CN117350176A - Automatic overcurrent protection method and device based on universal testing machine - Google Patents
Automatic overcurrent protection method and device based on universal testing machine Download PDFInfo
- Publication number
- CN117350176A CN117350176A CN202311648649.XA CN202311648649A CN117350176A CN 117350176 A CN117350176 A CN 117350176A CN 202311648649 A CN202311648649 A CN 202311648649A CN 117350176 A CN117350176 A CN 117350176A
- Authority
- CN
- China
- Prior art keywords
- test
- parameter
- testing machine
- parameters
- model
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 482
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000007613 environmental effect Effects 0.000 claims abstract description 15
- 238000010276 construction Methods 0.000 claims description 25
- 238000012795 verification Methods 0.000 claims description 23
- 238000006073 displacement reaction Methods 0.000 claims description 21
- 230000009467 reduction Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 abstract description 16
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000004590 computer program Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 9
- 239000000463 material Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000009471 action Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 5
- 238000000513 principal component analysis Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000010998 test method Methods 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012880 independent component analysis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 235000003642 hunger Nutrition 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000007777 multifunctional material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000037351 starvation Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000009864 tensile test Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Geometry (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The utility model provides an automatic overcurrent protection method and device based on a universal testing machine, which belongs to the technical field of equipment control. The method comprises the following steps: first, a target power prediction model is constructed through a first test parameter and an environmental parameter of a first test period to predict power required for a test. And then, on the basis of the first test period, acquiring a second test parameter of a second test period, and inputting the second test parameter into a target power prediction model to obtain the predicted power of the second test period. And then, monitoring the real-time power in the second test period, comparing the real-time power with the predicted power, and dynamically correcting the target power prediction model according to the difference. And finally, determining a target second test parameter of a second test period according to the corrected model and the maximum operating power of the equipment so as to ensure that the operation of the test equipment is in a safe power range. The method is used for solving the problem that the universal testing machine is over-current due to incorrect or large deviation of the testing parameters input in the testing process.
Description
Technical Field
The application relates to the technical field of equipment control, in particular to an automatic overcurrent protection method and device based on a universal testing machine.
Background
The universal tester (Universal Testing Machine, UTM) is a multi-functional material universal tester for evaluating mechanical properties of materials, such as tensile, compressive, bending, shear, and the like. It is widely used in engineering, material science, manufacturing industry and other fields for determining the strength, rigidity, ductility and other physical properties of materials to ensure the quality, performance and safety of products.
When evaluating the characteristics of the novel material, the lack of adequate knowledge of the characteristics of the sample to be tested can result in incorrect or greatly biased test parameters input during the test. The test parameters are not matched sufficiently, so that the load of the universal testing machine exceeds the bearing capacity of the universal testing machine, the universal testing machine is in an overcurrent condition, the universal testing machine is overloaded, and equipment is damaged.
Disclosure of Invention
The embodiment of the application provides an automatic overcurrent protection method and device based on a universal testing machine, which are used for solving the problems in the background technology.
In order to achieve the above purpose, the embodiments of the present application adopt the following technical solutions:
In a first aspect, an automatic overcurrent protection method based on a universal testing machine is provided, and the method comprises the following steps:
acquiring a first test parameter of a sample to be tested in a first test period, and constructing a target power prediction model of the universal testing machine according to the first test parameter and the environmental parameter;
acquiring a second test parameter of a sample to be tested in a first test period, and determining the second test parameter of the sample to be tested in the second test period according to the first test parameter of the first test period and the second test parameter of the first test period, wherein the first test parameter is an output parameter of a universal testing machine, and the second test parameter is an input parameter of the universal testing machine;
inputting a second test parameter of a second test period into a target power prediction model to obtain predicted power of the second test period of the universal testing machine;
acquiring real-time power of the universal testing machine in a second test period, and dynamically correcting the target power prediction model according to the deviation value of the real-time power and the predicted power;
and determining a target second test parameter of a second test period according to the corrected target power prediction model, wherein the real-time power corresponding to the target second test parameter is the maximum operation power of the universal testing machine.
According to the automatic overcurrent protection method, the target power prediction model is built through the first test parameters and the environment parameters, and the system can predict the proper power level required by the test, namely the target power. This ensures the rationality and matching of the test parameters and avoids the input of incorrect parameters when the characteristics of the sample to be tested are not known. By acquiring the second test parameters of the first test period in combination with the first test parameters, the system is able to determine the appropriate input parameters for the second test period to ensure that the test equipment is operating within the appropriate power range. And dynamically correcting the target power prediction model according to the real-time data to ensure that the target power prediction model adapts to the change and fluctuation in the test process, thereby improving the robustness of the system. According to the corrected model and the maximum operating power of the equipment, the system determines target input parameters of the second test period so as to ensure that the test equipment operates in a safe power range, and avoid the condition that the equipment is overloaded or over-current is possibly caused.
In summary, by combining model prediction, real-time monitoring and dynamic adjustment, the problems of incorrect test parameters, overload load and the like caused by insufficient understanding of the characteristics of the sample to be tested are effectively solved, so that the stability and reliability of the test are ensured. This helps to prevent equipment damage and improve test accuracy and controllability.
In one possible embodiment, the first test parameters include at least a load parameter, a displacement parameter, and a load parameter; constructing a target power prediction model of the universal testing machine according to the first testing parameters and the environment parameters, wherein the target power prediction model comprises the following components:
carrying out dimension reduction processing on the load parameter, the displacement parameter, the load parameter and the environment parameter, and calculating the parameter information quantity after the dimension reduction processing;
screening the load parameter, the displacement parameter, the load parameter of the universal testing machine and the environmental parameter according to the size relation between the parameter information quantity and the preset threshold value to obtain a plurality of model construction parameters;
and constructing a power prediction model according to the model construction parameters.
In one possible implementation, constructing the power prediction model from the model construction parameters includes:
randomly combining at least two model building parameters to obtain a plurality of combined results, wherein each combined result corresponds to a historical data set, and the historical data set comprises a first data set and a second data set;
training a preset model based on a plurality of first data sets to obtain a plurality of initial power prediction models;
performing accuracy verification on the plurality of initial power prediction models based on the plurality of second data sets to obtain a plurality of intermediate power prediction models;
And carrying out model fusion on the intermediate power prediction model to obtain a target power prediction model.
In one possible implementation manner, determining the second test parameter of the sample to be tested in the second test period according to the first test parameter of the first test period and the second test parameter of the first test period includes:
determining initial second test parameters of the second test period according to the corresponding relation between the first test parameters of the first test period and the second test parameters of the first test period;
and acquiring task test requirements of the sample to be tested, and correcting the initial second test parameters according to the task test requirements to acquire initial second test parameters of a second test period, wherein the task test requirements are used for verifying the accuracy and the range of the initial second test parameters.
In one possible implementation, inputting the second test parameter of the second test period into the target power prediction model to obtain the predicted power of the second test period of the universal tester, including:
constructing an input feature based on a second test parameter of a second test period;
and inputting the input characteristics into a target power prediction model to obtain the predicted power of the universal testing machine in the second test period.
In one possible implementation manner, the second test period includes a plurality of test sub-periods, the real-time power of the universal testing machine in the second test period is obtained, and the target power prediction model is dynamically modified according to the deviation value of the real-time power and the predicted power, including:
determining the real-time power of the universal testing machine in the second testing period according to the real-time operation parameters of the universal testing machine in the second testing period;
and carrying out multi-level verification on the deviation value of the real-time power and the predicted power according to the test sub-periods with different interval sizes, and carrying out dynamic correction on the target power prediction model according to the verification result.
In one possible embodiment, dynamically modifying the input parameters of the second test period according to the modified target power prediction model to obtain target input parameters includes:
and carrying out feedback adjustment based on the corrected target power prediction model and the maximum operating power of the universal testing machine, and determining target input parameters.
In a second aspect, an automatic overcurrent protection device based on a universal testing machine is provided, the device comprising:
the acquisition module is used for acquiring a first test parameter of a sample to be tested in a first test period and constructing a target power prediction model of the universal testing machine according to the first test parameter and the environment parameter;
The input parameter determining module is used for obtaining a second test parameter of the sample to be tested in the first test period and determining the second test parameter of the sample to be tested in the second test period according to the first test parameter of the first test period and the second test parameter of the first test period, wherein the first test parameter is an output parameter of the universal testing machine, and the second test parameter is an input parameter of the universal testing machine;
the prediction module is used for inputting second test parameters of a second test period into the target power prediction model to obtain the predicted power of the second test period of the universal testing machine;
the model correction module is used for acquiring the real-time power of the universal testing machine in the second test period and dynamically correcting the target power prediction model according to the deviation value of the real-time power and the predicted power;
and the parameter correction module is used for determining a target second test parameter of the second test period according to the corrected target power prediction model, wherein the real-time power corresponding to the target second test parameter is the maximum operation power of the universal testing machine.
In one possible implementation, the obtaining module includes:
the calculation sub-module is used for carrying out dimension reduction on the load parameter, the displacement parameter, the load parameter and the environment parameter and calculating the parameter information quantity after the dimension reduction;
The screening sub-module is used for screening the load parameter, the displacement parameter, the load parameter of the universal testing machine and the environmental parameter according to the size relation between the parameter information quantity and the preset threshold value, so as to obtain a plurality of model construction parameters;
and the construction submodule is used for constructing a power prediction model according to the model construction parameters.
In one possible embodiment, constructing a sub-module includes:
a combination unit for arbitrarily combining at least two model construction parameters to obtain a plurality of combination results, wherein each combination result corresponds to one historical data set, and the historical data set comprises a first data set and a second data set;
the model training unit is used for training a preset model based on a plurality of first data sets so as to obtain a plurality of initial power prediction models;
the model checking unit is used for checking the accuracy of the plurality of initial power prediction models based on the plurality of second data sets so as to obtain a plurality of intermediate power prediction models;
and the model fusion unit is used for carrying out model fusion on the intermediate power prediction model so as to obtain a target power prediction model.
In one possible implementation, the input parameter determination module includes:
The pre-input parameter determination submodule is used for determining initial second test parameters of the second test period according to the corresponding relation between the first test parameters of the first test period and the second test parameters of the first test period;
the pre-input parameter adjustment sub-module is used for acquiring task test requirements of a sample to be tested, correcting the initial second test parameters according to the task test requirements to obtain the initial second test parameters of the second test period, wherein the task test requirements are used for verifying the accuracy and the range of the initial second test parameters.
In one possible implementation, the prediction module includes:
the characteristic construction submodule is used for constructing input characteristics based on second test parameters of a second test period;
and the input sub-module is used for inputting the input characteristics into the target power prediction model so as to obtain the predicted power of the universal testing machine in the second test period.
In one possible implementation, the model modification module includes:
the real-time power calculation sub-module is used for determining the real-time power of the universal testing machine in the second testing period according to the real-time operation parameters of the universal testing machine in the second testing period;
And the real-time power verification calculation sub-module is used for carrying out multi-level verification on the deviation value of the real-time power and the predicted power according to the test sub-periods with different interval sizes, and carrying out dynamic correction on the target power prediction model according to the verification result.
In a third aspect, there is provided an electronic device comprising a memory storing a computer program executable on the processor and a processor implementing a method according to any one of the first aspects above when the program is executed by the processor.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as in any of the first aspects described above.
The technical effects of the second to fourth aspects are referred to the technical effects of the first aspect and any of its embodiments and are not repeated here.
Drawings
FIG. 1 is a flow chart of steps of an automatic overcurrent protection method based on a universal testing machine provided by an embodiment of the invention;
fig. 2 is a schematic diagram of a functional module of an automatic overcurrent protection device based on a universal testing machine according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to fig. 1 to 2 and the embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The terms "first," "second," and the like in the embodiments of the present application are used for the purpose of distinguishing between similar features and not necessarily for the purpose of indicating a relative importance, quantity, order, or the like.
The terms "exemplary" or "such as" and the like, as used in connection with embodiments of the present application, are intended to be exemplary, or descriptive. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
The terms "coupled" and "connected" in connection with embodiments of the present application are to be construed broadly, and may refer, for example, to a physical direct connection, or to an indirect connection via electronic devices, such as, for example, a connection via electrical resistance, inductance, capacitance, or other electronic devices.
Currently, in performing property evaluations of new materials, it is often necessary to use a universal tester to perform mechanical property tests such as stretching, bending, or compression. However, due to lack of adequate knowledge of the characteristics of the sample to be tested, incorrect or significant deviations in the test parameters entered during the test may result. Lack of knowledge may include lack of information on the strength, modulus of elasticity, fracture toughness, deformation behavior, etc. of the material.
When the test parameters are not sufficiently matched or accurate, the operation of the universal tester may be severely affected. In particular, if the test machine is set at a load or strain rate that is much higher than the actual capacity of the material, this may result in overload operation of the motors and sensors of the test machine. In this case, the tester may experience an overcurrent condition due to an excessive load in an attempt to forcibly perform the test, but cannot be effectively completed. This not only results in damage to the tester equipment, but can also pose a potential threat to the safety of the operator.
Based on this, the inventors have proposed the inventive concept of the present application: the operation of the universal testing machine is optimized according to the actual material characteristics and environmental parameters by dynamically establishing and correcting a target power prediction model. And collecting data in a first test period for constructing a model, and dynamically adjusting input parameters according to the deviation of the real-time power and the predicted power to ensure that the testing machine operates at the maximum operating power so as to improve the testing accuracy and the equipment reliability.
Referring to fig. 1, an embodiment of the present invention provides an automatic overcurrent protection method based on a universal testing machine, which may specifically include the following steps:
S101: and acquiring a first test parameter of a first test period of the sample to be tested, and constructing a target power prediction model of the universal testing machine according to the first test parameter of the first test period and the environmental parameter.
In this embodiment, during the process of testing a sample to be tested, the test process thereof is divided into a plurality of test periods, and different test conditions may be executed in different test periods. The first cycle is the initial phase of this test procedure, typically used to establish benchmarks and collect initial data. At this stage, the basic characteristic parameters of the sample to be tested and the operating parameters of the universal tester are collected. The first test parameters include a load parameter, a displacement parameter, and a load parameter, which are used to determine how to apply a force or load to the sample to be tested and how to record displacement or deformation. Baseline data and initial conditions are provided for subsequent test cycles to help build the target power prediction model and ensure that the universal tester operates under appropriate conditions.
The method comprises the following specific steps:
s1011: and carrying out dimension reduction processing on the load parameter, the displacement parameter, the load parameter and the environment parameter, and calculating the parameter information quantity after the dimension reduction processing.
In this embodiment, the purpose of the dimension reduction processing of the load parameters, displacement parameters, load parameters and environmental parameters is to reduce the complexity of the data in order to more efficiently analyze and process these parameters while ensuring that no important information is lost. The main principle of dimension reduction is to identify and remove redundant information and noise in data, while preserving key features of the data. This can be achieved by a variety of techniques including Principal Component Analysis (PCA), linear Discriminant Analysis (LDA), feature selection, independent Component Analysis (ICA), etc. The specific steps include:
data collection and preparation: first, raw data including load parameters, displacement parameters, load parameters, and environmental parameters are collected and prepared. These data may be time series data, recording various parameter values during the test.
Data normalization: the data is normalized to ensure that the different parameters have the same dimensions and ranges. This facilitates comparison and analysis of the different parameters in subsequent processing.
And (3) selecting a dimension reduction method: a suitable dimension reduction method is selected, such as Principal Component Analysis (PCA). PCA is a commonly used dimension reduction technique that maps high-dimensional data into low-dimensional space through linear transformation, and preserves the features of maximum variance. This helps to find the dimension of the most informative amount in the data.
The dimension reduction technology is applied: the selected dimension reduction technique is applied to the dataset. For each test parameter, this will result in the mapping of data from the feature space in the high dimension to the new space in the lower dimension.
Information quantity calculation: and evaluating the information content in the data set after the dimension reduction processing. By analyzing the variance or information gain of each new feature vector.
S1012: and screening the load parameter, the displacement parameter, the load parameter of the universal testing machine and the environmental parameter according to the size relation between the parameter information quantity and the preset threshold value, so as to obtain a plurality of model construction parameters.
In this embodiment, in order to construct an accurate and reliable target power prediction model, the information amount of each parameter needs to be considered. The information amount represents information about the test procedure and the object under test contained in one parameter. The amount of information is generally related to the magnitude and importance of the variation of the parameter. Some parameters may have a large range of variation during the test or have a significant impact on the test results, and these parameters typically contain more information. The preset threshold is a threshold used to determine whether the parameters are important enough to incorporate the model build. This threshold is typically set based on expertise and experience. If the information content of a certain parameter is above a preset threshold, it may be regarded as a key parameter to be used for constructing the target power prediction model. If the amount of information is below the threshold, it may be excluded from the model. The result of the screening process is to determine a plurality of model building parameters that will be used to build a plurality of model variants. These model variants can be used to test the effect of different parameter combinations on the predicted target power. By comparing the performance of these models, the most appropriate combination of parameters can be selected to construct the most accurate target power prediction model.
S1013: and constructing a power prediction model according to the model construction parameters.
After the model construction parameters are obtained through screening, a power prediction model is built based on the model construction parameters so as to accurately predict the required power in the test process, and the specific steps comprise:
s10131: randomly combining at least two model building parameters to obtain a plurality of combined results, wherein each combined result corresponds to a historical data set, and the historical data set comprises a first data set and a second data set;
s10132: training a preset model based on a plurality of first data sets to obtain a plurality of initial power prediction models;
s10133: performing accuracy verification on the plurality of initial power prediction models based on the plurality of second data sets to obtain a plurality of intermediate power prediction models;
s10134: and carrying out model fusion on the intermediate power prediction model to obtain a target power prediction model.
In the embodiments of S10131 to S10134, first, at least two parameters are selected from the available parameters according to the required model diversity, which may be different feature choices, model types, etc., to create a plurality of different combinations, each corresponding to one potential model variant, are tried. These parameter combinations may encompass a variety of aspects including load parameters, displacement parameters, load parameters, environmental parameters, and the like. By trying combinations of different parameters, a variety of possible model configurations can be explored, increasing the diversity of models. The method is beneficial to capturing modes and relations under different conditions and improving the adaptability and performance of a final prediction model. Each combination corresponds to a historical dataset that includes two parts, a first dataset and a second dataset, that contain previously collected data regarding the test. A predefined model is trained using a plurality of first data sets. This step aims at creating a plurality of initial power prediction models, each model being trained using a different combination of parameters and a first data set. These initial models may differ in model type, feature engineering, or super-parameter settings, among others. Each initial power prediction model is calibrated using a plurality of second data sets. This means that a model is applied to the second dataset to evaluate its performance on unknown data. This step helps to screen out intermediate power prediction models that perform well, and that exhibit high accuracy and reliability. And finally, carrying out model fusion on the plurality of intermediate power prediction models to obtain a final target power prediction model. Model fusion may employ different methods, such as weighted averaging, ensemble learning, or other techniques, to synthesize the prediction results of the various intermediate models to obtain a more accurate and stable power prediction model.
By combining using a plurality of different parameter combinations and models, a more comprehensive model of data and diversity can be obtained. This helps to improve the accuracy of the target power prediction model, as different models may perform better under different conditions, thereby reducing errors. The multi-model fusion method is beneficial to reducing the uncertainty of the model and improving the reliability of the model. By integrating the prediction results of the multiple models, more reliable power prediction can be obtained, and the risk of prediction errors is reduced.
S102: obtaining a second test parameter of the sample to be tested in the first test period, and determining the second test parameter of the sample to be tested in the second test period according to the first test parameter of the first test period and the second test parameter of the first test period.
In this embodiment, after the first test period is completed, the second test parameters of the sample to be tested during the period need to be obtained. The second test parameters of the first test cycle refer to parameters input to the universal tester during the first test cycle, and the first test parameters of the first test cycle refer to parameters output by the universal tester during the first test cycle, which are typically used to configure and control the operation of the tester for testing. By using the first test parameter of the first test period and the second test parameter of the first test period, the second test parameter of the sample to be tested in the second test period can be determined, so that the tester can be ensured to be correctly configured in the second test period to obtain accurate and reliable test results.
And its specific implementation includes:
s1021: determining initial second test parameters of the second test period according to the corresponding relation between the first test parameters of the first test period and the second test parameters of the first test period;
s1022: and acquiring task test requirements of the sample to be tested, and correcting the initial second test parameters according to the task test requirements to acquire the initial second test parameters of the second test period.
In the embodiments of S1021 to S1022, first, an initial second test parameter of the second test period is determined using a correspondence relationship between a first test parameter and a second test parameter of the first test period. The correspondence relationship has been established in advance, or may be obtained by analyzing the data of the first test period. In the first test period, a correspondence between the first test parameter and the second test parameter is established. This can be achieved by data recording and analysis. The correspondence indicates what second test parameter value the different first test parameter value corresponds to during the first test period. For example, it may be found that under different load or speed conditions, the second test parameter requires a different setting. The initial second test parameters are derived from the data and relationships of the first test period and are used to configure the test conditions of the second test period.
Then, task test requirements related to the sample to be tested are obtained. Test requirements include the required test accuracy, range, specific test conditions, or other requirements. And correcting the initial second test parameters based on the task test requirement to obtain initial second test parameters of the second test period. This correction process may include the steps of:
analyzing task test requirements: specific requirements for the test requirements are understood, including the required accuracy, range, test conditions, etc.
Comparing the initial parameters and the requirements: and comparing the initial second test parameters with the task test requirements to determine whether adjustment is needed.
Parameter correction: parameter corrections are made as needed, which may involve adjusting load, speed, temperature, etc. parameters to ensure that the test is performed within the desired range.
Checking precision and range: after correction, the initial second test parameters are checked to ensure that the accuracy and range in the test requirements are met.
S103: and inputting a second test parameter of the second test period into a target power prediction model to obtain the predicted power of the universal testing machine in the second test period.
In the present embodiment, the power of the second test period is predicted by the constructed target power prediction model, taking as input the second test parameter of the second test period. The second test parameters of the second test period are passed to a target power prediction model that will use these parameters to calculate to produce a predicted power value.
The specific implementation mode comprises the following steps:
s1031: constructing an input feature based on a second test parameter of a second test period;
s1032: and inputting the input characteristics into a target power prediction model to obtain the predicted power of the universal testing machine in the second test period.
In the embodiments of S1031 to S1032, it is first necessary to construct the input feature based on the second test parameters of the second test period. The input features are a set of values or attributes that represent relevant information during the test. The purpose of constructing the input features is to translate the test parameters of the second test period into a form understandable by the model for use in predicting the target power. This may involve feature engineering, data processing and conversion operations. Once the input features are built, they are then input into a pre-built target power prediction model. This model may be a statistical model, a machine learning model, or other mathematical model that aims to learn how to predict the required power level based on the input features. The model is mathematically operated and analyzed to generate a predicted power value for the second test period. When the input features are fed into the model, the model will generate the predicted power for the second test period.
S104: and acquiring the real-time power of the universal testing machine in the second test period, and dynamically correcting the target power prediction model according to the deviation value of the real-time power and the predicted power.
In this embodiment, first, the real power data during the test is obtained by monitoring and measuring the real-time power of the universal tester during the second test period. These data reflect the real-time force or load levels experienced by the sample under test under actual test conditions, and the corresponding displacement or deformation conditions.
These actual power data are then compared to the power previously predicted by the target power prediction model. By calculating the deviation value between the real-time power and the predicted power, the performance difference or error during the test can be determined. The magnitude of the deviation value reflects the prediction accuracy of the model, and if the deviation value is small, the prediction of the model is consistent with the actual situation.
And dynamically correcting the target power prediction model according to the magnitude of the deviation value. If the deviation value is large, the prediction of the model has errors, and the model needs to be adjusted to better match the actual test conditions. This may include adjusting model parameters, updating model weights, or improving feature engineering, etc.
By dynamically correcting the model, the system can adapt to the continuously-changing test conditions, and the accuracy and reliability of the model are improved. This helps to ensure stability of the test procedure, prevent overload or performance starvation, and ultimately achieve more accurate test results.
The dynamic correction process comprises the following steps:
s1041: determining the real-time power of the universal testing machine in the second testing period according to the real-time operation parameters of the universal testing machine in the second testing period;
s1042: and carrying out multi-level verification on the deviation value of the real-time power and the predicted power according to the test sub-periods with different interval sizes, and carrying out dynamic correction on the target power prediction model according to the verification result.
In the embodiments of S1041 to S1042, the purpose of the multi-level verification of the deviation value is to verify the difference between the real-time power and the predicted power in different time intervals to evaluate the performance of the model and the system state. Such multi-level verification may help detect short-term and long-term power fluctuations to better understand dynamic changes during testing.
Exemplary: assuming that a tensile test of the material is being performed, the second test period includes a plurality of test sub-periods, each having a time interval of 10 minutes. The goal of (c) is to ensure that the power control of the tester is stable and consistent with predictions throughout the test. The following measures are adopted:
Short term verification (small interval): at the beginning and end of each test sub-period, the actual power is measured and compared to the predicted power. If the deviation of the actual power from the predicted power exceeds a certain threshold in a short time, corrective action is immediately taken to ensure that the power control during the sub-period is accurate.
Mid-term verification (medium interval): the power data over the past 60 minutes were checked every hour. This check aims to detect power trends over a longer time frame in order to better understand whether there are long-term fluctuations. If instability is found in this interim check, a more extensive analysis may be performed, for example to check whether there is a change in environmental conditions.
Long-term verification (large interval): at the end of each day, the power data over the test period is summarized and compared. Such verification may capture trends and periodic changes over a longer time scale, such as diurnal changes over a day. If long-term instability occurs, more detailed analysis or calibration operations may be required.
The multi-stage verification allows monitoring the performance of the power control and timely taking corrective action based on data in different time intervals to ensure stability and accuracy of the test. By processing the data according to different verification levels, dynamic changes in the testing process can be more comprehensively known, and therefore robustness of the system is improved.
S105: and determining target second test parameters of a second test period according to the corrected target power prediction model.
In this embodiment, determining the target second test parameters of the second test cycle based on the modified target power prediction model refers to calculating or predicting the input parameters that should be used in the second test cycle using the modified model to achieve the desired power level in the universal tester. The specific process comprises the following steps:
and carrying out feedback adjustment based on the corrected target power prediction model and the maximum operating power of the universal testing machine, and determining target input parameters.
In the present embodiment, the target power prediction model corrected before is used. This model has been dynamically modified in previous steps with multi-level checksums to better accommodate the conditions and variations of the actual test. In view of the performance and limitations of the universal testing machine, it is desirable to know the maximum operating power of the universal testing machine when testing the sample. This is the highest power level that the device can withstand, beyond which may lead to device failure or performance degradation. And carrying out feedback adjustment according to the corrected model and the maximum operating power so as to determine target input parameters. This is an optimization procedure aimed at finding a combination of parameters that will achieve maximum operating power without exceeding the plant's capacity.
According to the automatic overcurrent protection method, the target power prediction model is built through the first test parameters and the environment parameters, and the system can predict the proper power level required by the test, namely the target power. This ensures the rationality and matching of the test parameters and avoids the input of incorrect parameters when the characteristics of the sample to be tested are not known. By acquiring the second test parameters of the first test period in combination with the first test parameters, the system is able to determine the appropriate input parameters for the second test period to ensure that the test equipment is operating within the appropriate power range. And dynamically correcting the target power prediction model according to the real-time data to ensure that the target power prediction model adapts to the change and fluctuation in the test process, thereby improving the robustness of the system. According to the corrected model and the maximum operating power of the equipment, the system determines target input parameters of the second test period so as to ensure that the test equipment operates in a safe power range, and avoid the condition that the equipment is overloaded or over-current is possibly caused.
The embodiment of the invention also provides an automatic overcurrent protection device based on the universal testing machine, and referring to fig. 2, a functional block diagram of the automatic overcurrent protection device based on the universal testing machine is shown, and the device can comprise the following modules:
The acquisition module 201 is configured to acquire a first test parameter of a sample to be tested in a first test period, and construct a target power prediction model of the universal testing machine according to the first test parameter and an environmental parameter;
the input parameter determining module 202 is configured to obtain a second test parameter of the sample to be tested in the first test period, and determine the second test parameter of the sample to be tested in the second test period according to the first test parameter of the first test period and the second test parameter of the first test period, where the first test parameter is an output parameter of the universal testing machine, and the second test parameter is an input parameter of the universal testing machine;
the prediction module 203 is configured to input a second test parameter of a second test period into a target power prediction model to obtain a predicted power of the universal testing machine in the second test period;
the model correction module 204 is configured to obtain real-time power of the universal testing machine in the second test period, and dynamically correct the target power prediction model according to a deviation value of the real-time power and the predicted power;
and the parameter correction module 205 is configured to determine a target second test parameter of the second test period according to the corrected target power prediction model, where the real-time power corresponding to the target second test parameter is the maximum operating power of the universal testing machine.
In one possible implementation, the obtaining module includes:
the calculation sub-module is used for carrying out dimension reduction on the load parameter, the displacement parameter, the load parameter and the environment parameter and calculating the parameter information quantity after the dimension reduction;
the screening sub-module is used for screening the load parameter, the displacement parameter, the load parameter of the universal testing machine and the environmental parameter according to the size relation between the parameter information quantity and the preset threshold value, so as to obtain a plurality of model construction parameters;
and the construction submodule is used for constructing a power prediction model according to the model construction parameters.
In one possible embodiment, constructing a sub-module includes:
a combination unit for arbitrarily combining at least two model construction parameters to obtain a plurality of combination results, wherein each combination result corresponds to one historical data set, and the historical data set comprises a first data set and a second data set;
the model training unit is used for training a preset model based on a plurality of first data sets so as to obtain a plurality of initial power prediction models;
the model checking unit is used for checking the accuracy of the plurality of initial power prediction models based on the plurality of second data sets so as to obtain a plurality of intermediate power prediction models;
And the model fusion unit is used for carrying out model fusion on the intermediate power prediction model so as to obtain a target power prediction model.
In one possible implementation, the input parameter determination module includes:
the pre-input parameter determination submodule is used for determining initial second test parameters of the second test period according to the corresponding relation between the first test parameters of the first test period and the second test parameters of the first test period;
the pre-input parameter adjustment sub-module is used for acquiring task test requirements of a sample to be tested, correcting the initial second test parameters according to the task test requirements to obtain the initial second test parameters of the second test period, wherein the task test requirements are used for verifying the accuracy and the range of the initial second test parameters.
In one possible implementation, the prediction module includes:
the characteristic construction submodule is used for constructing input characteristics based on second test parameters of a second test period;
and the input sub-module is used for inputting the input characteristics into the target power prediction model so as to obtain the predicted power of the universal testing machine in the second test period.
In one possible implementation, the model modification module includes:
The real-time power calculation sub-module is used for determining the real-time power of the universal testing machine in the second testing period according to the real-time operation parameters of the universal testing machine in the second testing period;
and the real-time power verification calculation sub-module is used for carrying out multi-level verification on the deviation value of the real-time power and the predicted power according to the test sub-periods with different interval sizes, and carrying out dynamic correction on the target power prediction model according to the verification result.
Based on the same inventive concept, another embodiment of the present invention provides an electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface, the memory complete communication with each other through the communication bus,
a memory for storing a computer program;
and the processor is used for realizing the automatic overcurrent protection method based on the universal testing machine when executing the program stored in the memory.
The communication bus mentioned by the above terminal may be a peripheral component interconnect standard (Peripheral Component Interconnect, abbreviated as PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus. The communication interface is used for communication between the terminal and other devices. The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one storage system located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In addition, in order to achieve the above objective, an embodiment of the present invention further provides a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements the automatic overcurrent protection method based on the universal testing machine according to the embodiment of the present invention.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable vehicles having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, and the like.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. "" and/or "" "means either or both of these can be selected. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the statement "" comprising one … … "", does not exclude the presence of other identical elements in a process, method, article or terminal device comprising the element.
The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. An automatic overcurrent protection method based on a universal testing machine is characterized by comprising the following steps:
acquiring a first test parameter of a sample to be tested in a first test period, and constructing a target power prediction model of the universal testing machine according to the first test parameter and the environmental parameter;
acquiring a second test parameter of a sample to be tested in a first test period, and determining the second test parameter of the sample to be tested in the second test period according to the first test parameter of the first test period and the second test parameter of the first test period, wherein the first test parameter is an output parameter of the universal testing machine, and the second test parameter is an input parameter of the universal testing machine;
inputting second test parameters of the second test period into the target power prediction model to obtain predicted power of the second test period of the universal testing machine;
Acquiring real-time power of the universal testing machine in the second test period, and dynamically correcting the target power prediction model according to the deviation value of the real-time power and the predicted power;
and determining a target second test parameter of a second test period according to the corrected target power prediction model, wherein the real-time power corresponding to the target second test parameter is the maximum operating power of the universal testing machine.
2. The universal tester-based automatic overcurrent protection method of claim 1, wherein the first test parameters include at least a load parameter, a displacement parameter, and a load parameter; the constructing a target power prediction model of the universal testing machine according to the first test parameter and the environment parameter comprises the following steps:
performing dimension reduction processing on the load parameter, the displacement parameter, the load parameter and the environment parameter, and calculating parameter information quantity after the dimension reduction processing;
screening the load parameter, the displacement parameter, the universal testing machine load parameter and the environment parameter according to the size relation between the parameter information quantity and a preset threshold value to obtain a plurality of model construction parameters;
And constructing the power prediction model according to the model construction parameters.
3. The universal tester-based automatic overcurrent protection method of claim 2, wherein the constructing the power prediction model from the model construction parameters comprises:
randomly combining at least two model construction parameters to obtain a plurality of combined results, wherein each combined result corresponds to one historical data set, and the historical data sets comprise a first data set and a second data set;
training a preset model based on a plurality of first data sets to obtain a plurality of initial power prediction models;
performing accuracy verification on the plurality of initial power prediction models based on the plurality of second data sets to obtain a plurality of intermediate power prediction models;
and carrying out model fusion on the intermediate power prediction model to obtain the target power prediction model.
4. The universal tester-based automatic overcurrent protection method of claim 1, wherein the determining the second test parameter of the sample under test in the second test period according to the first test parameter of the first test period and the second test parameter of the first test period comprises:
Determining an initial second test parameter of a second test period according to the corresponding relation between the first test parameter of the first test period and the second test parameter of the first test period;
and acquiring task test requirements of a sample to be tested, and correcting the initial second test parameters according to the task test requirements to obtain initial second test parameters of the second test period, wherein the task test requirements are used for verifying the accuracy and the range of the initial second test parameters.
5. The automatic overcurrent protection method based on the universal testing machine according to claim 1, wherein inputting the second test parameter of the second test period into the target power prediction model to obtain the predicted power of the second test period of the universal testing machine comprises:
constructing an input feature based on a second test parameter of the second test period;
and inputting the input characteristics into the target power prediction model to obtain the predicted power of the universal testing machine in the second test period.
6. The automatic overcurrent protection method based on the universal testing machine according to claim 1, wherein the second testing period includes a plurality of testing sub-periods, the obtaining the real-time power of the universal testing machine in the second testing period, and the dynamically correcting the target power prediction model according to the deviation value of the real-time power and the predicted power includes:
Determining the real-time power of the universal testing machine in the second testing period according to the real-time operation parameters of the universal testing machine in the second testing period;
and carrying out multi-level verification on the deviation value of the real-time power and the predicted power according to the test subcycles with different interval sizes, and carrying out dynamic correction on the target power prediction model according to the verification result.
7. The universal tester-based automatic overcurrent protection method of claim 1, wherein dynamically modifying the input parameters of the second test cycle according to the modified target power prediction model to obtain target input parameters comprises:
and carrying out feedback adjustment based on the corrected target power prediction model and the maximum operating power of the universal testing machine, and determining the target input parameters.
8. An automatic overcurrent protection device based on a universal testing machine, characterized in that the device comprises:
the acquisition module is used for acquiring a first test parameter of a sample to be tested in a first test period and constructing a target power prediction model of the universal testing machine according to the first test parameter and the environmental parameter;
The input parameter determining module is used for obtaining a second test parameter of a sample to be tested in a first test period, and determining a second test parameter of the sample to be tested in a second test period according to the first test parameter of the first test period and the second test parameter of the first test period, wherein the first test parameter is an output parameter of the universal testing machine, and the second test parameter is an input parameter of the universal testing machine;
the prediction module is used for inputting the second test parameters of the second test period into the target power prediction model to obtain the predicted power of the second test period of the universal testing machine;
the model correction module is used for acquiring the real-time power of the universal testing machine in the second test period and dynamically correcting the target power prediction model according to the deviation value of the real-time power and the predicted power;
and the parameter correction module is used for determining a target second test parameter of a second test period according to the corrected target power prediction model, wherein the real-time power corresponding to the target second test parameter is the maximum operation power of the universal testing machine.
9. The universal tester-based automatic overcurrent protection device of claim 8, wherein the acquisition module comprises:
the calculation sub-module is used for carrying out dimension reduction on the load parameter, the displacement parameter, the load parameter and the environment parameter, and calculating the parameter information quantity after the dimension reduction;
the screening sub-module is used for screening the load parameter, the displacement parameter, the universal testing machine load parameter and the environment parameter according to the size relation between the parameter information quantity and a preset threshold value to obtain a plurality of model construction parameters;
and the construction submodule is used for constructing the power prediction model according to the model construction parameters.
10. The universal tester-based automatic overcurrent protection device of claim 9, wherein the first test parameters include at least a load parameter, a displacement parameter, and a load parameter; the construction submodule comprises:
a combination unit, configured to arbitrarily combine at least two model building parameters to obtain a plurality of combined results, where each combined result corresponds to a historical dataset, and the historical dataset includes a first dataset and a second dataset;
The model training unit is used for training a preset model based on a plurality of first data sets so as to obtain a plurality of initial power prediction models;
the model checking unit is used for checking the accuracy of the initial power prediction models based on the second data sets so as to obtain intermediate power prediction models;
and the model fusion unit is used for carrying out model fusion on the intermediate power prediction model so as to obtain the target power prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311648649.XA CN117350176B (en) | 2023-12-05 | 2023-12-05 | Automatic overcurrent protection method and device based on universal testing machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311648649.XA CN117350176B (en) | 2023-12-05 | 2023-12-05 | Automatic overcurrent protection method and device based on universal testing machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117350176A true CN117350176A (en) | 2024-01-05 |
| CN117350176B CN117350176B (en) | 2024-03-22 |
Family
ID=89367009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311648649.XA Active CN117350176B (en) | 2023-12-05 | 2023-12-05 | Automatic overcurrent protection method and device based on universal testing machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117350176B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115952916A (en) * | 2023-01-10 | 2023-04-11 | 商丘工学院 | Artificial intelligence-based wind power prediction error correction method, device and equipment |
| CN116796641A (en) * | 2023-06-25 | 2023-09-22 | 电子科技大学 | SVR and OpenCV-based mechanical property prediction method for metal 3D printing component |
-
2023
- 2023-12-05 CN CN202311648649.XA patent/CN117350176B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115952916A (en) * | 2023-01-10 | 2023-04-11 | 商丘工学院 | Artificial intelligence-based wind power prediction error correction method, device and equipment |
| CN116796641A (en) * | 2023-06-25 | 2023-09-22 | 电子科技大学 | SVR and OpenCV-based mechanical property prediction method for metal 3D printing component |
Non-Patent Citations (3)
| Title |
|---|
| SAGAR CHOKSHI AND PIYUSH GOHIL: "Experimental Investigation and Mathematical Modeling of Longitudinally Placed Natural Fiber Reinforced Polymeric Composites including Interphase Volume Fraction", FIBERS AND POLYMERS 2022, vol. 23, no. 2, pages 488 - 501, XP037702479, DOI: 10.1007/s12221-021-2087-2 * |
| 朱程辉;方?王建平;: "万能试验机神经元自适应控制策略的研究与实现", 信息化纵横, no. 10, pages 19 - 23 * |
| 胡为;常新新;姬书得;李峰;宋崎;牛士玉;: "基于RBF-GA的铝/镁异材FSLW工艺参数优化", 焊接学报, no. 06, pages 54 - 59 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117350176B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111400850B (en) | Equipment fault analysis method, device, equipment and storage medium | |
| CN115422635A (en) | Steel structure engineering monitoring method, system, equipment and storage medium based on BIM | |
| CN115373370A (en) | Method and system for monitoring running state of programmable controller | |
| CN110866682B (en) | Underground cable early warning method and device based on historical data | |
| CN115841046A (en) | Accelerated degradation test data processing method and device based on wiener process | |
| CN117350176B (en) | Automatic overcurrent protection method and device based on universal testing machine | |
| CN110795324A (en) | Data processing method and device | |
| CN113624694A (en) | Inversion method and device for atmospheric methane concentration | |
| CN111259338A (en) | Component failure rate correction method and device, computer equipment and storage medium | |
| CN109214447B (en) | Disk life prediction method and device | |
| JP6765769B2 (en) | State change detection device and state change detection program | |
| CN113642209B (en) | Structure implantation fault response data acquisition and evaluation method based on digital twinning | |
| CN112948925B (en) | Bridge health state evaluation method, system and storage medium | |
| CN113139250B (en) | Method, device, equipment and computer readable medium for predicting fatigue life of tie bar | |
| CN111274687B (en) | Component failure rate prediction method and device, computer equipment and storage medium | |
| CN113569324A (en) | Slope deformation monitoring abnormal data analysis and optimization method | |
| CN114398228A (en) | Method and device for predicting equipment resource use condition and electronic equipment | |
| Lavaud et al. | Goodness-of-fit tests and selection methods for operational risk | |
| CN111931407A (en) | Structure reliability evaluation prediction method and system based on long-term monitoring data | |
| CN116306109B (en) | Marine fan soil structure interaction state identification method based on time domain model correction | |
| CN117055537B (en) | Motorcycle electric control system fault diagnosis method based on Internet of things | |
| CN114386525B (en) | Adaptive adjustment method, device, equipment and storage medium for evaluation standard | |
| US10438150B2 (en) | Energy intensity variability analysis | |
| CN117553864B (en) | Sensor acquisition method and system based on big data | |
| CN117309299B (en) | Servo driver vibration test method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |