Abstract: The disclosure relates to a wind turbine blade inspection system and method based on an unmanned aerial vehicle. The system includes: a collection module, used for collecting blade data and surrounding environment data of blades to be inspected, determining feature inspection points of the unmanned aerial vehicle according to the blade data and the surrounding environment data, and generating inspection paths; an inspection module, used for shooting corresponding blade at the feature inspection points according to the inspection paths to obtain a first inspection image and a second inspection image; an analysis module, used for receiving the first inspection image and the second inspection image, analyzing the first inspection image and the second inspection image to obtain a health state of the corresponding blade, and making a maintenance plan according to the health state of each of the blades.

Abstract: The disclosure relates to a wind turbine blade inspection system and method based on an unmanned aerial vehicle. The system includes: a collection module, used for collecting blade data and surrounding environment data of blades to be inspected, determining feature inspection points of the unmanned aerial vehicle according to the blade data and the surrounding environment data, and generating inspection paths; an inspection module, used for shooting corresponding blade at the feature inspection points according to the inspection paths to obtain a first inspection image and a second inspection image; an analysis module, used for receiving the first inspection image and the second inspection image, analyzing the first inspection image and the second inspection image to obtain a health state of the corresponding blade, and making a maintenance plan according to the health state of each of the blades.

Abstract: An experimental apparatus for rock-breaking through vibration impact, including a confining pressure loading assembly, a drill bit, a drill rod, a drilling fluid circulation assembly, a rotary impact assembly and an axial impact assembly. The confining pressure loading assembly is configured to apply pressures to a core sample located in a core cavity in three directions perpendicular to each other. The drill bit is capable of inserting into the core cavity to drill the core sample. The drilling fluid circulation assembly includes a drilling fluid inlet, a drilling fluid outlet and a mud pump connected therebetween. The rotary impact assembly includes a hydraulic rotary motor and a hydraulic swing motor connected to the drill rod, respectively. The axial impact assembly includes a first hydraulic cylinder, and a servo linear actuator connected to the first hydraulic cylinder and the drill rod.

Abstract: An experimental apparatus for rock-breaking through vibration impact, including a confining pressure loading assembly, a drill bit, a drill rod, a drilling fluid circulation assembly, a rotary impact assembly and an axial impact assembly. The confining pressure loading assembly is configured to apply pressures to a core sample located in a core cavity in three directions perpendicular to each other. The drill bit is capable of inserting into the core cavity to drill the core sample. The drilling fluid circulation assembly includes a drilling fluid inlet, a drilling fluid outlet and a mud pump connected therebetween. The rotary impact assembly includes a hydraulic rotary motor and a hydraulic swing motor connected to the drill rod, respectively. The axial impact assembly includes a first hydraulic cylinder, and a servo linear actuator connected to the first hydraulic cylinder and the drill rod.

Abstract: A method and a device for data processing are disclosed. The method includes: acquiring a point sequence including a plurality of coordinate points; interpolating the point sequence and constructing a multi-dimensional data structure tree by using the interpolated point sequence; obtaining a first point sequence by thinning the point sequence and interpolating the thinned point sequence; and obtaining elevations of the first point sequence based on the multi-dimensional data structure tree and the first point sequence.

Abstract: A method for fusing traffic markings includes: obtaining a first local part overlapped with a marking set to be fused from a target marking set and a second local part overlapped with the target marking set from the marking set to be fused; based on a target transformation relationship; generating a first transformed marking set transformed from the first local part and a second transformed marking set transformed from the second local part; determining a first translation parameter capable of fusing the second transformed marking set with the first transformed marking set; determining a second translation parameter by using the first translation parameter based on the target transformation relationship; and moving the marking set to be fused by using the second translation parameter.

Abstract: An integrated injection-molded light includes a light source module and a power supply module. The light source module includes a case with a sealed cavity, a circuit board located in the sealed cavity, and illuminants and electronic components arranged on the circuit board. The power supply module includes a line tube, and a power supply line fixed in the line tube and electrically connected to the circuit board. The manufacturing method includes: electrically connecting the power supply line and the circuit board via a connecting conductive wire; and forming, through injection molding, the line tube that wraps around the power supply line and the case in which the circuit board, illuminants and electronic components are sealed. The case enclosing the circuit board, illuminants and electronic components and the line tube enclosing the power supply line are formed integrally through injection molding. Thus, the light is water-proof.

Abstract: A neural network model conversion method, a server, and a storage medium are provided according to embodiments of the present disclosure. The neural network model conversion method includes: parsing a neural network model to obtain initial model information; reconstructing the initial model information to obtain streaming model information; generating a target model information file according to the streaming model information; and running, under a streaming architecture, the neural network model according to the target model information file.

Abstract: Provided are a conversion method and apparatus for a deep learning model, a server, and a storage medium. The method includes: parsing a target deep learning model into an intermediate representation of an instruction set computation graph; converting the intermediate representation of the instruction set computation graph into an intermediate representation of a data flow computation graph; adjusting the intermediate representation of the data flow computation graph to an intermediate representation of a customized architecture; and obtaining a converted target data flow network model corresponding to the target deep learning model according to the intermediate representation of the customized architecture.

Abstract: Provided are a method for the parallel processing of data, a device, and a storage medium. The method includes: identifying, from multiple first computing nodes, at least three first computing nodes which have a logical relationship are identified and defining the at least three first computing nodes which have the logical relationship as a first parallel node group, where the first parallel node group includes a first preceding node and at least two first subsequent nodes; acquiring a first input data model of the first preceding node and generating a first input tensor of the first preceding node; computing a first output tensor of the first preceding node according to the first input data model and the first input tensor; and acquiring a second input data model of the at least two first subsequent nodes and using the first output tensor as a second input tensor.

Abstract: Provided are a scheduling method and apparatus based on a deep learning node computation, and a storage medium. The scheduling method includes: a to-be-computed node of a preset neural network computation graph is acquired; a node type of the to-be-computed node is determined, where the node type includes a hardware computation node and a software computation node; in a case where the node type is the hardware computation node, the hardware computation node is scheduled to a first queue, and whether a hardware computing power module corresponding to the hardware computation node is occupied or not is determined; and in a case where the hardware computing power module is not occupied, the hardware computation node is input into the hardware computing power module for computing.

Abstract: Provided are a method and device for adjusting a deep learning network, a server and a storage medium. The method includes acquiring an initial data streaming computation graph that includes first operators for computing initial constant expressions; and obtaining a target data streaming computation graph according to parameters in the initial constant expressions. The target data streaming computation graph includes a second operator and is used for controlling a deep learning acceleration chip to perform data computation. The granularity of the second operator is larger than the granularity of a first operator to enable an adjustment of the amount of computation of the deep learning acceleration chip.

Abstract: A neural network model conversion method, a server, and a storage medium are provided according to embodiments of the present disclosure. The neural network model conversion method includes: parsing a neural network model to obtain initial model information; reconstructing the initial model information to obtain streaming model information; generating a target model information file according to the streaming model information; and running, under a streaming architecture, the neural network model according to the target model information file.

Abstract: A plating or coating method for producing a metal-ceramic composite coating on a substrate is provided. The method N comprises adding a sol of a ceramic phase to a plating solution or electrolyte and controlling the pH, degree of mixing, and/or temperature of the plating solution or electrolyte. An item or surface comprising a substrate and a metal-ceramic composite coating on the substrate, the metal-ceramic composite coating comprising a ceramic phase of dispersed amorphous ceramic particles having an average diameter of from 1 to 100 nm is also provided.