Quantum-behaved particle swarm optimization algorithm is firstly used in economic load dispatch of power system in this paper. Quantum-behaved particle swarm optimization algorithm is the integration ...of particle swarm optimization algorithm and quantum computing theory. The superposition characteristic and probability representation of quantum methodology are combined into particle swarm optimization algorithm. This can make a single particle be expressed by several certain probability states. And the quantum rotation gates are used to realize update operation of particles. The algorithm is simulated by two cases, which validates it can effectively solve economic load dispatch problem. Though performance comparison, it is obvious the solution is superior to that of improved particle swarm optimization algorithm and other optimization algorithms.
At present, due to the errors of wind power, solar power and various types of load forecasting, the optimal scheduling results of the integrated energy system (IES) will be inaccurate, which will ...affect the economic and reliable operation of the integrated energy system. In order to solve this problem, a day-ahead and intra-day optimal scheduling model of integrated energy system considering forecasting uncertainty is proposed in this paper, which takes the minimum operation cost of the system as the target, and different processing strategies are adopted for the model. In the day-ahead time scale, according to day-ahead load forecasting, an integrated demand response (IDR) strategy is formulated to adjust the load curve, and an optimal scheduling scheme is obtained. In the intra-day time scale, the predicted value of wind power, solar power and load power are represented by fuzzy parameters to participate in the optimal scheduling of the system, and the output of units is adjusted based on the day-ahead scheduling scheme according to the day-ahead forecasting results. The simulation of specific examples shows that the integrated demand response can effectively adjust the load demand and improve the economy and reliability of the system operation. At the same time, the operation cost of the system is related to the reliability of the accurate prediction of wind power, solar power and load power. Through this model, the optimal scheduling scheme can be determined under an acceptable prediction accuracy and confidence level.
Accurate and efficient short-term forecasting of multiple loads is of great significance to the operation control and scheduling of integrated energy distribution systems. In order to improve the ...effect of load forecasting, a mogrifier-quantum weighted memory enhancement long short-term memory (Mogrifier-QWMELSTM) neural network forecasting model is proposed. Compared with the conventional LSTM neural network model, the model proposed in this paper has three improvements in model structure and model composition. First, the mogrifier is added to make the data fully interact with each other. This addition can help enhance the correlation between the front and rear data and improve generalization, which is the main disadvantage of LSTM neural network. Second, the memory enhancement mechanism is added on the forget gate to realize the extraction and recovery of forgotten information. The addition can help improve the gradient transmission ability in the learning process of the neural network, make the neural network remain sensitive to distant data information, and enhance the memory ability. Third, the model is composed of quantum weighted neurons. Compared with conventional neurons, quantum weighted neurons have significant advantages in nonlinear data processing and parallel computing, which help to improve the accuracy of load forecasting. The simulation results show that the weighted mean accuracy of the proposed model can reach more than 97.5% in summer and winter. Moreover, the proposed model has good forecasting effect on seven typical days in winter, which shows that the model has good stability.
Recent progress has been made in defect detection using methods based on deep learning, but there are still formidable obstacles. Defect images have rich semantic levels and diverse morphological ...features, and the model is dynamically changing due to ongoing learning. In response to these issues, this article proposes a shunt feature fusion model (ST-YOLO) for steel-defect detection, which uses a split feature network structure and a self-correcting transmission allocation method for training. The network structure is designed to specialize the process of classification and localization tasks for different computing needs. By using the self-correction criteria of adaptive sampling and dynamic label allocation, more sufficiently high-quality samples are utilized to adjust data distribution and optimize the training process. Our model achieved better performance on the NEU-DET datasets and the GC10-DET datasets and was validated to exhibit excellent performance.
In order to improve the accuracy of the multiple load forecasting of a regional integrated energy system, a short-term multiple load forecasting model based on the quantum weighted GRU and multi-task ...learning framework is proposed in this paper. Firstly, correlation analysis is carried out using a maximum information coefficient to select the input of the model. Then, a multi-task learning architecture is constructed based on the quantum weighted GRU neural network, and the coupling information among multiple loads is learned through the sharing layer in order to improve the prediction accuracy of multiple loads. Finally, the PSO algorithm is used to optimize the parameters of the quantum weighted GRU. The simulation data of a regional integrated energy system in northern China are used to predict the power and cooling loads on summer weekdays and rest days, and the results show that, compared with the LSTM, GRU and single task learning QWGRU models, the proposed model is more effective in the multiple load forecasting of a regional integrated energy system.
Daily PM2.5 samples were collected at an urban site in Beijing during four one-month periods in 2009–2010, with each period in a different season. Samples were subject to chemical analysis for ...various chemical components including major water-soluble ions, organic carbon (OC) and water-soluble organic carbon (WSOC), element carbon (EC), trace elements, anhydrosugar levoglucosan (LG), and mannosan (MN). Three sets of source profiles of PM2.5 were first identified through positive matrix factorization (PMF) analysis using single or combined biomass tracers — non-sea salt potassium (nss-K+), LG, and a combination of nss-K+ and LG. The six major source factors of PM2.5 included secondary inorganic aerosol, industrial pollution, soil dust, biomass burning, traffic emission, and coal burning, which were estimated to contribute 31±37%, 39±28%, 14±14%, 7±7%, 5±6%, and 4±8%, respectively, to PM2.5 mass if using the nss-K+ source profiles, 22±19%, 29±17%, 20±20%, 13±13%, 12±10%, and 4±6%, respectively, if using the LG source profiles, and 21±17%, 31±18%, 19±19%, 11±12%, 14±11%, and 4±6%, respectively, if using the combined nss-K+ and LG source profiles. The uncertainties in the estimation of biomass burning contributions to WSOC due to the different choices of biomass burning tracers were around 3% annually and up to 24% seasonally in terms of absolute percentage contributions, or on a factor of 1.7 annually and up to a factor of 3.3 seasonally in terms of the actual concentrations. The uncertainty from the major source (e.g. industrial pollution) was on a factor of 1.9 annually and up to a factor of 2.5 seasonally in the estimated WSOC concentrations.
Display omitted
•Various biomass burning tracers were compared.•PM2.5 source profiles were compared using different biomass burning tracers.•Uncertainties in source attribution of PM2.5 and WSOC were quantified.
Motion detection from flexible and self-powered human-machine interfaces (HMI) is a promising research field for the Internet of Things (IoT) and virtual reality. The traditional HMI normally ...generated a signal curve that used the point value to represent motion status. With the proposed dual-electrode setup scheme, this research reported machine learning-augmented, wearable, self-powered, and sustainable HMI sensor in human finger motion and its virtual activities. The triboelectric friction between the moving object and the specific electrode array was used to regulate the programmable output curve of the instantaneous parameters with a unique and stable electrical signal. It demonstrated that the movable object’s motion can be tracked and accurately reproduced by the output signal using a decoupling algorithm into different motion patterns. Furthermore, the machine learning algorithm can classify fast and slow finger motions with obviously visualization performance. It also demonstrated that multiple linear regression (MLR) and the principal component analysis (PCA)+K-means clustering (K-means) presented substantially in terms of clustering, visualization, and motion speed interference. This research not only established the viability of designing self-powered HMI sensors but also demonstrated a way for identifying machine learning-augmented motion patterns and potential virtual activities by self-powered, wearable triboelectric HMI sensors.
Display omitted
•The programmable output curve of instantaneous parameters be well controlled by the triboelectric friction from HMI.•With the aid of machine learning, the motion of the object can be tracked and accurately repeated HMI sensor.•The fast and slow motion can be classified with a better visualization performance by the machine learning method.•The PCA+ K-means presented a much better cluster and avoided motion speed disturbance than PCA+ GMM in machine learning.•The self-powered HMI wearable sensors showed motion pattern identification in decoupling and virtual activities.
Background BRE-AS1 is a recently identified tumor suppressor in non-small cell lung cancer. It role in other human diseases remains elusive. Methods Differential expression of BRE-AS1 in with ...triple-negative breast cancer (TNBC) patients (n = 74, patient group) and healthy volunteers (n = 58, control group) was studied with RT-qPCR. The direct interaction between BRE-AS1 and premature microRNA-21 (miR-21) was assessed by RNA pull-down assay. The interactions among BRE-AS1, miR-21 and PTEN were evaluated by overexpression assays. CCK-8 assay and Transwell assay were used to evaluate cell behaviors. Results BRE-AS1 was downregulated in TNBC, while miR-21 was highly expressed in TNBC. Low expression levels of lncRNA BRE-AS1 and high expression levels of miR-21 were significantly correlated with unfavorable survival outcomes. BRE-AS1 and miRNA-21 were inversely correlated across TNBC samples, not control samples. BRE-AS1 decreased miR-21 expression and increased PTEN expression while miR-21showed no role in BRE-AS1 expression. RNA pull-down assay illustrated that BRE-AS1 may sponge premature miR-21 to suppress it maturation. Overexpression of BRE-AS1 decreased cell behaviors, while overexpression of miR-21 promoted cell behaviors. MiR-21 suppressed the role of BRE-AS1 in cancer cell behaviors. Conclusion Therefore, BRE-AS1 may inhibit TNBC by downregulating miR-21. Keywords: Triple-negative breast cancer, lncRNA BRE-AS1, miR-21, Survival
Multiple sensors are often mounted in a complex manufacturing process to detect failures. Due to the high reliability of modern manufacturing processes, failures only happen occasionally. Therefore, ...data collected in practical manufacturing processes are extremely imbalanced, which often brings about bias of supervised learning models. Data collected by the multiple sensors can be regarded as multivariate time series or multi-sensor stream data. The high dimension of multi-sensor stream data makes building models even more challenging. In this study, a new and easy-to-apply data augmentation approach, namely, imbalanced multi-sensor stream data augmentation (IMSDA), is proposed for imbalanced learning. IMSDA can generate high quality of failure data for all dimensions. The generated data can keep the similar temporal property of the original multivariate time series. Both raw data and generated data are used to train the failure detection models, but the models are tested by the same real dataset. The proposed method is applied to a real-world industry case. Results show that IMSDA can not only obtain good quality failure data to reduce the imbalance level but also significantly improve the performance of supervised failure detection models.
To explore the controlling factors for mass absorption efficiency (MAE) of elemental carbon (EC) in fine particles (PM2.5), major chemical compositions in size-segregated aerosol samples and bulk ...PM2.5 samples and light absorption coefficient (bap) of PM2.5 samples under dry condition were measured during four seasons in an urban environment in Guangzhou of south China. On seasonal average, absorption Ångström exponent (AAE) in the wavelength range of 370–880 nm measured by a transmissometer or in the range of 370–950 nm measured by an aethalometer ranged from 0.95 to 1.02 and from 1.01 to 1.14, respectively. The estimated EC MAE at 550 nm in PM2.5 were 10.1 ± 1.0, 8.9 ± 0.7, 9.1 ± 1.0 and 9.1 ± 0.7 m2 g−1 in spring, summer, autumn and winter, respectively, which were evidently higher than the value of 7.5 m2 g−1 for “pure EC”. More than 61% of EC mass in PM2.1 was distributed in the droplet mode (0.43–2.1 μm), which should be related to hygroscopic growth of aged EC particle as well as external mixing with coating materials. No significant correlations were found between EC MAE and mass fraction of EC or mass ratio of (SO42-+NO3−+OC)/EC in the droplet mode. The deliquescence of aerosol was primarily determined by NH4NO3, and the high EC MAE was mainly related to high nitrate mass concentration and positive ΔRH (ambient relative humidity minus deliquescence relative humidity of NH4NO3).
Display omitted
•Elemental carbon was mainly originated from vehicle emissions in urban Guangzhou.•EC was mainly distributed in the droplet mode largely due to external mixing.•The estimated EC MAE at 550 nm was evidently higher than that for pure EC.•Enhanced EC MAE was mainly caused by aerosol deliquescence by nitrate.