3results about How to "Avoid Engineering Accidents" patented technology

The application provides a deep-sea mining hydraulic lifting pipeline concentration monitoring method and system, and belongs to the field of deep-sea mineral resource development and detection. The application adopts indoor model experiment data and a small amount of field measurement data to construct a transfer learning neural network model, fuses a multi-scale convolution network, a multi-head attention mechanism and a transfer learning algorithm to form a full closed-loop system from indoor laboratory pre-training to deep-sea online precise concentration measurement, so that the purpose of significantly improving real-time monitoring accuracy is achieved. The deep-sea mining hydraulic lifting pipeline concentration monitoring system comprises a source domain data construction and model pre-training subsystem for constructing a land source domain data set and generating pre-training model parameters, and a target domain data acquisition and online transfer monitoring subsystem for acquiring deep-sea target domain data and loading pre-training parameters to perform online monitoring.

The invention discloses a Railway engineering reinforcement cage quality detection method based on Reighting fusion. The method comprises the following steps: calibrating a camera based on Reighting fusion; original images of the railway engineering reinforcement cage are obtained through a camera array and spliced; classifying and marking various types of reinforcing steel bar images in the reinforcing steel bar framework; performing instance segmentation learning based on an artificial intelligence algorithm, and generating a weight file; collecting railway engineering reinforcement cage production and processing image data; reinforcing steel bar framework data in the image are recognized through artificial intelligence; analyzing and extracting steel bar image data, and comparing with design to generate a detection result; and receiving and displaying detection result data through the platform. Geometric information identification is performed on the reinforcement cage based on a deep learning technology, high-precision and high-efficiency non-contact automatic reinforcement cage quality detection is realized through matching with design information, and data accuracy and operation safety are remarkably improved.

The invention provides a method, device and equipment for determining the distance between composite piles under the soil arch effect and a medium, and belongs to the field of civil engineering. The method comprises the steps that physical parameters of a target soil arch and the composite piles are obtained; determining a soil arch curve track according to the physical parameters of the composite pile; when the soil arch is in a limit equilibrium state, determining a first relational expression between the cohesive force and the large principal stress and between the internal friction angle and the large principal stress according to the Mohr-Coulomb theory; the axial force at the arch foot of the large pile is obtained through the soil arch curve track and the sliding force; determining a second relational expression between the axial force and the large principal stress according to the Mohr-Coulomb theory; and according to the first relational expression and the second relational expression, the target relational expression between the physical parameters of the target soil arch and the composite pile and the pile distance is determined, and then the pile distance is determined. Therefore, physical parameters of the soil arches and the piles are comprehensively analyzed, various influence factors are comprehensively considered, scientificity and reasonability of pile spacing design are ensured, accidents caused by unreasonable pile spacing are effectively prevented, and safe operation of engineering is ensured.