Many forensic techniques have recently been developed to determine whether an image has undergone a specific manipulation operation. When multiple consecutive operations are applied to images, forensic analysts not only need to identify the existence of each manipulation operation, but also to distinguish the order of the involved operations. However, image operator chain detection is still a challenging problem. In this paper, an order forensics framework for detecting image operator chain based on convolutional neural network (CNN) is presented. Two-stream CNN architecture is designed to capture both tampering artifact evidence and local noise residual evidence. Specifically, the new CNN-based method is proposed for forensically detecting a chain made of two image operators, which could automatically learn manipulation detection features directly from image data. Further, we empirically investigate the robustness of our proposed method in two practical scenarios: forensic investigators have no access to the operating parameters, and manipulations are applied to a JPEG compressed image. Experimental results show that the proposed framework not only obtains significant detection performance but also can distinguish the order in some cases that previous works were unable to identify.

Integrated energy systems (IES) with cooling, heat, electricity, and natural gas have drawn significant interest recently as we embrace more sustainable energy a midst climate change. However, the uncertain outputs of distributed generators (DGs) make it challenging for IES planning while maintaining low-cost installation and operation under carbon emission constraints. To tackle the challenge, this work proposes an optimal planning model for IES considering both DG output uncertainties and carbon emission punishments. To reduce the conservatism of the widely-adopted interval and affine algorithms, an affine model based on the matrix form is first proposed to model the uncertain DG outputs. A tiered dynamic charging cost model is further developed to introduce and minimize carbon emissions with a punishment mechanism at the planning stage. Based on these two sub-models, an optimal IES planning model is proposed to simultaneously minimize the overall costs of investment, operation, and carbon emissions. To solve the multi-dimensional nonlinear model, an improved quantum particle swarm optimization (IQPSO) algorithm is introduced with enhanced global optimization ability. Simulation results on the IEEE 33-bus and 69-bus IES network have demonstrated that the proposed method can effectively reduce the impacts of DG uncertainty and carbon emissions at the planning stage of IES with a better long-term economy.

Current ripples produced in single-phase onboard charging systems of electric vehicles (EVs) impact the lifetime of their batteries. In this paper, an isolated multi-functional charger topology is proposed. The charging system can be used to charge the auxiliary batteries or serve as an active filter (AF) for the power battery charger. By time-sharing multiplexing it, the high frequency (HF) and low frequency (LF/second harmonic) current ripple can be suppressed in driving and parking charging mode respectively. The proposed topology can also achieve zero voltage switching (ZVS) for all power switches under a full load range in driving charging mode. In addition, the integration and the power density of the charging system can be improved due to the reconstruction of the capacitive energy storage AF in parking charging mode. Finally, a 400W experimental prototype is developed and the experimental results are presented to validate the performance and feasibility of the proposed topology.

This letter presents a novel median filtering forensics approach, based on a convolutional neural network (CNN) with an adaptive filtering layer (AFL), which is built in the discrete cosine transform (DCT) domain. Using the proposed AFL, the CNN can determine the main frequency range closely related with the operational traces. Then, to automatically learn the multi-scale manipulation features, a multi-scale convolutional block is developed, exploring a new multi-scale feature fusion strategy based on the maxout function. The resultant features are further processed by a convolutional stream with pooling and batch normalization operations, and finally fed into the classification layer with the Softmax function. Experimental results show that our proposed approach is able to accurately detect the median filtering manipulation and outperforms the state-of-the-art schemes, especially in the scenarios of low image resolution and serious compression loss.

The estimation of the state of health (SOH) of lithium-ion batteries (LIBs) plays an important role in ensuring the safe and stable operation of LIB management systems. In order to more accurately predict SOH, a model based on a sparse self-attentive transformer (SSAT) with multitimescale feature fusion is proposed. The SSAT follows an encoder-decoder structure construction, and the model inputs are the extracted health indicators and SOH sequences. The encoder stacks three cross-stage partial (CSP)-ProbSparse attention self-attention blocks, between every two CSP-ProbSparse attention blocks, connections are made by dilated causal convolution and max-pooling layers to obtain exponential growth of the sensory field. All the feature maps output from the self-attention blocks are integrated by multiscale feature fusion, and finally, the appropriate feature dimensions are fed to the decoder through a transition layer to obtain the estimation of SOH. Numerous comparative and ablation experiments have demonstrated that the SSAT model achieves superior performance in a wide range of situations.

The ac side structure of a bridgeless single-stage isolated ac–dc converter reduces the number of components by sharing power switches between the bridgeless rectifier and the dual-active-bridge (DAB) dc–dc converter. However, it also makes it more difficult to achieve zero-voltage switching (ZVS) for the ac side switches. Therefore, a modulation scheme is proposed to achieve ZVS for all switches over the full ranges of the grid voltage and load. A quasi-fixed switching frequency control method is also applied, in which the switching frequency is constant during a half-cycle of the grid voltage. By adjusting the switching frequency, the grid side inductor can operate in critical conduction mode without a zero-current-detection circuit, which facilitates the ZVS realization of the ac side switches. In addition, a natural power factor correction can be realized without the grid-side current sensors. Finally, a 500 W prototype was built to validate the theoretical analysis and the effectiveness of the proposed modulation scheme.