264 results about "Normal range" patented technology

The invention discloses a primary and secondary fusion pole-mounted intelligent circuit breaker. The primary and secondary fusion pole-mounted intelligent circuit breaker comprises a fault detection module, a protection action module, a reclosing module and an information reporting module, the fault detection module collects multi-dimensional electrical quantity through a current transformer and a voltage transformer, and judges a fault and identifies the type in combination with a dynamic normal range and a duration threshold. The protection action module calculates the fault distance based on the correction impedance, judges whether to act or not by combining the current flow direction and the protection range, and selects a protection level according to the fault severity; the reclosing module dynamically sets an observation time window, distinguishes instantaneous or permanent faults through a retest verification mechanism, and adaptively adjusts a reclosing strategy; and the information reporting module uploads fault related information. According to the method, the problems of high misjudgment rate, poor protection selectivity, rigid reclosing logic and the like of a traditional circuit breaker are solved, and the accuracy, quickness and self-healing capability of power distribution network fault processing are remarkably improved.

The invention relates to the technical field of metering pumps, in particular to an external meshing gear metering pump flow calculation method based on linear regression and curve fitting, which comprises the following steps: generating an integrated data set by monitoring the flow rate, pressure, temperature and viscosity in real time, setting flow rate, pressure and temperature thresholds based on the data set, judging the flow state and recording abnormity, and calculating the flow rate of the external meshing gear metering pump. Flow velocity and viscosity are selected for flow calculation, a corrected flow value is generated, whether flow is normal or not is analyzed and determined, a flow stability evaluation result is generated, and a visual interface is created to display parameters and a calculation result. According to the method, the multiple sensors are installed at the inlet and the outlet of the metering pump, the flow speed, the pressure, the temperature and the viscosity are monitored in real time, an integrated data set provides a precise basis for flow calculation, a threshold value is set, data are monitored, it is ensured that parameters exceeding the normal range can be recorded and analyzed in time, and the process improves the accuracy of flow calculation and improves the working efficiency. And flow evaluation is optimized, and the operation safety and efficiency are improved.

The invention discloses an AI nursing whiteboard system and method based on a large model agent, the system comprises a nursing whiteboard terminal, an AI intelligent chain platform and a database, the nursing whiteboard terminal comprises an AI nursing assistant, and a whiteboard control system is arranged in the nursing whiteboard terminal. Through the functions of integration of multi-source data, intelligent early warning, accurate question and answer and the like, various diagnosis and treatment data, such as vital signs, medical advices, nursing records and the like, of a patient can be rapidly integrated and presented in a clear and visual mode, a large amount of time and energy are saved, the patient can rapidly know the condition of the patient, and the diagnosis and treatment efficiency is improved. Vital signs and illness state changes of a patient can be monitored in real time, early warning can be immediately given out once abnormal conditions such as heart rate and blood pressure exceeding normal ranges occur, a nurse can know the abnormal conditions in the first time and take corresponding measures, the response speed to emergency situations of the patient is greatly increased, and when the nurse encounters a question in the aspect of medical knowledge, the nurse can timely take corresponding measures. Inquiry may be made by an AI care assistant.

The invention discloses a cancer early warning management method and system based on a physical examination report, and belongs to the field of medicines.The method comprises the steps that health data of individuals are collected, and unstructured texts in the physical examination report are processed through combination of optical character recognition and a natural language processing technology; calculating a cancer risk based on a single physical examination report, evaluating a specific cancer by using a cancer risk scoring system, and analyzing whether an index exceeds a normal range or not through a rule engine; based on historical data trend prediction risks, index change rates are calculated, and an abnormal trend is analyzed and predicted in combination with a time sequence; multi-modal deep learning is utilized to predict individual cancer risks, and a Bayesian network is combined to perform joint analysis on multiple factors to generate a health management scheme; further examination is arranged according to the early warning level, and a screening strategy is provided for specific cancers. According to the method, the OCR + NLP technology is adopted, and the data quality is improved. And in combination with a multi-modal deep learning model, abnormal changes are found in advance, and early warning is realized.

The invention relates to the technical field of air leakage big data analysis, in particular to a compressed air pipeline air leakage intelligent analysis system and method based on LLM. A plurality of monitoring nodes in a compressed air pipeline are analyzed, and data normal range parameters and adaptive acquisition frequency are preset for each node in the pipeline operation stage; the clear definition standard avoids misjudgment of original data due to fuzzy threshold values, then data noise is effectively reduced by analyzing the data synchronization degree of each monitoring node and intelligently repairing the problems of missing, deviation and the like, the repaired data better fits the actual operation state of the compressed air pipeline, the missed detection and mispositioning risks are reduced, and the reliability of the compressed air pipeline is improved. And finally fusing the data of the gas leakage node and the adjacent node to supplement multi-dimensional information, and optimizing the fusion data quality. The LLM model depends on high-quality fusion data, deep analysis is carried out in combination with compressed air pipeline multi-monitoring-node correlation characteristics and historical experience, deviation caused by data defects is reduced, and the accuracy of an intelligent air leakage analysis result is greatly improved.

The invention relates to the technical field of remote monitoring, in particular to a critically ill patient remote monitoring system and method, and the system comprises a life signal collection module, a physiological state analysis module, a remote monitoring response module and a remote intervention operation module. According to the method, the data analysis and real-time feedback process is optimized, the efficiency and accuracy of medical response are improved, the key physiological indexes deviating from the normal range can be quickly and accurately recognized and analyzed by comprehensively analyzing the instant vital sign data and the historical medical records of the patient, the prediction accuracy is improved, and the prediction efficiency is improved. Medical personnel are allowed to receive clear health risk warnings at critical moments, direct communication with a medical network is enhanced through a rapid grading and alarm system, a faster medical intervention response is achieved, meanwhile, a treatment plan can be remotely and dynamically adjusted according to the current physiological state of a patient, the treatment process is more accurate, and the treatment efficiency is improved. And the survival rate and the treatment quality of patients are greatly improved.

The invention relates to the field of anesthetic concentration regulation and control, in particular to a method for analyzing and evaluating the administration concentration of an inhalation type anesthetic. The method comprises the following steps: firstly, according to characteristic data such as basic physiological data, previous anesthesia sensitivity and operation information of a patient, applying a fuzzy matching algorithm to obtain an initial administration concentration; physiological sign data such as blood pressure, heart rate, pulse oxyhemoglobin saturation and end-expiratory carbon dioxide partial pressure of the patient are monitored in real time in the anesthesia process and compared with a normal range, whether the physiological sign data are abnormal or not is judged, and an adjustment scheme of the administration concentration is determined according to the administration concentration-physiological sign correlation model; after the administration concentration is adjusted, the electroencephalogram double-frequency index is monitored to evaluate the anesthesia depth, the anesthesia depth matching degree is analyzed to judge the adjustment effect, and therefore closed-loop control over the anesthetic administration concentration is achieved. According to the method, the administration concentration can be accurately regulated and controlled, the concentration regulation mechanism is optimized, the safety and effectiveness of the anesthesia process are effectively improved, and a reliable guarantee is provided for clinical anesthesia.

The invention discloses a power system intelligent monitoring method based on artificial intelligence, and the method comprises the steps: carrying out the real-time prediction and analysis of newly-added data through an adjusted model parameter set in combination with the core knowledge representation of historical data, obtaining an operation state evaluation value of a current time period, and judging whether a system has an abnormal fluctuation trend or not; after the abnormal fluctuation trend is obtained, extracting a key mode from the existing knowledge by utilizing a pre-established knowledge distillation framework for the part of the evaluation value exceeding the normal range, and obtaining a refined knowledge subset; according to the refined knowledge subset and the feature vector set of the newly added data, performing fine adjustment on the model, and determining an updated monitoring model; according to the method, repeated calculation of total data in a traditional method is avoided, the data processing efficiency is greatly improved, the time requirement of real-time monitoring is met, the problem that model updating is lagged in the traditional method is solved, and the problem that precision is difficult to maintain after newly-added data is introduced is solved.

The invention relates to the technical field of transformers, and particularly discloses a transformer monitoring data processing method and system, and the method comprises the steps: obtaining the monitoring data of each part in a target transformer and a corresponding transformer state correlation graph; preprocessing the monitoring data; associating the preprocessed monitoring data to data nodes in a transformer state association graph; when abnormal data nodes occur, associated data nodes are tracked and acquired along causal influence edges based on the abnormal data nodes, and the abnormal data nodes are data nodes with monitoring data deviating from a preset normal range; analyzing the change characteristics of the monitoring data of the abnormal data nodes and the associated data nodes, and obtaining an abnormal mode; generating early warning information according to the abnormal mode, component nodes in the transformer state association graph and physical connection edges; according to the method, timely early warning is realized, the equipment damage risk is reduced, and the safe and stable operation level of a power system is improved.

The invention relates to the technical field of data processing, in particular to an intelligent analysis method and system for clinical test data, and the method comprises the steps: obtaining a data sequence of each physiological index of a patient, and calculating the deviation degree through quantifying the difference between a target data point and a corresponding physiological index normal range, calculating an abnormal index based on the deviation degree and the distribution characteristics of the corresponding data in the data sequence of the corresponding physiological indexes, and obtaining a fitting curve of each physiological index by fitting the abnormal index, so as to screen out time periods in which all the fitting curves are in a rising trend; and taking the physiological index pairs of which the correlation is greater than a preset value in the time period meeting the screening condition as target index pairs, constructing a causal graph by using a PC algorithm based on the target index pairs, and identifying the causal relationship of each physiological index. According to the method, the complexity of constructing the causal graph by the PC algorithm can be reduced while the important causal relationship among the physiological indexes is reserved.

The invention discloses a boric acid production material scheduling method and system based on the Internet of Things, and the method comprises the steps: obtaining multi-source data from a boric acid production line, carrying out the preprocessing of the multi-source data, and mapping the preprocessed multi-source data to a digital twinborn model; and extracting the scheduling demand of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and constructing a multi-target scheduling model when the scheduling demand meets the workshop production demand. The turbidity, crystal particle characteristics and color change of a solution on a production line are monitored in real time through an optical system, optical monitoring data are obtained, the crystallization state and the impurity content in the solution are determined in combination with multi-source data, and scheduling execution is carried out when the crystallization state or the impurity content deviates from a normal range. The optical monitoring data and the scheduling execution condition are fed back to the digital twinborn model based on the abnormal indication, so that the scheduling strategy and the process parameters of the boric acid production line are corrected, and the intelligence and the production efficiency of boric acid production are improved.

The invention discloses a sensor clamping mechanism and a mutual inductor crimping fault detection device and method, and relates to the technical field of mutual inductor detection. In a project verification process of an existing voltage-withstanding table and an error table, abnormal conditions such as inclination of a mutual inductor body, inaccurate tray positioning, abnormity of a magnetic switch, air leakage of an air cylinder air pipe and the like occur, so that a terminal stud of a test table cannot be in contact with a secondary side terminal of a mutual inductor to be tested; and detection interruption or false detection of a corresponding mutual inductor exists, so that the verification efficiency is reduced. According to the frame body, the measuring rod, the elastic piece and the sensor, the sensor can detect the relative displacement between the measuring rod and the frame body, if the relative displacement is within a normal range, the terminal stud is in successful crimping contact, and if the relative displacement exceeds the normal displacement range, the terminal stud has a crimping fault. Therefore, the system judges that the wiring terminal of the to-be-detected mutual inductor is failed in crimping with the wiring end, automatically identifies the crimping fault of the wiring end, and improves the operation efficiency of an assembly line.

The invention discloses a carbon dioxide plume monitoring-based carbon sequestration site safety assessment method. The method comprises the steps of obtaining monitoring data of each region in a carbon sequestration site in real time; monitoring data are stored in a monitoring database; when one kind of monitoring data obtained at the current monitoring moment is compared with the same kind of monitoring data at the previous monitoring moment, and the fluctuation amplitude exceeds a threshold value, the migration speed data are compared; if the migration speed data are the same, judging whether most of the other types of monitoring data do not fluctuate greatly, considering that the site is possibly abnormal when judging that most of the other types of monitoring data fluctuate greatly and the migration speed data obtained in the previous step is different, and entering the next step; acquiring permeability, porosity and bursting pressure data of the corresponding area at the current monitoring moment, judging whether the data are in a normal range or not, considering that potential safety hazards exist in the field when the data are not in the normal range, and giving an alarm. According to the invention, the site safety can be rapidly and timely evaluated accurately, the energy consumption is low, and the method is suitable for popularization.

The invention relates to the technical field of electric digital data processing, in particular to a method, device and system for reducing the fetal heart monitoring false positive rate of a high-risk pregnant patient, and the method comprises the steps: obtaining a fetal heart rate sequential sequence and a uterine contraction pressure sequential sequence, and analyzing the degree that the fetal heart rate deviates from a normal range according to the fetal heart rate sequential sequence; determining a fetal heart abnormality index of each undetermined abnormal section; performing regularity analysis on the suspected abnormal fetal heart segments according to the uterine contraction pressure time sequence, and determining the influence degree of uterine contraction on each suspected abnormal fetal heart segment; according to the fetal heart abnormality indexes and the influence degrees of all the suspected fetal heart abnormality sections, the credibility of the fetal heart rate sequential sequence is determined by combining the ratio condition of the target moment number to the current total fetal heart monitoring moment number. By determining the credibility, the situation that the fetal heart monitoring data is misjudged to be abnormal due to interference of uterine contraction can be avoided, and then the fetal heart monitoring false positive rate of the high-risk pregnant patient is reduced.

The invention discloses an operation state prediction method and device of a building new energy system, and the method comprises the steps: obtaining various monitoring variables of a target building, inputting the various monitoring variables of the target building into a trained prediction model, and obtaining the prediction results of the various monitoring variables of the target building in a set prediction time range; based on the prediction result, evaluating the operation state of the target building: firstly calculating a basic threshold value, and then determining a dynamic threshold value according to the basic threshold value, an equipment aging factor and a seasonal factor; the prediction result is compared with a dynamic threshold value, and if the prediction result is smaller than or equal to the dynamic threshold value, the operation state of the building new energy system is a normal state; and if the prediction result is greater than the dynamic threshold value, indicating that the operation state of the building new energy system deviates from the normal interval and the building new energy system has an abnormal phenomenon.

The present invention provides a method for diagnosing the faults of a board card based on the weighted sum of squares of the sensor signal residual sequence, which relates to the technical field of fault diagnosis of electronic controllers. The method includes: obtaining the original temperature process signals of each temperature sensor from a gas turbine electronic controller system, performing data preprocessing to form an original data set; inputting the original data set into a calculation model for the weighted sum of squares of the residual sequence; selecting the weighted sum of squares of all sensors associated with the IO board card and inputting it into a calculation model for the health degree of the IO board card to obtain the health degree value of the board card; calculating the difference between the health degree value of the board card and the boundary line of the preset normal range, and judging whether the board card has a fault according to the difference. This method can quickly diagnose the fault state of a thermocouple IO board card in an engineering manner, provide an engineering-applicable means for timely identifying the faults of the IO board card of an electronic controller, and provide important support for the fault diagnosis of the control system loop of a gas turbine.

The invention relates to a method and device for judging whether a grounding mechanism of a switch cabinet works normally or not, a grounding resistance online measurement module is arranged on a grounding knife switch structure of the switch cabinet, the resistance value of the grounding resistance is detected in real time, and whether grounding is correct or not is judged by judging whether the grounding resistance is in a normal range or not; the grounding resistance on-line measurement module is internally provided with a switch-on grounding state detection algorithm based on deep fusion of a neural network and Kalman filtering. According to the method, multiple factors such as the cumulative closing times, the contact resistance change rate, the oxidation coefficient, meteorological interference and the temperature are comprehensively considered, a dual-network self-adaptive modeling and federated Kalman filtering framework is adopted, high robustness and nonlinear processing capacity are achieved, and whether the switch cabinet grounding mechanism works normally or not is judged with high accuracy.

The invention discloses an image detection method, electronic equipment and a storage medium. The method comprises the steps that a product gray scale image is acquired, and the product gray scale image is marked with a difference area; calculating to obtain the gray scale distance of the difference area relative to the area where the difference area is located, or calculating to obtain the gray scale distance and the gray scale difference mean value and gray scale difference variance of the difference area relative to the normal range; and determining whether the difference region is a defect region or not by using the gray scale distance, or the gray scale distance, the gray scale difference mean value and the gray scale difference variance. After the difference area is marked, whether the difference area is a real defect or not is judged by utilizing the gray scale distance of the difference area relative to the area where the difference area is located or utilizing the gray scale distance and the gray scale difference mean value and the gray scale difference variance of the difference area relative to the normal range, and the detection efficiency of the difference area of the packaging substrate can be improved.

The invention discloses a risk early warning method and system for an emergency diesel generator of a nuclear power plant, and the method comprises the steps: collecting operation parameters of a generator set in a hot standby state, and when the parameters are not in a preset normal range, indicating that the parameters are abnormal and the generator set breaks down; preprocessing the acquired operating parameters, and extracting effective features of the preprocessed operating parameters; on the basis of the generator set with the fault, combining with the effective characteristics, and utilizing a high-frequency data flow transient anomaly recognition algorithm to capture an anomaly type label to obtain fault information; evaluating the risk degree of the generator set according to the effective features and the abnormal type labels of the preprocessed operation parameters; and carrying out risk early warning and response on the generator set according to the risk degree of the generator set. According to the invention, the operation state of the emergency diesel generator set can be monitored in real time, accurate risk assessment and early warning information is provided, and the risk management capability of managers is enhanced.

The invention discloses an online sensor data abnormity diagnosis method and system based on correlation analysis, and relates to the technical field of sensor data abnormity diagnosis, and the method comprises the steps: screening out a sensor combination from a plurality of sensors of a natural gas long-distance pipeline station when the natural gas long-distance pipeline station is in normal operation, determining a normal range of correlation coefficients between every two sensors in the sensor combination; calculating an actual correlation coefficient between every two sensors in the sensor combination according to the data sequence acquired by each sensor in the sensor combination within a second preset time period; judging whether the actual correlation coefficient between every two sensors in the sensor combination is in a corresponding normal range or not to obtain a plurality of first judgment results; and judging whether data exception exists or not according to all the first judgment results. According to the method and the device, the abnormal data can be determined more quickly, the range of the faulted sensor is determined, subsequent troubleshooting is facilitated, and the cost is reduced.

The invention relates to a high-voltage bushing fault grading alarm online monitoring method and device and a storage medium, and aims to realize high-voltage bushing fault monitoring. The method comprises the steps of obtaining time sequence detection data; a time sequence oil pressure parameter, a time sequence temperature parameter and a time sequence humidity parameter in the time sequence detection data are subjected to normalization processing and then input into a pre-trained high-voltage bushing fault detection model to calculate a deviation parameter of an actual neighborhood interval difference mean value; determining whether a neighborhood interval difference mean value has a fault according to the deviation parameter and a measurement threshold value, and determining a fault level according to the degree of deviation from a normal range; wherein the measurement threshold value is obtained through a high-voltage bushing fault detection model in the training process. According to the method, time sequence modeling is carried out on time sequence detection data in a normal operation state by adopting a self-supervision mode, and distribution of a neighborhood interval difference mean value of a prediction result is modeled by utilizing a Gaussian mixture model, so that the extreme degree of the neighborhood interval difference mean value under a normal condition is determined, and high-voltage bushing fault monitoring is carried out.

The invention discloses a blood fat monitoring system based on a vascular ultrasound image, and belongs to the technical field of medical image recognition. The problems that an existing system cannot automatically recognize the blood vessel structure and evaluate the blood fat level and cannot ensure the stability and real-time performance of data transmission are solved, the intima-media membrane and lumen contours in the blood vessel ultrasonic image are automatically recognized in a short time through the convolutional neural network model, multi-dimensional features are extracted from the intima-media membrane and lumen contours, and the accuracy of the blood vessel ultrasonic image is improved. The identification precision and the diagnosis accuracy are improved; a multi-node gateway communication channel is arranged, and an optimal gateway is selected for data feedback in combination with a network distance threshold value, so that a blood fat prediction result is fed back to a medical interaction terminal in real time, it is ensured that early warning is triggered in time when the blood fat level exceeds a normal range, and the situation that a certain gateway breaks down or the communication distance exceeds the threshold value is prevented. And the system can be automatically switched to other available gateways, so that the stability and the reliability of the data in the transmission process are ensured.

The invention relates to the technical field of databases, in particular to a database circulation track auditing method based on multi-source data fusion. The method comprises the following steps: collecting multi-source data of different logs, preprocessing to obtain preprocessed multi-source data, extracting key features of the preprocessed multi-source data, and serially connecting the key features according to a time sequence to generate a database circulation track; collecting operation behavior data of a user, calculating a mean value and a standard deviation corresponding to the operation behavior data to determine a normal range and generate an initial baseline, and designing an automatic trigger updating mechanism to dynamically update the initial baseline to generate a dynamic baseline; and calculating the deviation degree between the actual value of each operation behavior dimension and the dynamic baseline, carrying out weighted summation to calculate a total risk value, comparing the total risk value with a risk threshold, and classifying the total risk value into low risk, middle risk and high risk. According to the invention, the false alarm rate can be reduced, and multiple times of missing report of few hidden anomalies can be avoided; the auditing resources can be focused on the high risk preferentially, manual intervention of low-risk abnormity is reduced, and compared with single-dimension grading, the auditing efficiency is improved.

The invention relates to the technical field of medical monitoring, in particular to an infant feeding monitoring method, system and device and a medium, and the method comprises an information input module which is used for inputting basic information of an infant; the feeding information acquisition module is used for acquiring feeding state information, physiological state information and abnormal state information of an infant; the feeding analysis module is used for analyzing and judging whether feeding is reasonable or not based on the feeding state information to obtain a first analysis result, and analyzing and judging whether the physiological state exceeds a normal range or not based on the physiological state information; analyzing and judging whether the abnormal state information reaches a threshold value or not based on the abnormal state information to obtain a third analysis result; the feeding prompting module is used for respectively generating corresponding feeding prompting suggestions based on the first analysis result, the second analysis result and the third analysis result; and the feeding information display module is used for generating a chart for displaying the feeding state information and the physiological state information, so that the feeding of the baby can be effectively monitored.

The invention provides a control method and device of a pet feeder and the pet feeder, and relates to the technical field of intelligent control. The method comprises the steps that when it is detected that the distance between a target pet and a feeding tray is within a preset distance range, a plurality of pet images collected by a camera device are acquired; determining pet data of the target pet based on the pet image; based on the pet data, whether the target pet is a first abnormal state pet is judged, a fractional feeding strategy is configured for the first abnormal state pet, and the first abnormal state pet is used for indicating that the fat and thin degree of the target pet is lower than a lower limit value of a preset normal interval; the multi-time feeding strategy is used for indicating multi-time feeding for a specified first feeding amount in each specified first feeding time period; and cooperatively controlling a grain discharging mechanism according to the multi-time feeding strategy and / or the feeding monitoring result. The rationality and reliability of pet feeding are improved, and good health states of different pets are guaranteed.

The invention discloses a capacitor voltage transformer on-line verification and state early warning method and system, and the method comprises the steps: synchronously collecting the secondary side time sequence data of a target CVT and other CVTs of the same bus with the target CVT through a power monitoring system; based on secondary side time sequence data of a plurality of CVTs on the same bus, screening out a CVT equipment group with consistent state through group consistency analysis, and generating a virtual standard reference value for error calculation; calculating a relative deviation between the secondary voltage measurement value of the target CVT and the virtual standard reference value as a first evaluation result; performing feature extraction on the secondary side time sequence data to obtain a feature vector representing the operation state of the target CVT, inputting the feature vector into a pre-trained intelligent evaluation model to obtain an error prediction value or a health state score of the target CVT, and taking the error prediction value or the health state score as a second evaluation result; and fusing the first evaluation result and the second evaluation result to obtain a comprehensive evaluation conclusion of the running state of the target CVT, and if the state level exceeds a normal range, generating early warning information.

A power supply switch health diagnosis method, system, medium and product relate to the field of data processing. The method comprises the following steps: determining operation parameters of a power supply switch, including cumulative opening and closing times, opening and closing current and effective arcing time in each opening and closing process, and opening and closing action time; calculating the mechanical life state of the power supply switch based on the accumulated opening and closing times and the preset rated opening and closing times; based on the breaking current and the effective arcing time, adopting a breaking current weighted accumulation method to calculate and obtain an accumulated electrical wear value, and according to the accumulated electrical wear value and a preset theoretical total wear amount, evaluating and obtaining an electrical life state of the power supply switch; obtaining an action performance state of the power supply switch based on the opening and closing action time and a preset action time normal range; and synthesizing the mechanical life state, the electrical life state and the action performance state to generate a health diagnosis result of the power supply switch. By implementing the technical scheme provided by the invention, the accuracy of health diagnosis of the power supply switch is improved.

The invention discloses an electric power data analysis method and system based on an AI model, and the method comprises the steps: S10, collecting and preprocessing the data of a power grid monitoring point through an electric power data analysis system, and calculating a data stability baseline value; s20, based on the data stability baseline value, the power data analysis system trains an AI model to identify behaviors deviating from a normal range, and potential security threats are judged; s30, for data with security threats marked by the AI model, performing deep analysis by the power data analysis system, and calculating risk scores of comprehensive abnormal degree, duration and influence range; s40, the system automatically triggers a corresponding response mechanism according to the risk score; s50, the electric power data analysis system continuously updates a learning strategy of the AI model by evaluating the processed event effect; according to the invention, safe and stable operation of the power system can be effectively ensured, potential risks can be found in time, and effective measures can be taken for response.

The invention provides a fault root cause analysis method and system and a computer readable storage medium, and relates to the technical field of communication equipment fault analysis, and the method comprises the steps: obtaining operation data of communication equipment in a normal state, generating a feature index, calculating a mean value and a standard deviation of the feature index to establish a normal operation range, and constructing a fault analysis model; and taking the feature index as input, taking the fault prediction value as output, training a model by using normal data, comparing the fault prediction value output by the model with a normal range by combining historical fault data verification to judge whether the equipment is abnormal, and finally determining a fault source according to a set root cause positioning rule and the category of the feature index. According to the method, the mean value and the standard deviation of the feature indexes are calculated, and the multi-dimensional feature indexes are integrated, so that accurate detection and root cause positioning of communication equipment faults are realized.

The invention discloses a toxic gas concentration detection method based on multi-sensor data fusion and a toxic gas concentration acquisition system based on multi-sensor data fusion. A plurality of different types of toxic gas sensors are used for collecting toxic gas original data in real time; filtering and noise reduction are carried out on the collected data, so that the data quality is improved; fusing the preprocessed data by adopting a weighted average method and a Kalman filtering algorithm to obtain more accurate gas concentration information; calculating the actual concentration of the toxic gas according to the fused data; and monitoring the calculated concentration value in real time by combining a detection method based on a threshold value and a detection method based on statistical analysis, and when the concentration value exceeds a normal range or deviates from normal distribution of a statistical model, judging that the concentration value is abnormal. The concentration of toxic gas is accurately and dynamically monitored in real time by using various sensors, the abnormal condition of the gas concentration can be detected in time, and a powerful guarantee is provided for environmental safety and industrial production.