17results about How to "Solve the explosion" patented technology

The present invention relates to the technical field of sleep diagnosis, and in particular to a sleep staging method based on deep learning, the method comprising: collecting a number of target physiological signals, preprocessing each target physiological signal to obtain a number of standard physiological signals; synchronously aligning and integrating each standard physiological signal in turn to obtain a standard sleep data set; determining the actual correlation between each physiological signal to be integrated in the standard sleep data set, and determining an actual signal combination strategy according to the actual correlation; generating an actual sleep data set according to the actual signal combination strategy, and extracting features from the actual sleep data set to generate actual feature parameters; inputting the actual feature parameters into a deep learning model to determine the actual sleep state; analyzing the actual sleep state, and performing corresponding sleep intervention according to the analysis results. The present invention realizes low-cost non-intrusive sleep monitoring, thereby improving people's physical health.

The present invention relates to the field of network traffic classification, and in particular to a network traffic classification method based on an attention mechanism. Aiming at the characterization problem of different important features, this paper proposes a new classification model, which first pre-processes the original network traffic, then extracts spatial features through a CNN layer, extracts temporal features from an LSTM layer, then fuses the extracted multi-scale features, and uses an attention mechanism to extract multi-modal network traffic significant features to improve the output quality of dynamic structures and improve feature representation capabilities. Through the design of the present invention, the classification accuracy can be ultimately improved.

The invention provides a vehicle driving obstacle distance detection method and system based on a vehicle-mounted depth camera, and relates to the technical field of vehicle obstacle detection. Comprising the following steps: acquiring RGB image information, depth point cloud information and 3D coordinate information of a to-be-identified obstacle during vehicle driving; geometric features of key points in the RGB image information are extracted, and obstacles in the key points are recognized; aligning and integrating the 3D coordinate information and the depth point cloud information according to a timestamp, and combining the identified obstacle to obtain a 3D coordinate with the timestamp of the obstacle; and learning spatial features of different scales of the 3D coordinates with the timestamps of the obstacle, and performing feature extraction to obtain the distance between the obstacle and the vehicle body. According to the method, the RGB image information, the depth point cloud information and the 3D coordinate information of the to-be-recognized obstacle in the running process of the vehicle are acquired by using the depth camera installed on the vehicle body, and classification and regression are performed after different feature information is extracted by using the hybrid network model, so that the effects of efficiently and accurately recognizing the obstacle and predicting the distance between the obstacle and the vehicle body can be considered.

The invention provides a sodium chlorate (potassium chlorate) electrolyzer, which comprises a reactor, an electrolytic cell group and a lifting steel frame, a pressure discharge assembly is arranged between the input end of the reactor and the output end of the electrolytic cell group, is connected with an emptying pipe of the reactor and is mounted on the lifting steel frame, and the maximum pipe diameter of an input pipeline of the electrolytic cell group is larger than the sum of the pipe diameters of upper headers. The pressure difference between the upper collecting pipe and the lower collecting pipe is reduced by changing the height of the whole pipeline, the flow speed is increased, the phenomenon of no empty groove is achieved, hydrogen and electrolyte mixed liquid can be rapidly fed into the reactor, hydrogen is emptied through the top of the reactor, and therefore equipment can operate safely, and safety is greatly improved.

The application discloses a sea surface weak target detection method based on a residual network and a hypersphere constraint. The method can solve the problems of training underfitting or overfitting caused by the fact that the target sample is much smaller than the sea clutter sample under the sea clutter background, and the specific steps include: 1, performing short-time Fourier transform on each piece of data obtained after dividing the radar echo signal sample to obtain a time-frequency spectrum; 2, constructing an anomaly detection network model combined with a support vector data description based on a variational autoencoder of a residual network; 3, inputting the time-frequency spectrum into the anomaly detection network model for end-to-end training; 4, performing online detection of the target based on the trained model; and 5, evaluating the performance of the application from the constructed multi-dimensional index. The application can effectively enhance the separability between the target and the sea clutter, and improve the weak target detection precision under the condition of a real small sample.

A fireproof and explosion-proof device is added to the interface of the breathing tube of an inflammable and explosive storage tank, which belongs to the technical field of fuel and liquefied gas equipment. The device is characterized in that: the operating flange of the upper shell is connected with a self-closing quick connector, and the shell is divided into a common channel, a gas phase channel and a liquid phase channel. The space formed by each of them is a tubular structure, and its spatial position is a coaxial tube structure. The space formed by the gas phase channel and the liquid phase channel is a symmetrical structure. The common channel is provided with a valve core A, a steel solid filter, a core rod, and a rod spring. The gas phase channel is provided with a boundary sleeve, a boundary sleeve seal, a gas phase explosion-proof barrel, a gas phase explosion-proof core, a linkage, a valve core B, a valve core C, a valve seat, a limiter, a barrel spring, a spring seat, a retaining ring, and a core rod. The liquid phase channel is provided with a liquid phase explosion-proof core, and explosion-proof liquid inlet and explosion-proof liquid outlet are respectively provided at both ends of the boundary sleeve, and a liquid outlet control hole is provided at the lower end of the gas phase explosion-proof barrel. The beneficial effect is that the sparks generated by the liquid inlet and outlet are controlled separately, thereby solving the problem of causing explosions here.

The present application provides a smart energy industry internet data management method, system, medium and server, which relates to the technical field of data management, wherein the method includes the steps of first data acquisition and processing, first modeling, first model training and first production forecasting; the system includes a data acquisition and processing module, a modeling module, a model training module and a production forecasting module. When predicting the production value, the present application uses a white box model to extract features based on physical laws and chemical reaction principles, further improving the prediction accuracy.

This invention provides a method, apparatus, equipment, and medium for predicting oil and gas field flow data. The oil and gas field flow correction method includes the following steps: S1, acquiring and preprocessing wellhead data of oil and gas wells; S2, identifying influencing factors of wellhead flow data by analyzing the correlation between the wellhead data and wellhead flow data; S3, identifying influencing factors of wellhead flow data by analyzing the correlation between the wellhead data and wellhead flow data; S4, establishing a hybrid virtual metering model of oil and gas wells based on the aforementioned mechanism model, and labeling the characteristic variables of the hybrid virtual metering model according to the influencing factors; S5, predicting wellhead flow data based on the hybrid virtual metering model. This invention, by using existing data for mining and analysis, can achieve accurate measurement of wellhead flow, replacing the current complex back-matching mechanism, and can enhance the core competitiveness in the field of efficient oil and gas field development.

The present invention provides a natural language knowledge extraction method and device based on the collaboration of large and small models, which relates to the field of data processing technology. After converting a natural language text file into a vector format, it is input into a pre-constructed small model, and a recognition result is output, thereby determining the event indicated by the text file. Among them, the small model optimizes the parameters of the neural network based on the circular energy flow optimization algorithm, which enhances the adaptability and stability of the network at different training stages. In addition, it is constructed using an extreme learning machine classification algorithm based on a dynamic weight adjustment mechanism to improve the accuracy of classification. The training sample set for training the small model is constructed after event extraction from the initial sample set by a large natural language model. The present invention uses a large model to perform preliminary event extraction and refined training of the small model, which can efficiently process a large amount of data while maintaining high accuracy, especially in the extraction of specific events and entities.

The invention discloses a long-distance reasoning method and related equipment based on a large model and symbolic logic, and the method comprises the steps: firstly building a knowledge base and a fact database at a data level, and enabling the knowledge base to comprise stable conceptual knowledge, rules and the like; taking the input problem as a trigger for reasoning initiation, performing semantic understanding on the input problem by the large model, and performing automatic planning of reasoning steps to form a plurality of reasoning sub-targets; searching most relevant rules or knowledge for each sub-target through a searching technology; meanwhile, interacting with a database, and extracting related fact data; performing short-distance deductive reasoning by the large model according to the reasoning target, the fact data and the rule of the subtask, and returning a reasoning result; and finally, a returned inference result (Inference) is added to the next step after being checked, and inference of the next sub-target is started. According to the scheme, the reliability and interpretability of large-model long-distance reasoning can be improved.

The invention relates to a capacitor protection structure and a capacitor, and relates to the technical field of capacitors. The capacitor protection structure comprises a shell, an upper cover and an electrode terminal. One end of the shell is opened and an accommodating cavity is formed in the shell. A capacitor core group is arranged in the accommodating cavity. The upper cover is arranged at the opening end of the shell in a covering mode, and the upper cover is of a thin plate structure. The electrode terminal comprises a seat body and an insertion rod, the seat body is fixed in the accommodating cavity and is electrically connected with the capacitor core group, and one end of the insertion rod penetrates through the upper cover and is inserted into the seat body. When the upper cover protrudes, the upper cover can drive the plug to move towards a first direction, and the first direction corresponds to the direction, away from the base body, of the plug rod. The capacitor protection structure can improve the problem that explosion is easy to occur when the internal pressure of the capacitor is increased, and improves the safety of the capacitor.

The embodiment of the invention provides a data processing method and device, equipment and a computer readable storage medium. The method comprises the steps that in response to a setting instruction acting on a data query interface, query information is determined; when the query information indicates that the to-be-queried data table is a first wide table, in response to a query instruction acting on the data query interface, querying in the first wide table to obtain target data corresponding to the query information; wherein the number of the first service fields in the first wide table is equal to the maximum value in the number of the first attribute fields corresponding to the event fields. According to the embodiment of the invention, the data redundancy of the wide table model can be reduced, and the data query efficiency is improved.

The application provides a WGAN-based FRP sheet and concrete interface bonding slip model generation method, which can automatically, quickly and accurately obtain the bonding slip model and has a wide application prospect. After the automatic and rapid acquisition of the bonding slip model, the bonding performance between the FRP sheet and the concrete can be accurately reflected, and a safe and reliable reinforcement component design calculation method can be established. The WGAN is used to predict the strain, so that the training process can be simplified and the training can be stable. The WGAN can replace the traditional experimental analysis to quickly and accurately establish a bonding strength model. The LSTM is used as the generator of the WGAN model, so that the gradient disappearance and explosion problems of the RNN are solved, and the strain data related to time can be more accurately predicted. The CNN is used as the discriminator of the WGAN model, so that the quality and convergence speed of the generated samples are improved.

The invention discloses an air conditioner, a control method, a control device and a storage medium. The air conditioner comprises an indoor fan, a live part and an air pressure detection assembly, wherein the indoor fan communicates with the live part through a first air duct; the air pressure detection assembly is configured to collect the first air pressure of the indoor fan and the second air pressure of the first air duct and control the electrification part to be powered on and powered off according to the difference value between the first air pressure and the second air pressure. The air pressure switch is arranged between the air pressure detection assembly and the live part, so that the air pressure switch can detect the pressure difference in the first air duct, when it is detected that the pressure difference is reduced, it is indicated that the indoor fan breaks down, airflow blown out by the indoor fan cannot cool the live equipment or take away leaked refrigerants, and the indoor fan is prevented from breaking down. At the moment, the wind pressure switch controls the live part to be powered off, so that the live part can be prevented from exploding due to ignition of refrigerants caused by power-on ignition.

The application discloses a behavior fingerprint digital feature extraction method, system, medium and equipment, and the method comprises the following steps: acquiring a behavior fingerprint sequence of a user and extracting digital feature information of the user, constructing a digital feature vector matrix for a to-be-matched user set and a known user set respectively, extracting a feature vector set of the user for the acquired behavior fingerprint sequence of the user, calculating the similarity distance between the digital feature vector of the known user and the digital feature vector of the to-be-matched user based on a similarity distance formula, and judging the identity of the user according to a preset matching strategy. The application expands the behavior fingerprint of the user, solves the problem of the sparsity of the behavior fingerprint of the user to a certain extent, and achieves the effect of improving the recognition accuracy.

The invention discloses a network model training method and system for spiking neurons based on multi-synaptic connection, and the method comprises the steps: obtaining a training data set, and enabling the training data to comprise any one of image data, audio data and electroencephalogram data; constructing spiking neurons in multi-synapse connection for simultaneously encoding intensity information and time information of an input signal, wherein the input signal is an image, audio or electroencephalogram signal input into the spiking neurons in multi-synapse connection; constructing a network model of spiking neurons based on multi-synaptic connection; constructing a target gradient substitution function of the spiking neurons in multi-synaptic connection; and based on the target gradient substitution function and the training data set, training a network model of spiking neurons based on multi-synaptic connection in a back propagation mode. The stimulation intensity information and the time information can be coded at the same time, and the classification accuracy of the network model is improved.

The present invention provides a urinary stone detection and classification method based on an improved Faster RCNN algorithm. The method comprises the following steps: ① inputting CT images of patients with urinary stones; ② extracting features through a ResNet network; ③ fusing the features extracted from different stages of the ResNet network; ④ using a convolutional attention mechanism to weight the fused features to form a new feature map; ⑤ the new feature map generates a candidate frame through an RPN network; ⑥ the new feature map and the candidate frame obtain a fixed-size feature map through an ROI network; ⑦ classifying and locating stones through a prediction module. The present invention integrates the shallow features and deep features of the image, reduces the missed diagnosis rate of stones, improves the detection performance of the urinary stone detection and classification model based on the Faster RCNN algorithm, realizes the prediction of stone composition before surgery, assists doctors in selecting appropriate treatment plans, reduces the pain and burden of patients, and has clinical application value.