A method for evaluating human-machine adaptation of a ventilator

Abstract

The present invention relates to the technical field of ventilator adaptation, and discloses a ventilator human-machine adaptation evaluation method, including: constructing a ventilator human-machine adaptation parameter control model; using a feature decomposition algorithm to perform feature decomposition on the ventilator human-machine adaptation parameter control model to obtain ventilator human-machine adaptation feature components; obtaining a ventilator human-machine adaptation feature data set, decomposing the feature components of the feature data set using a feature decomposition algorithm, and establishing a ventilator human-machine adaptation model; establishing a ventilator human-machine adaptation evaluation model based on the ventilator human-machine adaptation model, and using the ventilator human-machine adaptation evaluation model to implement ventilator human-machine adaptation evaluation. The method of the present invention improves the human-machine adaptability of the ventilator by establishing a ventilator human-machine adaptation evaluation model and adaptively modifying parameters according to the human-machine adaptation evaluation results.

Description

Technical Field

[0001] The present invention relates to the technical field of ventilator adaptation assessment, and in particular to a ventilator human-machine adaptation assessment method. Background Art

[0002] Due to environmental pollution and an aging population, respiratory diseases have become one of the four major chronic diseases in the world, and home ventilators are the most effective means of treatment. Therefore, the domestic ventilator market size has increased at an average annual rate of 20%. Traditional ventilator parameter adjustment requires manual modification of parameters, and adaptive modification of ventilator parameters cannot be achieved.

[0003] In view of this, the present invention proposes a ventilator human-machine adaptation evaluation method, which improves the human-machine adaptability of the ventilator by establishing a ventilator human-machine adaptation evaluation model and adaptively modifying parameters according to the human-machine adaptation evaluation results. Summary of the invention

[0004] The present invention provides a method for evaluating the human-machine adaptation of a ventilator, the purpose of which is to (1) implement the evaluation of the human-machine adaptability of the ventilator; and (2) implement the adaptive control of the human-machine adaptation parameters of the ventilator.

[0005] To achieve the above object, the present invention provides a ventilator human-machine adaptation evaluation method, comprising the following steps:

[0006] S1: Construct a ventilator human-machine adaptation parameter control model;

[0007] S2: Using the eigendecomposition algorithm to perform eigendecomposition on the ventilator human-machine adaptation parameter control model to obtain the ventilator human-machine adaptation characteristic components;

[0008] S3: Obtain a ventilator human-machine adaptation feature data set, use a feature decomposition algorithm to decompose the feature data set to obtain feature components, and establish a ventilator human-machine adaptation model;

[0009] S4: Establish a ventilator human-machine adaptation evaluation model based on the ventilator human-machine adaptation model, and use the ventilator human-machine adaptation evaluation model to implement ventilator human-machine adaptation evaluation.

[0010] As a further improvement method of the present invention:

[0011] The parameter distribution function in the ventilator human-machine adaptation parameter control model is constructed in step S1, including:

[0012] The parameter distribution function in the ventilator human-machine adaptation parameter control model is constructed. The constructed parameter distribution function is:

[0013]

[0014] in:

[0015] Q represents the ventilator human-machine adaptation parameters, including the ventilator human-machine adaptation control parameters a and the ventilator human-machine adaptation amplitude adjustment parameters b; in a specific embodiment of the present invention, the ventilator human-machine adaptation control parameters include the voltage value and power of the ventilator, and the ventilator human-machine adaptation amplitude adjustment parameters include the speed and position of the ventilator;

[0016] f(t) represents the multi-dimensional parameter model of human-machine adaptation at time t, f(t) = a t β t +b t γ t , a t represents the ventilator human-machine adaptation control parameters at time t, b t represents the ventilator human-machine adaptation amplitude adjustment parameter at time t, β t and γ t They are respectively t and b t The coefficient of

[0017] Establish human-machine adaptation parameter task flow c:

[0018]

[0019] in:

[0020] q represents the scaling factor of the human-machine adaptation parameter, which is set to 2.

[0021] In the step S1, a ventilator human-machine adaptation parameter control model is constructed based on the parameter distribution function, including:

[0022] Establish the joint probability density function between the components of the ventilator:

[0023]

[0024] in:

[0025] p k represents the decoupling rate of component k in the ventilator, wherein the decoupling rate of component k represents the probability that component k has no connection relationship with other components;

[0026] Construct a ventilator human-machine adaptation parameter control model:

[0027]

[0028] in:

[0029] Y(Q) is the established human-machine adaptation parameter control model.

[0030] In the step S2, the ventilator human-machine adaptation parameter control model is subjected to characteristic decomposition to obtain the ventilator human-machine adaptation characteristic components, including:

[0031] According to the constructed ventilator human-machine adaptation parameter control model, the ventilator human-machine adaptation parameter control model is characterized by using the characteristic decomposition algorithm to obtain the ventilator human-machine adaptation characteristic components. The characteristic decomposition algorithm process is as follows:

[0032] 1) Obtain the human-machine adaptation parameter matrix W:

[0033]

[0034] in:

[0035] Q t Represents the ventilator human-machine adaptation parameters at time t;

[0036] a t represents the ventilator human-machine adaptation control parameters at time t, b t Represents the ventilator human-machine adaptation amplitude adjustment parameter at time t;

[0037] 2) Characteristic decomposition of the ventilator human-machine adaptation parameter control model:

[0038]

[0039] in:

[0040] x represents the decomposed human-machine adaptation parameter characteristics;

[0041] 3) Analyze the decomposed human-machine adaptation parameter characteristics to obtain the human-machine adaptation parameter characteristic components:

[0042]

[0043] in:

[0044] L(a i ,b i ) is the human-machine adaptation parameter combination (a i ,b i )’s characteristic components.

[0045] In the step S3, a ventilator human-machine adaptation feature data set is obtained, and the feature decomposition algorithm in the above step is used to decompose the feature data set, including:

[0046] Get the ventilator human-machine adaptation feature data set R = {r1, r2, ..., r j ,…,r n}, where r jrepresents the jth group of ventilator human-machine adaptation feature data, wherein the ventilator human-machine adaptation feature data includes ventilator human-machine adaptation parameters and human-machine adaptation evaluation scores;

[0047] For any set of ventilator human-machine adaptation feature data r in the ventilator human-machine adaptation feature data set R n , the following conditions are met:

[0048]

[0049] in:

[0050] f n (t) represents the ventilator human-machine adaptation feature data r n A multi-dimensional parameter model of human-machine adaptation.

[0051] The step S3 establishes a ventilator human-machine adaptation model, including:

[0052] Calculate the reliability parameters of the ventilator human-machine adaptation model:

[0053]

[0054] in:

[0055] u i Indicates the frequency of the ventilator human-machine adaptation amplitude adjustment;

[0056] Establishing the human-machine adaptation model U(r j ):

[0057] U(r j ) = log2[ε-r j ∫0 π Y(Q)dQ]-||Y(Q)-c|| 3

[0058] in:

[0059] Y(Q) is the established human-machine adaptation parameter control model;

[0060] c represents the human-machine adaptation parameter task flow.

[0061] In the step S4, a ventilator human-machine adaptation evaluation model is established based on the ventilator human-machine adaptation model, and the established ventilator human-machine adaptation evaluation model is used to implement human-machine adaptation evaluation, including:

[0062] According to the established ventilator human-machine adaptation model, the ventilator human-machine adaptation evaluation objective function is established:

[0063]

[0064] in:

[0065] Y represents the human-machine adaptation parameter control model, U represents the ventilator human-machine adaptation model, and Q represents the ventilator human-machine adaptation parameters;

[0066] f(t) represents the multi-dimensional parameter model of human-machine adaptation at time t;

[0067] F(t) represents the parameter distribution function of the ventilator human-machine adaptation parameters;

[0068] θ represents the ventilator human-machine adaptation coefficient matrix;

[0069] The probability density function of the ventilator human-machine adaptation evaluation is calculated:

[0070]

[0071] in:

[0072] p(Q) is the joint probability density function between the components of the ventilator;

[0073] α represents the adaptive weight;

[0074] Construct a ventilator human-machine adaptation evaluation model:

[0075] K(Q)=H(M(Q))

[0076] in:

[0077] H(·) is a mapping function, which maps M(Q) to an evaluation score interval of [0,100]. In a specific embodiment of the present invention, the present invention obtains a ventilator human-machine adaptation feature data set R, uses the ventilator human-machine adaptation parameters as the input of the ventilator human-machine adaptation evaluation probability density function, obtains the corresponding probability density function value, fits the probability density function value with the corresponding human-machine adaptation evaluation score, and obtains the mapping function H(·);

[0078] By taking the ventilator human-machine adaptation parameters as the input of the ventilator human-machine adaptation evaluation model, the ventilator human-machine adaptation evaluation score is output, and the ventilator human-machine adaptation parameters are adjusted according to the ventilator human-machine adaptation evaluation score. That is, if the ventilator human-machine adaptation evaluation score is low, the human-machine adaptation parameters are optimized to improve the ventilator human-machine adaptation evaluation score.

[0079] Compared with the prior art, the present invention proposes a ventilator human-machine adaptation evaluation method, which has the following advantages:

[0080] First, this scheme constructs a human-machine adaptation model by combining the human-machine adaptation feature data set of the ventilator. According to the established human-machine adaptation model, different parameters for improving human-machine adaptability are adopted under different human-machine adaptation evaluation results. The construction process of the human-machine adaptation model is as follows: obtain the human-machine adaptation feature data set R = {r1, r2, …, r j ,…,r n}, where r j represents the jth group of ventilator human-machine adaptation feature data, wherein the ventilator human-machine adaptation feature data includes ventilator human-machine adaptation parameters and human-machine adaptation evaluation scores; for any group of ventilator human-machine adaptation feature data r in the ventilator human-machine adaptation feature data set R n , the following conditions are met:

[0081]

[0082] Where: f n (t) represents the ventilator human-machine adaptation feature data r n Calculate the reliability parameters of the ventilator human-machine adaptation model:

[0083]

[0084] Where: u i Represents the frequency of the ventilator human-machine adaptation amplitude adjustment; establishes the ventilator human-machine adaptation model U(r j ):

[0085] U(r j ) = log2[ε-r j ∫0 π Y(Q)dQ]-||Y(Q)-c|| 3

[0086] Wherein: Y(Q) is the established human-machine adaptation parameter control model; c represents the human-machine adaptation parameter task flow, the ventilator human-machine adaptation model represents the matrix value under different adaptation scheduling strategies, and by converting the human-machine adaptation model into an evaluation model, the evaluation value under different adaptation scheduling strategies can be calculated, and the evaluation value can be used as the model independent variable. According to the established ventilator human-machine adaptation model, the adaptation scheduling strategy for improving human-machine adaptability is calculated to realize the adaptive control of the ventilator human-machine adaptation parameters.

[0087] At the same time, this scheme proposes a ventilator human-machine adaptation evaluation model, so as to realize human-machine adaptation evaluation by using the established ventilator human-machine adaptation evaluation model. The steps for establishing the ventilator human-machine adaptation evaluation model are as follows: According to the established ventilator human-machine adaptation model, the ventilator human-machine adaptation evaluation objective function is established:

[0088]

[0089] Where: Y represents the human-machine adaptation parameter control model, U represents the ventilator human-machine adaptation model, Q represents the ventilator human-machine adaptation parameters; f(t) represents the multidimensional parameter model of human-machine adaptation at time t; F(t) represents the parameter distribution function of the ventilator human-machine adaptation parameters; θ represents the ventilator human-machine adaptation coefficient matrix; the probability density function of the ventilator human-machine adaptation evaluation is calculated:

[0090]

[0091] Where: p(Q) is the joint probability density function between the components of the ventilator; α represents the adaptive weight; the ventilator human-machine adaptation evaluation model is constructed:

[0092] K(Q)=H(M(Q))

[0093] Wherein: H(·) is a mapping function, which maps M(Q) to an evaluation score interval of [0,100]. This scheme obtains the ventilator human-machine adaptation feature data set R, takes the ventilator human-machine adaptation parameters as the input of the ventilator human-machine adaptation evaluation probability density function, obtains the corresponding probability density function value, and fits the probability density function value with the corresponding human-machine adaptation evaluation score to obtain the mapping function H(·); This scheme uses the ventilator human-machine adaptation parameters as the input of the ventilator human-machine adaptation evaluation model, outputs the ventilator human-machine adaptation evaluation score, and adjusts the ventilator human-machine adaptation parameters according to the ventilator human-machine adaptation evaluation score, that is, if the ventilator human-machine adaptation evaluation score is low, the human-machine adaptation parameters are optimized to improve the ventilator human-machine adaptation evaluation score, thereby realizing the optimal scheduling of the ventilator human-machine adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] Figure 1 A schematic diagram of a flow chart of a method for evaluating human-machine adaptation of a ventilator provided by an embodiment of the present invention;

[0095] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0096] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0097] S1: Construct a ventilator human-machine adaptation parameter control model.

[0098] The parameter distribution function in the ventilator human-machine adaptation parameter control model is constructed in step S1, including:

[0099] The parameter distribution function in the ventilator human-machine adaptation parameter control model is constructed. The constructed parameter distribution function is:

[0100]

[0101] in:

[0102] Q represents the ventilator human-machine adaptation parameters, including the ventilator human-machine adaptation control parameters a and the ventilator human-machine adaptation amplitude adjustment parameters b; in a specific embodiment of the present invention, the ventilator human-machine adaptation control parameters include the voltage value and power of the ventilator, and the ventilator human-machine adaptation amplitude adjustment parameters include the speed and position of the ventilator;

[0103] f(t) represents the multi-dimensional parameter model of human-machine adaptation at time t, f(t) = a t β t +b t γ t , a t represents the ventilator human-machine adaptation control parameters at time t, b t represents the ventilator human-machine adaptation amplitude adjustment parameter at time t, β t and γ t They are respectively t and b t The coefficient of

[0104] Establish human-machine adaptation parameter task flow c:

[0105]

[0106] in:

[0107] q represents the scaling factor of the human-machine adaptation parameter, which is set to 2.

[0108] In the step S1, a ventilator human-machine adaptation parameter control model is constructed based on the parameter distribution function, including:

[0109] Establish the joint probability density function between the components of the ventilator:

[0110]

[0111] in:

[0112] p k represents the decoupling rate of component k in the ventilator, wherein the decoupling rate of component k represents the probability that component k has no connection relationship with other components;

[0113] Construct a ventilator human-machine adaptation parameter control model:

[0114]

[0115] in:

[0116] Y(Q) is the established human-machine adaptation parameter control model.

[0117] S2: Use the eigendecomposition algorithm to perform eigendecomposition on the ventilator human-machine adaptation parameter control model to obtain the ventilator human-machine adaptation characteristic components.

[0118] In the step S2, the ventilator human-machine adaptation parameter control model is subjected to characteristic decomposition to obtain the ventilator human-machine adaptation characteristic components, including:

[0119] According to the constructed ventilator human-machine adaptation parameter control model, the ventilator human-machine adaptation parameter control model is characterized by using the characteristic decomposition algorithm to obtain the ventilator human-machine adaptation characteristic components. The characteristic decomposition algorithm process is as follows:

[0120] 1) Obtain the human-machine adaptation parameter matrix W:

[0121]

[0122] in:

[0123] Q t Represents the ventilator human-machine adaptation parameters at time t;

[0124] a t represents the ventilator human-machine adaptation control parameters at time t, b t Represents the ventilator human-machine adaptation amplitude adjustment parameter at time t;

[0125] 2) Characteristic decomposition of the ventilator human-machine adaptation parameter control model:

[0126]

[0127] in:

[0128] x represents the decomposed human-machine adaptation parameter characteristics;

[0129] 3) Analyze the decomposed human-machine adaptation parameter characteristics to obtain the human-machine adaptation parameter characteristic components:

[0130]

[0131] in:

[0132] L(a i ,b i ) is the human-machine adaptation parameter combination (a i ,b i )’s characteristic components.

[0133] S3: Obtain a ventilator human-machine adaptation feature data set, use a feature decomposition algorithm to decompose the feature data set to obtain feature components, and establish a ventilator human-machine adaptation model.

[0134] Get the ventilator human-machine adaptation feature data set R = {r1, r2, ..., r j ,…,r n}, where r j represents the jth group of ventilator human-machine adaptation feature data, wherein the ventilator human-machine adaptation feature data includes ventilator human-machine adaptation parameters and human-machine adaptation evaluation scores;

[0135] For any set of ventilator human-machine adaptation feature data r in the ventilator human-machine adaptation feature data set R n , the following conditions are met:

[0136]

[0137] in:

[0138] f n (t) represents the ventilator human-machine adaptation feature data r n A multi-dimensional parameter model of human-machine adaptation.

[0139] The step S3 establishes a ventilator human-machine adaptation model, including:

[0140] Calculate the reliability parameters of the ventilator human-machine adaptation model:

[0141]

[0142] in

[0143] u i Indicates the frequency of the ventilator human-machine adaptation amplitude adjustment;

[0144] Establishing the human-machine adaptation model U(r j ):

[0145] U(r j ) = log2[ε-r j ∫0 π Y(Q)dQ]-||Y(Q)-c|| 3

[0146] in:

[0147] Y(Q) is the established human-machine adaptation parameter control model;

[0148] c represents the human-machine adaptation parameter task flow.

[0149] S4: Establish a ventilator human-machine adaptation evaluation model based on the ventilator human-machine adaptation model, and use the ventilator human-machine adaptation evaluation model to implement ventilator human-machine adaptation evaluation.

[0150] In the step S4, a ventilator human-machine adaptation evaluation model is established based on the ventilator human-machine adaptation model, and the established ventilator human-machine adaptation evaluation model is used to implement human-machine adaptation evaluation, including:

[0151] According to the established ventilator human-machine adaptation model, the ventilator human-machine adaptation evaluation objective function is established:

[0152]

[0153] in:

[0154] Y represents the human-machine adaptation parameter control model, U represents the ventilator human-machine adaptation model, and Q represents the ventilator human-machine adaptation parameters;

[0155] f(t) represents the multi-dimensional parameter model of human-machine adaptation at time t;

[0156] F(t) represents the parameter distribution function of the ventilator human-machine adaptation parameters;

[0157] θ represents the ventilator human-machine adaptation coefficient matrix;

[0158] The probability density function of the ventilator human-machine adaptation evaluation is calculated:

[0159]

[0160] in:

[0161] p(Q) is the joint probability density function between the components of the ventilator;

[0162] α represents the adaptive weight;

[0163] Construct a ventilator human-machine adaptation evaluation model:

[0164] K(Q)=H(M(Q))

[0165] in:

[0166] H(·) is a mapping function, which maps M(Q) to an evaluation score interval of [0,100]. In a specific embodiment of the present invention, the present invention obtains a ventilator human-machine adaptation feature data set R, uses the ventilator human-machine adaptation parameters as the input of the ventilator human-machine adaptation evaluation probability density function, obtains the corresponding probability density function value, fits the probability density function value with the corresponding human-machine adaptation evaluation score, and obtains the mapping function H(·);

[0167] By taking the ventilator human-machine adaptation parameters as the input of the ventilator human-machine adaptation evaluation model, the ventilator human-machine adaptation evaluation score is output, and the ventilator human-machine adaptation parameters are adjusted according to the ventilator human-machine adaptation evaluation score. That is, if the ventilator human-machine adaptation evaluation score is low, the human-machine adaptation parameters are optimized to improve the ventilator human-machine adaptation evaluation score.

[0168] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0169] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0170] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for evaluating human-machine adaptation of a ventilator, characterized in that: The method comprises: S1: Construct a ventilator human-machine adaptation parameter control model; The parameter distribution function in the ventilator human-machine adaptation parameter control model is constructed. The constructed parameter distribution function is: in: Q represents the ventilator human-machine adaptation parameters, including the ventilator human-machine adaptation control parameters and the ventilator human-machine adaptation amplitude adjustment parameter b; represents the multi-dimensional parameter model of human-machine adaptation at time t, , represents the ventilator human-machine adaptation control parameters at time t, represents the ventilator human-machine adaptation amplitude adjustment parameter at time t, as well as They are and The coefficient of Establish human-machine adaptation parameter task flow c: in: The scale factor representing the human-machine adaptation parameter is set to 2; Based on the parameter distribution function, a ventilator human-machine adaptation parameter control model is constructed, including: Establish the joint probability density function between the components of the ventilator: in: represents the decoupling rate of component k in the ventilator, wherein the decoupling rate of component k represents the probability that component k has no connection relationship with other components; Construct a ventilator human-machine adaptation parameter control model: in: The parameter control model for human-machine adaptation is established; S2: Using the eigendecomposition algorithm to perform eigendecomposition on the ventilator human-machine adaptation parameter control model to obtain the ventilator human-machine adaptation characteristic components; S3: Obtain a ventilator human-machine adaptation feature data set, use a feature decomposition algorithm to decompose the feature data set to obtain feature components, and establish a ventilator human-machine adaptation model; S4: Establish a ventilator human-machine adaptation evaluation model based on the ventilator human-machine adaptation model, and use the ventilator human-machine adaptation evaluation model to implement ventilator human-machine adaptation evaluation.

2. A ventilator human-machine adaptation evaluation method as claimed in claim 1, characterized in that: In the step S2, the ventilator human-machine adaptation parameter control model is subjected to characteristic decomposition to obtain the ventilator human-machine adaptation characteristic components, including: According to the constructed ventilator human-machine adaptation parameter control model, the ventilator human-machine adaptation parameter control model is characterized by using the characteristic decomposition algorithm to obtain the ventilator human-machine adaptation characteristic components. The characteristic decomposition algorithm process is as follows: 1) Obtain the human-machine adaptation parameter matrix W: in: Represents the ventilator human-machine adaptation parameters at time t; represents the ventilator human-machine adaptation control parameters at time t, Represents the ventilator human-machine adaptation amplitude adjustment parameter at time t; 2) Characteristic decomposition of the ventilator human-machine adaptation parameter control model: in: x represents the decomposed human-machine adaptation parameter characteristics; 3) Analyze the decomposed human-machine adaptation parameter characteristics to obtain the human-machine adaptation parameter characteristic components: in: The human-machine adaptation parameter combination is characteristic component.

3. A ventilator human-machine adaptation evaluation method as described in claim 2, characterized in that: In the step S3, a ventilator human-machine adaptation feature data set is obtained, and the feature decomposition algorithm in the above step is used to decompose the feature data set, including: Obtaining the human-machine adaptation feature dataset for ventilators ,in represents the jth group of ventilator human-machine adaptation feature data, wherein the ventilator human-machine adaptation feature data includes ventilator human-machine adaptation parameters and human-machine adaptation evaluation scores; For the ventilator human-machine adaptation feature dataset Any set of ventilator human-machine adaptation feature data , the following conditions are met: in: Represents the human-machine adaptation feature data of the ventilator A multi-dimensional parameter model of human-machine adaptation.

4. A ventilator human-machine adaptation assessment method as described in claim 3, characterized in that: The step S3 establishes a ventilator human-machine adaptation model, including: Calculate the reliability parameters of the ventilator human-machine adaptation model: in: Indicates the frequency of the ventilator human-machine adaptation amplitude adjustment; Establishing a human-machine adaptation model for ventilators : in: The parameter control model for human-machine adaptation is established; c represents the human-machine adaptation parameter task flow.

5. A ventilator human-machine adaptation assessment method as claimed in claim 4, characterized in that: In the step S4, a ventilator human-machine adaptation evaluation model is established based on the ventilator human-machine adaptation model, and the established ventilator human-machine adaptation evaluation model is used to implement human-machine adaptation evaluation, including: According to the established ventilator human-machine adaptation model, the ventilator human-machine adaptation evaluation objective function is established: in: Y represents the human-machine adaptation parameter control model, U represents the ventilator human-machine adaptation model, and Q represents the ventilator human-machine adaptation parameters; represents the multi-dimensional parameter model of human-machine adaptation at time t; Parameter distribution function representing the ventilator human-machine adaptation parameters; Represents the ventilator human-machine adaptation coefficient matrix; The probability density function of the ventilator human-machine adaptation evaluation is calculated: in: is the joint probability density function between the components of the ventilator; represents adaptive weight; Construct a ventilator human-machine adaptation evaluation model: in: As the mapping function, Mapped to the evaluation score interval of [0,100]; The ventilator human-machine adaptation parameters are used as the input of the ventilator human-machine adaptation evaluation model, the ventilator human-machine adaptation evaluation score is output, and the ventilator human-machine adaptation parameters are adjusted according to the ventilator human-machine adaptation evaluation score.

Images