Abstract: A method and device for blast furnace state monitoring based on multi-modes fusion. In the process of blast furnace state monitoring, the concept of sub-mode is introduced, and the method for pre-acquisition and multi-modes weighted fusion by sub-mode is proposed to monitor blast furnace state. After preprocessing the main parameter data of the blast furnace, several sub-modes of the blast furnace and their corresponding blast furnace state indication variable data are obtained by means of a mean shift clustering algorithm. Taking the real-time parameter data of the blast furnace as inputs, the Euclidean distance between the real-time parameter data of the blast furnace and each sub-mode is calculated, and the sub-modes are weighted and fused according to the distance, and the fusion result is the real-time blast furnace state, so as to realize the real-time state monitoring of the blast furnace in a smooth operation.

Abstract: A method and device for blast furnace state monitoring based on multi-modes fusion. In the process of blast furnace state monitoring, the concept of sub-mode is introduced, and the method for pre-acquisition and multi-modes weighted fusion by sub-mode is proposed to monitor blast furnace state. After preprocessing the main parameter data of the blast furnace, several sub-modes of the blast furnace and their corresponding blast furnace state indication variable data are obtained by means of a mean shift clustering algorithm. Taking the real-time parameter data of the blast furnace as inputs, the Euclidean distance between the real-time parameter data of the blast furnace and each sub-mode is calculated, and the sub-modes are weighted and fused according to the distance, and the fusion result is the real-time blast furnace state, so as to realize the real-time state monitoring of the blast furnace in a smooth operation.

Abstract: A method for predicting burning through point (BTP) based on an encoder-decoder network is provided, which belongs to a field of soft-sensing modeling in an industrial process. A BTP prediction model based on the encoder-decoder network with a temporal attention mechanism and a spatial attention mechanism is developed according to data acquired during an operation of a sintering machine, where the temporal attention mechanism is used to characterize temporal dynamics of samples, and the spatial attention mechanism is used to capture a correlation between an object variable and an advanced feature, to improve accuracy and robustness of the model. With the model, BTP in a sintering process can be predicted in real time, which has great practical significance for on-site process guidance and parameter adjustment.

Abstract: Disclosed is a method for estimating a blast furnace throat temperature based on a multilayer ore-to-coke ratio distribution model. According to the method, blast furnace equipment parameters and a burden distribution matrix are utilized, the burden layer profile of each layer is calculated according to the burden distribution movement process, a burden layer distribution model is established in combination with the descending process, and the ore-to-coke ratio of each burden layer is obtained. According to the method, the ore-to-coke ratio distribution of multiple layers and main parameters of a blast furnace are used as input, a generalized regression neural network is used for estimating the temperature at the corresponding measurement position of throat temperature, so as to realize the monitoring of throat temperature in the blast furnace process.

Abstract: A text error correction method and a text error correction apparatus based on a recurrent neural network of artificial intelligence are provided. The method includes: acquiring text data to be error-corrected; performing error correction on the text data to be error-corrected by using a trained recurrent neural network model so as to generate error-corrected text data.

Abstract: The present disclosure discloses a method for deriving fault diagnosis rules of a blast furnace based on a deep neural network, which relates to the field of industrial process monitoring, modeling and simulation. Firstly, a deep neural network is used to model historical fault data of the blast furnace. Then, for each kind of fault, the process starts from the output layer of the network, wherein sub-models of nodes in the adjacent layers in the deep neural network are established by using the decision tree in sequence, and the if-then rule is derived. Finally, the if-then rules are merged layer by layer, so as to finally obtain fault diagnosis rules of the blast furnace with blast furnace process variables being the rule antecedents and with fault categories being the rule consequents.

Abstract: Embodiments of the present invention provide a signal processing method and device. The method includes: receiving soft information corresponding to encoded signals sent by at least two base stations and CRC check results of decoding results of first subflows in the encoded signals, where the soft information includes first soft information corresponding to the first subflows; obtaining a selective combining result of the first subflows by performing selective combining according to the at least two CRC check results of the decoding results of the first subflows; and if the selective combining result of the first subflows is that CRC check is incorrect, determining a soft combining result of the first subflows according to at least two pieces of the first soft information. The signal processing method and device provided in the embodiments can increase a signal gain.

Abstract: A text error correction method and a text error correction apparatus based on a recurrent neural network of artificial intelligence are provided. The method includes: acquiring text data to be error-corrected; performing error correction on the text data to be error-corrected by using a trained recurrent neural network model so as to generate error-corrected text data.

Abstract: The present invention relates to a network device, a terminal device, and a voice service control method, a frame type of voice data is determined, and therefore, a voice service of the network device may be disconnected when no speech frame time exceeds set time, which prevents an economic loss caused by a non-talking call maintained for a long time, thereby saving a resource of an operator network, and improving utilization efficiency of the operator network.

Abstract: Embodiments of the present invention provide a signal processing method and device. The method includes: receiving soft information corresponding to encoded signals sent by at least two base stations and CRC check results of decoding results of first subflows in the encoded signals, where the soft information includes first soft information corresponding to the first subflows; obtaining a selective combining result of the first subflows by performing selective combining according to the at least two CRC check results of the decoding results of the first subflows; and if the selective combining result of the first subflows is that CRC check is incorrect, determining a soft combining result of the first subflows according to at least two pieces of the first soft information. The signal processing method and device provided in the embodiments can increase a signal gain.

Abstract: Embodiments of the present disclosure provide a signal processing method and device. The method includes: receiving soft information corresponding to encoded signals sent by at least two base stations and CRC check results of decoding results of first subflows in the encoded signals, where the soft information includes first soft information corresponding to the first subflows; obtaining a selective combining result of the first subflows by performing selective combining according to the at least two CRC check results of the decoding results of the first subflows; and if the selective combining result of the first subflows is that CRC check is incorrect, determining a soft combining result of the first subflows according to at least two pieces of the first soft information. The signal processing method and device provided in the embodiments can increase a signal gain.

Abstract: The present invention relates to a network device, a terminal device, and a voice service control method, a frame type of voice data is determined, and therefore, a voice service of the network device may be disconnected when no speech frame time exceeds set time, which prevents an economic loss caused by a non-talking call maintained for a long time, thereby saving a resource of an operator network, and improving utilization efficiency of the operator network.

Abstract: Embodiments of the present disclosure provide a signal processing method and device. The method includes: receiving soft information corresponding to encoded signals sent by at least two base stations and CRC check results of decoding results of first subflows in the encoded signals, where the soft information includes first soft information corresponding to the first subflows; obtaining a selective combining result of the first subflows by performing selective combining according to the at least two CRC check results of the decoding results of the first subflows; and if the selective combining result of the first subflows is that CRC check is incorrect, determining a soft combining result of the first subflows according to at least two pieces of the first soft information. The signal processing method and device provided in the embodiments can increase a signal gain.