56results about How to "Accurate solution" patented technology

The invention discloses a deep learning-based pipeline structure stress proxy model construction method, which belongs to the field of engineering mechanics, energy transmission and artificial intelligence, and comprises the following steps of: firstly, establishing a numerical model of a pipeline, simulating different environmental conditions by applying different loads, and solving to generate a large amount of simulation data; then, feature unit extraction is carried out on the simulation data so as to compress feature dimensions; then, a deep learning initial proxy model of pipeline stress is constructed, and initial training is carried out through finite element simulation data; and finally, transfer learning is carried out based on the initial agent model, the transfer learning is divided into two stages, enhanced actual measurement sample data is used for training in the pre-training stage, and accurate actual measurement samples are used for further training and fine adjustment in the strengthening stage, so that the generalization ability of the model is improved. According to the method, the stress distribution can be rapidly and accurately solved by constructing the stress agent model, the generalization ability is high, and the problem that a traditional physical modeling method is insufficient in real-time performance and precision in stress monitoring and prediction can be solved.

The invention discloses a method and device for detecting the center position in a laser spot image, and the method comprises the steps: obtaining a laser spot image which is a fuzzy circle / circular ring light spot, and solving the center-of-gravity coordinate of the fuzzy circle / circular ring light spot as an initial center position; calculating radial distances from the initial circle center position along a plurality of different directions of the fuzzy circle / circular ring light spot, and calculating an average value of the radial distances in the different directions as an average radius; based on the average radius, utilizing a least square method to fit a new circle center position; and taking the new circle center position as an initial circle center position, repeating iterative calculation until the difference between the current fitting new circle center position and the previous fitting new circle center position is smaller than a preset threshold value, and determining the current fitting new circle center position as a final circle center position. The method is more accurate in circle center position detection and higher in calculation speed.

The invention discloses a beam synchronous phase on-line measurement method, device and equipment and a medium. The beam synchronous phase on-line measurement method comprises the steps of obtaining an original cavity pressure Vc * and an original forward voltage Vf * of a radio frequency cavity; processing the original cavity voltage Vc * and the original forward voltage Vf * to obtain normalized cavity voltage Vc and forward voltage Vf; calculating steady-state values UC and UF of the cavity pressure Vc and the forward voltage Vf, and solving detuning delta omega in a steady state; carrying out linear fitting on the cavity pressure change Vcb caused by the beam current to obtain a phase angle Vcb; according to the selected time window TW, calculating a deflection angle alpha th of a phase angle Vcb caused by detuning delta omega; deducting the deflection angle alpha th from the phase angle Vcb to obtain the phase angle Vb of the beam equivalent voltage; and extracting a beam phase # imgabs0 # based on the phase Vb of the beam equivalent voltage. The calculation result of the method is not influenced by phase drift caused by environmental factors any more, and is not influenced by cavity detuning any more.

The invention provides a ranging positioning method, device and system. The method comprises the steps that first equipment receives first configuration information, second configuration information and third configuration information through a first communication frequency band, and receives first ranging information, second ranging information and third ranging information through a second communication frequency band. The bandwidth used in the second communication band is greater than the bandwidth used in the first communication band. And after completing time synchronization with the first terminal equipment on the first communication frequency band based on the first configuration information, the first equipment determines and receives the arrival time of the first ranging information. And determining the position of the first device according to the time difference of arrival of the first distance measurement information, the second distance measurement information and the third distance measurement information. The method can reduce the operation power consumption of the receiving equipment and improve the cruising ability of the equipment.

The invention discloses a production line configuration optimization method and device based on digital twinborn and dual-population genetic algorithm collaboration. The method comprises the following steps: constructing a PCB production line twinborn model; constructing a single-row layout model of the PCB production line, and constructing and forming a multi-target planning model by taking the maximum production efficiency, the maximum equipment utilization rate and the minimum logistics cost as targets; the method comprises the following steps: acquiring twinborn data in real time, acquiring a priority sequence of each process unit of a PCB production line according to the twinborn data, and encoding the priority sequence of each process unit and spacing distances among the process units by using a double-population genetic algorithm, carrying out iterative solution by using a fitness function constructed based on a multi-objective planning model to obtain an optimal configuration scheme; and mapping an optimal configuration scheme obtained by iterative solution to the twin model, and evaluating an optimization effect. According to the invention, an accurate and reliable PCB production line resource configuration optimization scheme can be efficiently generated, and the production line efficiency and the equipment utilization rate are improved.

The invention provides a single-valued transient electromagnetic apparent resistivity calculation method based on deep learning, and the method comprises the following steps: a), carrying out the normalization processing of an actually-measured induced voltage, and obtaining a normalized induced magnetic field; b) a deep neural network model comprising an input layer, a plurality of hidden layers and an output layer is constructed, the input layer receives the normalized induced magnetic field, and the output layer outputs transient field parameters; c) training the deep neural network model by using a Nadam optimization algorithm, wherein a training sample set comprises multiple groups of actually measured induced voltages and transient field parameters corresponding to the actually measured induced voltages; and d) inputting the actually measured induced voltage to be measured into the trained deep neural network model, obtaining the output transient field parameters, and calculating the apparent resistivity according to the theoretical formula of the transient electromagnetic field. Compared with a traditional method, the method has the advantages that the fitting capacity of nonlinear data is higher, and the transient electromagnetic apparent resistivity can be solved more accurately.

The invention discloses a zero-sample food image detection method based on visual semantic bidirectional guidance, which belongs to the technical field of image data processing and generation, takes DETR based on Transform as a detection framework, and fuses a food semantic enhancement network and a cross-modal bidirectional guidance module. Firstly, an image is input to an image backbone network branch to extract visual features, a category label is input to a food semantic enhancement network branch to extract semantic features, then the two obtained features are sent to a cross-modal two-way guide fusion module, the module comprises a two-way guide encoder, a two-way guide query vector and a two-way guide decoder, and the cross-modal two-way guide fusion module comprises a two-way guide query vector and a two-way guide decoder. Visual and semantic features are aligned and fused through coding and decoding processes, and finally, regression and classification tasks of zero sample food image detection are completed in a full connection layer. According to the method, detailed food attributes and visual features can be captured in the detection process, effective interaction of visual semantic modals is achieved, and therefore the detection precision of unseen food categories is improved.

The invention relates to a three-phase multi-loop tunnel cable core steady-state temperature prediction method and electronic equipment, and the method comprises the steps: building a single-phase single-loop tunnel cable steady-state thermal circuit model, and solving the single-phase single-loop cable core steady-state temperature through the built single-phase single-loop tunnel cable steady-state thermal circuit model; solving the steady-state temperature of the cable core under three-phase single-loop laying by using a correction method; for a single-phase four-loop laying situation, the influence of the mutual heating effect between loop cables on the cable core temperature is merged into mutual heating effect thermal resistance, and the mutual heating effect thermal resistance is introduced into a single-phase single-loop tunnel cable steady-state thermal circuit model to form an improved thermal circuit model to predict the cable core steady-state temperature of a single-phase multi-loop cable; the three-phase multi-loop cable is regarded as a single-phase single loop, and the cable core temperature of the three-phase multi-loop cable is predicted through the combination of a three-phase single loop and a single-phase multi-loop. Compared with the prior art, the method has the advantages of quickly and accurately predicting the steady-state temperature of the cable core of the three-phase multi-loop tunnel cable and the like.

The present invention relates to the field of micro-displacement detection technology, and specifically to a micro-displacement radar detection method, system, equipment and storage medium, and the steps are as follows: the radar transmits multiple groups of linear frequency modulation signals with different carrier frequencies for detection, and each group of signals includes multiple pulses; the echo received by each pulse is subjected to FFT transformation, and the results after FFT processing of all pulse groups are accumulated to obtain the range Doppler matrix of any pulse group; the range Doppler matrix of the first pulse group is subjected to target detection to obtain the detection target position, and the radar is repeatedly transmitted, and the fuzzy displacement is obtained by solving the phase difference of the detection target position; the phase difference between the detection target position and the detection target position of the subsequent pulse group is solved to obtain the rough displacement; the fuzzy displacement is solved based on the rough displacement to obtain the real displacement of the target. The present invention can increase the target signal-to-noise ratio, improve the detection capability and stability, and can accurately solve the target displacement even if the target displacement is greater than the radar wavelength.

The invention discloses an electric vehicle ordered charging and discharging control method based on an improved differential evolution algorithm. The method comprises the following steps: constructing a probability model of an electric vehicle charging behavior through a Monte Carlo method; demand analysis and electric vehicle dispatching feasibility judgment are carried out by acquiring power grid information and charging electric vehicle information; considering the power grid operation safety risk and the user credit rating, and formulating a dynamic electricity price; establishing a charging and discharging control model by taking minimization of the comprehensive cost of the user and the construction cost of the power grid as a target; and an improved differential evolution algorithm is adopted to solve the model to obtain the optimal electricity price and the optimal charging and discharging strategy, so that the operation efficiency and the economical efficiency of the power system are improved. The method effectively overcomes the defects of flexibility and cost of an existing electricity price strategy and the defects of dynamic electricity price making in the aspect of user credit, can effectively cope with power grid load fluctuation, and promotes coordinated development of the electric vehicle and the power grid.

The invention belongs to the technical field of vehicle attitude control, and discloses a magneto-rheological suspension control method and system based on IMU resolving, and the method comprises the following steps: obtaining measurement data of an inertial sensor at an initial installation position of a vehicle body, building a vehicle body coordinate system, and determining space coordinate positions of four corners of a suspension; decomposing the motion process of the vehicle body to obtain a resolving formula, and analyzing the obtained vertical acceleration of the four-corner measuring points of the vehicle suspension; calculating the vertical acceleration of the four corners of the vehicle suspension through a resolving formula in combination with the measured data and the spatial positions of the four corners of the vehicle suspension; and an expected force value is obtained through an H-infinity control algorithm, the magneto-rheological damper is controlled in real time, and the magneto-rheological suspension is controlled. By the adoption of the magneto-rheological suspension control method and system based on IMU calculation, the arrangement process is simplified, the precision and response speed of the system are improved, and the high-precision control requirement of the magneto-rheological suspension system under various road conditions and driving working conditions is met in combination with a control algorithm.

The invention discloses a flexible interconnected power distribution network fault recovery method and system considering important load ports. The method comprises the following steps: obtaining interconnection device recovery characteristics of a target flexible interconnected power distribution network in different control modes; establishing a post-disaster fault recovery optimization model of the flexible interconnected power distribution network considering the recovery characteristics of the interconnection device of the target flexible interconnected power distribution network in different control modes; solving the post-disaster fault recovery optimization model of the flexible interconnected power distribution network in combination with a second-order cone to obtain a solved post-disaster fault recovery optimization model of the flexible interconnected power distribution network; and according to the solved post-disaster fault recovery optimization model of the flexible interconnected power distribution network, performing fault recovery of the flexible interconnected power distribution network. According to the method, the problems of nonlinearity and complexity in the optimization model are effectively solved, so that the solving process is more efficient and accurate, and a high-quality fault recovery scheme can be quickly generated.

The present invention discloses a method for solving NS equations based on a neural network with integral constraints of conservation quantities, comprising the following steps: S1. Establishing NS equations to be solved according to actual application scenarios; S2. Performing numerical simulation of computational fluid dynamics methods; S3. Based on the theorem of conservation of energy, integrating and transforming the NS equations to be solved to obtain conservation quantity equations, and establishing a neural network model; S4. Training and solving the neural network model in S3, and verifying the solution results obtained with the numerical values ​​obtained in S2 until the predetermined solution accuracy of the neural network model is reached. The present invention solves the problem of accurately solving inviscid compressible NS equations, and accurately solves the solution information of the entire flow field when only initial incoming flow conditions and individual boundary data are required, which significantly reduces the demand for data and the difficulty of obtaining sampling points in the computational domain compared to PINN solutions.

The present application provides an ultra-short baseline positioning method and system based on CZT cross-correlation delay difference spectrum, which measures the propagation time and phase change of the sound wave between the target cooperation end and the USBL array composed of multiple hydrophones to obtain the propagation distance, and then estimates the three-dimensional coordinates of the target; the method includes: the target cooperation end amplifies and automatically gains the received data; performs fast Fourier transform and matched filtering on the data, and then performs inverse fast Fourier transform and peak detection to obtain the arrival time estimation of multiple channel target signals, and then estimates the distance between the target cooperation end and the center of the USBL array; calculates the frequency domain output of the matched filtering of multiple channels to obtain the secondary correlation output, and then performs band filtering, performs CZT transformation on the secondary correlation function, uses the peak to find the delay difference, and calculates the coordinates of the target cooperation end according to the delay difference. The advantages of the present application are: accurate target position solution and small amount of calculation.

The invention discloses an optimization iteration solving method for an aero-engine model based on an LM algorithm and a quasi-Newton method, and the method employs a variable cycle engine model as an example, builds a complete engine model, and compiles a complete engine model function library. A function library comprises a complete engine model, a thermodynamic function, a model solving algorithm and a GUI interface, a volume model is adopted for an engine, a balance equation and a co-working equation of the engine are established, a novel algorithm enabling an initial guess value to be more accurate is adopted when the model is solved, the convergence speed can be increased by 13.7%-29.1%, and the convergence speed can be increased by 13.7%-29.1%. And meanwhile, the LM algorithm or the quasi-Newton method is automatically matched in the subsequent solution, so that the model solution is faster and more accurate, the steady-state error of the solved model does not exceed 0.8%, and the simulation precision is higher.

The embodiment of the invention relates to the field of neutron spectrum detection research, in particular to a spectrum unfolding method suitable for a self-powered neutron spectrum detection assembly and computer equipment. A specific implementation mode of the method comprises the following steps: putting an energy spectrum measurement assembly into a neutron radiation field to be measured, and obtaining a corresponding radiation current measurement value; carrying out data acquisition processing on the energy spectrum measurement assembly; determining an energy region energy spectrum proportion combination information set; radiation current combination information is determined; performing screening processing on the radiation current combination information set; determining a radiation current root-mean-square value; and determining neutron radiation field energy spectrum information corresponding to the to-be-detected neutron radiation field. The implementation mode can be matched with a self-powered neutron energy spectrum detection assembly to achieve neutron energy spectrum detection, analysis operation is carried out on the current signal output by the detector, solving of the energy spectrum to be detected is achieved, and neutron energy spectrum unfolding can be accurately completed under the condition better conforming to physical reality.

The invention discloses a power distribution network photovoltaic consumption capability improving method considering time-space characteristics of rural electric vehicles, and belongs to the technical field of power distribution networks. The method comprises the following steps: constructing a rural electric vehicle charging and discharging behavior model based on a rural road condition, a meteorological condition and a temperature; determining a rural electric vehicle charging load curve and regulation potential based on the rural electric vehicle trip chain and the rural electric vehicle charging and discharging behavior model; the actual charging and discharging power range of the electric vehicle can be determined based on the charging load curve and the regulation potential of the rural electric vehicle, constraint conditions are constructed based on the actual charging and discharging power range of the electric vehicle, and a power distribution network optimization scheduling model which comprises a target function and the constraint conditions and faces the improvement of the photovoltaic consumption capability is constructed; and solving the power distribution network optimization scheduling model by using a grey wolf algorithm. According to the invention, the relation among the economy, the safety and the photovoltaic absorption capability can be effectively balanced.

This invention discloses an adaptive optimization method for optical scattering measurement. It involves parametrically modeling the nanostructure to be measured and building a basic coarse-grained sample library. A coarse-grained surrogate model is then trained based on this sample library, enabling rapid identification of multiple key regions. Adaptive sampling is then performed based on these key regions to build a fine-grained sample library. A fine-grained surrogate model is further trained based on this library, and this model performs fine-grained search optimization within the key regions to find the optimal values ​​within these regions. These optimal values ​​represent the relevant parameters of the sample to be measured. This invention can narrow the search range and rapidly build the library using a variable-grained surrogate model, and improve optimization efficiency through an adaptive optimization strategy, thereby achieving accurate and efficient solution for the relevant parameters of the sample to be measured.

The application discloses a kind of fuel cell proton membrane multi-component gas synchronous separation test methods, belong to material performance test technical field, it includes obtaining proton exchange membrane initial chamber parameter, by electromagnetic heating and spray humidification adjustment, build target temperature and humidity environment;Multi-component mixed gas is injected to high-pressure cavity and drives penetration, generates transmembrane pressure difference parameter and mixed permeation gas;Permeation gas is guided into water-resistant chromatography channel and is carried out gas-liquid-solid distribution processing, and output single component sequence;The change of sequence thermal conductivity is measured and is converted into electrical signal, generates concentration response signal;Model solution is carried out in combination with pressure difference parameter and response signal, and water vapor and multi-component gas permeability are obtained synchronously.The application adopts dynamic environment regulation and control technology of electromagnetic heating and spray humidification, combines water-resistant chromatography separation and thermal conductivity detection, can realize the synchronous, quantitative test of water vapor and multiple permeation gases of fuel cell proton membrane under multiple working conditions.

The invention relates to the technical field of machine vision and image processing, and discloses a non-ferrous metal intelligent impurity removal analysis method based on machine vision, and the method comprises the steps: collecting and correcting the hyperspectral time sequence data of the melt surface; constructing a spectrum prior weighted optical flow energy functional to calculate an accurate motion field capable of retaining a material boundary; combining information of two physical dimensions of spectrum and motion to identify a region of interest which is different from a background melt; extracting multi-dimensional features such as rheology, relative motion and spectral stability representing rigidity, motion independence and material stability of the region for the region; and carrying out collaborative analysis based on the characteristics to judge whether the artifacts are impurities or dynamic fluid artifacts. Through multi-dimensional feature collaborative analysis and physical judgment logic simulation, the problem that targets are difficult to distinguish only by means of single visual features is solved, and the accuracy and reliability of machine vision in intelligent impurity removal analysis application of non-ferrous metals are remarkably improved.

The utility model discloses a porcelain insulator fettling and shaping device which comprises a base, the upper surface of the base is fixedly connected with a positioning frame through a vertical plate, the interior of the positioning frame is fixedly connected with an air cylinder, the output end of the air cylinder is fixedly connected with a lap joint plate, and the interior of the lap joint plate is fixedly connected with an electric push rod. A plate body is fixedly connected to the output end of the electric push rod, a pressing disc is rotatably connected to the interior of the plate body, a column body is fixedly connected to the lower surface of the positioning frame, a mounting plate is in threaded connection to the exterior of the column body, and a two-way screw is rotatably connected to the interior of the mounting plate. Through the structure, the height of the pressing disc is adjusted through the electric push rod, precise pressing of an inwards-sunken or outwards-sunken structure of the top of a green body is achieved, the shaping direction of an umbrella skirt groove can be flexibly switched through the overturning function of the pressing disc, the dressing adaptability is improved, in addition, the dressing range and size can be adjusted through the variable pitch of the outer dressing knife, and the dressing efficiency is improved. Therefore, the fettling device can meet fettling requirements of porcelain insulators with specifications of different diameters, different umbrella skirt distances and the like.

The present invention discloses a method for obtaining key parameters of pollutant migration under the influence of site-scale temperature-hydrodynamic coupling, and a method for obtaining permeability parameters, thermal conductivity and diffusion coefficient of a contaminated site based on numerical simulation of multi-field coupling of hydrodynamic field-temperature field-concentration field. Site pollutant migration parameters are key indicators for site organic pollution investigation and treatment. Currently, the acquisition of aquifer parameters mainly relies on hydrogeological surveys, and the test methods and physical fields are single. Based on this, the present invention proposes the above method. The method shown in the present invention includes establishing a water-heat-salt coupling model for an organic polluted site through site drilling data and field physical test results in the early stage, performing multi-field coupling numerical inversion based on the site model and combining multiple field data, and adjusting the model parameters through manual trial and error to improve the model accuracy and obtain the optimal model.

The application discloses a profile error calculation method for a numerical control machining device, and relates to the technical field of numerical control machining.The method takes a time point corresponding to an expected position point as an initial value of a Newton iteration method, determines a potential time interval in which a time point corresponding to a minimum value of a profile error evaluation function is located by using a gradient descent method, and then dynamically switches the Newton iteration method and a dichotomy method to accurately solve a target time point in the potential time interval, so that the method quickly and reliably converges to a local optimal point closest to the expected position point.The method has the speed of the Newton iteration method and the stability of the dichotomy method, improves the reliability and robustness of a profile error calculation result, and provides an efficient and stable calculation basis for subsequent profile precision control and real-time compensation.

The present invention discloses a multi-modal pushover test system for deep underground structures based on hybrid tests, which belongs to the technical field of underground structure tests. The test system includes a numerical substructure composed of a numerical model of a deep underground structure and a part of the surrounding soil removed, and a test substructure composed of a large-scale stratum-deep underground structure pushover model test designed according to the removed part and a free field model composed of a one-dimensional soil column numerical model, which are respectively connected to the numerical substructure. The present invention also provides a multi-modal pushover test method for deep underground structures based on hybrid tests. The present invention integrates numerical simulation and model tests through hybrid test technology, which can provide more accurate mechanical boundary conditions for pushover tests, thereby being able to well reproduce the initial ground stress state of the deep underground structure while introducing the influence of high-order modes, and also overcome the problem of the traditional pushover test technology that the loading plate and the soil are detached during the loading process.

This invention provides a method, apparatus, and storage medium for calculating the optical properties of a spacecraft surface. The method includes: Step 1, analyzing the optical properties of the micro / nano structures on the spacecraft surface to obtain the absorbance of the surface micro / nano structures; Step 2, obtaining new material information of the spacecraft surface elements; Step 3, performing element-based processing on the complex surface of the spacecraft to obtain the spacecraft element normal and solar vector information in the J2000 coordinate system; Step 4, performing hidden surface removal judgment on the solar vector and element normal to obtain effective element information; Step 5, calculating the optical scattering characteristics of the effective elements to obtain the optical cross-sectional area of ​​the elements; Step 6, summing the optical cross-sectional areas of all elements to obtain the overall optical cross-sectional area of ​​the spacecraft, and calculating the apparent magnitude to obtain the optical properties of the spacecraft. This invention has the advantage of high calculation accuracy and can achieve accurate calculation of the optical properties of the spacecraft surface.

The invention relates to the field of power distribution network operation maintenance, in particular to a snowflake network operation situation awareness and dynamic reconstruction method and device, and the method comprises the steps: judging the operation situation of a snowflake network through an operation situation awareness model; the operation situation perception model is constructed based on a time domain convolutional network containing an attention mechanism; dynamically reconstructing the faulted snowflake network through the dynamic reconstruction model; the optimization target of the dynamic reconstruction model is that the weighted combination value of the load recovery amount and the network loss is maximum; the dynamic reconstruction model is solved through a data-driven evolutionary optimization algorithm, and the data-driven evolutionary optimization algorithm is constructed based on a genetic algorithm and a bidirectional long-short-term memory network. Through the snowflake network operation situation sensing and dynamic reconstruction method provided by the invention, accurate operation situation sensing early warning before the snowflake network breaks down and rapid dynamic reconstruction after the snowflake network breaks down can be realized.

The invention discloses a method for optimizing a speed curve of a heavy haul train in extreme weather. The method comprises the steps that a heavy-load train operation dynamic model is constructed according to the actual line condition under the extreme weather, and the constraint condition of the heavy-load train operation dynamic model considers the adhesion coefficient which changes along with the change of the train speed in the wet wheel-rail contact state; the maximum traction and braking force upper limit capable of being applied at the current running speed is calculated according to the adhesion coefficient in combination with the adhesion weight; for the constructed heavy haul train operation dynamic model, a total objective function is set by taking maximization of train operation distance per unit time, minimization of energy consumption and minimization of air braking time as objectives; and optimizing the speed curve of the heavy-load train by solving the total objective function. According to the method, the operation accuracy of the heavy haul train in the extreme weather is improved, and a solid technical guarantee can be provided for the safety and economical efficiency of heavy haul railway transportation in the future.

The invention discloses a financial voucher pressing machine, and belongs to the technical field of financial tools. Comprising a machining table and a machining unit, four sets of assemblies clamped by the inner end face of an assembly semi-ring are combined and spliced, materials with different thicknesses and different corners can be pressed and pressed under different requirements, due to the design, the situation that the device is limited in use due to the fact that the thickness of the materials is too large can be avoided, and meanwhile effective pressing of the thick materials is guaranteed; when a thick material needs to be subjected to corner pressing from one side, the side, needing to be pressed, of the material is placed over the table top, the side, not needing to be pressed, of the material extends out of the edge of the whole device, the other worker can hold the device by hand, two sets of transversely-arranged combined parts far away from one side of the lifting frame can be dismantled, and the device can be used for carrying out corner pressing on the material. The bottoms of only two sets of assemblies can only make contact with the upper portion of the material on the pressed side, and when a single corner of the material needs to be pressed, the lower end faces of the two sets of assemblies are used for pressing the corner position of the material.

The invention provides a distributed power supply planning method and device, electronic equipment and a storage medium, and belongs to the field of power distribution network planning, and the method comprises the steps: carrying out the important node screening of selectable nodes of a to-be-planned distributed power supply based on a small world theory, obtaining alternative nodes, and determining a solving space according to the alternative nodes; constructing an optimization objective function and constraint conditions, initializing a to-be-planned variable of a to-be-planned distributed power supply to obtain an initial dung beetle population, and performing adaptive weight and Levy flight strategy improved dung beetle algorithm optimization on the initial dung beetle population to obtain a filial generation population; and determining the population fitness of the offspring population according to the optimization objective function, performing screening to obtain a new round of dung beetle population, and performing iterative optimization to obtain an optimal planning variable. According to the method, important nodes are screened through the small world theory, the solution dimension can be effectively reduced, the algorithm convergence speed and the global search capability are improved through the adaptive weight and the Levy flight strategy, and rapid and accurate solution of the distributed power supply planning problem is achieved.

The invention provides an automatic deployment WiFi access point information map construction method and system. The method comprises the following steps: analyzing channel change characteristics, analyzing energy distribution of a signal on a time axis, identifying an energy concentration area, and obtaining a highest point of energy PLCR; establishing a correlation among the energy highest point PLCR, the human body movement speed and the human body position, obtaining and utilizing a model prediction framework, carrying out reverse solution on a track, fusing human body movement constraints and spatial constraints into a simulation data set, and utilizing the speed constraint in the movement constraints to derive a feasible region of the target position, so as to obtain the target position. Calculating a feature data set according to the simulation trajectory sequence, training to obtain a data-driven framework model, and processing to obtain a prediction trajectory; and carrying out similar SAGE iterative solution, and carrying out iterative optimization on the parameter estimation value by utilizing an SAGE algorithm until a preset convergence condition is met. The technical problems that large-scale deployment difficulty is large, dependence on specific antenna layout restricts system adaptability, and modeling and positioning operation precision is low are solved.