241results about How to "Avoid uncertainty" patented technology

The invention discloses an SSR (Simple Sequence Repeat) core primer combination and a kit for identifying a tea tree variety 'swan gooses 12' and application of the SSR core primer combination and the kit. According to the invention, three pairs of SSR core primers are screened by using an SSR fluorescence labeling detection technology, and the three pairs of SSR core primers can rapidly identify and detect the 'Yangou 12' from other tea tree varieties. The SSR core primer combination disclosed by the invention can be used for identifying the variety of the swan goose 12, the uncertainty of identification based on external morphological characteristics is overcome, the result is reliable and visual, the detection efficiency is high, the operation is simple and convenient, and meanwhile, the popularization, utilization and protection of the variety of the swan goose 12 are also facilitated.

The invention discloses a machine learning optimization method of a low-frequency sound absorption structure based on three-dimensional printing, and belongs to the technical field of artificial intelligence acoustics, the low-frequency sound absorption structure is prepared from a photosensitive resin material through photocuring three-dimensional printing, and comprises a side seam, an extension cavity, a circular through hole, a resonance cavity, a first partition plate, a second partition plate and a third partition plate, the method has good expansibility and can be adjusted according to different noise control requirements; through a machine learning optimization method, structure parameters can be quickly adjusted to cope with a noise control task on the premise of ensuring a small size, so that a remarkable sound absorption effect is obtained at a specific low-frequency band; according to the method, a machine learning method based on a multi-layer perceptron and a genetic algorithm is adopted, geometric parameters of the low-frequency sound absorption structure are optimized, simulation calculation is carried out by using a commercial finite element solver COMSOL Multiphysics, and the sound absorption performance of the structure is further verified and optimized.

The invention provides a credit management method and related equipment based on multi-temporal satellite remote sensing, and the method comprises the steps: determining a to-be-analyzed land parcel in response to a credit management instruction; acquiring a multi-temporal satellite remote sensing image of the land parcel to be analyzed; analyzing the multi-temporal satellite remote sensing image by using a preset image analysis system to obtain a normalized difference vegetation index (NDVI) sequence of the land parcel to be analyzed; determining crop species of the to-be-analyzed plot according to the NDVI sequence of the to-be-analyzed plot; inputting the NDVI sequence into a pre-constructed yield analysis model to obtain a crop yield prediction result of the crop variety; and carrying out credit granting on the credit granting object to which the to-be-analyzed land parcel belongs according to the crop yield prediction result of the crop type. By applying the method provided by the embodiment of the invention, the credit can be accurately granted to the customer.

The invention relates to the field of ocean energy development and utilization, in particular to a tidal current energy array field site selection method based on a three-dimensional high-precision numerical model, which comprises the following steps: (1) a macroscopic site selection method; (2) a microscopic site selection method; (3) establishing a high-precision layered three-dimensional numerical model; (4) a tidal current energy resource refined evaluation method; analyzing a model calculation result, analyzing tidal current properties such as a large tide rising and falling moment, a small tide rising and falling moment, tidal current stability, energy flow density, theoretical reserve of tidal current energy resources, single-width energy flow flux and the like of a target sea area, and presenting an evaluation result through a visualization technology so as to guide a laying mode of a tidal current energy unit; compared with a traditional two-dimensional or simplified three-dimensional model, the evaluation precision is greatly improved. The tidal current characteristics at different water depths can be meticulously simulated, so that tidal current energy resource assessment is more comprehensive and accurate.

The invention relates to a valve sealing performance detection system and method, and belongs to the technical field of valve detection. The problems that traditional valve detection is limited to sealing performance detection in a closed state, and monitoring on abnormal changes of pressure, temperature and flow parameters in detection is insufficient are solved. Comprising a valve installation module, a sealing performance evaluation module, a safety monitoring module and a control and display module. The control and display module determines the acquisition evaluation value and the acquisition frequency of the acquisition parameters according to the valve pressure and the opening range, so that the pertinence and the effectiveness of data acquisition are greatly improved; the sealing performance evaluation module establishes a pressure curve, a flow curve and a temperature curve by analyzing various parameters, and analyzes the pressure curve, the flow curve and the temperature curve to obtain a valve sealing value, so as to accurately judge the sealing performance of the valve; the safety monitoring module can deeply analyze the curve to calculate an alarm evaluation value, compares the alarm evaluation value with a preset threshold value, and gives an alarm for abnormal conditions of pressure, temperature and flow in time, so that the safety of the detection process is guaranteed.

The utility model provides a pile foundation concrete pouring over-pouring height measuring device which comprises an installation frame, a winding drum mechanism arranged on the installation frame, a coil spring arranged in the winding drum mechanism, a measuring rope with one end fixed and wound on the winding drum mechanism and a fixing piece connected with a reinforcement cage. The fixed part is arranged on the mounting frame, the floating ball mechanism is movably connected to the fixed part and connected with the other end of the measuring rope, the ratchet wheel is fixedly connected to the winding drum mechanism, and the alarm mechanism is arranged on the mounting frame and used for being matched with the ratchet wheel. The pile hole concrete surface ascends to push the floating ball mechanism to ascend, and then under the action of the coil spring, the winding drum measuring rope is driven to be shortened, the winding drum mechanism and the ratchet wheel are driven to rotate, so that the alarm mechanism matched with the ratchet wheel sends out a signal to remind constructors of the concrete pouring condition, and accurate control over the over-pouring height is achieved. Tediousness and uncertainty of manual judgment are avoided, and construction efficiency and construction quality of the pile foundation are effectively improved.

The invention provides a tight oil reservoir fluid occurrence type identification method and system based on nuclear magnetic resonance, and belongs to the technical field of petroleum geology exploration and development. The method comprises the following steps: on the basis of comparison between a nuclear magnetic resonance T2 relaxation time cumulative distribution curve of a tight oil reservoir sample and a high-pressure mercury injection pore throat diameter cumulative distribution curve, dividing pore throat types, and converting T2 relaxation time into pore throat diameters; judging occurrence fluids in different types of pore throats through a nuclear magnetic resonance spectrum to obtain fluid occurrence types corresponding to different signal domain ranges, and calculating the relative fluid content of each fluid occurrence type; and based on the signal domain range of each fluid occurrence type of the plurality of samples, establishing a nuclear magnetic resonance fluid occurrence type identification chart, and defining an identification standard of each fluid occurrence type. According to the method, the pore size distribution of the T2 relaxation time is combined with the nuclear magnetic resonance spectrum, the pore size range corresponding to the fluid occurrence type is determined, and the relative content of the fluid is calculated through the signal intensity of each signal domain, so that the accuracy is higher.

The invention provides a capacitance detection method, system and device and a storage medium, and relates to the technical field of capacitance detection. The method comprises the following steps: acquiring a capacitance type and a parameter range of a measured capacitor, and matching with a preset resonance library according to the capacitance type and the parameter range to obtain a target resonance inductance parameter; constructing a target LC resonance test circuit based on the target resonance inductance parameter, the capacitor type and the parameter range, and measuring the tested capacitor based on the target LC resonance test circuit to obtain resonance response data; and analyzing the resonance response data to obtain a capacitance performance index. Through the scheme, the capacitor testing efficiency is improved.

The invention discloses a BIM-based communication pipeline design intelligent optimization system and method, and relates to the technical field of BIM. An initial data set X is constructed, the electromagnetic interference intensity between each pair of pipelines is deduced in combination with an electromagnetic field theory, an interference intensity matrix EMI is finally generated, the relative position of a high-interference pipeline is dynamically adjusted by adopting an optimization algorithm, and the relative position of the high-interference pipeline is optimized. The method comprises the steps of generating a preliminary pipeline layout scheme Xop, applying the preliminary pipeline layout scheme Xop to a BIM model, further combining a spatial constraint Cs to perform verification and fine tuning, calculating a pipeline position optimization evaluation index Ft, and comparing the pipeline position optimization evaluation index Ft with a preset pipeline position optimization execution evaluation threshold Fth, thereby realizing scientific evaluation and decision-making of the scheme optimization effect, and improving the pipeline position optimization efficiency. The problems of insufficient electromagnetic interference influence evaluation, disjunction of an optimization process and spatial constraint and the like are solved in a targeted manner, and electromagnetic interference minimization, path optimization rationalization and space resource utilization maximization of communication pipeline layout are realized.

The invention relates to the technical field of pesticide efficacy evaluation, in particular to a compound pesticide preparation field efficacy evaluation method which can reduce unnecessary pesticide use and reduce the influence on the environment. The method comprises the following steps: dividing a pesticide application field into a plurality of pesticide application units according to a preset division strategy; obtaining a pesticide effect value of each pesticide application unit, and performing assignment based on the position of the pesticide application unit in the field to obtain a pesticide application field pesticide effect matrix; the pesticide effect value is obtained by subtracting the disease density of the pesticide applying unit after the preset time length of pesticide application from the disease density of the pesticide applying unit before pesticide application; performing uniform statistics on the pesticide effect matrix of the pesticide application field to obtain a pesticide effect uniform value of the compound pesticide, and correcting the pesticide effect uniform value of the compound pesticide by considering a pesticide application mode; the pesticide application modes comprise spraying, irrigation and sowing; and performing feature recognition on the pesticide effect matrix of the pesticide application field to obtain a pesticide effect feature value of the compound pesticide, and considering a relative relationship between a pesticide application time node and a disease period.

According to the regional load aggregator-oriented transformer area user flexible load scheduling method provided by the invention, the temperature control load, the electric vehicle, the energy storage equipment and the like are optimally scheduled, so that the balance of a power grid and the maximization of economic benefits are realized. The method comprises the following steps: predicting the load demand of a transformer area user through modeling analysis, and formulating an optimal scheduling strategy in combination with external signals such as real-time electricity price and environment temperature; a home energy efficiency management system (HEMS), a vehicle-to-power grid (V2G) control platform and an intelligent energy management system (EMS) are utilized to dynamically dispatch and control various flexible loads. The implementation result shows that the method effectively reduces the electric charge of the user, improves the revenue of the aggregator, improves the stability of the power grid, and has remarkable practicability and popularization value.

The invention discloses a nonlinear model predictive control method for a low-temperature multi-effect distillation seawater desalination system, which relates to the technical field of seawater desalination. The specific steps are: defining system parameters, deriving and establishing a dynamic model of the system, designing a nonlinear model predictive control controller, and designing a low-temperature multi-effect distillation seawater desalination system experiment. Considering the thermodynamic characteristics of the low-temperature multi-effect distillation seawater desalination system, a nonlinear MPC algorithm equation is established, and a NMPC module is used to calculate the power steam flow rate W. ms With the feed seawater flow rate W sw Two major types of control inputs are used to achieve automatic control of the maximum water production ratio. The method of the present invention can effectively overcome the uncertainty, nonlinearity and parallelism of the process, and conveniently handle various constraints in the controlled variables and manipulated variables in the process to achieve a control effect with good stability and strong robustness.

The invention discloses a multi-task PEM unmanned aerial vehicle energy scheduling method and system based on MPC and DDPG, and the method comprises the steps: building a stress model and a power model in each flight mode according to the flight mode of a hydrogen fuel cell unmanned aerial vehicle; establishing a mathematical model, an objective function and operation constraints of the hydrogen fuel cell unmanned aerial vehicle energy system; constructing an MPC model by combining the stress model and the power model of the unmanned aerial vehicle in each flight mode, collecting state parameters of the unmanned aerial vehicle, and obtaining electric power predicted by the MPC model; and constructing a DDPG model based on the mathematical model, the objective function and the operation constraint of the hydrogen fuel cell unmanned aerial vehicle energy system, and taking the predicted electric power as the input of the trained DDPG model to obtain an energy scheduling result. According to the invention, energy utilization can be optimized in a complex task environment, and the task completion efficiency and cruising ability of the unmanned aerial vehicle are improved.

The invention provides a method for eliminating delta ferrite in austenitic stainless steel and the austenitic stainless steel, and belongs to the technical field of metal materials. The method comprises the following steps that an austenitic stainless steel ingot containing the delta ferrite is subjected to heat preservation for first set time at the first set temperature for first heat treatment; heating the austenitic stainless steel ingot subjected to the first heat treatment to a second set temperature, and carrying out heat preservation for a second set time at the second set temperature for second heat treatment; and cooling the austenitic stainless steel ingot subjected to the second heat treatment, or sequentially and repeatedly carrying out the first heat treatment and the second heat treatment on the austenitic stainless steel ingot subjected to the second heat treatment for at least one time, and then cooling to obtain the austenitic stainless steel subjected to delta ferrite elimination. The first heat treatment and the second heat treatment are performed, and the second set time is limited, so that the austenitic stainless steel is prevented from being in a high-temperature environment for a long time, and austenite grains are prevented from obviously growing.

The invention provides a power system anomaly detection method and system, and the method comprises the steps: carrying out the prediction of a photovoltaic panel assembly based on real-time environment parameters collected in real time and a constructed power prediction model, and obtaining theoretical power generation power data; comparing the obtained real-time power generation power data of the photovoltaic panel assembly with the theoretical power generation power data to obtain a comparison result, and determining an abnormal photovoltaic panel assembly; and performing analysis based on the image data of the abnormal photovoltaic panel assembly acquired in real time to obtain an abnormal result. According to the method, by comparing the real-time power generation power and the theoretical power generation power of the photovoltaic panel assembly, the photovoltaic panel assembly with the abnormal power generation efficiency can be rapidly identified, potential problems can be directly, effectively and timely found, energy waste and potential safety hazards caused by reduction of the power generation efficiency are avoided, and the power generation efficiency of the photovoltaic panel assembly is improved. By acquiring and analyzing the image data of the photovoltaic panel assembly in real time, the actual condition of the photovoltaic panel can be known more visually, and the accuracy of anomaly detection is improved.

The invention relates to an anti-seismic performance test method and system for an engineering structure, and relates to the field of anti-seismic performance tests.The method comprises the steps that deployment region information of a target engineering structure and an engineering structure three-dimensional model are obtained, and a first vibration case set is obtained; zooming the three-dimensional model of the engineering structure to obtain a three-dimensional model of the test engineering structure, and zooming the first vibration case set to obtain a second vibration case set; a test engineering structure is manufactured, the second vibration case set is traversed, a pseudo-dynamic test is executed, and a first anti-seismic performance test result set is obtained; when the first anti-seismic performance test result set has no ultimate anti-seismic performance, case optimization is carried out on the second vibration case set, and a third vibration case set test is obtained; and when the first anti-seismic performance test result set has the ultimate anti-seismic performance, outputting the ultimate anti-seismic performance. The technical problems of long anti-seismic performance test time and low test efficiency caused by subjective configuration of a vibration case for a user in the prior art are solved.

The invention discloses a false data injection detection method and system based on a bidirectional long short-term memory network, and belongs to the field of distributed automation system and FDIA detection in a new energy power grid, and the method comprises the steps: constructing a new energy power grid load redistribution attack model based on local information; constructing a new energy power grid false data injection detection model based on a bidirectional long short-term memory network; taking the output of the constructed new energy power grid load redistribution attack model as the input of a false data injection detection model; acquiring data of a new energy power grid; new energy power grid data are incorporated into an IEEE node system to verify the adaptive capacity of the detection model after renewable energy integration; operating data of the power system are collected in real time, preprocessed and input into the verified false data injection detection model, whether the power system is abnormal or not is judged according to a detection result output by the false data injection detection model, and corresponding response measures are taken.

The invention relates to a regulation and control method and system for mine fireproof doors, a terminal and a medium, and belongs to the technical field of mine fireproofing. The regulation and control method comprises the steps that sensing data sent by sensors around each fireproof door are received; according to the multiple sets of sensing data, whether a fire occurs in the mine or not is judged; if yes, determining a target fireproof door according to the fire spreading area; acquiring personnel position information of workers around the target fireproof door; based on the personnel position information, whether a worker is on a fire spreading path and is located between the target fireproof door and a fire spreading boundary is judged; if yes, the closing degree of the target fireproof door is controlled according to the spreading speed of the fire; if not, the closing degree of the target fireproof door is controlled according to the fire behavior of the fire. The intelligent monitoring management system has the beneficial effect that intelligent monitoring management of the fireproof door can be conveniently realized according to the field environment.

The invention discloses a risk assessment method and device, a computer readable storage medium and electronic equipment. The method relates to the field of artificial intelligence, and comprises the following steps: obtaining target data of N users, the target data comprising user data and credit data of the users; the N users are clustered according to the target data of the N users through a target clustering algorithm, M user clusters are obtained, and an initial clustering center set of the target clustering algorithm is determined based on an eagle optimization algorithm; and for each user cluster, evaluating the credit risk of the first user in the user cluster to obtain a risk evaluation result, and determining the risk evaluation result as a risk evaluation result corresponding to each user in the user cluster. Through the credit risk assessment method and device, the problem that the accuracy of credit risk assessment is affected due to poor clustering accuracy caused by randomly determining the initial clustering center of the clustering algorithm when the credit risk of the user is assessed based on the clustering algorithm in the related technology is solved.

The utility model discloses a switching value detection circuit and device, and the circuit comprises a third-order filter circuit, the input end of the third-order filter circuit is used for being connected with the output pin of an external switching value interface, the first grounding end of the third-order filter circuit is connected with the grounding pin of the switching value interface, and the second grounding end of the third-order filter circuit is connected with the grounding pin of the switching value interface. The second grounding end of the third-order filter circuit is grounded; the first-order filter circuit is connected in parallel between the first grounding end of the third-order filter circuit and the second grounding end of the third-order filter circuit and is used for being combined with the third-order filter circuit and performing double third-order filter processing on the switching signal output by the switching value interface; the input end of the signal conversion circuit is connected with the output end of the third-order filter circuit, and the signal conversion circuit is used for outputting a state detection signal of a corresponding level according to the switching signal; the technical scheme of the utility model aims to realize suppression of voltage surge caused by switching pulse and power supply disturbance with low cost during switching value detection.

The invention provides a belt conveyor which is characterized in that a head roller and a tail roller are rotatably arranged on a frame body, the tail roller and a belt storage part are movably arranged on the frame body, and the moving direction of the belt storage part is perpendicular to the width direction of the frame body; the conveying belt is wound on the head roller, the tail roller and the belt storage piece; the first adjusting piece can adjust the position of the tail roller relative to the frame body, and the second adjusting piece can adjust the position of the belt storage piece relative to the frame body. The distance measuring part can detect the moving distance of the belt storage part and the tail roller; the control piece is in signal connection with the distance measuring piece, the first adjusting piece and the second adjusting piece so as to control the first adjusting piece and the second adjusting piece to work according to the detection result of the distance measuring piece. Through the technical scheme provided by the invention, the problem that the adjustment of the tail position adjustment mode of the belt conveyor for adapting to the change of the working surface in the prior art is inaccurate can be solved.

The invention discloses a method for simulating halogen plasma etching silicon or silicon dioxide through molecular dynamics. The method comprises the steps of modeling through a silicon or silicon dioxide substrate material, performing LAMMPS software initialization setting, performing plasma etching circulation, and performing data output and analysis processing. According to the method, a plasma-surface interaction mechanism is simulated on the atomic scale by using a molecular dynamics method, the property of a surface modification layer is analyzed, the simulated etching conditions are independent and controllable, plasma etching with different energies, incident angles and incident doses can be simulated, and the influence of a single variable on an etching result can be accurately analyzed; the method can accurately and quickly predict the effect of etching silicon or silicon dioxide by the halogen plasma under different incidence conditions, avoids high cost, complexity and uncertainty caused by experiments, and greatly shortens the development process of the process of etching silicon or silicon dioxide by the halogen plasma.

The invention discloses an elephant-only numerical simulation method for femtosecond laser ablation removal, and belongs to the technical field of femtosecond laser processing. The implementation method comprises the following steps of: dividing the surface of a target material into nodes at equal intervals along the horizontal direction by adopting a discretization numerical method; on the surface of the target material, under single pulse irradiation with the position (x0, y0) as the center, the incident flux at the given point is calculated according to an incident flux formula; describing the surface topography change and incubation effect caused by laser irradiation by using a manifestation method; according to the included angle between the laser incidence direction and the local normal vector, net ablation flux is obtained through calculation, and numerical simulation of the ablation removal process is carried out; and data cycle calibration is performed based on experiments, a material removal coefficient xi is obtained, displacement of any point on the surface of the material is calculated, and surface topography simulation prediction of femtosecond laser single pulse or multi-pulse machining is realized. According to the method, the numerical simulation result of the machining process can be quickly generated according to different laser flux parameters, and the experiment cost is remarkably reduced.

The invention discloses a track height unevenness detection system, a track height unevenness detection method and a track height unevenness measurement calibration method. Comprising a control system, a power supply module, a first three-axis accelerometer, a second three-axis accelerometer, a first pressure sensor, a second pressure sensor and a non-contact displacement detection device. A detection train comprises a train body, a bogie and wheels, and the wheels comprise the front wheel and the rear wheel. The vehicle body is connected with the bogie through a secondary suspension system, and the bogie is connected with the wheels through a primary suspension system; the triaxial accelerometer I and the pressure sensor I are respectively arranged at the top and the bottom of a spring of the front wheel primary suspension system; the triaxial accelerometer II and the pressure sensor II are respectively arranged at the top and the bottom of a spring of the rear wheel primary suspension system; the non-contact displacement detection device is arranged at the position of a center shaft of the bogie. According to the invention, more accurate detection of the irregularity of the track can be realized, and online metering calibration of an original track detection system can be realized.

The invention discloses a dry quenching circulating air volume online prediction method and system based on an AGRU-PLS model, and belongs to the technical field of dry quenching production process intelligent prediction. According to the method, the production process data of the dry quenching full-process technology is collected, and a corresponding information database is constructed and stored; preprocessing the data, including cleaning and filling missing data, and finally performing standardization processing on the data; performing feature processing on the data in a correlation analysis mode, and finding out variable features with high correlation with the circulating air volume in the whole process; establishing an AGRU-PLS model, establishing a characteristic and circulating air volume covariance maximum model through an outer model, and solving a data collinearity problem in a mode of solving latent variables by iteration; the method comprises the following steps: establishing an Attention-GRU internal model, and mining nonlinear and dynamic relationships among data; the model is updated, and online prediction of the circulating air volume is achieved; and the prediction result of the circulating air volume is converted into a given value of the circulating fan, and the given value is written into UaExpert software to achieve control over the circulating fan.

The invention provides an obstacle association method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining measurement data from at least one sensor, and enabling the measurement data to comprise a plurality of obstacle measurements and detection information thereof; for each obstacle measurement to be associated, selecting a target reference point type from a plurality of predefined candidate reference point types according to detection information of the obstacle measurement to be associated; determining a measurement reference point from the detection information of the obstacle measurement based on a target reference point type selected for each obstacle measurement; determining a matching measure between a measurement reference point and a track reference point based on the measurement reference point measured by the obstacle and the track reference point determined for the fused track; according to the calculation result of the matching measurement between all the obstacle measurements and all the fused tracks, the association relationship between the obstacle measurements and the fused tracks is determined, and the accuracy and the reliability of obstacle association can be remarkably improved by adopting the method.

According to the pressure-temperature dual-mode sensor and the preparation method and application thereof provided by the invention, the pressure sensing layer is designed into the gradient inclined magnetic column array which is distributed in a rectangular array, and the gradient inclined magnetic column array has the layout characteristics of gradient change and inclination of the length, the position and the like of the magnetic columns; a special magnetic field gradient can be created in the space, and the magnetic field gradient can enable the pressure-temperature dual-mode sensor to generate linear or relatively uniform change response to external stimuli with different magnitudes, so that the measuring range of pressure testing can be widened; the problems of inaccurate measurement and small measurement range caused by the stress concentration problem of other microstructures and the large structure overlapping phenomenon are effectively solved. And meanwhile, the pressure sensing layer and the temperature sensing layer are tested in a layered manner, so that the problem of mutual crosstalk of a temperature signal and a pressure signal is avoided, and the detection accuracy and precision of the pressure-temperature dual-mode sensor are further improved.

The application discloses a feature placement method and system for multi-GPU sampling graph neural network training, uniformly models a sampling graph neural network training process, and obtains hardware topology information; in a pre-sampling process, the number of times of accessing node features is counted as node heat, the node features are sorted according to the node heat, the node features are divided into a plurality of feature blocks according to a single-block capacity, and the feature blocks are divided into hot blocks or cold blocks according to block heat; based on the feature block set obtained by the division and the obtained hardware topology information, a mixed integer programming model is constructed, with the minimum bottleneck link time in a feature extraction stage and the memory load imbalance degree as targets, the mixed integer programming model is solved, and the placement position, access path and link flow of the globally jointly optimized hot block are obtained. The application can obtain a high-quality feature placement scheme under a given hardware constraint, minimize the extraction time, and improve the resource utilization rate of a multi-GPU system.

The invention discloses an automatic magnetic field forming system which comprises a pressed blank conveying device, a boxing box, a conveying material box, a magnetic field pressing machine, a first glove box, a third isolation valve and a discharging box. The pressed blank conveying device comprises a conveying device shell and a conveying belt; the multiple magnetic field presses are connected to the conveying device shell side by side. The conveying device shell is fixed, and the magnetic field press can move relative to the conveying device shell. And the tail end of the pressed blank conveying device is connected with the boxing box. The pressed blank conveying device serves as a conveying channel of the automatic magnetic field forming system and conveys pressed blanks pressed by the magnetic field pressing machines into the boxing box. The pressed blank conveying device, the boxing box and the magnetic field pressing machine in the working state form a closed space, and the closed space is filled with protective gas; the conveying material box can move to the opposite face of the boxing box to be in butt joint with the boxing box, or the butt joint with the boxing box is relieved, and the conveying material box moves away from the boxing box. The invention further discloses an automatic magnetic field forming method which is implemented by adopting the automatic magnetic field forming system.

The invention relates to the technical field of DC high-voltage GIS insulation, and discloses a DC insulating gas state evaluation method and related equipment based on dark current measurement, and the method comprises the steps: obtaining insulating gas dark current signals under different gas pressures, different guide rod roughness and different electric field characteristics; processing the obtained insulating gas dark current signal to obtain an average dark current value corresponding to each electric field intensity; and evaluating the insulation margin of the insulating gas under different conditions on the average dark current value based on an SVM algorithm, and completing the state evaluation of the insulating gas. According to the invention, through real-time measurement and processing of the dark current signal, real-time monitoring and dynamic evaluation of the state of the insulating gas can be realized.