that abnormal cells can be detected as early as one week before the accident. Furthermore, a real-time multilevel prognosis strategy based on the determined anomaly coefficients is proposed, which can highlight the faulty cells and improve the prognosis sensitivity by filtering out the redundant scales. The verification results on the accident vehicle show that the early abnormal cells can be effectively diagnosed, preventing the occurrence of thermal runaway and safeguarding the safety of drivers and passengers in real-world vehicular operation.

Dynamic model development for vehicle air conditioners based on physics-guided deep learning

Air conditioners (AC) are responsible for the largest portion of energy use among all auxiliary components of vehicles. Most white-box models developed for dynamic modeling of vapor compression systems (VCS) are not adequate to model vehicle ACs due to stronger dynamics and disturbances caused by frequent door open/close, random numbers of passengers entering/leaving the vehicles as well as intermittent shading effect on roads. In this study, a novel physics-guided deep learning method is proposed for dynamic modeling of vehicle ACs based on both domain knowledge and historical operational data. To maximize the practical values of the model in control and diagnosis of ACs, this research aims at developing an integrated VCS model consisting of individual models of major AC components rather than a black-box model of the entire system. Domain knowledge guides the determination of model inputs and outputs, design of the model structure, and understanding of temporal relationship in developing dynamic heat exchanger models. A newly developed NARX-LSTM-MLP neural network is proposed for heat exchange process modelling. The compressor is modelled by a multiple-layer perception (MLP). Component models are integrated by referring to the physical system structure. Field AC operation data from a city bus collected by IoT sensors are used in this study. Validation results indicate good accordance between measurements and simulation results. The model developed is less expensive, more convenient, and more feasible for health monitoring of numerous vehicle ACs at city level in the context of IoT.

Identification of the characteristic parameters for gas pipe sections using the maximum likelihood method and least square method

AbstractThe pipeline efficiency factor (E‐value) and the overall heat transfer coefficient (K‐value) are, respectively, the characteristic parameters that describe the flow and heat transfer behavior of gas pipe sections. These parameters have a significant impact on the accuracy of the thermo‐hydraulic calculations of the gas flow processing. Hence, they should be investigated thoroughly. Due to various complex factors affecting the E‐value and the K‐value in operating the in‐service gas pipe sections, it is often difficult to calculate the two characteristic parameters accurately using physics‐based formulae. Based on quasi‐steady‐state historical operational data sets of the in‐service gas pipe section, the characteristic parameters are identified with the maximum likelihood method and the least square method, respectively. Besides, the characteristic parameters of the gas pipe section are derived from solving the inverse problem of the steady‐state thermo‐hydraulic calculations. Both methods are applied to an in‐service pipeline, and the two parameters are obtained from 144 historical operational data sets. By introducing the two parameters into the thermo‐hydraulic calculations for certain quasi‐steady‐state historical conditions in the same gas pipe section, the maximum relative errors occurred between the calculated results and the measured data are 2.91% and 2.66%, respectively. Additionally, the difference between the two methods is small, with a gap of 0.0037 W/(m2 K) in K‐value and 0.0206 in E‐value. The proposed identification methods are extendable to provide adequate technical support for large‐scale gas pipeline networks.

Modeling and Optimization of Multiaction Dynamic Dispatching Problem for Shared Autonomous Electric Vehicles

The fusion of electricity, automation, and sharing is forming a new Autonomous Mobility-on-Demand (AMoD) system in current urban transportation, in which the Shared Autonomous Electric Vehicles (SAEVs) are a fleet to execute delivery, parking, recharging, and repositioning tasks automatically. To model the decision-making process of AMoD system and optimize multiaction dynamic dispatching of SAEVs over a long horizon, the dispatching problem of SAEVs is modeled according to Markov Decision Process (MDP) at first. Then two optimization models from short-sighted view and farsighted view based on combinatorial optimization theory are built, respectively. The former focuses on the instant and single-step reward, while the latter aims at the accumulative and multistep return. After that, the Kuhn–Munkres algorithm is set as the baseline method to solve the first model to achieve optimal multiaction allocation instructions for SAEVs, and the combination of deep Q-learning algorithm and Kuhn–Munkres algorithm is designed to solve the second model to realize the global optimization. Finally, a toy example, a macrosimulation of 1 month, and a microsimulation of 6 hours based on actual historical operation data are conducted. Results show that (1) the Kuhn–Munkres algorithm ensures the computational effectiveness in the large-scale real-time application of the AMoD system; (2) the second optimization model considering long-term return can decrease average user waiting time and achieve a 2.78% increase in total revenue compared with the first model; (3) and integrating combinatorial optimization theory with reinforcement learning theory is a perfect package for solving the multiaction dynamic dispatching problem of SAEVs.

Conceptual design of smart multi-farm produce dehydrator using a low-cost programmable logic controller and raspberry pi

Background: Acceptable food processing techniques require the removal of water contents from the crop or food sample without destroying the nutritional qualities of the food sample. This poses a strict requirement on the dehydrator or oven that will be used in the dehydrating techniques to have the ability to control both temperature and humidity of its drying chamber. Methods: This work centres on how an autonomous multi-farm produce dehydrator that can also serve as an oven can be designed with a raspberry pi and a low-cost programmable logic controller (PLC). The dehydrator gives the users the flexibility to control both the drying chamber’s temperature and humidity from its web interface via a mobile device or the dehydrator’s HMI. Heat energy from the Liquid Petroleum Gas (LPG) is used so that the dehydrator can be readily available for commercial or industrial use. The small electricity required to power the electronics devices is obtained from the hybrid power solution with an electric energy source from either the mains electricity supply or solar.. The design was tested by creating an operation profile from the proposed web application for the dehydrator. The operation trend was analysed from the web application’s Trendlines page. Results: The report showed that both the temperature and humidity of the dehydrator could be controlled, and access to historical operation data will give insight to the user on how to create a better operation profile. Conclusion: The setup described in this work, when implemented was able to produce a dehydrator/oven whose temperature and humidity can be perfectly controlled and its generated heat is evenly distributed in its drying chamber to ensure efficient and effective drying techniques use in crop preservation and food processing.

Research on Operation Optimization of Central Air Conditioning Cold Source System Based on PSO-SA Algorithm

This paper takes a data center air-conditioning cold source system as the research object. According to the historical operating data of the cold source system in the transition season, a cold source model is built on the EBSILON platform. The total energy consumption of the cold source system is the research goal. This paper establishes an overall optimization strategy based on PSO-SA. A simulation experiment was conducted on a typical day in the transition season, and the results showed that the optimization strategy can achieve 21.68% energy saving based on the original operation mode when the wet bulb temperature in the transition season is low.

An energy‐efficiency evaluation method for high‐sulfur natural gas purification system using artificial neural networks and particle swarm optimization

Natural gas purification, especially with high sulfur content, is an energy-intensive chemical production process, for which there are considerable differences in the energy consumption patterns of different purification plants. Therefore, these purification plants are required to establish a universal evaluation standard for energy consumption performance. This article proposed a novel approach to evaluate the energy efficiency of the natural gas purification process from the systems engineering perspective. An evaluation system is established for the hierarchical indicators of energy consumption using this technique providing the detailed definition of evaluation indicators for process, unit, and device. At the same time, a technical route is proposed for intelligent algorithm optimization and artificial neural network modeling based on historical operation data of the plant to discover the energy consumption benchmarks under various raw gas flow rates. Using this proposed method, the energy consumption efficiency can be evaluated while analyzing the energy-savings potential of these natural gas purification plants with various process types or raw gas characteristics. Furthermore, the model based on historical operating data can objectively and truly reflect the plant's energy consumption features; therefore, the plant's energy consumption can be decreased to benchmark by adjusting the corresponding operation parameters. Ultimately, the computational process of the energy consumption benchmark is described thoroughly for a high-sulfur natural gas purification plant.

Scheduling Thermostatically Controlled Loads to Provide Regulation Capacity Based on a Learning-Based Optimal Power Flow Model

Thermostatically controlled load (TCL, such as heating, ventilation, and air conditioning system) is a desirable demand-side flexibility source in distribution networks. It can participate in regulation services and mitigate power imbalances from fluctuating distributed renewable generation. To effectively utilize the load flexibility from spatially and temporally distributed TCLs in a distribution network, it is necessary to consider power flow constraints to avoid possible voltage or current violations. Published works usually adopt optimal power flow models (OPF) to describe these constraints. However, these models require accurate topology of the distribution network that is often unobservable in practice. To bypass this challenge, this paper proposes a novel learning-based OPF to optimize TCLs for regulation services. This method trains three regression multi-layer perceptrons (MLPs) based on the distribution network's historical operation data to replicate its power flow constraints. The trained MLPs are further equivalently reformulated into linear constraints with binary variables so that the optimization problem becomes a mixed-integer linear program that can be effectively solved. Numerical experiments based on the IEEE 123-bus system validate that the proposed method can achieve better TCL power scheduling performance with guaranteed feasibility and optimality than other state-of-art models.

Study on Capacity Estimation Methods of Second-Life Application Batteries

For the capacity estimation problem of cells in series-retired battery modules, this paper proposed three different methods from the perspective of data-driven, battery curve matching and recession characteristics for different applications. Firstly, based on the premise that the battery history data are available, the features of the IC curve are selected as input for the linear regression models. To avoid multicollinearity among features, we apply a filter-based feature selection method to eliminate redundant features. The results show that the average errors with Multiple Linear Regression are within 1.5%. Secondly, for the situation with a lack of historical operating data, the battery-curve-matching-based method is proposed based on the Dynamic Time Warping algorithm. This method could achieve the curve matching between the reference cell and target cell, and then the curve contraction coefficients can be obtained. The result shows that the method’s average error is 2.34%. Thirdly, whereas the tougher situation is that only part of the battery curve is available, we present a substitute method based on the battery degradation mechanism. This method can estimate most of the battery plant capacity through the partial battery curve. The result shows that the method’s average error is within 2%. Lastly, we contrast the applicability and limitations of every method based on the retired battery test data after deep cycling aging.

Analytic hierarchy process-based fuzzy post mining method for operation anomaly detection of building energy systems

Association rule mining has shown outstanding capacity in extracting operation patterns from numerous building operational data. However, only a very small portion of them is valuable for energy efficiency enhancement. Advanced post mining methods are necessary for automatically deleting most of worthless association rules. Therefore, this study proposes an analytic hierarchy process-based fuzzy post mining method. Three criteria and six corresponding sub-criteria are developed to evaluate the value of each association rule in energy efficiency enhancement. They offer new levels to assess the value of association rules. The fuzzy set theory is introduced to grade each sub-criterion of an association rule. It considers the uncertainties from the imprecise judgments, which can improve the robustness of rule assessing. Analytic hierarchy process is adopted to determine the weight of each criterion/sub-criterion for getting the weighted overall score of an association rule. It provides a solution to assessing the value of association rules from multiple aspects, which can improve the performance of post mining. The proposed method is evaluated using 117,636 association rules extracted from the one-year historical operational data of an actual chiller plant. Four common indexes (support, confidence, lift and distance correlation) are selected as a traditional method for comparison with the proposed method. The two methods can both filter out approximately 96.00% of worthless association rules. As for valuable association rules, the traditional method only extracts 17.28% of them, while this proportion is 93.51% for the proposed method. It proves that the proposed method has excellent performance of valuable association rule extraction.

Conceptual design of smart multi-farm produce dehydrator using a low-cost programmable logic controller and raspberry pi

Background: Acceptable food processing techniques require the removal of water contents from the crop or food sample without destroying the nutritional qualities of the food sample. This poses a strict requirement on the dehydrator or oven that will be used in the dehydrating techniques to have the ability to control both temperature and humidity of its drying chamber. Methods: This work centres on how an autonomous multi-farm produce dehydrator that can also serve as an oven can be designed with a raspberry pi and a low-cost programmable logic controller (PLC). The dehydrator gives the users the flexibility to control both the drying chamber's temperature and humidity from its web interface via a mobile device or the dehydrator's HMI. Heat energy from the Liquid Petroleum Gas (LPG) is used so that the dehydrator can be readily available for commercial or industrial use. The small electricity required to power the electronics devices is obtained from the hybrid power solution with an electric energy source from either the mains electricity supply or solar.. The design was tested by creating an operation profile from the proposed web application for the dehydrator. The operation trend was analysed from the web application's Trendlines page. Results: The report showed that both the temperature and humidity of the dehydrator could be controlled, and access to historical operation data will give insight to the user on how to create a better operation profile. Conclusion: The setup described in this work, when implemented was able to produce a dehydrator/oven whose temperature and humidity can be perfectly controlled and its generated heat is evenly distributed in its drying chamber to ensure efficient and effective drying techniques use in crop preservation and food processing.

A Many-Objective Optimization for an Eco-Efficient Flue Gas Desulfurization Process Using a Surrogate-Assisted Evolutionary Algorithm

The flue gas desulfurization process in coal-fired power plants is energy and resource-intensive but the eco-efficiency of this process has scarcely been considered. Given the fluctuating unit load and complex desulfurization mechanism, optimizing the desulfurization system based on the traditional mechanistic model poses a great challenge. In this regard, the present study optimized the eco-efficiency from the perspective of operating data analysis. We formulated the issue of eco-efficiency improvement into a many-objective optimization problem. Considering the complexity between the system inputs and outputs and to further reduce the computational cost, we constructed a Kriging model and made a comparison between this model and the response surface methodology based on two accuracy metrics. This surrogate model was then incorporated into the NSGA-III algorithm to obtain the Pareto-optimal front. As this Pareto-optimal front provides multiple alternative operating options, we applied the TOPSIS to select the most appropriate alternative set of operating parameters. This approach was validated using the historical operation data from the desulfurization system at a coal-fired power plant in China with a 600 MW unit. The results indicated that the optimization would cause an improvement in the efficiency of desulfurization and energy efficiency but a slight increase in the consumption of limestone slurry. This study attempted to provide an effective operating strategy to enhance the eco-efficiency performance of desulfurization systems.

Evaluation of the operation data for improving the prediction accuracy of heating parameters in heating substation

For the heating system with thermal inertia, accurate prediction of heating parameters is the premise of achieving on-demand heating. The existing prediction models do not evaluate the historical operation data before model training, which may lead to the establishment of non-on-demand models and affect their application in actual project. In this paper, firstly, the data evaluation method and application process were proposed based on heating professional mechanism and actual operation data. Secondly, the proposed method was used to evaluate the historical data of a heating substation, and the relationship between outdoor temperature and heating parameters (daily secondary supply temperature and daily heating consumption) for different indoor temperature intervals were obtained. Finally, the prediction models were training by historical data with and without evaluation method, and compared them from evaluation criteria and professional mechanism. The results showed that the accuracy of prediction model established by historical data with evaluation method was greatly improved, and can be used to guide the energy-saving operation of heating substation. In addition, it was also obtained that the prediction model established by big data can be used for prediction guidance at the middle heating period, and linear regression method was suitable for the end of heating period.

Modeling and optimization of the NOX generation characteristics of the coal-fired boiler based on interpretable machine learning algorithm

ABSTRACT The present work focused on modeling the nitrogen oxides (NOX) generation characteristics based on the interpretable machine learning algorithm for an in-service coal-fired power plant. Computational Fluid Dynamics is available to obtain the NOX generation data, which coupled with the historical operation data collected from Distributed Control System were used to improve the model’s prediction ability. The results showed that the depth and integrity of the dataset could be improved by adding simulation data. Compared with the Artificial Neural Network (ANN) and Support Vector Regression (SVR), the Gradient Boost Regression Tree (GBRT) model had higher accuracy than that of ANN and SVR model, and the GBRT model with more vital nonlinear transformation expression and time sequence is more suitable for the dataset, where the mean absolute error and coefficient of determination of the GBRT model were 3.85 and 0.98, respectively. Moreover, the Shapley additive interpretation analysis approach was presented for the GBRT model of NOX generation prediction, which is helpful to the field operators to realize the efficient and low pollution operation of boiler equipment.

Exploratory data analysis for airline disruption management

Reliable platforms for data collation during airline schedule operations have significantly increased the quality and quantity of available information for effectively managing airline schedule disruptions. To that effect, this paper applies macroscopic and microscopic techniques by way of basic statistics and machine learning, respectively, to analyze historical scheduling and operations data from a major airline in the United States. Macroscopic results reveal that majority of irregular operations in airline schedule that occurred over a one-year period stemmed from disruptions due to flight delays, while microscopic results validate different modeling assumptions about key drivers for airline disruption management like turnaround as a Gaussian process.