Abstract: Provided is a method and a system for accelerated life testing (ALT) of a proton exchange membrane fuel cell (PEMFC). In the present disclosure, a collected voltage-time sequence data of the PEMFC is filtered and subjected to empirical mode decomposition (EMD), such that a voltage data is decomposed to obtain K intrinsic mode functions. A constructed bidirectional long short-term memory-based artificial neural network (BiLSTM) shows majority input characteristics and can model each of the intrinsic mode functions independently, thereby reducing a difficulty of long-cycle life prediction in limited training data scenarios. In addition, optimal parameters of the BiLSTM are optimized through a sparrow search algorithm, which greatly improves a prediction accuracy of a remaining useful life for the PEMFC. The method and the system of the present disclosure exhibit low computing cost, simple parameter setting, and high prediction accuracy, and are extremely suitable for operation and maintenance of the PEMFC.

Abstract: The present disclosure provides a fuel cell fault diagnosis method and system.

Abstract: A saline wastewater treatment method is provided. Raw water is pretreated to obtain pretreated raw water. The pretreated raw water is pressurized to a preset pressure, injected with zone, separated and filtered by a filtering device with a hollow fiber nanofiltration membrane or a hollow fiber reverse osmosis membrane inside to obtain a concentrate and a permeate. A pressure of the concentrate is controlled such that ozone in the concentrate is released to form micro-nano bubbles. The concentrate is partially injected into the pretreated raw water. A pressure of the permeate and a pressure of the raw water are respectively controlled such that ozone in the permeate and the raw water is released inside the filtering device to form micro-nano bubbles to flush the hollow fiber nanofiltration membrane or the hollow fiber reverse osmosis membrane. A saline wastewater treatment system is also provided.

Abstract: A method for controlling a hollow fiber nanofiltration membrane system with controllable power consumption, including the following steps. A filtration flow rate is determined by the program control system according to preset working conditions and the electricity price and the inlet water temperature obtained by a first monitoring module when the hollow fiber nanofiltration membrane assembly is started to perform a filtration process. The inlet water pressure change and the permeability change are monitored and recorded by a second monitoring module during the filtration process. A flushing mode and a flushing intensity of the cleaning system are determined by the program control system according to the inlet water pressure change and the permeability change during the filtration when the filtration process is completed.

Abstract: A hollow fiber nanofiltration membrane system and its control method are provided. The system includes a water feeding system, a return system, a hollow fiber nanofiltration membrane group, a water production system, a cleaning system, a dosing system and a program control system. Through the self-matching, self-adaptation and self-adjustment functions of the program control system, an intelligent and accurate operation control is formed according to water quality and operation condition. In the control method, the program control system presets an operation mode according to a preset working condition and an inlet water quality, automatically selects whether to add the scale inhibitor or perform concentrated water return at a beginning of filtration, automatically outputs a dosage of the scale inhibitor or the concentrated water return flow, and monitor a change of the inlet water quality, and the feedwater pressure or a transmembrane pressure in real time.

Abstract: A hollow fiber nanofiltration membrane system and its control method are provided. The system includes a water feeding system, a return system, a hollow fiber nanofiltration membrane group, a water production system, a cleaning system, a dosing system and a program control system. Through the self-matching, self-adaptation and self-adjustment functions of the program control system, an intelligent and accurate operation control is formed according to water quality and operation condition. In the control method, the program control system presets an operation mode according to a preset working condition and an inlet water quality, automatically selects whether to add the scale inhibitor or perform concentrated water return at a beginning of filtration, automatically outputs a dosage of the scale inhibitor or the concentrated water return flow, and monitor a change of the inlet water quality, and the feedwater pressure or a transmembrane pressure in real time.

Abstract: A saline wastewater treatment method is provided. Raw water is pretreated to obtain pretreated raw water. The pretreated raw water is pressurized to a preset pressure, injected with zone, separated and filtered by a filtering device with a hollow fiber nanofiltration membrane or a hollow fiber reverse osmosis membrane inside to obtain a concentrate and a permeate. A pressure of the concentrate is controlled such that ozone in the concentrate is released to form micro-nano bubbles. The concentrate is partially injected into the pretreated raw water. A pressure of the permeate and a pressure of the raw water are respectively controlled such that ozone in the permeate and the raw water is released inside the filtering device to form micro-nano bubbles to flush the hollow fiber nanofiltration membrane or the hollow fiber reverse osmosis membrane. A saline wastewater treatment system is also provided.

Abstract: A method for controlling a hollow fiber nanofiltration membrane system with controllable power consumption, including the following steps. A filtration flow rate is determined by the program control system according to preset working conditions and the electricity price and the inlet water temperature obtained by a first monitoring module when the hollow fiber nanofiltration membrane assembly is started to perform a filtration process. The inlet water pressure change and the permeability change are monitored and recorded by a second monitoring module during the filtration process. A flushing mode and a flushing intensity of the cleaning system are determined by the program control system according to the inlet water pressure change and the permeability change during the filtration when the filtration process is completed.

Abstract: A method for breeding a new variety of a ratoon rice crop and a cultivation method for the new variety of a ratoon rice crop. The method comprises: breeding a photosensitive variety of a rice crop; growing a ratoon rice crop under conditions of a long photoperiod; and taking corresponding cultivation measures to extend the growth duration of the ratoon rice crop. The invention increases grain yield while also permitting more uniform maturity of a ratoon rice crop. When compared to existing methods for cultivating ratoon rice crops, the invention greatly improves the grain yield and quality of a ratoon rice crop, and has economic and social benefits.

Abstract: A system and method for treating reverse-osmosis (RO) concentrated water with high temporary hardness. The system includes a crystallization unit, a precipitation unit, a dewatering unit, and a programmable logic controller (PLC) system. The crystallization unit, precipitation unit and dewatering unit are connected in series, and the PLC system is configured to control pumps, valves, and displays in the crystallization unit, precipitation unit and dewatering unit. The crystallization unit includes a storage tank and a crystallization reactor communicated therewith. The crystallization reactor is provided with a pH meter, a liquid-level gauge, and a stirrer. A connection pipe between the crystallization reactor and the RO concentrated water is provided with an inlet pump and a inlet valve. A connection pipe between the crystallization reactor and the storage tank is provided with a feeding pump and a feeding valve.

Abstract: A system and method for treating reverse-osmosis (RO) concentrated water with high temporary hardness. The system includes a crystallization unit, a precipitation unit, a dewatering unit, and a programmable logic controller (PLC) system. The crystallization unit, precipitation unit and dewatering unit are connected in series, and the PLC system is configured to control pumps, valves, and displays in the crystallization unit, precipitation unit and dewatering unit. The crystallization unit includes a storage tank and a crystallization reactor communicated therewith. The crystallization reactor is provided with a pH meter, a liquid-level gauge, and a stirrer. A connection pipe between the crystallization reactor and the RO concentrated water is provided with an inlet pump and a inlet valve. A connection pipe between the crystallization reactor and the storage tank is provided with a feeding pump and a feeding valve.

Abstract: A dosing control method for micro-flocculation in ultrafiltration, including: calculating a preset value of a first differential pressure before an initial backwash and a preset value of a second differential pressure before a final backwash in each chemically enhanced backwash cycle; calculating a preset value of a third differential pressure between the first differential pressure and the second differential pressure according to the preset value of the first differential pressure and the preset value of the second differential pressure; obtaining a predicted value of the third differential pressure according to a differential pressure curve plotted based on online filtration differential pressure data; and comparing the preset value of the third differential pressure and the predicted value of the third differential pressure to determine whether to dose. A dosing control system is also provided.

Abstract: A dosing control method for micro-flocculation in ultrafiltration, including: calculating a preset value of a first differential pressure before an initial backwash and a preset value of a second differential pressure before a final backwash in each chemically enhanced backwash cycle; calculating a preset value of a third differential pressure between the first differential pressure and the second differential pressure according to the preset value of the first differential pressure and the preset value of the second differential pressure; obtaining a predicted value of the third differential pressure according to a differential pressure curve plotted based on online filtration differential pressure data; and comparing the preset value of the third differential pressure and the predicted value of the third differential pressure to determine whether to dose. A dosing control system is also provided.

Abstract: A method for breeding a new variety of a ratoon rice crop and a cultivation method for the new variety of a ratoon rice crop. The method comprises: breeding a photosensitive variety of a rice crop; growing a ratoon rice crop under conditions of a long photoperiod; and taking corresponding cultivation measures to extend the growth duration of the ratoon rice crop. The invention increases grain yield while also permitting more uniform maturity of a ratoon rice crop. When compared to existing methods for cultivating ratoon rice crops, the invention greatly improves the grain yield and quality of a ratoon rice crop, and has economic and social benefits.

Abstract: Retrieval of images of objects from a large-scale database of object images, based on a query image. The database may, for example, contain images of objects such as faces, vehicles, people and luggage. Semantic attributes such as doors or windows in the case of vehicles are used as high level semantic cues to determine identities of objects in the images. Salient visual characteristics of the images are labeled with attribute information, and a transformation is learned so as to transform the labeled visual characteristics into a discrimination vector that discriminates between the labels. A similarity metric is learned using the discrimination vectors, such that different images depicting the same object are determined to be close while those having different objects are determined to be far apart. Candidates are retrieved based on a query image, and a re-ranking step may be applied to improve results. Validation experiments are described.

Abstract: Systems, devices, and methods for generating attribute scores obtain a plurality of object images; generate a respective first attribute score of a first attribute for each object image in the plurality of object images based on the object images; calculate a respective pairwise object-similarity measure for pairs of object images in the plurality of object images; and refine the first attribute score of an object image in the plurality of object images based at least in part on the attribute scores of other object images in the plurality of object images and on the object-similarity measures of the pairs of object images in the plurality of object images.

Abstract: Retrieval of images of objects from a large-scale database of object images, based on a query image. The database may, for example, contain images of objects such as faces, vehicles, people and luggage. Semantic attributes such as doors or windows in the case of vehicles are used as high level semantic cues to determine identities of objects in the images. Salient visual characteristics of the images are labeled with attribute information, and a transformation is learned so as to transform the labeled visual characteristics into a discrimination vector that discriminates between the labels. A similarity metric is learned using the discrimination vectors, such that different images depicting the same object are determined to be close while those having different objects are determined to be far apart. Candidates are retrieved based on a query image, and a re-ranking step may be applied to improve results. Validation experiments are described.

Abstract: Systems, devices, and methods for generating attribute scores obtain a plurality of object images; generate a respective first attribute score of a first attribute for each object image in the plurality of object images based on the object images; calculate a respective pairwise object-similarity measure for pairs of object images in the plurality of object images; and refine the first attribute score of an object image in the plurality of object images based at least in part on the attribute scores of other object images in the plurality of object images and on the object-similarity measures of the pairs of object images in the plurality of object images.

Abstract: Systems and methods for organizing images extract low-level features from an image of a collection of images of a specified event, wherein the low-level features include visual characteristics calculated from the image pixel data, and wherein the specified event includes two or more sub-events; extract a high-level feature from the image, wherein the high-level feature includes characteristics calculated at least in part from one or more of the low-level features; identify a sub-events in the image based on the high-level feature and a predetermined model of the specified event, wherein the predetermined model describes a relationship between two or more sub-events; and annotate the image based on the identified sub-event.

Abstract: There is provided a novel approach for automatic human face authentication. Taking a 3D triangular facial mesh as input, the approach first automatically extracts the bilateral symmetry plane of the face surface. The intersection between the symmetry plane and the facial surface, namely the Symmetry Profile, is then computed. By using both the mean curvature plot of the facial surface and the curvature plot of the symmetry profile curve, three essential points of the nose on the symmetry profile are automatically extracted. The three essential points uniquely determine a Face Intrinsic Coordinate System (FICS). Different faces are aligned based on the FICS. The Symmetry Profile, together with two transversal profiles, namely the Forehead Profile and the Cheek Profile compose a compact representation, called the SFC representation, of a 3D face surface. The face authentication and recognition steps are finally performed by comparing the SFC representation of the faces.