42results about How to "The warning result is accurate" patented technology

The invention relates to a vehicle intersection collision early warning method. Firstly, the position, direction, track radius, speed and acceleration information of a local vehicle and a target vehicle is collected; the driving trajectories and the collision point of the local vehicle and the target vehicle are calculated according to the position, direction and track radius information, and a collision area is calculated according to the collision point; whether the time from driving into the area to driving out of the collision area of the local vehicle and the time from driving into the collision area to driving out of the collision area of the target vehicle are overlapped or not is judged, when the two times are overlapped, the time T needed by the driving into the collision area of the local vehicle with a current speed and acceleration is calculated, and if the time T is smaller than a set value, the early warning result of alarm is executed. According to the scheme, the problems that a collision position is not accurate, the estimated time deviation of arriving an intersection is large and a lot of wrong alarms exist in the prior art are solved.

The invention relates to an electrical equipment operation condition classification method, which comprises the steps of building training data of a mean clustering model; pre-processing the training data, deleting invalid data and carrying out normalization processing; adopting a K-means++ algorithm for determining an initial clustering center; determining upper and lower limitations of clustering classification categories; circularly realizing a clustering process of multiple categories; carrying out evaluation analysis on a clustering result, and determining an optimal clustering category number K value; selecting an optimal K value model as an optimal condition classification result, so that the efficiency and the accuracy are improved.

The invention discloses a tribological performance monitoring and early-warning device and a method of a disc brake. The method comprises the following steps: developing a tribological performance testing experiment through simulating the braking working condition of the disc brake to obtain a data sample; constructing a tribological performance intelligent predicting model based on the neural network technology by utilizing the data sample; and realizing the real-time monitoring of the tribological performance of the disc brake and the automatic early warning of an abnormal tribological state based on the predicting capability of the model by utilizing the monitoring and early-warning device. The device consists of a sensing detecting system, a data collecting system, a calculation processing system and a software system; the sensing detecting system detects braking working condition parameters of the disc brake in real time through a photoelectric encoder, a positive pressure sensor and a temperature-measuring thermocouple; the data collecting system collects, amplifies and converts detected signals; and the calculation processing system receives braking working condition data uploaded by the data collecting system, and then, calls a neural network predicting module, predicts and outputs the tribological performance parameters of the disc brake, and carries out real-time display and automatic early warning through a software system. The method and the device have high monitoring precision and a quick and accurate early-warning result.

The invention discloses an intelligent early warning method for dam safety monitoring data. The method comprises the steps of early warning model establishment, threshold value setting and mutual feedback type early warning. Gross error identification and gross error processing are carried out, model sample data quality is improved, according to the monitoring items, independent variable relevance, historical monitoring data quantity and historical monitoring data distribution, different early warning models and indexes are established, including a stepwise regression model, a correlation vector machine model and a gray system model; the established models can reflect the relationship between the independent variable and the dependent variable more truly and are wide in application range,according to a measuring instrument, measuring point attributes, a threshold value, an early warning model and indexes, real-time early warning is carried out on monitoring data, monitoring instrumentabnormity early warning is sent to monitoring personnel, or dam safety early warning is sent to dam safety management personnel, experts with professional knowledge and rich experience are not needed, the workload is small, the early warning speed is high, and the early warning result is more accurate and reliable.

An embodiment of the invention discloses an urban inland inundation early warning system and an urban inland inundation early warning method. The urban inland inundation early warning system comprisesa data acquisition device and a cloud server, wherein the data acquisition device is configured to acquire and store urban basic data and urban monitoring data of a to-be-early-warned region; the cloud server is configured to determine rainfall runoff production and rainfall confluence of the to-be-early-warned region according to the urban basic data and the urban monitoring data, perform urbaninland inundation simulation on the to-be-early-warned region according to the rainfall runoff production and rainfall confluence to obtain an inland inundation simulation result for performing inlandinundation early warning. By adopting the urban inland inundation early warning system and the urban inland inundation early warning method, urban inland inundation early-warning analysis is achievedby means of the cloud server, urban inland inundation early-warning is more convenient by utilizing the advantages that the cloud server is easy to deploy rapidly, change flexibly, low in cost, easyto manage in a centralized mode and the like, and due to the processing capacity of the cloud server, the urban inland inundation early-warning analysis capacity is higher, and the early-warning result is more precise.

The invention provides a CNN-based power equipment fault judgment and early warning method, a terminal and a readable storage medium. The method comprises the steps of obtaining test data; preprocessing the data; processing the data by using an offline model; and performing fault prediction of data. According to the method, the coal mill data is modeled through a deep learning method, fault prediction is achieved, mass historical data of coal mill equipment are fully mined through an existing data mining and machine learning modeling method, and an efficient and practical model is establishedto conduct detection and early warning on the real-time state of the coal mill. Knowledge and experience of experts and operating personnel are combined with data mining and machine learning methods and complemented with each other. The data can be automatically analyzed and modeled according to the data characteristics, and the threshold of operating personnel is lowered. The fault prediction model of the coal mill established by the invention can contain more complex causal relationships implicit among the indexes, so that the possibility of loss of a large amount of effective information isavoided, and the result is relatively reasonable and accurate.

The invention discloses a distribution network fault early warning method and device, a readable medium and electronic equipment. The method comprises the following steps: dividing a distribution network to obtain sub-distribution networks; periodically obtaining historical operation data and historical influence data of the sub-distribution network; adjusting a historical fault threshold value according to the obtained historical operation data, historical influence data and a pre-obtained threshold value adjustment rule, and determining a current fault threshold value corresponding to the sub-distribution network; obtaining current operation data and current influence data of the sub-distribution network; determining current evaluation data corresponding to the sub-distribution network according to the current operation data, the current influence data, pre-obtained operation data and weight coefficients corresponding to all indexes in the influence data; and judging whether early warning information is generated or not according to the current fault threshold and the current evaluation data respectively corresponding to the sub-distribution networks. According to the distribution network fault early warning method provided by the invention, the distribution network is divided, and the current fault threshold of the sub-distribution network is periodically adjusted, so that the accuracy of the fault early warning result is improved.

The present invention discloses a lightning stroke flashover early warning method and system based on historical information. The method comprises: collecting the historical information of the lightning stroke, dividing the historical information of the lightning stroke into a lightning stroke flashover and non-flashover of the lightning stroke, and constructing a KD tree according to the historical information of the lightning stroke; when the lightning stroke happens, obtaining the lightning stroke information to be subjected to early warning through the real-time monitoring of an atmospheric electric field and the like, and employing the KD tree nearest neighbor search algorithm to search K neighbor points of the lightning stroke information to be subjected to early warning; and finally determining the category of the information to be subjected to early warning through adoption of the K neighbor algorithm to output an early warning result. The early warning result through the method provided by the invention is more accurate.

The present invention relates to a road risk early warning method and device. Data corresponding to dimensions required by a road model is screened out from sample data comprising a plurality of datasources, wherein the data sources comprise map data, traffic data, weather data, automobile company data, driver data and accident data, the data sources are very rich, and based on this, informationof the established road model is more completed. Based on the established road model, each road is subjected to clustering for classification to allow the most similar roads to be classified to one class, therefore, the most similar safety levels are classified to one class, the risk early warning levels of the roads are determined, and the early warning result is more accurate.

The invention provides a monitoring and early warning method and system for a special steel production workshop, and belongs to the technical field of special steel, and the method comprises the steps: collecting and obtaining a plurality of historical production information sets of the production workshop in the historical production process; acquiring a historical product information set of the production workshop in a historical production process; analyzing and judging the correlation between the historical product information set and the plurality of historical production information sets to obtain a correlation information set; according to the correlation information set, a plurality of historical production information sets with the maximum correlation are selected and obtained, and a plurality of pieces of sensitive production information are obtained; acquiring a real-time sensitive production information set of the production process of the current production workshop; and inputting the real-time sensitive production information set into an early warning analysis model for early warning. The technical problem that the current special steel production monitoring effect is poor is solved, and the technical effect of improving the accuracy, timeliness and efficiency of special steel production workshop monitoring and early warning is achieved.

The invention provides an equipment fault early warning method and system based on multi-modal sensitive feature selection fusion, which are used for solving the technical problems of low accuracy and narrow application range of an early warning system based on single-modal features. The method comprises the following steps: firstly, extracting a feature vector of collected parameter operation data of a normal state of historical equipment, and standardizing the feature vector; secondly, obtaining sensitive features of the standardized feature data by using kernel PCA based on a Mercer kernel, and training a GMM according to the sensitive features; then obtaining real-time state data of the equipment during operation on line, and selecting multi-mode sensitive features according to the steps; and finally, inputting the multi-modal sensitive features into a trained GMM model, and determining whether to give an alarm according to whether the obtained probability value is smaller than a preset threshold value. According to the invention, through selection and fusion of the multi-modal features of the equipment, the accuracy of an equipment fault early warning system is improved, and off-line early warning model construction and on-line real-time fault early warning are realized.

The invention relates to the technical field of atmospheric environmental monitoring, and particularly discloses a warning method for atmospheric environmental monitoring, the warning method includesthe steps of acquiring atmospheric environmental element data, and processing the atmospheric environmental element data to acquire data processing results; monitoring the data processing results in real time; constructing graphics for the data processing results, and displaying and analyzing the constructed graphics; setting corresponding warning thresholds for the atmospheric environmental element data; according to the real-time monitoring conditions and the constructed graphics, performing alarm display of the data reaching the warning thresholds, the invention further discloses a warningsystem for atmospheric environmental monitoring. By the warning method, the problem that environmental monitoring warning cannot be conducted in the prior art can be solved effectively.

The invention discloses a three-dimensional dynamic detection and grading early warning device for the tower top position of a building tower crane, which is used for a building tower crane system. The building tower crane system comprises a tower body of the building tower crane, a GNSS detection station located at the top of the tower body and a GNSS reference station located on a construction site. The device comprises a three-dimensional dynamic detection and calculation unit for receiving satellite positioning data with high sampling rate from the GNSS reference station and the GNSS detection station and calculating position detection results of the north direction, the east direction and the zenith direction of the tower top, a detection parameter determination unit which is used fordetermining tower top three-dimensional dynamic detection parameters of the current detection epoch according to the position detection results in the north direction, the east direction and the zenith direction of the tower top, an early warning parameter determination unit which is used for determining early warning parameters of the current detection epoch according to the nominal detection precision of the GNSS detection station, and an early warning unit which is used for comparing the tower top three-dimensional dynamic detection parameters with the early warning parameters and determining to carry out early warning according to a comparison result.

The invention discloses a bearing fault early warning method based on high-frequency signal characteristic amplitude, which belongs to the field of rolling bearing fault early warning. The bearing fault early warning method comprises the steps of: collecting vibration signals of a trained bearing at equal intervals; carrying out discrete wavelet transform on the vibration signals and extracting high-frequency components; sorting absolute values of the high-frequency components to obtain an enhanced impact amplitude LR and a carpet impact amplitude HR; taking an LR-HR value corresponding to thesame moment as an early warning feature of the moment; carrying out normal stage and fault stage division on the trained bearing according to the LR-HR value of the whole life cycle of the trained bearing; performing Weibull distribution fitting on the early warning feature of each stage to obtain probability distribution; acquiring an LR-HR value of a test bearing in operation; and calculating the probability that the test bearing is in a normal stage and a fault stage based on the probability distribution. According to the bearing fault early warning method, the high-frequency noise signalsare used for fault early warning, the complex denoising and signal enhancement processes are avoided, the fault early warning characteristics can be increased along with the degradation severity, theearly warning speed is high, and the method is suitable for practical application.

The invention discloses a disaster detection and early warning system which comprises a data center, a meteorological module, a rainwater detection module, a wind speed detection module, a soil texture detection module, a cruise scanning module, a fixed-point scanning module, an analysis module, a prompt module and an early warning module. The rainwater detection module is used for detecting the precipitation amount of the orchard area in real time; the wind speed detection module is used for detecting the wind speed of the orchard area in real time; the soil texture detection module is used for detecting the soil texture structure of the ground surface layer of the orchard area; the fixed-point scanning module is used for monitoring areas where debris flow and landslide easily occur in the orchard, and the areas include slope areas with the gradient larger than 10 degrees; a region having a fault; a rock-soil type geological area; the vegetation covers less than 40% of the area. According to the disaster detection and early warning system, influence data possibly causing debris flow or landslide are comprehensively collected and comprehensively analyzed, so that the early warning result is more accurate.

The invention discloses a debris flow early warning system based on mechanism and machine learning coupling. The debris flow early warning system comprises a feature vector set unit, a data input unitand a model training unit. The data input unit is used for inputting the feature vector set unit into a machine learning model; and the model training unit is used for training a machine learning model by calling a function interface in a machine learning library sklearn and testing the machine learning model. The invention further discloses a debris flow early warning method. The debris flow early warning method comprises the following steps: S1, constructing a feature vector set of the unstable small watershed unit and the stable small watershed unit; s2, based on the data characteristics of the feature vector set, selecting a machine learning model, and based on a machine learning library sklearn with a built-in appropriate kernel function, establishing a debris flow disaster prediction model; s3, and carrying out forecasting. The prediction accuracy can be effectively improved, and the false alarm rate of the model is reduced.

The invention discloses a cardiovascular disease big data analysis system. The cardiovascular disease big data analysis system adopts a B / S architecture, and includes a web-based user interaction interface, a web application server, and a database server, wherein the web-based user interaction interface sends an operation request to the web application server, and receives operation request response data of the web application server to display the operation request response data; the web application server receives the operation request of the web-based user interaction interface, accesses the database server based on a Hibernate framework and receives an operation result returned by the database server; and the web application server further receives medical examination data uploaded bythe web-based user interaction interface and the user physical condition self-evaluation data corresponding to the current medical examination data, and performs big data analysis on the uploaded medical examination data and the user physical condition self-evaluation data to obtain a disease early warning conclusion. The invention also discloses a cardiovascular disease big data analysis method.

The invention relates to an online monitoring and early warning method of grain depot underground pipe network liquid leakage. The online monitoring and early warning method of grain depot undergroundpipe network liquid leakage comprises the following steps that firstly, credible neighbor sets of a to-be-detected current node are selected out based on collaborative filtering; secondly, a final credible neighbor set is selected out and formed; thirdly, during detection, according to the flow speed differences between the current node and all the nodes in the final credible neighbor set, statistics of the number of the nodes, with the flow speed difference exceeding a flow speed difference threshold value, in the final credible neighbor set is conducted, and if the number of the nodes is larger than a quantity threshold value, the current node is marked as an abnormal node; and fourthly, an abnormal pipe section on a branch pipe can be determined through the abnormal node, and the monitoring platform sends out early warning. According to the online monitoring and early warning method of grain depot underground pipe network liquid leakage, the nodes for online parameter measurement are configured, node data are gathered to conduct selection and comparison on the nodes based on collaborative filtering, the abnormal node is obtained based on the difference of the comparison difference values, the abnormal pipe section is determined according to the abnormal node, and then an alarm and early warning are given out; and therefore, the online monitoring and early warning method ofthe grain depot underground pipe network liquid leakage is worthy of great popularization.

The invention provides a wind turbine generator transmission chain fault early warning method based on big data analysis. The wind turbine generator transmission chain fault early warning method comprises the following steps: step 1, establishing a flexible multi-body system dynamic model corresponding to a wind turbine generator transmission chain; step 2, obtaining a resonance point corresponding to the wind turbine generator transmission chain according to the obtained flexible multi-body system dynamic model, and determining an element with abnormal vibration in the wind turbine generator transmission chain according to the obtained resonance point; step 3, setting a test point of the wind turbine generator transmission chain in actual operation, and performing vibration benchmark test on abnormal vibration elements in the wind turbine generator transmission chain at the test point to obtain benchmark test data corresponding to each abnormal vibration element; step 4, judging the working condition of the transmission chain of the wind turbine generator according to the obtained benchmark test data, and if the transmission chain of the wind turbine generator is abnormal, entering step 5; 5, judging the fault position of the transmission chain of the wind turbine generator by using a preset network algorithm; according to the invention, multiple monitoring and early warning work can be carried out on the transmission chain of the wind turbine generator, so that the early warning result is more accurate, workers can find the early warning result in time, and unnecessary loss is reduced.

The invention provides a complaint early warning processing method and device. The method comprises the following steps: obtaining complaint amount data in a preset first time period, screening abnormal time points from the data of each time point based on a statistics and rule method, labeling the abnormal time points, constructing sample data according to complaint amount data of normal time points and complaint amount data of abnormal time points labeled, and standardizing the sample data according to different complaint businesses and cities; for the data of each time point in the obtainedcomplaint amount data, features are constructed according to the accumulated complaint amount, and the constructed features are screened according to importance sorting; training the standardized sample data and the screened features to obtain a trained fusion model, and performing complaint early warning by using the fusion model; wherein the fusion model is combined with a logistic regression model and a random forest model. Automatic early warning of full-service incoming call complaints in the communication field can be realized, the fault discovery time delay can be shortened, and the early warning result is more accurate.

The invention discloses a dangerous chemical road transportation risk early warning method, which comprises the following steps of: S10, determining the weight of an early warning index, and analyzinga dangerous chemical road transportation early warning index system by adopting an analytic hierarchy process to obtain the weight of the early warning index and determine an early warning gray classto which each index belongs; s20, calculating a gray early warning coefficient; step S30, calculating a gray early warning weight vector and a weight matrix, and processing decentralized informationof early warning experts into a weight vector for describing different gray degrees; step S40, comprehensive early warning: performing single-valued processing on the basis of the step S30 to obtain acomprehensive early warning value and an early warning level of the single road transportation risk; and step S50, taking prevention measures, namely taking prevention measures matched with the earlywarning levels according to the early warning levels obtained in the step S40. Compared with the prior art, the hazardous chemical substance road transportation risk early warning method provided bythe invention effectively divides the risk early warning level of hazardous chemical substance road transportation, and improves the safety of hazardous chemical substance road transportation.

The invention provides a portable multi-parameter motor state detection device and method. The device comprises a vibration sensor, a noise sensor, a voltage sensor, a current sensor, a temperature sensor, a lithium battery, a signal acquisition board card, a control board card and a display screen. The signal acquisition board card is respectively connected with the vibration sensor, the noise sensor, the voltage sensor, the current sensor, the temperature sensor, the lithium battery and the control board card; the control board card is connected to the display screen; according to the device and the method, state parameter information such as vibration, noise, voltage, current, temperature and the like of the motor can be synchronously acquired, real-time online data signal processing is carried out, the health state of the tested motor is comprehensively evaluated by adopting a weight coefficient calculation method, and early warning grading is carried out.

The invention discloses a transparent monitoring system and method for a mine fire. The transparent monitoring system comprises gas, temperature and potential monitoring sensor modules, multi-point information data processing modules, a wired transmission private network, a ground expert monitoring system, a user terminal and the like. The multi-point gas, temperature and potential monitoring modules are in communication with one another to form a monitoring network. The monitoring method adopts the system, and comprises the following steps that after being processed in the first step, information acquired by the monitoring network is transmitted to the multi-point information data processing modules through a radio signal, and after being processed and gathered in the second step, the information forms an electric signal which is transmitted to the ground expert monitoring system through the wired transmission private network; and the expert monitoring system inverts the information state of the goaf according to the gas, temperature and potential multi-point information, displays the danger levels of different areas in real time, and gives out early warnings of different levels according to the danger levels. The system and method are reliable, stably provide underground omnibearing monitoring information during operation, and effectively realizes real-time monitoring of an underground monitoring area.

The invention discloses an information type manipulation automatic identification method based on multi-channel heterogeneous data. The method comprises the following steps: obtaining multichannel heterogeneous data, classifying and storing the obtained heterogeneous data according to the structured data and the unstructured data; establishing an information sensing and monitoring database; establishing a multi-dimensional monitoring index, establishing an integrated discrimination model taking the multi-dimensional monitoring index as a feature, monitoring the data in the information perception and monitoring database in real time by adopting the discrimination model, outputting a primary early warning result, and forming a secondary early warning result based on core index screening on the basis of the primary early warning result; according to the method, the whole process from active acquisition of multi-channel heterogeneous data to automatic pushing of information type control clues can be realized, so that a financial supervision department is helped to actively discover suspicious clues of information type control on the market and strike in time, and the supervision efficiency is improved.

The invention relates to a real-time early warning method and device based on AIOT and an enterprise safety index; the method comprises the steps: obtaining the distribution image data of goods on a storage shelf, calculating the uniformity of the goods, calculating the shaking degree of the goods, and calculating the instability of the goods according to the obtained shaking degree of the goods at different moments; then acquiring the danger degree distribution of all the goods on the goods shelf by combining the uniformity of the goods; processing the danger degree distribution of the goods to obtain danger sources and association weights among the different danger sources; calculating the danger level of the goods on the current shelf in combination with the working danger level of the working vehicle; acquiring the final goods shelf danger degree in combination with the goods shelf accident degree, and performing real-time alarming on operation vehicles surrounding the goods shelf. According to the invention, serious consequences caused by domino effect or superposition of risk factors at different moments and in different places can be found, and the risk early warning capability is stronger and more reliable.

The invention provides a risk behavior monitoring and early warning method and system suitable for special crowds. The invention discloses a risk behavior monitoring and early warning method suitablefor special populations. The method comprises the steps of obtaining individual facial activity monitoring data of the special populations; Inputting the recorded facial activity characteristics of the special crowd individuals into a pre-trained emotion classifier for emotion classification; And determining whether to carry out early warning according to the emotion type of the special crowd individual. According to the embodiment, the emotion state is recognized and analyzed through the face image, and therefore the early warning result can be more accurate. Moreover, the emotion of the individual can be dynamically monitored in real time, the real-time performance of monitoring can be achieved, and the monitoring efficiency can be improved.

The invention discloses a three-dimensional dynamic detection and classification early warning device for the top position of a construction tower crane, which is used in a construction tower crane system. The construction tower crane system includes a tower body of a construction tower crane and a GNSS detection station located at the top of the tower body 1. The GNSS reference station located at the construction site, the device includes: a three-dimensional dynamic detection calculation unit, which receives high-sampling satellite positioning data from the GNSS reference station and the GNSS detection station, and calculates the north direction, east direction and sky direction of the tower top. The top position detection result; the detection parameter determination unit, from the north, east and zenith position detection results of the tower top, determines the three-dimensional dynamic detection parameters of the tower top in the current detection epoch; the early warning parameter determination unit, based on GNSS detection The nominal detection accuracy of the station determines the early warning parameters of the current detection epoch; the early warning unit compares the three-dimensional dynamic detection parameters at the top of the tower with the early warning parameters and determines the early warning according to the comparison result.

The embodiment of the invention provides a small sample threat risk early warning method and device based on deep learning, and the method comprises the steps: collecting Internet threat risk information; obtaining corresponding word sequence data according to the Internet threat risk information; respectively inputting the word sequence data into a fragment semantic extraction model and a semantic matching model to respectively obtain a first feature vector and a second feature vector, and fusing the first feature vector and the second feature vector to obtain a deep feature; inputting the deep features into a trained deep neural network model to obtain an early warning result of the Internet threat risk information; and obtaining the trained deep neural network model by training according to the deep feature samples and the corresponding classification labels. According to the method, Internet threat risk information early warning is carried out by using the extracted deep features, so that the obtained early warning result of the Internet threat risk information is more accurate.