4823results about "Hydro energy generation" patented technology

The invention discloses a water turbine operation state monitoring method based on digital twinning, which comprises the following steps: collecting vibration and pressure signals of limited measuring points of a water turbine in real time to form observation data; establishing a physical constraint Fourier operator network based on the observation data, and obtaining an operation state prediction result; performing data assimilation processing on a prediction result by using the observation data as a constraint condition through an iteration set Kalman smoother; the Fourier operator network is corrected through feedback of an optimization estimation result; and reconstructing vibration and pressure states of unmeasurable positions of the water turbine, realizing state field reconstruction, and judging abnormal positions and types. Accurate monitoring and real-time abnormity early warning of the running state of the water turbine can be achieved, and the monitoring accuracy and stability are improved.

The invention relates to the field of hydroelectric generation automation control, discloses an intelligent flow-pressure double closed-loop control method and system for a water inlet ball valve of a water turbine, and aims to solve the technical problems that flow stability and pressure fluctuation suppression are difficult to consider, dynamic response is delayed and working condition adaptability is poor in existing single-loop control. The method comprises the steps that inlet pressure and flow data are collected in real time through a pressure sensor and an ultrasonic flowmeter, a cascade structure of outer ring flow control and inner ring pressure control is constructed in combination with working condition parameters such as the rotating speed of a unit and the opening degree of a guide vane, and a working condition self-adaptive weight distribution module is introduced to dynamically adjust the double-ring gain coefficient; meanwhile, a feed-forward compensation mechanism and an optimal efficiency curve database are fused, and dynamic matching of set values and advanced response of load instructions are achieved. The system comprises a data acquisition unit, a double-closed-loop control unit, a weight distribution unit, an electro-hydraulic servo execution mechanism and a safety interlocking module, and supports microsecond-level gain updating and high-precision valve position control. According to the technical scheme, the adjusting precision and the response speed of the water turbine under the complex working condition are remarkably improved, the actual measurement efficiency is improved by 2.5%-4.8%, the adjusting time is shortened to be within 3 seconds, the positioning precision reaches + / -0.5 degree, and safe and stable operation of the system is guaranteed.

The invention belongs to the technical field of hydropower station monitoring and early warning, and particularly relates to a hydropower station intelligent inspection and fault early warning linkage method, which comprises the following steps: arranging a redundant sensor network at key equipment parts, synchronously acquiring pressure, flow, vibration and water turbidity data, establishing a flow-pressure loss reference relationship, and calculating real-time pressure-flow ratio deviation; performing spectral analysis on the vibration signals, extracting characteristic frequency band energy, performing collaborative study and judgment in combination with a turbidity change trend, and ensuring data credibility through data cross validation of main and auxiliary sensors; performing time sequence difference operation on the pressure-flow ratio deviation to obtain a change rate, fusing vibration-turbidity abnormal performance, and comprehensively diagnosing water diversion blockage or foreign matter invasion; early warning levels are divided according to the deviation and the change rate, corresponding response measures are triggered, response actions are executed according to a preset risk priority sequence, and linkage control of the whole process from state sensing, anomaly recognition, fault diagnosis to intelligent response is achieved.

A gate linkage control method and device and a parallel water supply and power generation system are provided. The method comprises the following steps of: acquiring current gate opening degree information of the parallel water supply and power generation system and a current water level of a third trunk canal, the current gate opening degree information comprising current first gate opening degree information and current second gate opening degree information; determining a target gate linkage control strategy of the parallel water supply and power generation system according to the current gate opening degree information of the parallel water supply and power generation system and the current water level of the third trunk canal; and controlling a gate opening degree of a target gate according to the target gate linkage control strategy of the parallel water supply and power generation system.

The invention discloses a pumped storage unit fault diagnosis method based on multi-modal data fusion, and the method comprises the steps: collecting a voiceprint signal, an infrared thermal imaging image and historical operation data of a pumped storage unit, and carrying out the noise reduction of a voiceprint set through employing an improved unscented Kalman filtering algorithm, a COMRes + model is used to train the voiceprint signal after noise reduction and historical operation data, a future voiceprint signal is predicted, an improved Deeplabv3 + model is used to train an image set, and features of an infrared thermal imaging image are extracted; the voiceprint feature, the historical operation data text feature and the image feature are input into an improved CentraNet model for multi-modal data fusion, and a fault category is output through a classification recognition module, so that diagnosis of the pumped storage unit fault is completed; according to the method, through fusion of the multi-modal data and optimization of the deep learning model, the accuracy and efficiency of fault diagnosis can be effectively improved, and a powerful guarantee is provided for safe operation of the pumped storage unit.

The invention particularly discloses a visual monitoring system and an analysis method for the abrasion state of an impulse turbine set, and relates to the technical field of hydroelectric power generation equipment monitoring. The device comprises a visual monitoring module, a control module and an abrasion analysis early warning module, the visual monitoring module collects images through an industrial camera, an LED light source, a packaging protection structure and a water and mist removing device. The control module formulates an imaging mechanism according to working conditions such as strong water mist interference, idling no water, static no water and the like, and is linked with a unit PLC control system to realize imaging triggering, state adjustment and data interaction; and the abrasion analysis and early warning module identifies an abrasion area through a U-Net + + algorithm, calculates abrasion parameters based on a multi-view vision technology, grades the abrasion parameters, predicts a trend by adopting an ARIMA model, and recommends a maintenance scheme through rule reasoning in combination with threshold early warning. Automatic and intelligent monitoring and analysis of the abrasion state of the impact type unit are achieved, and guarantee is provided for safe and efficient operation of the unit.

A curtain grouting reinforcement method for a tunnel group in a deep backfill area, and a reinforcement effect assessment method. The reinforcement method comprises the following steps: S1, calibrating hole positions according to design; S2, mounting a drilling rig; S3, drilling holes; S4, burying orifice pipes; S5, performing grouting; S6, sealing the holes; and S7, performing the next drilling and grouting cycle. Investment saving and safe and efficient construction are achieved, tunnel surrounding rocks can be fully reinforced, engineering geological conditions are improved, tunnel cavern stability is good, and ground surface settlement is small. The reinforcement effect assessment method comprises an inspection-hole drilling method, multi-wave and multi-component engineering seismograph inspection, assessment based on a high-definition drilling video, assessment based on soil and stone mixture parameter changes before and after grouting, etc., such that multi-angle comprehensive analysis can be achieved, grouting reinforcement effect assessment is more accurate, and a curtain grouting effect assessment system is further improved, thereby providing research ideas for inspecting and assessing the grouting effect in soil-rock mixed backfill areas.

The invention discloses a construction method applied to underground mine vertical shaft surrounding rock condition improvement. The construction method comprises the steps that a flat working face is cleaned, a temporary water nest is arranged for drainage, the drilling position is projected, and a down-the-hole drill is debugged; rock drilling is conducted according to the designed angle, direction and depth, propelling pressure is adjusted along with the depth, and cleaning and plugging are conducted after hole forming; grouting pipes with holes are used as pipe sheds to be driven into the holes, and are welded into a whole through annular steel bars; single-liquid-slurry and double-liquid-slurry segmented grouting is adopted, and the grouting pressure is controlled; during construction, grout diffusion and stratum deformation are monitored, after surrounding rock consolidation reaches the standard, weak blasting is matched with a small excavator for excavation, and after acceptance inspection is qualified, reinforcing steel bars are bound, formworks are installed, and concrete is poured. Compared with the prior art, the problems of collapse and water gushing of the vertical shaft under the strong weathering and water-rich geology can be solved, and the defects of insufficient supporting strength, grouting uniformity, construction efficiency and long-term stability in the traditional technology are overcome.

The invention discloses a device and method for measuring the abrasion amount of a spray needle of an impulse turbine, and the device comprises a fixed platform which is used for placing the spray needle to be measured, and the spray needle to be measured is provided with a plurality of points to be measured; the inner and outer slide rails are arranged at the top of the fixed platform, are positioned on the outer side of the to-be-measured spray needle and axially coincide with the to-be-measured spray needle; the rotating platform is in sliding connection with the inner and outer sliding rails and can rotate around the to-be-measured spray needle; the telescopic platform is arranged at the top of the rotating platform, and the end, away from the rotating platform, of the telescopic platform is connected with an inclined platform; the distance measuring probe system is detachably connected to the inclined platform, and the measuring end of the distance measuring probe system faces the to-be-measured spray needle; the measuring device is combined with a multi-degree-of-freedom adjusting mechanism to realize accurate positioning and vertical alignment of the probe, then the probe system is used for reading the displacement and deducting the thickness of the sleeve to obtain the real abrasion depth, non-destructive high-precision abrasion amount detection of any point of a complex curved surface can be realized, and the measuring device is suitable for a hydropower station overhaul site.

The invention provides a tool applied to the field of petroleum drilling, and particularly relates to an underground non-circular gear intelligent impact tool which comprises a power module, an axial impact module and a circumferential impact module, the power module enables drilling fluid to impact a turbine in a directional mode through a drainage disc, hydraulic energy is converted into mechanical energy, and the mechanical energy is transmitted to the axial impact module. The power is transmitted to the axial impact module and the circumferential impact module, the axial impact module lifts a rack punch hammer to compress a spring through meshing of an incomplete gear and the rack punch hammer, and when the incomplete gear is disengaged from the rack punch hammer, the spring releases energy to generate axial impact downwards. The circumferential impact module is composed of two groups of incomplete gears and racks which are arranged in an up-down 90-degree staggered mode, the rack punch hammer compresses a spring through meshing of the incomplete gears and the rack punch hammer, and the spring is released to generate circumferential impact when the incomplete gears and the rack punch hammer are disengaged. Periodic impact can be achieved, the mechanical rock breaking efficiency is effectively improved, and the stick-slip phenomenon at the drill bit is reduced.

The invention relates to the technical field of pumped storage power station water diversion systems, and discloses a method and device for determining a pressure pipeline reinforcement ultra-high performance concrete lining structure. The method comprises the steps that internal pressure information, radius information and lining thickness information of a target water channel, the design tensile strength of a tensile steel bar, the tensile stress borne by ultra-high performance concrete and the lining section area per unit length are obtained; calculating circumferential stress information of the target water channel based on the internal pressure information and the radius information; based on the circumferential stress information and the lining thickness information, the tensile force resultant force of the lining section in unit length is determined; determining the total sectional area of the tensile steel bars based on the tensile resultant force of the section of the lining in unit length, the designed tensile strength of the tensile steel bars, the tensile stress of the ultra-high performance concrete and the section area of the lining in unit length; determining the number of to-be-assembled reinforcements based on the total sectional area of the tensile reinforcements; and the pressure pipeline reinforcement ultra-high performance concrete lining structure is determined based on the number of the to-be-assembled steel bars and a preset steel bar arrangement rule.

The invention belongs to the field of automatic control of hydroelectric generating sets, and particularly discloses a primary frequency modulation optimization control method and system based on power opening nonlinear prediction.The method comprises the steps that frequency deviation is converted into primary frequency modulation power variable quantity, the power variable quantity and a basic power set point of a set are added, and a dynamic power target is obtained; integrating the power deviation signal to obtain a power integration opening reference instruction; taking the dynamic power target and the unit water head as input of a feed-forward model, and obtaining a feed-forward dominant opening instruction; the opening degree deviation value is input into a PID controller, and a feedback opening degree correction instruction is generated; and a guide vane opening given value is obtained based on the feed-forward dominant opening instruction and the feedback opening correction instruction and serves as a given signal of a guide vane position control loop. According to the invention, through nonlinear prediction and a unique feedback structure, high self-adaption to the working condition change of the unit is realized, and the rapidity, consistency and robustness of the primary frequency modulation response of the unit are remarkably improved.

The invention provides a water turbine guide vane spraying control method and system based on a neural network model, and relates to the technical field of water turbine guide vane coating spraying, and the method comprises the steps: obtaining historical operation state data when a water turbine guide vane works; initial spraying thickness information is determined based on historical operation state data when the water turbine guide vane works; performing secondary spraying on the preliminarily sprayed test water turbine guide vane on the basis of the secondary test spraying information of each wear area, and acquiring operation state data of the secondarily sprayed test water turbine guide vane during working; determining a target spraying scheme based on the operation state data of the test water turbine guide vane during working after secondary spraying; and based on the target spraying scheme, spraying control over the graphene ceramic coating is conducted on the water turbine guide vane of the product line. According to the method, the adaptive graphene ceramic coating spraying scheme can be accurately formulated according to the actual abrasion state of the water turbine guide vane.

The utility model discloses vertical shaft hydroelectric power generation equipment which comprises a power generation module and a power output module, the power generation module comprises a floating platform, a power generator and a power input shaft, the power input shaft is vertically arranged and arranged on the floating platform in a swinging mode, the power generator is arranged on the floating platform, and a motor shaft of the power generator is in transmission connection with the power input shaft; the driving module comprises a water wheel assembly, the water wheel assembly comprises a plurality of blades, the blades are distributed around the rotating axis of the water wheel assembly, and the water wheel assembly is connected with the power input shaft; the counterweight assembly comprises a connecting rod, a rotating seat, a first anchor chain and a first counterweight part, the lower end part of the connecting rod is rotatably arranged on the rotating seat, and the first anchor chain is connected between the rotating seat and the first counterweight part; the upper end of the connecting rod is connected to the bottom of the water wheel assembly. The power generation efficiency of the hydroelectric power generation equipment is improved.

The invention discloses a pumped storage power station model construction method based on digital twinning, relates to the technical field of power system modeling and intelligent control, and is used for solving the problem of low modeling precision of a unit operation state. According to the method, uniform space-time criterion and asset semantic graph driven twinborn observation frames are constructed, consistent mapping of multi-source heterogeneous data and a pumped storage unit structure is established, fine modeling of a working condition state and a safety boundary is realized, on the basis, an online assimilation mechanism and a sub-scene baseline model set are fused, and the working condition state and safety boundary of the pumped storage unit are improved. Continuous self-correction of hydraulic, electromechanical and control parameters under disturbance of different working conditions is achieved, then a time delay budget-driven hierarchical assembly mechanism is introduced, a high-fidelity model and a data-driven model are dynamically called according to scenes, the prediction precision and response efficiency are improved, the out-of-limit risk is avoided through linkage of uncertainty labeling and a conservative mode, and the reliability of the system is improved. And closed-loop iterative updating is formed based on simulation verification and gray rollback, so that synchronous improvement of model credibility, strategy robustness and power station operation economy is realized.

The invention discloses an ultra-deep vertical shaft crawler-type shaft sinking hanging scaffold system and a using method thereof. According to the system, a crawler climbing mechanism is arranged in a crawler mounting space on a shaft sinking hanging scaffold; the supporting base is installed on the outer circle face of the crawler belt supporting disc. The track oil cylinder and the swing connecting plate are connected to the supporting base and are connected with the track trolley through the trolley body connecting frame; the anti-skid tight supporting mechanism is arranged in a supporting shoe mounting space on the sinking hanging scaffold; the anti-skid tight supporting mechanism comprises a guide support and a telescopic supporting shoe assembly. The guide supporting assembly comprises a heightening support and an inner guide supporting plate. The gripper oil cylinder is connected with the anti-skid gripper through the guide connecting plate, and the inner guide supporting plate guides the movement of the outer guide connecting plate. The method comprises the following steps: fixing a construction position by jointly supporting a well wall through crawler climbing and an anti-slip supporting mechanism; and the crawler climbing mechanism is used for driving the whole sinking hanging scaffold to lift and move in a well. The shaft sinking hanging scaffold can continuously move in a shaft, and the lifting efficiency is remarkably improved compared with a stepping type shaft sinking hanging scaffold.

The invention discloses a displacement monitoring device for a fast gate of an impedance type surge chamber, and relates to the technical field of hydraulic engineering, the displacement monitoring device comprises a steel wire rope, a steering assembly, a swing arm assembly and a displacement sensor, the steering assembly comprises a pulley yoke and a first fixed pulley, and the pulley yoke is installed on a surge chamber platform and arranged over the fast gate in an opposite mode; the first fixed pulley is installed on the pulley frame, the swing arm assembly comprises a swing arm, a swing arm frame, a second fixed pulley and a hydraulic damper, the swing arm frame is installed on the surge chamber platform, the hinged end of the swing arm is installed on the swing arm frame, the second fixed pulley is installed at the swing end of the swing arm, and the hydraulic damper is connected between the swing arm frame and the swing arm; the displacement sensor is arranged on the surge chamber platform; the lower end of the steel wire rope is connected to the quick gate, the upper end of the steel wire rope extends to the water surface and sequentially bypasses the first fixed pulley and the second fixed pulley to be connected to the displacement sensor, and the displacement sensor is used for obtaining displacement of the upper end of the steel wire rope to monitor vertical displacement of the quick gate.

The invention relates to the technical field of water turbine design and simulation, in particular to a water turbine guide vane structure optimization design method, system and device and a medium, and the method comprises the steps that a multi-physical field coupling simulation model of a guide vane working environment is built and solved, and guide vane multi-working-condition performance data is obtained; on the basis of the multi-working-condition performance data, a mixed agent model for predicting guide vane performance statistical characteristics is constructed in combination with self-adaptive test design and uncertainty quantitative analysis; performing multi-objective collaborative optimization on the design parameter set of the guide vane and sealing system by using the mixed agent model to generate a robustness optimization solution set; based on the robustness optimization solution set and guide vane dynamic characteristics extracted from the multi-working-condition performance data, dynamic modeling and parameter calibration are carried out on the sealing system; and performing simulation verification and sensitivity analysis on the robustness optimization solution set, and outputting a parameterized design result. The method aims at improving simulation fidelity, optimization efficiency and robustness of optimization design of the guide vane structure of the water turbine.

A floating power-generation group comprises a floating hub such as a spar buoy that is anchored to subsea foundations by anchor lines. Floating power producer units such as wind turbines are connected electrically and mechanically to the hub. The power producer units are each moored by mooring lines. At least one mooring line extends inwardly toward the hub to effect mechanical connection to the hub and at least one other mooring line extends outwardly toward a subsea foundation. The groups are combined as a set whose hubs are connected electrically to each other via subsea energy storage units. Anchor lines of different groups can share subsea foundations. The storage units comprise pumping machinery to expel water from an elongate storage volume and generating machinery to generate electricity from a flow of water entering the storage volume. The pumping machinery can be in deeper water than the generating machinery.

The invention provides a multi-task comprehensive utilization system and method for a low-water-head high-variable-amplitude pumped storage power station. The multi-task comprehensive utilization system comprises an upper reservoir, a lower reservoir, a diversion tunnel, a pumped storage unit, a communicating pipeline and a peripheral water distribution main line. The upper reservoir and the lower reservoir simultaneously have a water supply function and a function of guaranteeing operation and power generation of the pumped storage unit; monitoring water level changes of the upper reservoir and the lower reservoir in real time through an intelligent monitoring system to obtain a water head difference; the water quantity of the upper reservoir and the lower reservoir is dynamically dispatched according to the water head difference, the water supply requirements of areas around a project are met preferentially, and meanwhile safe and stable operation of a power grid is guaranteed as much as possible. According to the invention, a multi-objective genetic algorithm is used to optimize power generation, water supply and ecological benefit objectives; meanwhile, excavated earthwork is processed and treated to serve as building aggregate, the ecology is improved through the water surface of the power station, and local economy is promoted. According to the method, multi-task cooperation of water supply, power generation, aggregate supply, ecological improvement and economic development is achieved, the comprehensive benefits of engineering are improved, and sustainable development is promoted.

A gate linkage control method and device and a series water supply and power generation system are provided. The method comprises the following steps of: acquiring a water demand and current water level information of the series water supply and power generation system, the current water level information at least comprising current riverway water level information and current water diversion trunk canal water level information; determining a gate opening degree control strategy of a first water diversion gate and a second water diversion gate according to the water demand and the current water level information of the series water supply and power generation system; and carrying out linkage control on the first water diversion gate and the second water diversion gate according to the gate opening degree control strategy.

The invention provides a system platform and method for checking adjustment characteristics of a control system based on semi-physical simulation, and belongs to the technical field of power system control equipment detection. The system comprises an all-digital real-time simulation system (ADPSS), a water turbine governor to be tested, a physical interface communication module, a wave recording device and a signal interaction module. A full-electromagnetic example model constructed based on PSASP is built in the ADPSS, a closed-loop detection environment is constructed through the physical interface communication module and a water turbine governor to be detected, bidirectional signal transmission is achieved through the signal interaction module, and key parameters are recorded through the wave recording device. The method comprises the steps of simulation environment establishment, signal interactive transmission, multi-dimensional detection and check and result judgment and output. According to the method, multi-dimensional checking of the speed regulator acquisition and display function, the transfer function consistency, the grid-connected performance and the like and power grid stability influence verification can be completed without field installation, the coverage scene is comprehensive, the checking precision is high, and the method is suitable for performance detection of different types of speed regulators and has remarkable practical value.

The invention discloses a differential early warning method for a water turbine speed regulating system based on data driving, and aims to solve the problems of poor real-time performance, low accuracy, weak adaptability and lack of differential early warning of a traditional method. The method comprises the following steps: collecting data such as guide vane opening and unit frequency in real time, and preprocessing the data through median filtering and Kalman filtering; identifying working conditions by using a rule engine and fuzzy logic and processing according to the working conditions; extracting time domain and frequency domain characteristic parameters, and constructing statistical indexes; integrating statistics, nonlinearity and twinborn simulation to build a threshold model, and combining a production rule, a fault tree and a Bayesian network to build a rule model; and three types of early warning models are constructed, early warning levels are divided according to an expert scoring method, information is pushed, and a differentiation strategy is formulated. The method improves the early warning real-time performance and accuracy, adapts to complex working conditions, and guarantees the safe operation of the hydropower station.

A hydro power generation system may include a powerhouse and an entrance region structure. The powerhouse may include an intake port, a draft port, and a power generator disposed therebetween, the power generator configured to generate electrical power. The entrance region structure may be coupled to the powerhouse and define a portion of a boundary of an entrance region and the natural run-of-the-river portion of a waterway. The entrance region may be distinct from the natural run-of-the-river portion of the waterway and fluidically adjacent to the intake port.

The present application relates to the technical field of water resources and hydropower. Disclosed is a circumferential stiffener assembling device suitable for unequal-diameter penstocks of a pumped storage power station. The circumferential stiffener assembling device comprises: a traveling mechanism (1) capable of being adapted to end faces of penstocks with different diameters, and a circumferential stiffener assembling hanger (2) fitting with outer surfaces of the penstocks with different diameters, wherein the traveling mechanism (1) extends outwards to provide an expansion connecting base (3) connected to the top of the circumferential stiffener assembling hanger (2). The present application has the abilities of position adjustment and movement, and can realize the assembly of circumferential stiffeners with different diameters and different pitches by means of simple adjustment; the circumferential stiffener assembling device travels in a circumferential direction of the penstocks, thereby realizing the assembly of a ring of circumferential stiffener sections; the present application has the function of automatically aligning the circumferential stiffeners during assembly, thus eliminating the procedures of scribing and alignment; and the present application has the ability of automatic seam compression, and can effectively eliminate gaps between the circumferential stiffeners and the outer diameters of penstock walls.

The invention relates to the technical field of hydroelectric generation, in particular to an impulse turbine, a water bucket and a mortise and tenon joint structure for the water bucket and a hub. The water bucket comprises water bucket blades and tenons arranged at the roots of the blades; the shape of the tenon is configured to be movably assembled with a mortise formed in a hub of the water turbine in a fit clearance mode. According to the structure, a movable assembly mode with a fit clearance can be realized, and the water bucket can generate limited displacement in a gradual change clearance under different jet flow impact load conditions, so that the original traditional rigid connection is changed into flexible movable connection. The water bucket can be reliably connected with the hub without depending on welding or bolt fixing, and the common problem that in an original mode, a water head and a hub welding seam are prone to breakage under high-strength water impact force is solved.

The invention relates to the technical field of hydroelectric power generation equipment structure reliability evaluation, and particularly provides a water turbine top cover bolt time-varying reliability evaluation method and device based on parameter sensitivity analysis. According to the technical scheme provided by the invention, key variables are highlighted through parameter sensitivity analysis, and the response surface method and Monte Carlo simulation are combined, so that the calculation efficiency is remarkably improved while the precision is ensured, and the reliability evolution rule of the bolt in the whole life cycle can be scientifically represented; and an important basis is provided for maintenance decision and structure optimization of the water turbine top cover bolt.

The invention discloses a high-rotating-speed hydraulic generator rotor bolt looseness detection method and system, belongs to the technical field of hydropower station high-rotating-speed rotating mechanical equipment detection, and aims at solving the technical problems that hydraulic generator rotor bolt looseness detection is low in efficiency and poor in precision, real-time monitoring cannot be achieved, and safe and stable operation of a hydropower station is seriously affected. According to the invention, the image of the rotor bolt area is collected, and the image is accurately processed by using an image correction algorithm, so that image distortion is eliminated; thirdly, fusing an improved YOLOv8 target detection technology, a DeepLabV3 + semantic segmentation technology and a DeepSort multi-target tracking technology, and accurately extracting angle features of the bolt marking line; and then, a looseness identification objective function is constructed based on the angle change of the bolt, the function is solved in real time, and a detection result is output. According to the invention, high-precision, non-contact and real-time bolt looseness detection is realized, the detection efficiency and reliability are effectively improved, and a solid guarantee is provided for safe operation of a hydropower station.

The invention discloses a hydroelectric generating set rotor acoustic diagnosis method and device based on a space-time joint feature map and a medium, and belongs to the technical field of hydroelectric machines. Generating an acoustic signal with a complete spatio-temporal information mark; forming a preliminary acoustic feature vector; further analyzing the preliminary acoustic feature vectors, and determining phase differences among the acquisition nodes; generating a space-time synchronization acoustic signal subjected to coupling alignment; further feature extraction is carried out on the space-time synchronous acoustic signals subjected to coupling alignment, and a space-time joint feature map used for describing the operation state of the hydroelectric generating set rotor is constructed; and performing automatic analysis on the space-time joint feature map to generate a final fault diagnosis report. According to the method, weighted focusing is carried out on the high-energy disturbance characteristics in the frequency domain and the time sequence dimension in combination with a self-attention mechanism, and the recognition resolution of complex multiple fault modes is improved.