CN105843743A - Method for verifying correctness of actual output result of special automatic test case - Google Patents
Method for verifying correctness of actual output result of special automatic test case Download PDFInfo
- Publication number
- CN105843743A CN105843743A CN201610220057.1A CN201610220057A CN105843743A CN 105843743 A CN105843743 A CN 105843743A CN 201610220057 A CN201610220057 A CN 201610220057A CN 105843743 A CN105843743 A CN 105843743A
- Authority
- CN
- China
- Prior art keywords
- value
- output
- test
- test case
- automatic test
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a method for verifying correctness of an actual output result of a special automatic test case. According to the method, when actual data of the automatic test case are subjected to specific analysis processing, the progress of an automatic test is not influenced. The method comprises steps as follows: step 1: Bug-free data are acquired and stored in a local file; step 2: a neural network model is trained through the acquired Bug-free data; step 3: given feature vectors in m dimensions are input values from x1 to xm, the corresponding automatic test case is executed, and an actual test result Tk is obtained; step 4, the input values in the step 3 are substituted into a neural network trained in the step 2, a prediction output value ok is obtained through training of the neural network, the actual test result Tk acquired after the corresponding automatic test case is executed in the step 3 is compared with the prediction value ok output by the trained neural network, and whether Bug occurs in the test case is judged according to a comparison result delta Tk.
Description
Technical field
The present invention relates to the verification method of a kind of specific automation test case actual output result correctness, belong to
Automatic test field.
Background technology
The checking that automatic test cases performs result at present is the automatic test use in design specific function
First provide the expected result determined before example, during implementation of test cases, expected results before is entered with actual result
Row compares, if it is expected that result is identical with actual result, illustrates that this function, without Bug, otherwise illustrates that this function goes out
Existing Bug.The checking of this test case execution result is well suited for setting of the automatic test cases of known accurate result
Meter, and those test cases are performed result unforeseen test case the method and can not verify.By
In the particularity of industrial software, so this defect is particularly evident in the automatic test of industrial software.
Currently for existing automatization testing technique problems faced, it is that automatic test field is badly in need of solving
A difficult problem.And the present invention can solve problem above well.
Summary of the invention
Present invention aim at the deficiency existed for existing automatic test cases verification technique, it is provided that
A kind of correctness verification method of specific automation test case output data.The present invention is by gathering without Bug
Data train neutral net so that can calculate its expected results when designing special test case, from
And design complete test case.The present invention can solve intended automatic test cannot to use test result
The design of example.
The present invention solves its technical problem and is adopted the technical scheme that: the invention provides a kind of specific automation
The verification method of test case actual output result correctness, said method comprising the steps of:
Step 1: obtain and be stored under local file without Bug data；
Step 2: train a neural network model by the data without Bug got；
Step 3: the characteristic vector of given m dimension is input value [x1,x2,...,xi,...,xm], perform corresponding automatization
Test case obtains actual test result Tk；
Step 4: the input value in above-mentioned steps 3 is substituted in the neutral net trained in step 2,
Training through neutral net draws prediction output valve ok, then step 3 will perform corresponding automatic test
Use-case obtains actual test result TkThe predictive value o exported with the neutral net after having trainedkCompare,
By result of the comparison Δ TkJudge whether this test case Bug occurs.
Further, in the step 1 of the method for the invention, by using automated test tool to gather nothing
Bug data are stored under local file, and these data include that input value and output valve, input value therein refer to set
According to the feature of this test case during meter nominative testing use-case, the input numerical value given when edit script can also
The numerical value etc. of input when being recording interface, during execution automatic test, these input numerical value are to corresponding parameter
Assignment；Output valve refers to that this test case can also be machine in the result value of interface display after being finished
Information in the log of feedback.
Further, in step 2 of the present invention, the data obtained in step 1 are carried out neutral net
Training, i.e. set up neural network model.N the sample collected in step 1 is divided into two parts, respectively
It is training sample and test sample.The input and output value using training sample trains neutral net, uses the most again
The input and output value of test sample tests the accuracy of the neutral net trained.
Further, in step 3 of the present invention, with given data [x1,x2,...,xi,...,xm] for inputting
Value performs the automatic test cases of specific function, obtains corresponding real output value Tk。
Further, in step 4 of the present invention, the input value that described step 3 is used
[x1,x2,...,xi,...,xm] substitute in the neutral net that step 2 has trained, exported result accordingly, i.e.
Desired value o of specific automatic test casesk, by defeated for the reality performing the automatic test cases of corresponding function
Go out result TkObtain, after having trained, desired value o that system exportskContrasting, trying to achieve input value is
[x1,x2,...,xi,...,xm] time output error Δ Tk, according to error delta TkJudge whether that this is occurred in that by brake
Bug, sets threshold value μ, when error delta TkWhen exceeding threshold value μ, script is used to write Bug in test report,
And terminate the execution of this automatic test cases, continue executing with next automatic test cases；Work as error
ΔTkWhen being not above threshold value μ, continue the execution of this automatic test cases.
Beneficial effect:
1, the present invention is by carrying out neural net model establishing and training to history without Bug data so that originally cannot
The test case predicted in advance performs result and becomes measurable.
2, the present invention solves the bottleneck of special industry software automated testing, i.e. cannot obtain test case
During expected results, it is impossible to the execution result of this test case is verified.
Accompanying drawing explanation
Fig. 1 is the flow chart of the inventive method.
Fig. 2 is the schematic network structure of BP (Backpropagation) algorithm.
Detailed description of the invention
Below in conjunction with Figure of description, the invention is described in further detail.
As it is shown in figure 1, the invention provides a kind of specific automation test case actual output result correctness
Verification method, said method comprising the steps of:
Step 1: obtain and be stored under local file without Bug data；
Use automated test tool to gather the numerical value without Bug, such as use Ranorex automatic test work
Tool, quoting storage in Ranorex has the Excel of the required n bar record of test, it is assumed that in Excel, every
Record has m numerical value, i.e. characteristic vector to be m dimensions.Perform the automatic test of corresponding function, hold guaranteeing
During row automatic test cases without Bug in the case of, performing, with automatic test cases, the result that obtains is
Output valve.N the output valve storage that n bar input value in Excel and execution automatic test cases are obtained
In the file of certain format, this is that in file, storage has n sample, has (m+1) individual numerical value in each sample,
Wherein having m is input value, and 1 is output valve.
Step 2: train a neural network model by the data without Bug got；
The data obtained in step 1 are used to carry out the training of neutral net.The neutral net that this training uses
Model is the neutral net of BP algorithm.Before using neural metwork training data, it must be determined that neutral net
Structure, i.e. the number of plies of neutral net and the number of every layer of neural node.
(1) network structure of BP algorithm
Fig. 2 is aimed at the network structure of the BP algorithm of this training design.
Introduce mark: xiRepresent the input value of input layer i-th nerve node, assume in the present invention to collect
N sample, and be classified as two parts, be training sample (p) and test sample (n-p is individual) respectively,
Each of which sample there are m input value, 1 output valve, the i.e. characteristic vector of an example are
[x1,x2,…,xi,…,xm]；wijRepresent the weight between neural node i and neural node j；ojRepresent neural node
The output valve of j；θjRepresenting biasing, each of which nerve node has specific biasing.
The BP algorithm of neural network used in the present invention has one layer of input layer, one layer of hidden layer, one layer of output
Layer.The neural node number of input layer is characterized the dimension m of vector；The neural node number of hidden layer can be
Arbitrarily, and the later stage can be according to experiment test error, and accuracy is tested and improved, in the present invention
We first arrange hidden layer nerve node number for (k-1)；Output layer nerve node number is the dimension of output valve
1。
(2) BP algorithm principle
BP algorithm is the example processing in training set by iterative, and BP algorithm divides two steps to carry out, i.e. forward
Propagate and back propagation.Needed all weights of random initializtion (generally before starting to train BP neutral net
The weight randomly selected is between-1 to 1) and random initializtion biases, and (bias generally randomly selected exists
Between-0.5 to 0.5).The two process is first sketched as a example by single sample by the present invention:
(2.1) forward-propagating
The sample of input in layer processes through hidden layer nerve node from input layer, by all of hidden
After hiding layer, then it is transmitted to output layer；During successively processing, the state of each layer of neuron is only to next
The state of layer neuron produces impact.At output layer, reality output and desired output are compared, if actual
Output is not equal to desired output, then enter back-propagation process.
The neutral net forward-propagating specific algorithm being directed to the present invention is as follows:
Sigmoid function (S curve) is used to carry out the simulation of non-linear relation in the present invention.Neural node j
Output valve ojSolution procedure be that the weighted sum of the last layer first drawing neural node j place layer is added
Sum of the biasing of neural node j, the most again to its with carry out non-linear conversion, concrete formula is as follows:
Wherein ojRepresent the output valve of neural node j；IjRepresent the weighting of the last layer of neural node j place layer
The sum of the biasing of neural node j is added after summation；wijRepresent between neural node i and neural node j
Weight；oiRepresent the output valve of last layer nerve node i；θjRepresent the biasing of neural node j.
All hidden layers and output valve o of output layer nerve node is obtained according to formula (1) (2)j(j=1,2 ..., k).
The actual output o of this sample is drawn by forward-propagatingk, by itself and desired output TkCompare, such as fruit
Border output is not equal to desired output, then enter back-propagation process.
(2.2) back propagation
During back propagation, error is reversely passed back by the path of original forward-propagating, and each to each hidden layer
Weight and the biasing of individual neuron are modified, to hope that output error tends to minimum.
Reversely transmit according to error
Error E rr between output actual for output layer nerve node k and desired outputk:
Errk=ok(1-ok)(Tk-ok) formula (3)
Wherein ErrkRepresent the error between the actual output of output layer nerve node k and desired output；οkTable
Show the actual output of neural node k；TkRepresent the desired output of neural node k.ok(1-ok) it is sigmoid
Function derivative.
Error E rr between output actual for hidden layer nerve node j and desired outputj:
Wherein ErrjRepresent the error between the actual output of hidden layer nerve node j and desired output；ojTable
Show the real output value of neural node j；
Weight updates:
Δwij=(l) ErrjoiFormula (5)
wij=wij+ΔwijFormula (6)
Wherein Δ wijRepresent weight w after propagated forwardijWith weight w after back-propagatingijBetween error；l
Represent learning rate or rate of change, can randomly select between 0 to 1.The w on formula (6) the equal sign left sideijRepresent
The weight updated after back-propagating；
Biasing updates:
Δθj=(l) ErrjFormula (7)
θj=θj+ΔθjFormula (8)
Wherein Δ θjRepresent weight θ after propagated forwardjWith weight θ after back-propagatingjBetween error；Formula (8)
The θ on the equation left sidejThe bias updated after representing back-propagating；
By the back propagation step of formula (3)～(8) weight to hidden layer Yu each neuron of output layer
Modify with biasing so that output error value gradually tends to minimum.
It is above the concrete step using a sample that training philosophy and the BP algorithm of BP neutral net are realized
Suddenly, the training of other (p-1) individual samples of the present invention is as above.After p sample has all been trained, use
(n-p) individual test specimens tested the accuracy of the BP neutral net trained originally.
Step 3: the characteristic vector of given m dimension is input value [x1,x2,...,xi,...,xm], perform corresponding automatization
Test case obtains actual test result Tk；
In step 3, given input value [x1,x2,...,xi,...,xm] perform the automatic test cases of specific function.
In Ranorex, such as quote storage have the Excel of test desired data, perform the automatic test of corresponding function,
Obtain corresponding real output value Tk。
Step 4: the input value in above-mentioned steps 3 is substituted in the neutral net trained in step 2,
Training through neutral net draws prediction output valve ok, then step 3 will perform corresponding automatic test
Use-case obtains actual test result TkThe predictive value o exported with the neutral net after having trainedkCompare,
By result of the comparison Δ TkJudge whether this test case Bug occurs.
In step 4, [x step 3 used1,x2,...,xi,...,xm] input value substitutes in step 2 and train
In good BP neutral net, exported result accordingly, desired value o of the most specific automatic test casesk。
Actual output result T of the automatic test cases of corresponding function will be performedkSystem is obtained with training defeated after completing
Desired value o gone outkContrast, and try to achieve input value for [x1,x2,...,xi,...,xm] time output error Δ Tk,
According to error delta TkJudge whether that this is occurred in that Bug by brake.In view of in actual environment, industrial software
The machinery controlled may be affected by working environment and machinery self-temperature, loss etc., sets threshold value μ,
When error delta TkWhen exceeding threshold value μ, Ranorex will write Bug in report, and terminate this automatic test
The execution of use-case, continues executing with next automatic test cases；When error delta TkWhen being not above threshold value μ,
Continue the execution of this automatic test cases.
Present invention is generally directed to existing automatic test cases test result verification method problems faced, it is provided that
The verification method of a kind of specific automation test case actual output result correctness, this invention will be to industrial software
The solution of specific automation testing case result verification problem there is application value.
In the above-described embodiments, only the present invention has been carried out exemplary description, but those skilled in the art are readding
Can without departing from the spirit and scope of the present invention the present invention be carried out various after reader patent application
Amendment.
Claims (5)
1. the verification method of a specific automation test case actual output result correctness, it is characterised in that described method bag
Include following steps:
Step 1: obtain and be stored under local file without Bug data；
Step 2: train a neural network model by the data without Bug got；
Step 3: the characteristic vector of given m dimension is input value [x1,x2,...,xi,...,xm], perform corresponding automatic test cases and obtain
Actual test result Tk；
Step 4: the input value in above-mentioned steps 3 is substituted in the neutral net trained in step 2, through neutral net
Training draw prediction output valve ok, then obtain actual test result T by step 3 performs corresponding automatic test caseskWith
The predictive value o of the neutral net output after having trainedkCompare, by result of the comparison Δ TkJudge that this test case is
No there is Bug.
Method the most according to claim 1, it is characterised in that in described step 1, uses automated test tool to adopt
Collection is stored under local file without Bug data, and these data include that input value and output valve, input value therein refer to that design is specified
Feature according to this test case during test case, input when the input numerical value given when edit script can also be recording interface
Numerical value etc., when performing automatic test, these input numerical value are to the assignment of corresponding parameter；Output valve refers to this test case
After being finished result value in interface display can also be machine feedback log in information.
Method the most according to claim 1, it is characterised in that in described step 2, sets up neural network model, will
N the sample using automated test tool to collect is divided into two parts, is training sample and test sample respectively, uses training
The input and output value of sample trains neutral net, tests, by the input and output value of test sample, the nerve trained the most again
The accuracy of network.
Method the most according to claim 1, it is characterised in that in described step 3, with given data
[x1,x2,...,xi,...,xm] be input value to perform the automatic test cases of specific function, obtain corresponding real output value Tk。
Method the most according to claim 1, it is characterised in that in described step 4, uses in described step 2 and trains
The neutral net completed, the input value [x that described step 3 is used1,x2,...,xi,...,xm] substitute into the nerve net that step 2 has trained
In network, exported result, desired value o of the most specific automatic test cases accordinglyk, the automatization of corresponding function will be performed
Actual output result T of test casekObtain, after having trained, desired value o that system exportskContrasting, trying to achieve input value is
[x1,x2,...,xi,...,xm] time output error Δ Tk, according to error delta TkJudge whether that this is occurred in that Bug by brake, set threshold
Value μ, when error delta TkWhen exceeding threshold value μ, use script to write Bug in test report, and terminate the survey of this automatization
The execution of example on probation, continues executing with next automatic test cases；When error delta TkWhen being not above threshold value μ, continue this certainly
The execution of dynamicization test case.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610220057.1A CN105843743B (en) | 2016-04-11 | 2016-04-11 | A kind of verification method of specific automation test case reality output result correctness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610220057.1A CN105843743B (en) | 2016-04-11 | 2016-04-11 | A kind of verification method of specific automation test case reality output result correctness |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105843743A true CN105843743A (en) | 2016-08-10 |
| CN105843743B CN105843743B (en) | 2018-10-02 |
Family
ID=56597138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610220057.1A Active CN105843743B (en) | 2016-04-11 | 2016-04-11 | A kind of verification method of specific automation test case reality output result correctness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105843743B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107967218A (en) * | 2017-12-26 | 2018-04-27 | 中原工学院 | Boundary value test method in industrial software on-the-spot test based on user's history data |
| CN108304318A (en) * | 2018-01-02 | 2018-07-20 | 深圳壹账通智能科技有限公司 | The test method and terminal device of equipment compatibility |
| CN108874665A (en) * | 2018-05-29 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | A kind of test result method of calibration, device, equipment and medium |
| CN109636786A (en) * | 2018-12-11 | 2019-04-16 | 杭州嘉楠耘智信息科技有限公司 | Verification method and device of image recognition module |
| CN110232020A (en) * | 2019-05-20 | 2019-09-13 | 平安普惠企业管理有限公司 | Test result analysis method and relevant apparatus based on intelligent decision |
| CN110309064A (en) * | 2019-05-30 | 2019-10-08 | 重庆金融资产交易所有限责任公司 | Unit test method, device, equipment and storage medium based on log recording |
| CN110377511A (en) * | 2019-07-11 | 2019-10-25 | 河海大学 | A kind of method for generating test case of Data Flow Oriented |
| CN111026664A (en) * | 2019-12-09 | 2020-04-17 | 遵义职业技术学院 | Program detection method and detection system based on ANN and application |
| CN111445115A (en) * | 2020-03-20 | 2020-07-24 | Oppo（重庆）智能科技有限公司 | Test item checking method and device, electronic equipment and computer readable storage medium |
| CN113434408A (en) * | 2021-06-25 | 2021-09-24 | 北京理工大学 | Unit test case sequencing method based on approximate test prediction |
| CN108470000B (en) * | 2018-03-06 | 2024-05-03 | 睿云联(厦门)网络通讯技术有限公司 | Automatic testing method, system and medium for communication terminal software |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040078693A1 (en) * | 2002-03-22 | 2004-04-22 | Kellett Stephen Richard | Software testing |
| CN103092748A (en) * | 2011-11-07 | 2013-05-08 | 阿里巴巴集团控股有限公司 | Method and system of test cases surely needing to perform regression testing |
-
2016
- 2016-04-11 CN CN201610220057.1A patent/CN105843743B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040078693A1 (en) * | 2002-03-22 | 2004-04-22 | Kellett Stephen Richard | Software testing |
| CN103092748A (en) * | 2011-11-07 | 2013-05-08 | 阿里巴巴集团控股有限公司 | Method and system of test cases surely needing to perform regression testing |
Non-Patent Citations (1)
| Title |
|---|
| 庞金茹: "汽车产品回收再制造企业特征属性与生产性服务需求匹配预测研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107967218A (en) * | 2017-12-26 | 2018-04-27 | 中原工学院 | Boundary value test method in industrial software on-the-spot test based on user's history data |
| CN108304318A (en) * | 2018-01-02 | 2018-07-20 | 深圳壹账通智能科技有限公司 | The test method and terminal device of equipment compatibility |
| CN108304318B (en) * | 2018-01-02 | 2020-12-04 | 深圳壹账通智能科技有限公司 | Device compatibility testing method and terminal device |
| CN108470000B (en) * | 2018-03-06 | 2024-05-03 | 睿云联(厦门)网络通讯技术有限公司 | Automatic testing method, system and medium for communication terminal software |
| CN108874665A (en) * | 2018-05-29 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | A kind of test result method of calibration, device, equipment and medium |
| CN109636786A (en) * | 2018-12-11 | 2019-04-16 | 杭州嘉楠耘智信息科技有限公司 | Verification method and device of image recognition module |
| CN109636786B (en) * | 2018-12-11 | 2022-11-22 | 嘉楠明芯(北京)科技有限公司 | Verification method and device of image recognition module |
| CN110232020A (en) * | 2019-05-20 | 2019-09-13 | 平安普惠企业管理有限公司 | Test result analysis method and relevant apparatus based on intelligent decision |
| CN110309064A (en) * | 2019-05-30 | 2019-10-08 | 重庆金融资产交易所有限责任公司 | Unit test method, device, equipment and storage medium based on log recording |
| CN110377511A (en) * | 2019-07-11 | 2019-10-25 | 河海大学 | A kind of method for generating test case of Data Flow Oriented |
| CN110377511B (en) * | 2019-07-11 | 2021-04-06 | 河海大学 | Test case generation method oriented to data flow |
| CN111026664A (en) * | 2019-12-09 | 2020-04-17 | 遵义职业技术学院 | Program detection method and detection system based on ANN and application |
| WO2021115186A1 (en) * | 2019-12-09 | 2021-06-17 | 遵义职业技术学院 | Ann-based program test method and test system, and application |
| CN111445115A (en) * | 2020-03-20 | 2020-07-24 | Oppo（重庆）智能科技有限公司 | Test item checking method and device, electronic equipment and computer readable storage medium |
| CN111445115B (en) * | 2020-03-20 | 2023-10-17 | Oppo（重庆）智能科技有限公司 | Test item verification method, device, electronic equipment and computer readable storage medium |
| CN113434408B (en) * | 2021-06-25 | 2022-04-08 | 北京理工大学 | Unit test case sequencing method based on test prediction |
| CN113434408A (en) * | 2021-06-25 | 2021-09-24 | 北京理工大学 | Unit test case sequencing method based on approximate test prediction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105843743B (en) | 2018-10-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105843743A (en) | Method for verifying correctness of actual output result of special automatic test case | |
| Costa et al. | Application of artificial neural networks in a history matching process | |
| Wang et al. | A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation | |
| Shahamiri et al. | Artificial neural networks as multi-networks automated test oracle | |
| CN106407649A (en) | Onset time automatic picking method of microseismic signal on the basis of time-recursive neural network | |
| CN105957086A (en) | Remote sensing image change detection method based on optimized neural network model | |
| EP4075281A1 (en) | Ann-based program test method and test system, and application | |
| CN112668809B (en) | Method for establishing autism children rehabilitation effect prediction model | |
| WO2019160138A1 (en) | Causality estimation device, causality estimation method, and program | |
| CN112150304A (en) | Power grid running state track stability prejudging method and system and storage medium | |
| CN115081321B (en) | Corrosion fatigue life prediction method, system and equipment for marine welding structure | |
| CN110334478A (en) | Machinery equipment abnormality detection model building method, detection method and model | |
| Alenazi et al. | Using obstacle analysis to support SysML-based model testing for cyber physical systems | |
| Masud et al. | Strategy for mutation testing using genetic algorithms | |
| CN115392434A (en) | Depth model reinforcement method based on graph structure variation test | |
| Gardner et al. | A probabilistic framework for forward model-driven SHM | |
| CN114238102A (en) | Staged workload prediction method and system based on composite variable characteristics | |
| CN111241614A (en) | Engineering structure load inversion method based on condition generation confrontation network model | |
| CN111582632B (en) | Multi-factor safety stage prediction method for whole process of underground large space construction | |
| CN116069646B (en) | Test set determination method and system for multi-objective testability optimization | |
| CN117078236B (en) | Intelligent maintenance method and device for complex equipment, electronic equipment and storage medium | |
| CN113240000B (en) | Machine state monitoring method, readable storage medium and electronic device | |
| CN117349770B (en) | Structural health monitoring multi-strain sensor data anomaly detection and repair method | |
| Worthington | Machine learning predictions of crack paths in brittle and ductile media | |
| CN113095594A (en) | Block chain-based test joint debugging method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |