16results about How to "Realize online" patented technology

According to the aging detection method for the vehicle sealing strip, the electronic equipment and the vehicle, when the aging detection condition is met, aging detection is carried out, interference of the environment inside and outside the vehicle can be reduced, a compartment acoustic cavity is formed in the space in the vehicle, and the aging detection accuracy is guaranteed. A low-frequency sweep-frequency signal is played to excite a compartment acoustic cavity, a transfer function representing acoustic characteristics in a vehicle is determined in combination with a synchronously collected sound pressure response signal, and lossless, online and quantitative evaluation of the aging state of the vehicle door sealing strip is realized by analyzing the change of the transfer function relative to a health baseline.

The invention provides an online fault early warning method and system based on fluid dynamics of a storage tank floating disc and spectral analysis of a sealing device of the storage tank floating disc, and the method comprises the steps: collecting structure parameters and operation parameters of the storage tank floating disc, and calculating fluid dynamics parameters for the quantitative evaluation of an inclination state, a buoyancy state and a friction state of the storage tank floating disc; collecting a plurality of vibration time domain signals of the sealing device on the floating disc, and converting the vibration time domain signals into frequency domain signals to obtain a frequency spectrum curve; constructing a frequency spectrum feature library based on the frequency spectrum curves in different operation states, comparing the actually monitored frequency spectrum curves with the frequency spectrum feature library, and identifying differentiated frequency spectrum features and corresponding fault types; and performing comprehensive evaluation by combining a quantitative evaluation result of the hydrodynamic parameters and a spectral analysis identification result, thereby realizing intelligent fault early warning of the storage tank floating tray system. The method solves the technical problems that the existing storage tank floating disc operation state monitoring cannot accurately find the early-stage potential fault hidden danger of the floating disc in real time, and floating disc faults and even safety accidents are easily caused.

The invention discloses a multi-grid-connected inverter instability source positioning analysis method and device based on impedance ratio perception, and the method comprises the steps: obtaining the output impedance of a grid-connected inverter and the input impedance of a power grid side through a multi-sine wave injection impedance measurement technology under a dq system in combination with an online impedance measurement strategy of power adaptive stable operation; a multi-grid-connected inverter parameter model is constructed; node equivalent impedance aggregation is carried out through an impedance model obtained through measurement, and node stability analysis based on the impedance ratio is achieved by dividing the two ends of each inverter node into a source sub-module and a load sub-module. According to the method provided by the invention, efficient online positioning of the instability source of the multi-machine system can be quickly and accurately realized, so that the stability of the subsequent system is ensured.

The invention relates to the technical field of power system monitoring, and discloses an icing torsion inversion method, system and device based on a physical constraint neural network, and a medium, and the method comprises the steps: collecting the torsion angle data, environmental parameter data and historical icing thickness data of a transmission conductor; establishing a physical constraint model between the torsion angle and the icing thickness based on a wire mechanics principle; constructing a first neural network based on the physical constraint model, and defining a composite loss function including a data driving loss function and a physical constraint loss function; training a first neural network by using historical icing thickness data, and optimizing network parameters through a back propagation algorithm to minimize a composite loss function; and inputting the torsion angle data and the environmental parameter data into a trained first neural network for prediction to obtain an icing thickness prediction value of the current wire. According to the method, the mechanical physical model is embedded into the neural network training process, so that accurate inversion from the wire torsion angle to the icing thickness is realized.

The present application relates to the technical field of industrial motion control and process control, and provides a method and system for tuning PID control parameters based on an improved genetic algorithm. The method comprises: locally optimizing the nth generation PID control parameter to obtain a first PID control parameter; globally optimizing the first PID control parameter to obtain a second PID control parameter; if the chromosome fitness of the second PID control parameter does not reach a preset fitness threshold, and n is less than or equal to a preset termination evolutionary generation, then repeatedly optimizing the next generation PID control parameter; if the chromosome fitness of the second PID control parameter reaches a preset fitness threshold, or n is greater than a preset termination evolutionary generation, outputting the tuned PID control parameter and terminating the genetic algorithm. The method has a strong global search optimization capability and a fast local search optimization speed, and can realize online or offline self-tuning of PID control parameters.

The application relates to a crystallization-preventing heating pipeline system of a marine urea supply injection device. The pipeline system comprises a pipeline subsystem, an air heating subsystem and a water heating subsystem. The pipeline subsystem comprises an inner pipe for urea flow and an outer pipe sleeved outside the inner pipe, and an annular gap is formed between the inner pipe and the outer pipe. The air heating subsystem is used for sending hot air into the annular gap to heat the inner pipe at the initial stage of cold start. The water heating subsystem is used for sending hot water into the annular gap to replace the air heating subsystem to heat the inner pipe after the engine cooling water temperature reaches a preset value. The dredging subsystem is used for cleaning the outer wall of the inner pipe. The air heating subsystem is arranged to directly heat the urea pipeline by using the waste heat of the engine exhaust at the initial stage of cold start (when the water temperature is lower than 40 DEG C), so that the rapid response of the system is realized, and the crystallization risk is greatly reduced.

The invention discloses a composite separation membrane and a preparation method and application thereof.The composite separation membrane comprises a porous substrate and a composite membrane layer attached to at least one face of the porous substrate, and the composite membrane layer is a GO-PEI composite membrane layer formed by compounding graphene oxide and branched polyethyleneimine; and the GO-PEI composite film layer is of a single-layer or multi-layer structure formed by layer-by-layer overlapping. The composite separation membrane has an ultrathin structure, good mechanical stability and an adjustable transmission channel, can give consideration to permeability and selectivity, and can adapt to various application scenes such as gas separation, seawater filtration / purification, seawater quality detection and the like; meanwhile, a corresponding membrane assembly and device are provided, and engineering use and detection coupling are facilitated.

The present application relates to the technical field of direct current power management and fault monitoring, and discloses a multi-dimensional abnormal early warning monitoring method and system in direct current power management, comprising: configuring a passive induction sheet in the center area of the top surface of the explosion-proof valve of the electrolytic capacitor in the direct current power supply; determining a signal acquisition pair between the passive induction sheet and the cathode of the electrolytic capacitor, and connecting a negative bias ADC channel and a polarity ADC channel in parallel on the signal acquisition pair; monitoring the negative direct current bias signal and the polarity inversion signal of the signal acquisition pair through the negative bias ADC channel and the polarity ADC channel respectively; analyzing the monotone increasing trend of the negative direct current bias signal and the relaxation time of the polarity inversion signal respectively; and realizing early failure warning of the electrolytic capacitor in the direct current power supply based on the monotone increasing trend and the relaxation time. The present application can realize long-term, online and non-interference early warning of the early failure phenomenon of the electrolytic capacitor in the direct current power supply under real working conditions.

The utility model relates to the technical field of modular assembly dust removal, in particular to a modular bag type dust collector, which comprises a plurality of modular box bodies and filter components arranged in the modular box bodies, ultra-low emission filter bags and spring type reinforced bag cages are arranged in the modular box bodies, pulse injection devices are arranged at the upper parts of the ultra-low emission filter bags, and the upper parts of the spring type reinforced bag cages are connected with the pulse injection devices. A smoke inlet and outlet air duct is arranged on the side face of each modular box body, a pneumatic louver valve is arranged on the end face of each smoke inlet and outlet air duct, an ash bucket is arranged at the bottom of each modular box body, and the modular box bodies are the same in structural size and connected through screws. The pulse injection device adopts pulse drainage point-to-point injection, the dust remover adopts a flat strip ultra-low emission filter bag, a spring type reinforced bag cage is adopted, the filter bag and the bag cage are transversely mounted in the modular box bodies, the modular box bodies are connected through bolts and sealing gaskets, the modular box bodies in different numbers are configured, and the dust removal efficiency is improved. The modular box body is freely combined, and installation is convenient.

This invention discloses a method for large-scale online detection and counting of orchard fruits using drones. It utilizes drones to collect video footage of orchards; establishes a drone live-streaming platform for online, real-time video transmission; builds a fruit detection model to perform real-time detection of the drone video footage, obtaining the center point and detection frame position information of each fruit; employs the DeepSORT algorithm to assign a specific ID to each fruit in the drone video footage and tracks them across frames; and constructs a fruit counter to achieve global calculation of the orchard fruit count. This invention overcomes the limitation that drones can only perform offline operations in orchard scenarios, and simultaneously solves the problems of missing small-sized fruits and severely occluded fruits within the drone's field of view, providing farmers with effective information for subsequent decision-making in a short period of time.

The invention discloses a superconducting magnet attitude monitoring and active adjusting system, which relates to the technical field of superconducting magnets and comprises a superconducting magnet arranged in a Dewar. A pressure sensing assembly is directly arranged on a force transmission path of each key pull rod, and a real-time sensing network covering a magnet suspension system is constructed, so that in the dynamic process of cooling, excitation and quench, axial load change of a magnet acting on a Dewar through the pull rods can be directly and continuously captured, and therefore, the axial load change of the magnet acting on the Dewar through the pull rods can be directly and continuously captured. Indirect and accurate monitoring of the real-time change of the posture of the magnet is realized; on the basis, the control box carries out fusion processing and intelligent judgment on load distribution data measured by all the pressure sensing assemblies, and after a load mode representing posture abnormity is recognized, the corresponding adjustment execution assembly is immediately driven to adjust the length or stress state of the specific pull rod. Therefore, a passive risk which is difficult to perceive and intervene in the past is converted into a closed-loop control process which can be monitored in real time and can be corrected actively.

The invention discloses a machine vision driven telescopic pipe defect intelligent identification method and system, and the method comprises the steps: 1, positioning and conveying a to-be-detected suction pipe to a detection station, and enabling the to-be-detected suction pipe to generate circumferential vibration or rotation during conveying; step 2, uniformly illuminating the to-be-detected straw by adopting an arched light source; step 3, acquiring different side images of each to-be-detected straw; step 4, preprocessing the image; 5, dividing the straw defects into wrinkling leakage pipe defects and non-wrinkling leakage pipe appearance defects; wherein the wrinkling leakage pipe type defects comprise sealing wrinkling, ball head wrinkling and leakage pipe; step 6, detecting wrinkled pipe defects by using the suction pipe defect deep learning model; and 7, detecting the appearance defects of the non-wrinkling leakage pipe by using a mean filtering method. According to the invention, the appearance defects of the telescopic suction tube can be automatically and intelligently detected, and the problems of low detection precision and poor robustness caused by light reflection of the surface of the suction tube, a tubular curved surface structure and the like can be solved by adopting the arched light source.

The present invention relates to a method and a device for monitoring the performance of a refractory layer of a high temperature gas treatment system. The high temperature gas treatment system comprises a high temperature gas generating device and a cooling device connected downstream of the high temperature gas generating device, a cooling medium in the cooling device exchanging heat with the high temperature gas from the high temperature gas generating device, the method comprising the steps of: measuring in real time an operating parameter of the high temperature gas treatment system, calculating a heat loss J A of the high temperature gas, calculating a heat load J B of the cooling device, defining a performance index P of the refractory layer as: P=(J A -J B ) / J A , and determining the performance state of the refractory layer according to the magnitude of the P value.

The invention belongs to the field of computer vision, aims to solve the problem of point location planning in application of an industrial robot to paste a cushion block on an end ring, and particularly relates to an end ring pasting point location planning method based on linear structured light scanning. The line structure light sensor is fixed above the rotary table to scan end ring contour data; fitting the circle center of the end ring and calculating angle values of all contour points relative to the circle center; positioning a starting point and an ending point of an end ring gap in the contour data; pasting points of the cushion block along the inner contour of the end ring are symmetrically planned at equal angles relative to the center line of the notch; and calculating the distance between the adjacent pasting points, and iteratively optimizing and planning the point positions to ensure that the point intervals are equal, so that an equal-interval pasting effect is obtained when the end ring has processing deviation. According to the invention, on-line, automatic and non-contact measurement of a nearly-circular object can be realized; equidistant operation on the contour can be realized, and the planning precision is high; the requirement for object machining precision is low, and the system flexibility is good.

This invention discloses a defect detection method for semi-transparent multilayer film materials. It utilizes a multi-camera setup, combining a line scan camera, a PMD area array camera, and a small-field-of-view CCD camera, along with a robotic arm for flipping to inspect the front and back of the product. A unified coordinate system is established through spatial registration, and a multi-layered composite logic filtering mechanism is employed to identify defects and reject over-detected defects. Specifically, this includes front and back grayscale and morphology data acquisition, spatial coordinate registration, multi-dimensional defect identification, and logical processing for bubble deduplication, dust filtering, and system noise filtering. Simultaneously, multi-focus CCD imaging enables layered defect determination. This invention improves the accuracy of defect detection and discrimination, achieving high-precision and high-reliability detection of defects in semi-transparent multilayer films, and is suitable for online quality inspection during the production process of semi-transparent multilayer films.

The application discloses a kind of cold-rolled roller chrome plating layer defect repair devices, it is related to metal rolling equipment technical field.The device includes workbench, first supporting roll, load roll, second supporting roll, cold-rolled roller, repair device and shroud;Repair device includes support, recess, driving motor, screw rod, slot block and composite repair execution mechanism.Support is fixed to the side of cold-rolled roller, and composite repair execution mechanism can be moved radially by driving motor.Three load-bearing structures that can move synchronously in axial direction are integrated in composite repair execution mechanism, respectively carrying online detection module, laser cleaning head and cold spraying deposition head, and loading assembly that can automatically adjust angle is arranged on each load-bearing structure.It is close to cold-rolled roller when repairing, scanning and identifying defects, and driving laser cleaning head and cold spraying deposition head to clean and deposit repair defects in turn.The application realizes the online, automatic repair of cold-rolled roller, shortens maintenance time, and guarantees the continuity of rolling production.