12results about How to "Determine science" patented technology

The invention relates to the technical field of offshore wind power operation risk analysis, and discloses an offshore wind power operation risk analysis system based on deep learning, and the system comprises a data collection and preprocessing module which is used for collecting wind power equipment operation state data and environment data of multiple types of sensors, and carrying out the cleaning and preprocessing of the data; the multi-modal data fusion and feature extraction module is used for extracting and fusing multi-modal features from different data sources; and the real-time risk prediction and intelligent decision module is used for analyzing the operation state of the wind power equipment in real time based on a deep learning model, and performing prediction and alarm when a fault trend is detected. By introducing a self-attention mechanism and a Transform architecture, deep fusion analysis is performed on multi-modal data from wind power equipment, and information of different data sources can be weighted and integrated in a unified feature space, so that the system can adaptively focus on important features, and the analysis precision and fault detection capability of the multi-modal data are remarkably improved.

The invention relates to the technical field of permanent magnet motors, in particular to a winding connection selection method and device for reducing the short-circuit demagnetization risk of a permanent magnet motor, and the method comprises the steps: when the permanent magnet motor is in a three-phase short-circuit state, taking the relation between the torque loss ratio of star connection and delta connection at different permanent magnet temperatures and different starting rotor positions as the basis; finding a target permanent magnet temperature threshold value; if the permanent magnet temperature is higher than a target permanent magnet temperature threshold value, triangular connection is selected, and otherwise, star connection is selected; when the permanent magnet motor is in a two-phase short-circuit state, a first intersection rotor position and a second intersection rotor position at the current permanent magnet temperature are found on the basis of the relation between the torque loss ratio of star connection and triangular connection at the current permanent magnet temperature and different starting rotor positions, and then the two-phase short-circuit state of the permanent magnet motor is determined according to the intersection rotor positions. And a proper winding connection mode is selected. The operation reliability of the permanent magnet motor can be improved, and it is ensured that the short-circuit demagnetization risk of the permanent magnet motor is effectively reduced.

The invention discloses a bay water quality monitoring station layout optimization method, and the method comprises the steps: carrying out the grid division of a research region, and obtaining data points; determining an initial range of algorithm search according to the characteristic values of the data points; the optimal step length of data point updating is determined by calculating gradient and curvature information of a target function, the position of the data point is updated based on the comparison result of the actual decline amount and the predicted decline amount of the target function, loop iteration is carried out until the preset convergence condition is reached, and the finally obtained position of the data point is the bay water quality monitoring station site. On the basis of the trust region mapping method, the site selection and layout problem of the bay water quality monitoring stations is rapidly solved through the particle swarm optimization algorithm, the appropriate number of stations can be given according to requirements when the number of the monitoring stations is not restrained, calculation reasonability is high, and the method has high application value.

The invention provides an urban inland inundation risk analysis method and device and electronic equipment, and belongs to the technical field of data processing, and the method comprises the steps: building an urban surface inundation simulation model, and obtaining an urban inland inundation ponding map; performing superposition analysis on the facility distribution diagram, the population distribution diagram and the waterlogging ponding diagram to obtain a ponding risk value, a plurality of sub-facility influence values, a plurality of sub-population influence values and a plurality of sub-economic loss values of each grid unit; determining a waterlogging risk grade value of any grid unit based on a weighted summation result of the plurality of sub-element values; the first weight of the plurality of child element values is predetermined based on the importance degree of the child element relative to the parent element; and determining a waterlogging risk grade map of the city based on the waterlogging risk grade values of all the grid units. According to the method, the self influence and extension influence caused by waterlogging and ponding events in the city can be comprehensively considered, the waterlogging risk grade map of the city can be determined more scientifically and reasonably, and the region seriously influenced by waterlogging in the city can be accurately identified.

The invention relates to a method for predicting the damage degree of an island building group after being hit, and the method comprises the following steps: dividing the island building group into n building samples, and distributing different damage evaluation weights for each building sample; random variables influencing the damage degree of the island building group are screened, and related parameters of the random variables are determined; establishing an island reef building group damage model; generating m groups of data of random variables based on a random sampling method, inputting the m groups of data into the island building group damage model for damage simulation, and obtaining damage data of each building sample; setting a damage threshold value, judging whether the damage data of each building sample reaches the damage threshold value or not, and determining the damage failure rate of each building sample; and determining the average damage target number of the island building group. The method can perform toughness evaluation on the anti-deliberate strike capability and damage degree of the deep sea island building group, considers the uncertain data boundary of the complex environment, and provides scientific data and information basis for the determination of the protection grade of the deep sea island.

The present invention provides a method for designing parameters for strong compaction treatment of saturated soft soil foundation, which belongs to the technical field of foundation treatment and solves the problem in the prior art that the spacing between tamping points and the interval time between two tampings are mainly determined by engineering experience. Before construction, a monitoring hole is arranged at the center of the test area, and a pore water pressure monitoring sensor is installed in the monitoring hole; tamping construction is carried out at positions with different distances from the monitoring hole, and the pore water pressure monitoring sensor monitors the size of the excess pore water pressure generated in the monitoring hole when the tamping construction is carried out at positions with different distances; the minimum distance between two tamping points that meet the tamping requirements and the minimum value of the interval time between two tampings are obtained by calculation. In the case of obtaining the permeability coefficient based on geological survey data, the method provided by the present invention can be used to more scientifically and reliably determine the spacing between tamping points and the interval time between two tampings, so that the construction period can be reasonably planned and the tamping cost can be saved.

The invention relates to the technical field of oil-gas exploration, and discloses a shallow fault lateral sealing performance evaluation method, which comprises the following steps: S1, data collection and preprocessing: collecting lithology data, hydrocarbon reservoir depth data D, fault displacement data T, fluid properties, pressure conditions and temperature of a fault hanging wall and a footwall of a research area; s2, calculating the smearing of the fault hanging wall mudstone on the research point: calculating the mudstone smearing ASGRHih of all calculation points on the research point of a single mudstone Hih, and superposing the mudstone smearing of all the mudstones on the research point in the fault hanging wall to obtain ASGRh; s3, calculating the smearing of the fault footwall mudstone on the research point: calculating the mudstone smearing ASGRHif of all calculation points on the research point of a single mudstone Hif, and superposing the mudstone smearing of all the mudstones on the research point in the fault footwall to obtain ASGRf; and S4, multi-source data fusion and comprehensive evaluation: determining a threshold value Q by using K-means, and performing customized adjustment by considering the geological background, fault type and oil and gas reservoir characteristic factors of the research area.

The application provides a radiation work risk grade determination method and system based on quantitative analysis. The method comprises the following steps: obtaining a radiation risk grade corresponding to each risk value and each item that has an influence on the radiation risk; determining each radiation risk quantitative analysis item and a weight corresponding to each radiation risk quantitative analysis item according to each item that has an influence on the radiation risk; establishing a radiation risk analysis model based on each radiation risk quantitative analysis item, the weight corresponding to each radiation risk quantitative analysis item, and the radiation risk grade corresponding to each risk value; obtaining each work parameter data corresponding to radiation work, and determining a risk grade corresponding to the radiation work based on the radiation risk analysis model. The technical scheme provided by the application can quantitatively, scientifically and accurately determine the risk grade of the radiation work of a nuclear power plant.

The invention relates to the technical field of water conservancy and hydropower engineering, and discloses a diversion tunnel, flood spilling tunnel, flood discharge and sand discharge tunnel and ecological drainage tunnel combined structure and a construction method thereof. The structure comprises a flood spilling tunnel vertical shaft section, the diversion tunnel is formed in one end of the bottom of the flood spilling tunnel vertical shaft section, and a flood spilling tunnel recession tunnel section is arranged at the other end of the bottom of the flood spilling tunnel vertical shaft section; the flood spilling tunnel recession tunnel section is connected with the flood spilling tunnel vertical shaft section through a horizontal pressure slope section; a stilling pool, a diversion tunnel and a spillway tunnel vertical shaft section are arranged at the tail end of the spillway tunnel recession tunnel section, and an ecological drainage tunnel is arranged below the spillway tunnel recession tunnel section; the flood spillway vertical shaft section comprises a vertical shaft, a stilling well is downwards formed in the bottom end of the vertical shaft, a service gate is arranged on the side, close to the diversion tunnel, of the vertical shaft, when the service gate is closed, the service gate is used for playing a flood spillway function, and when the service gate is opened, the service gate is used for playing a flood discharge and sand discharge function. The structural arrangement and the construction method have the advantages of reducing the engineering quantity, shortening the construction period, saving the engineering investment and the like.

The invention relates to the field of bridge construction, and discloses a method for determining the tension releasing time of a pre-tensioned box girder by combining hydration heat and mechanical properties, and the method comprises the following steps: arranging a temperature sensor and a strain gauge in a first girder of each batch of prefabricated pre-tensioned box girders to monitor the change of the hydration heat effect and the stress of a steel strand; testing the compressive strength and elastic modulus of concrete at different ages along with a beam curing concrete test block, and preliminarily drawing up a tension releasing age according to the early-age mechanical property; by analyzing the development of the temperature difference between the core part and the superficial part of the pre-tensioned box girder, the temperature difference between the superficial part and the environment and the temperature difference between the core part and the mold entering temperature along with time, the tension releasing time is controlled based on the hydration heat effect; and finally, combining the hydration heat effect of the box girder and the mechanical property of concrete, and comprehensively determining the prestress releasing time based on temperature-stress double control. According to the method, the situation that prestress releasing is conducted when hydration heat is still obvious is avoided, beam body cracking and extra prestress loss caused by too large stress are prevented, and the bearing capacity and durability of the prestress pre-tensioned box beam are guaranteed.

The invention discloses a UPFC configuration optimization method and system, and the method comprises the steps: carrying out the analysis of the obtained topological structure information and operation parameters of a target power system, so as to construct a key channel line set; simulating power grid power flow distribution after the UPFC to be configured is connected to different key channel lines, and calculating load rates of the key channel lines based on simulation results of the power grid power flow distribution; calculating weighted power flow entropy according to the load rate, and taking the key channel line with the minimum weighted power flow entropy as the optimal access line of the UPFC to be configured; performing load flow calculation on the power grid operation state of the target power system in the preset fault scene, and calculating the power transfer support strength of the key channel line according to a load flow calculation result; and establishing a UPFC grid-connected capacity optimization model, and calculating the UPFC grid-connected capacity optimization model to obtain the optimal capacity of the UPFC to be configured. The method provided by the invention can be widely used for optimizing the power flow distribution of the regional power grid.

The invention provides a battery cell sampling method and a method for testing the moisture content in a battery cell. The sampling method comprises the following steps: (1) carrying out vacuum baking treatment on a battery cell to obtain a baked battery cell; (2) sampling the baked battery cell in the thickness direction, the length direction and the width direction, and sampling a positive pole piece, a negative pole piece and a diaphragm at each sampling point to obtain a sample of which the moisture content is to be detected. According to the sampling method provided by the invention, the most representative moisture content test position in the battery cell can be scientifically and accurately obtained, so that the safety risk and battery performance degradation caused by unqualified moisture are avoided; meanwhile, the highest position of the water content is taken as a subsequent batch production sampling point, so that the detection time can be greatly saved, and the detection efficiency is improved.