109 results about "Polynomial regression model" patented technology

The invention discloses a safety risk assessment system based on slope construction, relates to the technical field of slope construction, constructs a complete system composed of a data acquisition module, a dynamic disturbance identification module, a risk assessment module and an intelligent early warning and decision-making module, and acquires multi-source data such as displacement, cracks, pore water pressure, seismic disturbance and blasting vibration at high frequency. The time sequence analysis and disturbance feature extraction algorithm is combined to realize the rapid identification of the sudden disturbance event; risk score prediction is further carried out based on a polynomial regression model, and multi-level early warning is generated through comparison with a set threshold value; and finally, by combining the construction state, the support parameters and the disturbance intensity, a safety control suggestion is dynamically generated, so that the response speed and prediction precision of the system to the sudden slope instability risk are effectively improved, and real-time perception and intelligent management and control of the risk in the slope construction process are realized.

The invention provides an image color correction method and device, a color correction robot and a storage medium, and the method comprises the steps: obtaining a to-be-processed image, extracting the color value of each pixel point in a plurality of color blocks in the to-be-processed image, and obtaining a color value list; setting a weight coefficient for each color value in the color value list; fitting a polynomial regression model by using the color value list with the weight coefficient to obtain a fitted polynomial regression model; generating a color conversion matrix by using the fitted polynomial regression model, wherein the color conversion matrix is used for representing a mapping relation between a color value in the to-be-processed image and a standard color value in the colorimetric card; and correcting the color values of the pixel points in the to-be-processed image by using the color conversion matrix to obtain a corrected image. According to the embodiment, the color accuracy of the image is improved, the reliability and authenticity of image information are ensured, and therefore reliable data support is provided for subsequent intelligent analysis and auxiliary diagnosis.

The invention discloses a dynamic scheduling method for an intelligent manufacturing system, and particularly relates to the technical field of intelligent scheduling. Through a scheduling performance evaluation mechanism fusing a task switching interference index and a target function offset index, a polynomial regression model is utilized to realize scheduling health score prediction, and scheduling performance abnormity is accurately identified; under the abnormal condition, the system can dynamically adjust and dispatch a target function structure and algorithm disturbance parameters according to different index sources, the capability of jumping out of local optimum is effectively enhanced, and the global optimization effect is improved; through a closed-loop scheduling execution and feedback mechanism, the robustness, the self-adaptability and the execution feasibility of the scheduling system are remarkably improved, it is guaranteed that high-quality tasks are completed in time, and the overall production efficiency is improved.

The invention discloses a machine tool multi-source sensing method and system based on dynamic characteristic coupling analysis, and belongs to the technical field of machine tool monitoring. A polynomial regression model is used for evaluating and grading the accuracy of a coupling relation between node pairs, self-adaptive edge weight correction is carried out on incomplete accurate edges, and finally an optimized coupling network diagram and key network indexes are output, so that the authenticity and the stability of coupling recognition of the machine tool structure are effectively improved, and the accuracy and the reliability of the machine tool structure are improved. And a more reliable structure sensing basis is provided for subsequent operation state monitoring and fault prediction.

The invention provides a hyperspectral imaging-based traditional Chinese medicine organic acid content prediction method and system, and relates to the technical field of traditional Chinese medicine analysis and detection. The method comprises the following steps: acquiring the organic acid content of a traditional Chinese medicine sample, acquiring specific wave band reflectivity by using a hyperspectral imaging technology to construct a traditional Chinese medicine data set, calculating wavelengths, calculating wavelength derivatives, screening wavelengths possibly associated with the organic acid content, and grouping to establish an associated data set; and constructing a polynomial regression model by using the screened wavelengths possibly associated with the organic acid and the corresponding reflectance, and performing optimization through a correlation coefficient formula so as to predict the content of the organic acid, namely counting the proportion of the number of samples of which the residual error exceeds a threshold value for traditional Chinese medicines of which the actual content of the organic acid is different from the predicted value of the model, and determining the content of the organic acid in the traditional Chinese medicines. A model is independently constructed for traditional Chinese medicine types exceeding a proportion threshold value to predict the organic acid content, a prediction system is perfected, and a lossless and accurate solution is provided for detection of the organic acid content of traditional Chinese medicine.

The invention belongs to the field of phase change heat storage, and discloses a phase change heat exchange fin parameter optimization method and a related device.According to the method, a three-dimensional parameterized model of a tree-shaped fractal fin containing the length ratio, the width fractal dimension and the fin number is established, representative parameter sample points are efficiently generated through Box-Behnken experimental design, and the representative parameter sample points are optimized; and a liquid phase rate and a total heat storage capacity response value are obtained by combining numerical simulation of phase change heat transfer, and multi-target parameter global optimization is realized based on a second-order polynomial regression model. By the adoption of the method, optimization efficiency and precision are remarkably improved, on the premise that a large number of repeated experiments or simulations are not needed, the optimal fin structure parameters capable of cooperatively strengthening heat conduction, promoting melting of the phase-change materials and maximizing the heat storage capacity are rapidly obtained, and a reliable design basis is provided for engineering application of the fractal fin strengthening phase-change heat storage technology.

The invention discloses an automatic regulation and control method and device for a valve of a heat supply pipeline and a medium, and relates to the field of automatic control over a heat supply system.The method comprises the steps that the opening value of the valve of a target heat supply pipeline is obtained in real time, and according to the opening value, the heat difference and the heat difference change rate of the target heat supply pipeline are predicted through a fitted polynomial regression model; converting the predicted heat difference and the predicted heat difference change rate into corresponding membership values through a membership function, and obtaining a total membership value of a preset fuzzy set; performing matching in a fuzzy rule base based on the membership value, and determining a fuzzy value; performing defuzzification on the fuzzy value according to the total contribution and the total membership value of a preset fuzzy set to obtain a specific value of the valve adjustment amount; and adjusting the control parameters of the automatic controller based on the specific value. And by continuously optimizing automatic control parameters, the steady-state error of the system is reduced, the control precision of the system is improved, and it is ensured that the heat supply effect is more stable.

The invention relates to the field of LED screen control, and discloses a low-power-consumption LED screen control system and method for outdoor display, and the method comprises the steps: additionally arranging a radio frequency signal intensity detection unit, dynamically adjusting node connection, triggering self-inspection, comparing adjacent node data to correct errors, and building a polynomial regression model to correct a light intensity detection value. Based on the corrected light intensity detection value, constructing a reward function, calculating a state adjustment value, dynamically adjusting a driving voltage, constructing a temperature compensation model, determining a compensation coefficient, selecting a plurality of random feature subset training models and verification set errors to evaluate model performance, dynamically adjusting a tolerance value according to verification set error changes, and optimizing a model training process; the method comprises the steps of collecting environment light intensity data, predicting a future illumination change trend, dynamically adjusting a piecewise function turning point for optimal estimation, evaluating the influence of a geographical environment on illumination, optimizing and adjusting parameters, dynamically adjusting turning point parameters according to a prediction error, capturing a turning point of illumination intensity change, and analyzing and reducing power consumption.

The invention discloses an establishing method, a monitoring method and an adding method of a monitoring model for the concentration of hydrochloric acid in an etching solution. The establishing method of the monitoring model for the concentration of hydrochloric acid in the etching solution comprises the following steps: acquiring sample data; calculating each coefficient value in a pre-established multivariate polynomial regression model according to the sample data to obtain a regression model; obtaining verification data, taking the temperature, the oxidation-reduction potential, the hydrochloric acid concentration and the Cu < 2 + > concentration in the verification data as the input of the regression model, and outputting the predicted value of the conductivity; calculating the closeness degree of the predicted value of the conductivity and the actual value of the conductivity in the verification data; when the calculated closeness degree is smaller than a preset threshold value, recalculating each coefficient value in the regression model until the closeness degree is greater than or equal to the preset threshold value; and when the calculated closeness degree is greater than or equal to a preset threshold value, taking the obtained regression model as a hydrochloric acid concentration monitoring model.

The invention provides a process parameter optimization method and system for a functionally graded material and a medium, which can be applied to the technical field of process parameter optimization. According to the method, after corresponding technological parameters and forming response data under different component gradients are obtained through an orthogonal test, a quadratic term polynomial regression model used for representing the mapping relation between the technological parameters and the forming response data in the different component gradients is constructed according to the technological parameters and the forming response data. A quadratic term polynomial regression model is used as a virtual simulation environment, meanwhile, after a multi-dimensional continuous strengthening model is constructed based on a double-delay depth deterministic strategy gradient algorithm, based on the multi-dimensional continuous strengthening model, through dynamic interaction of an intelligent agent and the virtual simulation environment, an optimal process parameter combination is searched in different component gradients; and thus, cross-component gradient process parameter optimization is realized. And finally, verifying the optimal process parameter combination through a physical experiment, and determining the accuracy of model prediction.

The invention relates to the technical field of natural product extraction, and provides an extraction process for optimizing bougainvillea speetabilis bract total flavonoids by a response surface method.A bougainvillea speetabilis bract raw material is received and pretreated, a constant-temperature reflux and ultrasonic-assisted extraction technology is adopted, and Box-Behnken design in the response surface methodis combined, so that the bougainvillea speetabilis bract total flavonoids are obtained. Multi-factor interaction analysis is carried out on ultrasonic time, ethanol concentration and a material-liquid ratio, and a second-order polynomial regression model is established to predict an optimal extraction condition. According to the optimized extraction parameter combination, the ultrasonic time is 13.7 + / -0.5 min, the ethanol concentration is 60.0 + / -2.0%, the material-liquid ratio is 1: 29.7 + / -1.0, and under the conditions, the total flavone extraction rate can reach 8.48% or above. According to the method, the extraction efficiency of the bougainvillea speetabilis bract total flavonoids is remarkably improved, the process stability and the resource utilization efficiency are enhanced, meanwhile, the method has good industrial production suitability and technical innovation, and a new method is provided for extraction and utilization of the bougainvillea speetabilis bract total flavonoids.

The invention discloses a cloud service dynamic load balancing system based on an AI (artificial intelligence) agent, and particularly relates to the technical field of dynamic load balancing. According to the method, service node operation state portraits are constructed through multi-dimensional data acquisition, nonlinear relation modeling of RPS and load values is realized in combination with a dynamic polynomial regression model; and iteratively optimizing model parameters by adopting a batch gradient descent algorithm with regularization parameters, and selecting an optimal model through cross validation. The system introduces a double-threshold data queue management mechanism to guarantee timeliness and scale controllability of model training data, abnormal nodes are dynamically filtered based on a 3 sigma criterion, an instantaneous flow intensity sensing module is designed, an adjustment coefficient is comprehensively calculated through a baseline multiple, a resource occupancy rate and duration, and a real-time flow intensity sensing module is designed. And load prediction dynamic correction under burst traffic is realized. Compared with a traditional static strategy, the resource allocation efficiency and the overall robustness of the system in a high-concurrency scene are remarkably improved through cooperation of the self-learning ability of the AI model and real-time flow perception.

The invention discloses a photoresist consumption prediction method and device, a storage medium and equipment. The method comprises the following steps: acquiring the number of wafers fed in a to-be-predicted time length; using a preset polynomial regression model to predict the photoresist consumption in the to-be-predicted duration, and outputting a prediction result; the goodness of fit of the preset polynomial regression model is greater than that of a linear regression model. By adopting the scheme provided by the invention, the accuracy of predicting the consumption of the photoresist can be improved.

The invention discloses a bioretention facility design method based on numerical simulation and multi-objective optimization, and belongs to the technical field of rainwater management, and the method comprises the following steps: S1, obtaining a special background demand of a bioretention facility of a target area; s2: according to a filler selection layering model constructed by an analytic hierarchy process, inputting a special background demand into the filler selection layering model to obtain an internal optimal filler combination of the bioretention facility; s3, constructing a DRAINMOD hydrological model, and establishing a parameter space through BOX-Behnken experimental design to generate a plurality of groups of virtual working conditions; s4, simulating the multiple groups of virtual working conditions through a DRAINMOD hydrological model to obtain a simulation result; s5, on the basis of a sensitivity analysis method, key regulation and control parameters are determined according to simulation results; and S6, based on a simulation result, optimizing the key regulation and control parameters through a second-order polynomial regression model to obtain an optimal design parameter combination.

The invention relates to a subway station large passenger flow early warning method and system based on real-time data, and the method comprises the steps: obtaining the real-time mobile phone signaling data of a subway station and the surrounding, and carrying out the preprocessing of the real-time data; performing short-time passenger flow prediction and long-time passenger flow prediction based on the processed mobile phone signaling data; wherein the short-time passenger flow prediction adopts an ARIMA model to predict the passenger flow of each time window in the future set hours; according to long-time passenger flow prediction, an addition time sequence decomposition model is adopted to decompose a passenger flow sequence into a trend item, a season item and a residual item, the trend item is predicted through a polynomial regression model, the season item is predicted through a model based on Fourier series, and a long-time passenger flow prediction result is obtained based on the predicted trend item and the predicted season item; and performing early warning judgment according to the passenger flow prediction result and an early warning threshold dynamically updated based on the real-time passenger flow data. Compared with the prior art, the accuracy, timeliness and adaptability of large passenger flow early warning are effectively improved, and powerful support is provided for subway operation safety.

The invention provides a preparation method and device of a composite matrix for sewage treatment and a server, and relates to the technical field of water treatment material.The preparation method comprises the steps that center combination treatment is conducted on a ternary composite matrix for sewage treatment, and a test formula set is generated; obtaining test data corresponding to the test formula set, and taking the removal rate corresponding to each matrix as a response value to obtain target test data; substituting the target test data into a quadratic polynomial regression model of the ternary composite matrix to carry out regression analysis processing to obtain a model predicted value, and carrying out model verification updating processing on the quadratic polynomial regression model by utilizing the model predicted value and the target test data to determine a target quadratic polynomial regression model; and through the target quadratic polynomial regression model, optimizing the ratio of the ternary composite matrix, and determining the target mass ratio of the ternary composite matrix. According to the invention, the pollutant removal rate of synergistic decontamination of various pollutants in the sewage treatment process can be obviously improved.

The invention relates to an index prediction method and device for a regional economy space-time knowledge graph, and the method comprises the steps: constructing the regional economy space-time knowledge graph; performing knowledge representation learning on the spatial-temporal knowledge graph of the regional economy by using a preset relational graph convolutional network; determining target targeting indexes influencing regional economic development according to the cosine similarity; comparing index prediction degrees of a preset R-GCNs + XGBoost model, a preset random forest and a preset polynomial regression model for regional economic development; and predicting at least one key index of regional economy based on a preset R-GCNs + XGBoost model and the comparison data. According to the method, regional economy and the knowledge graph technology are creatively and deeply fused, inherent dynamic nature and space-time characteristics of economic development in a real scene are fully considered, and powerful technical support is provided for regional economy targeted index analysis and future index prediction by using powerful information organization and interpretation capabilities of the knowledge graph.

The invention discloses a sight tracking method and system based on cascade deep learning and distance correction, and a storage medium. The method comprises the following steps: processing an eye image through a cascade deep learning model, and obtaining pupil center coordinates and cornea reflection light spot coordinates of two eyes; calculating a binocular pixel distance as a distance correction factor based on the pupil center coordinates, and calculating a relative position difference vector based on the pupil and light spot coordinates; establishing a three-dimensional nonlinear polynomial regression model taking the relative position difference vector and the distance correction factor as input; obtaining calibration data through a multi-distance sampling strategy and solving a model coefficient; and in the real-time tracking stage, calculating the coordinates of the fixation point of the screen by using the solved model. According to the method, the distance correction factor and the three-dimensional mapping model are introduced, so that geometric errors caused by forward and backward movement of the head of the user are effectively eliminated, meanwhile, the feature point positioning precision is ensured through cascaded deep learning detection, and the precision and robustness of a sight line tracking system are remarkably improved.

The present application relates to the field of welding quality detection, and discloses a method for establishing a shear force prediction model for resistance spot welding, which includes the following steps: first, by acquiring the dynamic resistance curve data and welding process parameters in the resistance spot welding process, extracting key feature quantities and performing correlation analysis, and screening out features that are highly correlated with shear force; then, a multivariate polynomial regression model is established based on these features, and the shear force prediction model is further constructed using the XGBoost algorithm; in order to optimize the hyperparameter combination of the XGBoost model, the sparrow search algorithm is introduced for parameter tuning, and the initial population distribution of the sparrow search algorithm is optimized using chaotic mapping to enhance the global search capability; after training and verification, the weld shear force prediction model is finally obtained. This method can realize online real-time monitoring of welding quality, improve the automation level of the welding production process, and provide reliable technical support for resistance spot welding quality control.

The invention provides a traffic flow and charging station load prediction method based on deep learning, and aims to improve the precision of traffic flow prediction and accurately predict the load condition of an electric vehicle charging station. The method comprises the following steps of: firstly, predicting future traffic flow and traffic speed by adopting a space-time graph convolutional network model based on an attention mechanism; and secondly, based on the probability distribution of the daily travel distance of the vehicle, calculating the charging demand of the electric vehicle by using a hybrid model and an expectation maximization algorithm, and predicting the energy consumption of the electric vehicle through a polynomial regression model. And finally, based on the driving behaviors of the electric vehicles, an electric vehicle queuing model is constructed, the model comprehensively considers the behaviors of capacity limitation, overlong waiting time, intolerant leaving and the like of the charging station, and the load prediction of the charging station is calculated through a random Markov chain analysis method. The method can effectively capture the time-space characteristics of the traffic flow and the charging demand of the electric vehicle, and improves the accuracy of load prediction of the charging station.

The invention provides a direct drinking water equipment water quality data analysis and accurate control method based on an intelligent algorithm, and relates to the technical field of intelligent control of direct drinking water equipment.The method comprises the steps that water quality data including the total dissolved solid content, the pH value, the oxidation-reduction potential, the residual chlorine concentration and the temperature are collected in real time through a multi-sensor module; performing dynamic standardization preprocessing on the data to generate a multidimensional feature vector containing a timestamp; the water quality state is evaluated based on a water quality dynamic deviation index WDDI and a system response efficiency coefficient SRE, the WDDI quantifies the parameter dynamic deviation degree through a piecewise function, and the SRE represents the equipment response efficiency through a polynomial regression model; an NSGA-II algorithm and LSTM prediction are fused to generate a dynamic control strategy set; an optimal strategy is screened according to the real-time SRE value, and filter element mode switching, backwashing adjustment and sterilization power adjustment are driven; algorithm parameters are optimized through closed-loop feedback, and abnormal detection and safety mode switching are achieved in combination with an isolated forest algorithm.

The invention discloses a Tibetan antelope behavior analysis system based on multi-modal image fusion and an optimized transmission method, and belongs to the technical field of image fusion. Through synchronously acquiring an infrared image and a visible light image, performing registration, denoising and normalization processing on the infrared image and the visible light image, and extracting a temperature texture collaborative anomaly index and a spatial dynamic transaction index, the optimal transmission of the Tibetan antelope behavior analysis system is realized; constructing a polynomial regression model for identifying a non-target heat source, and outputting a high-temperature non-target object analysis value; the system divides a high-temperature area in the infrared image into a credible target level, an uncertain level and an interference level, and calculates a fusion interference risk value for the uncertain area in combination with the response strength and weight distribution of an image fusion algorithm; finally, Tibetan antelope behavior recognition is executed based on the fused image, the recognition confidence coefficient is dynamically adjusted in combination with the interference risk, and high-precision and anti-interference recognition of Tibetan antelope real behaviors is achieved. According to the method, the behavior recognition accuracy and ecological monitoring intelligence level of multi-modal image fusion in a complex environment are improved.

The invention relates to the technical field of earphone equipment, in particular to a Bluetooth earphone non-contact type dynamic control system and method based on gesture recognition, and the system comprises an induction signal collection module which obtains the total number of clock cycles and generates an original count value, a signal standardization module which carries out the operation of the original count value to generate a standardization intensity value, and a control module. The spatial feature distinguishing module is used for generating a spatial curvature gradient coefficient based on the standardized intensity numerical value and screening an effective intensity numerical value; and the linear mapping control module is used for performing nonlinear correction mapping on the effective numerical value, generating a vertical distance coordinate numerical value and generating a volume gain control parameter based on a change rate. According to the method, environment interference is eliminated through standardized data differential operation, effective fingertip control gestures and large-area skin contact are distinguished through space curvature gradient coefficients, a polynomial regression model is called to establish the corresponding relation between signal intensity and distance coordinates, non-contact hovering interaction is achieved, and ear canal compression and mechanical abrasion are avoided.

The invention discloses an inflatable rescue boat self-righting structure optimization method based on RSM-GA, and belongs to the technical field of ship engineering and optimization design, and the method comprises the steps: S1, employing computer aided design software to establish an inflatable rescue boat three-dimensional model, employing simulation software to carry out static stability analysis, and obtaining a three-dimensional model of the inflatable rescue boat; s2, establishing a second-order polynomial regression model of the self-righting capability and design parameters of the inflatable rescue boat by using a response surface method, quantifying interaction of the parameters, and determining an optimization target, and S3, performing multi-target optimization on the second-order polynomial regression model by combining a genetic algorithm, and obtaining optimal design parameters of a self-righting structure when engineering constraint conditions are met at the same time; according to the method for optimizing the self-righting structure of the inflatable rescue boat based on the RSM-GA, the stability and the safety of the rescue boat can be guaranteed, meanwhile, the sailing resistance is effectively reduced, the sailing efficiency is improved, and the self-righting capacity and the sailing performance of the rescue boat are remarkably improved.

The present application relates to a kind of shale oil carbon dioxide fracturing production dynamic intelligent prediction method, the method is applied to the improved AHP-GRA-EWM method quantitatively calculate the influence weight of different categories factors to different stage carbon dioxide fracturing-throughput shale oil well production dynamic parameter, obtain the main control influence factor of different production stage production dynamic parameter;The main control influence factor of different production parameters of different production stages is respectively introduced into different artificial neural network system, nonlinear polynomial regression model system and different percolation mathematical model, establishes prediction model, selects the model with highest prediction accuracy to correct improvement, combination generates the production dynamic intelligent prediction model of the entire production cycle of target shale reservoir block carbon dioxide fracturing-throughput shale oil well;Based on the intelligent prediction model, the different production parameter values of different production stages of new well are calculated, and the production dynamic curve is drawn.The method designed by the present application can realize the fine and efficient prediction of carbon dioxide fracturing-throughput shale oil well production dynamics, provide basis for the development of development plan and optimization, improve the single-well production and recovery ratio of target shale reservoir block.

The present application relates to the technical field of prosthesis lattice design, in particular to a kind of orthopedic implant lattice design method, system and application, by establishing parameterized lattice model sample set, and the polynomial regression model of elastic modulus and permeability coefficient is combined with the bayesian optimization framework with comprehensive score objective function as optimization goal, so that it can be iteratively optimized in parameter range efficiently, finally output optimal design parameter to make the mechanical property and mass transfer performance reach the best balance, fundamentally solve the problem that existing PEEK lattice implant design lacks double performance collaborative optimization, further improve lattice prosthesis postoperative recovery effect.

The invention discloses a sensitivity optimization method of a touch capacitance switch and the capacitance switch. The method comprises the following steps: acquiring a capacitance baseline value and environment temperature data in a non-touch state in real time, and updating the capacitance baseline value according to the environment temperature data; noise samples and real touch signals in different environments are collected, a training data set is constructed, and the noise samples and the real touch signals are distinguished by using a lightweight learning model; a touch event is determined based on the updated capacitance baseline value and the determination value. The invention further relates to the capacitance switch adopting the method. Through the technical means of a polynomial regression model, a Kalman filtering algorithm, a double-Kalman filtering architecture and the like, the problems that in the prior art, a capacitive touch switch temperature compensation model is insufficient in precision, noise classification depends on a fixed threshold value, complex environments are difficult to adapt, and adaptability to long-term sensor aging is lacked are solved. Wide application prospects are realized.

The present invention discloses a cloud service dynamic load balancing system based on AI intelligent body, which specifically relates to the field of dynamic load balancing technology. The method constructs a service node operation status portrait through multi-dimensional data collection, combines a dynamic polynomial regression model to realize nonlinear relationship modeling between RPS and load value, adopts a batch gradient descent algorithm with regularization parameters to iteratively optimize model parameters, and selects the optimal model through cross-validation. The system introduces a dual-threshold data queue management mechanism to ensure the timeliness and scale controllability of model training data, dynamically filters abnormal nodes based on the 3σ criterion, and designs an instantaneous traffic intensity perception module. The adjustment coefficient is calculated by comprehensively calculating the baseline multiple, resource occupancy rate and duration to realize dynamic correction of load prediction under burst traffic. Compared with traditional static strategies, the present invention significantly improves the resource allocation efficiency and overall system robustness in high-concurrency scenarios through the collaboration of AI model self-learning ability and real-time traffic perception.

The invention discloses a method for evaluating the influence of data-driven distributed photovoltaic grid connection on feeder line voltage fluctuation. According to the method, the thought of combining simulation data modeling and actual measurement data correction is comprehensively utilized, and accurate quantitative evaluation can be carried out on node voltage fluctuation characteristics in the absence of comprehensive monitoring conditions; a voltage variation polynomial regression model is constructed through a simulation sample, regression model parameter correction is carried out in combination with actually measured historical data, and finally distributed photovoltaic output is input to obtain a whole-network voltage variation sequence. And accurate prediction of node voltage fluctuation amplitude and frequency index caused by distributed photovoltaic output under the condition of incomplete monitoring data is realized through data processing. The method is high in accuracy and high in engineering applicability, is particularly suitable for being applied to a medium and low voltage power distribution system which comprises a plurality of photovoltaic access points and is relatively high in fluctuation characteristic, and has a good popularization prospect.

The invention relates to the technical field of bearing fault diagnosis, and discloses a bearing degradation starting point detection method based on an auto-encoder and an AOMM, and the method comprises the steps: collecting a real-time vibration signal of a bearing; obtaining a characteristic sequence of the real-time vibration signal by using an auto-encoder; obtaining a symbolized feature sequence of the real-time vibration signal according to an optimal symbol number obtained by pre-training; obtaining a plurality of sliding windows according to an optimal window size obtained by pre-training; an AOMM method is applied to adaptively adjust the Markov order based on the symbol distribution entropy and the polynomial regression model, and a state stationary probability matrix is obtained; and inputting the state stationary probability matrix and the label data into a pre-trained adaptive enhancement classifier for prediction, and outputting a predicted degradation starting point. According to the method, the degradation starting point is identified more accurately, and the problems that the feature extraction of the degradation starting point is not comprehensive and is greatly influenced by noise, and the detection of the degradation starting point depends on the signal amplitude and neglects the dynamic behavior of the signal are solved.