75 results about "Diagnosis problem" patented technology

A system and process for providing a computerized medical and biographical records database and diagnostic information. A medical records database and diagnostic program is stored on a central computer that is accessible to individuals using remotely situated computers connected to a computer network. Individual patient medical and biographical records are owned by individual patients who can enter information in their record as well as grant or deny authorization to others, such as health care professionals, insurance providers and other entities, to review part or all of their record. The diagnostic program provides a series of diagnostic questions to an individual who must respond either "yes" or "no" to each question. Each potential response is weighted relative to its importance to a particular disease diagnosis. Relative weights for all responses to diagnostic questions are summed to identify potential diagnoses to connected to the answered questions. The diagnostic program provides the individual with a list of potential diagnoses as well as permitting the individual to save the information to his or her individual medical and biographical record. The information maintained in the above system and process is utilized for health care financing and insurance.

Thousands of process and equipment measurements are gathered by the modern digital process control systems that are deployed in refineries and chemical plants. Several years of these data are historized in databases for analysis and reporting. These databases can be mined for the data patterns that occur during normal operation and those patterns used to determine when the process is behaving abnormally. These normal operating patterns are represented by sets of models. These models include simple engineering equations, which express known relationships that should be true during normal operations and multivariate statistical models based on a variation of principle component analysis. Equipment and process problems can be detected by comparing the data gathered on a minute by minute basis to predictions from these models of normal operation. The deviation between the expected pattern in the process operating data and the actual data pattern are interpreted by fuzzy Petri nets to determine the normality of the process operations. This is then used to help the operator localize and diagnose the root cause of the problem.

A peripheral electronic device includes a health check application configured to execute automatically upon connection of the peripheral device to a data source, such as a personal computer. The health check application can diagnose problems and if necessary, repair the problems with the peripheral device, the data source, or both. Examples of problems include corrupted data and indications of software, firmware, and hardware failures or impending failures. In some instances, the health check application can provide a warning of an impending failure. The health check application, after initially executing, can be triggered in various ways to scan again for problems. In addition to finding and repairing problems, the health check application can also attend to maintenance.

The invention provides a ground grid fault diagnosis method based on a self-adaptive particle swarm optimization algorithm. A fault diagnosis equation is established according to a node voltage analytical method in an electric network theory, then a target optimization function is obtained according to a minimum energy principle, the problem of ground grid fault diagnosis is converted into the problem of target optimization with constraint conditions, then the self-adaptive particle swarm optimization algorithm is adopted to solve the optimization problem, and a diagnosis result is obtained. In the ground grid fault diagnosis method based on the self-adaptive particle swarm optimization algorithm in the invention, through establishing a mathematical model for ground grid fault diagnosis, and using the optimization target function, the ill-condition degree of the diagnosis equation is lowered, and the global optimization capability of the self-adaptive particle swarm optimization algorithm is called, thereby improving the efficiency and the accuracy of solving the optimization model, and enabling the diagnosis result to be accurate and reliable.

The invention discloses a DSP failure diagnostic system based on an immunity genetic algorithm, which consists of an FTU, a RTU, a DSP and an industrial controlling upper computer of a failure signal output display unit. The immunity genetic algorithm comprises the steps of: preparing a parameter code; setting an initial group; designing an adaptability function; setting a matching set; setting a controlling parameter; and solving iteration. The application of DSP failure diagnosis based on the algorithm comprises the steps of: taking the DSP as a core control process system; taking a discrete signal as an input signal of the DSP core control process system when the FTU and the RTU monitor the variable quantity of failure power frequency; and transferring a result which is obtained by the algorithm into a failure message in a practical system through the DSP core control process system to be showed on a monitoring upper computer. The invention has the advantages of: (1) solving the problem of the failure diagnosis of an electrical power system when a protection message is imperfect; and (2) inducing the application of an immune system-matching set to improve the whole searching capability of the algorithm.

There is provided a data processing system-implemented method, system and an article of manufacture for providing a serviceability framework for autonomic resource management in a computer data centre. The data centre is monitored based on a logical representation (model) in the serviceability framework representative of the actual physical devices. The data centre logical model is constantly synchronized with the physical devices of the actual data centre where inconsistencies occur, and fast reporting is required before more problems occur. Monitoring agents associated with all the data centre devices are implemented to quickly identify and deal with problems before human intervention is required. A data centre health monitor is capable of detecting the malfunctions of typical devices and sub-systems in the data centre. For problems or failures that require drastic steps, the subsystem may be isolated and then interrogated separately from the rest of the data centre. Interruptions may be avoided by cloning a designated portion of the data centre systems for off-line trouble-shooting, thereby saving the systems from shutting down totally. A robust set of messages and trace logs including current operational status and health of the data centre may be provided for further diagnostic problem determination.

The invention relates to a fault code, data stream and freeze frame data storage and playback method. The method includes the steps that first, fault code, data stream and freeze frame data are recorded in a data area of a memory; second, indexes of the fault code, data stream and freeze frame data are recorded in an index area of the memory; third, when the next record is made, the start address of the index area and the start address of the data area are recorded in a public area of the memory; fourth, when the data are played back, the index area is searched so as to correspondingly read out the data in the data area. According to the fault code, data stream and freeze frame data storage and playback method, through recording of a large amount of data of fault codes, data streams and freeze frames, professionals and car owners can reasonably analyze data of cars so as to judge the using states and the diagnosis problems of the cars, and thus professional analysis is obtained.

A program storage device is provided readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for classification of biological tissue by gene expression profiling. The method steps include providing a training set of gene expression profiles of known tissue samples, providing a first-layer strong classifier of the known tissue samples by combining weak classifiers using boosting, creating two sample sets based on the first classifier, populating the two sample sets with a next-layer of classifiers based on a previous-layer classifier, organizing the classifiers in a tree data structure, and outputting the tree data structure as a probabilistic boosting tree classifier for tissue sample classification and disease subtype discovery. A multi-class diagnosis problem is transformed to a two-class diagnosis process by finding an optimal feature and dividing the multi-class problem into two-classes.

The invention relates to a fault diagnosis method based on a model, which recognizes unknown nonlinear terms by utilizing a least square support vector machine and a back scrolling method; a recognition model is added to a nonlinear proportional high-order integral observer, and thereby, the influences of the unknown nonlinear terms on fault diagnosis accuracy are eliminated, and the rapid accurate estimation of system faults is realized. The fault diagnosis method is disclosed in allusion to that the fault diagnosis problems of the unknown nonlinear terms exist in the system model; a specific equipment fault model is utilized to verify the fault diagnosis method, and the fault diagnosis method can be expanded to the fault diagnosis of other equipment which can be described by the model.

The present invention discloses a method for clinical detection of SARS virus and its kit. According to the characteristic analysis of SARS virus genome sequence a specific region can be selected, and according to the characteristics of that said virus is of ribonucleic acid virus a specific primer sequence can be used and the reagent and techniques related to RT-PCR and PCR can be adopted so as to create a set of methods for quickly detecting SARS virus. Said invented method has higher accuracy, and provides its diagnosis method and its kit.

The invention discloses a rapid fault diagnosis method used for a microgrid, which adopts a mode of step-by-step diagnosis and comprises the following steps that firstly, primary diagnosis is carried out by utilizing the switch information of a network, i.e. newly added passive sub-networks are judged as fault regions and fault elements according to the difference of before and after topology analysis results of faults, and for simple faults, a unique fault region and fault element can be determined. For complicated faults, a plurality of suspected fault solutions can be possibly presented in the result of the primary diagnosis of the switch information. At this moment, a second-step diagnosis is entered, and the diagnosis is carried out by utilizing the protection information of the network. A new target function is established in protection information diagnosis by utilizing the protection information of the elements; the fault diagnosis problem of the microgrid is expressed as the 0-1 integer programming problem; a genetic algorithm and tabu search mixed strategy is introduced to solve the target function; and the fault elements are determined by the optimal solution. The invention can effectively improve the fault diagnosis efficiency, reduces the time of fault diagnosis and improves the fault diagnosis quality.

The invention discloses a multi-scale binary tree blast furnace fault diagnosis method based on sample segmentation, belonging to the technical field of blast furnace fault diagnosis. The method comprises the following steps of: firstly, acquiring blast furnace production condition and equipment operation state data, detecting the data and performing normalization for the extracted data through a mean-variance normalization method; converting a blast furnace fault diagnosis problem into a dichotomy problem to perform multi-classifier design; finding a segmentation plane through an improved generalized eigenvalue support vector machine, converting into two dichotomy problems, respectively finding a distance measuring matrix having local properties and being adaptive for each type of fault data itself, and designing two classification hyperplanes based on different scales through the support vector machine. The method provided by the invention is suitable for identification of high-dimensional nonlinear fault data; and by means of segmenting sample data and measuring similarity among the samples with a multi-scale standard, the method gives consideration to global and local logic structures of the identified data, reduces complexity of the identified fault problem and improves precision of fault diagnosis.

The invention discloses a method and system for diagnosing online part faults of turbofan engines. The method comprises the following steps of: establishing a diagnosis model by adoption of a Broydeniteration method; establishing an LM optimizer; solving a health parameter; determining a mutational fault mode; estimating thrust and a margin; and storing above diagnosis results and outputting a diagnosis report. According to the method and system, the diagnosis problem when fault sample data is lack and process noise is non-Gaussian noise during existing turbofan engine online fault diagnosisprocess is solved; unmeasurable flow and efficiency can be estimated; thrust, fan margin and gas compressor margin performance parameters can be monitored, so that diagnosis basis is provided for subsequent possible fault-tolerant control measures; and the calculation amount is relatively small and the turbofan engine onboard real-time requirements can be satisfied.

The invention discloses a decision tree SVM fault diagnosis method for a three-level inverter of a photovoltaic diode clamp type. Aiming at a fault diagnosis problem of the three-level inverter in a photovoltaic microgrid and taking an inversion state as an example, the method comprises the steps: firstly analyzing the operation state of an inverter main circuit, and carrying out the fault classification; secondly taking three bridge arm voltages (middle, upper and lower) as measurement signals, and extracting characteristic signals through employing a wavelet multi-scale decomposition method, thereby generating a decision tree SVM classification model through employing a particle clustering algorithm; finally achieving the multi-mode fault diagnosis of the three-level inverter of the photovoltaic diode clamp type. The method is advantageous in that the method can clearly distinguish all fault states of the three-level inverter of the photovoltaic diode clamp type, employs a smaller number of classification models to complete the fault diagnosis task, is high in diagnosis precision, and is strong in anti-interference capability.

The invention provides an active fault detection and diagnosis method for a variable air volume box (VAV box). Aiming at the practical situation that faults are difficult to diagnose effectively through a traditional passive fault detection and diagnosis method, the invention provides a method for obtaining a targeted fault symptom measurement value by introducing specific disturbance into an automatic control system. According to the method, most of the faults of the variable air volume box can be effectively diagnosed under the condition that no additional measure point and diagnostic information are added; and a complete fault detection and diagnosis process is provided, in addition, a complete active fault diagnosis rule is formulated for common faults of the variable air volume box, and therefore the fault diagnosis problems caused by the facts that the number of sensors of an existing variable air volume box is small, the diagnosis information is incomplete and the fault featuresare similar can be solved. The novel active fault detection and diagnosis method has the advantage that most of the faults of the variable air volume box can be effectively detected and diagnosed.

The invention discloses a zero-sample learning method based on data enhancement. The zero-sample learning method comprises the steps of drawing a contour of a focus, performing focus contour processing on the contour according to a morphological operation method, and then filling a color on the focus by means of a continuous gradient color filling method; increasing diversity of the focus with filled colors by means of a matrix linear transforming method, generating a plurality of simulated focus pictures, and combining the simulated focus pictures with a disease background picture by means ofimage fusion technology, and adding a Gaussian white noise to the fused picture for obtaining an expanded sample set; training a VGG classifier by means of the expanded sample set, and training an optimal classifier; and testing a dermatopathy case by means of the optimal classifier. The zero-sample learning method effectively settles a zero-sample learning auxiliary diagnosis problem of a rare disease.

The embodiment of the invention discloses a double 2-vote-2 system and a safety diagnosis method thereof and relates to the computer system safety processing technology field. The system comprises a main system unit, a standby system unit and a switching unit. The safety diagnosis method comprises the following steps of carrying out power on; carrying out power on self-checking; carrying out dataoutput; carrying out data input; operating; self-checking; and then successively carrying out a cycle period of data output, data input, operation and self-checking. In the cycle period of data output, data input, operation and self-checking, a first CPU of a main system and a second CPU of the main system are synchronized, mutually inspected and compared, and the first CPU of a standby system andthe second CPU of the standby system are synchronized, mutually inspected and compared. In the prior art, the double 2-vote-2 system lacks diagnosis of intermediate process data, a detection coverageis not high, the system is difficult to reach a safety requirement, and the system lacks diagnosis of a state of the system itself. In the invention, the above diagnosis problems can be solved.

The invention discloses a fuzzy FMEA (Failure Mode and Effect Analysis) based system automatic fault diagnosis method, and relates to the technical field of electronic communication fault detection. Effective quantitative processing for the fault mode occurrence degree, the fault mode severity and the fault mode detection degree is realized through a fuzzy FMEA analysis system. System fault diagnosis problems are overcome, and the accuracy of fault diagnosis is ensured. Meanwhile, automatic diagnosis for faults is realized, so that manpower and working hours are saved. The technical scheme comprises the key points that a diagnosis data source is acquired; analysis and processing are carried out on the diagnosis data source, and the processed diagnosis data source is inputted into the fuzzy FMEA analysis system; the fuzzy FMEA analysis system carries out analysis on the processed diagnosis data source and acquires a fault diagnosis result. The method disclosed by the invention is mainly applied to system automatic fault diagnosis.

The invention discloses a power transformer defect precedent citing diagnosis method applying oil chromatography monitoring data. Currently, transformer defect diagnosis is still a work demanding rich experience. Because of lack of an effective mathematical model, in an actual production process, the transformer defect diagnosis is mainly based on experience-based judgment of personnel for measuring, regulating and operating, and thus it is hard to make breakthroughs in both the diagnosis efficiency and accuracy. Aiming at the distribution characteristics of oil chromatography characteristic gas data, a normalization hypercube mapping method is put forward, and the oil chromatography data is mapped to a hypercube spatial area which can be directly applied; meanwhile, a precedent citing similarity algorithm and a diagnosis result judgment method which is based on weighting vote are put forward pertinently. According to the power transformer defect precedent citing diagnosis method applying the oil chromatography monitoring data, the power transformer defect diagnosis problem is solved, the analysis accuracy is improved, and the capacity of a power grid operation and maintenance department in processing the defects and faults of oil immersed type transformer equipment is promoted.

The invention discloses a gear box single and composite fault diagnosis method, device and system, and belongs to the field of mechanical equipment state monitoring and fault diagnosis. The diagnosismethod comprises the following steps: (1) collecting vibration signals of the gearbox; (2) dividing the acquired vibration signals into a plurality of data segments, and calculating to obtain a wavelet time-frequency image corresponding to each data segment, wherein two adjacent data segments have overlapped data; (3) dividing the wavelet time-frequency image into a training set and a test set, and normalizing the training set and the test set; (4) training a multi-label convolutional neural network by using the training set; (5) testing the trained multi-label convolutional neural network byusing the test set; and (6) taking the qualified multi-label convolutional neural network as a fault diagnosis model. According to the method and equipment, the excellent feature extraction capabilityof wavelet transform, the excellent pattern recognition capability of the multi-label convolutional neural network and the applicability to the composite fault diagnosis problem are fully utilized, and single and composite fault diagnosis of the gearbox can be effectively realized.

The invention relates to a wireless sensor network fault diagnosis method based on a time weight K neighbor algorithm, comprising steps of establishing a K-neighbor algorithm training database, sampling WSN state characteristic value to form characteristic vector through timing discrete, wherein each characteristic vector represents the sampling state of the wireless sensor network, performing a pre-diagnosis on a WSN characteristic vector through the K-neighbor algorithm and starting up a time correlation mechanism, starting up a weight amendment rule if the condition is met, and outputting results. The invention can establish the characteristic value according to the system fault mechanism by targeting the wireless sensor network (WSN) system fault diagnosis problem, and can design the fault diagnosis classification rules and parameters based on the weight according to the WSN system fault time correlation, and can establish a system fault diagnosis model by combining with the K-neighbor algorithm to achieve the fact the current diagnosis result is amended according to the diagnosis history. The invention can achieve the fault self-diagnosis and self updating of the WSN, has distributed calculation characteristics and guarantees the accuracy and low power consumption.