Abstract: The present invention provides a dynamic joint distribution alignment network-based bearing fault diagnosis method under variable working conditions, including acquiring bearing vibration data under different working conditions to obtain a source domain sample and a target domain sample; establishing a deep convolutional neural network model with dynamic joint distribution alignment; feeding both the source domain sample and the target domain sample into the deep convolutional neural network model with initialized parameters, and extracting, by a feature extractor, high-level features of the source domain sample and the target domain sample; calculating a marginal distribution distance and a conditional distribution distance; obtaining a joint distribution distance according to the marginal distribution distance and the conditional distribution distance, and combining the joint distribution distance and a label loss to obtain a target function; and optimizing the target function by using SGD, and training the

Abstract: The invention relates to a fault diagnosis method for a rolling bearing under variable working conditions. Based on a convolutional neural network, a transfer learning algorithm is combined to handle the problem of the reduced universality of deep learning models. Data acquired under different working conditions is segmented to obtain samples. The samples are preprocessed by using FFT. Low-level features of the samples are extracted by using improved ResNet-50, and a multi-scale feature extractor analyzes the low-level features to obtain high-level features as inputs of a classifier. In a training process, high-level features of training samples and test samples are extracted, and a conditional distribution distance between them is calculated as a part of a target function for backpropagation to implement intra-class adaptation, thereby reducing the impact of domain shift, to enable a deep learning model to better carry out fault diagnosis tasks.

Abstract: The present invention provides a dynamic joint distribution alignment network-based bearing fault diagnosis method under variable working conditions, including acquiring bearing vibration data under different working conditions to obtain a source domain sample and a target domain sample; establishing a deep convolutional neural network model with dynamic joint distribution alignment; feeding both the source domain sample and the target domain sample into the deep convolutional neural network model with initialized parameters, and extracting, by a feature extractor, high-level features of the source domain sample and the target domain sample; calculating a marginal distribution distance and a conditional distribution distance; obtaining a joint distribution distance according to the marginal distribution distance and the conditional distribution distance, and combining the joint distribution distance and a label loss to obtain a target function; and optimizing the target function by using SGD, and training the

Abstract: The invention provides an adaptive manifold probability distribution-based bearing fault diagnosis method, including constructing transferable domains and transfer tasks; converting a data sample in each transfer task into frequency domain data via Fourier transform, inputting the frequency domain data into a GFK algorithm model, and calculating a manifold feature representation matrix related to a bearing fault in each transfer task by using the GFK algorithm model; calculating a cosine distance between centers of a target domain and a source domain in each transfer task according to a manifold feature representation, and defining a target function of in-domain classifier learning; then solving the target function, to obtain a probability distribution matrix of the target domain; and selecting a label corresponding to the largest probability value corresponding to each data sample in the target domain from the probability distribution matrix as a predicted label of the data sample in the target domain.

Abstract: The invention provides an adaptive manifold probability distribution-based bearing fault diagnosis method, including constructing transferable domains and transfer tasks; converting a data sample in each transfer task into frequency domain data via Fourier transform, inputting the frequency domain data into a GFK algorithm model, and calculating a manifold feature representation matrix related to a bearing fault in each transfer task by using the GFK algorithm model; calculating a cosine distance between centers of a target domain and a source domain in each transfer task according to a manifold feature representation, and defining a target function of in-domain classifier learning; then solving the target function, to obtain a probability distribution matrix of the target domain; and selecting a label corresponding to the largest probability value corresponding to each data sample in the target domain from the probability distribution matrix as a predicted label of the data sample in the target domain.

Abstract: The invention relates to a fault diagnosis method for a rolling bearing under variable working conditions. Based on a convolutional neural network, a transfer learning algorithm is combined to handle the problem of the reduced universality of deep learning models. Data acquired under different working conditions is segmented to obtain samples. The samples are preprocessed by using FFT. Low-level features of the samples are extracted by using improved ResNet-50, and a multi-scale feature extractor analyzes the low-level features to obtain high-level features as inputs of a classifier. In a training process, high-level features of training samples and test samples are extracted, and a conditional distribution distance between them is calculated as a part of a target function for backpropagation to implement intra-class adaptation, thereby reducing the impact of domain shift, to enable a deep learning model to better carry out fault diagnosis tasks.

Abstract: The present invention relates to a high-strength high-toughness steel plate and a method of manufacturing the steel plate. The steel plate contains the following chemical compositions, by weight, C: 0.03-0.06%, Si?0.30%, Mn: 1.0-1.5%, P?0.020%, S?0.010%, Al: 0.02-0.05%, Ti: 0.005-0.025%, N?0.006%, Ca?0.005%, and more than one of Cr?0.75%, Ni?0.40%, Mo?0.30%, other compositions being Ferrum and unavoidable impurities. The finished steel plate, with a thickness of 6-25 mm, has a yield strength of ?700 MPa, an elongation A50 of ?18%, Akv at ?60° C. of ?150 J and good cool bending property.

Abstract: The present invention provides a high-strength wear-resistant steel plate with Brinell hardness of ?HB420, comprising the following chemical compositions (by weight %) C: 0.205-0.25%, Si: 0.20-1.00%, Mn: 1.0-1.5%, P?0.015%, S?0.010%, Al: 0.02-0.04%, Ti: 0.01-0.03%, N?0.006%, Ca?0.005%, and at least one of Cr?0.70%, Ni?0.50%, Mo?0.30%, other compositions being Ferrum and unavoidable impurities. Also provided is a method of manufacturing the wear-resistant steel plate has remarkable TRIP effect in use, improving substantially its wear resistance, thereby meeting the high demand for wear-resistant steel plates in related industries.

Abstract: A steel plate with a low yield ratio and high toughness. The steel plate comprises components of, by weight: C (0.05-0.08%), Si (0.15-0.30%), Mn (1.55-1.85%), P (less than or equal to 0.015%), S (less than or equal to 0.005%), Al (0.015-0.04%), Nb (0.015-0.025%), Ti (0.01-0.02%), Cr (0.20-0.40%), Mo (0.18-0.30%), N (less than or equal to 0.006%), O (less than or equal to 0.004%), Ca (0.0015-0.0050%), and Ni (less than or equal to 0.40%), a ratio of Ca to S being greater than or equal to 1.5, and the residual being Fe and inevitable impurities.

Abstract: A steel plate with a low yield ratio and high toughness. The steel plate comprises components of, by weight: C (0.05-0.08%), Si (0.15-0.30%), Mn (1.55-1.85%), P (less than or equal to 0.015%), S (less than or equal to 0.005%), Al (0.015-0.04%), Nb (0.015-0.025%), Ti (0.01-0.02%), Cr (0.20-0.40%), Mo (0.18-0.30%), N (less than or equal to 0.006%), O (less than or equal to 0.004%), Ca (0.0015-0.0050%), and Ni (less than or equal to 0.40%), a ratio of Ca to S being greater than or equal to 1.5, and the residual being Fe and inevitable impurities.

Abstract: The present invention provides a high-strength wear-resistant steel plate with Brinell hardness of ?HB420, comprising the following chemical compositions (by weight %) C: 0.205-0.25%, Si: 0.20-1.00%, Mn: 1.0-1.5%, P?0.015%, S?0.010%, Al: 0.02-0.04%, Ti: 0.01-0.03%, N?0.006%, Ca?0.005%, and more than one of Cr?0.70%, Ni?0.50%, Mo?0.30%, other compositions being Ferrum and unavoidable impurities. Also provided is a method of manufacturing the wear-resistant steel plate has remarkable TRIP effect in use, improving substantially its wear resistance, thereby meeting the high demand for wear-resistant steel plates in related industries.

Abstract: The present invention relates to a high-strength high-toughness steel plate and a method of manufacturing the steel plate. The steel plate contains the following chemical compositions, by weight, C: 0.03-0.06%, Si?0.30%, Mn: 1.0-1.5%, P?0.020%, S?0.010%, Al: 0.02-0.05%, Ti: 0.005-0.025%, N?0.006%, Ca?0.005%, and more than one of Cr?0.75%, Ni?0.40%, Mo?0.30%, other compositions being Ferrum and unavoidable impurities.The finished steel plate, with a thickness of 6-25 mm, has a yield strength of ?700 MPa, an elongation A50 of ?18%, Akv at ?60° C. of ?150 J and good cool bending property.