CN107679624A - Lung ventilator pressure stability method based on BP algorithm - Google Patents
Lung ventilator pressure stability method based on BP algorithm Download PDFInfo
- Publication number
- CN107679624A CN107679624A CN201710994923.7A CN201710994923A CN107679624A CN 107679624 A CN107679624 A CN 107679624A CN 201710994923 A CN201710994923 A CN 201710994923A CN 107679624 A CN107679624 A CN 107679624A
- Authority
- CN
- China
- Prior art keywords
- pressure
- parameter
- sample
- treatment
- value
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M16/00—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes
Abstract
The present invention relates to a kind of lung ventilator leakage pressure antihunt means based on back-propagation algorithm, comprise the following steps:First sample is set, then judges sample size;If sample size is less than, it is further added by a new samples, each sample parameter of new samples is read, each sample parameter under the state is obtained into sample using back-propagation algorithm calculates treatment pressure value, and whether the sample mean square deviation that judgement sample treatment pressure sample calculates treatment pressure is less than critical value;If it is less than critical value, calculate the weights of each parameter and be stored in storage region, read the actual parameter value under therapeutic state, call the weights of each parameter in storage region, the calculating treatment pressure under therapeutic state is calculated again, and pressure is treated using the mask end and treated to sufferer;If mean square deviation is more than critical value, sample size is rejudged, into next circulation.The present invention can realize quick, the accurate compensation of air leakage, the effect for the treatment of be effectively ensured and comfort level that patient uses.
Description
Technical field
The invention belongs to lung ventilator field, is carried out in particular to when gas leakage occurring during a kind of Use of respirator
Pressure is followed the trail of and stable method, especially a kind of lung ventilator leakage pressure antihunt means based on back-propagation algorithm.
Background technology
At present, sleep-respiratory machine is the maximally effective means for treating sleep apnea syndrome, and it uses simple, treatment
Positive effect, main frame is by a breathing pipeline through oral nose mask, the treatment pressure required to patient's conveying.Obviously, it is stable
Stress control promptly and accurately, it is being effectively ensured for sleep-respiratory machine curative effect.
However, patient is in use, different degrees of gas leakage may occur for the position such as mask or pipeline, if do not had
There is timely detection and accurately judge and make corresponding control measure, pressure can decline, and cause therapeutic effect to fail.
In consideration of it, propose a kind of lung ventilator pressure stability method based on the BP algorithm problem of the invention to be studied.
The content of the invention
In view of the above-mentioned problems, the present invention provides a kind of lung ventilator leakage pressure antihunt means based on back-propagation algorithm,
Its purpose is to solve in the prior art, when different degrees of gas leakage occurs for the position such as mask or pipeline, lung ventilator reacts not
Come over, the problem of so as to cause therapeutic effect to fail.
To achieve these goals, the present invention uses following technical scheme:A kind of lung ventilator pressure based on BP algorithm is steady
Determine method, the pressure stability method includes the training for treatment stage, and the training for treatment stage comprises the following steps:
S1.1:First sample is set, the sample includes pressure parameter P in the same state, flow parameter F, air leakage ginseng
Number S, control pressure parameter P1, loine pressure loss parameter P2 and mask air leakage amount parameter X, into S1.2;
S1.2:Judge whether sample size is more than numerical value of N;If the sample size is less than numerical value of N, S1.3 is gone to;If the sample
This quantity is more than numerical value of N, then goes to S1.5;
S1.3:Increase a new samples, the increased new samples include pressure parameter P in the same state, flow parameter F,
Air leakage parameter S, control pressure parameter P1, loine pressure loss parameter P2 and mask air leakage amount parameter X;Read under the state
Each sample parameter of new samples, each sample parameter under the state is used sample calculating treatment pressure is obtained in back-propagation algorithm
Force value Ps, into S1.4;
S1.4:Judge that the sample actual therapeutic pressure value P m- samples under the state calculate treatment pressure value P s sample mean square deviation
Whether critical value T is less than;If the sample mean square deviation is less than critical value T, S1.5 is transferred to;If the mean square deviation is more than critical value
T, then return to S1.2;
S1.5:The weights of each parameter are calculated, the weights are stored in storage region, and enter S1.6;
S1.6:The actual parameter value corresponding with the sample under therapeutic state is read, calls each parameter in storage region
Weights, with actual parameter value be multiplied by weights again using back-propagation algorithm calculate the training for treatment stage calculating treat pressure
Value Ps ', and enter S1.7;
S1.7:Mask end actual therapeutic pressure now corresponding to mask is reasonable, is controlled using mask end treatment pressure to sufferer
Treat;
Wherein, the pressure parameter P is measured by pressure sensor, and the flow parameter F is measured by flow sensor, institute
It is the factory settings formula for producing the mask to state actual therapeutic pressure Pm, brings the pressure parameter P measured into and measures
Flow parameter F can be calculated.
Relevant content in above-mentioned technical proposal is explained as follows:
1st, the pressure stability method also includes dynamic adjustment treatment stage, and the dynamic adjustment treatment stage includes following step
Suddenly:
S3.1:A COEFFICIENT K is set, and is stored in the storage region, into S3.2;
S3.2:Read the COEFFICIENT K, read actual pressure P values and actual flow F values that the pressure sensor measures, enter
S3.3;
S3.3:Actual control pressure value parameter P1 now is calculated by the COEFFICIENT K, actual pressure P and actual flow F,
Into S3.4;
S3.4:By the pressure parameter P under the state, flow parameter F, air leakage parameter S, the control pressure parameter P1, pipeline
Pressure loss parameter P2 and mask air leakage amount parameter X brings the calculating treatment pressure that back-propagation algorithm is adjusted treatment stage into
Force value Ps ", into S3.5;
S3.5:Judge the calculating treatment pressure Ps " of the actual therapeutic pressure Pm- adjustment treatment stages of adjustment treatment stage treatment
Whether mean square deviation is less than critical value T;If the treatment mean square deviation is less than critical value T, given using actual therapeutic pressure Pm
Sufferer;If the treatment mean square deviation is more than critical value T, S3.3 is returned to.
As the further improvement of such scheme, also include a determination step before using dynamic adjustment treatment stage,
The determination step is located between the S1.6 and S1.7 in the training for treatment stage;
The determination step includes S2.1:Judge the calculating in the actual therapeutic pressure Pm '-training for treatment stage in training for treatment stage
Whether treatment pressure Ps ' treatment mean square deviation is less than critical value T;
S2.2:If the treatment mean square deviation is less than critical value T, S1.7 is gone to;If the treatment mean square deviation is more than critical value T,
The dynamic adjustment treatment stage is then carried out, goes to the S3.1.
As the further improvement of such scheme, the numerical value of N is more than or equal to 6000.
As the further improvement of such scheme, the numerical value of N is equal to 8000.
As the further improvement of such scheme, the pressure parameter P refers to the lung ventilator layer that pressure sensor measures
Pressure value at flow tube;The flow parameter F refers to that flow sensor measures flow value, because mask is certain, mask
Pipeline be it is certain, and pressure value, it is known that flow value, it is known that can then calculate the air leakage parameter S values under same state, control
Pressure P1 values, loine pressure loss P2 values and mask air leakage amount X values.
As the further improvement of such scheme, the weights of each parameter refer to that pressure parameter P obtains weights Wp, flow
Parameter F weights Wf, air leakage parameter S weights Ws, control pressure parameter P1 weights Wp1, loine pressure loss parameter P2
Weights Wp2 and mask air leakage amount parameter X weights Wx.
The principle of the invention, design and effect are as follows:
A kind of lung ventilator leakage pressure antihunt means based on back-propagation algorithm provided by the invention, this method include two portions
Point:Part I is before lung ventilator dispatches from the factory, and first passes through Back Propagation Algorithm batch and learns, allows lung ventilator self study in different leakages
Treatment pressure output under tolerance, then again preserves data, when lung ventilator really starts treatment, is met by contrasting calling
It is required that treatment pressure;Part II be in Use of respirator after a period of time, error is gradually increased, and passes through another algorithm
Adjustment treatment pressure.
Compared with prior art, the invention is due to corresponding in the case where having learnt various air leakages before lung ventilator dispatches from the factory
Pressure is treated, need to only call satisfactory treatment pressure in actual use, therefore can quickly give because of mask or pipeline
Deng position occur gas leakage when treatment pressure compensation, make treatment output end pressure stablize in time setting pressure.And when breathing
Machine in use for some time, when there is larger error, by computational methods dynamic adjustment treatment pressure again, remains able to
Treatment output end pressure is set to stablize in time in setting pressure.The present invention reaches the quick, smart of air leakage using the two parts
Really compensation, is effectively ensured the effect for the treatment of and comfort level that patient uses.
Brief description of the drawings
Accompanying drawing described here is only used for task of explanation, and is not intended in any way to limit model disclosed in the present application
Enclose.In addition, shape and proportional sizes of each part in figure etc. are only schematical, the understanding to the application is used to help, and
It is not the specific shape and proportional sizes for limiting each part of the application.Those skilled in the art, can under teachings of the present application
To select various possible shapes and proportional sizes to implement the application as the case may be.In the accompanying drawings:
Accompanying drawing 1 is the flow chart that lung ventilator leakage pressure is stable in the embodiment of the present invention 1;
Accompanying drawing 2 is the flow chart that lung ventilator leakage pressure is stable in the embodiment of the present invention 2.
Embodiment
The present invention will be further illustrated in example below.These embodiments are merely to illustrate the present invention, but not to appoint
Where formula limitation is of the invention.
Embodiment 1:A kind of lung ventilator pressure stability method based on BP algorithm
Referring to accompanying drawing 1, the lung ventilator includes pressure sensor, flow sensor, signal processing module, control pressure computing mould
Block, back-propagation algorithm module, breathing pipeline and mask.The leakage pressure antihunt means include the training for treatment stage, adopt
Operated according to the following steps with above lung ventilator:
S1.1:First sample is set, the sample includes pressure parameter P in the same state, flow parameter F, air leakage ginseng
Number S, control pressure parameter P1, loine pressure loss parameter P2 and mask air leakage amount parameter X, into S1.2.
S1.2:Judge whether sample size is more than numerical value of N;If the sample size is less than numerical value of N, S1.3 is gone to;If institute
State sample size and be more than numerical value of N, then go to S1.5, in the present embodiment, the numerical value of N is taken as 4000.
S1.3:Increase a new samples, pressure parameter P, the flow that the increased new samples include in the same state are joined
Number F, air leakage parameter S, control pressure parameter P1, loine pressure loss parameter P2 and mask air leakage amount parameter X;Read the shape
Each sample parameter of new samples under state, each sample parameter under the state is controlled using sample calculating is obtained in back-propagation algorithm
Pressure value P s is treated, into S1.4.
S1.4:Judge that the sample actual therapeutic pressure value P m- samples under the state calculate treatment pressure value P s sample standard deviation
Whether variance is less than critical value T;If the sample mean square deviation is less than critical value T, S1.5 is transferred to;If the mean square deviation is more than and faced
Dividing value T, then return to S1.2.
S1.5:The weights of each parameter are calculated, the weights are stored in storage region, and enter S1.6.
S1.6:The actual parameter value corresponding with the sample under therapeutic state is read, is called each in storage region
The weights of parameter, with actual parameter value be multiplied by weights again using back-propagation algorithm calculate the training for treatment stage calculating treat
Pressure value P s ', and enter S1.7.
S1.7:Mask end actual therapeutic pressure now corresponding to mask is reasonable, using mask end treatment pressure to disease
Suffer from treatment.
Wherein, the pressure parameter P is measured by pressure sensor, and the flow parameter F is surveyed by flow sensor
, the actual therapeutic pressure Pm is the factory settings formula for producing the mask, brings the pressure parameter P measured and survey into
The flow parameter F obtained can be calculated.
Embodiment 2:A kind of lung ventilator leakage pressure antihunt means based on back-propagation algorithm
Referring to accompanying drawing 2, the leakage pressure antihunt means include training for treatment and dynamic adjustment treatment, and a determination step;
Operated according to the following steps:
S1.1:First sample is set, the sample includes pressure parameter P in the same state, flow parameter F, air leakage ginseng
Number S, control pressure parameter P1, loine pressure loss parameter P2 and mask air leakage amount parameter X, into S1.2.
S1.2:Judge whether sample size is more than numerical value of N;If the sample size is less than numerical value of N, S1.3 is gone to;If institute
State sample size and be more than numerical value of N, then go to S1.5, in the present embodiment, the numerical value of N is taken as 5000.
S1.3:Increase a new samples, pressure parameter P, the flow that the increased new samples include in the same state are joined
Number F, air leakage parameter S, control pressure parameter P1, loine pressure loss parameter P2 and mask air leakage amount parameter X;Read the shape
Each sample parameter of new samples under state, each sample parameter under the state is controlled using sample calculating is obtained in back-propagation algorithm
Pressure value P s is treated, into S1.4.
S1.4:Judge that the sample actual therapeutic pressure value P m- samples under the state calculate treatment pressure value P s sample standard deviation
Whether variance is less than critical value T;If the sample mean square deviation is less than critical value T, S1.5 is transferred to;If the mean square deviation is more than and faced
Dividing value T, then return to S1.2.
S1.5:The weights of each parameter are calculated, the weights are stored in storage region, and enter S1.6.
S1.6:The actual parameter value corresponding with the sample under therapeutic state is read, is called each in storage region
The weights of parameter, with actual parameter value be multiplied by weights again using back-propagation algorithm calculate the training for treatment stage calculating treat
Pressure value P s ', and enter S1.7.
Also include a determination step, the determination step includes S2.1:Judge the actual therapeutic pressure in training for treatment stage
Whether the calculating treatment pressure Ps ' in Pm '-training for treatment stage treatment mean square deviation is less than critical value T.
S2.2:If the treatment mean square deviation is less than critical value T, S1.7 is gone to;If the treatment mean square deviation is more than critical
Value T, then the dynamic adjustment treatment stage is carried out, goes to the S3.1.
S3.1:A COEFFICIENT K is set, and is stored in the storage region, into S3.2.
S3.2:Read the COEFFICIENT K, read actual pressure P values and actual flow F values that the pressure sensor measures,
Into S3.3.
S3.3:Pass through the actual control pressure value parameter of the COEFFICIENT K, actual pressure P and actual flow F calculating now
P1, into S3.4.
S3.4:By the pressure parameter P under the state, flow parameter F, air leakage parameter S, the control pressure parameter P1,
Loine pressure loss parameter P2 and mask air leakage amount parameter X, which brings back-propagation algorithm into and is adjusted the calculating for the treatment of stage, to be controlled
Pressure value P s " is treated, into S3.5.
S3.5:Judge calculating treatment pressure Ps " of the actual therapeutic pressure Pm- adjustment treatment stages of adjustment treatment stage
Whether treatment mean square deviation is less than critical value T;If the treatment mean square deviation is less than critical value T, using actual therapeutic pressure Pm
Give sufferer;If the treatment mean square deviation is more than critical value T, S3.3 is returned to.
In above example, what the pressure parameter P was measured by pressure sensor, the flow parameter F passes through flow
Sensor measures, and the actual therapeutic pressure Pm is the factory settings formula for producing the mask, brings the pressure ginseng measured into
Number P and the flow parameter F measured can be calculated.
The pressure parameter P refers to the pressure value at the lung ventilator laminar flow pipe that pressure sensor measures;The flow ginseng
Number F refer to that flow sensor measures flow value, due to mask be it is certain, mask pipeline be it is certain, and pressure value, it is known that
Flow value is, it is known that can then calculate the air leakage parameter S values under same state, control pressure P1 values, loine pressure loss P2 values
And mask air leakage amount X values.
The weights of each parameter refer to that pressure parameter P obtains weights Wp, flow parameter F weights Wf, air leakage parameter S
Weights Ws, control pressure parameter P1 weights Wp1, loine pressure loss parameter P2 weights Wp2 and mask air leakage amount ginseng
Number X weights Wx.
It is described in detail below with reference to the present embodiment 2:The Back Propagation Algorithm being mainly concerned with Fig. 2 is batch study mould
Formula, lung ventilator need to carry out batch study before treatment, and the main frame MCU of lung ventilator reads lung ventilator in different air leakages in real time
Pressure sensor signal P and flow sensor signal F under S, and signal feeding signal processing module 3 is filtered and amplified
Processing, control pressure computing module 4 adjust system pressure drive circuit signal by computing, produce the control pressure of needs
P1, and then calculate breathing pipeline pressure loss P2 and mask air leakage amount X.As shown in Fig. 2, by above-mentioned pressure sensor signal
P, flow sensor signal F, breathing pipeline pressure loss P2, control pressure P1, mask are let out caused by control pressure computing module 4
Tolerance X and current air leakage S is combined into 5000 parts of training sample input Back Propagation Algorithm modules 4 and carries out batch study.Face to face
The cover end actual treatment pressure Pm and treatment pressure Ps calculated mean square error terminates batch when being less than critical value T and learnt,
Calculate the weights of each input parameter and be stored in storage region E2.
The weights of each input parameter in E2 can be read when lung ventilator is in treatment and bring calculating into, and explanation in detail below is realized
Process:
As shown in Figure 2:When lung ventilator is powered and starts treatment, main frame can read the pressure sensor signal P in deposit E2 respectively
Weights Wp, flow sensor signal F weights Wf, control pressure P1 weights Wp1, breathing circuit pressure loss P2 power
Value Wp2, mask air leakage amount X weights Wx and air leakage S weights Ws.Then each parameter is multiplied by weights and brings back-propagating calculation into
Method module 4, mask end treatment pressure theory value Pm is calculated, and judge the mean square error size between actual value and theoretical value.
If error is less than critical value T, the input control pressure P1 of input batch study calculating is only needed, then mask end just occurs
Satisfactory treatment pressure Pm;Then following methods are used when being more than setting critical value T if there is mean square error in treatment
Dynamic adjusts.
In respirator system, if from blower outlet is directly over pipeline, mask reaches patient, pipeline and mask
Load of the part equivalent to air blower.The pressure of air blower output has the reduction of obstructed degree after overload, reduction it is more
The size of few gas circuit resistance for depending on load.
The above embodiments merely illustrate the technical concept and features of the present invention, and its object is to allow person skilled in the art
Scholar can understand present disclosure and implement according to this, and it is not intended to limit the scope of the present invention.It is all according to the present invention
The equivalent change or modification that Spirit Essence is made, it should all be included within the scope of the present invention.
It should be noted that in the description of the present application, unless otherwise indicated, " multiple " be meant that two or two with
On.
Using term "comprising" or " comprising " describing the combination of element here, composition, part or step it is also contemplated that
Substantially the embodiment being made up of these elements, composition, part or step.Here by using term " can with ", it is intended to illustrate
Described any attribute that " can with " includes all is optional.
Multiple element, composition, part or step can be provided by single integrated component, composition, part or step.It is alternative
Ground, single integrated component, composition, part or step can be divided into multiple element, composition, part or the step of separation.It is used for
The open "a" or "an" for describing element, composition, part or step is not said to exclude other elements, composition, part
Or step.
It should be understood that above description is to illustrate rather than to be limited.By reading above-mentioned retouch
State, many embodiments and many applications outside the example provided all will be aobvious and easy for a person skilled in the art
See.Therefore, the scope of this teaching should not determine with reference to foregoing description, but should with reference to preceding claims and this
The four corner of the equivalent that a little claims are possessed determines.It is for comprehensive purpose, all articles and special with reference to including
The disclosure of profit application and bulletin is all by reference to being incorporated herein.Theme disclosed herein is omitted in preceding claims
Any aspect is not intended to abandon the body matter, also should not be considered as applicant the theme is not thought of as it is disclosed
Apply for a part for theme.
Those listed above it is a series of describe in detail only for the application feasibility embodiment specifically
Bright, they are simultaneously not used to limit the protection domain of the application, all equivalent implementations made without departing from the application skill spirit
Or change should be included within the protection domain of the application.
Claims (5)
- A kind of 1. lung ventilator pressure stability method based on BP algorithm, it is characterised in that:The pressure stability method includes training Treatment stage, the training for treatment stage comprise the following steps:S1.1:First sample is gathered, the sample includes pressure parameter P in the same state, flow parameter F, air leakage ginseng Number S, control pressure parameter P1, loine pressure loss parameter P2 and mask air leakage amount parameter X, into S1.2;S1.2:Judge whether sample size is more than numerical value of N;If the sample size is less than numerical value of N, S1.3 is gone to;If the sample This quantity is more than numerical value of N, then goes to S1.5;S1.3:Increase a new samples, the increased new samples include pressure parameter P in the same state, flow parameter F, Air leakage parameter S, control pressure parameter P1, loine pressure loss parameter P2 and mask air leakage amount parameter X;Read under the state Each sample parameter of new samples, each sample parameter under the state is used sample calculating treatment pressure is obtained in back-propagation algorithm Force value Ps, into S1.4;S1.4:Judge that the sample actual therapeutic pressure value P m- samples under the state calculate treatment pressure value P s sample mean square deviation Whether critical value T is less than;If the sample mean square deviation is less than critical value T, S1.5 is transferred to;If the mean square deviation is more than critical value T, then return to S1.2;S1.5:The weights of each parameter are calculated, the weights are stored in storage region, and enter S1.6;S1.6:The actual parameter value corresponding with the sample under therapeutic state is read, calls each parameter in storage region Weights, with actual parameter value be multiplied by weights again using back-propagation algorithm calculate the training for treatment stage calculating treat pressure Value Ps ', and enter S1.7;S1.7:Mask end actual therapeutic pressure now corresponding to mask is reasonable, is controlled using mask end treatment pressure to sufferer Treat;Wherein, the pressure parameter P is measured by pressure sensor, and the flow parameter F is measured by flow sensor, institute It is the factory settings formula for producing the mask to state actual therapeutic pressure Pm, brings the pressure parameter P measured into and measures Flow parameter F can be calculated.
- 2. the lung ventilator leakage pressure antihunt means according to claim 1 based on back-propagation algorithm, it is characterised in that: The pressure stability method also includes dynamic adjustment treatment stage, and the dynamic adjustment treatment stage comprises the following steps:S3.1:A COEFFICIENT K is set, and is stored in the storage region, into S3.2;S3.2:Read the COEFFICIENT K, read actual pressure P values and actual flow F values that the pressure sensor measures, enter S3.3;S3.3:Actual control pressure value parameter P1 now is calculated by the COEFFICIENT K, actual pressure P and actual flow F, Into S3.4;S3.4:By the pressure parameter P under the state, flow parameter F, air leakage parameter S, the control pressure parameter P1, pipeline Pressure loss parameter P2 and mask air leakage amount parameter X brings the calculating treatment pressure that back-propagation algorithm is adjusted treatment stage into Force value Ps ", into S3.5;S3.5:Judge the calculating treatment pressure Ps " of the actual therapeutic pressure Pm- adjustment treatment stages of adjustment treatment stage treatment Whether mean square deviation is less than critical value T;If the treatment mean square deviation is less than critical value T, given using actual therapeutic pressure Pm Sufferer;If the treatment mean square deviation is more than critical value T, S3.3 is returned to.
- 3. the lung ventilator leakage pressure antihunt means according to claim 2 based on back-propagation algorithm, it is characterised in that: Also include a determination step before using dynamic adjustment treatment stage, the determination step is located at the training for treatment stage Between S1.6 and S1.7;The determination step includes S2.1:Judge the calculating in the actual therapeutic pressure Pm '-training for treatment stage in training for treatment stage Whether treatment pressure Ps ' treatment mean square deviation is less than critical value T;S2.2:If the treatment mean square deviation is less than critical value T, S1.7 is gone to;If the treatment mean square deviation is more than critical value T, The dynamic adjustment treatment stage is then carried out, goes to the S3.1.
- It is 4. described according to any described lung ventilator leakage pressure antihunt means based on back-propagation algorithm of claim 1-3 Numerical value of N is more than or equal to 6000.
- 5. the lung ventilator leakage pressure antihunt means, the numerical value of N etc. according to claim 4 based on back-propagation algorithm In 8000.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710994923.7A CN107679624A (en) | 2017-10-24 | 2017-10-24 | Lung ventilator pressure stability method based on BP algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710994923.7A CN107679624A (en) | 2017-10-24 | 2017-10-24 | Lung ventilator pressure stability method based on BP algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107679624A true CN107679624A (en) | 2018-02-09 |
Family
ID=61141482
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710994923.7A Pending CN107679624A (en) | 2017-10-24 | 2017-10-24 | Lung ventilator pressure stability method based on BP algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107679624A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101035584A (en) * | 2004-10-06 | 2007-09-12 | 雷斯梅德有限公司 | Method and apparatus for non-invasive monitoring of respiratory parameters in sleep disordered breathing |
CN103736183A (en) * | 2013-12-13 | 2014-04-23 | 科迈(常州)电子有限公司 | Pressure control device and method for double-level respirator |
CN105854142A (en) * | 2016-05-10 | 2016-08-17 | 苏州鱼跃医疗科技有限公司 | Respirator treatment pressure stabilizing method based on back propagation algorithm |
-
2017
- 2017-10-24 CN CN201710994923.7A patent/CN107679624A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101035584A (en) * | 2004-10-06 | 2007-09-12 | 雷斯梅德有限公司 | Method and apparatus for non-invasive monitoring of respiratory parameters in sleep disordered breathing |
CN103736183A (en) * | 2013-12-13 | 2014-04-23 | 科迈(常州)电子有限公司 | Pressure control device and method for double-level respirator |
CN105854142A (en) * | 2016-05-10 | 2016-08-17 | 苏州鱼跃医疗科技有限公司 | Respirator treatment pressure stabilizing method based on back propagation algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105854142B (en) | A kind of respirator treatment pressure stability method based on back-propagation algorithm | |
NZ701856A (en) | Automated control for detection of flow limitation | |
EP3027252B1 (en) | Medical measuring device, ventilation device and method for operating a medical measuring device | |
CN108619597A (en) | A kind of pressure compensating method of lung ventilator runner | |
CN105136265B (en) | A kind of accurate metering method of weighing and burden | |
CN101957356A (en) | Biochemical oxygen demand BOD soft measurement method based on elastic radical basis function neural network | |
CN103028170A (en) | Breathing pressure fuzzy control type respirator and breathing pressure fuzzy control method | |
CN106456921A (en) | A method for controlling mechanical lung ventilation | |
CN103071213A (en) | Leakage compensation method for single-loop non-invasive ventilators | |
CN104764141A (en) | Air conditioner temperature control method and air conditioner | |
CN107679624A (en) | Lung ventilator pressure stability method based on BP algorithm | |
WO2017113546A1 (en) | Fuzzy adaptive pid control-based capacity control method of anesthesia machine | |
CN109996579A (en) | The method and system that patient airway and leakage flow for invasive ventilation are estimated | |
CN104329777B (en) | Frequency control method and system | |
CN108427285B (en) | Rotating speed self-adaptive control system and method for engine pedestal | |
CN107735133A (en) | The method and system that patient airway and leakage flow for invasive ventilation are estimated | |
Jo et al. | A two-loop robust controller for HIV infection models in the presence of parameter uncertainties | |
Timms et al. | Leveraging intensive longitudinal data to better understand health behaviors | |
CN108363292A (en) | A kind of fired power generating unit AGC control method and device based on fuzzy control strategy | |
Campello et al. | Optimal Laguerre series expansion of discrete Volterra models | |
CN114110940A (en) | Intelligent electric regulating valve adjusting method and system for air-conditioning water system | |
CN106422009B (en) | A kind of respiratory pressure follower method | |
CN220142381U (en) | Noninvasive ventilator gas circuit connection structure | |
Zhu et al. | A Concept on Dual Control of Mechanical Ventilation Based on the Extension Strategy | |
CN117046856B (en) | Air quantity control method, exhaust cabinet and computer storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180209 |
|
RJ01 | Rejection of invention patent application after publication |