34results about How to "Avoid diagnostic errors" patented technology

The invention provides an analog circuit fault diagnosis method based on improvement. The conventional technology is improved from two aspects: 1. a DAGSVA method is improved: an SVM with the maximum inter-class distance acts as the uppermost layer node of the DAGSVM. If the root node classification result is i-type, the SVM with the maximum inter-class distance to the i-type is selected to act as the child node of the layer, and if the root node classification result is j-type, the SVM with the maximum inter-class distance to the j-type is selected to act as the child node of the layer; if the classification result does not belong to the i-type or the j-type, the two types are eliminated, two types of SVM with the maximum inter-class distance Dij are selected among the rest classes to act as the nodes of the layer, and the two aforementioned steps are continued unit a diagnosis result is obtained so that a situation of error of the final result caused by high-layer node diagnosis error can be effectively avoided. 2. particle swarm optimization (PSO) is performed on each child SVM for parameter optimization in order to enhance diagnosis accuracy rate of each child node so that SVM diagnosis accuracy rate of each node is enhanced, and thus diagnosis accuracy rate of the whole DAGSVM is enhanced.

The invention relates to a mechanical arm controlling method and device, equipment, a storage medium and a system. The method is applied to a diagnosis and treatment system. The diagnosis and treatment system comprises medical imaging equipment, computer equipment and a telescopic mechanical arm, wherein the medical imaging equipment and the mechanical arm are separately connected with the computer equipment. The method comprises the following steps of determining a diagnosis and treatment path of a diagnosis and treatment target; according to the transforming relation between an image coordinate system of the medical image equipment and a coordinate system of the mechanical arm, transforming the diagnosis and treatment path into a target diagnosis and treatment path on the coordinate system of the mechanical arm; and according to the target diagnosis and treatment path, controlling the mechanical arm to extend into a scanning drum of the medical imaging equipment for operations. According to the mechanical arm controlling method provided by the invention, errors caused by repeated movement of the diagnosis and treatment target are avoided, and the precision rate and the efficiencyof the diagnosis and treatment operations are improved.

The invention discloses a PWM output fault diagnosis method. The method includes the steps that whether the PWM output duty ratio is 100% or not is judged; if yes, the diagnosis process with the duty ratio being 100% is executed, and a diagnosis result is output according to the state of a feedback signal side; if not, whether the PWM output duty ratio is 0% or not is judged, if yes, the diagnosis process with the duty ratio being 0% is executed, and a diagnosis result is output according to the state of the feedback signal side; if not, the conventional diagnosis process is executed, and a diagnosis result is output according to the state of the feedback signal side. Fault diagnosis can be achieved by reading the state of the feedback signal side at different duty ratios, and the real-time performance of PWM output fault diagnosis is improved. The invention further discloses a PWM output fault diagnosis system.

The invention discloses a power grid fault diagnosis method and belongs to the technical field of power grid fault diagnosis. An outage region is obtained through protection and circuit breaker information, lines in the outage region are taken as suspected fault lines, and comprehensive current of the lines is constructed to serve as sample sequences; a DTW algorithm is used, the DTW distance between the sample sequence of each suspected fault line and a reference sequence of a reference line outside the outage area is obtained, and transverse difference degrees are constructed; meanwhile, theDTW algorithm is used for solving the DTW distance between the sample sequences of the suspected fault lines before and after faults, and longitudinal difference degrees are constructed. The transverse and longitudinal difference degrees of the N suspected fault lines form a 2*N difference degree matrix; clustering is carried out on the matrix by utilizing an artificial fish swarm clustering algorithm, the matrix is divided into a fault class and a normal class, the class with a larger clustering center value is diagnosed as the fault class, and the lines in the fault class are judged to be the fault lines. By means of the method, the fault lines can be accurately diagnosed, the influence of fault positions, transition resistance, fault types and the like is avoided, and the performance is good.

The invention relates to a household appliance device diagnosis system and method, wherein product information is output according to a set signal tone by a household appliance device and the signal tone is transmitted through a connected communication net so that a remote service center can easily confirm the state of the household appliance device; and when analyzing the signal tone of the household appliance device, the diagnostic server of the service center selects a plurality of headers candidates and utilizes weighted value to detect data more effectively, thus realizing fast diagnosis, preventing data analysis errors and the diagnosis errors caused by data analysis errors. In addition, the system of the invention can provide more accurate failure diagnosis service, thus improving the degree of satisfaction and reliability of users.

The invention provides a fault diagnosis system. The fault diagnosis system includes an execution terminal, a controller, a fault diagnosis module, a first output terminal and a background server; the execution terminal is arranged in a vehicle and is connected with the controller, and monitors the operation signals of various components in the vehicle; the controller is connected with the fault diagnosis module, monitors the fault diagnosis module, and transmits monitored first monitoring signals and received operation signals to the fault diagnosis module; the fault diagnosis module monitors the controller, receives the first monitoring signals and the operation signals, and performs diagnosis; and the background server receives abnormal signals and judges the fault condition of the vehicle. Thus, the controller and the fault diagnosis module in the fault diagnosis system can monitor each other and give feedback to each other, so that errors in detection results caused by the damage of the controller or the fault diagnosis module can be avoided.

The invention provides an inspection device used for the automatic inspection of a power battery for a hybrid electric vehicle, which comprises a main controller, an automatic inspection indicating lamp, an LCD display, an input device and a load resistor. The functions of parameter acquisition and state judgment are realized via the communication between the main controller and the power battery, the automatic inspection result of the device is reflected by the automatic inspection indicating lamp, threshold parameters are variably set by the LCD display screen and the input device, and the load resistor is used for measuring the dynamic characteristics of the power battery. The device can realize the function of automatically inspecting different types of power batteries, and the inspection result is displayed by the LCD display screen. The invention also provides an inspection method, which comprises important steps inspection system initialization, power supply, important parameter acquisition via communication, high-voltage conduction, disconnection, parameter comparison and the like, and logical order. The method can complete the inspection on the basic state of the whole power battery within 1 minute.

The invention provides an external biochemical analyzer for a reaction disc signal sampling device, belonging to a medical apparatus; the invention comprises a reaction disc part arranged in a machine shell of the biochemical analyzer; the invention is characterized in that the reaction disc part comprises a bottom plate of the reaction disc(1), a reaction disc(2), a driving motor(3), a synchronous belt(4), a synchronous belt wheel(5), a shaft of the reaction disc(6), an insulation box of the reaction disc(7) and a reaction cup frame(8), wherein the reaction cup frame(8) is provided with a ring-shaped reaction cup groove(11), the outer side of which is provided with a light source entrance(12); eight optical fibers(17) matched with eight color filters have ends arranged in optical fiber mounting holes(13) and other ends penetrating the insulation box of the reaction disc(7) and fixed in eight corresponding optical fiber positioning sleeves(16) arranged on a signal plate fixing frame(15); the signal plate fixing frame(15) is fixed on the bottom plate of the reaction disc(1) and positioned on the outer side of the insulation box of the reaction disc(7). The external biochemical analyzer has the advantages of good pollution preventive effect and simple structure.

The invention relates to an emergency patient clinic health monitoring system. The system is characterized by at least comprising an information acquisition module, a grading evaluation module and anearly warning evaluation module, wherein the information acquisition module acquires at least one physiological information data of a patient in a contact manner and is associated with two-dimensionalcode information of the patient; the grading evaluation module evaluates a first danger grade of the patient under the condition that at least one kind of physiological information data are abnormalon the basis of an abnormal physiological data change curve containing abnormal data in a preset time interval and a grade list associated with the abnormal physiological data change curve; the earlywarning evaluation module selects at least one terminal equipment associated with an emergency department as an alternative early warning terminal and evaluates the early warning priority order on thebasis of the danger level and / or symptom characteristics; and early warning is carried out according to the priority sequence under the condition that the abnormal physiological data change curve and / or the abnormal frequency trigger an early warning condition.

Disclosed is a rolling bearing early fault feature extraction method. The invention provides a rolling bearing early fault feature method based on sparse optimization, and the method comprises a first step of acquiring acceleration signals of a rolling bearing as signals to be analyzed; a second step of establishing a sparse optimization function of the signals to be analyzed, and solving for period impact components in the signals to be analyzed; and a third step of conducting an envelope demodulation analysis of the period impact components to obtain the fault feature frequency. The invention makes use of the prior knowledge that the rolling bearing fault signals have sparsity, does not need the coefficient sparsity under dictionary transform based on fault signals, and avoids the problem of diagnostic errors caused by the selection of an inappropriate dictionary.

The invention discloses a remote medical diagnosis system based on a medical image, an algorithm and a block chain, and aims to improve the reliability of remote medical diagnosis. The system comprises a user terminal, an image storage server, a diagnosis server and a block chain network; the diagnosis server is used for receiving a diagnosis request sent by the user terminal, and the diagnosis request carries a transaction ID; according to the transaction ID, obtaining a unique identifier corresponding to the transaction ID from a block chain network; a medical image corresponding to the transaction ID is acquired from the image storage server according to the transaction ID; generating a unique identifier of the medical image according to the acquired medical image; the generated unique identifier is compared with a unique identifier obtained from the block chain network; and under the condition that the medical image is consistent with the disease prediction result, carrying out noise reduction processing on the medical image to obtain a medical image after noise reduction, and carrying out disease prediction on the medical image after noise reduction to obtain the disease prediction result.

The invention discloses a multidirectional suspending rack used for a display screen of a medical angiography X-ray machine. The multidirectional suspending rack comprises a suspending beam, a telescopic column, a containing box, a supporting rack and an air pump, the telescopic column is connected to the middle of the bottom face of the suspending beam through a bolt, the bottom end of the telescopic column is connected with the middle of the bottom face of the suspending beam, one end of the telescopic head of the telescopic column is connected with the middle of the top end of the containing box, an opening is formed in the front face of the containing box, and the supporting rack is fixedly connected to the middle of the bottom face of the inner side of the containing box through bolts. With the multidirectional suspending rack, the problems are solved that a support for suspending the display screen of the medical angiography X-ray machine is small in movement range, the range where the display can move becomes smaller, and the display screen of the medical angiography X-ray machine can not be stored, and occupies much space; the problems are solved that a common suspending rack used for the display screen of the medical angiography X-ray machine cannot adjust the display screen longitudinally by a large magnitude with easiness, the support, which can realize longitudinallarge-magnitude adjustment, for the display screen cannot bear too heavy display screens, and adjustment for the display screen is limited greatly.

The invention discloses a detection device for a urine flow rate meter. The detection device comprises a water inlet, a water outlet, a first pipeline and a power supply, wherein two ends of the first pipeline are connected with the water inlet and the water outlet respectively; a first pump and a first electromagnetic valve are arranged on the first pipeline; the first electromagnetic valve is electrically connected with a first time relay; the power supply is used for supplying power to the first pump to start the first pump, and used for supplying power to the first time relay to start the first electromagnetic valve; the first pipeline is communicated when the first pump and the first electromagnetic valve are started simultaneously, and a liquid flowing into from the water inlet flows out from the water outlet through the first pipeline and flows into the urine flow rate meter. By adopting the detection device disclosed by the invention, whether the urine flow rate meter is qualified or not can be accurately detected, diagnosis mistakes caused by faults of the urine flow rate meter can be avoided for doctors, and thus medical accidents can be reduced.

The invention provides a motor fault diagnosis and degradation trend prediction method and system, and the system comprises a data collection unit which is mainly used for collecting the voltage and current data of a motor, and marking the data at the same time; the server unit can be connected with a plurality of acquisition units and is mainly used for performing preprocessing, spectrum analysis, fault diagnosis, degradation trend prediction and the like on data; the database unit is used for storing typical fault samples of historical data. The system adopts a machine learning and manual intervention method to carry out monitoring and fault diagnosis on the motor. The method is not influenced by voltage grades and operation conditions, and can intelligently analyze the current state of the motor and predict the fault development trend. By adopting the motor fault diagnosis and deterioration trend prediction method and system, the severity of the motor fault can be judged, and the fault development trend can be predicted. A shutdown overhaul and maintenance plan is arranged in advance, production efficiency is improved, equipment operation and maintenance cost is reduced, and enterprise economic and safety benefits are increased.

The invention belongs to the technical field of artificial intelligence and relates to a wisdom tooth detection and evaluation system based on artificial intelligence. The system comprises the following units of: a neural network unit for detecting a tooth center point and a tooth surrounding frame; a tooth quantity detection unit used for detecting the actual quantity of the teeth, the quantity of lost teeth and the number of to-be-corrected teeth; a wisdom tooth positioning unit used for positioning wisdom teeth by utilizing a dentition symmetry axis and a tooth position relation based on the number of the to-be-corrected teeth; a growth direction detection unit used for acquiring growth directions of wisdom teeth and adjacent teeth thereof; and an influence degree evaluation unit used for evaluating the influence degree of the wisdom teeth on oral health according to the growth direction deviation and the spacing distance between the wisdom teeth and the adjacent teeth. Under the condition that teeth are missing, the wisdom teeth are quickly and accurately positioned by means of the position relation of the teeth at the two ends of the dentition and the distance from the teeth at the two ends of the dentition to the symmetry axis of the dentition, so that the influence degree of the wisdom teeth on oral health is accurately evaluated, and diagnosis errors are avoided.

The invention discloses a process monitoring and fault diagnosis method based on tree structure sparsity. Training data and test data are collected, and principal components of the training data and process monitoring statistic control limits are extracted through principal component analysis; process monitoring statistics of the test data are calculated, and a comparison is made and whether a fault occurs or not is judged; if a fault is monitored, a fault isolation model is established for processing a fault diagnosis problem, training data is converted into a tree structure, the weight of each node in the tree structure is established, and a fault diagnosis model based on tree structure sparsity is established according to the fault isolation model; and the fault diagnosis model based ontree structure sparseness is solved to obtain an optimal fault amplitude, and process variables of the fault are positioned and separated by utilizing the optimal fault amplitude. The method can be conveniently expanded to a parallel or distributed version, can meet the requirements for solving speed and precision of a large data set in the industrial process, and provides effective support for industrial production control behaviors.

The invention discloses a movable CT device for the radiology department, and relates to the field of CT equipment, in particular to the movable CT device for the radiology department; the device comprises a scanning frame and a ray scanning slit; supports are connected to the lower ends of the two sides of the scanning frame, a base is fixed to the lower ends of the supports, and a control panel is installed at the front end of the scanning frame. An anti-interference wireless transmitter is embedded in the upper end of one side of the scanning frame; and the ray scanning slit is formed in the inner side of the scanning frame. The movable CT device for the radiology department is provided with a third motor which drives a specially-shaped gear meshed with a rotating gear, so that a bed frame fixedly connected with the specially-shaped gear drives the scanning bed to stand up, a patient can walk on a pedal and stand well during examination. And along with rotation of the third motor, the scanning bed is slowly laid flat, and the patient can lie on the scanning bed for CT examination without bending down, so that convenience is provided for examination of part of patients difficult to move, and the examination comfort is improved.

The invention discloses a karyotype detecting system for automatically hiding sexuality information and a method. The method comprises the following steps of performing karyotyping of a chromosome bymeans of an intelligent system, when a sexuality chromosome has no genetic pathological characteristic, deleting the picture and the mark of the sexuality chromosome in an electronic diagnosis reportwhich is generated by the intelligent system; and if the sexuality chromosome has the genetic pathological characteristic, reserving the picture and the pathological mark of the sexuality chromosome in the electronic diagnosis report which is generated by the intelligent system and a formal report. In performing genetic disease detection on the fetus, the karyotype detecting system and the methodhave advantages of preventing an illegal behavior of performing fetus sexuality identification, preventing technology abuse, and sufficiently utilizing detecting equipment and labor of core regions for realizing field detection of the patients in remote regions.

The invention belongs to the technical field of medical diagnosis, and discloses a doctor pulmonary nodule auxiliary diagnosis system, which is provided with a main body device, a pulmonary nodule auxiliary diagnosis prompting device, an input device for inputting basic information, treatment information and a pulmonary nodule image of a patient, and a display device; the pulmonary nodule auxiliary diagnosis prompting device is arranged in the main body device and comprises an information image memory for storing basic information and doctor seeing information of a patient input through the input device and a pulmonary nodule image of the patient; an image processing module, a pulmonary nodule recognition module and a communication module are arranged in the main body device; and the image processing module comprises an image preprocessing module and an image deep processing and recognizing module. The image processing module, a pulmonary nodule recognition module and a communication module are arranged in the main body device, and the communication module is connected with a cloud server, so that big data processing, judgment and analysis can be realized, and the diagnosis accuracy and efficiency are improved.

The invention discloses a grid fault diagnosis method, which belongs to the technical field of grid fault diagnosis. The power outage area is obtained from the protection and circuit breaker information, and the lines in it are taken as suspected fault lines, and their comprehensive current is constructed as a sample sequence; the sample sequence of each suspected fault line and the reference line outside the power outage area are obtained by using the DTW algorithm. The DTW distance between the sequences is constructed as the horizontal difference degree; at the same time, the DTW distance between the sample sequences before and after the fault of each suspected fault line is obtained by using the DTW algorithm, which is constructed as the vertical difference degree. The horizontal and vertical difference degrees of N suspected faulty lines are formed into a 2×N difference degree matrix, and the artificial fish clustering algorithm is used to cluster the matrix, which is divided into fault classes and normal classes, and the one with the larger cluster center value The class is diagnosed as a fault class, and the lines in the fault class are judged as faulty lines. The invention can accurately diagnose the fault line, is not affected by fault location, transition resistance, fault type, etc., and has good performance.

The invention provides a disease determination method and device, equipment and a storage medium, and relates to the technical field of data processing, in particular to the fields of artificial intelligence, deep learning, AI medical treatment and the like. According to the specific implementation scheme, medical entity information is determined according to description information of a suspected patient; using the medical entity information to determine a sub-atlas related to the suspected patient in a disease atlas, the disease atlas being pre-constructed, and the disease atlas at least comprising a disease and a plurality of entity items corresponding to the disease; using at least one of the description information of the suspected patient, the medical entity and the sub-atlas to carry out disease determination of a specified category on the suspected patient. Through the process, the accuracy of disease determination can be improved.

The invention discloses a general practitioner intelligent image auxiliary diagnosis system which is characterized by comprising a general practitioner image camera and a computer workstation. The general practitioner image camera is used for photographing the focus position to obtain a picture; the computer workstation is in communication connection with the generalpractitioner image camera and is used for acquiring pictures and performing classification analysis and comparison according to the content of the pictures so as to make auxiliary diagnosis suggestions; an analysis database used for making auxiliary diagnosis suggestions is stored in the computer workstation, and standard comparison images are stored in the analysis database according to the patient position and disease classification; and the computer workstation compares the obtained pictures with corresponding positions and diseases in an analysis database under the operation of a doctor, so as to obtain auxiliary diagnosis suggestions. By means of the auxiliary diagnosis system, auxiliary guidance can be provided for diagnosis and treatment of primary doctors, and therefore the problem that diagnosis errors of partof diseases are caused by insufficient experience of the doctors is solved.

The invention relates to the field of disease early warning systems, in particular to a high-risk disease early warning and notification system which comprises a server, an expert terminal and a user terminal. The server comprises a database module, a data transceiving module, a data processing module, a symptom comparison module, a disease information sending module, an expert feedback information processing module and a high-risk disease early warning module; the database module is used for storing various information of high-risk diseases; the data processing module organizes disease information; the symptom comparison module is used for obtaining a specific disease type; the disease information sending module is used for sending the high-risk disease information to the expert terminal; the expert terminal uploads a feedback result; the expert feedback information processing module is used for receiving feedback of all experts; and the high-risk disease early warning module sends the first round of server diagnosis result and the second round of sorting result fed back by the expert to the user terminal. According to the invention, through double diagnosis of the server and the experts, the diagnosis correctness of high-risk diseases is ensured.

The invention provides a doubly-fed generator turn-to-turn fault diagnosis system and a doubly-fed generator turn-to-turn fault diagnosis method. The doubly-fed generator turn-to-turn fault diagnosis method comprises the following steps of: collecting generator stator three-phase current waveforms within given time particles; converting the three-phase current to a dq plane and fitting an ellipse; calculating the eccentricity of the ellipse obtained by fitting; and judging whether a turn-to-turn fault of the doubly-fed generator occurs or not according to the obtained eccentricity. According to the Doubly-fed generator turn-to-turn fault diagnosis system and the Doubly-fed generator turn-to-turn fault diagnosis method, diagnosis errors caused by differences of different motors can be effectively avoided, and the diagnosis precision is improved.