Abstract: Method and system for displaying one or more regions of interest of an original image. For example, a computer-implemented method for displaying one or more regions of interest of an original image includes: obtaining one or more detection results of one or more first regions of interest, each detection result of the one or more detection results corresponding to one first region of interest of the one or more first regions of interest, each detection result including image information and one or more attribute parameters for their corresponding first region of interest; and obtaining one or more attribute parameter thresholds provided by a user in real time, each attribute parameter threshold of the one or more attribute parameter thresholds corresponding to one attribute parameter of the one or more attribute parameters.

Abstract: An oriented silicon steel product with a low iron loss for a low-noise transformer, and manufacturing method thereof are provided. The oriented silicon steel product comprises: a silicon steel substrate, a magnesium silicate bottom layer formed on a surface of the silicon steel substrate, and an insulation coating applied on the magnesium silicate bottom layer. The magnesium silicate bottom layer has a visible light normal reflectivity (R) of 40-60% for. By strictly controlling the visible light normal reflectivity of the magnesium silicate bottom layer of the silicon steel substrate and the evenness of the gloss of magnesium silicate bottom layer, lower iron loss, and reduced magnetostriction can be achieved, and thus a silicon steel product with low noise and particularly suitable for transformers can be obtained.

Abstract: A method and a system for image reconstruction are provided. The method may include acquiring raw image data, wherein the raw image data may include a plurality of frequency domain undersampled image data samples. The method may include generating a first reconstruction result based on the raw image data using a first reconstruction method, and generating a second reconstruction result based on the raw image data using a second reconstruction method. The method may further include fusing the first reconstruction result and the second reconstruction result, and generating a reconstructed image based on a result of the fusion.

Abstract: A method for generating a trained neural network model for scanning correction corresponding to one or more imaging parameters is provided. The trained neural network model may be trained using training data. The training data may include at least one first set of training data. The first set of training data may be generated according to a process for generating the first set of training data. The process may include obtaining a first image and a second image corresponding to the one or more imaging parameters. The second image may include less scattering noises than the first image. The process may further include determine the first set of training data based on the first image and the second image.

Abstract: A non-oriented electrical steel having excellent magnetic properties, the chemical elements thereof in percentage by mass being: Si: 0.2-1.5%, Mn: 0.01-0.30%, Al: 0.001-0.009%, O: 0.005-0.02%, C?0.005%, S?0.005%, N?0.005%, and Ti?0.002%, the remainder being Fe and other unavoidable impurities, and Al/Si?0.006 and Mn/Si?0.2. The method for producing comprises the following sequence of steps: (1) smelting; (2) hot rolling: the slab heating temperature being 850° C. to 1250° C., and the final rolling temperature being 800-1050° C.; (3) acid pickling; (4) cold rolling; (5) annealing: the annealing plate temperature being controlled between 620° C.-900° C.; and (6) coating.

Abstract: Method and system for displaying one or more regions of interest of an original image. For example, a computer-implemented method for displaying one or more regions of interest of an original image includes: obtaining one or more detection results of one or more first regions of interest, each detection result of the one or more detection results corresponding to one first region of interest of the one or more first regions of interest, each detection result including image information and one or more attribute parameters for their corresponding first region of interest; and obtaining one or more attribute parameter thresholds provided by a user in real time, each attribute parameter threshold of the one or more attribute parameter thresholds corresponding to one attribute parameter of the one or more attribute parameters.

Abstract: The invention discloses a device for preheating before welding and post-welding heat treatment of tank. The device includes a first roller, two electric heating belts, calipers, a thermostat, two positioners and hinges. Both of the electric heating belts are arranged around the tank and distributed on both sides of the welded seam. A number of calipers are provided on both sides of each electric heating belt, one end of each caliper can operatively clamp the side of the electric heating belt, another end of each caliper is rotatably connected to a first roller. The hinge is connected to the electric heating belt, and one end of the hinge away from the electric heating belt is in a fixed state. The heating temperature of the electric heating belt is controlled, thereby realizing preheating of the tank before welding, heat preservation during welding and post-welding heat treatment without transferring.

Abstract: The invention discloses a device for preheating before welding and post-welding heat treatment of tank. The device includes a first roller, two electric heating belts, calipers, a thermostat, two positioners and hinges. Both of the electric heating belts are arranged around the tank and distributed on both sides of the welded seam. A number of calipers are provided on both sides of each electric heating belt, one end of each caliper can operatively clamp the side of the electric heating belt, another end of each caliper is rotatably connected to a first roller. The hinge is connected to the electric heating belt, and one end of the hinge away from the electric heating belt is in a fixed state. The heating temperature of the electric heating belt is controlled, thereby realizing preheating of the tank before welding, heat preservation during welding and post-welding heat treatment without transferring.

Abstract: Method and system for displaying one or more regions of interest of an original image. For example, a computer-implemented method for displaying one or more regions of interest of an original image includes: obtaining one or more detection results of one or more first regions of interest, each detection result of the one or more detection results corresponding to one first region of interest of the one or more first regions of interest, each detection result including image information and one or more attribute parameters for their corresponding first region of interest; and obtaining one or more attribute parameter thresholds provided by a user in real time, each attribute parameter threshold of the one or more attribute parameter thresholds corresponding to one attribute parameter of the one or more attribute parameters.

Abstract: A method and a system for image reconstruction are provided. The method may include acquiring raw image data, wherein the raw image data may include a plurality of frequency domain undersampled image data samples. The method may include generating a first reconstruction result based on the raw image data using a first reconstruction method, and generating a second reconstruction result based on the raw image data using a second reconstruction method. The method may further include fusing the first reconstruction result and the second reconstruction result, and generating a reconstructed image based on a result of the fusion.

Abstract: A method for generating a trained neural network model for scanning correction corresponding to one or more imaging parameters is provided. The trained neural network model may be trained using training data. The training data may include at least one first set of training data. The first set of training data may be generated according to a process for generating the first set of training data. The process may include obtaining a first image and a second image corresponding to the one or more imaging parameters. The second image may include less scattering noises than the first image. The process may further include determine the first set of training data based on the first image and the second image.

Abstract: Disclosed is a non-oriented electrical steel plate having a good surface state, a high magnetic induction and a low iron loss, the contents of various chemical elements of the non-oriented electrical steel plate in mass percentage being: 0<C?0.004%, 0.1%?Si?1.6%, 0.1%?Mn?0.8%, 0.1%?Al?0.6%, Ti?0.0015%, and the balance being Fe and other inevitable impurities, with 0.2%?(Si+Al)?2.0% being met. Also disclosed is a method for manufacturing the above-mentioned steel plate, comprising the steps: a liquid iron pretreatment, smelting with a converter, RH refining, casting into slabs, hot rolling, acid pickling, cold rolling, annealing and coating. The non-oriented electrical steel plate of the present invention has an excellent magnetic property, an ultralow iron loss and a higher steel purity; in addition the surface quality of the steel plate is good and the production cost is low.

Abstract: A method and a system for image reconstruction are provided. The method may include acquiring raw image data, wherein the raw image data may include a plurality of frequency domain undersampled image data samples. The method may include generating a first reconstruction result based on the raw image data using a first reconstruction method, and generating a second reconstruction result based on the raw image data using a second reconstruction method. The method may further include fusing the first reconstruction result and the second reconstruction result, and generating a reconstructed image based on a result of the fusion.

Abstract: A method for generating a trained neural network model for scanning correction corresponding to one or more imaging parameters is provided. The trained neural network model may be trained using training data. The training data may include at least one first set of training data. The first set of training data may be generated according to a process for generating the first set of training data. The process may include obtaining a first image and a second image corresponding to the one or more imaging parameters. The second image may include less scattering noises than the first image. The process may further include determine the first set of training data based on the first image and the second image.

Abstract: Method and system for displaying one or more regions of interest of an original image. For example, a computer-implemented method for displaying one or more regions of interest of an original image includes: obtaining one or more detection results of one or more first regions of interest, each detection result of the one or more detection results corresponding to one first region of interest of the one or more first regions of interest, each detection result including image information and one or more attribute parameters for their corresponding first region of interest; and obtaining one or more attribute parameter thresholds provided by a user in real time, each attribute parameter threshold of the one or more attribute parameter thresholds corresponding to one attribute parameter of the one or more attribute parameters.

Abstract: A non-oriented electrical steel having excellent magnetic properties, the chemical elements thereof in percentage by mass being: Si: 0.2-1.5%, Mn: 0.01-0.30%, Al: 0.001-0.009%, O: 0.005-0.02%, C?0.005%, S?0.005%, N?0.005%, and Ti?0.002%, the remainder being Fe and other unavoidable impurities, and Al/Si?0.006 and Mn/Si?0.2. The method for producing comprises the following sequence of steps: (1) smelting; (2) hot rolling: the slab heating temperature being 850° C. to 1250° C., and the final rolling temperature being 800-1050° C.; (3) acid pickling; (4) cold rolling; (5) annealing: the annealing plate temperature being controlled between 620° C.-900° C.; and (6) coating.

Abstract: An oriented silicon steel product with a low iron loss for a low-noise transformer, and manufacturing method thereof are provided. The oriented silicon steel product comprises: a silicon steel substrate, a magnesium silicate bottom layer formed on a surface of the silicon steel substrate, and an insulation coating applied on the magnesium silicate bottom layer. The magnesium silicate bottom layer has a visible light normal reflectivity (R) of 40-60% for. By strictly controlling the visible light normal reflectivity of the magnesium silicate bottom layer of the silicon steel substrate and the evenness of the gloss of magnesium silicate bottom layer, lower iron loss, and reduced magnetostriction can be achieved, and thus a silicon steel product with low noise and particularly suitable for transformers can be obtained.

Abstract: A method and a system for image reconstruction are provided. The method may include acquiring raw image data, wherein the raw image data may include a plurality of frequency domain undersampled image data samples. The method may include generating a first reconstruction result based on the raw image data using a first reconstruction method, and generating a second reconstruction result based on the raw image data using a second reconstruction method. The method may further include fusing the first reconstruction result and the second reconstruction result, and generating a reconstructed image based on a result of the fusion.

Abstract: A method for generating a trained neural network model for scanning correction corresponding to one or more imaging parameters is provided. The trained neural network model may be trained using training data. The training data may include at least one first set of training data. The first set of training data may be generated according to a process for generating the first set of training data. The process may include obtaining a first image and a second image corresponding to the one or more imaging parameters. The second image may include less scattering noises than the first image. The process may further include determine the first set of training data based on the first image and the second image.

Abstract: Disclosed is a non-oriented electrical steel plate having a good surface state, a high magnetic induction and a low iron loss, the contents of various chemical elements of the non-oriented electrical steel plate in mass percentage being: 0<C?0.004%, 0.1%?Si?1.6%, 0.1%?Mn?0.8%, 0.1%?Al?0.6%, Ti?0.0015%, and the balance being Fe and other inevitable impurities, with 0.2%?(Si+Al)?2.0% being met. Also disclosed is a method for manufacturing the above-mentioned steel plate, comprising the steps: a liquid iron pretreatment, smelting with a converter, RH refining, casting into slabs, hot rolling, acid pickling, cold rolling, annealing and coating. The non-oriented electrical steel plate of the present invention has an excellent magnetic property, an ultralow iron loss and a higher steel purity; in addition the surface quality of the steel plate is good and the production cost is low.