Search

Stage-built long-span bridges deform with temperature, affecting alignment to design needs. In this paper, a model for predicting temperature time series is proposed, which can predict temperatures in engineering practice and utilize the predicted results to adjust the elevation of stage construction. The model employs convolutional neural networks (CNNs) for initial feature extraction, followed by bidirectional long short-term memory (BiLSTM) layers to capture temporal dependencies. An attention mechanism is applied to the LSTM output, enhancing the model’s ability to focus on the most relevant parts of the sequence. The Crested Porcupine Optimizer (CPO) is used to fine-tune parameters like the number of LSTM units, dropout rate, and learning rate. The experiments on the measured temperature data of an under-construction cable-stayed bridge are conducted to validate our model. The results indicate that our model outperforms the other five models in comparison, with all the R2 values exceeding 0.97. The average of the mean absolute error (MAE) on the 30 measure points is 0.19095, and the average of the root mean square error (RMSE) is 0.28283. Furthermore, the model’s low sensitivity to data makes it adaptable and effective for predicting temperatures and adjusting the elevation in large-span bridge construction.

The warning of the potential faults occurring in the future in a sucker rod well can help technicians adjust production strategies in time. It is of great significance for safety during well production. In this paper, the key characteristic parameters of dynamometer cards were predicted by a temporal neural network to implement the warning of different working conditions which might result in failures. First, a one-dimensional damped-wave equation was used to eliminate the dynamic loads’ effect of surface dynamometer cards by converting them into down-hole dynamometer cards. Based on the down-hole dynamometer cards, the characteristic parameters were extracted, including the load change, the position of the valve opening and closing point, the dynamometer card area, and so on. The mapping relationship between the characteristic parameters and working conditions (classification model) was obtained by the Xgboost algorithm. Meanwhile, the noise in these parameters was reduced by wavelet transformation, and the rationality of the results was verified. Second, the Encoder–Decoder and multi-head attention structures were used to set up the time series prediction model. Then, the characteristic parameters were predicted in a sequence-to-sequence way by using historical characteristic parameters, date, and pumping parameters as input. At last, by inputting the predicted results into the classification model, a working conditions warning method was created. The results showed that noise reduction improved the prediction accuracy significantly. The prediction relative error of most characteristic parameters was less than 15% after noise reduction. In most working conditions, their F1 values were more than 85%. Most Recall values could be restored to over 90% of those calculated by real parameters, indicating few false negative cases. In general, the warning method proposed in this paper can predict faulty working conditions that may occur in the future in a timely manner.

Bluetooth Low Energy Mesh (BLE Mesh) enables Bluetooth flexibility and coverage by introducing Low-Power Nodes (LPNs) and enhanced networking protocol. It is also a commonly used communication method in sensor networks. In BLE Mesh, LPNs are periodically woken to exchange messages in a stop-and-wait way, where the tradeoff between energy and efficiency is a hard problem. Related works have reduced the energy consumption of LPNs mainly in the direction of changing the bearer layer, improving time synchronization and broadcast channel utilization. These algorithms improve communication efficiency; however, they cause energy loss, especially for the LPNs. In this paper, we propose a constrained flooding algorithm based on time series prediction and lightweight GBN (Go-Back-N). On the one hand, the wake-up cycle of the LPNs is determined by the time series prediction of the surrounding load. On the other, LPNs exchange messages through lightweight GBN, which improves the window and ACK mechanisms. Simulation results validate the effectiveness of the Time series Prediction and LlightWeight GBN (TP-LW) algorithm in energy consumption and throughput. Compared with the original algorithm of BLE Mesh, when fewer packets are transmitted, the throughput is increased by 214.71%, and the energy consumption is reduced by 65.14%.

Monitoring the condition of rotating machinery is critical in aerospace applications like aircraft engines and helicopter rotors. Faults in these components can lead to catastrophic outcomes, making early detection essential. This paper proposes a novel approach using vibration signals and time series prediction methods for fault detection in rotating aerospace machinery. By extracting relevant features from vibration signals and using prediction models, fault severity can be effectively quantified. Our experimental results show that the proposed method has potential in early fault detection and is applicable to various types of bearing faults and the different statuses of these faults under complex running conditions, achieving very good generalization ability.

Accurately estimating the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for maintaining the safe and stable operation of rechargeable battery management systems. However, this task is often challenging due to the complex temporal dynamics. Recently, attention-based networks, such as Transformers and Informer, have been the popular architecture in time series forecasting. Despite their effectiveness, these models with abundant parameters necessitate substantial training time to unravel temporal patterns. To tackle these challenges, we propose a straightforward MLP-Mixer-based architecture named “Intra–Inter Patch Mixer” (IIP-Mixer), which leverages the strengths of multilayer perceptron (MLP) models to capture both local and global temporal patterns in time series data. Specifically, it extracts information using an MLP and performs mixing operations along both intra-patch and inter-patch dimensions for battery RUL prediction. The proposed IIP-Mixer comprises parallel dual-head mixer layers: the intra-patch mixing MLP, capturing local temporal patterns in the short-term period, and the inter-patch mixing MLP, capturing global temporal patterns in the long-term period. Notably, to address the varying importance of features in RUL prediction, we introduce a weighted loss function in the MLP-Mixer-based architecture, marking the first time such an approach has been employed. Our experiments demonstrate that IIP-Mixer achieves competitive performance in battery RUL prediction, outperforming other popular time series frameworks, such as Informer and DLinear, with relative reductions in mean absolute error (MAE) of 24% and 10%, respectively.

This paper presents a First-Order Recurrent Neural Network activated by a wavelet function, in particular a Morlet wavelet, with a fixed set of parameters and capable of identifying multiple chaotic systems. By maintaining a fixed structure for the neural network and using the same activation function, the network can successfully identify the three state variables of several different chaotic systems, including the Chua, PWL-Rössler, Anishchenko–Astakhov, Álvarez-Curiel, Aizawa, and Rucklidge models. The performance of this approach was validated by numerical simulations in which the accuracy of the state estimation was evaluated using the Mean Square Error (MSE) and the coefficient of determination (r2), which indicates how well the neural network identifies the behavior of the individual oscillators. In contrast to the methods found in the literature, where a neural network is optimized to identify a single system and its application to another model requires recalibration of the neural algorithm parameters, the proposed model uses a fixed set of parameters to efficiently identify seven chaotic systems. These results build on previously published work by the authors and advance the development of robust and generic neural network structures for the identification of multiple chaotic oscillators.

This paper introduces BiLSTM-MLAM, a novel multi-scale time series prediction model. Initially, the approach utilizes bidirectional long short-term memory to capture information from both forward and backward directions in time series data. Subsequently, a multi-scale patch segmentation module generates various long sequences composed of equal-length segments, enabling the model to capture data patterns across multiple time scales by adjusting segment lengths. Finally, the local attention mechanism enhances feature extraction by accurately identifying and weighting important time segments, thereby strengthening the model’s understanding of the local features of the time series, followed by feature fusion. The model demonstrates outstanding performance in time series prediction tasks by effectively capturing sequence information across various time scales. Experimental validation illustrates the superior performance of BiLSTM-MLAM compared to six baseline methods across multiple datasets. When predicting the remaining life of aircraft engines, BiLSTM-MLAM outperforms the best baseline model by 6.66% in RMSE and 11.50% in MAE. In the LTE dataset, it achieves RMSE improvements of 12.77% and MAE enhancements of 3.06%, while in the load dataset, it demonstrates RMSE enhancements of 17.96% and MAE improvements of 30.39%. Additionally, ablation experiments confirm the positive impact of each module on prediction accuracy. Through segment length parameter tuning experiments, combining different segment lengths has resulted in lower prediction errors, affirming the effectiveness of the multi-scale fusion strategy in enhancing prediction accuracy by integrating information from multiple time scales.

‎Artificial neural networks with amazing properties‎, ‎such as universal approximation‎, ‎have been utilized to approximate the nonlinear processes in many fields of applied sciences‎. ‎This work proposes the rough-neural networks (R-NNs) for the one-step ahead prediction of chaotic time series‎. ‎We adjust the parameters of R-NNs using a continuous-time Lyapunov-based training algorithm‎, ‎and prove its stability using the continuous form of Lyapunov stability theory‎. ‎Then‎, ‎we utilize the R-NNs to predict the well-known Mackey-Glass time series‎, ‎and Henon map‎, ‎and compare the simulation results with some well-known neural models‎.

Long Short-Term Memory (LSTM) Neural Network has great potential to predict sequential data. Time series prediction is one of the most popular experimental subjects of LSTM. To this end, various LSTM algorithms have been developed to predict time series data. However, there are a few works considering the hyperparameter optimization of LSTM along with parallelization approaches. To address this problem, a parallelized classic LSTM is proposed to predict time series. In the preprocessing phase, it first replaces missing values with zero and then normalizes the time series matrix. The transposed matrix is divided into training and testing parts. Consequently, a core-based parallelism is established, thereby utilizing forking to split prediction into multiple processes. Derivative-free optimization techniques are also analyzed to find out what sort of hyperparameter optimization technique is much more feasible for a parallelized LSTM. Further, a state-of-the-art comparison is included in the study. Experimental results show that training loss is optimal when using Nelder–Mead. Employing effort-intensive optimization methods such as genetic algorithms results in a remarkable CPU time reduction in parallelized designs according to the results. Last, the proposed algorithm outperformed the comparison methods with respect to the prediction errors.

We present an algorithm for extracting basis functions from the chaotic Lorenz system along with timing and bit-sequence statistics. Previous work focused on modifying Lorenz waveforms and extracting the basis function of a single state variable. Importantly, these efforts initiated the development of solvable chaotic systems with simple matched filters, which are suitable for many spread spectrum applications. However, few solvable chaotic systems are known, and they are highly dependent upon an engineered basis function. Non-solvable, Lorenz signals are often used to test time-series prediction schemes and are also central to efforts to maximize spectral efficiency by joining radar and communication waveforms. Here, we provide extracted basis functions for all three Lorenz state variables, their timing statistics, and their bit-sequence statistics. Further, we outline a detailed algorithm suitable for the extraction of basis functions from many chaotic systems such as the Lorenz system. These results promote the search for engineered basis functions in solvable chaotic systems, provide tools for joining radar and communication waveforms, and give an algorithmic process for modifying chaotic Lorenz waveforms to quantify the performance of chaotic time-series forecasting methods. The results presented here provide engineered test signals compatible with quantitative analysis of predicted amplitudes and regular timing.

Concerns that impair human societies frequently include a heavy dependence on petroleum and coal and emissions of greenhouse gases. Thus, adopting renewable energy sources, such as wind power, has become a practical solution to this problem. Therefore, to carry out the research on wind velocity energy, a time-series structure is necessary. This study uses the Markov chain Monte Carlo approach and the Seasonal Autoregressive Integrated Moving Average (SARIMA) model to estimate short-term and long-term sustained winds. The significance of building a wind energy system is initially discussed, after which a wind velocity time-series framework based on a SARIMA is presented, followed by a short-term and Long-term wind speed projection. Furthermore, a methodology utilizing the Markov chain Monte Carlo method (MCMC) is suggested to establish a wind energy time-series analysis. This framework draws a Markov chain for time-series data on wind energy to maintain stochasticity and realize the probability transition matrix. Gibbs sampling is employed as well. The model's forecasting abilities were tested using the original database and various efficiency assessment measures, including Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) with efficiency of 13.09 and 1.03. In this study, a framework with the highest KGE and WI as well as the lowest RMSE and MAE was chosen. The findings demonstrate that the approach used in the operation provides outstanding predictability.

This research paper proposes a novel method, Exponential Moving Average Long Short-Term Memory (EMA LSTM), for multi-step vector output prediction of time series data using deep learning. The method combines the LSTM with the exponential moving average (EMA) technique to reduce noise in the data and improve the accuracy of prediction. The research compares the performance of EMA LSTM to other commonly used deep learning models, including LSTM, GRU, RNN, and CNN, and evaluates the results using statistical tests. The dataset used in this study contains daily stock market prices for several years, with inputs of 60, 90, and 120 previous days, and predictions for the next 20 and 30 days. The results show that the EMA LSTM method outperforms other models in terms of accuracy, with lower RMSE and MAPE values. This study has important implications for real-world applications, such as stock market forecasting and climate prediction, and highlights the importance of careful preprocessing of the data to improve the performance of deep learning models.

Given a large number of applications and complex processing procedures, how to efficiently shift and schedule tax officers to provide good services to taxpayers is now receiving more attention from tax authorities. The availability of historical application data makes it possible for tax managers to shift and schedule staff with data support, but it is unclear how to properly leverage the historical data. To investigate the problem, this study adopts a user-centered design approach. We first collect user requirements by conducting interviews with tax managers and characterize their requirements of shifting and scheduling into time series prediction and resource scheduling problems. Then, we propose Tax-Scheduler, an interactive visualization system with a time-series prediction algorithm and genetic algorithm to support staff shifting and scheduling in the tax scenarios. To evaluate the effectiveness of the system and understand how non-technical tax managers react to the system with advanced algorithms and visualizations, we conduct user interviews with tax managers and distill several implications for future system design.

The time series is generally a set of random variables that are observed and collected at a certain frequency in the course of something??s development. The task of time series forecasting is to extract the core patterns from a large amount of data and to make accurate estimates of future data based on known factors. Due to the access of a large number of IoT data collection devices, the explosive growth of multidimensional data and the increasingly demanding requirements for prediction accuracy, it is difficult for classical parametric models and traditional machine learning algorithms to meet high efficiency and high accuracy requirements of prediction tasks. In recent years, deep learning algorithms represented by convolutional neural networks, recurrent neural networks and Trans-former models have achieved fruitful results in time series forecasting tasks. To further promote the development of time series prediction technology, common characteristics of time series data, evaluation indexes of datasets and models are reviewed, and the characteristics, advantages and limitations of each prediction algorithm are experimentally compared and analyzed with time and algorithm architecture as the main research line. Several time series prediction methods based on Transformer model are highlighted and compared. Finally, according to the problems and challenges of deep learning applied to time series prediction tasks, this paper provides an outlook on the future research trends in this direction.

Forecasting container throughput is critical for improved port planning, operations, and investment strategies. Reliability of forecasting methods need to be ensured before utilizing their outcomes in decision making. This study compares forecasting performances of various time series methods, namely autoregressive integrated moving average (ARIMA), seasonal ARIMA (SARIMA), Holt-Winter's Exponential Smoothing (HWES), and the Prophet model. Since forecast combinations can improve performance, simple and weighted combinations of ARIMA, SARIMA and HWES have been explored, too. Monthly container throughput data of port of Shanghai, Busan, and Nagoya are used. The Prophet model outperforms others in the in-sample forecasting, while combined models outperform others in the out-sample forecasting. Due to the observed differences between the in-sample and out-sample forecast accuracy measures, this study proposes a forecast performance metric consistency check approach for informed real-world applications of forecasting models in port management decision-making.

Artificial Neural Network (ANN) is an effective machine learning technique for addressing regression tasks. Nonetheless, the performance of ANN is highly dependent on the values of its parameters, specifically the weight and bias. To improve its predictive generalization, it is crucial to optimize these parameters. In this study, the Barnacles Mating Optimizer (BMO) is employed as an optimization tool to automatically optimize these parameters. As a relatively new optimization algorithm, it has been shown to be effective in addressing various optimization problems. The proposed hybrid predictive model of BMO-ANN is tested on time series data of stock price using six selected inputs to predict the next day’ closing prices. Evaluated based on Mean Square Error (MSE) and Root Mean Square Error (RMSPE), the proposed BMO-ANN exhibits significant superiority over the other identified hybrid algorithms. Additionally, the difference in means between BMO-ANN and other identified hybrid algorithms was found to be statistically significant, with a significance level of 0.05%.

The development of predictive models for infectious diseases, specifically COVID-19, is an important step in early control efforts to reduce the mortality rate. However, traditional time series prediction models used to analyze the disease spread trends often encounter challenges related to accuracy, necessitating the need to develop prediction models with enhanced accuracy. Therefore, this research aimed to develop a prediction model based on the Long Short-Term Memory (LSTM) networks to better predict the number of confirmed COVID-19 cases. The proposed optimized LSTM (popLSTM) model was compared with Basic LSTM and improved MinMaxScaler developed earlier using COVID-19 dataset taken from previous research. The dataset was collected from four countries with a high daily increase in confirmed cases, including Hong Kong, South Korea, Italy, and Indonesia. The results showed significantly improved accuracy in the optimized model compared to the previous research methods. The contributions of popLSTM included 1) Incorporating the output results on the output gate to effectively filter more detailed information compared to the previous model, and 2) Reducing the error value by considering the hidden state on the output gate to improve accuracy. popLSTM in this experiment exhibited a significant 4% increase in accuracy.

With the deep integration of the global economy and the continuous individuality of technology, the complexity of enterprise operation and management is increasing, which makes the traditional accounting and accounting methods difficult to meet the needs of modern enterprises. This paper proposes an enterprise accounting accounting method applying information computing technology, which applies association rules to generate frequent item sets of data for the accounting data under the financial sharing mode and obtains the optimal rules through pruning. Based on the time series prediction of the enterprise’s financial data, changes are made. Taking the actual enterprise case study, the association rules involved in accounting are more accurate, the calculation results are basically the same as the actual value, and the final cost accounting value is only nearly 2 million yuan different from the actual value, the accounting error is only 0.02%. Furthermore, the association rule algorithm has a significant impact on improving the efficiency of accounting work. The service time of counter personnel can be reduced by 30% after Bank P applies the management rules to accounting management. The average execution time of the initial ticket examination operation has been accelerated from 10.53 seconds to 5.42 seconds. The association rule algorithm can effectively improve the precision of enterprise accounting and the efficiency of accounting personnel, while also identifying existing problems in the current management system.

Electroencephalography (EEG) serves as a diagnostic technique for measuring brain waves and brain activity. Despite its precision in capturing brain electrical activity, certain factors like environmental influences during the test can affect the objectivity and accuracy of EEG interpretations. Challenges associated with interpretation, even with advanced techniques to minimize artifact influences, can significantly impact the accurate interpretation of EEG findings. To address this issue, artificial intelligence (AI) has been utilized in this study to analyze anomalies in EEG signals for epilepsy detection. Recurrent neural networks (RNNs) are AI techniques specifically designed to handle sequential data, making them well-suited for precise time-series tasks. While AI methods, including RNNs and artificial neural networks (ANNs), hold great promise, their effectiveness heavily relies on the initial values assigned to hyperparameters, which are crucial for their performance for concrete assignment. To tune RNN performance, the selection of hyperparameters is approached as a typical optimization problem, and metaheuristic algorithms are employed to further enhance the process. The modified hybrid sine cosine algorithm has been developed and used to further improve hyperparameter optimization. To facilitate testing, publicly available real-world EEG data is utilized. A dataset is constructed using captured data from healthy and archived data from patients confirmed to be affected by epilepsy, as well as data captured during an active seizure. Two experiments have been conducted using generated dataset. In the first experiment, models were tasked with the detection of anomalous EEG activity. The second experiment required models to segment normal, anomalous activity as well as detect occurrences of seizures from EEG data. Considering the modest sample size (one second of data, 158 data points) used for classification models demonstrated decent outcomes. Obtained outcomes are compared with those generated by other cutting-edge metaheuristics and rigid statistical validation, as well as results' interpretation is performed. [ABSTRACT FROM AUTHOR]

As a special form of recurrent neural network (RNN), echo state networks (ESNs) have achieved good results in nonlinear system modeling, fuzzy nonlinear control, time series prediction, and so on. However, the traditional single-reservoir ESN topology limits the prediction ability of the network. In this paper, we design a multireservoir olfactory feelings echo state network (OFESN) inspired by the structure of the Drosophila olfactory bulb, which provides a new connection mode. The connection between subreservoirs is transformed into the connection between each autonomous neuron, the neurons in each subreservoir are sparsely connected, and the neurons in different subreservoirs cannot communicate with each other. The OFESN greatly simplifies the coupling connections between neurons in different libraries, reduces information redundancy, and improves the running speed of the network. The findings from the simulation demonstrate that the OFESN model, as introduced in this study, enhances the capacity to approximate sine superposition function and the Mackey–Glass system when combined. Additionally, this model exhibits improved prediction accuracy by 98% in some cases and reduced fluctuations in prediction errors. [ABSTRACT FROM AUTHOR]

Deep learning technique is an effective method for representation of complex relationships applied in various subjects and areas. Acoustic emission technique, a powerful non-destructive testing method, has been used widely to collect acoustic emission signals and monitor rock deformation and damage. This study proposed a deep learning approach to model the relationship between the remaining time to failure and data monitored by acoustic emission technique and predict failure time of sandstone in the uniaxial compression loading experiment. In the meantime, optimal feature combination of model input and optimal parameters of the model structure were obtained and discussed. Three different types of models were established, including fully connected neural networks, gated recurrent units*** and mixed model combining convolutional neural networks with gated recurrent units. The mixed model's coefficient of determination for sandstone failure prediction under uniaxial compression was 0.9699 and its mean absolute percentage error 11.64%. Its performance surpasses those of the others on tested samples. Furthermore, the metric coefficient of determination exhibits significant improvement compared with previous studies. Therefore, the obtained metric results demonstrate a satisfactory level of accuracy for predicting sandstone failure in laboratory-scale applications. Finally, this work demonstrates the capability of deep learning to predict sandstone failure via acoustic emission monitoring technique and offers the theoretical reference for practical applications at the engineering scale. Highlights: This work investigates a novel method for prediction of sandstone failure under uniaxial compression loading based on deep learning method using acoustic emission data. This work exploits an available and efficient approach for input feature selection without traversing. The average signal level (ASL) is found a critical acoustic emission characteristic for prediction of sandstone failure. In this work, the mixed model performs best comprehensively compared with the others. This work proves the applicability and potential of sandstone failure prediction based on deep learning method via acoustic emission technique. [ABSTRACT FROM AUTHOR]

To accurately analyze the dynamics and changing trends of KPI (Key Performance Indicator) data in the daily monitoring of cloud computing clusters and predict its subsequent development to achieve high availability of cloud computing clusters, we propose a three-frequency cloud KPI data prediction approach based on combined attention model of EWT-ARIMA-Auto-TPA (EAAT for short). First, low, medium and high frequency Intrinsic Mode Variables (IMFs) of cloud KPI data are obtained via Empirical Wavelet Transform (EWT) to reduce the complexity of data prediction. Second, according to the information characteristics of low, medium and high frequency IMFs obtained from the decomposition, models of ARIMA, Autoformer, and TPA-BiLSTM are used to predict each type of IMFs. Finally, the classification prediction results are combined through the Inverse EWT (IEWT) to obtain the prediction result of the KPI. The proposed prediction approach has been verified on four datasets from Google and Amazon. Whether the data is periodic and stable or not, the proposed approach outperforms comparison models. [ABSTRACT FROM AUTHOR]

Copyright of Electric Power Engineering Technology is the property of Editorial Department of Electric Power Engineering Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The stability of navigation in waves is crucial for ships, and the effect of the waves on navigation stability is complicated. Hence, the LSTM neural network technique is applied to predict the course changing of a ship in different wave conditions, where K-means clustering analysis is used for the category of the ship's navigation data to improve the quality of the database. In this paper, the effect of the initial database obtained by the K-means clustering analysis on prediction accuracy is studied first. Then, different input features are used to establish the database to train the neural network, and the influence of the database by different input features on the accuracy of the navigation prediction is discussed and analyzed. Finally, multi-task learning is used to make the neural network better predict the navigation in various wave conditions. Using the improved neural network model, the course of an autopilot ship in waves is predicted, and the results show that the current database and the neural network model are accurate enough for the course prediction of the autopilot ship in waves. [ABSTRACT FROM AUTHOR]

The black-box nature of neural networks is an obstacle to the adoption of systems based on them, mainly due to a lack of understanding and trust by end users. Providing explanations of the model's predictions should increase trust in the system and make peculiar decisions easier to examine. In this paper, an architecture of a machine learning time series prediction system for business purchase prediction based on neural networks and enhanced with Explainable artificial intelligence (XAI) techniques is proposed. The architecture is implemented on an example of a system for predicting the following purchases for time series using Long short-term memory (LSTM) neural networks and Shapley additive explanations (SHAP) values. The developed system was evaluated with three different LSTM neural networks for predicting the next purchase day, with the most complex network producing the best results across all metrics. Explanations generated by the XAI module are provided with the prediction results to the user to allow him to understand the system's decisions. Another benefit of the XAI module is the possibility to experiment with different prediction models and compare input feature effects. [ABSTRACT FROM AUTHOR]

The quality prediction of batch processes is an important task in the field of biological fermentation. However, dynamic nonlinearity, unequal sampling intervals, uneven duration, and multiple features of a batch process make this task challenging. Thus, the multiple-feature fusion transformer (MFFT) model is proposed for the time series quality prediction of a batch process. First, the application of sequence-to-sequence architecture enables MFFT to perform a wide range of sequence prediction tasks. Second, the transformer parallel operation model imposes no rigid requirement for the order of sequence input, allowing the model to deal with problems of unequal interval sampling and utilize the sequence information. Third, MFFT integrates a pretrained ResNet50 as a mycelium status classifier for fusing image information into the features. Moreover, a multiple-feature encoding structure is proposed to integrate sampling time and mycelium status. Finally, multiple tasks in penicillin fermentation have shown that MFFT significantly outperforms existing methods for time series prediction. [ABSTRACT FROM AUTHOR]

The prediction of energy-related time series for computer numerical control (CNC) machine tool axes is an essential enabler for the shift towards autonomous and intelligent production. In particular, a precise prediction of energy consumption is needed to determine the environmental impact of a product and the optimization of its production. For this purpose, a novel approach for predicting high-frequency time series of numerically controlled axes based on the program code to be executed is presented. The method involves simulative preprocessing of the input NC code to determine each axis's acceleration, velocity, and process force. Combined with the material removal rate, these variables are input for a machine learning (ML) model that delivers axis-specific high-frequency time series predictions. Compared to common approaches, it is thus possible to make predictions for the variable energy consumption of machine tools for any tool path or target resolution in the time domain. Experiments show that this approach achieves a high precision when a robust learning data basis is available. For the X-, Y-, and Z-axis, errors of 0.2%, −1.09%, and 0.09% for aircut and of 0.15%, −3.55%, and 0.08% for material removal can be achieved. The potentials for further improvement are identified systematically. [ABSTRACT FROM AUTHOR]

Copyright of Journal of East China University of Science & Technology is the property of Journal of East China University of Science & Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of East China University of Science & Technology is the property of Journal of East China University of Science & Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the building field, campus buildings are a building group with great energy-saving potential due to a lack of reasonable energy management policies. The accurate prediction of power energy usage is the basis for energy management. To address this issue, this study proposes a novel combined forecasting model based on clustering results, which can achieve a short-time prediction of daily electricity based on a campus building's electricity data over the past 15 days. Considering the diversity of campus buildings in energy consumption and functional aspects, the selected campus buildings are firstly classified into three categories using K-Means clustering in terms of their daily power consumption. Compared with the mainstream building energy consumption prediction models, i.e., LSTM and SVR, the results show that the combined forecast model is superior to other models. Furthermore, an average percentage fluctuation (APF) index is found to be close to the MAPE, which can reflect the prediction accuracy in advance. [ABSTRACT FROM AUTHOR]