21 results about "Normal range" patented technology

A computer-implemented method for data-driven program selection of an implantable medical device, including the steps of providing patient medical data including a plurality of medical parameters acquired by an implantable medical device, triggering a patient information request if at least one of the plurality of medical parameters deviates from a predetermined normal range and / or based on a predefined schedule, wherein a type of patient information request triggered depends on which of the at least one of the plurality of medical parameters deviates from the predetermined normal range, and selecting a program or adapting parameters of an existing program of the implantable medical device based on a response to the patient information request. Furthermore, the present disclosure relates to a system for data-driven program selection of an implantable medical device.

This invention relates to a method for identifying successive grounding faults in a distribution network based on the characteristics of phase current mutations. Applied to multiple monitoring points along the line, the method includes the following steps: When any monitoring point identifies the first single-phase grounding fault, the remaining monitoring points enter the successive grounding fault identification stage and perform the following actions: extracting the mutation characteristics of the three-phase and zero-sequence currents; calculating the effective value of each phase mutation and the vector sum of the mutations of the two non-faulty phases; determining the line experiencing a successive single-phase grounding fault; when the first faulted line trips and is disconnected, supplementary judgment is made based on the change in the three-phase current mutation at the moment of disconnection; for the identified successive faulted lines, the effective value and duration of the zero-sequence current are continuously monitored; tripping is executed when the successive fault protection criteria are met; if the zero-sequence current returns to the normal range, the successive grounding fault identification stage is exited; thereby achieving local identification and distributed protection of cross-line single-phase grounding faults of the same and different phases.

This application discloses a power equipment operation and maintenance management system, belonging to the field of power management technology, including: a data detection module, used to periodically detect the operating status of the power equipment and classify the detected status data to obtain the priority of the operating status of the power equipment, wherein the operating status of the power equipment includes load status, voltage status and power supply status; and an operating status control model, which uses the classified status data to obtain the operating status control model of the power equipment through a neural network, thereby realizing the prediction of the operating status of the power equipment, determining whether the operating status of the power equipment is within the normal range, and if it is not within the normal range, locating the fault status of the power equipment and analyzing the fault factors caused by the fault status, and processing the operating status of the power equipment in batches according to the priority.

The application provides an abnormality detection and acousto-optic interaction method and system for multi-modal perception of process layer equipment, relates to the technical field of industrial automation, and comprises the following steps: collecting energy consumption fluctuation data and wireless communication quality data of a process layer equipment cluster, combining with equipment identification to form an original operation data set and labeling the original operation data set with equipment-associated identification to form an associated data set, adjusting and verifying initial filter gain parameters of an adaptive filter circuit to determine target filter gain parameters, filtering signals of the associated data set according to the target filter gain parameters, finally generating an equipment operation link, identifying abnormal equipment with parameters deviating from a normal range in the link, generating an equipment abnormality judgment result, determining an alarm level, and generating corresponding alarm audio signals, optical signals and ultrasonic carrier waves; and modulating characteristic parameters to the ultrasonic carrier waves to complete directional acousto-optic prompting of an abnormal area in combination with the optical signals, so that the application realizes intelligent and accurate identification, detection and acousto-optic prompting of implicit abnormalities under complex working conditions.

This invention provides a therapeutic device and a control method for the therapeutic device. The therapeutic device includes a radiator body, a power module, a first temperature sensor, a second temperature sensor, a power unit, and a processing unit. The first temperature sensor monitors the temperature of the radiator body; the second temperature sensor monitors the temperature of the radiated object; the processing unit calculates characteristic parameters of the radiator body based on the temperature rise value of the radiator body measured by the first temperature sensor being within the normal range; the processing unit controls the power output of the power unit to the radiator body based on the characteristic parameters. In the therapeutic device and control method provided by this invention, both the performance of the radiator body itself and the environmental variables between the radiator body and the radiated object are taken into account to control the power output to the radiator body, thereby maintaining a stable surface temperature of the radiated object and improving the temperature stability of the object heated by the therapeutic device.

The application discloses an air conditioner compressor control method, an electronic device and a storage medium. The method comprises the following steps: acquiring a first temperature difference related parameter between a set temperature and an ambient temperature; determining a second temperature difference related parameter based on the ambient temperature; wherein the second related parameter represents the difference between the saturation temperature corresponding to the pressure value at the preset position of the compressor and the actual temperature at the preset position; determining the basic speed of the compressor based on the first temperature difference related parameter; and determining the protection speed of the compressor based on the second temperature difference related parameter; determining the output speed of the compressor based on the basic speed and the protection speed. In the foregoing manner, the application can ensure that the output speed of the compressor is within a normal range and protect the compressor.

The present application relates to the technical field of clinical risk early warning, in particular to a surgery anesthesia intraoperative risk early warning method based on AI multi-modal data fusion, comprising the following steps: constructing an ideal steady-state residence model based on anesthesia records, monitoring signs in combination with blood loss and calculating cumulative load of drug metabolism, evaluating physiological steady-state confidence, comparing benchmarks to determine implicit compensation failure, and generating compensation depletion risk early warning instructions. In the present application, a probability density model representing the physiological steady-state maintenance capability is constructed, the risk assessment dimension is expanded from a single numerical amplitude to a time residence length, the blood loss and drug load data accumulated in real time during the operation are used to perform dynamic time domain compression and coordinate translation transformation on the benchmark distribution curve, the implicit failure risk is identified in advance when the vital sign readings have not yet exceeded the normal range but the compensation potential is about to be depleted, the steady-state collapse trend caused by the time cumulative effect is effectively quantified, and the forward-looking of risk identification is improved.

Monitoring device set up for a coolant circuit (10) with: at least two temperature sensors (14, 16), each of which can be arranged on and / or in the coolant circuit (10) or is fixedly arranged such that at least two individual temperature values ​​(T1 to T4) of local temperatures of a coolant (12) of the coolant circuit (10) in at least two different partial volumes of the coolant circuit (10) can be measured by means of the at least two temperature sensors (14, 16) arranged on and / or in the coolant circuit (10); and an evaluation device (18) which is designed to calculate at least one difference (Δ1, Δ2) between the individual temperature quantities (T1 to T4) measured in different partial volumes, and, if the at least one difference (Δ1, Δ2) deviates from at least one specified normal range, to output a warning information (20) regarding a low coolant level in the coolant circuit (10).

This invention discloses a method and system for predicting flight arrival times. The prediction method includes: outlier detection using multi-interval regression isolated forest, dynamically estimating the normal range of the original data, identifying and removing outlier data, wherein the original data includes historical airport operation data; progressive random forest feature selection, combining feature importance ranking and progressive subset validation to identify the most predictive feature subset, used to reduce model complexity and enhance generalization ability, wherein the model is used to predict flight arrival times; the model is a deep ensemble model based on ITLR, employing a deep ensemble learning framework that integrates Transformer, LSTM, and random forest branches in parallel, and integrating them through a dynamic weight strategy; and hyperparameter optimization based on IGWO, automatically searching for model hyperparameters. This invention can accurately identify and remove multi-dimensional outlier data, automatically select the optimal feature subset, and improve the model's generalization ability.

This application relates to the field of printing equipment condition monitoring technology, and discloses a method and system for monitoring and fault early warning of the rotational state of printing rollers. By collecting vibration and temperature data of the printing rollers, a time series decomposition algorithm is used to separate short-term fluctuations and long-term trends to obtain a trend sequence; the slope change of the trend sequence is calculated, and deterioration signs are captured by combining signal strength and duration, generating a slope growth pattern sequence; positive growth portions are identified and potential deterioration tendencies exceeding duration thresholds are marked, forming a labeling sequence; the deviation between cluster centers and normal ranges is calculated through cluster analysis to obtain a deviation degree sequence; the deviation values ​​are compared with thresholds to generate a candidate fault signal set; finally, a fault progression feature model is matched to determine and confirm the fault signal set. This application can effectively capture early abnormal trends of the rollers, improve the accuracy of fault judgment, and is suitable for online condition monitoring and intelligent early warning of printing equipment, realizing fault prediction and health management of the equipment.

The application provides a cutting head anti-interference method, system, device, medium and computer program product, and belongs to the technical field of laser processing. The method of the application arranges a capacitive sensor and a photoelectric sensor side by side on the cutting head, detects the distance between the cutting head and the surface of the side of the plate material close to the cutting head by the capacitive sensor, and detects whether there is plate material below the cutting head by the photoelectric sensor, and comprises the following steps: synchronously acquiring the detection data of the two types of sensors, combining the capacitive detection value range and the photoelectric detection result to judge whether the capacitive detection is disturbed by the splashed iron slag; if it is judged that the capacitive detection is disturbed, the cutting head is controlled to keep the height at the previous moment, the capacitive detection value is continuously monitored, and after the capacitive detection value returns to the normal range, the cutting head is controlled to resume the cutting mode. The application can solve the technical defects that the traditional single capacitive sensor is easily disturbed by the splashed iron slag, can identify the false detection caused by the iron slag, and the judgment logic is simple and reliable.

The present application relates to offshore oil exploration and drilling engineering technical field, more particularly, to an abnormal pressure detection and correction method of pressure sensing device. It includes the following steps: S1: converting data into time series format; S2: data segmentation; S3: setting the window size of sliding time window and quantile multiple distance; S4: calculating the difference between the current value and the median value of pressure value in the sliding time window; S5: judging whether the difference falls within the normal range interval; S6: judging whether the current value is equal to the maximum value of pressure value of short-term sequence x2; S7: judging whether the difference between the suspected abnormal value and the median value of pressure of short-term sequence x2 is greater than or equal to the maximum threshold, if yes, the suspected abnormal value is corrected, otherwise the process is ended. The present application can detect abnormal pressure value caused by external factors interference, and correct the abnormal pressure value to normal pressure value, avoiding the misjudgment of the working state of pressure sensing device caused by external factors interference.

The present invention relates to the technical field of cable fault detection. Disclosed are a data recognition method and system for characteristic gases of cable thermal degradation. The method comprises: performing synchronous high-precision collection on a plurality of gases released during cable thermal degradation; preprocessing collected data; and packaging the preprocessed data, and then classifying the packaged data, and detecting whether there is an anomaly. In the present invention, an SVM model is used to perform classification and recognition, and therefore not only can classification of characteristics of different gases be efficiently performed, but whether data has deviated from a normal range can also be identified by means of anomaly detection. An optimal solution is searched for by means of dynamically adjusting positions of a wolf pack, such that the SVM model can adapt to complex cable degradation status, thereby improving the accuracy of recognition. The thermal degradation status of a cable can be analyzed on the basis of real-time monitoring data, such that the degradation process and possible fault types are accurately predicted, thereby providing early warning, reducing the risk of unexpected faults of a power device, and ensuring the safe and stable operation of a power system.

The application provides a fluid delivery stability real-time intervention method for a high-speed rotating machine, and relates to the technical field of process control, and comprises the following steps: acquiring a current output intensity value of a driving force source driving the high-speed rotating machine and a current actual rotating speed of the high-speed rotating machine in real time; calculating a real-time driving efficiency ratio, which represents the actual rotating speed driven by unit driving force intensity; determining whether the high-speed rotating machine enters a rotating speed instability critical state caused by abnormal increase of fluid load according to a change trend of the real-time driving efficiency ratio relative to a preset reference; if it is determined that the rotating speed instability critical state is entered, a cooperative intervention operation is performed, which comprises: increasing the output intensity of the driving force source to increase the rotating speed, and reducing the supply rate of the fluid delivered in unit time; after the cooperative intervention operation is performed, the real-time driving efficiency ratio is continuously monitored, and the fluid supply rate is gradually restored to a set value after the real-time driving efficiency ratio returns to a normal range.

This invention relates to the field of medical electronic medical record data processing technology, and discloses a collaborative imputation method for missing values ​​in medical electronic medical records based on knowledge graphs. The method includes: a knowledge graph construction module extracting a lower bound constant and an upper bound constant of the physiological boundary, and a covariate proportion constant; an R-GCN knowledge encoding module generating a knowledge embedding vector; a temporal preprocessing and fusion module generating a knowledge-enhanced input sequence; a bidirectional Transformer encoding module generating an imputation result matrix; a multi-task joint optimization module updating the model parameter matrix; and an MC-Dropout uncertainty quantification module generating a complete dataset with confidence intervals. This invention utilizes the lower bound constant of the physiological boundary, the upper bound constant of the physiological boundary, and the covariate proportion constant in the multi-task joint optimization module to constrain the imputation result matrix and generate a knowledge consistency penalty loss, thus avoiding deviations of the imputation result matrix from the normal range threshold constraint relationship and physiological correlation.

The processor of the control device performs the following operations: associating detection distance with light intensity per detection pixel and acquiring data in each detection cycle (Cd); among the detection pixels that detect a failure echo that is associated with a detection distance within a failure range closer than the normal range and light intensity above the failure threshold, counting a first extraction number (N1) of detection pixels whose normal echoes within the normal range were not detected in the same detection cycle as the failure echo; among the detection pixels that detect a failure echo, counting a second extraction number (N2) of detection pixels that detect a normal echo in the same detection cycle as the failure echo; generating detection data (Dd) indicating a shading state in response to the first extraction number (N1) increasing to or exceeding the first determination threshold (Nt1); and generating detection data (Dd) indicating a dirty state in response to the second extraction number (N2) increasing to or exceeding the second determination threshold (Nt2).

The application discloses a tunnel risk real-time early warning method based on edge computing and cloud cooperation, relates to the technical field of tunnel risk early warning, and establishes a vehicle behavior set Beh on the edge side and further generates a vehicle waveform set Bwf representing the multidimensional dynamic change of the vehicle flow, wherein the wave front compression amount Cpr calculated by using the time series convergence of the deceleration peak value between adjacent vehicles can accurately reflect the early signs of the potential sudden stop wave formed in the vehicle flow, and the early prediction is no longer dependent on the lag signal of single vehicle deceleration, but is based on the change of the vehicle group structure. When the wave front compression amount Cpr and the vehicle group sudden stop deviation value Dis generated by comparing the normal vehicle flow wave propagation template set Tpl of the cloud exceed the normal range, it is found that the vehicle flow propagation mode has entered the abnormal interval, and the sudden stop warning set Trig constructed at this time can identify the group sudden stop risk to be formed in several seconds to tens of seconds.

In an environment where the demand, usefulness, and perceived value of resources change over time, the present invention provides devices, methods, and computer program products for automated prediction and modeling that improve one or more channels and associated conditions through which resources are directed to users. [Solution] A resource characteristics dataset from a third party with questionable reliability and a resource characteristics dataset from a distributed user platform are input into an exception detection model, and the two datasets are integrated and compared. Specifically, the difference (offset) between the two datasets is identified, and periods in which the deviation of that offset falls outside the normal range are detected as exception periods. Then, these exception periods are removed from the third-party data to create an updated dataset, and a reliable resource characteristics dataset is generated based on this updated dataset.

The present application belongs to the technical field of voiceprint recognition, and specifically relates to a voiceprint recognition method and system for elevator operation state monitoring. The present application adjusts the voiceprint feature model dynamically to adapt to sound changes under different working conditions, effectively removes noise interference and enhances sound features. The method constructs a sound identification atlas reflecting the sound characteristics of the normal operation of the elevator. By comparing the newly collected sound with the identification atlas and recording the difference points, and according to these difference points, whether the elevator state deviates from the normal range is evaluated. Finally, according to the evaluation result, a maintenance or alarm signal is triggered. This method not only improves the accuracy and reliability of the monitoring system, but also significantly enhances the noise resistance and stability of the system, reduces the false alarm rate, and realizes the rapid response to abnormal states, ensuring the safe operation of the elevator and improving the maintenance efficiency and safety.