Search NASA⌕ Search

Engineering topics

Machalek, Derek

Publications and source records attributed to Machalek, Derek.

Dynamic energy system modeling using hybrid physics-based and machine learning encoder–decoder models

Three model configurations are presented for multi-step time series predictions of the heat absorbed by the water and steam in a thermal power plant. The models predict over horizons of 2, 4, and 6 steps into the future, where each step is a 5-minute increment. The evaluated models are a pure machine learning model, a novel hybrid machine learning and physics-based model, and the hybrid model with an incomplete dataset. The hybrid model deconstructs the machine learning into individual boiler heat absorption units: economizer, water wall, superheater, and reheater. Each configuration uses a gated recurrent unit (GRU) or a GRU-based encoder–decoder as the deep learning architecture. Mean squared error is used to evaluate the models compared to target values. The encoder–decoder architecture is over 11% more accurate than the GRU only models. The hybrid model with the incomplete dataset highlights the importance of the manipulated variables to the system. The hybrid model, compared to the pure machine learning model, is over 10% more accurate on average over 20 iterations of each model. Automatic differentiation is applied to the hybrid model to perform a local sensitivity analysis to identify the most impactful of the 72 manipulated variables on the heat absorbed in the boiler. The models and sensitivity analyses are used in a discussion about optimizing the thermal power plant.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A novel implicit hybrid machine learning model and its application for reinforcement learning

A novel methodology to develop implicit hybrid models is presented. PyTorch is used to integrate physics-based equations with machine learning models. Automatic differentiation of the hybrid model is leveraged to solve the implicit equations. Iterative solving enables gradient based updates to the machine learning model. The novel methodology is compared to an explicit hybrid approach on a continuously stirred tank reactor (CSTR). The novel method results in a lower modelling error. Both hybrid models effectively train with noisy data. To test the implicit hybrid model, it is employed as a reinforcement learning (RL) training model. The RL algorithm trained on the hybrid model outperforms real time optimization of the CSTR and performs nearly as well as RL trained directly on the CSTR and a traditional gradient based approach. Training RL directly on the CSTR requires over 60,000 system interactions compared to 6000 historical data points for hybrid model development.

42 ENGINEERING↗

State-by-State comparison of combined heat and power to photovoltaic installations at manufacturing facilities with heat and power loads

Manufacturing facilities with large electricity and steam loads commonly meet those loads with a grid and boiler (GB) system configuration. In this study, two alternatives, a natural gas turbine cycle driven combined heat and power (CHP) system configuration and a grid boiler system augmented with photovoltaics (GB-PV), are investigated sustainable manufacturing in reference to the GB system configuration. For this purpose, their discounted payback period (DPP), carbon dioxide (CO 2 ) and nitrogen oxides (NO x ) emission reductions, and primary fossil energy impacts are calculated. The major contribution of this study is that it directly compares the application of both CHP and PV technologies at an assumed manufacturing facility in all 50 states of the United States. This highlights the location-specific impacts of the facility. The examined manufacturing facility utility requirements are 5 MW of power and over 12,000 kg/h of 250 kPa and 400 K saturated steam. A DPP of less than 25 years, the technology lifetime, is found in 44 states for the CHP system configuration and 6 states for the GB-PV system configuration. GB-PV and CHP cost-effectively reduce CO 2 in 44 and 38 states, respectively. CHP is better for NO x reduction, whereas GB-PV is better for primary fossil energy reduction.

14 SOLAR ENERGY↗

Economic and environmental impacts of a non-traditional combined heat and power system for a discrete manufacturing facility

Combined heat and power (CHP) is an electricity generation strategy that benefits all sides with a vested interest in the nations’ energy future. The technology allows for the efficient production of electricity and heat, which in turn reduces the carbon footprint and energy costs of a facility with significant heat and electricity loads. This paper investigates, through a detailed dynamic simulation, how a highly non-traditional CHP facility can leverage those forces to economically and environmentally benefit. Four system configurations of a composites manufacturing facility, one existing and three proposed systems, including two CHP configurations and one combined cooling, heating, and power (CCHP) configuration are evaluated from both economic and environmental views. The three proposed configurations are based on a 600 kW microturbine as the primary mover. The dynamic model showed great potential to capture the dynamics of the system configurations including the dynamics of temperature, oven exhaust fraction, electrical efficiency, and overall efficiency of the system configurations. All 3 CHP systems have a payback period between 8.03 and 8.33 years. The proposed system configurations reduce up to 22.7% of the CO 2 emission compared to the existing facility, supplying the demands in a cleaner manner.

42 ENGINEERING↗

Automated electrical demand peak leveling in a manufacturing facility with short term energy storage for smart grid participation

Demand side management of energy is a vital function in the smart grid that allows for greater integration of renewable energy resources, and is facilitated with economic incentives in energy and demand pricing schedules. Manufacturing systems can take advantage of these incentives to reduce their energy costs through active energy management. This paper is a simulation analysis on the implementation of a novel algorithm that levelizes the maximum power load of an industrial bakery that operates under an on-peak demand price structure. The algorithm takes advantage of an untapped thermal energy storage resource in the facility, a chilled glycol buffer tank, to level the short intra-day power oscillations that the facility experiences. One of the key advantages of the algorithm is that it does not require precise demand forecasting or complex control algorithms, such as model predictive control. Even with substantial error in peak power estimates (5%), the algorithm is expected to result in at least a 2% peak reduction. Under ideal prediction, the algorithm reduces the on-peak facility power maximum by 7.3% of the possible 9.0% reduction the storage can provide. Further, the algorithm uses very few facility specific inputs, and can readily be adapted for any facility with short intra-day oscillatory power profiles and untapped storage capacity. The key insight of the paper is the employment of a novel algorithm to leverage untapped energy storage in manufacturing facilities to transform them into smart grid participants with no major capital investment.

24 POWER TRANSMISSION AND DISTRIBUTION↗