538 results about "Hybrid drive" patented technology

The invention discloses a physical and data hybrid driven mechanical arm dynamic model identification method which is characterized by comprising the following steps: S1, acquiring parameters of each axis of a robot, establishing a dynamic model of a mechanical arm, and linearizing the dynamic model according to a minimum inertia principle to obtain a dynamic minimum parameter set and a corresponding regression matrix; s2, an excitation track of the mechanical arm is designed based on the finite Fourier series; s3, the mechanical arm runs the designed excitation track, angles, angular velocities, angular accelerations and torque data of all joints of the mechanical arm in the movement process are collected and filtered, and an observation torque vector and an observation matrix are calculated; s4, performing preliminary estimation on the minimum parameter set by using an iterative reweighted least square method; and S5, aiming at the dynamic characteristics of LuGre friction force in the movement process of the mechanical arm, establishing a mechanical arm dynamic model under physical and data hybrid driving.

The invention discloses a photovoltaic array life prediction method based on hybrid driving of a physical model and data. The method comprises the following steps: defining failure time and residual life of a photovoltaic array; preprocessing data; degeneration trend extraction: separating a trend term, a seasonal term and a residual term of output power through block median filtering and seasonal effect correction, and eliminating the influence of environmental fluctuation on degeneration analysis; residual life prediction based on data driving; parameter prediction based on a physical model: identifying degradation parameters of the double-diode model; a degradation parameter trajectory model is established, an output power attenuation curve is inverted, and the remaining life is predicted; and result fusion: comparing data driving and physical model prediction results, and outputting a final residual life value through weighted average or confidence interval fusion. According to the invention, a set of complete photovoltaic array residual life prediction system is constructed, a whole-process closed loop from data acquisition, mechanism analysis to life prediction is realized, and an efficient and accurate solution is provided for reliability evaluation of a photovoltaic system.

The invention discloses a permanent magnet synchronous motor temperature monitoring method based on digital-analog hybrid drive, and the method specifically comprises the steps: dividing a motor into a plurality of heat source nodes, including a stator winding, a stator tooth part, a rotor core and the like, connecting the nodes through a thermal resistance and thermal capacity network, building a thermal network model of the motor, and carrying out the thermal network model; calculating the initial values of thermal resistance and thermal capacity of each component of the motor, and optimizing parameters in a thermal network model by using a differential evolution algorithm based on the lumped parameter thermal network model and in combination with a data-driven strategy. Furthermore, temperature rise prediction is dynamically adjusted according to motor state data (such as stator current, rotating speed and the like) collected in real time so as to realize real-time temperature estimation. The method is high in temperature estimation precision, does not affect the performance of the motor, is simple in calculation, is good in real-time performance, and has physical interpretability. The temperature rise of the motor can be predicted in real time under different working conditions, early warning is given out, motor faults caused by too high temperature rise are effectively avoided, and the reliability and safety of the motor are improved.

The invention relates to a physical-data hybrid drive vehicle driving state estimation method, and belongs to the technical field of intelligent vehicle chassis dynamics state estimation. Constructing a mapping relation between the state estimation vector and sensor data by adopting a ridge regression method so as to explicitly express a vehicle movement mechanism; secondly, constructing a data driving model to implicitly extract vehicle sensor data features, and constructing an enhanced LSTM neural network with a double-stage attention mechanism as the data driving model; then, performing dynamic weighted fusion on an output result of the physical model and a sensor sample sequence output by the data driving model to realize deep coupling of physical mechanism knowledge and data driving characteristics; according to the method, the superiority of the method compared with other methods is verified through simulation testing and real vehicle testing.

A hybrid drive system for a motor vehicle includes an internal combustion engine supplying first torques via a drive shaft to drive the motor vehicle and an electric machine having a rotor via which second drive torques can be supplied by the electric machine to drive the motor vehicle. An axle drive has an axle drive input gear wheel via which the axle drive can be driven. The system includes a gearbox having a first partial gearbox and a second partial gearbox. The first partial gearbox has a first planetary gear set having a first element, a second element, and a third element, The first partial gearbox also has a second planetary gear set having a fourth element, a fifth element, and a sixth element.

The invention discloses a method for improving hybrid power drive by adding a motor to an automobile engine, and relates to the technical field of automobile hybrid power drive systems, an independent PO motor is added to a gasoline car, and a drive controller, a group of high-capacity power batteries and a 12V DC-DC power supply module are added to the gasoline car. A vehicle networking data interface and a hardware interface of an AI algorithm processing unit are reserved in the vehicle control module, and the system has the advantages that the vehicle networking communication unit and the AI algorithm processing unit are integrated in the vehicle control module, real-time traffic flow, road condition parameters and driving behavior data are collected, a road condition prediction model is constructed by using an LSTM neural network, and the driving behavior data are predicted by using the LSTM neural network. The dynamic power distribution strategy is generated in combination with the driving habits of the user, the defects that in the prior art, an energy management strategy is fixed and cannot adapt to road conditions and driving behavior changes are overcome, fuel consumption is reduced by predicting the energy requirement of the front road condition in advance, and the intelligence and economical efficiency of the hybrid power driving system are enhanced.

The invention relates to a hybrid drive type bionic light-weight nursing mechanical arm which comprises a shoulder joint module, a rope-driven elbow joint module and a rope-driven wrist joint module which are connected in sequence. The shoulder joint module is of a series-parallel structure, a first servo motor directly drives a center linkage platform to achieve forward flexion and backward extension of the shoulder, and a second servo motor and a third servo motor cooperatively drive a closed-loop structure formed by a driven branch chain unit to achieve adduction, abduction, internal rotation and external rotation of the shoulder. The elbow joint module achieves elbow bending and stretching and inward and outward rotation driven by a fifth servo motor through rope wheel transmission and gear meshing. The wrist joint module achieves forward flexion, backward extension, abduction and adduction of the wrist through a rope winding path and bevel gear meshing. Compared with the prior art, the adaptability and efficiency of the mechanical arm in rehabilitation nursing are improved, it is ensured that all the joints can work precisely and cooperatively under multi-degree-of-freedom movement, and the control precision and stability of a driving system are optimized while the high-load bearing capacity is ensured.

The invention discloses a shield tunneling machine attitude prediction method and system, and relates to the field of shield tunneling machine construction.The shield tunneling machine attitude prediction method comprises the steps that firstly, shield tunneling machine construction parameters, geological environment parameters and tunnel planning parameters are obtained and preprocessed, and related characteristics are extracted; secondly, mapping the extracted features into nodes by using a heterogeneous graph model, and updating node features in real time through weighted processing of a graph attention mechanism; then, the node features and the connection relation are input into the trained hybrid drive prediction model, and time sequence, physical and space prediction values of the attitude angle of the shield tunneling machine are obtained; and finally, constructing a Bayesian causal graph to quantify the influence of each factor on the attitude angle, carrying out dynamic weighted fusion based on a quantization result, and outputting a final predicted value and a confidence interval. The problem that the prediction effect is poor under the complex geological condition due to the fact that prediction only depends on single shield tunneling machine parameters in the prior art is solved, and accurate prediction of the attitude angle of the shield tunneling machine can be achieved.

The invention discloses a lithium battery remaining service life prediction method based on an intelligent hybrid drive model, and the method comprises the steps: carrying out the modeling of a long-term degradation trend of a target system through a double-index degradation model (DEDM), and fitting model parameters through a nonlinear least square method; performing dynamic learning on the residual fluctuation of the actual observation data and the degradation trend through a fuzzy random configuration network (F-SCN); and finally, integrating trend prediction and residual prediction results through Gaussian process regression (GPR) to realize high-precision residual life prediction. According to the method, through collaborative optimization of the physical model and the data-driven model, the problem that trend fitting and local fluctuation are difficult to consider under limited data in a traditional method is solved, and the prediction precision and reliability are remarkably improved.

The invention discloses an electric power inspection exoskeleton modular structure, and belongs to the technical field of human body exoskeleton machine assistance, the electric power inspection exoskeleton modular structure comprises a supporting system, the supporting system comprises a back supporting plate, a waist supporting frame and thigh supporting rods, and a main body supporting frame is formed; the modular interface system comprises at least one group of mechanical interfaces, electrical interfaces and data interfaces which are uniformly distributed on a force transmission path of the support system; the functional module comprises a plurality of interchangeable power assisting modules, operation modules and protection modules, and the functional module is detachably connected with the supporting system through the modular interface system; a hybrid drive system includes a rigid driver and a flexible driver for providing position control and compliance force control, respectively. By means of the modular interface system, plug-and-play of functional modules such as power assisting, operation and protection is achieved, needed exoskeleton configuration can be rapidly assembled, multiple sets of exoskeleton equipment do not need to be arranged, and the equipment utilization rate and task adaptability are greatly improved.

The invention relates to the technical field of big data processing, in particular to an offshore wind plant generation power prediction method and system based on big data. According to the method, an ultra-short-term generated power prediction model based on data and physical hybrid driving is adopted to predict the generated power of the offshore wind plant, and the ultra-short-term generated power prediction model based on data and physical hybrid driving comprises a deep learning model, a physical model module, a reinforcement learning module and a dynamic switching mechanism; the dynamic switching mechanism is used for dynamically selecting the deep learning model module or the physical model module according to a wind speed fluctuation threshold value and feedback of the reinforcement learning module; according to the model selection logic provided by the invention, the prediction precision can be remarkably improved; meanwhile, in combination with feedback of a wind speed fluctuation threshold value and reinforcement learning, a dynamic switching mechanism improves the robustness and generalization ability of a prediction model.

A hybrid drive carrier frame includes a front rail comprising a first end, a second end, and a body extending along a transverse direction between the first and second ends. The frame comprises a first side rail extending from the first end of the front rail perpendicular to the transverse direction and a second side rail extending from the second end of the front rail perpendicular to the transverse direction and parallel to the first side rail. The first side rail is formed from a metal material and includes a locking tab extending along the transverse direction. The front and second side rails are formed from a plastic material. The front rail includes a locking channel at the first end of the front rail and the first side rail is connected to the first end of the front rail via engagement of the locking tab within the locking channel.

A hybrid drive omni-directional motion actuator based on an origami structure, comprising at least one actuating module. The actuating module comprises a columnar shell deforming based on the origami structure, an upper cover plate and a lower cover plate. The columnar shell is the origami structure derived from Waterbomb crease, and a cavity containing gas is formed inside the shell. The two ends of the cavity are open, and the openings are respectively connected with the upper cover plate and the lower cover plate for blocking the openings. The lower cover plate is provided with vent holes communicating with the cavity, and the upper cover plate and the lower cover plate are pulled by driving ropes arranged in a crossed manner. Through the cooperation of gas and tendon drive, the columnar shell can have deformations of contraction, bending and torsion, so that a single actuating module has omni-directional movement capability.

The invention provides a hybrid drive system and a vehicle with the same. The hybrid drive system comprises a differential mechanism, a first half shaft of the differential mechanism is connected with a left front wheel, and a second half shaft of the differential mechanism is connected with a right front wheel; the driving motor is provided with a motor input shaft, the motor input shaft is connected with the first half shaft through a first gear pair, the output torque of the driving motor is transmitted to the first half shaft through the motor input shaft and the first gear pair, and then the left front wheel is driven to rotate; the generator is provided with a generator input shaft, the generator input shaft is connected with the second half shaft through a second gear pair, and the output torque of the generator is transmitted to the second half shaft through the generator input shaft and the second gear pair so as to drive the right front wheel to rotate. According to the scheme, the left front wheel and the right front wheel can be independently driven, independent torque control is provided for each wheel, a distributed driving mode under electric driving is achieved, and the technical problem that a hybrid driving system in the prior art cannot adapt to complex road surfaces is solved.

The invention relates to the technical field of robots, in particular to a hybrid drive leg device and a humanoid robot. The leg device comprises a thigh assembly and a shank assembly. The thigh assembly comprises a first driving mechanism, a second driving mechanism, a thread shifting device and a pair of first structural plates. The first driving mechanism comprises a first motor, a first conical wheel, a first guide wheel and a first rope. The first motor drives the first conical wheel to rotate and drives the first structural plate to swing. The shank assembly comprises a pair of second structural plates, and the second driving mechanism is used for driving the second structural plates to swing. The thread shifting device drives the first rope to move in the axial direction of the first conical wheel and drives the second rope to move in the axial direction of the second conical wheel, so that the leg device can stably operate under the conditions of different gaits and loads. In addition, the leg device of the scheme comprises the elastic buffer piece and the hydraulic damper, the elastic buffer piece and the hydraulic damper can absorb impact force borne by the leg device in real time in the movement or landing impact process of the leg device, and the overall stability of the leg device is improved.

Hybrid drive snowmobile comprising an IC engine, a variable speed drive comprising a first pulley connected to a drive shaft of the IC engine, a second pulley and a belt coupled to the first and second pulleys, an intermediate shaft-connected to the second pulley of the variable speed drive, an output shaft connected to the intermediate shaft by a transmission and a drive wheel of a motor track of the snowmobile connected to the output shaft and a reversible electrical machine connected to the intermediate shaft.

This invention provides a hybrid power drive device and a vehicle having the same. The hybrid power drive device includes an engine, a first motor, a second motor, and a compound planetary gear set. The output end of the engine is driven to the motor shaft of the first motor. The motor shaft of the second motor drives the wheels to rotate. A first sun gear meshes with a first planetary gear, and both the second sun gear and the first planetary gear mesh with a second planetary gear. The second planetary gear meshes with a ring gear, and the ring gear is driven to the wheels. A brake controls the operating state of the second sun gear, a first clutch controls the engagement or disengagement of the engine output end with the first sun gear, and a second clutch controls the engagement or disengagement of the engine output end with the planetary carrier. The technical solution provided in this application solves the problem in related technologies where hybrid power drive devices struggle to simultaneously achieve efficiency and compactness across multiple operating modes, as well as flexible drive switching.

The invention discloses a learning and model hybrid driven autonomous vehicle safety control method and system, which are suitable for expressway convergence control in a hybrid traffic environment. According to the method, multi-agent reinforcement learning and a safety potential field theory are combined to construct a hybrid control framework; collaborative decision and adaptive control of ramp and main line automatic driving vehicles are realized through a multi-agent near-end strategy optimization algorithm; meanwhile, a novel relatively safe potential field energy index is introduced, the interactive collision risk between the vehicles is quantified in real time, and a reward function is designed based on the index to guide an intelligent agent to learn safer behaviors; in addition, a dynamic safety intervention mechanism is further arranged, when risk assessment exceeds a preset threshold value, protective action coverage is automatically triggered, and risk avoidance is implemented. According to the method, the collision rate is remarkably reduced, meanwhile, high passing efficiency and reward revenue are kept, and the safety, coordination and deployability of the automatic driving vehicle are effectively improved.

The present invention relates to a hybrid drive system (1) of a motor vehicle. The hybrid drive system (1) comprises an internal combustion engine (10) and a transmission (20), wherein the internal combustion engine (10) has an output shaft (11) and the transmission (20) has an input shaft (21), wherein the hybrid drive system (1) comprises an axial flux machine (30), wherein the axial flux machine (30) has a stator (34) and a rotor (31) rotatable relative to the stator with at least one rotor disk, wherein the hybrid drive system (1) comprises a dual-mass flywheel (70), wherein the output shaft (11) of the internal combustion engine (10) is rotationally fixedly coupled to a first flywheel of the dual-mass flywheel (70), wherein the rotor (31) of the axial flux machine (30) is rotationally fixedly coupled to a second flywheel of the dual-mass flywheel (70), and wherein the input shaft (21) of the transmission (20) is connected to the rotor (31) of the axial flux machine (30). is coupled in a rotationally fixed manner.

The invention discloses a wind power mixed tower structure reaction extremum prediction method based on model and data hybrid driving, and aims to solve the problem that there is no standard and accurate processing method for wind power mixed tower structure reaction extremum prediction at present. According to the wind power mixed tower structure reaction extreme value prediction method, after effect data is extracted according to wind power mixed tower structure input data and structure output data, an average condition exceeding rate function and a statistical model thereof are constructed; obtaining extreme load values and response values in different return periods through a trend fitting mode and an extrapolation mode according to an average condition exceeding rate function statistical model; a structure health monitoring system is established, input data and output data of a wind power mixed tower structure are obtained under a unified clock and a set reasonable sampling frequency, and the input data of the wind power mixed tower structure comprise the wind speed, the wind direction, the base acceleration and the base temperature; the output data of the wind power mixed tower structure comprises the acceleration, the top displacement, the differential settlement, the cable force of the prestressed cable and the inclination angles of different heights of a mixed tower drum.

The invention discloses a hybrid electric vehicle thermal management system mechanism-data hybrid drive modeling method, and belongs to the technical field of new energy vehicle thermal management, and the method comprises the steps: obtaining sample data under an optimization purpose; performing mechanism-data hybrid modeling on subsystems of the thermal management system of the hybrid electric vehicle to obtain modeling results of different subsystems; performing model integration on the modeling result to obtain a system model; and the system model is verified and optimized in real time through sample data, and an optimized system model is obtained for thermal management of the hybrid electric vehicle. According to the technical scheme, high-precision dynamic modeling, global energy efficiency optimization and dynamic real-time control of the thermal management system of the hybrid electric vehicle can be realized.

The present invention relates to a hybrid drive system (1) of a motor vehicle. The hybrid drive system (1) comprises an internal combustion engine (10) and a transmission (20), wherein the internal combustion engine (10) has an output shaft (11) and the transmission (20) has an input shaft (21), wherein the hybrid drive system (1) comprises an axial flux machine (30), wherein the axial flux machine (30) comprises a stator (34) and a rotor (31) rotatable relative to the stator with at least one rotor disk (32), wherein the axial flux machine (30) is arranged between an engine block (16) of the internal combustion engine (10) and a transmission housing (26) of the transmission (20).

The invention relates to the technical field of computer vision and artificial intelligence, and discloses a public area pedestrian trajectory monitoring system based on cross-camera tracking and hybrid simulation completion. The system comprises a camera array module, a pedestrian detection and cross-camera tracking module, a monitoring blind area information base module, a hybrid drive pedestrian simulation engine module, a track fusion and complementation module and a simulation integration propulsion module. According to the invention, monitoring blind area tracks can be effectively filled, track continuity and prediction accuracy are improved, existing hardware is fully utilized to reduce cost, and modular design is easy to integrate and convenient to use. The generated complete track can be widely applied to scenes such as public safety monitoring, passenger flow analysis and emergency evacuation plan making in public places such as ports, subway hubs, cruise ship wharfs and commercial complexes, and supports a real-time monitoring or post-analysis mode.

The invention discloses a dual-fuel ship energy efficiency operation index prediction method based on physical data hybrid drive. The method comprises the steps that historical energy efficiency data of a liquefied natural gas dual-fuel ship are collected and preprocessed; and obtaining input features through feature selection. Constructing a physical mechanism model to predict fuel consumption, and establishing a two-way recurrent neural network data driving model based on a Bayesian optimization and whale optimization two-stage optimization algorithm framework to predict an error between the physical mechanism model and each piece of historical ship fuel consumption data; and adding each fuel consumption predicted based on the physical mechanism model and an error output by the data driving model through a physical data hybrid driving model formed by combining the data driving model and the physical mechanism model to obtain a final prediction result of each fuel consumption, and calculating to obtain a ship energy efficiency operation index. According to the method, the relative error of the energy efficiency operation indexes of the liquefied natural gas dual-fuel ship obtained through prediction can be smaller, and the actual energy efficiency management requirement is met.

A hybrid power drive system (100), comprising: an engine (10), a driving shaft (20), first electric motors (40), second electric motors (60), a planetary gear mechanism (30), and a limiting unit (50). The second electric motors are transmittingly connected to the driving shaft; the planetary gear mechanism comprises a first rotating member (31), a second rotating member (32), and a third rotating member (33) that can rotate coaxially; the first rotating member is connected to an output end of the engine, the second rotating member is transmittingly connected to the driving shaft, and the third rotating member is connected to the first electric motors; and the limiting unit is configured to limit the transmission of torque from the first electric motors to the engine and to form a torque transmission path between the first electric motors and the driving shaft. The system can ensure the power performance and economy of vehicles. In addition, the present invention further relates to a vehicle (200).

The invention discloses a flexible self-adaptive grabbing finger based on a paper folding structure and a method, and relates to the technical field of manipulators. The finger comprises a finger seat and at least two finger bodies, wherein each finger body comprises a joint module, a finger section module and a connecting piece; the joint module is a first hollow body formed by a triangular variant Yoshimura paper folding structure in a surrounding mode, an air bag is arranged on the back side of the joint module, and a first guide hole is formed in the ventral side of the joint module. The finger section module is a second hollow body; the connecting piece is detachably connected with the joint module and the finger section module; the first rope penetrates through the first guide hole to be connected with the ventral side of the finger section module at the tail end, and the second rope penetrates through the second guide hole in the connecting piece to be connected with the middle position of the finger section module at the tail end. A paper folding structure and air-rope hybrid driving are adopted, and through the hierarchical control strategy of pneumatic rapid enveloping and rope-driven event driving, the structure is simplified, control is reliable, maintenance is convenient and fast, the self-adaptive grabbing capacity is achieved, and the mechanical arm is particularly suitable for agricultural picking and other complex environments.

The invention provides a multi-energy-flow real-time updating method based on a building integrated energy system, and belongs to the technical field of energy scheduling, and the method comprises the steps: obtaining an equipment set and a typical state vector, and constructing a building integrated energy mechanism model based on mechanism data and balance constraint data; collecting a plurality of historical operation data, and determining a plurality of period-mode historical data and a plurality of environment clustering data; determining a plurality of response clustering data, and constructing a data driving model of each environment label of each period-mode label; acquiring equipment parameter data, and determining fitting residual data of each environment label of each period-mode label; performing first optimization on each data driving model; and constructing a mechanism-data hybrid drive model and realizing adaptive optimization. The method can accurately adapt to a subdivided scene, improve deviation fitting precision, give consideration to explanatory and prediction precision, dynamically adapt to system time-varying characteristics, improve the adaptability of the model in a complex scene, and guarantee long-term prediction reliability.

The invention discloses a seawater intrusion dynamic early warning method and platform, and relates to the technical field of machine learning, and the method comprises the steps: collecting monitoring data through a monitoring well sensor network to form a multi-source time series data set; constructing a hybrid drive prediction model containing a physical model branch, a data drive branch and a fusion layer; pre-processing the multi-source time sequence data set, and inputting the pre-processed multi-source time sequence data set into the hybrid drive prediction model to obtain a seawater intrusion prediction value; and inputting the seawater intrusion prediction value into a pre-trained intrusion risk classifier, evaluating different degrees of seawater intrusion probabilities in a preset time window, and triggering an early warning signal of a corresponding level. According to the invention, the technical problems that the water body source is difficult to distinguish and the seawater intrusion trend determination is inaccurate in the traditional seawater intrusion early warning are solved, and the technical effects of accurately distinguishing the seawater intrusion water body source, dynamically predicting the intrusion trend, triggering the corresponding grade of early warning, and effectively improving the seawater intrusion early warning accuracy and the control pertinence are achieved.