Biosafety laboratory energy efficiency optimization method and system based on analog simulation

Abstract

The invention discloses a biosafety laboratory energy efficiency optimization method and system based on analog simulation, and the method comprises the steps: collecting simulation data and related data of a simulation biosafety laboratory, and carrying out the preprocessing of the simulation data and the related data; performing comparison clustering on the simulation data according to an energy efficiency threshold value to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio; performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing association influence analysis on the related data to obtain a variable coefficient; and constructing a biosafety laboratory energy efficiency optimization model according to the optimization rate and the variable coefficient, optimizing the biosafety laboratory energy efficiency optimization model, inputting to-be-optimized data into the biosafety laboratory energy efficiency optimization model, and outputting an optimization result. According to the method, the precision of biosafety laboratory energy efficiency optimization based on analog simulation is improved, meanwhile, the method has good interpretability, and the method can be directly applied to an energy efficiency optimization system.

Description

Technical Field

[0001] The present invention relates to the field of simulation optimization, and in particular to a method and system for optimizing energy efficiency of a biosafety laboratory based on simulation. Background Art

[0002] With the rapid development of life science research, biosafety laboratories, as important places for disease prevention and control, drug development and biotechnology research, are receiving increasing attention for their operating efficiency and safety. However, the energy consumption management of biosafety laboratories has long faced many challenges, including but not limited to a wide variety of equipment, complex operating modes, strict environmental control requirements, and uncertainty in experimental operations. These factors together make it difficult to accurately control and optimize energy efficiency.

[0003] Traditional biosafety laboratory energy efficiency management relies on manual experience adjustment and regular equipment maintenance, lacking systematic data analysis and scientific prediction and optimization methods. In addition, the complex relationship between laboratory internal environmental parameters and energy consumption makes it difficult to achieve global energy efficiency optimization through single parameter adjustment. Therefore, developing a biosafety laboratory energy efficiency optimization method based on simulation has become an important way to improve laboratory energy efficiency, reduce operating costs, and ensure experimental safety. Summary of the invention

[0004] The purpose of the present invention is to provide a method for optimizing the energy efficiency of a biosafety laboratory based on simulation.

[0005] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0006] The present invention comprises the following steps:

[0007] Collecting simulation data and related data of a simulated biosafety laboratory, and preprocessing the simulation data and the related data;

[0008] Comparing and clustering the simulation data according to the energy efficiency threshold to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio;

[0009] Performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing correlation impact analysis on the related data to obtain a variable coefficient;

[0010] A biosafety laboratory energy efficiency optimization model is constructed according to the optimization rate and the variable coefficient, the biosafety laboratory energy efficiency optimization model is optimized, the data to be optimized is input into the biosafety laboratory energy efficiency optimization model, and the optimization result is output.

[0011] Collecting simulation data and related data of a simulated biosafety laboratory, and preprocessing the simulation data and the related data;

[0012] Comparing and clustering the simulation data according to the energy efficiency threshold to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio;

[0013] Performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing correlation impact analysis on the related data to obtain a variable coefficient;

[0014] A biosafety laboratory energy efficiency optimization model is constructed according to the optimization rate and the variable coefficient, the biosafety laboratory energy efficiency optimization model is optimized, the data to be optimized is input into the biosafety laboratory energy efficiency optimization model, and the optimization result is output.

[0015] Furthermore, the method of obtaining grouped data by comparing and clustering the simulation data according to the energy efficiency threshold includes:

[0016] Calculate the energy efficiency value based on the simulation data:

[0017]

[0018] The energy efficiency value is The unit price of the xth energy is The consumption of the xth energy at the sth moment is E x,s , the amount of energy is M1, and the weight of the vth energy efficiency evaluation index is η v , the value of the vth energy efficiency evaluation index at the sth moment is The upper limit of simulation time is T;

[0019] Cross-validation is used to obtain the energy efficiency threshold according to the energy efficiency value, and the simulation data greater than the energy efficiency threshold is used as the research data, and the non-repeated data in the research data are used to form the initial center set;

[0020] Calculate the similarity between the study data and the initial center set:

[0021]

[0022] The number of research data is P, and the number of research data for the cth simulation is P c , the number of research data in the τth initial center set is P τ , the i-th research data of the c-th simulation is u c,i , the i-th research data of the τ-th initial center set is u τ,i , the control factor is α, and the optimization coefficient is The similarity between the cth simulation research data and the τth initial center set is

[0023] The research data with the greatest similarity is used as the element of the initial center set to obtain the initial classification cluster;

[0024] Calculate the mean distance between the initial classification clusters:

[0025]

[0026] The mean distance between the initial classification clusters is The number of initial classification clusters is W, and the research data of the jth initial classification cluster is u j , the research data of the λth initial classification cluster is u λ , research data λ and research data j The distance is ds(u j ,u λ );

[0027] Compute central compactness:

[0028]

[0029] The center compactness of the jth initial classification cluster is The center point of the jth initial classification cluster is The number of elements in the jth initial classification cluster is W1;

[0030] Update the elements of the initial classification cluster by the center compactness until the center compactness reaches the maximum, and output the clustering result as grouped data, otherwise replace the initial center set.

[0031] Furthermore, the method of performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio includes:

[0032]

[0033] The upper limit of the simulation time is T, and the vth temperature barrier coefficient at the sth time is The number of elements in the grouped data is The energy efficiency value of the kth group data at the sth time is The importance of the vth group data is The contribution of the kth group data is ζ k , the energy efficiency of the cth simulation is The initial energy efficiency value of the cth group data is The energy efficiency ratio of the cth simulation is φ c .

[0034] Furthermore, the method of obtaining the optimization rate by comparing and analyzing the grouped data according to the energy efficiency ratio includes:

[0035] The comparative analysis method is used to compare the energy efficiency ratio of the grouped data and calculate the optimization rate:

[0036]

[0037] The control factor is The energy efficiency value of the kth group data is The energy efficiency value of the fth group data is The energy efficiency ratio of the kth group data is φ k , the energy efficiency ratio of the fth group data is φ f , the optimization rate of the kth group data and the fth group data is χ(k,f).

[0038] Furthermore, the method for obtaining the variable coefficient by performing correlation influence analysis on the relevant data includes:

[0039] Calculate the influence of relevant data:

[0040]

[0041] The influence of the zth related data is The initial energy efficiency value is H o , the energy efficiency value of the zth related data after the change is H z , the number of relevant data is N, the adjustment factor is γ, and the contribution of the zth relevant data to the energy efficiency change is

[0042] Calculate the correlation:

[0043]

[0044] The relevant data are The number of relevant data y is n, the correlation coefficient between relevant data y and energy efficiency value change ΔH is ρ(ΔH,y), and the control factor of relevant data y is The correlation between the zth relevant data and the energy efficiency value change ΔH is ε z (ΔH z );

[0045] The relevant data with a correlation degree greater than 0.315 are regarded as key data, and the machine learning algorithm is used to analyze the impact of key data according to energy efficiency changes;

[0046] Compute the coefficient of variation for correlated data:

[0047]

[0048] The predicted energy efficiency value of the zth related data is H z , the proportional control coefficient is ξ, and the predicted energy efficiency value is H z The probability of occurrence is Q(H z ), and the predicted energy efficiency value H zand key data z The probability is Q(H z ,y z ), the error coefficient is υ, and the variation coefficient of the zth related data is The first weight is The second weight is

[0049] Furthermore, a method for constructing a biosafety laboratory energy efficiency optimization model according to the optimization rate and the variable coefficient includes:

[0050] Construct the objective function based on the correction data:

[0051]

[0052] The control weight is The natural constant is e, and the energy efficiency of the κth simulation is The variable coefficient of the κth simulation is χ κ , the optimization rate φ of the κth simulation κ , the loss coefficient of the κth simulation is ζ κ ;

[0053] The energy efficiency optimization model of the biosafety laboratory includes decision tree algorithm, energy efficiency evaluation, and machine learning algorithm;

[0054] The decision tree algorithm classifies data based on the similarity of input data to obtain classified data;

[0055] Energy efficiency evaluation is carried out based on the classified data to obtain the energy efficiency value;

[0056] The machine learning algorithm analyzes the optimization patterns and relationships of the categorized data according to the differences in energy efficiency values, and makes predictions on the energy efficiency optimization of the biosafety laboratory based on the optimization patterns and relationships.

[0057] Furthermore, the method for optimizing the biosafety laboratory energy efficiency optimization model comprises:

[0058] Introduce the search sub-population and perform chaotic mapping on the search sub-population. The expression is:

[0059]

[0060] The chaotic random number from 0 to 1 is b, and the w+1th dimension is X w+1 , the wth dimension is X w ;

[0061] Calculate the fitness of the searcher, take the position of the particle with the largest fitness as the optimal searcher position, and update the position of the searcher. The expression is:

[0062] Za,w (t+1)=Z a,w (t)+r1·(Z a,w (t)-(Z * +β)·(1+ξ))

[0063] The random number from 1 to 2 is v1, and the position of the search sub-sub in the w-th dimension of the a-th search sub-sub in the t+1-th iteration of the exploration phase is Z a,w (t+1), the position of the searcher in the wth dimension of the ath searcher in the tth iteration is Z a,w (t), the first random number from 0 to 1 is r1, the Cauchy operator is ξ, the perturbation factor is β, and the optimal search subposition is Z * ;

[0064] Update the search sub-position according to the search area to obtain the regional position. The expression is:

[0065]

[0066] The region position of the w-th dimension of the a-th searcher in the t+1-th iteration is The decay factor is μ and the maximum number of iterations is t max , the adaptive inertia weight is l, the current number of iterations is t, the upper bound of the search area is Ub, and the lower bound of the search area is Lb;

[0067] The corrected position is obtained by using the position updated by the standard deviation, and the expression is:

[0068]

[0069] The suppression factor parameter is ω, and the standard deviation of the normal distribution random number κ is θ κ , the gamma function is The region position of the w-th dimension of the a-th searcher in the t-th iteration is The corrected position of the wth dimension of the ath searcher at the t+1th iteration is The lower bound of the w-th dimension is The upper bound of the w-th dimension is

[0070] The updated upper and lower bounds of the search area are expressed as:

[0071]

[0072] The updated upper bound of the search area is Ub * , the updated search area lower bound is Lb * ;

[0073] Iterate continuously until the maximum number of iterations is reached, then stop iterating, otherwise update the adaptive inertia weight.

[0074] The second aspect is the biosafety laboratory energy efficiency optimization system based on simulation, including:

[0075] Data acquisition module: used to collect simulation data and related data of the simulated biosafety laboratory, and pre-process the simulation data and the related data;

[0076] Cluster evaluation module: used for comparing and clustering the simulation data according to the energy efficiency threshold to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio;

[0077] Comparative analysis module: performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing correlation impact analysis on the related data to obtain a variable coefficient;

[0078] Constructing an optimization module: used to construct a biosafety laboratory energy efficiency optimization model according to the optimization rate and the variable coefficient, optimize the biosafety laboratory energy efficiency optimization model, input the data to be optimized into the biosafety laboratory energy efficiency optimization model, and output the optimization result.

[0079] The beneficial effects of the present invention are:

[0080] The present invention is a method and system for optimizing the energy efficiency of a biosafety laboratory based on simulation. Compared with the prior art, the present invention has the following technical effects:

[0081] The present invention can improve the accuracy of energy efficiency optimization of simulated biosafety laboratories through preprocessing, comparative clustering, energy efficiency evaluation, comparative analysis, correlation impact analysis, model construction and model optimization steps, thereby improving the precision of energy efficiency optimization of simulated biosafety laboratories. The energy efficiency optimization of simulated biosafety laboratories can be optimized, which can greatly save resources and improve work efficiency. It can realize intelligent optimization of the energy efficiency of biosafety laboratories and perform multi-data fusion on the energy efficiency optimization of simulated biosafety laboratories in real time. It is of great significance to the energy efficiency optimization of simulated biosafety laboratories, can adapt to energy efficiency optimization of simulated biosafety laboratories of different standards and energy efficiency optimization needs of different simulated biosafety laboratories, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 It is a flowchart of the steps of the method for optimizing the energy efficiency of a biosafety laboratory based on simulation according to the present invention; Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0083] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0084] The biosafety laboratory energy efficiency optimization method and system based on simulation of the present invention include the following steps:

[0085] like Figure 1 As shown, in this embodiment, the following steps are included:

[0086] Collecting simulation data and related data of a simulated biosafety laboratory, and preprocessing the simulation data and the related data;

[0087] In the actual assessment, the XXX biosafety laboratory was used as a simulation object, and a control group simulation data was collected;

[0088] The simulation data includes the experimenter’s operation steps, operation time, equipment used, sample collection data, storage data, processing data, transportation parameters, and biological sample test results;

[0089] Relevant data include video records of actual operations, detailed descriptions of experimental steps, operating status of equipment, fault records, maintenance logs, identity information of experimental personnel, training records, health status, source, type, quantity, storage conditions of samples, temperature, humidity, and air quality in the laboratory;

[0090] Comparing and clustering the simulation data according to the energy efficiency threshold to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio;

[0091] In the actual evaluation, the grouping data were: the operation steps, operation time, and equipment used by the experimenters in group 1, the collection data, storage data, processing data, transportation parameters, and test results of biological samples in group 2. The energy efficiency ratio of the control group was 0.241;

[0092] Performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing correlation impact analysis on the related data to obtain a variable coefficient;

[0093] In the actual evaluation, the optimization rate of the control group was 0.354, and the coefficient of variation of the control group was 0.176;

[0094] A biosafety laboratory energy efficiency optimization model is constructed according to the optimization rate and the variable coefficient, the biosafety laboratory energy efficiency optimization model is optimized, the data to be optimized is input into the biosafety laboratory energy efficiency optimization model, and the optimization result is output.

[0095] Collecting simulation data and related data of a simulated biosafety laboratory, and preprocessing the simulation data and the related data;

[0096] Comparing and clustering the simulation data according to the energy efficiency threshold to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio;

[0097] Performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing correlation impact analysis on the related data to obtain a variable coefficient;

[0098] A biosafety laboratory energy efficiency optimization model is constructed according to the optimization rate and the variable coefficient, the biosafety laboratory energy efficiency optimization model is optimized, the data to be optimized is input into the biosafety laboratory energy efficiency optimization model, and the optimization result is output.

[0099] In this embodiment, the method of obtaining grouped data by comparing and clustering the simulation data according to the energy efficiency threshold includes:

[0100] Calculate the energy efficiency value based on the simulation data:

[0101]

[0102] The energy efficiency value is The unit price of the xth energy is The consumption of the xth energy at the sth moment is E x,s , the amount of energy is M1, and the weight of the vth energy efficiency evaluation index is η v , the value of the vth energy efficiency evaluation index at the sth moment is The upper limit of simulation time is T;

[0103] Cross-validation is used to obtain the energy efficiency threshold according to the energy efficiency value, and the simulation data greater than the energy efficiency threshold is used as the research data, and the non-repeated data in the research data are used to form the initial center set;

[0104] Calculate the similarity between the study data and the initial center set:

[0105]

[0106] The number of research data is P, and the number of research data for the cth simulation is P c , the number of research data in the τth initial center set is P τ , the i-th research data of the c-th simulation is u c,i , the i-th research data of the τ-th initial center set is u τ,i , the control factor is α, and the optimization coefficient is The similarity between the cth simulation research data and the τth initial center set is

[0107] The research data with the greatest similarity is used as the element of the initial center set to obtain the initial classification cluster;

[0108] Calculate the mean distance between the initial classification clusters:

[0109]

[0110] The mean distance between the initial classification clusters is The number of initial classification clusters is W, and the research data of the jth initial classification cluster is u j , the research data of the λth initial classification cluster is u λ , research data λ and research data j The distance is ds(u j ,u λ );

[0111] Compute central compactness:

[0112]

[0113] The center compactness of the jth initial classification cluster is The center point of the jth initial classification cluster is The number of elements in the jth initial classification cluster is W1;

[0114] Update the elements of the initial classification cluster by the center compactness until the center compactness reaches the maximum, and output the clustering result as grouped data, otherwise replace the initial center set.

[0115] In this embodiment, the method of performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio includes:

[0116]

[0117] The upper limit of the simulation time is T, and the vth temperature barrier coefficient at the sth time is The number of elements in the grouped data is The energy efficiency value of the kth group data at the sth time is The importance of the vth group data is The contribution of the kth group data is ζ k , the energy efficiency of the cth simulation is The initial energy efficiency value of the cth group data is The energy efficiency ratio of the cth simulation is φ c .

[0118] In this embodiment, the method for obtaining an optimization rate by performing comparative analysis on the grouped data according to the energy efficiency ratio includes:

[0119] The comparative analysis method is used to compare the energy efficiency ratio of the grouped data and calculate the optimization rate:

[0120]

[0121] The control factor is The energy efficiency value of the kth group data is The energy efficiency value of the fth group data is The energy efficiency ratio of the kth group data is φ k , the energy efficiency ratio of the fth group data is φ f , the optimization rate of the kth group data and the fth group data is χ(k,f).

[0122] In this embodiment, the method for obtaining the variable coefficient by performing correlation influence analysis on the relevant data includes:

[0123] Calculate the influence of relevant data:

[0124]

[0125] The influence of the zth related data is The initial energy efficiency value is H o , the energy efficiency value of the zth related data after the change is H z , the number of relevant data is N, the adjustment factor is γ, and the contribution of the zth relevant data to the energy efficiency change is

[0126] Calculate the correlation:

[0127]

[0128] The relevant data are The number of relevant data y is n, the correlation coefficient between relevant data y and energy efficiency value change ΔH is ρ(ΔH,y), and the control factor of relevant data y is The correlation between the zth relevant data and the energy efficiency value change ΔH is ε z (ΔH z );

[0129] The relevant data with a correlation degree greater than 0.315 are regarded as key data, and the machine learning algorithm is used to analyze the impact of key data according to energy efficiency changes;

[0130] Compute the coefficient of variation for correlated data:

[0131]

[0132] The predicted energy efficiency value of the zth related data is H z , the proportional control coefficient is ξ, and the predicted energy efficiency value is H zThe probability of occurrence is Q(H z ), and the predicted energy efficiency value H z and key data z The probability is Q(H z ,y z ), the error coefficient is υ, and the variation coefficient of the zth related data is The first weight is The second weight is

[0133] In this embodiment, the method for constructing a biosafety laboratory energy efficiency optimization model according to the optimization rate and the variable coefficient includes:

[0134] Construct the objective function based on the correction data:

[0135]

[0136] The control weight is The natural constant is e, and the energy efficiency of the κth simulation is The variable coefficient of the κth simulation is χ κ , the optimization rate φ of the κth simulation κ , the loss coefficient of the κth simulation is ζ κ ;

[0137] The energy efficiency optimization model of the biosafety laboratory includes decision tree algorithm, energy efficiency evaluation, and machine learning algorithm;

[0138] The decision tree algorithm classifies data based on the similarity of input data to obtain classified data;

[0139] Energy efficiency evaluation is carried out based on the classified data to obtain the energy efficiency value;

[0140] The machine learning algorithm analyzes the optimization patterns and relationships of the categorized data according to the differences in energy efficiency values, and makes predictions on the energy efficiency optimization of the biosafety laboratory based on the optimization patterns and relationships.

[0141] In this embodiment, the method for optimizing the biosafety laboratory energy efficiency optimization model includes:

[0142] Introduce the search sub-population and perform chaotic mapping on the search sub-population. The expression is:

[0143]

[0144] The chaotic random number from 0 to 1 is b, and the w+1th dimension is X w+1 , the wth dimension is X w ;

[0145] Calculate the fitness of the searcher, take the position of the particle with the largest fitness as the optimal searcher position, and update the position of the searcher. The expression is:

[0146] Z a,w (t+1)=Z a,w (t)+r1·(Z a,w (t)-(Z * +β)·(1+ξ))

[0147] The random number from 1 to 2 is v1, and the position of the search sub-sub in the w-th dimension of the a-th search sub-sub in the t+1-th iteration of the exploration phase is Z a,w (t+1), the position of the searcher in the wth dimension of the ath searcher in the tth iteration is Z a,w (t), the first random number from 0 to 1 is r1, the Cauchy operator is ξ, the perturbation factor is β, and the optimal search subposition is Z * ;

[0148] Update the search sub-position according to the search area to obtain the regional position. The expression is:

[0149]

[0150] The region position of the w-th dimension of the a-th searcher in the t+1-th iteration is The decay factor is μ and the maximum number of iterations is t max , the adaptive inertia weight is l, the current number of iterations is t, the upper bound of the search area is Ub, and the lower bound of the search area is Lb;

[0151] The corrected position is obtained by using the position updated by the standard deviation, and the expression is:

[0152]

[0153] The suppression factor parameter is ω, and the standard deviation of the normal distribution random number κ is θ κ , the gamma function is The region position of the w-th dimension of the a-th searcher in the t-th iteration is The corrected position of the wth dimension of the ath searcher at the t+1th iteration is The lower bound of the w-th dimension is The upper bound of the w-th dimension is

[0154] The updated upper and lower bounds of the search area are expressed as:

[0155]

[0156] The updated upper bound of the search area is Ub * , the updated search area lower bound is Lb* ;

[0157] Iterate continuously until the maximum number of iterations is reached, then stop iterating, otherwise update the adaptive inertia weight.

[0158] The second aspect is the biosafety laboratory energy efficiency optimization system based on simulation, including:

[0159] Data acquisition module: used to collect simulation data and related data of the simulated biosafety laboratory, and pre-process the simulation data and the related data;

[0160] Cluster evaluation module: used for comparing and clustering the simulation data according to the energy efficiency threshold to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio;

[0161] Comparative analysis module: performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing correlation impact analysis on the related data to obtain a variable coefficient;

[0162] Constructing an optimization module: used to construct a biosafety laboratory energy efficiency optimization model according to the optimization rate and the variable coefficient, optimize the biosafety laboratory energy efficiency optimization model, input the data to be optimized into the biosafety laboratory energy efficiency optimization model, and output the optimization result.

[0163] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A biosafety laboratory energy efficiency optimization method based on simulation, characterized in that: The following steps are involved: Collecting simulation data and related data of a simulated biosafety laboratory, and preprocessing the simulation data and the related data; Comparing and clustering the simulation data according to the energy efficiency threshold to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio; Performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing correlation impact analysis on the related data to obtain a variable coefficient; A biosafety laboratory energy efficiency optimization model is constructed according to the optimization rate and the variable coefficient, the biosafety laboratory energy efficiency optimization model is optimized, the data to be optimized is input into the biosafety laboratory energy efficiency optimization model, and the optimization result is output.

2. The method for optimizing the energy efficiency of a biosafety laboratory based on simulation according to claim 1, characterized in that: The method of obtaining grouped data by comparing and clustering the simulation data according to the energy efficiency threshold comprises: Calculate the energy efficiency value based on the simulation data: The energy efficiency value is The unit price of the xth energy is The consumption of the xth energy at the sth moment is E x,s , the amount of energy is M1, and the weight of the vth energy efficiency evaluation index is η v , the value of the vth energy efficiency evaluation index at the sth moment is The upper limit of simulation time is T; Cross-validation is used to obtain the energy efficiency threshold according to the energy efficiency value, and the simulation data greater than the energy efficiency threshold is used as the research data, and the non-repeated data in the research data are used to form the initial center set; Calculate the similarity between the study data and the initial center set: The number of research data is P, and the number of research data for the cth simulation is P c , the number of research data in the τth initial center set is P τ , the i-th research data of the c-th simulation is u c,i , the i-th research data of the τ-th initial center set is u τ,i , the control factor is α, and the optimization coefficient is The similarity between the cth simulation research data and the τth initial center set is The research data with the greatest similarity is used as the element of the initial center set to obtain the initial classification cluster; Calculate the mean distance between the initial classification clusters: The mean distance between the initial classification clusters is The number of initial classification clusters is W, and the research data of the jth initial classification cluster is u j , the research data of the λth initial classification cluster is u λ , research data λ and research data j The distance is ds(u j ,u λ ); Compute central compactness: The center compactness of the jth initial classification cluster is The center point of the jth initial classification cluster is The number of elements in the jth initial classification cluster is W1; Update the elements of the initial classification cluster by the center compactness until the center compactness reaches the maximum, and output the clustering result as grouped data, otherwise replace the initial center set.

3. The method for optimizing the energy efficiency of a biosafety laboratory based on simulation according to claim 1, characterized in that: The method of performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio includes: The upper limit of the simulation time is T, and the vth temperature barrier coefficient at the sth time is ρ &,v , the number of elements of the grouped data is The energy efficiency value of the kth group data at the sth time is The importance of the vth group data is The contribution of the kth group data is ζ k , the energy efficiency of the cth simulation is The initial energy efficiency value of the cth group data is The energy efficiency ratio of the cth simulation is φ c .

4. The method for optimizing the energy efficiency of a biosafety laboratory based on simulation according to claim 1, characterized in that: The method for obtaining an optimization rate by comparing and analyzing the grouped data according to the energy efficiency ratio includes: The comparative analysis method is used to compare the energy efficiency ratio of the grouped data and calculate the optimization rate: The control factor is The energy efficiency value of the kth group data is The energy efficiency value of the fth group data is The energy efficiency ratio of the kth group data is φ k , the energy efficiency ratio of the fth group data is φ f , the optimization rate of the kth group data and the fth group data is χ(k,f).

5. The method for optimizing the energy efficiency of a biosafety laboratory based on simulation according to claim 1, characterized in that: The method for obtaining the variable coefficient by performing correlation influence analysis on the relevant data includes: Calculate the influence of relevant data: The influence of the zth related data is The initial energy efficiency value is H o , the energy efficiency value of the zth related data after the change is H z , the number of relevant data is N, the adjustment factor is γ, and the contribution of the zth relevant data to the energy efficiency change is Calculate the correlation: The relevant data are The number of relevant data y is n, the correlation coefficient between relevant data y and energy efficiency value change ΔH is ρ(ΔH,y), and the control factor of relevant data y is The correlation between the zth relevant data and the energy efficiency value change ΔH is ε z (ΔH z ); The relevant data with a correlation degree greater than 0.315 are regarded as key data, and the machine learning algorithm is used to analyze the impact of key data according to energy efficiency changes; Compute the coefficient of variation for correlated data: The predicted energy efficiency value of the zth related data is H z , the proportional control coefficient is ξ, and the predicted energy efficiency value is H z The probability of occurrence is Q(H z ), and the predicted energy efficiency value H z and key data z The probability is Q(H z ,y z ), the error coefficient is υ, and the variation coefficient of the zth related data is The first weight is The second weight is 6. The method for optimizing the energy efficiency of a biosafety laboratory based on simulation according to claim 1, characterized in that: The method for constructing a biosafety laboratory energy efficiency optimization model according to the optimization rate and the variable coefficient comprises: Construct the objective function based on the correction data: The control weight is The natural constant is e, and the energy efficiency of the κth simulation is The variable coefficient of the κth simulation is χ κ , the optimization rate φ of the κth simulation κ , the loss coefficient of the κth simulation is ζ κ ; The energy efficiency optimization model of the biosafety laboratory includes decision tree algorithm, energy efficiency evaluation, and machine learning algorithm; The decision tree algorithm classifies data based on the similarity of input data to obtain classified data; Energy efficiency evaluation is carried out based on the classified data to obtain the energy efficiency value; The machine learning algorithm analyzes the optimization patterns and relationships of the categorized data according to the differences in energy efficiency values, and makes predictions on the energy efficiency optimization of the biosafety laboratory based on the optimization patterns and relationships.

7. The method for optimizing the energy efficiency of a biosafety laboratory based on simulation according to claim 1, characterized in that: The method for optimizing the biosafety laboratory energy efficiency optimization model comprises: Introduce the search sub-population and perform chaotic mapping on the search sub-population. The expression is: The chaotic random number from 0 to 1 is b, and the w+1th dimension is X w+1 , the wth dimension is X w ; Calculate the fitness of the searcher, take the position of the particle with the largest fitness as the optimal searcher position, and update the position of the searcher. The expression is: Z a,w (t+1)=Z a，w (t)+r1·(Z a,w (t)-(Z * +β)·(1+ξ)) The random number from 1 to 2 is v1, and the position of the search sub-sub in the w-th dimension of the a-th search sub-sub in the t+1-th iteration of the exploration phase is Z a ,w(t+1), the position of the searcher in the wth dimension of the ath searcher in the tth iteration is Z a ,w(t), the first random number from 0 to 1 is r1, the Cauchy operator is ξ, the perturbation factor is β, and the optimal search subposition is Z*; Update the search sub-position according to the search area to obtain the regional position. The expression is: The region position of the w-th dimension of the a-th searcher in the t+1-th iteration is The decay factor is μ and the maximum number of iterations is t max , the adaptive inertia weight is l, the current number of iterations is t, the upper bound of the search area is Ub, and the lower bound of the search area is Lb; The corrected position is obtained by using the position updated by the standard deviation, and the expression is: The suppression factor parameter is ω, and the standard deviation of the normal distribution random number κ is θ κ , the gamma function is The region position of the w-th dimension of the a-th searcher in the t-th iteration is The corrected position of the wth dimension of the ath searcher at the t+1th iteration is The lower bound of the w-th dimension is The upper bound of the w-th dimension is The updated upper and lower bounds of the search area are expressed as: The updated upper bound of the search area is Ub * , the updated search area lower bound is Lb * ; Iterate continuously until the maximum number of iterations is reached, then stop iterating, otherwise update the adaptive inertia weight.

8. A biosafety laboratory energy efficiency optimization system based on simulation, used to execute the method described in any one of claims 1 to 7, characterized in that: include: Data acquisition module: used to collect simulation data and related data of the simulated biosafety laboratory, and pre-process the simulation data and the related data; Cluster evaluation module: used for comparing and clustering the simulation data according to the energy efficiency threshold to obtain grouped data, and performing energy efficiency evaluation on the grouped data to obtain an energy efficiency ratio; Comparative analysis module: performing comparative analysis on the grouped data according to the energy efficiency ratio to obtain an optimization rate, and performing correlation impact analysis on the related data to obtain a variable coefficient; Constructing an optimization module: used to construct a biosafety laboratory energy efficiency optimization model according to the optimization rate and the variable coefficient, optimize the biosafety laboratory energy efficiency optimization model, input the data to be optimized into the biosafety laboratory energy efficiency optimization model, and output the optimization result.

Images