CN105510693A - Method for monitoring using state of large medical equipment based on hall current and image changing - Google Patents

Method for monitoring using state of large medical equipment based on hall current and image changing Download PDF

Info

Publication number
CN105510693A
CN105510693A CN201510829345.2A CN201510829345A CN105510693A CN 105510693 A CN105510693 A CN 105510693A CN 201510829345 A CN201510829345 A CN 201510829345A CN 105510693 A CN105510693 A CN 105510693A
Authority
CN
China
Prior art keywords
state
image
medical equipment
sample point
image change
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201510829345.2A
Other languages
Chinese (zh)
Other versions
CN105510693B (en
Inventor
王清波
虞成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou First Peoples Hospital
Original Assignee
Hangzhou First Peoples Hospital
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou First Peoples Hospital filed Critical Hangzhou First Peoples Hospital
Priority to CN201510829345.2A priority Critical patent/CN105510693B/en
Publication of CN105510693A publication Critical patent/CN105510693A/en
Application granted granted Critical
Publication of CN105510693B publication Critical patent/CN105510693B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
    • G01R19/25—Arrangements for measuring currents or voltages or for indicating presence or sign thereof using digital measurement techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R15/00—Details of measuring arrangements of the types provided for in groups G01R17/00 - G01R29/00, G01R33/00 - G01R33/26 or G01R35/00
    • G01R15/14—Adaptations providing voltage or current isolation, e.g. for high-voltage or high-current networks
    • G01R15/20—Adaptations providing voltage or current isolation, e.g. for high-voltage or high-current networks using galvano-magnetic devices, e.g. Hall-effect devices, i.e. measuring a magnetic field via the interaction between a current and a magnetic field, e.g. magneto resistive or Hall effect devices
    • G01R15/202—Adaptations providing voltage or current isolation, e.g. for high-voltage or high-current networks using galvano-magnetic devices, e.g. Hall-effect devices, i.e. measuring a magnetic field via the interaction between a current and a magnetic field, e.g. magneto resistive or Hall effect devices using Hall-effect devices

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses a method for monitoring a using state of large medical equipment based on a hall current and image changing. The method comprises: step one, a hall current sensor detects the operating current intensity of large medical equipment and a display image of the large medical equipment is also collected, the display image is converted into a gray level image, and an image changing rate is calculated; step two, a cluster analysis is carried out on the operating current intensity and the image changing rate and thus the operating current intensity and the image changing rate correspond to different using states, wherein the using states at least include a shutdown state, a standby state, and an operating state; and step three, the operating current intensity and the image changing rate of the large medical equipment are collected in real time, and a corresponding using state is obtained based on a cluster result. Therefore, a non-linear state analysis can be carried out on the using state of the large medical equipment automatically without any manual intervention and accurate using state information also can be obtained.

Description

A kind of method of monitoring Large-scale Medical Equipment using state based on Hall current and image change
Technical field
The present invention relates to monitoring of equipment technical field, be specifically related to a kind of method of monitoring Large-scale Medical Equipment using state based on Hall current and image change.
Background technology
Constantly perfect along with China's medical system structure, the large-scale valuable Medical Devices of each large and medium-sized hospital and the quantity of instrument also constantly increase, and therefore, how to improve the service efficiency of Large-scale Medical Equipment, improving the comprehensive benefit of hospital, is the topic should inquired into deeply in medical instrument management.
In the daily management of hospital, as radiation, the equipment such as ultrasonic substantially all adopt the mode of labor management, carry out equipment dailyly to enable, the statistics of the using state such as stopping, the mode subjectivity of complicate statistics is stronger, and cannot accomplish real-time monitoring.In this process, if labor management is slightly neglected, namely with the waste of equipment electric energy and the reduction of equipment use efficiency.
Inquire about through available data, the comparatively approximate article that has is called " the Medical Devices using state monitoring system based on RFID ", in June, 2015 is published in " Chinese medical equipment ", is mainly used in recording standby, the using state of Medical Devices and identifies instrument numbering with RFID.In this section of document, monitoring system mainly comprises client and server, wherein, client is made up of four parts such as current detection module, RFID identification module, central control module, wireless transport modules, the identity information of primary responsibility identification Medical Devices, monitoring Medical Devices neutral line current, and above-mentioned identity information and neutral line current data are sent to server, client Organization Chart as shown in Figure 1.
The ac current measurement circuit based on current transformer is adopted in the document, detect the current value flowing through equipment zero line, wherein ac current measurement adopts punch current transfomer, after recording electric current, classify according to such as lower threshold value, each class corresponds to standby or using state.
Standby current threshold value=preliminary survey standby current × (1+10%)
Working current threshold value=preliminary survey working current × (1-10%)
New Medical Devices are when first time drops into Clinical practice, the test pattern of client is started by operating personnel, in test mode, operating personnel successively make equipment be in holding state and duty respectively, the preliminary survey standby current of client measurements record Medical Devices and preliminary survey working current, and the number information of these two preliminary survey electric currents and equipment is together sent to server, server is according to preliminary survey current settings 2 grades of threshold values, then by single-chip microcomputer image data, wireless transport module receives neutral line current data and device RF ID number information by UART interface, server is sent to via wireless router subsequently by Wi-Fi.
The method that the document is reported has following shortcoming:
(1) adopt punch current transfomer as the circuit block of current measurement, if AC current transformer is opened a way, then high voltage can be produced, line insulation can be punctured time serious, produce the safety that electric shock threatens staff, meanwhile, due to the impact of tested current distortion, multiple harmonic, non-sinusoidal wave etc., make the accuracy of Measurement Result of Current Transformer poor.
(2) foundation of disaggregated model, needs independently test pattern, and this test pattern needs the manpower intervention of staff to operate, if the number of devices in hospital is more, will occur a large amount of duplication of labour, more difficultly applies.
(3) object-oriented is Medical Devices, but article main body is patient monitor, lung ventilator etc., this kind equipment is middle-size and small-size equipment within the hospital, equipment state is divided into standby mode and using forestland substantially, its standby mode is in equipment out of use state substantially, has larger difference with the pattern of main equipment.
Article is separately had to be published in " Chinese medicine equipment ", article is called " concentrating the central monitoring system research and development of supervision ultrasonic device open state ", this article, by carrying out informationization, centralized start detection to ultrasonic image equipment, completes the centralized management to ultrasonic device and supervision.Concrete grammar is: use Hall current sensor to gather B ultrasonic current signal, comparator circuit converts 0-1 status information to; Use MSP430F449 and serial ports to turn mixed-media network modules mixed-media, send data to acquisition terminal; Acquisition terminal data are also sent to central monitoring server after being arranged.
In the document, although object-oriented is Large-scale Medical Equipment, state only has 0-1 state, i.e. startup and shutdown state, cannot distinguish the different conditions such as standby, the use under open state.In the document, the judgement of different conditions also adopts the mode of threshold determination, and hardware circuit is set by the slide rheostat resistance of comparator circuit, namely adopts the method for experience manually to set.And in actual use, because of machine performance change, also likely occur equipment use, but the situation that electric current declines before comparing on the contrary.
For Large-scale Medical Equipment, usual using state is not two, but is divided into various states, such as, shutdown, standby, using state etc., for Large-scale Medical Equipment, because power consumption is larger, if machine was stopped using the same day, should off-mode be in, save energy consumption.Under open state, be also divided into standby non-working condition and using state, using state such as: as B ultrasonic shooting, CT exposure etc.
Large-scale Medical Equipment, under the special states such as patient information operation, and uses current conditions no significant difference under holding state, in prior art, the simple strength of current that relies on cannot accurately be distinguished.Further, in prior art, if be judged as standby to the using state of Large-scale Medical Equipment, and be in holding state for a long time, still need manually Large-scale Medical Equipment to be shut down.
Summary of the invention
The invention provides a kind of method of monitoring Large-scale Medical Equipment using state based on Hall current and image change, automatically can carry out nonlinear state analysis to the using state of Large-scale Medical Equipment, break away from manual intervention, obtain using state information accurately.
Monitor a method for Large-scale Medical Equipment using state based on Hall current and image change, comprising:
Step 1, utilizes Hall current sensor to detect the running current intensity of Large-scale Medical Equipment, and gathers the display image of Large-scale Medical Equipment simultaneously, after display image is converted into gray level image, and computed image rate of change;
Step 2, carries out cluster analysis to running current intensity and image change rate, makes running current intensity and image change rate correspond to different using states, and using state at least comprises shutdown, standby, operation;
Step 3, the running current intensity of Real-time Collection Large-scale Medical Equipment and image change rate, according to cluster result, obtain corresponding using state.
Hall current sensor utilizes electromagnetic induction principle, alternating current is measured in real time, adopt accurate constant current technology and linear temperature compensation technology, be the DC signal output of standard by its isolated variable, the present invention utilizes Hall current sensor to measure the running current of Large-scale Medical Equipment, and security is higher, and the linearity is good, and improve without the need to carrying out destructiveness to medical equipment on hardware, it is convenient to implement.
Utilize image change etc. in the present invention and use relevant factor, combining the electric current of operation intensity simultaneously, medical equipment is carried out to the analysis of running status, the state that shutdown, standby, operation etc. are different can be distinguished, break away from manual intervention, realize automatic classification.
As preferably, in step 1, the method for computed image rate of change is as follows:
Each pixel gray-scale value of 1-a, current time gray level image is designated as y mn, the total quantity of pixel is S, and the pixel gray-scale value of the average gray image that current time is reviewed forward in predetermined amount of time is designated as y avg mn;
1-b, utilize formula z mn=| y mn-y avg mn| the pixel gray-scale value z of calculated difference gray level image mn;
In 1-c, calculated difference gray level image, pixel gray-scale value exceedes threshold value y cpixel amount R t;
1-d, utilize x (t)=R t/ S computed image rate of change x (t).
Owing to considering the data of running current intensity and image change rate two dimensions simultaneously, therefore, under different using states, data present aspherical distribution, and traditional cluster mode can not use, and need the clustering algorithm considering the distribution of use aspherical, the present invention adopts density peaks quick clustering algorithm to obtain classification center, for real-time grading Sample Storehouse, particularly, in step 2, the step of cluster analysis is as follows:
2-a, following formula is utilized to be normalized image change rate and current signal:
x n o r m ( t ) = x ( t ) x m a x ( t ) , i n o r m ( t ) = i ( t ) i m a x ( t )
In formula, x (t) and i (t) is respectively image change rate and running current intensity;
X norm(t) and i normt () is respectively the image change rate after normalization and running current intensity;
X max(t) and i maxt () is respectively the maximal value of image change rate and running current intensity;
2-b, in two-dimensional space, respectively using the image change rate after normalization and running current intensity as the sample coordinate point in each moment, calculate the local density ρ of each sample point i, the distance δ to put to high local density i, and high local density's point indicate k i;
2-c, utilize J i=δ i× ρ icalculate eigenwert J i, and the eigenwert of all sample points is sorted, get maximum some sample points as classification center, the using state of the corresponding a kind of Large-scale Medical Equipment of each classification center;
2-d, residue sample point determine affiliated medical equipment using state successively according to local density's order from high to low.
The usability of Large-scale Medical Equipment changed with service time, in order to accurately know the using state of medical equipment, need the result adjusting cluster analysis, to tell the using state of medical equipment more exactly, the present invention uses classification center update algorithm, preferably, in step 2, after the predetermined amount of time of interval, upgrade cluster result, update method is as follows:
Assuming that the replaced sample point of current need is X m, be X for substituting the data point of this sample point s;
Calculate X mand the distance d between other sample points mj, the set of j ∈ sample point, record d mj<d csample point set be Ψ, d cfor blocking distance, d mjfor sample point m is to the Euclidean distance of sample point j;
Calculate X sand the distance d between other sample points sj, the set of j ∈ sample point, record d sj<d csample point set be Π, d sjfor sample point s is to the Euclidean distance of sample point j;
Obtaining the sample set that other sample points Zhong Gao local density's point is denoted as m is Ρ;
Replace sample point X mfor X s, and do following renewal:
Upgrade ρ afor ρ a': ρ a'=ρ a-1, a ∈ Ψ;
Upgrade ρ bfor ρ b': ρ b'=ρ b+ 1, b ∈ Π;
Upgrade ρ mfor ρ ' m: wherein, if d mj-d c<0, then otherwise
Upgrade δ mfor δ m': &delta; m &prime; = min &rho; j > &rho; m d m j ;
Upgrade δ vfor δ v': &delta; v &prime; = min &rho; j , &rho; v d v j , v &Element; P .
As preferably, also comprise step 4, the using state of gained is carried out remote data transmission.
By the using state remote data transmission of gained to server, be convenient to the real-time monitoring that each Large-scale Medical Equipment is concentrated.
As preferably, also comprise step 5, if using state is judged to be standby, and standby time exceedes threshold value, then automatically shut down Medical Devices.Described threshold value sets as required, turns off Medical Devices by arranging power-off control module.
Beneficial effect of the present invention is as follows:
(1) detect real-time operating current intensity by Hall current sensor, reduce the difficulty of scrap build, Hall element current detecting can realize isolation detection, does not affect existing equipment performance.
(2) use density peaks quick clustering algorithm, compare traditional clustering method, can process aspheric classification form, classification center update algorithm can avoid the cluster completely again of sample, uses legacy data, realizes Sample Storehouse fast and upgrades.
(3) utilize network communications technology using state to be transferred to central monitoring unit and be used for monitoring and record in real time.
(4) network communication may be used for the remote monitoring that Large-scale Medical Equipment uses.Power-off controls to automatically shut down hospital equipment, places carelessness and uses, economize energy.
Accompanying drawing explanation
Fig. 1 is the client framework map in " the Medical Devices using state monitoring system based on RFID ", and in June, 2015 is published in " Chinese medical equipment ";
Fig. 2 is the process flow diagram of method provided by the invention;
Fig. 3 is the system schematic implementing the inventive method;
Fig. 4 is power detecting module diagram in the system of enforcement the inventive method;
Fig. 5 is the schematic diagram of image detection module in the system of enforcement the inventive method;
Fig. 6 is the schematic diagram of three condition detection module in real time in the system of enforcement the inventive method;
Fig. 7 is the schematic diagram of communication transmission module in the system of enforcement the inventive method;
Fig. 8 is the schematic diagram of control module in the system of enforcement the inventive method.
Embodiment
Below in conjunction with accompanying drawing, the method that the present invention is based on Hall current and image change monitoring Large-scale Medical Equipment using state is described in detail.
As shown in Figure 3, the supervisory system structure realizing method provided by the invention comprises: current detection module, Image Change Detection module, in real time three condition detection module, communication transmission module and power-off control module; Wherein current detection module, Image Change Detection module and real-time three condition detection module communicate to connect, and real-time three condition detection module is connected with communication transmission module, power-off control module is connected with communication transmission module.
The magnetic field that alternating current produces is converted to linear DC voltage by Hall effect by current detection module, and is converted to accessible numerical data; Image Change Detection module obtains the image data of Medical Devices by wired connection, is converted to gray level image, by image change rate detection algorithm, and real-time image acquisition rate of change; Real-time three condition detection module respectively with current detection module wired connection, with Image Change Detection module wired connection; Communication transmission module is wiredly connected to by serial ports.
Obtain accessible numerical data from current detection module, be converted to representative shutdown, standby, run 3 classification status informations, be provided in communication transmission module; Communication transmission module, by receiving classification status information, utilizing serial ports to turn mixed-media network modules mixed-media and being sent to computer and receiving, the teledata transmitting element simultaneously on computer sends data to teledata receiving element, completes remote data monitoring.
As shown in Figure 4, current detection module comprises power supply unit, Hall current sensor, signal modulation circuit and analog/digital conversion circuit.Power supply unit comprises Switching Power Supply, analog voltage circuit and reference voltage circuit.Wherein Switching Power Supply adopts great extra large Switching Power Supply JMD30-1209,12V direct current supply and 9V direct current supply are provided, analog voltage circuit connects its 9V and exports, 7805 chip voltage are used to export to 5V, reference voltage circuit adopts AD780, AD780 is a superhigh precision bandgap voltage reference, provides 2.5V to export, and inputs and is provided by analog voltage 5V output.12V direct current supply connects Hall current sensor driving voltage end, and analog voltage 5V exports connection signal modulation circuit and analog/digital conversion circuit, and wherein 2.5V reference voltage exports and inputs as analog/digital conversion circuit reference voltage.
Hall current sensor adopts the strange A-CT2010LT Hall current sensor suddenly in Nanjing.Signal modulation circuit adopts common integrated transporting discharging follow circuit, and chip adopts rail-to-rail amplifier OPA343.Analog/digital conversion circuit adopts AD7705 preferred circuit, and reference voltage is provided by AD780, and data transmission is connected with real-time three condition detection module.
As shown in Figure 5, Image Change Detection module comprises image acquisition unit, image conversion unit, image change rate computing unit.Image acquisition unit and image conversion unit wired connection, image conversion unit and image change rate computing unit can be positioned on one piece of microprocessor, and internal processes connects.Image acquisition unit is responsible for image and is converted to unified output, and selection of technical scheme is that composite video BNC exports, and conventional main equipment output format comprises DVI, VGA substantially, composite video (BNC) exports.Export if interface is DVI, DVI can be used to turn HDMI wiring and connect HDMI modular converter, HDMI modular converter can select PlayvisionLC101HDMI-BNC converter; Export if interface is VGA, green VGA can be used to turn HDMI converter, be converted to HDMI and export, recycling PlayvisionLC101HDMI-BNC converter is converted to SD video, carries out aftertreatment; BNC exports because output frequency is higher, first utilizes bright strong BNC to turn HDMI converter and is converted to high definition HDMI signal, and recycling PlayvisionLC101HDMI-BNC converter is converted to SD video, carries out aftertreatment.Adopt the FI1206VCABoard development board of sky falcon image to be responsible for carrying image converting unit, image change rate computing unit relative program, adopt TVP5151 digit chip and TMS320DM6437 chip.
DM6437 is configured TVP5146 chip by I2C bus, such as input clock frequency, video formats and video input form etc.Under control of the synchronization signal, the view data will gathered by 8 position datawires, with the format transmission of YCbCr video data stream to VPFE for TVP5151 chip.
As shown in Figure 6, real-time three condition detection module comprises state classification unit, the real-time training unit of sorter, cluster data storage unit.State classification unit uses dsp chip TMS320F2812, the SPI interface of TMS320F2812 and AD7705 wired connection in current detection module analog/digital conversion circuit, acquisition 16Bit data.The real-time training unit of sorter also adopts TMS320F2812, with state classification unit chip by serial ports wired connection.Storage unit is AT24C256 storer, and AT24C256 stores training sample point, storaging current data, image change data, sample point local density, distance, the high local density point sign put to high local density.
As shown in Figure 7, communication transmission module comprises microprocessor, Date Conversion Unit, teledata transmitting element and teledata receiving element.Microprocessor adopts STC12C5A60S2 chip to be the circuit of core, and serial ports 1 receives the data mode that real-time three condition detection module comes, and serial ports 2 is connected with Date Conversion Unit is wired, is responsible for data and carries out transmitting and receiving to medical equipment network.Microprocessor I/O port and power-off modular carry out wired connection, transfer equipment cut-off signals simultaneously, are 0-1 data.Date Conversion Unit can adopt serial ports to turn mixed-media network modules mixed-media, uses the USR-TCP232-2 module that can purchase.Software can adopt VB6.0 to carry out program design, adopts Winsock control to programme, uses Transmission Control Protocol, need to connect before communication.Server unit arranges oracle listener and is responsible for data decryptor, and carries out monitor data display.
As shown in Figure 8, power-off control module comprises low-voltage control high voltage unit and solid-state relay.Low-voltage controls high voltage unit and uses the T73SRD-5VDC-SL-C relay that control voltage is 5V, and input end serial connection triode, triode is input as the equipment cut-off signals of communication transmission module.Export termination 1 end to be connected with 12V Switching Power Supply, the other end and solid-state relay wired connection.Low-voltage controls high voltage unit and is used for circuit isolation.Solid-state relay can adopt your model of MAG to be the three-phase solid relay of MGR-30323840Z, control voltage is the output terminal wired connection that low-voltage controls high voltage unit, solid-state relay input end access power supply interface, output terminal connects power supply lead-out terminal, can mate be connected with device line.
As shown in Figure 2, a kind of method of monitoring Large-scale Medical Equipment using state based on Hall current and image change, comprising:
Step 1, utilizes Hall current sensor to detect the running current intensity of Large-scale Medical Equipment, and gathers the display image of Large-scale Medical Equipment simultaneously, after display image is converted into gray level image, and computed image rate of change.
Obtain display image with the form of YCbCr video data stream, and utilize following formula that Y, Cr, Cb component is converted to RGB image:
R＝1.164*(Y-16)+1.596*(Cr-128)；
G＝1.164*(Y-16)-0.392*(Cb-128)-0.813*(Cr-128)；
B＝1.164*(Y-16)+2.017*(Cb-128)。
Utilize following publicity that RGB component is converted to gray level image:
Gray＝(R*299+G*587+B*114+500)/1000。
The method of computed image rate of change is as follows:
Each pixel gray-scale value of 1-a, current time gray level image is designated as y mn, the total quantity of pixel is S, and the pixel gray-scale value that current time reviews forward the average gray image of (predetermined amount of time sets as required) in predetermined amount of time is designated as y avg mn;
1-b, utilize formula z mn=| y mn-y avg mn| the pixel gray-scale value z of calculated difference gray level image mn;
In 1-c, calculated difference gray level image, pixel gray-scale value exceedes threshold value y cpixel amount R t;
1-d, utilize x (t)=R t/ S computed image rate of change x (t).
Step 2, carries out cluster analysis to running current intensity and image change rate, makes running current intensity and image change rate correspond to different using states, and using state at least comprises shutdown, standby, operation.
If storer head byte is 0, then show to there is no cluster result, carry out clustering learning, the step of cluster analysis is as follows:
2-a, following formula is utilized to be normalized image change rate and current signal:
x n o r m ( t ) = x ( t ) x m a x ( t ) , i n o r m ( t ) = i ( t ) i m a x ( t )
In formula, x (t) and i (t) is respectively image change rate and running current intensity;
X norm(t) and i normt () is respectively the image change rate after normalization and running current intensity;
X max(t) and i maxt () is respectively the maximal value of image change rate and running current intensity;
2-b, in two-dimensional space, respectively using the image change rate after normalization and running current intensity as the sample coordinate point in each moment, calculate the local density ρ of each sample point i, the distance δ to put to high local density i, and high local density's point indicate k i.
Following formula is utilized to calculate the local density ρ of each sample point i i:
If d ij-d c<0, then otherwise
D ijfor the Euclidean distance between other sample points j and sample point i; d cfor blocking distance, the Euclidean distance between other sample points j and sample point i is less than this when blocking distance, and sample point i local density adds 1, blocks 1% of the desirable normalization data maximal value of distance acquiescence, can modify according to actual needs.
Following formula is utilized to calculate the distance δ of sample point i to high local density's point i:
&delta; i = min &rho; j > &rho; i d i j
Wherein d ijfor the Euclidean distance between sample point j and sample point i;
High local density's point indicates k imeet:
d ki＝δ i
D kifor the Euclidean distance between sample point k and sample point i;
Sample point is to the distance beta of Ci Gao local density's point i:
&beta; i = min &rho; j > &rho; i , k &NotEqual; j d i j
2-c, utilize J i=δ i× ρ icalculate eigenwert J i, and the eigenwert of all sample points is sorted, get maximum some sample points as classification center, the using state of the corresponding a kind of Large-scale Medical Equipment of each classification center.
In present embodiment, using state is divided into shutdown, standby, operation three kinds, often kind of correspondence classification center.
2-d, residue sample point determine affiliated medical equipment using state successively according to local density's order from high to low.
After determining classification center, classification center is numbered by with center zero distance size, is respectively 0,1,2, represents shutdown, standby, operation three states.Other sample points determine generic, the classification of classification corresponding to classification center nearest in neighborhood of each non-categorical central sample point successively according to local density's order from high to low.Storer head byte status is replaced by data storage area first address.
If storer head byte is not 0, then shows existing cluster result, do not need clustering learning, enter real-time grading pattern.During start, if after the real-time training unit of sorter enters real-time grading pattern, state classification unit receives the current data of AD7705, and image change rate data, and contrasted with Sample Storehouse by the real-time training unit of sorter, according to the principle that Euclidean distance is nearest, determine the most similar training sample, determine class categories.After determining class categories, serial data is sent to communication transmission module.
To the data of real-time grading and classification results stored in buffer memory, every 1 hour, the data under current class are averaged, and the storage data under this classification are upgraded, pointer ring shift.Distance, the high local density's point beacon information of upgrade corresponding sample point local density, putting to high local density simultaneously.
After the predetermined amount of time of interval, upgrade cluster result, update method is as follows:
Assuming that the replaced sample point of current need is X m, be X for substituting the data point of this sample point s;
Calculate X mand the distance d between other sample points mj, the set of j ∈ sample point, record d mj<d csample point set be Ψ, d cfor blocking distance, d mjfor sample point m is to the Euclidean distance of sample point j;
Calculate X sand the distance d between other sample points sj, the set of j ∈ sample point, record d sj<d csample point set be Π, d sjfor sample point s is to the Euclidean distance of sample point j;
Obtaining the sample set that other sample points Zhong Gao local density's point is denoted as m is Ρ;
Replace sample point X mfor X s, and do following renewal:
Upgrade ρ afor ρ a': ρ a'=ρ a-1, a ∈ Ψ;
Upgrade ρ bfor ρ b': ρ b'=ρ b+ 1, b ∈ Π;
Upgrade ρ mfor ρ ' m: wherein, if d mj-d c<0, then otherwise
Upgrade δ mfor δ m': &delta; m &prime; = min &rho; j > &rho; m d m j ;
Upgrade δ vfor δ v': &delta; v &prime; = min &rho; j > &rho; v d v j , v &Element; P .
Step 3, the running current intensity of Real-time Collection Large-scale Medical Equipment and image change rate, according to cluster result, obtain corresponding using state.
Step 4, carries out remote data transmission by the using state of gained.
Draw together step 5, if using state is judged to be standby, and standby time exceedes threshold value, then automatically shut down Medical Devices.

Claims (6)

1. monitor a method for Large-scale Medical Equipment using state based on Hall current and image change, it is characterized in that, comprising:
Step 1, utilizes Hall current sensor to detect the running current intensity of Large-scale Medical Equipment, and gathers the display image of Large-scale Medical Equipment simultaneously, after display image is converted into gray level image, and computed image rate of change;
Step 2, carries out cluster analysis to running current intensity and image change rate, makes running current intensity and image change rate correspond to different using states, and using state at least comprises shutdown, standby, operation;
Step 3, the running current intensity of Real-time Collection Large-scale Medical Equipment and image change rate, according to cluster result, obtain corresponding using state.
2. monitor the method for Large-scale Medical Equipment using state as claimed in claim 1 based on Hall current and image change, it is characterized in that, in step 1, the method for computed image rate of change is as follows:
Each pixel gray-scale value of 1-a, current time gray level image is designated as y mn, the total quantity of pixel is S, and the pixel gray-scale value of the average gray image that current time is reviewed forward in predetermined amount of time is designated as y avg mn;
1-b, utilize formula z mn=| y mn-y avg mn| the pixel gray-scale value z of calculated difference gray level image mn;
In 1-c, calculated difference gray level image, pixel gray-scale value exceedes threshold value y cpixel amount R t;
1-d, utilize x (t)=R t/ S computed image rate of change x (t).
3. monitor the method for Large-scale Medical Equipment using state as claimed in claim 2 based on Hall current and image change, it is characterized in that, in step 2, the step of cluster analysis is as follows:
2-a, following formula is utilized to be normalized image change rate and current signal:
x n o r m ( t ) = x ( t ) x m a x ( t ) , i n o r m ( t ) = i ( t ) i m a x ( t )
In formula, x (t) and i (t) is respectively image change rate and running current intensity;
X norm(t) and i normt () is respectively the image change rate after normalization and running current intensity;
X max(t) and i maxt () is respectively the maximal value of image change rate and running current intensity;
2-b, in two-dimensional space, respectively using the image change rate after normalization and running current intensity as the sample coordinate point in each moment, calculate the local density ρ of each sample point i, the distance δ to put to high local density i, and high local density's point indicate k i;
2-c, utilize J i=δ i× ρ icalculate eigenwert J i, and the eigenwert of all sample points is sorted, get maximum some sample points as classification center, the using state of the corresponding a kind of Large-scale Medical Equipment of each classification center;
2-d, residue sample point determine affiliated medical equipment using state successively according to local density's order from high to low.
4. monitor the method for Large-scale Medical Equipment using state as claimed in claim 3 based on Hall current and image change, it is characterized in that, in step 2, after the predetermined amount of time of interval, upgrade cluster result, update method is as follows:
Assuming that the replaced sample point of current need is X m, be X for substituting the data point of this sample point s;
Calculate X mand the distance d between other sample points mj, the set of j ∈ sample point, record d mj<d csample point set be Ψ, d cfor blocking distance, d mjfor sample point m is to the Euclidean distance of sample point j;
Calculate X sand the distance d between other sample points sj, the set of j ∈ sample point, record d sj<d csample point set be Π, d sjfor sample point s is to the Euclidean distance of sample point j;
Obtaining the sample set that other sample points Zhong Gao local density's point is denoted as m is Ρ;
Replace sample point X mfor X s, and do following renewal:
Upgrade ρ afor ρ a': ρ a'=ρ a-1, a ∈ Ψ;
Upgrade ρ bfor ρ b': ρ b'=ρ b+ 1, b ∈ Π;
Upgrade ρ mfor ρ ' m: wherein, if d mj-d c<0, then otherwise
Upgrade δ mfor δ m': &delta; m &prime; = min &rho; j > &rho; m d m j ;
Upgrade δ vfor δ v': &delta; v &prime; = m i n &rho; j > &rho; v d v j , v &Element; P .
5. monitor the method for Large-scale Medical Equipment using state as claimed in claim 4 based on Hall current and image change, it is characterized in that, also comprise step 4, the using state of gained is carried out remote data transmission.
6. monitor the method for Large-scale Medical Equipment using state as claimed in claim 5 based on Hall current and image change, it is characterized in that, also comprise step 5, if using state is judged to be standby, and standby time exceedes threshold value, then automatically shut down Medical Devices.
CN201510829345.2A 2015-11-24 2015-11-24 A kind of method based on Hall current and image change monitoring Large-scale Medical Equipment use state Active CN105510693B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510829345.2A CN105510693B (en) 2015-11-24 2015-11-24 A kind of method based on Hall current and image change monitoring Large-scale Medical Equipment use state

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510829345.2A CN105510693B (en) 2015-11-24 2015-11-24 A kind of method based on Hall current and image change monitoring Large-scale Medical Equipment use state

Publications (2)

Publication Number Publication Date
CN105510693A true CN105510693A (en) 2016-04-20
CN105510693B CN105510693B (en) 2018-05-25

Family

ID=55718814

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510829345.2A Active CN105510693B (en) 2015-11-24 2015-11-24 A kind of method based on Hall current and image change monitoring Large-scale Medical Equipment use state

Country Status (1)

Country Link
CN (1) CN105510693B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106777984A (en) * 2016-12-19 2017-05-31 福州大学 A kind of method that photovoltaic array Working state analysis and fault diagnosis are realized based on density clustering algorithm
CN108693804A (en) * 2018-05-11 2018-10-23 广东冉盛科学仪器有限公司 A kind of contactless monitoring device and processing method
CN111257805A (en) * 2019-11-29 2020-06-09 广东中科慈航信息科技有限公司 Method and device for monitoring running state of equipment based on Hall sensor
CN111256757A (en) * 2020-02-25 2020-06-09 深圳哈维生物医疗科技有限公司 Medical equipment monitoring system and method based on cloud computing
CN112307671A (en) * 2020-10-27 2021-02-02 杭州电子科技大学 Method for self-adapting to different large-scale equipment instrument state threshold values
CN114061659A (en) * 2021-11-15 2022-02-18 江苏中天互联科技有限公司 Device monitoring method, device, electronic device, storage medium, and program product

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005003541A (en) * 2003-06-12 2005-01-06 Auto Network Gijutsu Kenkyusho:Kk Sensor circuit, magnetic sensor circuit, current sensor circuit, and method for detecting level of magnetism or current
US20090315566A1 (en) * 2006-07-10 2009-12-24 Soren Thim Aps AC Current Sensor for Measuring Electric AC Current in a Conductor and an Indicator System Comprising Such a Sensor
CN101893655A (en) * 2009-05-21 2010-11-24 徐启峰 Digital optical current sensor
CN102565524A (en) * 2012-03-15 2012-07-11 江苏省电力公司常州供电公司 Real-time monitoring method for short-circuit current of near zone of transformer
KR20130088284A (en) * 2012-01-31 2013-08-08 에스케이이노베이션 주식회사 Power relay assembly

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005003541A (en) * 2003-06-12 2005-01-06 Auto Network Gijutsu Kenkyusho:Kk Sensor circuit, magnetic sensor circuit, current sensor circuit, and method for detecting level of magnetism or current
US20090315566A1 (en) * 2006-07-10 2009-12-24 Soren Thim Aps AC Current Sensor for Measuring Electric AC Current in a Conductor and an Indicator System Comprising Such a Sensor
CN101893655A (en) * 2009-05-21 2010-11-24 徐启峰 Digital optical current sensor
KR20130088284A (en) * 2012-01-31 2013-08-08 에스케이이노베이션 주식회사 Power relay assembly
CN102565524A (en) * 2012-03-15 2012-07-11 江苏省电力公司常州供电公司 Real-time monitoring method for short-circuit current of near zone of transformer

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106777984A (en) * 2016-12-19 2017-05-31 福州大学 A kind of method that photovoltaic array Working state analysis and fault diagnosis are realized based on density clustering algorithm
CN106777984B (en) * 2016-12-19 2019-02-22 福州大学 A method of photovoltaic array Working state analysis and fault diagnosis are realized based on density clustering algorithm
CN108693804A (en) * 2018-05-11 2018-10-23 广东冉盛科学仪器有限公司 A kind of contactless monitoring device and processing method
CN111257805A (en) * 2019-11-29 2020-06-09 广东中科慈航信息科技有限公司 Method and device for monitoring running state of equipment based on Hall sensor
CN111257805B (en) * 2019-11-29 2022-09-06 广东中科慈航信息科技有限公司 Method and device for monitoring running state of equipment based on Hall sensor
CN111256757A (en) * 2020-02-25 2020-06-09 深圳哈维生物医疗科技有限公司 Medical equipment monitoring system and method based on cloud computing
CN112307671A (en) * 2020-10-27 2021-02-02 杭州电子科技大学 Method for self-adapting to different large-scale equipment instrument state threshold values
CN114061659A (en) * 2021-11-15 2022-02-18 江苏中天互联科技有限公司 Device monitoring method, device, electronic device, storage medium, and program product

Also Published As

Publication number Publication date
CN105510693B (en) 2018-05-25

Similar Documents

Publication Publication Date Title
CN105510693A (en) Method for monitoring using state of large medical equipment based on hall current and image changing
CN104181430A (en) Off-board charger detection device and method
CN108508396A (en) Multiple-in-one collecting device detecting system and method
CN107464146A (en) Resident&#39;s class client&#39;s electricity charge accounting method and device
CN102507995B (en) Online electric quantity compensating device
CN108732524A (en) A kind of the automation Calibration Circuit and system of forming and capacity dividing test power supply
CN205940863U (en) Pointer instrument of transformer substation reading automatic identification equipment
CN205563677U (en) Cloud intelligence energy management system
CN104931907A (en) Digital display electrical measurement instrument quality group-detection system based on robot visual sense
CN201369859Y (en) Street lamp-dimming energy-saving control system
CN206331009U (en) A kind of electric power metering device with long-distance positioning function
CN209013419U (en) Portable air-conditioning system energy efficiency monitor
CN205592228U (en) Portable multi -functional hydraulic control valve failure diagnosis test instrument of intelligence
CN207909325U (en) A kind of power grid taiwan area identifying system
CN204965088U (en) Remote monitoring device for transformer
CN206557348U (en) A kind of simple breaker test fixture
CN105137254A (en) Submersible transformer automatic detection system based on PLC and embedded system
CN109613354A (en) A kind of power quality wireless monitor system and its monitoring method
CN205539139U (en) Electric energy quality measuring device
CN205139329U (en) Module lithium cell testing arrangement
CN204904085U (en) Current -voltage conversion module tester
CN108196496A (en) Infrared measurement of temperature remote management and control system
CN107422204A (en) A kind of electric power network transmits power quality detection system
CN204013555U (en) A kind of interchangeability testing apparatus of power information acquisition terminal telecommunication unit
CN208477055U (en) A kind of high-low pressure metering cabinet wiring testing device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant