CN114202212A - Chemical defense equipment data acquisition and analysis evaluation method and system - Google Patents
Chemical defense equipment data acquisition and analysis evaluation method and system Download PDFInfo
- Publication number
- CN114202212A CN114202212A CN202111534151.1A CN202111534151A CN114202212A CN 114202212 A CN114202212 A CN 114202212A CN 202111534151 A CN202111534151 A CN 202111534151A CN 114202212 A CN114202212 A CN 114202212A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- data
- test
- index
- questionnaire
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention provides a method and a system for data acquisition, analysis and evaluation of chemical defense equipment, and belongs to the technical field of data analysis and processing. The method comprises the following steps: acquiring an index system established according to a chemical defense equipment test outline; determining a data item and a questionnaire question bank collected in a test link according to an index system; acquiring test data acquired based on data items acquired in a test link and questionnaire data acquired based on a questionnaire question bank; carrying out multi-dimensional query statistics on the preprocessed test data and questionnaire data, and verifying the integrity and accuracy of the test data and questionnaire data; the verified test data and questionnaire data are associated and bound with the final-stage index of the index system to obtain a binding relationship; evaluating chemical defense equipment according to the binding relationship and the index weight to obtain an evaluation result; and acquiring and dynamically adjusting the index weight according to the evaluation results obtained by the plurality of test units, and regenerating new evaluation results. The invention can carry out scientific and effective evaluation on chemical defense equipment.
Description
Technical Field
The invention relates to the technical field of data analysis and processing, in particular to a method and a system for data acquisition, analysis and evaluation of chemical defense equipment.
Background
In recent years, with the continuous distribution of troops by a batch of novel chemical defense equipment, a new outline also puts new requirements on daily combat readiness training of our army. By applying the chemical defense equipment, officers and soldiers can quickly break through the obstacles and preserve the fighting capacity in chemical defense training. Therefore, the chemical defense equipment plays a role in playing a great role in modern combat. Meanwhile, the chemical defense equipment has a plurality of application scenes in each team, and the quantity is large, so that the related test data quantity is large, and the processing difficulty is large.
In order to evaluate and test newly developed chemical defense equipment, an effective and feasible evaluation method is needed, the performance advantages and the disadvantages of the chemical defense equipment and the function and the structural design which need to be improved are found through the evaluation and test, effective reference data are provided for the subsequent research and development of the chemical defense equipment, and therefore all index performances of the newly developed chemical defense equipment are improved.
However, an effective and feasible chemical defense equipment performance evaluation analysis method is not available at present.
Disclosure of Invention
Therefore, the technical problem to be solved by the embodiments of the present invention is to overcome the defect that the existing technology lacks an effective and feasible chemical defense equipment performance evaluation analysis method, thereby providing a chemical defense equipment data acquisition and analysis evaluation method and system.
Therefore, the invention provides a chemical defense equipment data acquisition and analysis evaluation method, which comprises the following steps:
acquiring an index system established according to a chemical defense equipment test outline;
determining a data item and a questionnaire question bank collected in a test link according to the index system;
acquiring test data acquired based on the data items acquired in the test link and questionnaire data acquired based on the questionnaire question bank;
preprocessing the test data and the questionnaire data;
carrying out multi-dimensional query statistics on the preprocessed test data and questionnaire data, and verifying the integrity and accuracy of the test data and the questionnaire data;
the verified test data and questionnaire data are associated and bound with the final-stage index of an index system to obtain a binding relationship;
evaluating chemical defense equipment according to the binding relationship and the determined index weight to obtain an evaluation result;
and acquiring and dynamically adjusting the index weight according to the evaluation results obtained by the plurality of test units, and regenerating new evaluation results.
Optionally, the preprocessing the test data and the questionnaire data includes:
and performing data screening and/or data cleaning and filtering on the test data and the questionnaire data.
Optionally, the associating and binding the verified test data and questionnaire data with the final-stage indicator of the indicator system to obtain a binding relationship, including:
s61: determining the incidence relation between each test link acquisition data item and each questionnaire question in the questionnaire question library and the final-stage index of the index system according to the test outline, wherein the incidence relation comprises a one-to-one incidence relation and a many-to-one incidence relation;
s62: processing the test data according to the evaluation standards of the data items collected in different test links according to the test outline and expert evaluation, assigning values to different final-stage indexes in the index system, and judging the evaluation level space to which the test data belongs;
s63: and processing the questionnaire data according to different final-stage index data source standards according to the test outline and expert evaluation, and judging that the statistics of questionnaire question options are assigned to the membership matrix of the final-stage index.
Optionally, the evaluating the chemical defense equipment according to the binding relationship and the determined indicator weight to obtain an evaluation result includes:
determining a scoring standard, the number of evaluation levels and the index weight according to the test outline and the data structures of the test data and the questionnaire data;
aiming at the chemical defense equipment, an evaluation value matrix D is obtained:
wherein d isijIndicating the evaluation score of the jth expert on the ith index for the chemical defense equipment,i＝1,2,3,…,n，j＝1,2,3,…,m；
converting the evaluation value matrix into a membership weight evaluation matrix R by using a membership function;
and performing evaluation calculation by combining the membership weight evaluation matrix to obtain an evaluation result.
Optionally, the converting the evaluation value matrix into a membership weight evaluation matrix by using a membership function includes:
calculating the membership X of the ith index belonging to the ith evaluation gradei,l：
Wherein f is a membership function;
calculating the membership weight R of the ith index belonging to the ith evaluation leveli,l：
Wherein Z is the number of the evaluation grades;
obtaining a membership weight evaluation matrix R consisting of membership weights of n indexes belonging to each evaluation level:
optionally, the performing evaluation calculation by combining the membership weight evaluation matrix includes:
obtaining an evaluation result vector according to the following formula: e ═ A1,A2,…,An)RT＝(e1,e2,…,eZ) Wherein (A)1,A2,…,An) A weight vector for each index;
and mapping the evaluation result vector to a specific evaluation value EA according to the following formula: EA ═ e1*v1,e2*v2,…,eZ*vZ) Wherein v isl＝1,2,...zThe evaluation score corresponding to the ith evaluation scale is shown.
Optionally, the obtaining and dynamically adjusting the index weight according to the evaluation results obtained by the plurality of test units, and regenerating a new evaluation result, includes:
obtaining evaluation results obtained by a plurality of test units, wherein the evaluation result of each test unit comprises evaluation values of indexes of all levels in the index system;
in the evaluation results obtained by a plurality of test units, searching the lowest evaluation value in the current-level index layer by layer from the 2 nd-level index according to the hierarchical order of the indexes, adjusting the weight of the current-level index, and re-evaluating to enable the evaluation value of each test unit to the current-level index to be close.
Optionally, the evaluating the chemical defense equipment according to the binding relationship and the determined indicator weight to obtain an evaluation result includes:
forming an input vector comprising first data and the index weight according to the binding relationship, wherein the first data comprises data obtained according to the test data and the questionnaire data;
inputting the input vector into an artificial intelligence evaluation model; the artificial intelligence evaluation model comprises a BP neural network and an extreme learning machine;
and obtaining the evaluation result according to the output of the artificial intelligence evaluation model.
Optionally, before inputting the input vector into the artificial intelligence evaluation model, the method further includes:
determining the range of the number of hidden layer nodes of the BP neural network according to the following formula:
wherein, UinNumber of nodes of input layer, U, adapted to said input vectoroutThe number of output layer nodes is equal to the number of evaluation levels, and P is the number of hidden layer nodes;
selecting one node from the range of the number of the hidden layer nodes as the number of the hidden layer nodes;
optimizing the weight and the bias value of each layer in the artificial intelligence evaluation model;
inputting training samples into the artificial intelligence evaluation model after the weight and the bias value are optimized to obtain the output of the training samples;
iteratively updating the weight and the offset value of each layer in the artificial intelligence evaluation model by adopting a Kalman filtering algorithm, and acquiring a minimum loss function value of the artificial intelligence evaluation model after training is finished;
judging whether the minimum loss function value meets a preset condition or not;
and if the minimum loss function value does not meet the preset condition, reselecting one node from the range of the hidden layer nodes as the number of the hidden layer nodes according to a preset rule, and training the artificial intelligence evaluation model after the hidden layer nodes are updated until the minimum loss function value meets the preset condition.
The invention also provides a data acquisition and analysis evaluation system for chemical defense equipment, which comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, the one or more programs cause the one or more processors to implement any of the chemical defense equipment data collection and analysis evaluation methods described above.
The technical scheme of the embodiment of the invention has the following advantages:
according to the chemical defense equipment data acquisition and analysis evaluation method and system provided by the embodiment of the invention, through determining the specific index system and setting the test link acquisition data item, questionnaire question and the like according to the index system, the pertinence of data acquisition is improved, the waste of data acquisition workload is avoided, and the accuracy and reliability of an evaluation result can be improved. By binding the test data and the questionnaire data with the indexes in the index system, specific test data and questionnaire data (such as off-road time of armed equipment of the portable mask, driving time of wearing the mask, airtightness inspection of the worn mask, once-wearing qualification rate of the mask and the like) are input as evaluation data. And calculating according to a set evaluation flow to obtain an evaluation result, thereby scientifically and effectively evaluating chemical defense equipment. In addition, the weight of each level index is dynamically adjusted according to the evaluation results of a plurality of test units, and a new evaluation result is obtained, so that the evaluation result is more objective and reliable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a specific example of a method for acquiring, analyzing, and evaluating chemical defense equipment data according to embodiment 1 of the present invention;
fig. 2 is a flowchart of a specific example of a chemical defense equipment evaluation method in embodiment 1 of the present invention;
fig. 3 is a schematic block diagram of a specific example of the chemical defense equipment data acquisition, analysis and evaluation system in embodiment 2 of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In describing the present invention, it is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises" and/or "comprising," when used in this specification, are intended to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The term "and/or" includes any and all combinations of one or more of the associated listed items. The terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," "outer," and the like are used in the orientation or positional relationship indicated in the drawings for convenience in describing the invention and for simplicity in description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be construed as limiting the invention. The terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The terms "mounted," "connected," and "coupled" are to be construed broadly and may, for example, be fixedly coupled, detachably coupled, or integrally coupled; can be mechanically or electrically connected; the two elements can be directly connected, indirectly connected through an intermediate medium, or communicated with each other inside; either a wireless or a wired connection. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The embodiment provides a method for collecting, analyzing and evaluating chemical defense equipment data, as shown in fig. 1, comprising the following steps:
s1: acquiring an index system established according to a chemical defense equipment test outline;
s2: determining a data item and a questionnaire question bank collected in a test link according to the index system;
s3: acquiring test data acquired based on the data items acquired in the test link and questionnaire data acquired based on the questionnaire question bank;
s4: preprocessing the test data and the questionnaire data;
s5: carrying out multi-dimensional query statistics on the preprocessed test data and questionnaire data, and verifying the integrity and accuracy of the test data and the questionnaire data;
s6: the verified test data and questionnaire data are associated and bound with the final-stage index of an index system to obtain a binding relationship;
s7: evaluating chemical defense equipment according to the binding relationship and the determined index weight to obtain an evaluation result;
s8: and acquiring and dynamically adjusting the index weight according to the evaluation results obtained by the plurality of test units, and regenerating new evaluation results.
In the embodiment of the invention, by determining the specific index system and setting the test link acquisition data items, questionnaire questions and the like according to the index system, the pertinence of data acquisition is improved, the waste of data acquisition workload is avoided, and the accuracy and reliability of the evaluation result can be improved. By binding the test data and the questionnaire data with the indexes in the index system, specific test data and questionnaire data (such as off-road time of armed equipment of the portable mask, driving time of wearing the mask, airtightness inspection of the worn mask, once-wearing qualification rate of the mask and the like) are input as evaluation data. And calculating according to a set evaluation flow to obtain an evaluation result, thereby scientifically and effectively evaluating chemical defense equipment. In addition, the weight of each level index is dynamically adjusted according to the evaluation results of a plurality of test units, and a new evaluation result is obtained, so that the evaluation result is more objective and reliable.
Specifically, the data items collected in the test link can be formed into a collection engineering model, and the questionnaire question bank can be formed into a questionnaire model file. After the acquisition engineering model and the questionnaire model file are generated, the acquisition engineering model and the questionnaire model file can be transmitted to a portable recording acquisition system installed on a portable recording terminal, the portable recording acquisition system loads and analyzes the received acquisition engineering model and questionnaire model file to obtain a test link acquisition data item and a questionnaire question bank, and a test link acquisition data item and questionnaire answer interface are displayed on a display screen of the portable recording terminal. And then, in a field test, recording test data corresponding to the data items acquired in the test link by using the portable recording terminal, and answering a questionnaire after the test is finished to obtain corresponding questionnaire data.
In the embodiment of the invention, the portable recording and acquiring system is configured, and the portable recording and acquiring system is installed on the portable recording terminal to acquire data on site, so that the flexibility of setting the portable recording terminal is improved, and the convenience of data acquisition is improved.
In addition, the portable recording terminal can be provided with a communication module which is in communication connection with equipment (such as an equipment acquisition data model configuration management system) for executing chemical defense equipment evaluation, so that the field recovery of field acquisition data is realized, and the accuracy and the reliability are ensured.
The data in the embodiment of the invention also comprises basic data, wherein the basic data comprises chemical defense equipment parameters, test site parameters and test personnel information parameters.
Optionally, in step S4, the preprocessing the test data and the questionnaire data includes:
and performing data screening and/or data cleaning and filtering on the test data and the questionnaire data.
According to the embodiment of the invention, the test data and the questionnaire data are preprocessed, so that the influence of abnormal extreme values on the evaluation result of the chemical defense equipment is reduced, and the accuracy and the reliability of the evaluation result are further improved.
Optionally, the associating and binding the verified test data and questionnaire data with the final-stage indicator of the indicator system to obtain a binding relationship, including:
s61: determining the incidence relation between each test link acquisition data item and each questionnaire question in the questionnaire question library and the final-stage index of the index system according to the test outline, wherein the incidence relation comprises a one-to-one incidence relation and a many-to-one incidence relation;
s62: processing the test data according to the evaluation standards of the data items collected in different test links according to the test outline and expert evaluation, assigning values to different final-stage indexes in the index system, and judging the evaluation level space to which the test data belongs;
s63: and processing the questionnaire data according to different final-stage index data source standards according to the test outline and expert evaluation, and judging that the statistics of questionnaire question options are assigned to the membership matrix of the final-stage index.
Optionally, as shown in fig. 2, in step S7, that is, the evaluating the chemical defense equipment according to the binding relationship and the determined indicator weight to obtain an evaluation result includes:
s71: determining a scoring standard, the number of evaluation levels and the index weight according to the test outline and the data structures of the test data and the questionnaire data;
specifically, the scoring criterion is a quantitative criterion of a qualitative index.
S72: aiming at the chemical defense equipment, an evaluation value matrix D is obtained:
wherein d isijRepresents the evaluation score of the jth expert on the ith index for the chemical defense equipment, i is 1,2,3, …, n, j is 1,2,3, …, m;
s73: converting the evaluation value matrix into a membership weight evaluation matrix R by using a membership function;
s74: and performing evaluation calculation by combining the membership weight evaluation matrix to obtain an evaluation result.
Optionally, the converting the evaluation value matrix into a membership weight evaluation matrix by using a membership function includes:
calculating the membership X of the ith index belonging to the ith evaluation gradei,l：
Wherein f is a membership function;
calculating the membership weight R of the ith index belonging to the ith evaluation leveli,l：
Wherein Z is the number of the evaluation grades;
in this embodiment, the membership weight of the ith index belonging to the ith evaluation level refers to the relative weight of the ith index belonging to the ith evaluation level, and the membership weight of the ith index belonging to any evaluation level can be obtained by the above method.
Obtaining a membership weight evaluation matrix R consisting of membership weights of n indexes belonging to each evaluation level:
optionally, the performing evaluation calculation by combining the membership weight evaluation matrix includes:
obtaining an evaluation result vector according to the following formula: e ═ A1,A2,…,An)RT＝(e1,e2,…,eZ) Wherein (A)1,A2,…,An) A weight vector for each index;
and mapping the evaluation result vector to a specific evaluation value EA according to the following formula: EA ═ e1*v1,e2*v2,…,ez*vz) Wherein v isl＝1,2,...ZThe evaluation score corresponding to the ith evaluation scale is shown.
Optionally, the obtaining and dynamically adjusting the index weight according to the evaluation results obtained by the plurality of test units, and regenerating a new evaluation result, includes:
obtaining evaluation results obtained by a plurality of test units, wherein the evaluation result of each test unit comprises evaluation values of indexes of all levels in the index system;
in the evaluation results obtained by a plurality of test units, searching the lowest evaluation value in the current-level index layer by layer from the 2 nd-level index according to the hierarchical order of the indexes, adjusting the weight of the current-level index, and re-evaluating to enable the evaluation value of each test unit to the current-level index to be close.
Specifically, after obtaining evaluation results obtained by a plurality of trial units, a plurality of evaluation values of the index belonging to the same hierarchy may be sorted. For example, the indexes of the respective stages may be sorted in order of evaluation value from high to low. The weight of the current-level index is adjusted, specifically, the weight of each index in the current-level index is adjusted.
In the embodiment of the invention, the evaluation results of a plurality of test units are obtained, and the weight of each level index is dynamically adjusted according to the evaluation results of the plurality of test units, so that the evaluation values of the test units are close to each other, the influence of subjective factors of expert weights is reduced, and a new evaluation result is obtained.
In other optional specific embodiments, the evaluating the chemical defense equipment according to the binding relationship and the determined indicator weight to obtain an evaluation result, that is, step S7 includes:
forming an input vector comprising first data and the index weight according to the binding relationship, wherein the first data comprises data obtained according to the test data and the questionnaire data;
inputting the input vector into an artificial intelligence evaluation model; the artificial intelligence evaluation model comprises a BP neural network and an Extreme Learning Machine (ELM);
and obtaining the evaluation result according to the output of the artificial intelligence evaluation model.
In the embodiment of the invention, the artificial intelligence evaluation model is used for analyzing the test data and the questionnaire data to obtain the evaluation result of the chemical defense equipment, so that the intellectualization of the chemical defense equipment is realized, and the evaluation efficiency, the reliability and the accuracy are higher.
Optionally, before inputting the input vector into the artificial intelligence evaluation model, the method further includes:
determining the range of the number of hidden layer nodes of the BP neural network according to the following formula:
wherein, UinNumber of nodes of input layer, U, adapted to said input vectoroutThe number of output layer nodes is equal to the number of evaluation levels, and P is the number of hidden layer nodes;
selecting one node from the range of the number of the hidden layer nodes as the number of the hidden layer nodes;
optimizing the weight and the bias value of each layer in the artificial intelligence evaluation model;
inputting training samples into the artificial intelligence evaluation model after the weight and the bias value are optimized to obtain the output of the training samples;
iteratively updating the weight and the offset value of each layer in the artificial intelligence evaluation model by adopting a Kalman filtering algorithm, and acquiring a minimum loss function value of the artificial intelligence evaluation model after training is finished;
judging whether the minimum loss function value meets a preset condition or not;
and if the minimum loss function value does not meet the preset condition, reselecting one node from the range of the hidden layer nodes as the number of the hidden layer nodes according to a preset rule, and training the artificial intelligence evaluation model after the hidden layer nodes are updated until the minimum loss function value meets the preset condition.
Wherein, the preset rule is as follows: reselecting the number of hidden layer nodes according to the following formula:
p' is the number of hidden layer nodes reselected, E is the minimum loss function value, and h () is a calculation function.
According to the embodiment of the invention, when the artificial intelligence evaluation model is constructed, the appropriate number of nodes of the hidden layer can be selected through the method, so that the convergence efficiency and effect of the artificial intelligence evaluation model during training are better, the generalization performance of the artificial intelligence evaluation model is better, and the evaluation accuracy and speed of the artificial intelligence evaluation model are higher.
Further optionally, the optimizing the weight and the bias value of each layer in the artificial intelligence evaluation model includes:
optimizing the weight and the bias value of each layer in the artificial intelligence evaluation model by using a quantum particle swarm optimization algorithm; the method specifically comprises the following steps:
initializing a population of quantum particle swarms, wherein particles in the quantum particle swarms represent weight and bias values of each layer in the artificial intelligence evaluation model;
for each particle, comparing the current fitness with the fitness of the best position which is experienced before, and if the fitness is better, updating the best position of the individual; for each particle, comparing the fitness of the individual best position with the fitness of the global best position, and if the fitness is better, updating the global best position with the individual best position; the updating rule of the quantum particle swarm optimization algorithm is as follows:
μ＝rand(0,1)
ωk(t)＝rand(0,1)
wherein p isk(t) is the attractor of the kth particle at the tth iteration, xk(t) is the current position of the kth particle at the tth iteration, pbk(t) the current individual optimal solution for the kth particle at the tth iteration, gb (t) the global optimal solution at the tth iteration, γ is the compression-expansion factor, γ1、γ2T is the preset total number of iterations for the upper and lower bounds of the compression-expansion factor.
In the embodiment of the invention, the initially constructed artificial intelligence evaluation model parameters are optimized by the method, so that the training efficiency of the model is improved.
Example 2
The present embodiment provides a chemical defense equipment data acquisition and analysis evaluation system 30, as shown in fig. 3, including:
one or more processors 301;
a storage device 302 for storing one or more programs;
the one or more programs, when executed by the one or more processors 301, cause the one or more processors 301 to implement any of the chemical defense equipment data collection and analysis evaluation methods described above in embodiment 1.
In the embodiment of the invention, by determining the specific index system and setting the test link acquisition data items, questionnaire questions and the like according to the index system, the pertinence of data acquisition is improved, the waste of data acquisition workload is avoided, and the accuracy and reliability of the evaluation result can be improved. By binding the test data and the questionnaire data with the indexes in the index system, specific test data and questionnaire data (such as off-road time of armed equipment of the portable mask, driving time of wearing the mask, airtightness inspection of the worn mask, once-wearing qualification rate of the mask and the like) are input as evaluation data. And calculating according to a set evaluation flow to obtain an evaluation result, thereby scientifically and effectively evaluating chemical defense equipment. In addition, the weight of each level index is dynamically adjusted according to the evaluation results of a plurality of test units, and a new evaluation result is obtained, so that the evaluation result is more objective and reliable.
Specifically, the chemical defense equipment data acquisition and analysis and evaluation system in this embodiment may be an equipment acquisition data model configuration management system.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A chemical defense equipment data acquisition and analysis evaluation method is characterized by comprising the following steps:
acquiring an index system established according to a chemical defense equipment test outline;
determining a data item and a questionnaire question bank collected in a test link according to the index system;
acquiring test data acquired based on the data items acquired in the test link and questionnaire data acquired based on the questionnaire question bank;
preprocessing the test data and the questionnaire data;
carrying out multi-dimensional query statistics on the preprocessed test data and questionnaire data, and verifying the integrity and accuracy of the test data and the questionnaire data;
the verified test data and questionnaire data are associated and bound with the final-stage index of an index system to obtain a binding relationship;
evaluating chemical defense equipment according to the binding relationship and the determined index weight to obtain an evaluation result;
and acquiring and dynamically adjusting the index weight according to the evaluation results obtained by the plurality of test units, and regenerating new evaluation results.
2. The method of claim 1, wherein the pre-processing the test data and the questionnaire data comprises:
and performing data screening and/or data cleaning and filtering on the test data and the questionnaire data.
3. The method according to claim 1, wherein the step of binding the verified test data and questionnaire data with the final index of the index system in an associated manner to obtain a binding relationship comprises:
s61: determining the incidence relation between each test link acquisition data item and each questionnaire question in the questionnaire question library and the final-stage index of the index system according to the test outline, wherein the incidence relation comprises a one-to-one incidence relation and a many-to-one incidence relation;
s62: processing the test data according to the evaluation standards of the data items collected in different test links according to the test outline and expert evaluation, assigning values to different final-stage indexes in the index system, and judging the evaluation level space to which the test data belongs;
s63: and processing the questionnaire data according to different final-stage index data source standards according to the test outline and expert evaluation, and judging that the statistics of questionnaire question options are assigned to the membership matrix of the final-stage index.
4. The method according to claim 1 or 3, wherein the evaluating the chemical defense equipment according to the binding relationship and the determined indicator weight to obtain an evaluation result comprises:
determining a scoring standard, the number of evaluation levels and the index weight according to the test outline and the data structures of the test data and the questionnaire data;
aiming at the chemical defense equipment, an evaluation value matrix D is obtained:
wherein d isijRepresents the evaluation score of the jth expert on the ith index for the chemical defense equipment, i is 1,2,3, and n, j is 1,2,3,. and m;
converting the evaluation value matrix into a membership weight evaluation matrix R by using a membership function;
and performing evaluation calculation by combining the membership weight evaluation matrix to obtain an evaluation result.
5. The method of claim 4, wherein transforming the matrix of merit values into a matrix of membership-weighted merit values using a membership function comprises:
calculating the membership X of the ith index belonging to the ith evaluation gradei，l：
Wherein f is a membership function;
calculating the membership weight R of the ith index belonging to the ith evaluation leveli，l：
Wherein Z is the number of the evaluation grades;
obtaining a membership weight evaluation matrix R consisting of membership weights of n indexes belonging to each evaluation level:
6. the method of claim 5, wherein the performing an evaluation calculation in conjunction with the membership weight evaluation matrix comprises:
obtaining an evaluation result vector according to the following formula: e ═ A1，A2，…，An)RT＝(e1，e2，…，eZ) Wherein (A)1，A2，…，An) Is one by oneA weight vector for each index;
and mapping the evaluation result vector to a specific evaluation value EA according to the following formula: EA ═ e1*v1，e2*v2，…，eZ*vZ) Wherein v isl＝1，2，…ZThe evaluation score corresponding to the ith evaluation scale is shown.
7. The method according to claim 1, wherein the obtaining and dynamically adjusting the index weight according to the evaluation results obtained by the plurality of test units to regenerate new evaluation results comprises:
obtaining evaluation results obtained by a plurality of test units, wherein the evaluation result of each test unit comprises evaluation values of indexes of all levels in the index system;
in the evaluation results obtained by a plurality of test units, searching the lowest evaluation value in the current-level index layer by layer from the 2 nd-level index according to the hierarchical order of the indexes, adjusting the weight of the current-level index, and re-evaluating to enable the evaluation value of each test unit to the current-level index to be close.
8. The method of claim 1, wherein the evaluating the chemical defense equipment according to the binding relationship and the determined indicator weight to obtain an evaluation result comprises:
forming an input vector comprising first data and the index weight according to the binding relationship, wherein the first data comprises data obtained according to the test data and the questionnaire data;
inputting the input vector into an artificial intelligence evaluation model; the artificial intelligence evaluation model comprises a BP neural network and an extreme learning machine;
and obtaining the evaluation result according to the output of the artificial intelligence evaluation model.
9. The method of claim 8, wherein prior to inputting the input vector into an artificial intelligence evaluation model, further comprising:
determining the range of the number of hidden layer nodes of the BP neural network according to the following formula:
wherein, UinNumber of nodes of input layer, U, adapted to said input vectoroutThe number of output layer nodes is equal to the number of evaluation levels, and P is the number of hidden layer nodes;
selecting one node from the range of the number of the hidden layer nodes as the number of the hidden layer nodes;
optimizing the weight and the bias value of each layer in the artificial intelligence evaluation model;
inputting training samples into the artificial intelligence evaluation model after the weight and the bias value are optimized to obtain the output of the training samples;
iteratively updating the weight and the offset value of each layer in the artificial intelligence evaluation model by adopting a Kalman filtering algorithm, and acquiring a minimum loss function value of the artificial intelligence evaluation model after training is finished;
judging whether the minimum loss function value meets a preset condition or not;
and if the minimum loss function value does not meet the preset condition, reselecting one node from the range of the hidden layer nodes as the number of the hidden layer nodes according to a preset rule, and training the artificial intelligence evaluation model after the hidden layer nodes are updated until the minimum loss function value meets the preset condition.
10. The utility model provides a chemical defense equipment data acquisition and analysis evaluation system which characterized in that includes:
one or more processors;
storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the chemical defense equipment data collection and analysis evaluation method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111534151.1A CN114202212A (en) | 2021-12-15 | 2021-12-15 | Chemical defense equipment data acquisition and analysis evaluation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111534151.1A CN114202212A (en) | 2021-12-15 | 2021-12-15 | Chemical defense equipment data acquisition and analysis evaluation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114202212A true CN114202212A (en) | 2022-03-18 |
Family
ID=80653994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111534151.1A Pending CN114202212A (en) | 2021-12-15 | 2021-12-15 | Chemical defense equipment data acquisition and analysis evaluation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114202212A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115186013A (en) * | 2022-07-25 | 2022-10-14 | 中国人民解放军陆军航空兵学院 | Data acquisition and analysis method based on aviation equipment |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020429A (en) * | 2012-11-27 | 2013-04-03 | 浙江工业职业技术学院 | Comprehensive decision-making and evaluating method for health condition of tied-arch bridge |
| CN104835103A (en) * | 2015-05-11 | 2015-08-12 | 大连理工大学 | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation |
| CN106547961A (en) * | 2016-10-20 | 2017-03-29 | 西北工业大学 | Civil aircraft main cabin comfortableness method for quantitatively evaluating |
| CN106919784A (en) * | 2017-01-19 | 2017-07-04 | 上海隧道工程有限公司 | A kind of shield tunnel military service method of evaluating performance based on variable weight |
| CN107045490A (en) * | 2017-05-09 | 2017-08-15 | 衢州学院 | A kind of method for estimating state of nonlinear system |
| CN107194519A (en) * | 2017-06-16 | 2017-09-22 | 内蒙古科技大学 | A kind of dangerous critical level pre-judging method in goaf |
| CN109190143A (en) * | 2018-07-11 | 2019-01-11 | 北京晶品镜像科技有限公司 | A kind of network-enabled intelligent ammunition multi-scheme appraisal procedure based on operation l-G simulation test |
| CN109543939A (en) * | 2018-10-11 | 2019-03-29 | 北京信息科技大学 | A kind of method of green building productions certification risk evaluation model building |
| CN109614729A (en) * | 2018-12-18 | 2019-04-12 | 上海机电工程研究所 | A kind of equipment Efficacy assessment result rapid analysis method based on meta-model |
| CN110084324A (en) * | 2019-05-10 | 2019-08-02 | 杭州电子科技大学 | Kalman filtering parameter adaptive update method based on extreme learning machine |
| CN110174878A (en) * | 2019-05-20 | 2019-08-27 | 苏州肯博思智能科技有限公司 | A kind of unmanned intelligence equipment is healthy and ensures integrated management general-purpose system |
| CN111626646A (en) * | 2020-07-07 | 2020-09-04 | 中国人民解放军陆军防化学院 | Equipment integrity check information fusion method |
| CN112215446A (en) * | 2019-07-10 | 2021-01-12 | 小蜜蜂互联（北京）消防信息技术有限公司 | Neural network-based unit dynamic fire risk assessment method |
| CN113391621A (en) * | 2021-06-23 | 2021-09-14 | 哈尔滨工业大学 | Health state evaluation method of electric simulation test turntable |
-
2021
- 2021-12-15 CN CN202111534151.1A patent/CN114202212A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020429A (en) * | 2012-11-27 | 2013-04-03 | 浙江工业职业技术学院 | Comprehensive decision-making and evaluating method for health condition of tied-arch bridge |
| CN104835103A (en) * | 2015-05-11 | 2015-08-12 | 大连理工大学 | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation |
| CN106547961A (en) * | 2016-10-20 | 2017-03-29 | 西北工业大学 | Civil aircraft main cabin comfortableness method for quantitatively evaluating |
| CN106919784A (en) * | 2017-01-19 | 2017-07-04 | 上海隧道工程有限公司 | A kind of shield tunnel military service method of evaluating performance based on variable weight |
| CN107045490A (en) * | 2017-05-09 | 2017-08-15 | 衢州学院 | A kind of method for estimating state of nonlinear system |
| CN107194519A (en) * | 2017-06-16 | 2017-09-22 | 内蒙古科技大学 | A kind of dangerous critical level pre-judging method in goaf |
| CN109190143A (en) * | 2018-07-11 | 2019-01-11 | 北京晶品镜像科技有限公司 | A kind of network-enabled intelligent ammunition multi-scheme appraisal procedure based on operation l-G simulation test |
| CN109543939A (en) * | 2018-10-11 | 2019-03-29 | 北京信息科技大学 | A kind of method of green building productions certification risk evaluation model building |
| CN109614729A (en) * | 2018-12-18 | 2019-04-12 | 上海机电工程研究所 | A kind of equipment Efficacy assessment result rapid analysis method based on meta-model |
| CN110084324A (en) * | 2019-05-10 | 2019-08-02 | 杭州电子科技大学 | Kalman filtering parameter adaptive update method based on extreme learning machine |
| CN110174878A (en) * | 2019-05-20 | 2019-08-27 | 苏州肯博思智能科技有限公司 | A kind of unmanned intelligence equipment is healthy and ensures integrated management general-purpose system |
| CN112215446A (en) * | 2019-07-10 | 2021-01-12 | 小蜜蜂互联（北京）消防信息技术有限公司 | Neural network-based unit dynamic fire risk assessment method |
| CN111626646A (en) * | 2020-07-07 | 2020-09-04 | 中国人民解放军陆军防化学院 | Equipment integrity check information fusion method |
| CN113391621A (en) * | 2021-06-23 | 2021-09-14 | 哈尔滨工业大学 | Health state evaluation method of electric simulation test turntable |
Non-Patent Citations (3)
| Title |
|---|
| 孟庆均 等: ""装备在役考核评估指标体系"", 《装甲兵工程学院学报》, vol. 32, no. 1, 28 February 2018 (2018-02-28) * |
| 张杰 等著: "《效能评估方法研究》", 31 July 2009, pages: 3 * |
| 徐强 等: ""基于 Fuzzy-AHP 的武器装备作战试验鉴定指标体系评估"", 《火力与指挥控制》, vol. 46, no. 7, 31 July 2021 (2021-07-31) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115186013A (en) * | 2022-07-25 | 2022-10-14 | 中国人民解放军陆军航空兵学院 | Data acquisition and analysis method based on aviation equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107578104B (en) | A kind of Chinese Traditional Medicine knowledge system | |
| CN110472817A (en) | A kind of XGBoost of combination deep neural network integrates credit evaluation system and its method | |
| CN112859822B (en) | Equipment health analysis and fault diagnosis method and system based on artificial intelligence | |
| CN110533067A (en) | The end-to-end Weakly supervised object detection method that frame based on deep learning returns | |
| CN110221965A (en) | Test cases technology, test method, device, equipment and system | |
| CN113012811B (en) | Traditional Chinese medicine syndrome diagnosis and health evaluation method combining deep convolutional network and graph neural network | |
| CN108241964A (en) | Capital construction scene management and control mobile solution platform based on BP artificial nerve network model algorithms | |
| CN107491992B (en) | Intelligent service recommendation method based on cloud computing | |
| CN103886030B (en) | Cost-sensitive decision-making tree based physical information fusion system data classification method | |
| CN110348490A (en) | A kind of soil quality prediction technique and device based on algorithm of support vector machine | |
| CN109711424A (en) | A kind of rule of conduct acquisition methods, device and equipment based on decision tree | |
| CN110232405A (en) | Method and device for personal credit file | |
| CN114202212A (en) | Chemical defense equipment data acquisition and analysis evaluation method and system | |
| Prashanthi et al. | Plant disease detection using Convolutional neural networks | |
| CN115619271A (en) | Charging pile state evaluation method and device based on CNN and random forest | |
| CN106447117A (en) | Pet feeding method and system based on pet daily data analysis | |
| CN111352926A (en) | Data processing method, device, equipment and readable storage medium | |
| CN111382807B (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN109145431A (en) | A kind of modeling method and device monitoring electric power secondary system operating status | |
| CN116680633B (en) | Abnormal user detection method, system and storage medium based on multitask learning | |
| CN102779241B (en) | PPI (Point-Point Interaction) network clustering method based on artificial swarm reproduction mechanism | |
| Zhang et al. | Three-way group decisions with incomplete spherical fuzzy information for treating parkinson’s disease using IoMT devices | |
| CN110910263A (en) | Grain condition monitoring method based on GA-BP neural network | |
| CN112183292B (en) | Method for extracting drought phenotype and evaluating drought resistance of field crops based on low-altitude remote sensing | |
| CN115169675A (en) | Consequence study and judgment based emergency resource allocation method and system for narrow non-exposed space |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 327, third floor, No. 2, Stadium South Road, Shijingshan District, Beijing 100043 Applicant after: Beijing Zhongke Zhiyi Technology Co.,Ltd. Address before: Room 330, third floor, No. 2, Stadium South Road, Shijingshan District, Beijing 100043 Applicant before: Beijing Zhongke Zhiyi Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 327, third floor, No. 2, Stadium South Road, Shijingshan District, Beijing 100043 Applicant after: Beijing Zhongke Zhiyi Technology Co.,Ltd. Address before: Room 327, third floor, No. 2, Stadium South Road, Shijingshan District, Beijing 100043 Applicant before: Beijing Zhongke Zhiyi Technology Co.,Ltd. |
|
| CB02 | Change of applicant information |