317 results about "Multiple linear regression model" patented technology

The invention relates to the technical field of water treatment intelligent control, in particular to an AI-based intelligent urban water purification and sewage treatment process optimization system and method, and the method comprises the steps: obtaining related sensor data information, and monitoring and recording the change of key data in real time; establishing a water quality change prediction model by using a multiple linear regression model, wherein the water quality change prediction model predicts the water quality change according to the key data change acquired in real time; the dynamic agent AI model adjusts the dosage, and the water treatment chemical / biological reaction kinetics AI model predicts the pollutant degradation condition; a local lightweight AI model optimizer and a multi-target genetic algorithm are combined with energy consumption, medicament cost, processing efficiency and carbon emission to obtain an optimal control model; the optimal control model optimizes the operation parameters of the sewage treatment process according to the pollutant degradation condition. According to the method, the operation parameters of the sewage treatment process are optimized through the optimal control model, the energy consumption, the agent cost and the carbon emission are reduced, and the treatment efficiency is improved.

The invention discloses a reservoir group delivery flow prediction method considering climate change and artificial regulation and storage. The method comprises the following steps: collecting hydro meteorological data of a research basin; determining an upstream inlet reservoir, an interval reservoir and an outlet reservoir according to the reservoir position distribution of the research basin; determining reservoir inlet flow calculation modes of the reservoirs at different positions and reservoir outlet flow models of the reservoirs; and for the outlet reservoir, according to the outlet flow of the upstream reservoir and the hydrometeorological data, the reservoir inlet flow of the reservoir is obtained through a vector autoregression model or a multiple linear regression model, the outlet flow simulation of the reservoir is carried out, and an outlet flow residual prediction model based on deep learning is established, so that the outlet flow prediction of the outlet reservoir is realized. According to the method, the influence of the artificial regulation and storage effect of the reservoir on the downstream reservoir is considered on the basis of the inflow and outflow hydraulic relation between the reservoir groups, and the outflow process of the downstream reservoir is predicted by combining the conceptual rainfall runoff model, the reservoir regulation model and the deep learning model.

The invention discloses a battery charging control method for a battery replacement cabinet based on the Internet of Things, relates to the technical field of charging control, and has higher adaptability in the aspects of battery replacement demand prediction, charging mode switching and charging safety management compared with a traditional fixed charging mode. The problems of sudden increase of battery replacement demands, changes of environmental factors and the like can be effectively solved, and the operation stability of the battery replacement cabinet is improved; the method comprises the following steps: acquiring a battery state, a battery replacement demand and meteorological data, predicting a future battery replacement demand curve in combination with a long-short term memory (LSTM) network and a multiple linear regression model, introducing a meteorological influence factor, adjusting a charging plan of a battery replacement cabinet 24 hours before severe weather early warning, and matching the battery stock with a peak demand; the charging modes comprise a fast charging mode, a general charging mode and a slow charging mode, dynamic switching is carried out according to the battery replacement demand peak value and the daily average battery replacement demand, the fast charging mode is preferentially adopted in the battery replacement peak period, the battery supply rate is increased, and meanwhile part of charging resources are reserved.

The invention discloses a switch cabinet discharge detection method and system, and relates to the technical field of power equipment state monitoring and fault diagnose.The light intensity attenuation rate and the vibration frequency are collected through a photonic crystal fiber, the concentration of decomposed gas is detected in combination with a Raman spectrum, and a space-time joint feature matrix is generated; performing space weight distribution on the space-time joint feature matrix based on the switch cabinet structure, and inputting the space weight to an RBF-SVM (Radial Basis Function-Support Vector Machine) to generate discharge type probability distribution; based on a high-frequency energy parameter and a gas decomposition concentration parameter in the spatio-temporal joint characteristic matrix, inputting the parameters into a multiple linear regression model, calculating an insulation aging index, and judging an insulation degradation grade according to a threshold value; the photonic crystal fiber is used for collecting the light intensity attenuation rate and the vibration frequency, the Raman spectrum is combined for detecting the decomposition gas concentration to generate the space-time joint characteristic matrix, synchronous monitoring of various physical and chemical parameters in the switch cabinet is achieved, and the accuracy and comprehensiveness of recognition of different types of discharge phenomena are improved.

The invention discloses a method, a system and equipment for optimizing batching parameters in an industrial silicon smelting process. The method comprises the following steps: firstly, acquiring process parameters in an industrial silicon smelting process, standardizing the process parameters, then converting the process parameters into weight factors influencing a smelting result, and mapping a relation between the smelting result and the weight factors into a parameter equation based on a preset multiple linear regression model, obtaining a parameter set containing a weight factor and a linear regression coefficient; then, based on the parameter set, the initial raw material parameters and the reaction process parameters, an equivalent circuit model is constructed and simulated to generate smelting result data under different parameter combinations, and therefore parameter adjustment variables are obtained; according to the numerical range of the parameter adjustment variables and the initial raw material parameters, an optimal batching parameter combination is obtained; and finally, performing optimization treatment on batching parameters in the industrial silicon smelting process. According to the method, accurate control and rapid optimization adjustment of batching parameters can be stably achieved in the industrial silicon smelting process.

The invention discloses an OVOC source analysis method, system, medium and equipment in the atmospheric environment, and relates to the technical field of environmental protection, and the method comprises the steps: monitoring the environment, and collecting pollutant concentration data and environmental data during observation; analyzing a plurality of pollution sources of the primary emission part of the OVOC and the concentration of each compound in each pollution source by utilizing a multiple linear regression model and an atmospheric pollutant source analysis receptor model; and inputting into an atmospheric photochemical box-type model to simulate the net generation rate of each oxygen volatile organic compound. The pollution source concentration is quantitatively reduced, the pollution source concentration and other pollution source concentration data which are not reduced are respectively input into an atmospheric photochemical box-type model to simulate the net generation rate and sensitivity of each OVOC, and quantitative analysis of the secondary generation process of the oxygen-containing volatile organic compounds is realized through a relative increment reaction activity coefficient method. Weighted calculation is carried out on the proportion of a primary emission source and a secondary generation source obtained through a multi-line element regression method, and full-process OVOC source quantitative analysis in the atmospheric environment is achieved.

The invention relates to the technical field of carbon emission treatment, in particular to a building full-life-cycle carbon emission calculation method based on multiple linear regression. Comprising the following steps: acquiring carbon emission data of each stage of a building through a BI model, and extracting key characteristic variables such as a material carbon emission coefficient and energy consumption intensity by adopting a Latin hypercube sampling method and a fuzzy clustering algorithm; modeling carbon emission by using a multiple linear regression model, and constructing a carbon emission prediction model; optimizing model parameters through a differential evolution algorithm; and finally, calculating the total amount of carbon emission, analyzing key influence factors in a high-carbon emission stage through a causal reasoning algorithm, proposing an optimization strategy, generating an analysis report, and realizing accurate prediction and effective optimization of the carbon emission in the whole life cycle of the building. According to the method, the carbon emission of the whole life cycle of the building can be accurately evaluated, and powerful support can be provided for optimization decision-making of the carbon emission.

The invention belongs to the technical field of high-speed monitoring point optimization, and provides an intelligent traffic system high-speed monitoring point layout optimization method and system, and the method comprises the steps: obtaining the information of a target monitoring road; according to road characteristics and a traffic jam model, determining a preliminary area set by each monitoring point; taking a congestion point identification increasing quantity and a traffic flow variable quantity after an emergency lane is started as positive indexes, taking monitoring cost as a negative index, and constructing a corresponding benefit evaluation function to form a target function; and solving by utilizing a quantum particle swarm optimization algorithm, or obtaining a plurality of optimization schemes by adjusting the number of monitoring points and uniformly distributing the monitoring points, evaluating the obtained optimization schemes based on a multiple linear regression model, and selecting a final optimization scheme. According to the invention, reasonable design of monitoring points can be ensured, effective monitoring of traffic congestion is facilitated, and whether an emergency lane is temporarily started or not is considered.

An expressway holiday travel traffic volume prediction method based on the influence of a weather factor, said method belonging to the technical field of road traffic flow prediction. In order to solve the problem of accurate holiday expressway travel traffic volume prediction based on the influence of a weather factor, the method of the present application comprises: establishing a relative influence coefficient between historical weather and travel traffic volume; constructing a travel traffic volume transfer model based on weather data; selecting basic travel traffic volume features, constructing derived travel traffic volume features by means of a cross operation between the basic travel traffic volume features, and then constructing a multiple linear regression model based on historical travel traffic volume features; correcting a predicted travel traffic volume obtained by the multiple linear regression model; correcting a predicted travel traffic volume of the remaining days of a holiday; constructing a layered flow road network travel traffic volume model; and constructing an objective function, and using a reverse gradient propagation method to optimize and solve the layered flow road network travel traffic volume model, so as to obtain an expressway holiday travel traffic volume prediction result based on the influence of a weather factor.

The invention discloses an indoor temperature and humidity spatial data prediction method fusing spatial interpolation and a graph convolutional network, and relates to the field of smart city and environment monitoring, and the method comprises the steps: obtaining indoor multi-point temperature and humidity data actually measured by a sensor, and the spatial position information of a monitoring mark point corresponding to the indoor multi-point temperature and humidity data; the temperature and humidity data, the spatial position information and the time dimension features of the marked points are used as input of Kriging interpolation, and temperature and humidity linear predicted values of part of unmarked points are generated; constructing a multiple linear regression model taking the Kriging prediction result, the measured data of the mark points, the time dimension characteristics, the spatial characteristics and the external meteorological data as independent variables and the target temperature and humidity values as dependent variables, and performing multi-dimensional fitting on the Kriging interpolation result; and constructing a feature matrix by using a linear predicted value output by the regression model and other features, and taking the feature matrix and an adjacent matrix as input of a graph convolutional network to generate indoor temperature and humidity three-dimensional space distribution. According to the invention, high-precision indoor space data prediction can be realized.

The invention discloses a roadbed settlement prediction method and system for a permafrost region. The roadbed settlement prediction method comprises the steps of obtaining roadbed historical data corresponding to the permafrost region; intercepting data of a preset fixed length and settlement monitoring data corresponding to the data of the preset fixed length at a future moment, and constructing a permafrost region roadbed settlement sample database; building a base model; training the base model through the established database to obtain a trained base model; outputting a preliminary prediction result through the trained base model; the prediction result of the base model is used as the input of a meta-model through a stacking model, the meta-model is a multiple linear regression model, the prediction results of multiple prediction units of the base model are integrated, and the roadbed settlement corresponding to the final permafrost region future moment is output. According to the method, prediction results of a plurality of models are fused, so that the final model is more robust for abnormal values and noise data, and the stability of training prediction of the model for large fluctuation of roadbed settlement data in the frozen soil region is improved.

The invention discloses a sales volume prediction method based on second-order cross multiple linear regression and a terminal. The method comprises the following steps: dividing obtained historical sales data into a training set and a test set; obtaining a to-be-adjusted value in the training set and a default value corresponding to the to-be-adjusted value; calculating a target tensor corresponding to the test set, and generating a mask at the position of a default value unequal to the target tensor; and training the initial second-order cross multiple linear regression model according to the training set to obtain a target second-order cross multiple linear regression model, and ignoring the mask when a loss function is calculated. According to the method, the data with masks are ignored when the loss function is calculated in the iteration process of the model, so that the quality requirement on the original training data is reduced, the high-error part in the original training data is automatically ignored in the iteration process of the model, the influence of the low-quality part in the original training data on the model training is reduced, and the training efficiency is improved. The prediction precision of the model is improved under the condition that the original training data quality cannot be further improved.

The invention relates to electroencephalogram signal acquisition, in particular to an electroencephalogram signal acquisition and monitoring system, which comprises a mobile terminal, a signal acquisition device, an EEG (electroencephalogram) signal, an fNIRS hemodynamic signal and IMU (inertial measurement unit) motion data, a physical information neural network method of a self-adaptive sampling strategy is adopted to identify a BCG vascular pulse pseudo-film segment in an EEG signal by using an fNIRS hemodynamic signal, and then a multiple linear regression model of motion artifacts is established based on the fNIRS hemodynamic signal and IMU motion data so as to identify a motion pseudo-film segment in the EEG signal. Performing interpolation restoration on the detected pseudo-film segments to eliminate artifacts in the EEG electroencephalogram signals, and drawing and displaying an electroencephalogram in real time according to the EEG electroencephalogram signals after the artifacts are eliminated; according to the technical scheme provided by the invention, the defect that BCG vascular pulsation artifacts and motion artifacts in the EEG signals are difficult to effectively eliminate can be effectively overcome.

The invention discloses a disastrous big wave occurrence probability and wave height combined prediction method, device and equipment, a medium and a product, and relates to the technical field of meteorological ocean forecasting. The method comprises the following steps: acquiring an effective wave height measured value and environmental factor data of a to-be-predicted region in a historical time period; key environment factors are screened through spatial correlation analysis and linear fitting verification, a first training data set and a second training data set are constructed, and a multiple linear regression model and a logic regression model are trained respectively to obtain a wave height prediction model and a big wave occurrence probability prediction model; and inputting the key environmental factors of the current time period of the to-be-predicted region into the model to obtain the predicted occurrence probability of the disastrous waves and the predicted value of the significant wave height in the predicted time period. According to the method, the key environmental factors are screened and the two models are used for respective prediction, the influence of the various environmental factors on the big waves is considered, the occurrence probability and the wave height of the disastrous big waves can be predicted more accurately, and the ocean safety is effectively guaranteed.

The invention relates to the technical field of electric power, in particular to an electricity price fluctuation quantification method, device, equipment and medium based on regression analysis, and the method comprises the steps: taking electric power price fluctuation in peak load of electric power as a dependent variable, and taking new energy power generation, thermal power generation, electric power demand, generating capacity and capacity electricity price as independent variables; establishing a multiple linear regression model; verifying whether the independent variable and the dependent variable have a linear relationship or not, preliminarily carrying out multiple linear regression analysis, finding an optimal regression coefficient by minimizing a residual sum of squares, and carrying out multiple linear problem judgment; a ridge regression analysis method is adopted, a regularization item is added into a loss function to limit the size of a regression coefficient, overfitting of the model is reduced, and a ridge function is confirmed through cross validation; performing overall significance test and regression coefficient significance test on the multiple linear regression model, and analyzing the fitting degree; and performing quantitative analysis on electricity price fluctuation by using the fitted multiple linear regression model.

The invention discloses a heart tension index dynamic calculation and risk assessment method based on HRV, and the method comprises the steps: carrying out the filtering and denoising of an electrocardiosignal through a Butterworth filter, and obtaining a filtered electrocardiosignal; calculating interval data of adjacent wave crests; processing the interval data according to fast Fourier transform to obtain frequency domain features, and combining the interval data to obtain time domain features; performing normalization processing on the time domain and frequency domain features based on a maximum and minimum normalization method; calculating a cardiac tension index according to the normalized features and a pre-trained multiple linear regression model; matching a pre-constructed reference database according to the individual age, gender and body mass index to obtain a reference cardiac tension index; calculating a cardiovascular risk score in combination with the normalized frequency domain features and a reference cardiac tension index; and repeating the above steps regularly, smoothing through a moving average method based on continuous multiple cardiovascular risk scores, and analyzing the trend to send out cardiovascular risk early warning information.

The invention discloses an LED energy storage street lamp management method and system combined with Internet of Things perception, relates to the technical field of Internet of Things and intelligent illumination, and solves the problem that it is difficult to use the Internet of Things to monitor, collect and process various data in real time so as to predict maximum brightness demand values of street lamps in different time periods. The influence of shelters on the illumination intensity of the street lamp is difficult to analyze; the battery state and the energy storage efficiency of the LED energy storage street lamp are difficult to evaluate; a charging and discharging control strategy is difficult to generate; the energy consumption under the charge and discharge control instruction is difficult to optimize by using digital twinning, and the optimized charge and discharge control instruction is difficult to execute. Various sensing data are collected and processed through the Internet of Things, the brightness requirement of the street lamp is predicted by using a multiple linear regression model, a dynamic shielding coefficient is analyzed, and the battery state and energy storage efficiency of the LED energy storage street lamp are evaluated, so that an intelligent charging and discharging control strategy and a digital twin model simulation energy consumption optimization strategy are generated; and the energy consumption of the LED energy storage street lamp is reduced.

The invention provides a multi-tree forest aboveground biomass remote sensing estimation method and system and a storage medium, and the method comprises the steps: obtaining multi-source remote sensing data based on a target region, including airborne LiDAR point cloud, ground survey data and DEM data; constructing a terrain heterogeneity index DGTHI in combination with DEM data, and quantifying terrain complexity through weight fusion of standardized terrain factors; extracting forest characteristic parameters and calculating the overground biomass of the single tree; performing classification modeling on the sampling region based on DGTHI, respectively establishing multiple linear regression models for different tree species, and optimizing feature parameter selection; and evaluating the precision of the model through cross validation, and popularizing the model to a county scale to perform overground biomass space inversion and mapping. According to the method, terrain heterogeneity classification and tree species specificity modeling are fused, so that the estimation precision of the forest biomass in the complex terrain region is remarkably improved, and a technical support is provided for regional carbon sink monitoring and sustainable forestry management.

The invention discloses a pillow regulation and control method self-adaptive to cervical vertebra flexion and shoulder width and application of the pillow regulation and control method to a pillow, and relates to the technical field of sleeping posture regulation. The method comprises the steps of registering a three-dimensional contour point cloud through an ICP algorithm, calculating a neck curvature value, establishing a multiple linear regression model in combination with a pressure gradient change curve and a pressure peak offset, and realizing quantitative correlation between pressure data and a cervical vertebra inclination angle; based on the curvature change amplitude and shoulder breadth classification, a personalized model is constructed; and through attitude monitoring and pressure feedback, a real-time optimization instruction is generated. A target displacement error is set, and correction is stopped after the bending degree reaches the standard continuously for three times; pre-storing a medical-level support parameter library; multi-user switching is achieved through pressure feature and head contour double verification, and physical compression emergency stop is set. According to the method, through multi-source data fusion, scientific model construction and dynamic closed-loop control, the personalization and safety of pillow supporting are improved, and the method is suitable for people with sub-health cervical vertebrae and multi-user scenes.

The invention provides a vacuum coating equipment fault detection method and system based on coating quality, and relates to the technical field of vacuum coating equipment detection.The method comprises the steps that dependent variables are obtained by adjusting various fault types and independent variables in a normal state; according to the fault contrast data set, constructing a multiple linear regression model of the fault contrast data set; determining the optimal quantile of the fault contrast data set in combination with an information criterion; carrying out regression on each section of fault contrast data set by utilizing a multiple linear regression model to obtain multiple linear regression model coefficients under each section of fault contrast data set; calculating the influence weight of each piece of coating quality data on each influence factor; combining each influence weight to construct a naive Bayes classifier which is used for outputting a fault category and has a weighted value; acquiring real-time coating quality data; and taking the real-time coating quality data as input data of the improved naive Bayes classifier, and outputting a prediction fault category. And the fault detection efficiency and accuracy are improved.

The invention discloses a clinical examination equipment remote calibration method and system based on edge calculation, and relates to the field of instrument calibration, the system is composed of a plurality of functional modules, and the system comprises: a multi-modal data acquisition module for acquiring historical calibration data of absorbance, including fluorescence images, cell fluorescence signal intensity and morphological characteristics; the edge calculation module is used for establishing a multiple linear regression model according to historical calibration data of the absorbance and predicting an attenuation curve of the optical detection unit; on the basis of a federated learning framework, a fluorescence signal intensity compensation matrix is optimized by utilizing shared parameters among edge nodes, and light path gain parameters are automatically adjusted; performing outlier analysis on each batch of detection data through a built-in Westgard rule engine, and triggering automatic redetection of morphological characteristics; analyzing absorbance time sequence data in combination with a 1D-CNN model, and identifying reagent pollution and optical assembly aging; and the drifting calibration module adopts a PID controller to dynamically adjust the power of the laser.

The invention relates to the technical field of exploration and development of water flooded layers, in particular to a sandy conglomerate water flooded layer porosity determination method based on an XRD (X-Ray Diffraction) logging technology, which comprises the following steps of: performing correlation analysis on the content of each mineral in mineral content data and the actually measured porosity of the same group; screening out mineral types of which the determination coefficient with the actually measured porosity is greater than a determination coefficient set value; performing multiple linear regression fitting on the content of each mineral type obtained by screening and the corresponding actually measured porosity of the same group to obtain an optimal multiple linear regression model; and for the rock debris sample of the non-coring section of the reservoir stratum of the glutenite water flooded layer, obtaining the porosity calculated value of the rock debris sample through the optimal multiple linear regression model. The porosity data of the rock debris sample of the non-coring section of the reservoir stratum of the glutenite water-flooded layer can be obtained, and the porosity data of the oil reservoir water-flooded layer of the whole well can be obtained by combining the porosity data of the coring section of the rock debris sample, so that the porosity data of the whole oil reservoir water-flooded layer can be obtained.

The present invention discloses a method for predicting errors of digital temperature and humidity meters in workshops based on machine learning, and belongs to the field of industrial metrology technology. The technical method proposed in the present invention accurately predicts the measurement error of the meter under test by introducing data smoothing, peak extraction, filtering and outlier processing, and establishing a multivariate linear regression model; the measurement calibration cycle is dynamically adjusted according to the predicted error, which not only ensures the accuracy of the measured data, but also realizes error prediction. The method of the present invention effectively solves the metrology problems caused by small amount of data, misaligned data time series, poor data continuity, unclear performance indicators, and poor abnormal response on site, and combines time series and adaptive adjustment algorithms to improve the credibility of model prediction. The above technical method can reduce human errors in on-site measurements, the algorithm responds in real time, saves manpower, promotes the construction of digital workshops, and ensures the mathematical basis support for measurement.

The invention provides a soil comprehensive nutrient evaluation method and device based on a satellite remote sensing image, equipment and a medium. The method comprises the following steps: acquiring a Sentinel-2 multispectral image, cultivated land vector boundary data and actually measured soil nutrient data of a target area; establishing a multiple linear regression model by utilizing the wave band reflectivity of the Sentinel-2 multispectral image and actually measured soil nutrient data, generating a region-level nutrient content grid map, and extracting a nutrient content grid map of soil in a cultivated land range of a research region; classifying the grid map by adopting a spatial constraint natural breakpoint method clustering target function; a three-digit decimal code is adopted to represent a grading result, a soil comprehensive nutrient spatial distribution diagram is generated, coordinated color matching is set, various areas and proportions of soil comprehensive nutrients are counted, and fertilization suggestions are given, so that the defects of single sensing dimension and disjunction of decision support during remote sensing monitoring of the soil nutrients are overcome; and a closed loop serving precision agricultural practice is difficult to form.

The invention discloses a method for detecting tissue evolution in a heating process after quenching of tool steel based on saturation magnetization, resistivity and hardness, and relates to the technical field of metal material detection.The method comprises the steps that heating parameters are set for different types of tool steel, and an actual tempering process is simulated; then, the saturation magnetization intensity, the resistivity and the hardness are measured through professional equipment, and data are obtained through accurate measurement and scientific calculation; and then, sorting the data to establish a database, analyzing by using a multiple linear regression model, and judging an organization evolution stage according to a preset result range. According to the method, the structure evolution of the tool steel can be accurately and comprehensively monitored, the detection accuracy and scientificity are improved, powerful support is provided for quality control and process optimization in the tool steel production process, and the tool steel product performance and production efficiency are effectively improved.

The invention relates to the technical field of brand marketing, in particular to a brand marketing system and method based on a block chain. Comprising a market monitoring module, a dynamic pricing module, a consumption prediction module and an evaluation optimization module. The market data is monitored in real time through the market monitoring module, a multivariate linear regression model between market demands and prices is established through the dynamic pricing module, the price of the brand is dynamically adjusted by taking profit maximization as a target, the consumption prediction module is utilized to construct a random forest model, and the price of the brand is dynamically adjusted. Each consumer is classified into a corresponding level according to a comprehensive score, personalized marketing suggestions are generated, the price of a brand is dynamically adjusted according to the change of market demands, the price of the brand can be ensured to conform to the change of the market in real time, the purpose of brand promotion is achieved, targeted marketing of consumer groups is achieved, and the market promotion efficiency is improved. And the marketing quality and efficiency of the brand are improved.

The invention discloses a cable anomaly detection method based on visible light and infrared image fusion, and the method comprises the steps: obtaining a multi-modal image of a cable, and the multi-modal image comprises a visible light image and an infrared thermal image; fusing the multi-modal image based on a wavelet analysis algorithm and a deep learning algorithm to obtain a cable fusion image; training a multiple linear regression model according to the cable fusion image to predict the fault type and position of the cable; and acquiring multi-modal image data of the cable in real time, and inputting the multi-modal image data into the trained multiple linear regression model for cable fault prediction. According to the invention, the technical problem of insufficient cable fault type accuracy in the background technology is solved.

The invention discloses a locomotive brake detection performance determination method, and the method comprises the steps: employing a vehicle-mounted device on a locomotive to collect dynamic data generated in a brake test process in real time, and the dynamic data comprise air cylinder pressure, pipeline pressure, a brake handle position signal and other operation related parameters; the collected dynamic data are preprocessed, a test standard curve set is constructed in combination with historical test data, and the standard curve set is classified and stored according to the locomotive model and the brake model. According to the invention, a standard test data set is constructed based on a large amount of test data of locomotives and brakes of different models, feature extraction and fitting analysis of dynamic data are realized in combination with a feature sampling algorithm, a least square fitting algorithm and a multiple linear regression model, and through comparison of a fitting curve and a standard test curve, a dynamic test result is obtained. The system automatically judges the normalization and integrity of the operation, and subjective errors and omissions of manual analysis are avoided.

The invention discloses a coal bed gas typical reservoir gas content evaluation method based on well logging information, and relates to the technical field of coal bed gas evaluation. According to the coal bed gas typical reservoir gas content evaluation method based on the logging information, logging data and core data of a set area are obtained and preprocessed; performing screening processing based on the logging data to obtain a screening set of the set area; based on the core data, constructing a lithology indication matrix and physical property constraint characteristics of the set area; constructing a constrained multiple linear regression model of the set area based on the screening set of the set area, the lithology indication matrix and the physical property constraint characteristics; according to the method, the target logging data of the to-be-evaluated target layer section are obtained, analysis is carried out in combination with the logging coefficient set, and the coal seam gas content value of the to-be-evaluated target layer section is obtained, so that the gas content of coal seam gas is evaluated more accurately; and the accuracy and reliability of the evaluation result are improved.

The invention discloses a six-dimensional force sensor calibration method based on an intelligent algorithm and ensemble learning, which improves calibration precision and system adaptability by combining data anomaly detection, the intelligent algorithm and the ensemble learning. The calibration method comprises the following steps: S1, building a six-dimensional force sensor calibration system; s2, loading and unloading experiments of force and torque are carried out on the six-dimensional force sensor on the standard calibration table, and multi-channel analog signal data output by the six-dimensional force sensor are obtained; s3, repeating the operation in the step S2 for a plurality of times; s4, data anomaly detection; s5, performing preliminary calibration by adopting a multiple linear regression model to obtain a preliminary decoupling matrix of the six-dimensional force sensor; s6, calculating error data after multiple linear regression calibration, and taking the error data as input characteristics of subsequent error compensation; s7, performing error compensation based on the residual neural network; and S8, determining calibration precision and outputting a final model.