41 results about "Electricity" patented technology

A chip package includes a housing, one or more electrical connections coupled to an exterior of the housing, a photonic integrated circuit, and a scanning unit. Both the photonic integrated circuit and the scanning unit are disposed within the housing. The photonic integrated circuit has at least one waveguide designed to guide a beam of light. The scanning unit is designed to laterally scan the beam of light across a focal plane outside of the housing. The scanning unit is aligned with the photonic integrated circuit such that the beam of light is coupled between the photonic integrated circuit and the scanning unit.

The invention provides a test method and device for a motor active short-circuit relay, and a storage medium. The method includes the steps: performing the zero speed detection of a motor after a motor controller completes a low-voltage power-on operation, wherein when the motor controller is powered down, a first relay and a second relay are both switched on; controlling the second relay to be turned on if the motor passes the zero speed detection, and injecting a first excitation signal at the control ends of a first phase winding and a third phase winding through the motor controller; performing injection detection of the first excitation signal to determine whether the first excitation signal is successfully injected or not; controlling the first relay to be turned on if the first excitation signal is successfully injected, and obtaining a voltage across two ends of the first relay; and judging whether the power-on test of the first relay is successful or not according to the voltage across two ends of the first relay. The method can realize the turn-on test of the short-circuit relay, and ensures the reliability of the active short-circuit function of the vehicle motor duringdriving.

The invention discloses a disperse relaxation factor tidal current model based minimum electricity generating cost incremental quantity obtaining method. When a minimum electricity generating cost incremental quantity model only containing one balance node tidal current model is solved, the total demand unit change of a system is fixed on a balance node, and an obtained lambda, namely electricity generating cost minimum incremental quantity cannot reflect actual operation of the system in most cases during total demand unit change of a system. The disperse relaxation factor tidal current model based minimum electricity generating cost incremental quantity obtaining method adopts solves the provided model by means of an original antithesis interior point method, and the lambda of the system is controllable according to selected disperse relaxing factors.

The invention relates to a simple and reliable touch control switch. The simple and reliable touch control switch consists of a 12-V direct-current power supply, a one-way silicon controlled rectifier 1 (SCR1) trigger circuit, a one-way silicon controlled rectifier 2 (SCR2) trigger circuit, a relay control circuit and a load RL circuit. A conventional mechanical self-locking rocker switch or a toggle switch has the defects that actions are mechanical, operating actions are different because of persons, a contact is easy to jitter, a contact is easy to ablate, abrade and the like. The touch control switch is realized by only using a small number of common components and two touch metal pieces, namely an on-load circuit is switched on by touching a touch electrode once, and an off-load circuit is switched off by touching the touch electrode once. The overall touch control switch is made of discrete components, and strong electricity can be effectively isolated from weak electricity through a relay, so that the power supply of a load can use alternating current and also can use direct current. Therefore, the touch control switch has a certain function in the field of household appliances, industrial automation, and optical, mechanical and electrical integration.

The invention provides a multifunctional cycle power generation system and method by a gravity lever. The system comprises a supporting rack and a balance weight arranged on the supporting rack and slidably matched with the supporting rack, wherein engines are arranged on one side or two sides of the balance weight; the input shaft of each engine is connected to a transmission shaft; two or more single-directional clutches are fixedly connected to the middle of the transmission shaft; the locking directions of the single-directional clutches are same, gears are fixed to the peripheries of thesingle-directional clutches, and a rack matched with each gear to drive the transmission shaft to rotate is arranged next to each single-directional clutch; at least one pair of racks is arranged on the upper part and the lower part, separately, the racks and the balance weight which reciprocates are in driving movement and the balance weight is arranged on the supporting rack to swing through a lifting mechanism in a reciprocating manner. As the balance weight which swings in the reciprocating manner pulls the racks to drive the transmission shaft to rotate in the single direction, multiple engines can be driven synchronously to generate electricity synchronously, and the power needed by a supporting rack lifting device is alleviated greatly by means of a swing mode like to a lever, so that the energy sources are saved and the power generation efficiency is improved greatly.

The invention provides a high-power high-reliability voltage retainer used for an automobile starting and stopping system. The high-power high-reliability voltage retainer is higher in power and reliability and smaller in size and ripple. The high-power high-reliability voltage retainer comprises a through circuit module (1), a booster circuit module (2), a reversed polarity circuit module (3), a CAN transceiver (4), a CPU (5), a DSP (digital signal processor) (6) and a battery. A battery input port and a battery output port are formed in the through circuit module (1), a battery input port and a battery output port are formed in the booster circuit module (2), and the reversed polarity circuit module (3) is electrically connected with the booster circuit module (2); the CAN transceiver (4), the CPU (5) and the DSP (6) are sequentially and electrically connected; the CPU (5) is electrically connected with the through circuit module (1), and the DSP (6) is electrically connected with the through circuit module (1); the DSP (6) is electrically connected with the booster circuit module (2).

The invention belongs to the technical field of geological engineering monitoring and multi-physics field intelligent sensing, and discloses a separation grouting slurry migration monitoring method and system, and the method comprises the steps: constructing an acoustics-optics-electricity-electromagnetism multi-physics field coupling monitoring system; a grouting hole and a monitoring drilling hole array are arranged in a target stratum, a distributed optical fiber sensor, a drilling hole ultrasonic imager, a resistivity measuring device and a transient electromagnetic detection device are installed, and a three-dimensional monitoring network is formed; synchronously acquiring sound field, light field, electric field and magnetic field data; four-field monitoring data and overlying strata multi-parameter observation data are fused, a coal seam mining three-dimensional overlying strata separation model is constructed, and a slurry diffusion three-dimensional visualization model is generated through numerical simulation; and based on the four-field monitoring response difference of the separation space before and after grouting, in combination with a monitoring frequency domain correction model of multiple indexes of grout diffusion, the diffusion range, compactness and filling effect of the grouting grout are evaluated, and abnormal early warning is triggered.

The invention discloses a photovoltaic module early-stage fault early-warning method based on electric-thermal characteristic joint analysis, and belongs to the field of photovoltaic module early-stage fault early-warning, and the method comprises the steps: segmenting an irregular high-temperature or low-temperature region according to a temperature distribution image through employing a data segmentation algorithm, and extracting the boundary contour and area quantification characteristics of the abnormal region; performing joint feature vector construction by using the abnormal region boundary contour and area quantization feature and the current and voltage fluctuation amplitude in the electrical signal time sequence to obtain the comprehensive fault diagnosis vector; according to the preliminary fault classification label, extracting a temperature electrical corresponding association mode of a similar fault case from a historical fault diagnosis database, and obtaining an enhanced fault corresponding relation model; and generating a system risk assessment report by adopting the final fault diagnosis classification result, triggering a corresponding alarm mechanism, and judging the overall risk level of the renewable energy system.

The invention provides a heat preservation box capable of rapidly replacing a cold source. The heat preservation box comprises a box body and cold storage plates; the box body is provided with a box door, a cold storage area, a control area and a cold source area are arranged in the box body, the cold storage area is separated from the control area and the cold source area through a middle partition board, and the control area and the cold source area are separated through a side partition board; a backflow partition board is arranged in the cold source area, the cold source area is divided into a cold source cavity and a backflow cavity through the backflow partition plate, the cold source cavity communicates with the lower portion of the backflow cavity, a plurality layers of cold sourceframes used for containing the cold storage plates are arranged in the cold source cavity, and the cold source cavity communicates with the cold storage area through an air inlet channel; an exhaustfan is arranged on the air inlet channel, the cold storage area communicates with the backflow cavity through a backflow channel, and an air blower is arranged on the backflow channel; a control module is arranged in the control area, a first temperature sensor is arranged in the cold storage area, the exhaust fan, the air blower, and the first temperature sensor are electrically connected with the control module; and box body, the middle partition plate and the side partition plate are all made of vacuum composite plates. According to the heat preservation box, the replacement efficiency of the cold source is improved.

The invention discloses an abnormal Transform model-based electricity larceny detection method and device and a storage medium, and relates to the field of electric power system electricity larceny detection, and the abnormal Transform model-based electricity larceny detection method comprises the following steps: capturing complex correlation among different time points in sequence data by using a self-attention mechanism of a Transform model; the characteristics of the normal time point and the abnormal time point are effectively distinguished by learning the relevance difference of each time point, the accuracy of electricity stealing user identification is improved, and the misjudgment rate is reduced. The method comprises the following steps: S1, obtaining user multi-dimensional power consumption time series data, preprocessing the data, and constructing a sliding window sample; s2, constructing an electricity larceny detection model based on an Angle-Attention mechanism, wherein the electricity larceny detection model comprises a prior correlation branch and a sequence correlation branch; s3, quantifying the time dependence deviation of the power consumption behavior by taking the relevance difference as an anomaly judgment standard; s4, training the model by using a minimax optimization strategy, and amplifying the relevance difference between normal electricity utilization and electricity stealing electricity utilization; and S5, performing electricity larceny risk prediction and model performance evaluation through the joint score of the relevance difference and the reconstruction error.

The invention belongs to the field of life, and particularly relates to a thermos bottle with visible water storage capacity. The thermos bottle comprises a shell and an inner container arranged inside the shell. A base capable of vertically moving is mounted at the bottom of the shell, an elastic airbag is fixedly connected between the upper end of the base and the lower end of the inner container, a vertical strip opening is hermetically connected onto the side wall of the shell, a transparent tube is fixedly connected into the strip opening, the lower end of the transparent tube is communicated with the elastic airbag, and a piston block is hermetically connected into the transparent tube. The quantity of water in the thermos bottle can be known by observing the position of a piston block, a piezoelectric ceramic is used for power generation when water is injected, an LED (light-emitting diode) lamp in the piston block can emit light, the quantity of the water in the thermos bottlecan be known conveniently by people, and scalding is avoided. In addition, by the aid of an annular air cushion, when the thermos bottle falls, a good buffering function can be achieved, and impact onthe inner container is reduced.

The invention discloses an abnormal power consumption detection method and system based on multi-scale neighborhood density and a storage medium. The method comprises the following steps: S1, preprocessing original data; s2, carrying out adaptive granular ball representation on the original user sample set; s3, calculating a fuzzy relation matrix among the pellets; s4, calculating the fuzzy density of the pellets; s5, calculating a sample neighborhood density based on the Chebyshev boundary; s6, multi-scale neighborhood abnormal factors of all samples are calculated; s7, judging abnormal users in the power consumption data through threshold comparison; according to the method, the limitation of a current density-based anomaly detection method in adaption to the data characteristics of the electric power Internet of Things is solved, and the capability of depicting the multi-scale neighborhood density by the unsupervised learning model is improved.

The invention relates to a knitting machine and particularly relates to a controller for a yarn changer. The controller comprises a controller skeleton arranged on an outer plate of a yarn changer main body, a transfer bar, a digital circuit and a drive mechanism for driving the transfer bar to carry out linear motion, wherein the transfer bar is connected with the controller skeleton in a sliding manner; the transfer bar drives a yarn clamping and shearing device of the yarn changer to complete yarn selecting and yarn guiding actions while carrying out linear motion; the digital circuit and the drive mechanism are arranged on the controller skeleton separately; and the digital circuit is electrically connected with a drive mechanism. External drive is not needed, and the drive mechanism can be controlled to drive the transfer bar to carry out linear motion by virtue of the digital circuit, so that the transfer bar drives the yarn clamping and shearing device to complete the yarn selecting and yarn guiding actions, and independent control on yarn selecting and yarn guiding of the yarn changer is achieved; and the controller is small in impact vibration, high in applicability, stable in working, simple in structure and beneficial to improvement of the production stability of the knitting machine.

The invention provides a near-electricity risk early warning method and system based on electric field and magnetic field distribution. The method comprises the following steps: acquiring three-dimensional space electromagnetic field data in a target scene every first preset time; preprocessing the three-dimensional space electromagnetic field data, and constructing an electric field distribution model and a magnetic field distribution model according to the preprocessed electric field data and magnetic field data; respectively extracting a field intensity gradient amplitude and an electromagnetic field energy density from the electric field distribution model and the magnetic field distribution model, calculating a risk index of each space point according to the field intensity gradient amplitude and the electromagnetic field energy density, and dividing a risk area according to the risk indexes; and acquiring the current position of the operator, judging whether the current position is in the risk area, and if so, sending out early warning information. According to the method, the near-electricity risk can be comprehensively and accurately evaluated, the accuracy and effectiveness of early warning are improved, and the safety of operators is effectively guaranteed.

The invention discloses an electromagnetic heating system, and a method and a device for detecting the thermistor of the electromagnetic heating system. The method comprises the following steps of: recording the temperature value obtained by the thermistor as a first temperature value when the electromagnetic heating system is powered on; recording the temperature value obtained by the thermistoras a second temperature value when the electromagnetic heating system is in a standby state; obtaining the maximum temperature value and the minimum temperature value of the temperature value obtainedby the thermistor in a continuously preset second preset time every other first preset time during the heating process of the electromagnetic heating system; and judging whether the thermistor is ina failure state or not according to the first temperature value and / or the second temperature value, the maximum temperature value, and the minimum temperature value. The method for detecting the thermistor of the electromagnetic heating system judges whether the thermistor fails or not according to the static temperature values at the time of power-on and standby and the dynamic temperature valuein the heating process, so that the accuracy and the reliability of the judgment are greatly improved, and the safety of the system is improved.

The present application belongs to the technical field of electrical equipment state monitoring and fault diagnosis, and particularly relates to an automatic electricity stealing identification method based on data mining technology.The present application constructs an "electric-thermal-acoustic" multi-physical field coupling benchmark physical model through a BP neural network, mines the dynamic correlation law between the current and the temperature, acoustic emission physical quantities through the benchmark physical model, effectively captures the multi-dimensional physical quantity abnormal coupling characteristics caused by electricity stealing behavior, and through the model residual blood sequence output by the benchmark physical model, the deviation degree between the temperature measured value and the acoustic emission measured value of the actual collected power user equipment under the current power utilization state and the predicted value output by the BP neural network can be reflected, so as to strengthen the identification accuracy of electricity stealing behavior.

The invention relates to the technical field of electric power measurement, in particular to a method and a device for identifying the electric quantity of an electric energy substitution project, and the method comprises the steps: firstly obtaining a first electricity consumption data queue of the substitution project and a first factor influencing the electricity consumption of the substitution project; then selecting a dimension first conversion matrix according to the first factor, and performing dimension reduction and reproduction on the first electricity consumption data queue through the first dimension conversion matrix to obtain a second electricity consumption data queue; calculating the deviation between the first power consumption data queue and the second power consumption data queue, and standardizing the obtained deviation to obtain a first deviation queue; and finally, inputting the first deviation queue into a deviation analysis model, and determining the credibility of the first electricity consumption data queue according to the output of the deviation analysis model. The deviation analysis model is simple, so that resources consumed in the construction process and the application process are few, and the method is suitable for popularization.

The present application belongs to the technical field of microgrid stability analysis, and particularly relates to a stability analysis and early warning method for a building hydrogen-electricity coupling direct current microgrid, which comprises the following steps: obtaining electromagnetic transient state variables of an electrical subsystem in the direct current microgrid and electrochemical reaction state variables of a hydrogen energy subsystem, and constructing a unified feature matrix of time scale dynamic characteristics; extracting stability features, projecting the stability features to a low-dimensional space through nonlinear mapping, forming a representation fingerprint, and calculating an instantaneous stability margin under a current state; performing time sequence deduction, calculating a stability evolution trajectory within a future time window, and generating a predicted offset vector of an offset direction and amplitude; when the predicted offset vector exceeds the instantaneous stability margin, taking minimization of the predicted offset vector as an optimization objective, and generating a collaborative control strategy for collaborative regulation of a hydrogen energy subsystem operating point and an electrical subsystem operating point. The present application can realize perception and early warning of instability risks, and guarantee stable and reliable operation of the microgrid.

The invention provides an electric quantity theft detection method and system based on an ultrasonic vibration spectrum, and belongs to the technical field of electric quantity detection, and the method comprises the steps: constructing a correlation model, analyzing a target region feature and a user portrait, and presetting a feature threshold value of an electricity theft type and an abnormal triggering condition; capturing an ultrasonic signal, calling electricity load of an electricity meter and running state data of equipment, and carrying out time calibration and data fusion; converting the ultrasonic signal into a frequency spectrum feature vector, and screening out double abnormal targets with an ultrasonic feature anomaly and a behavior track anomaly; signal enhanced acquisition, power utilization data time sequence reconstruction and equipment state remote diagnosis are started for the double abnormal targets, and the electricity stealing behavior is confirmed; and outputting a targeted treatment instruction, and updating the feature threshold value and the abnormal triggering condition. According to the electric quantity theft detection method based on the ultrasonic vibration spectrum provided by the invention, the accuracy, real-time performance and high efficiency of electric quantity theft detection are realized through an active identification mode of accurate screening, multi-dimensional verification, targeted treatment and dynamic optimization.

The present application relates to the field of power system safety, and particularly relates to a high-voltage sensitive user electricity hidden danger identification method, system, device and medium, the method comprises obtaining a plurality of disaster-causing factors based on the electricity data of high-voltage sensitive users, and constructing a multi-dimensional factor vector with the plurality of disaster-causing factors as elements; obtaining a plurality of electricity hidden danger types based on historical electricity hidden danger and fault data, and constructing a hidden danger risk vector with the plurality of electricity hidden danger types as elements; using a multi-dimensional mapping function to establish a hidden danger risk mapping model of the multi-dimensional factor vector and the hidden danger risk vector, to obtain the risk values of various hidden dangers under the influence of the multi-dimensional factor vector; weighting the risk values of various hidden dangers according to the hidden danger severity weight to obtain a comprehensive risk index; using the comprehensive risk index to identify and warn the electricity hidden danger of high-voltage sensitive users, which significantly improves the scientificity and accuracy of identification.

This invention relates to the field of electrical testing technology, specifically to a method and system for detecting anomalies in electricity meters. The method includes: activating a wideband programmable power source to apply a composite excitation signal to the electricity meter under test; acquiring electrical parameters such as discrete current and voltage sequences to generate a heterogeneous operating condition dataset; generating a physical field correction tensor through a thermomagnetic dynamic correction model, performing physical field mapping operations on the discrete current and voltage sequences to generate an environmental hysteresis loop trajectory; receiving the environmental hysteresis loop trajectory, performing piecewise linearization analysis to generate a core depth saturation distortion index; and projecting the core depth saturation distortion index onto a metering error tolerance evaluation interval to generate a magnetic saturation metering anomaly signal. This invention, by constructing a strong coupling mechanism between environment, physics, and geometry, ensures that the anomaly judgment logic no longer relies solely on electrical thresholds, resulting in more accurate judgments of minor metering deviations induced by environmental factors.

This application provides a method and apparatus for electricity consumption forecasting. The method includes: acquiring the electricity consumption category and time of the day to be forecasted, historical load data, production plan data, workday data, production equipment status data, and meteorological data of the target location within a historical period; inputting the electricity consumption category, historical load data, production plan data, workday data, production equipment status data, and meteorological data into a feature filtering and processing module in an electricity consumption forecasting model to obtain a feature to be predicted in at least one dimension corresponding to the electricity consumption category of the day to be forecasted; inputting the electricity consumption time of the day to be forecasted and the feature to be predicted in at least one dimension into a load forecasting module in the electricity consumption forecasting model to obtain the target electricity consumption forecast result under the electricity consumption category within the electricity consumption time of the day to be forecasted. This application can accurately predict the electricity consumption under a specified electricity consumption category within a specified electricity consumption time period.

This invention discloses a method and system for analyzing abnormal electricity consumption data. The method includes: determining whether the sequence deviation between a first target electricity consumption data subsequence and a second target electricity consumption data subsequence is greater than a preset deviation threshold; if it is greater than the preset deviation threshold, they are defined as a first suspicious electricity consumption data subsequence and a second suspicious electricity consumption data subsequence, respectively, and performing electricity consumption data anomaly analysis on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence according to a preset first data analysis strategy; and based on the first suspicious electricity consumption data subsequence and the second suspicious electricity consumption data subsequence, using a preset second data analysis strategy to perform abnormal electricity consumption data anomaly analysis on a first non-target electricity consumption data subsequence adjacent to the first suspicious electricity consumption data subsequence and a second non-target electricity consumption data subsequence adjacent to the second suspicious electricity consumption data subsequence. This method can accurately identify abnormal electricity consumption data.

The invention provides a detection method and device for an electricity stealing behavior and electronic equipment, and relates to the technical field of power grid management. The method comprises the following steps: constructing a structure optimization model by adopting multi-scale feature extraction, spatial-temporal feature modeling, a channel attention mechanism, a dynamic adaptive network structure and lightweight design and multi-dimensional aggregation, and constructing a combined loss function based on weighted cross entropy loss and focus loss; an improved residual network is obtained based on the structure optimization model and the combined loss function, hyper-parameters of the improved residual network are adjusted and optimized by adopting a Bayesian optimization method, and an electricity stealing behavior detection model is obtained; and establishing an index system based on the confusion matrix and an electricity larceny detection threshold, and determining a detection result of the electricity larceny behavior according to the electricity larceny behavior detection model and the index system. According to the invention, the electricity stealing behavior detection accuracy can be improved.

The invention discloses a stress analysis method and system based on a multi-physics coupling GIS bus, and relates to the technical field of electric power, and the method comprises the steps: collecting engineering structure parameters, and determining a historical typical heat-electricity-force working condition operation parameter set; performing parameter missing region identification, and determining a parameter missing region set; respectively performing stress field completion on the parameter missing region set to obtain a completed stress field set; constructing a driving projection completion model based on the historical typical thermal-electric-force working condition operation parameter set, the parameter missing region set and the completion stress field set; and performing stress field completion analysis on the target GIS bus under thermal-electric-force multi-physics field coupling through the driving projection completion model, and determining a target completion stress field. According to the method, the technical problem that the stress missing area under GIS bus multi-physics field coupling cannot be accurately identified and complemented in the prior art is solved, and the technical effect of improving stress analysis integrity and accuracy is achieved.

The invention discloses a method for identifying safe and abnormal electricity consumption of an electric energy meter, and aims to solve the problems that temperature rise of a wire and a contact is difficult to identify in time and the early stage of fire is easy to miss under the condition that a temperature sensor is not added. According to the method, voltage and current are collected synchronously, the ratio of voltage variation to current variation is extracted based on current step to obtain equivalent series resistance and confidence, baseline resistance and environment proxy temperature are estimated in a low-load section, and a temperature sensor including wire temperature and temperature sensor temperature is constructed. A triple physical constraint ordinary differential equation of contact temperature and damage factors is adopted, assimilation observation is carried out, contact temperature slope and resistance drift are fused, and online change point identification and dynamic threshold grading early warning are carried out, so that advanced identification of an abnormal electricity-induced temperature rise trend is realized only by depending on voltage and current data of an electricity meter; the early warning advance is improved; the false alarm is reduced; and the robustness and the interpretability are enhanced.

This invention discloses a method for identifying electricity theft based on a multimodal large model, belonging to the field of electricity theft identification technology. The key technical solutions include the following steps: constructing a multimodal electricity consumption data acquisition system for power users; collecting structured electricity consumption data, unstructured on-site evidence data, and time-series load curve data from users' historical electricity consumption to form a multivariate dataset; generating a multimodal electricity consumption feature dataset based on the multimodal dataset; extracting core abnormal features related to electricity theft behavior based on the multimodal electricity consumption feature dataset to determine historical electricity theft target feature vectors; identifying correlation features in the multimodal electricity consumption feature dataset that have spatiotemporal or causal correlations with historical electricity theft target feature vectors. The effect is to achieve full-dimensional coverage of electricity consumption information, capturing both numerical features such as sudden drops in power consumption and abnormal line loss rates, as well as visual evidence such as on-site wiring diagrams and equipment images, significantly reducing the probability of missed or false positives.

The invention discloses a remote anti-electricity-stealing monitoring and alarming method based on artificial intelligence, and particularly relates to the field of power monitoring, which comprises the following steps: S1, multi-source data acquisition: acquiring user electricity consumption data and power grid operation data based on a preset frequency, S2, primary data processing: performing abnormal value processing, noise data processing and missing data processing on the acquired data, and S3, carrying out secondary data processing on the acquired data. S3, carrying out secondary data processing, carrying out standardization processing on numeric data after primary processing, and carrying out data coding on non-numeric data; S4, carrying out electricity consumption abnormity marking based on time sequence analysis, constructing an autoregression integral moving average model, predicting future electricity consumption power and comparing the future electricity consumption power with real-time power; S5, carrying out electricity stealing identification, and establishing a theoretical calculation model to calculate power deviation. And extracting harmonic characteristics to calculate a distortion rate, and comparing with a preset threshold to judge an electricity stealing behavior. Through multi-dimensional data acquisition and intelligent analysis, the anti-electricity-stealing identification precision is improved, and stable operation of a power system is effectively guaranteed.

This invention discloses a semi-normalized electricity load regression prediction method and system, comprising: explicitly defining and collecting known influencing factors affecting electricity load; constructing an electricity load prediction model, wherein the electricity load prediction model is used to calculate the predicted electricity load value; performing a first-step training, based on historical electricity load data and historical known influencing factors, training the weights of each known influencing factor and the random error term in the electricity load prediction model; performing a second-step training, based on the results of the first-step training, extracting the residuals, training the coefficients of unknown influencing factors in the electricity load prediction model, and summarizing the statistical regularities of the unknown influencing factors; inputting the known influencing factors at the time to be predicted into the trained electricity load prediction model, and calculating the predicted electricity load value at the time to be predicted. This invention reduces the data length requirement, enables small-sample learning, can explicitly integrate known regularities, and enhances flexibility and interpretability.

The invention discloses an electricity stealing behavior detection method based on granular ball fuzzy information entropy, and the method comprises the steps: obtaining multi-source data in a power system, carrying out the normalization processing of the multi-source data, and constructing granular balls with different granularities according to a processed data set; calculating the relative fuzzy entropy of each particle ball; forming a combined particle ball, calculating a local reachable distance according to the combined particle ball, and calculating a local abnormal degree of the power consumption sample in the combined particle ball according to a local reachable density difference; performing weighted calculation on the final electricity stealing anomaly score of each electricity consumption sample by combining the global anomaly degree of the pellets and the local anomaly information of the electricity consumption samples; whether the abnormal scores of the data are larger than an abnormal score threshold value or not is judged one by one, if yes, the electricity stealing behavior is judged and an abnormal result is output, and if not, the normal electricity utilization data is judged. According to the method, the global mode and the local details of the electricity stealing behavior are accurately captured, and the accuracy of the detection result is remarkably improved.