Intelligent true triaxial mechanical testing system and testing method based on parameter self-adaptation

Abstract

The present application relates to the technical fields of rock indoor loading test, in particular to an intelligent true triaxial mechanics test system and test method based on parameter self-adaption, comprising the following steps: S1: based on known test data, testing known rock samples to obtain historical parameter data, historical operation data, historical experimental data and rock characteristic data of the rock samples; S2: based on operation time data, marking corresponding time points of the historical parameter data and historical experimental data to obtain parameter subsets and experimental subsets; S3: analyzing the parameter subsets and experimental subsets to obtain intervention relationship; S4: determining the data relationship between rock characteristics and test parameters of the true triaxial test equipment to obtain basic parameter relationship; S5: testing and data monitoring the rock samples to be tested to obtain rock experimental data, and judging and self-adapting based on the intervention relationship, which improves the analysis rate while ensuring the reliability and accuracy of the test results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rock indoor loading test, in particular to an intelligent true triaxial mechanics test system and test method based on parameter self-adaptation. BACKGROUND

[0002] The task of rock true triaxial test is to understand the mechanical properties of deep engineering rock under three-dimensional stress, to provide basic data for revealing the failure mechanism of deep rock and the stability evaluation of rock mass engineering, and to provide basic parameters for engineering design and construction. In the use process of the existing true triaxial test equipment, the test parameters of the true triaxial test equipment are usually evaluated by relevant staff according to the rock characteristics before the test, but in the actual test process, due to the error of the previous human evaluation and the change of rock data, the true triaxial test equipment can only mechanically test according to the test parameters determined in the previous period, which is easy to lead to test failure.

[0003] The Chinese invention patent with the authorized announcement number CN108414346B discloses an intelligent true triaxial test system and test method with adaptive test parameters, which comprises: using a self-learning model trained according to existing data samples to obtain the reasonable range of true triaxial test condition parameters corresponding to the rock sample according to the nature of the rock sample; setting the true triaxial test condition parameters according to the obtained reasonable range of true triaxial test condition parameters, and simulating the true triaxial test output to determine whether the test result of the simulated true triaxial test output is within the bearing capacity range of the current true triaxial test equipment: if yes, outputting a control instruction according to the set true triaxial test condition parameters to control the true triaxial test equipment to perform true triaxial test on the rock sample according to the set true triaxial test condition parameters, and obtaining pressure, displacement and temperature data at each time during the true triaxial test; calculating the real-time deformation rate of the rock in each direction in real time, and real-time regulating the loading rate to complete the true triaxial test; otherwise, re-setting the true triaxial test condition parameters, and obtaining reasonable test parameters through self-adaptation of the test rock sample to guide the test personnel to set the true triaxial test parameters, thereby improving the test efficiency and success rate. The present application provides a test method different from the above-mentioned disclosed scheme, and aims to improve the analysis rate while ensuring the reliability and accuracy of the test results. SUMMARY

[0004] In order to overcome the deficiencies in the prior art, the present application provides an intelligent true triaxial mechanics test system and test method based on parameter self-adaptation.

[0005] To achieve the above-mentioned purpose, the intelligent true triaxial mechanics test method based on parameter self-adaptation disclosed by the present application comprises the following steps:

[0006] S1: The true triaxial test equipment tests a known rock sample based on known test data, monitors test process data of the true triaxial test equipment, and obtains historical parameter data, historical operation data, historical experimental data of the true triaxial test equipment, and rock characteristic data of the rock sample;

[0007] S2: Obtain operation time data in the historical operation data, mark corresponding time points of the historical parameter data and historical experimental data based on the operation time data, divide the historical parameter data and historical experimental data according to the marked time points, and obtain a parameter subset and an experimental subset;

[0008] S3: Analyze the parameter subset and the experimental subset based on the operation time data, determine operation instructions and operation data corresponding to the operation instructions required under different experimental results, and obtain an intervention relationship;

[0009] S4: Comprehensive analyze the historical parameter data and the rock characteristic data, determine the data relationship between the rock characteristic and the test parameter of the true triaxial test equipment, and obtain a basic parameter relationship;

[0010] S5: Obtain rock characteristic data of a rock sample to be tested, generate test parameter data required for testing according to the basic parameter relationship, test and monitor data of the rock sample to be tested based on the test parameter data, and obtain rock experimental data; judge and adaptively adjust the rock experimental data based on the intervention relationship.

[0011] Further, the step S2 includes the following steps:

[0012] S21: Divide the historical experimental data based on the historical parameter data, and determine execution instructions at each time point in the historical experimental data and execution time lengths corresponding to the execution instructions;

[0013] S22: Determine execution instructions corresponding to the operation time data based on the operation time data, determine a data selection interval of the historical parameter data according to the execution time lengths of the execution instructions, select the historical parameter data according to the data selection interval, and obtain a parameter subset;

[0014] S23: Divide the historical experimental data based on the parameter subset, and obtain an experimental subset.

[0015] Further, if the time point corresponding to the operation time data is located at an intersection point between two execution instructions in the step S22, the sum of the execution time lengths of the two execution instructions is taken as a data selection interval according to the time sequence, the historical parameter data is selected according to the data selection interval, and a parameter subset is obtained. The intersection point is an intersection position when the end of one instruction and the beginning of another instruction.

[0016] Further, the step S3 is specifically as follows:

[0017] Determining the inflection points of the parameter subset and the experiment subset, and determining whether the operation time data is the inflection point of the parameter subset and the experiment subset based on the operation time data; the inflection point of the parameter subset is the start time data and the end time data of each execution instruction in the parameter subset; the inflection point of the experiment subset is the time point when the experiment data collected in the experiment subset meets the test requirement and the time point when the experiment data changes;

[0018] Result A: if the time point of the operation time data is the inflection point of the parameter subset and the experiment subset, it is determined that the operation instruction corresponding to the historical operation data is the interrupt operation, and the corresponding intervention relationship is determined;

[0019] Result B: if the time point of the operation time data is the inflection point of the parameter subset but not the inflection point of the experiment subset, it is determined that the operation instruction corresponding to the historical operation data is the cycle operation, and the corresponding intervention relationship is determined;

[0020] Result C: if the time point of the operation time data is the inflection point of the experiment subset but not the inflection point of the parameter subset, it is determined that the operation instruction corresponding to the historical operation data is the parameter modification operation, and the corresponding intervention relationship is determined;

[0021] Result D: if the time point of the operation time data is not the inflection point of the experiment subset and the inflection point of the parameter subset, it is determined that the operation instruction corresponding to the historical operation data is the load frequency modulation operation, and the corresponding intervention relationship is determined.

[0022] Further, the result A determination method is as follows:

[0023] Based on the operation time data, the time interval of the experiment subset containing the corresponding time point is determined, and the inflection point of the experiment subset is determined based on the time interval;

[0024] If it is determined that there are multiple inflection points in the time interval, it is determined that the operation instruction corresponding to the historical operation data is the interrupt operation, and the corresponding relationship between the inflection point data of the experiment subset and the operation instruction is established to obtain the intervention relationship.

[0025] Further, the result B determination method is as follows:

[0026] The historical experiment data is compared with the corresponding test requirement data to determine whether the historical experiment data meets the test requirement data;

[0027] If the historical experimental data does not meet the test requirement data, the execution instruction before the corresponding time point and the execution instruction after the corresponding time point on the parameter subset are compared to determine whether the execution instruction before the corresponding time point and the execution instruction after the corresponding time point are repeated instructions;

[0028] If it is determined that the repeated instructions are repeated instructions, it is determined that the operation instruction is a loop operation, and a relationship between the operation instruction and the corresponding experimental subset is established to obtain an intervention relationship, otherwise, it is determined that the historical operation data is invalid operation.

[0029] Further, the result C judgment method is:

[0030] The historical experimental data before the inflection point is subjected to data change judgment to obtain a data change rule of the corresponding experimental collection item;

[0031] The historical operation data corresponding to the operation time data is subjected to parameter item matching with the historical parameter data to determine the parameter item modified by the historical operation data;

[0032] Based on the modified parameter item, the parameter item data before the modification is compared with the historical experimental data before the inflection point, and the parameter item data after the modification is compared with the historical experimental data after the inflection point to determine the relationship between the data change of the corresponding parameter item and the data change of the experimental data, and a first data change relationship is obtained. The corresponding relationship between the data change rule, the first data change relationship and the corresponding operation instruction is established to obtain an intervention relationship.

[0033] Further, the result D judgment method is:

[0034] The time point of the operation time data is taken as a reference, and the experimental subset in the corresponding time interval is divided into first experimental sub-data before the time point and second experimental sub-data after the time point;

[0035] The first experimental sub-data and the second experimental sub-data are subjected to data amount change rate judgment to obtain data change rates of the two experimental sub-data before and after the time point, and the data change rates are respectively recorded as a first data change rate and a second data change rate;

[0036] Based on the historical operation data, the adjustment result of the loading frequency modulation parameter item in the corresponding operation instruction is determined to obtain an adjustment data amount, and based on the difference between the adjustment data amount and the first data change rate and the second data change rate, the relationship between the adjustment data amount and the data change rate is determined to obtain a second data change relationship. The corresponding relationship between the first data change rate, the second data change relationship and the corresponding operation instruction is constructed to obtain an intervention relationship.

[0037] Further, the step S4 is:

[0038] Obtain the historical parameter data and the corresponding historical operation data of the corresponding test, and modify the historical parameter data based on the historical operation data to obtain ideal parameter data of the corresponding test;

[0039] Match the historical parameter data of each test with the rock characteristic data of the corresponding test to determine the parameter items corresponding to the characteristics of different rocks;

[0040] Statistically analyze the ideal parameter data of the same parameter item under the same rock characteristic and the ideal parameter data of the same parameter item under different rock characteristics to determine the relationship between the rock characteristic and the data value of the parameter item, and obtain the basic parameter relationship.

[0041] The application also discloses a test system based on the intelligent true triaxial mechanical test method based on parameter self-adaption, which comprises a database establishment module, a data relationship construction module and a self-adaptive adjustment module.

[0042] The database establishment module performs a test on a known rock sample based on known test data, and performs data monitoring on the true triaxial test equipment in the test to obtain the historical parameter data, the historical operation data, the historical experimental data of the true triaxial test equipment and the rock characteristic data of the rock sample.

[0043] The data relationship construction module obtains the operation time data of the historical operation data, and divides the historical parameter data and the historical experimental data based on the operation time data to obtain a parameter subset and an experimental subset; the parameter subset and the experimental subset are analyzed to determine the operation instructions required under different test conditions and the operation data corresponding to the operation instructions to obtain an intervention relationship; the historical parameter data and the rock characteristic data are comprehensively analyzed to determine the data relationship between the rock characteristic and the test parameter of the true triaxial test equipment to obtain a basic parameter relationship;

[0044] The self-adaptive adjustment module obtains the rock characteristic data of the rock sample to be tested, generates the test parameter data required for the test according to the basic parameter relationship, and judges and self-adaptively adjusts the rock sample to be tested based on the intervention relationship.

[0045] The application has the following beneficial effects:

[0046] 1、The present application constructs a database of parameter data, operation data, experimental data and rock characteristic data in different rock samples by retesting and data monitoring on known rock samples, determines the data segment intervened by human by reading the operation time point of the operation data at each test, thereby reducing the amount of data to be analyzed when analyzing the data relationship, improving the analysis rate, improving the data quality of the data to be analyzed, and improving the accuracy of the analysis result; by utilizing the change relationship between the experimental subset and the parameter subset, the execution of each operation instruction in the operation data and the data amount of the execution are constructed, the data obtained by human analysis is mechanically and intelligently converted by utilizing the rock characteristic data and the corresponding parameter data, the mental activity of human is reduced, the test monitoring and data analysis on the rock sample to be tested are carried out by utilizing the intervention relationship and the basic parameter relationship obtained by analysis, the data of the true triaxial test equipment in the test process is adjusted in time, the normal progress of the test is ensured, and the test reliability is improved;

[0047] 2、By means of historical reference data, the execution instruction at each time point in the test process and the execution time of the corresponding execution instruction are determined, so that when the data at the corresponding time point is selected according to the operation time data, the completeness of the selected data is ensured, the data quality of the selected data is improved, the effectiveness of the judgment result is improved, and the corresponding relationship between the historical operation data and the historical parameter data, the historical experimental data is determined by selecting the historical parameter data and the historical experimental data according to the operation time data, thereby further improving the accuracy of the analysis and judgment result;

[0048] 3、The time dimension relationship between the operation time data in the historical operation data and the parameter subset and the experimental subset is comprehensively utilized, so that the operation purpose of the corresponding operation is determined, different judgment methods are adopted according to different operation purposes, the judgment accuracy of the data relationship between the operation data and the parameter data, the experimental data under the corresponding operation purpose is improved, and the normal execution of the test is effectively ensured when the rock is subjected to self-adaptive test monitoring in the true triaxial test according to the intervention relationship obtained by judgment, and the reliability of the test result is improved. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 The overall method step flowchart of the present application;

[0050] Figure 2 The step flowchart of obtaining the parameter subset and the experimental subset in the present application. DETAILED DESCRIPTION

[0051] The following will be described in detail with reference to the accompanying drawings Figure 1 to the accompanying drawings Figure 2The principles and features of the present application are described, and the examples are only used to explain the present application, and are not used to limit the scope of the present application.

[0052] Embodiment 1: An intelligent true triaxial mechanics test method based on parameter self-adaption, as shown in the following figure, includes the following steps: Figure 1

[0053] S1: The true triaxial test equipment tests a known rock sample based on known test data, monitors the test process data of the true triaxial test equipment, obtains historical parameter data, historical operation data, historical experimental data of the true triaxial test equipment, and rock characteristic data of the rock sample;

[0054] S2: Obtain operation time data in the historical operation data, mark the corresponding time points of the historical parameter data and the historical experimental data based on the operation time data, divide the historical parameter data and the historical experimental data according to the marked time points, and obtain parameter subsets and experimental subsets;

[0055] S3: Analyze the parameter subsets and the experimental subsets based on the operation time data, determine the operation instructions required under different experimental results and the operation data corresponding to the operation instructions, and obtain the intervention relationship;

[0056] S4: Comprehensive analysis of the historical parameter data and the rock characteristic data, determine the data relationship between the rock characteristics and the test parameters of the true triaxial test equipment, and obtain the basic parameter relationship;

[0057] S5: Obtain the rock characteristic data of the rock sample to be tested, and generate the test parameter data required for the test according to the basic parameter relationship, test and monitor the data of the rock sample to be tested based on the test parameter data, and obtain the rock experimental data; judge and self-adaptively adjust the rock experimental data based on the intervention relationship.

[0058] ​In the embodiment, the database of parameter data, operation data, experimental data and rock characteristic data in different rock samples is constructed by retesting and data monitoring on known rock samples, the operation time point of the operation data in each test is read to determine the data segment intervened by human, and thus the amount of data to be analyzed is reduced when the data relationship is analyzed, the analysis rate is improved, the data quality of the data to be analyzed is improved, and the accuracy of the analysis result is improved. Specifically, the reason for the reduction of the amount of data to be analyzed is that only the data segment intervened by human needs to be analyzed in the embodiment. When there is no human intervention, the test result is executed according to the pre-set operation data. When human intervention occurs, it indicates that the test result exceeds the expectation of the test personnel, and thus adjustment is needed to achieve the target effect. Therefore, by analyzing the data segment intervened by human, the reason for human intervention in the test process is determined, and thus corresponding automatic operation can be performed according to the corresponding situation when the next test is performed, so as to improve the test efficiency and the correctness of the result. By utilizing the change relationship between the experimental subset and the parameter subset, the execution of each operation instruction in the operation data and the data amount of the execution are constructed. By utilizing the rock characteristic data and the corresponding parameter data, the data obtained by human analysis is mechanically and intelligently converted, the mental activity of human is reduced, the test monitoring and data analysis on the rock sample to be tested are performed by utilizing the intervention relationship and the basic parameter relationship obtained by analysis, the true triaxial test equipment in the test process is adjusted in time, the normal progress of the test is ensured, and the test reliability is improved.

[0059] Specifically, when conducting a true triaxial test, staff first cut and process the rock sample to be tested according to regulations. During this process, the basic properties of the rock sample can be determined, such as whether the rock is brittle or ductile, porous or low-permeability, soft or layered, etc. After determining the basic properties of the rock sample, staff manually judge the basic properties of the rock sample to develop a set of test data for the true triaxial test. Typical test data includes loading path and rate, confining pressure, and pore pressure. Based on the developed test data, various parameters of the true triaxial test equipment are adjusted. For example, if the test parameters are the order of loading paths X, Y, and Z, then the loading path items X, Y, and Z on the true triaxial test equipment are activated. If the loading rate is a, then the loading rate of loading paths X, Y, and Z on the true triaxial test equipment is adjusted to a. The equipment with adjusted parameters is tested. During the test, since the parameters are manually evaluated, some deviations may occur in the actual test process. In order to ensure the safety and effectiveness of the test, when some deviations occur or to speed up the test efficiency, it is necessary to manually readjust the equipment with adjusted parameters to ensure the effective conduct of the test. In this process, the manual readjustment constitutes the operation data, and the collection of a certain test result of the rock sample during the test constitutes the experimental data.

[0060] At the same time, since the rock samples to be tested are unknown, the normal progress of the test cannot be guaranteed when the initial parameter adjustment of the true triaxial test equipment is performed. At the same time, in order to improve the intelligence of the true triaxial test and reduce the number of human interventions, it is necessary to determine the relationship between rock property data and parameter data based on historical test data, and to determine the relationship between operation data, experimental data, and parameter data. Specifically, by retesting known rock samples, a sample database is constructed. By analyzing the sample database, the relationship between rock property data and parameter data, as well as the relationship between operation data, experimental data, and parameter data, is determined. Therefore, when performing true triaxial tests on unknown rock samples, a valid set of parameter data can be generated based only on the input rock property data. During the test, by monitoring the experimental data and the parameter data, it is determined whether parameter adjustment is required and the corresponding adjustment amount, ensuring the correct progress of the test. This realizes the adaptive adjustment of parameters in the true triaxial test, improves the intelligence level of the true triaxial test equipment, and thus improves the reliability of the test results.

[0061] Furthermore, if Figure 2 As shown, step S2 includes the following steps:

[0062] S21: dividing the historical experiment data based on the historical parameter data, determining the execution instruction at each time point in the historical experiment data and the execution duration of the corresponding execution instruction; wherein the execution duration is the execution duration of the execution instruction in the actual test.

[0063] S22: determining the execution instruction corresponding to the operation time data based on the operation time data, determining the data selection interval of the historical parameter data according to the execution duration of the execution instruction, and selecting the historical parameter data according to the data selection interval to obtain the parameter subset.

[0064] If the time point corresponding to the operation time data is located at the intersection point between two execution instructions, then the sum of the execution durations of the two execution instructions is taken as the data selection interval according to the time sequence, and the historical parameter data is selected according to the data selection interval to obtain the parameter subset; the intersection point is the intersection position when the end of one instruction and the beginning of another instruction, for example, there are execution instruction a and execution instruction b, the execution time interval of execution instruction a is (0, 10), and the execution time interval of execution instruction b is (10, 20), if the time point corresponding to the operation time data is 10, it is determined that the time point is located at the intersection point of execution instructions a and b.

[0065] S23: dividing the historical experiment data based on the parameter subset to obtain the experiment subset.

[0066] In this embodiment, by using the historical reference data, the execution instruction at each time point in the test process and the execution duration of the corresponding execution instruction are determined, so that when the data at the corresponding time point is selected according to the operation time data, the integrity of the selected data is ensured, the data quality of the selected data is improved, and the effectiveness of the judgment result is improved. At the same time, by selecting the historical parameter data and the historical experiment data according to the operation time data, the corresponding relationship between the historical operation data and the historical parameter data and the historical experiment data is determined, and the accuracy of the analysis and judgment result is further improved.

[0067] Specifically, when the historical parameter data and the historical experiment data are divided according to the operation time data in the historical operation data, the selected data should not only be able to effectively identify the change rule of the data, but also the data amount should be as small as possible, so that the divided data is more concise and accurate.

[0068] Since the execution result corresponding to the same execution instruction in the parameter data should be unchanged, and if the execution process is not problematic, then no human intervention is needed, otherwise, when human intervention occurs, it indicates that the execution instruction is not suitable for the current test situation. Similarly, since human intervention is based on the actual test situation for judgment, when the actual test situation does not generate as expected, it indicates that intervention adjustment is needed. Therefore, by selecting the parameter data when human intervention occurs, the experimental data that does not match the parameter data can be determined, which not only realizes the accuracy of data selection, but also improves the simplicity of the selected data and improves the data quality.

[0069] For example, the historical parameter data is execution instructions a, b, and c, where the execution duration of execution instructions a, b, and c is 10 minutes. Assuming there is operation data p, if the operation data p is located in the execution process of execution instruction b, the execution process of execution instruction b is selected to obtain the corresponding parameter subset, and if the operation data p is located at the end of execution instruction a and at the beginning of execution instruction b, the execution process of execution instruction a and execution instruction b is selected to obtain the corresponding parameter subset.

[0070] For example, the parameter subset is execution instruction b, and the time interval corresponding to execution instruction b is (t, t+10), then the corresponding experimental data is read according to the time interval to obtain the corresponding experimental subset.

[0071] Further, step S3 is as follows:

[0072] Determine the inflection points of the parameter subset and the experimental subset, and determine whether the operation time data is the inflection point of the parameter subset and the experimental subset based on the operation time data; wherein the definition of the inflection point: the start time data and the end time data of each execution instruction in the parameter subset are the inflection points of the parameter subset; for the experimental subset, the time point when the experimental data collected in the experimental subset meets the test demand and the time point when the experimental data occurs mutation are the inflection points of the experimental subset. For example, the execution time interval of execution instruction a is (0, 10), then the time point at 0 and the time point at 10 are marked as inflection points.

[0073] Result A: if the time point of the operation time data is the inflection point of the parameter subset and the experimental subset, it is determined that the operation instruction corresponding to the historical operation data is interrupted operation, and the corresponding intervention relationship is determined;

[0074] Result B: if the time point of the operation time data is the inflection point of the parameter subset but not the inflection point of the experimental subset, it is determined that the operation instruction corresponding to the historical operation data is a loop operation, and the corresponding intervention relationship is determined;

[0075] Result C: if the time point of the operation time data is the inflection point of the experimental subset but not the inflection point of the parameter subset, it is determined that the operation instruction corresponding to the historical operation data is a parameter modification operation, and the corresponding intervention relationship is determined;

[0076] Result D: if the time point of the operation time data is neither the inflection point of the experimental subset nor the inflection point of the parameter subset, it is determined that the operation instruction corresponding to the historical operation data is a load frequency modulation operation, and the corresponding intervention relationship is determined.

[0077] In the embodiment, by determining the time dimension relationship between the operation time data in the historical operation data and the parameter subset and the experimental subset, the operation purpose of the corresponding operation is determined, and then different judgment methods are adopted according to different operation purposes, so as to improve the judgment accuracy of the data relationship between the operation data and the parameter data and the experimental data under the corresponding operation purpose, so that the intervention relationship obtained by judgment can effectively ensure the normal execution of the test when the true triaxial test of the rock is carried out, and the reliability of the test result is improved.

[0078] Specifically, when the operation instructions corresponding to different test phenomena are determined according to the parameter subset and the experimental subset, the data position of the operation time of the historical operation data to be analyzed in the parameter subset and the experimental subset is determined, so that different analysis methods are adopted, so that the results obtained by the final analysis are more targeted and accurate.

[0079] For example, when the operation time of the operation data is located at the inflection point of the execution instruction a and the execution instruction b in the parameter subset, it is indicated that the test process changes the next instruction to be executed after the execution of the instruction a is completed; therefore, the experimental subset needs to be judged, if the operation time is also located at the inflection point of the corresponding experimental subset, it is indicated that the test requirement is met during the execution of the instruction a, and the next test requirement collection needs to be carried out, so it can be judged that the purpose of the operation data is to interrupt the execution of the instruction a.

[0080] If the operation time is not the inflection point of the experimental subset, it is indicated that the test process does not reach the test requirement, for example, the test requirement reached by the execution of the instruction a is to determine the A value of the rock, and the A value of the rock is not determined after the execution of the instruction a is completed, so the execution of the instruction a needs to be re-executed until the A value of the rock is determined, and then the next test requirement collection is carried out, and then it is judged that the purpose of the operation data is to execute the instruction a repeatedly.

[0081] If the operation time is not the inflection point of the parameter subset but the inflection point of the experimental subset, since there are two cases when the experimental subset appears the inflection point, one is that the experimental data meets the test requirement, and the other is that the experimental data mutates; if it is that the experimental data meets the test requirement, the next instruction should be executed to collect the next data, and since the operation time is not the inflection point of the parameter subset, there is no experimental data that meets the test requirement, so in the case of intervention without executing the next instruction, it can be judged that the reason why the experimental subset appears the inflection point in this case is that the experimental data mutates, and the mutation is not the data of the test requirement, so the parameter data of the true triaxial test device needs to be adjusted to meet the test requirement, so the purpose of the operation data is to adjust the parameter data of the instruction a.

[0082] If the operation time data is not the inflection point of the parameter subset and the experimental subset, it indicates that after the intervention, the true triaxial test device continues to execute the instruction a and continues to collect the A value of the rock, so that the operation is basically equal to no operation, so it can be judged that the operation is a loading frequency modulation operation to speed up the test rate within the range that the rock can withstand.

[0083] Further, the result A judgment method is:

[0084] Based on the operation time data, the time interval of the experimental subset containing the corresponding time point is determined, and the inflection point of the experimental subset is judged based on the time interval; wherein the time interval is the time interval between the start time of the time period containing the time point in the experimental subset and the time point.

[0085] If it is determined that there are multiple inflection points in the time interval, it is determined that the operation instruction corresponding to the historical operation data is the interrupt operation, and the corresponding relationship between the inflection point data of the corresponding experimental subset and the operation instruction is established to obtain the intervention relationship. If it is determined that there are no multiple inflection points in the time interval, the execution instruction sequence is judged according to the historical parameter data to determine whether the execution instruction sequence without historical operation data intervention is the same as the execution instruction sequence with historical operation data intervention.

[0086] If the execution instruction sequence is the same, it is determined that the historical operation data is invalid operation, otherwise, the inflection point data of the corresponding experimental subset and the operation instruction are bound to establish the intervention relationship.

[0087] In the embodiment, the intervention relationship refers to a corresponding relationship between a certain test result and an execution instruction when the execution instruction needs to be executed after the test result appears. For example, there are three instructions a, b and c in the test data, each instruction is executed for 10 seconds, and the three instructions correspond to three experimental phenomena A, B and C respectively. When the instruction a is executed, if the phenomenon A appears at the 5th second, the instruction b is directly executed. At this time, the relationship between the experimental phenomenon A and the instruction b is the intervention relationship.

[0088] In the embodiment, based on the logical characteristics of human intervention, the time interval of the experimental subset containing the time point corresponding to the operation time data is determined, the inflection point of the experimental subset in the corresponding time interval is determined, the operation purpose of the operation data is quickly determined, and the corresponding relationship between the inflection point data and the operation instruction is established, so that when the experimental data of a new rock sample appears the experimental data changes, the corresponding operation instruction is used to realize the intelligent operation of the true triaxial test equipment and improve the reliability of the test results.

[0089] Specifically, when the operation time data is the inflection point of the parameter subset and the experimental subset, there are two cases: the first case is that the instruction a has not been executed completely and the desired A value has been obtained; and the second case is that the desired A value is obtained after the instruction a is executed completely.

[0090] For the first case, it can be directly judged that the operation is interrupted, and for the second case, it can be that the execution step of the parameter data is modified or false intervention or invalid intervention. Since the execution step is obtained according to the test step of the true triaxial test equipment, the possibility of modifying the parameter data is excluded, and the false intervention and invalid intervention cases are retained.

[0091] If it is the first case, the experimental subset will first appear data changes to form an inflection point during the execution process, and then the staff will judge that the test demand is met according to the collected experimental data and then interrupt the current instruction to execute the next instruction. Therefore, by reading the inflection point of the experimental subset before the operation time data, the corresponding situation of the operation data can be quickly determined. If there is an inflection point, it indicates that the purpose of the operation data is to interrupt the execution of the instruction, and if there is no inflection point, it indicates that the operation data is invalid operation and invalid intervention.

[0092] Further, the result B judgment method is:

[0093] The historical experimental data and the corresponding test demand data are compared to determine whether the historical experimental data meets the test demand data.

[0094] If the historical experimental data does not meet the test requirement data, the execution instruction before the corresponding time point and the execution instruction after the corresponding time point in the parameter subset are compared to determine whether the execution instruction before the corresponding time point and the execution instruction after the corresponding time point are repeated instructions; wherein the repeated instruction refers to two instructions being the same instruction, and the completeness of the execution instruction before the time point reaches 100%.

[0095] If it is determined that the repeated instruction, it is determined that the operation instruction is a loop operation, and a relationship between the operation instruction and the corresponding experimental subset is established to obtain an intervention relationship, otherwise, it is determined that the historical operation data is invalid operation.

[0096] In the embodiment, the experimental subset at the corresponding time point is compared with the corresponding test requirement data to verify again whether the time point is the inflection point of the experimental subset, so that the judgment is more accurate, and the execution instruction before the time point and the execution instruction after the time point in the parameter subset are compared to determine whether the historical operation data is a loop operation, and the corresponding relationship between the operation data determined as the loop operation and the experimental subset and the parameter subset is established, so that the execution result of each execution instruction can meet the test requirement, and the normal test is ensured, and the reliability of the test result is improved.

[0097] Specifically, when the time point of the operation time data is the inflection point of the parameter subset, it indicates that before the time point, it represents the end of an execution instruction, and after the time point, it represents the beginning of an execution instruction; when the time point of the operation time data is not the inflection point of the experimental subset, it indicates that the experimental data does not meet the test requirement data.

[0098] Therefore, when it is determined that the experimental data at the time point does not meet the test requirement data, the historical parameter data is judged to determine whether the execution instruction before the time point is the same as the execution instruction after the time point, if the same, it indicates that the instruction is re-executed, so that the purpose of the operation data is determined as a loop operation, so that the experimental data can meet the test requirement.

[0099] Further, the result C judgment method is:

[0100] The historical experimental data before the inflection point is judged to obtain the data change rule of the corresponding experimental collection item; wherein the data change rule can be obtained by a mathematical statistical analysis algorithm or determined by a machine learning algorithm.

[0101] The historical operation data corresponding to the operation time data is matched with the historical parameter data to determine the parameter item modified by the historical operation data;

[0102] Based on the modified parameter item, the pre-modification parameter item data is compared with the historical experimental data before the inflection point, and the post-modification parameter item data is compared with the historical experimental data after the inflection point, to determine the relationship between the data change of the corresponding parameter item and the data change of the experimental data, and obtain a first data change relationship; a corresponding relationship between the data change rule, the first data change relationship and the corresponding operation instruction is established, and an intervention relationship is obtained.

[0103] In the embodiment, after determining that the operation purpose of the historical operation data is to perform data adjustment on the historical parameter data, data change is performed on the historical experimental data before the inflection point, so that, according to the data change rule of the experimental data, the data change rule is taken as a judgment index for starting the operation, and it is determined whether the parameter data needs to be modified; by determining the modified parameter item and the corresponding modified data amount, a data relationship between the data change of the modified parameter item and the data change of the experimental data is constructed, and then the data adjustment amount when performing parameter adjustment is determined, so that the true triaxial test equipment can adaptively adjust the test parameters of the test equipment according to the real-time collected experimental data, ensure the smooth progress of the test, and improve the reliability of the test results.

[0104] Specifically, when the time point of the operation time data is the inflection point of the experimental subset but not the inflection point of the parameter subset, it indicates that there can be two cases at the time point in the test process: the first case is that the test result meets the test requirement; and the second case is that the experimental data is mutated in the test process.

[0105] The first case: the test result meets the test requirement, and the corresponding execution instruction continues to be executed. If human intervention is performed on the execution instruction meeting the test requirement, the next execution instruction should be executed, but the execution instruction does not change, which is inconsistent with the actual situation, and thus the first case is not established.

[0106] The second case: the experimental data is mutated, and the corresponding execution instruction continues to be executed. If human intervention is performed on the mutated experimental data, since the execution instruction does not meet the desired test requirement, the execution instruction needs to be executed again. Since the experimental data is mutated, it indicates that the parameter data corresponding to the execution instruction cannot meet the test requirement of the rock sample, and thus the operation needs to adjust the data of the execution instruction, so that the adjusted instruction can meet the test requirement. This case is consistent with the actual situation, and thus it is determined that the purpose of the operation data is to modify the parameter of the execution instruction.

[0107] Further, the result D judgment method is:

[0108] The experimental subset in the corresponding time interval is divided into first experimental sub-data before the time point and second experimental sub-data after the time point according to the time point of the operation time data;

[0109] The first data change rate and the second data change rate are obtained by performing data change rate judgment on the first experimental sub-data and the second experimental sub-data;

[0110] Based on the historical operation data, the adjustment result of the loading frequency modulation parameter item in the corresponding operation instruction is determined to obtain the adjustment data amount, and the relationship between the adjustment data amount and the data change rate is determined based on the difference between the adjustment data amount and the first data change rate and the second data change rate, to obtain the second data change relationship. The corresponding relationship between the first data change rate, the second data change relationship and the corresponding operation instruction is constructed to obtain the intervention relationship.

[0111] In the embodiment, by taking the time point of the operation time data as the reference, the experimental subset in the corresponding time interval is divided, and the data change rate before the intervention and the data change rate after the intervention are determined, and then the start condition of the intervention and the target data of the intervention are determined. Then, by judging the adjustment data amount in the historical operation data and judging the data change relationship between the adjustment data amount and the difference between the first data change rate and the second data change rate, the intervention amount at the time of intervention can be calculated according to the data change relationship, so that the intervention is more accurate and effective, and the normal operation of the test is ensured, and the reliability of the test result is improved.

[0112] Specifically, when the time point of the operation time data is not the inflection point of the experimental subset and the inflection point of the parameter subset, it indicates that the experimental data has not reached the test requirement and the execution instruction has not been executed when the intervention is performed.

[0113] When the time point is not the inflection point of the parameter subset, there are two cases: the first case is to adjust the parameter; the second case is to adjust the loading rate.

[0114] If the first case is to adjust the parameter, after changing the data value of the parameter item in the historical parameter data, the corresponding collected experimental data will also change, thereby forming an inflection point. Since the time point is not the inflection point of the experimental subset, it reflects that the collected experimental data is not abnormal, and the test process without abnormality theoretically does not need to be intervened by adjusting the parameter, which is inconsistent with the actual situation, and then it is determined that the purpose of the intervention is not to adjust the data value of the parameter item in the test process.

[0115] If the second case is adjusted, the loading rate, after changing the loading rate of the historical parameter data, the historical parameter data does not change, so that the changed experimental data does not change, forming an inflection point, so the time point is not the inflection point of the experimental subset, which is consistent with the actual situation, and then determines that the purpose of the intervention is to adjust the loading rate.

[0116] When it is determined that the loading rate is adjusted, the data change rate of the experimental data before adjustment and the data change rate of the experimental data after adjustment are determined, the starting factor of adjusting the loading rate and the final adjustment target are determined, so that the normal start and normal adjustment of the loading rate are ensured; the operation amount of the operation data and the data change relationship between the corresponding adjusted experimental sub-data are determined, so that the loading rate can be accurately and effectively adjusted when it is determined that the loading rate needs to be adjusted.

[0117] Further, step S4 is:

[0118] The historical parameter data corresponding to the test and the corresponding historical operation data are obtained, and the historical parameter data is modified based on the historical operation data to obtain ideal parameter data corresponding to the test;

[0119] The historical parameter data of each test and the rock property data corresponding to the test are matched to determine the parameter items corresponding to different rock properties;

[0120] The ideal parameter data of the same rock property parameter item is statistically analyzed, and the ideal parameter data of the same parameter item under different rock properties is statistically analyzed to determine the relationship between the rock property and the data value of the parameter item, and obtain the basic parameter relationship.

[0121] In this embodiment, by integrating the historical operation data in the test process into the historical parameter data, the accuracy and precision of the parameter data are maximized, by using big data analysis means, the historical parameter data and the rock property data of multiple tests are matched, so that the parameter items corresponding to different rock properties are determined, and the ideal parameter data corresponding to the parameter items under the same rock property are statistically analyzed, so that the best data value of the corresponding parameter item under the corresponding rock property is determined, and the best data value of the same parameter item under different rock properties is statistically analyzed, so that the relationship between different rock properties and the parameter item is determined, and the parameter data evaluated by the system is more accurate when the unknown rock is tested, the number of system adaptive interventions is reduced, and the efficiency, accuracy and reliability of the test are improved.

[0122] Specifically, since the initial historical parameter data is evaluated by the staff according to the rock characteristic data, and there is an intervention behavior to intervene in the test during the test process, it is shown that the initial evaluated historical parameter data has a large error. In order to reduce the error, the data relationship between the historical parameter data, the historical operation data and the rock characteristic data of the corresponding rock sample can be constructed, so as to ensure that the true triaxial test equipment can directly evaluate the required parameter data during the test according to the rock characteristic data input by the staff, and then improve the accuracy.

[0123] In the embodiments of the application, the self-adaptive intelligent true triaxial mechanical test method based on the above parameters comprises the following steps:

[0124] The database establishment module is used for performing a test on a known rock sample by a true triaxial test equipment based on known test data, performing data monitoring on the true triaxial test equipment during the test, and obtaining historical parameter data, historical operation data, historical experimental data of the true triaxial test equipment and rock characteristic data of the rock sample.

[0125] The data relationship construction module is used for obtaining operation time data of the historical operation data, dividing the historical parameter data and the historical experimental data based on the operation time data, obtaining a parameter subset and an experimental subset, analyzing the parameter subset and the experimental subset, determining operation instructions required in different test situations and operation data corresponding to the operation instructions, obtaining an intervention relationship, and comprehensively analyzing the historical parameter data and the rock characteristic data, determining a data relationship between the rock characteristic and the test parameters of the true triaxial test equipment, and obtaining a basic parameter relationship.

[0126] The self-adaptive adjustment module is used for obtaining rock characteristic data of a rock sample to be tested, generating test parameter data required for the test according to the basic parameter relationship, performing a test on the rock sample to be tested based on the test parameter data and performing data monitoring, obtaining rock sample experimental data, and judging and performing data self-adaptive adjustment on the rock sample to be tested based on the intervention relationship.

[0127] Compared with the existing true triaxial test system, the application improves the analysis rate and ensures the reliability of the test results.

[0128] The above only describes the preferred embodiments of the application and is not intended to limit the application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. An intelligent true triaxial mechanical test method based on parameter self-adaption, characterized in that: The method comprises the following steps: S1: a true triaxial test device tests a known rock sample based on known test data, monitors test process data of the true triaxial test device, and obtains historical parameter data, historical operation data, historical test data and rock characteristic data of the rock sample; S2: operation time data in the historical operation data is obtained, the historical parameter data and the historical test data are marked at corresponding time points based on the operation time data, the historical parameter data and the historical test data are divided according to the marked time points, and a parameter subset and a test subset are obtained; The S2 comprises the following steps: S21: the historical test data is divided based on the historical parameter data, execution instructions at each time point in the historical test data and execution time lengths of the corresponding execution instructions are determined; S22: execution instructions corresponding to the operation time data are determined based on the operation time data, a data selection interval of the historical parameter data is determined according to the execution time lengths of the execution instructions, the historical parameter data is selected according to the data selection interval, and a parameter subset is obtained; S23: the historical test data is divided based on the parameter subset, and a test subset is obtained; S3: the parameter subset and the test subset are analyzed based on the operation time data, operation instructions required under different test results and operation data corresponding to the operation instructions are determined, and an intervention relationship is obtained; The S3 is specifically as follows: An inflection point of the parameter subset and the test subset is determined, and whether the operation time data is the inflection point of the parameter subset and the test subset is judged based on the operation time data; The inflection point of the parameter subset is the start time data and the end time data of each execution instruction in the parameter subset; The inflection point of the test subset is a time point at which test data collected in the test subset meets test requirements and a time point at which the test data changes suddenly; Result A: if the time point of the operation time data is the inflection point of the parameter subset and the test subset, it is determined that the operation instruction of the corresponding historical operation data is an interrupt operation, and the corresponding intervention relationship is determined; Result B: if the time point of the operation time data is the inflection point of the parameter subset but not the inflection point of the test subset, it is determined that the operation instruction of the corresponding historical operation data is a cyclic operation, and the corresponding intervention relationship is determined; Result C: if the time point of the operation time data is the inflection point of the test subset but not the inflection point of the parameter subset, it is determined that the operation instruction of the corresponding historical operation data is a parameter modification operation, and the corresponding intervention relationship is determined; Result D: if the time point of the operation time data is neither the inflection point of the test subset nor the inflection point of the parameter subset, it is determined that the operation instruction of the corresponding historical operation data is a load frequency modulation operation, and the corresponding intervention relationship is determined; S4: the historical parameter data and the rock characteristic data are comprehensively analyzed, a data relationship between rock characteristics and test parameters of the true triaxial test device is determined, and a basic parameter relationship is obtained; S5: obtaining rock characteristic data of a rock sample to be tested, generating test parameter data required for the test according to the basic parameter relationship, testing and data monitoring the rock sample to be tested based on the test parameter data, and obtaining rock test data; judging and self-adapting the test data based on the intervention relationship.

2. The intelligent true triaxial mechanical test method based on parameter self-adaption according to claim 1, characterized in that, If the time point corresponding to the operation time data is located at an intersection point between two execution instructions in the S22, the execution time length of the two execution instructions is summed as a data selection interval according to the time sequence, the historical parameter data is selected according to the data selection interval, and a parameter subset is obtained. The intersection point is the intersection position of the end of one instruction and the beginning of another instruction. 3.The parameter-adaptive intelligent true triaxial mechanical test method according to claim 1, characterized in that, The result A judgment method is: determining a time interval containing an experimental subset corresponding to a time point based on operation time data, and determining a turning point of the experimental subset based on the time interval; if it is determined that there are multiple turning points in the time interval, it is determined that the operation instruction corresponding to the historical operation data is an interrupt operation, and a corresponding relationship between the turning point data of the corresponding experimental subset and the operation instruction is established, and an intervention relationship is obtained. 4.The parameter-adaptive intelligent true triaxial mechanical test method according to claim 1, characterized in that, The result B judgment method is: comparing the historical experimental data with the corresponding test requirement data to determine whether the historical experimental data meets the test requirement data; if the historical experimental data does not meet the test requirement data, the execution instruction before the corresponding time point and the execution instruction after the corresponding time point on the parameter subset are compared to determine whether the execution instruction before the corresponding time point and the execution instruction after the corresponding time point are repeated instructions; if it is determined that the operation instruction is a repeated instruction, it is determined that the operation instruction is a loop operation, and the operation instruction and the corresponding experimental subset are related to obtain an intervention relationship, otherwise, it is determined that the historical operation data is invalid operation.

5. The intelligent true triaxial mechanical test method based on parameter self-adaption according to claim 1, characterized in that, The result C judgment method is: judging the data change of the historical experimental data before the turning point to obtain the data change rule of the corresponding experimental acquisition item; matching the historical operation data corresponding to the operation time data with the historical parameter data to determine the parameter item modified by the historical operation data; based on the modified parameter item, comparing the parameter item data before the modification with the historical experimental data before the turning point, and comparing the parameter item data after the modification with the historical experimental data after the turning point, to determine the relationship between the data change of the corresponding parameter item and the data change of the experimental data, and obtain a first data change relationship; and establishing a corresponding relationship between the data change rule, the first data change relationship and the corresponding operation instruction to obtain an intervention relationship.

6. The intelligent true triaxial mechanical test method based on parameter self-adaption according to claim 1, characterized in that, The result D judgment method is: dividing the experimental subset in the corresponding time interval into first experimental sub-data before the time point and second experimental sub-data after the time point according to the time point of the operation time data; judging the data amount change rate of the first experimental sub-data and the second experimental sub-data to obtain the data change rate of the two experimental sub-data before and after the time point, and respectively denoted as a first data change rate and a second data change rate; Based on the historical operation data, the adjustment result of the loading frequency modulation parameter item in the corresponding operation instruction is determined to obtain an adjustment data amount, and based on the difference between the adjustment data amount and the first data change rate and the second data change rate, the relationship between the adjustment data amount and the data change rate is determined to obtain a second data change relationship; a corresponding relationship between the first data change rate, the second data change relationship and the corresponding operation instruction is constructed to obtain an intervention relationship. 7.The parameter-adaptive intelligent true triaxial mechanical test method according to claim 1, wherein, The S4 is: Obtain historical parameter data and corresponding historical operation data of the corresponding test, and modify the historical parameter data based on the historical operation data to obtain ideal parameter data of the corresponding test; Match the historical parameter data of each test with the rock property data of the corresponding test to determine the parameter items corresponding to the properties of different rocks; Statistically analyze the ideal parameter data of the same rock property and the ideal parameter data of the same parameter item under different rock properties to determine the relationship between the rock property and the data value of the parameter item, and obtain a basic parameter relationship.

8. The test system based on the intelligent true triaxial mechanical test method with parameter self-adaptation according to any one of claims 1-7, characterized in that: The database establishment module, the data relationship construction module and the adaptive adjustment module are included. The database establishment module, the true triaxial test equipment based on known test data tests the known rock sample, and the data of the true triaxial test equipment in the test is monitored to obtain the historical parameter data, the historical operation data, the historical experimental data of the true triaxial test equipment and the rock property data of the rock sample; The data relationship construction module obtains operation time data of the historical operation data, and divides the historical parameter data and the historical experimental data based on the operation time data to obtain a parameter subset and an experimental subset; the parameter subset and the experimental subset are analyzed to determine the operation instruction and the operation data of the corresponding operation instruction required under different test conditions to obtain an intervention relationship; the historical parameter data and the rock property data are comprehensively analyzed to determine the data relationship between the rock property and the test parameter of the true triaxial test equipment to obtain a basic parameter relationship; The adaptive adjustment module obtains the rock property data of the rock sample to be tested, generates the test parameter data required for the test according to the basic parameter relationship, and judges and adaptively adjusts the data of the rock sample to be tested based on the intervention relationship.

Images