Search

As complex industries move towards small batches and customization, the uncertainty of the operation time of intermittent electrical devices increases, leading to an increasing fluctuation range of the complex industrial electrical load. To ensure the regular production process, the fossil power plant increases the installed capacity of generators, which can sharply raise carbon emissions. Renewable energy generation has been introduced to reduce carbon emissions and achieve power generation sustainability. However, the instability of renewable energy generation increases the fluctuation range of transmission voltage, leading to highly unsafe electricity transmission. Energy Storage Systems (ESSs) solves the instability problem of renewable energy generation. Thus, this study proposes a two-stage energy scheduling optimization model for complex industrial processes. The first stage proposes a scheduling optimization model for intermittent electrical devices with high electricity consumption. The second stage proposes a scheduling optimization model for the ESS to optimize the transmission capacity proportion of photovoltaic (PV) power plants, ESS, and fossil power plants. The results show that the proposed two-stage scheduling optimization model for the complex industrial process can reduce electricity cost by 7.1%–9.1%, and carbon emissions by 384 tons of standard coal in a year. [ABSTRACT FROM AUTHOR]

Hydrogen energy is widely regarded as one of the most promising clean energy sources for carbon emissions reduction due to its high-grade energy and complete clean combustion. Since the mechanism of the production process is difficult to elucidate and efficient production cannot be maintained at all times, it has the disadvantages of instability and low efficiency of production processes. The forecasting results can help the biomass based hydrogen production process to adjust the material input in time, thus ensuring a stable and efficient production. Therefore, to solve those problems, the dynamic hydrogen production yield forecasting model based on the Discrete Grey Method (DGM) and the Gradient Boosting Regression Tree (GBRT) has been proposed. The results show that the forecasting results of the GBRT based model have a strong correlation with the input data, while the DGM based model can eliminate some unreasonable forecasting results. Thus, the proposed model can get good forecasting results in different scenarios since its MAE is 0.2. To verify the proposed model, five widely used forecasting models are used as the contrasting models. The forecasting results show that it has the highest precision and has no uncertainty results. [Display omitted] • Dynamic forecasting model is proposed for biomass-based hydrogen production yield. • The proposed model is developed based on GBRT-DGM (1, n) algorithm. • The model shows high accuracy and has no uncertain results. • The accuracy of the proposed method is compared with other models. [ABSTRACT FROM AUTHOR]

• Fuel composition forecasting model is proposed for waste tires pyrolysis process. • The proposed model is developed based on the GBRT algorithm. • The proposed model exhibits high accuracy and strong generalization ability. • Over 60% of the forecasting results have REP values lower than 30%. Waste tire pyrolysis oil holds significant potential as an energy source and chemical feedstock, playing a crucial role in enhancing resource efficiency and promoting environmental sustainability. This study aims to develop a reliable forecasting model for determining the composition proportions of waste tire pyrolysis oil and assessing its performance. This study employed the gradient boosting decision tree (GBDT) method to develop the model that accurately forecasts the composition proportions of aromatic, aliphatic, and other compounds present in waste tire pyrolysis oil. Importance in XGboost and Cramer's V analysis in correlation analysis were used to select the input variables for the forecasting mode. Additionally, this study normalized the percentages of the three components to ensure consistency. To evaluate the performance of the proposed models, we compared them with 13 models from the Decision Tree series, BPNN series, SVM series, and HDMR series, thereby verifying the accuracy of our models. Furthermore, this study conducted random sampling to examine the stability and generalization ability of our proposed models. The experimental results demonstrate that the forecasting model exhibits excellent performance in estimating the proportions of aromatic compounds, aliphatic compounds, and other compounds. Over 60% of the samples yielded relative error percentage (REP) values below 30%. This indicates that this proposed model is capable of accurately forecasting the composition proportions of waste tire pyrolysis oil. The proposed model holds the potential to facilitate dynamic optimization of the waste tire resource reuse process and contribute to the sustainable development of waste tires. [ABSTRACT FROM AUTHOR]

Gasification is one of the recommended processes for poultry litter valorization, and its success is largely dependent on process input parameters for syngas production. The quality of syngas, characterized by a higher heating value (HHV) and lower heating value (LHV), is significantly influenced by hydrogen. In this research, integration of Aspen Plus simulation and Convolutional Neural Network (CNN) have been done to estimate the hydrogen content in syngas. The gasification process has been optimized using the response surface method, and the results have been supported by the particle swarm optimization (PSO) technique. The statistical analysis of the response surface model revealed that the optimal process parameters are around 408 °C, 2.0 (biomass to air ratio) BMR, and 2.0 bars. Interestingly, PSO led to nearly identical optimum values (400 °C, 2.0 BMR, and 2.0 bars), resulting in high-quality syngas. Furthermore, CNN exhibited a good predicting performance with a coefficient of determination (R2) exceeding 0.96, coupled with mean square error (MSE) and mean absolute error (MAE) of 0.01 and 0.05, respectively. This solidifies the integration of Aspen Plus simulations and CNN as an accurate surrogate model for predicting hydrogen levels during poultry litter gasification, enabling effective process optimization. Therefore, the proposed model serves as a reliable tool for predicting and optimizing the syngas produced during the gasification process of poultry litter, with potential applications in enhancing energy production and waste management practices. • Hydrogen prediction in poultry litter gasification process through CNN. • Optimum parameters around 408 °C, 2.0 biomass to air ratio (BMR), and 2.0 bars. • BMR has a most significant effect on the amount of H 2 , HHV, and LHV of syngas. • CNN predicting performance with coefficient of determination (R2) exceeding 0.96. [ABSTRACT FROM AUTHOR]

Quality syngas production with higher moles of hydrogen and methane are the primary objective of gasification process which is dependent upon the process parameters and composition of biomass. However, it is always a costly and time-consuming task to get the optimum biomass composition and process parameters for quality syngas production. In this research, artificial intelligence (AI) algorithms have been applied for high quality syngas prediction with better moles fractions of hydrogen and methane using hydrothermal gasification (HTG). Comparative analysis of Convolutional Neural Network (CNN), Artificial Neural Network (ANN), Gradient Boost Regressor (GBR), Extreme Boost Regressor (XGB), and Random Forest Regressor (RFR) based algorithms have been done to select an optimal one. Ultimate analysis of biomass and process input parameters inlcuding temperature, pressure, percentage solid content of biomass, and resident time have been used as an input parameter for prediction models. Final comparative results of these AI models conclude that XGB has a better prediction result as compared to other with coefficient of determinant (R2) and mean square errors ranges from 0.85 to 0.95 and 0.008–0.01, respectively. Furthermore, process temperature and the resident time are the most contributing factors in mole fractions of hydrogen and methane. Higher hydrogen and oxygen contents in the biomass, significantly contributes to the production of quality syngas. [Display omitted] [ABSTRACT FROM AUTHOR]

The industrial process consumes substantial energy and emits large amounts of carbon dioxide. With the help of accurate energy consumption and carbon emissions forecasting, industrial enterprises would find it easier to achieve cleaner production, optimize the energy structure, and reduce production costs and carbon emissions by gaining deeper control over the production situation. Due to the oversaturation of machine learning modeling methods, forecasting models face difficulties in improving accuracy and extracting data features. The deep learning method is introduced to address these issues. However, the inaccurate measurement of key parameters and anomalies in data transmission strengthens the uncertainty of industrial big data. This makes the machine learning-based forecasting models show strong uncertainty and poor generalizability. Thus, it is significantly difficult to improve the accuracy of the current industrial energy consumption and carbon emissions forecasting model in different industrial scenarios. This work summarizes the research on energy consumption and carbon emissions forecasting for industrial processes in recent years. Combined with the actual problems of current industrial processes, this work summarizes three kinds of forecasting models: (i) the multi-step forecasting model based on the combination of deep learning and model uncertainty, (ii) the combined mechanism and data-driven method-based forecasting model, and (iii) the intelligent algorithms-based forecasting model. These models could become a new path for establishing generic industrial process energy consumption and carbon emissions forecasting models in the future. [Display omitted] • Industrial energy consumption and carbon emissions forecasting is overviewed timely. • Complementary frameworks of developing industrial forecasting models is proposed. • Unique issues of industrial forecasting problem are analyzed comprehensively. • Three kind of forecasting models are summarized as new paths for industrial sector. [ABSTRACT FROM AUTHOR]

Abstract Process industry consumes tremendous amounts of electricity for production. Electric load forecasting could be conducive to managing the electricity consumption, determining the optimal production scheduling, and planning the maintenance schedule, which could improve the energy efficiency and reduce the production cost. This paper proposed a short term electric load forecasting model based on the hybrid GA-PSO-BPNN algorithm. The GA-PSO algorithm is used in a short-term electric load forecasting model to optimize the parameters of BPNN. The forecasting model avoids the shortcoming that the prediction result is easy to fall into local optimum. The papermaking process, as one of the most representative process industries, is selected as the study case. The real-time production data from two different papermaking enterprises is collected to verify the proposed model. Besides the proposed GA-PSO-BPNN model, the GA-BPNN and PSO-BPNN based electric load forecasting models are also studied as the contrasting cases. The verification results reveal that the GA-PSO-BPNN model is superior to the other two hybrid forecasting models for future application in the papermaking process since its MAPE is only 0.77%. Highlights • A short term electric load forecasting model is proposed for papermaking process. • The proposed model is structured based on hybrid GA-PSO-BPNN algorithm. • The model is verified by industrial real-time data. • The model shows high accuracy with 0.77% of the MAPE. • Electricity purchasing cost can be saved by the forecasting results. [ABSTRACT FROM AUTHOR]

Forecasting accuracy electricity load can help industrial enterprises optimise production scheduling based on peak and off-peak electricity prices. The electricity load forecasting results can be provided to an electricity system to improve electricity generation efficiency and minimize energy consumption by developing electricity generation plans in advance and by avoiding over or under the generation of electricity. However, because of the different informatization levels in different industries, few reliable intelligent electricity management systems are applied on the power supply side. Based on industrial big data and machine learning algorithms, this study proposes an integrated model to forecast short-term electricity load. The hybrid model based on the hybrid mode decomposition algorithms is proposed to decompose the total electricity load signal. To improve the generalisation ability of the forecasting model, a dynamic forecasting model is proposed based on the improved hybrid intelligent algorithm to forecast the short-term electricity load. The results show that the accuracy of the proposed dynamic integrated electricity load forecasting model is as high as 99%. The integrated framework could forecast abnormal electricity consumption in time and provide reliable evidence for production process scheduling. • Forecasting models are too difficult to embedded in industrial process systems. • The novel integrated framework has been proposed for industrial processes. • The proposed integrated model has been implemented in papermaking enterprise. • The accuracy of the proposed dynamic load forecasting model is greater than 99%. • The proposed energy management system framework is conducive to green production. [ABSTRACT FROM AUTHOR]

Forecasting accuracy electricity load can help industrial enterprises optimise production scheduling based on peak and off-peak electricity prices. The electricity load forecasting results can be provided to an electricity system to improve electricity generation efficiency and minimize energy consumption by developing electricity generation plans in advance and by avoiding over or under the generation of electricity. However, because of the different informatization levels in different industries, few reliable intelligent electricity management systems are applied on the power supply side. Based on industrial big data and machine learning algorithms, this study proposes an integrated model to forecast short-term electricity load. The hybrid model based on the hybrid mode decomposition algorithms is proposed to decompose the total electricity load signal. To improve the generalisation ability of the forecasting model, a dynamic forecasting model is proposed based on the improved hybrid intelligent algorithm to forecast the short-term electricity load. The results show that the accuracy of the proposed dynamic integrated electricity load forecasting model is as high as 99%. The integrated framework could forecast abnormal electricity consumption in time and provide reliable evidence for production process scheduling. • Forecasting models are too difficult to embedded in industrial process systems. • The novel integrated framework has been proposed for industrial processes. • The proposed integrated model has been implemented in papermaking enterprise. • The accuracy of the proposed dynamic load forecasting model is greater than 99%. • The proposed energy management system framework is conducive to green production. [ABSTRACT FROM AUTHOR]

Natural gas is regarded as a cleaner alternative to coal combustion-based power generation (CPG) for urban use. Because of the insufficient natural gas reserve in China, coal-based synthetic natural gas (SNG) has been under rapid development. However, coal-based SNG production process has problems of environmental pollution and emission transfer. This paper uses life cycle assessment to compare the CPG and SNG energy production and usage routes, in order to find a reasonable way to reduce the environmental pollution and production cost. Results show that the CPG route is superior to the SNG route in terms of the haze pollution emissions, greenhouse gases emissions, coal resource consumption and life cycle cost. However, the water consumption of the CPG route is much higher than that of the SNG route. The SNG route is more suitable to adopt in water-deficient areas. [ABSTRACT FROM AUTHOR]

[Display omitted] • Four integrated processes of poultry litter valorization are proposed. • Thermodynamic and techno-economic assessments are carried out. • The highest energy/exergy efficiency is accompanied by the highest H 2 yield. • The most exergy loss link occurs at gasification unit and Rankine cycle. • CO 2 separators in integrated processes show limited effect on energy-saving and cost-reduction. The utilization of poultry litter for converting poultry litter into energy or value-added products has great potential for energy saving and environmental protection. In this study, four integrated processes for treating poultry litter and obtaining high-value-added products have been studied: supercritical water gasification for hydrogen and electricity (SCWG-HE), supercritical water gasification for electricity (SCWG-E), steam gasification for electricity (SG-E) and steam gasification for hydrogen (SG-H). Thermodynamic and tech-economic assessments have been adopted to analyze the treatment alternatives comprehensively. The following findings have been obtained: (1) The energy/exergy efficiency of process has a positive correlation with the heat value of syngas; (2) The highest energy/exergy efficiency (57 % / 72 %) is accompanied by the highest H 2 yield (50.87 mol∙kg−1) under the operation conditions; (3) For each integrated process, the most exergy loss link occurs at the gasification unit and Rankine cycle; (4) CO 2 separators in integrated processes contribute little to energy-saving, accompanied with high investment (more than 27.5 % in SCWG-E, even until 74.2 % in SG-E). In conclusion, the findings of the study revealed the potential of multi-energy utilization for poultry litter in a farm and suggested that SG-H might be a better alternative with the highest efficiency and lowest equipment cost. [ABSTRACT FROM AUTHOR]

Abstract The paper drying process has the highest level of energy consumption in the pulp and paper production process. Analysis and optimization of the energy system during the paper drying process is critical for improving the energy efficiency of the entire paper mill. In the existing model for the paper drying process, the solution requires accurate boundary conditions such as the air temperature and humidity of the pocket area and the cylinder surface temperature, which are very difficult to obtain in the papermaking process. This can result in significant deviations between the model solution and the actual production process. This paper focuses on the single-tier dryer cylinder-based paper drying process that has been widely used with high-speed papermaking machines in recent years. A mathematical model is proposed based on real-time data. The verification via industrial production demonstrates that the proposed model is reliable for the paper drying process. Based on the simulation results, two optimization operations have been proposed. The energy consumption decreases from 1.51 t steam/t paper to 1.44 t steam/t paper, 4.6% of the steam and 1.26 × 106 RMB can be saved for a medium-scale paper mill with the annual production capacity of 105 t paper. Highlights • Mathematical model for the single-tier cylinder based paper drying process is proposed. • Both the steam-condensate system and the paper drying process are considered. • The simulation results are verified by the industrial data from a papermaking enterprise. [ABSTRACT FROM AUTHOR]