Diesel engine destructive damage monitoring and early warning method based on thermotechnical data driving

Abstract

The invention provides a diesel engine destructive damage monitoring and early warning method based on thermotechnical data driving. The diesel engine destructive damage monitoring and early warning method comprises the following steps that the symptom opportunity of diesel engine rack destructive damage is captured, and sensitive parameters are identified; and carrying out destructive damage early warning on the diesel engine rack. The method has the beneficial effects that the human intervention process of sensitive indexes and detection opportunity control marks is avoided, so that the warning effect has relatively high repeatability and extremely high reliability; according to the early warning method provided by the invention, the working intensity of operators is reduced, the subsequent destructive damage identification knowledge can be continuously expanded, the safety warning of performance verification of various parts is met, and the early warning method has an extremely high value for lightweight development of the diesel engine.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of diesel engine bench monitoring, and particularly relates to a diesel engine destructive damage monitoring and early warning method based on thermal data driving. BACKGROUND

[0002] Bench test is an indispensable link for diesel engine research and performance identification, and a new diesel engine needs to be identified through multiple rounds of bench performance and durability verification to determine the technical state of the design goal of low cost, high power and high reliability.

[0003] Problems existing in the prior art: (1) In order to prevent the diesel engine from being damaged, the diesel engine controller has certain water temperature, oil temperature, exhaust temperature and oil pressure protection measures, but in order to meet the high reliability and low cost target, the number of sensors installed on board is extremely limited, the diesel engine is not sensitive to the abnormal running state, especially in the high risk limit verification process of high transient state and overload, it is difficult to effectively warn, and the serious fault of the research test occurs frequently; (2) The current diesel engine thermal collection bench has complete thermal detection parameter collection and alarm functions, but its core main function is mainly for process control of the running condition, including adjusting the water temperature, oil temperature, oil supply and load in the test according to the test specification, the safety alarm limit depends on the manual experience setting, and in order to meet the normal operation of the diesel engine in the whole working condition range, the fault alarm tolerance limit is relatively wide, which cannot reflect the time-varying deterioration state of the diesel engine after entering the working condition, the response warning degree of the high transient fault is not high, and the fault alarm opportunity is late, which cannot protect the diesel engine in time; (3) In the verification of the new research diesel engine, experienced test personnel are usually configured to test the equipment and diesel engine safety, but the abnormal process is random, and it is difficult for personnel to control the timely shutdown opportunity, the fault is exposed in the late stage, which has caused serious loss, and the high mechanical load factor of the light weight design of the diesel engine makes it difficult for personnel to respond to the window period of safety monitoring. SUMMARY

[0004] Therefore, the present application aims to provide a diesel engine destructive damage monitoring and early warning method based on thermal data driving to solve at least one of the above problems existing in the prior art.

[0005] To achieve the above purpose, the technical scheme of the present application is as follows: The diesel engine destructive damage monitoring and early warning method based on thermal data driving comprises the following steps: S1, capturing the sign opportunity of diesel engine bench destructive damage and identifying sensitive parameters; S2, diesel engine bench destructive damage early warning; In step S1, the signs of diesel engine bench destructive damage are captured and sensitive parameters are identified, including: S11, thermal data collection and arrangement, forming a data resource; S12, based on the data resource, data preprocessing is performed to form a data sample; S13, based on the thermal data reflecting the time of destructive failure, a moving window function is constructed; S14, based on the data sample, the characteristic value is calculated to form a data sample matrix; S15, based on the moving window function and the data sample matrix, data set division is performed to form a training set and a test set; S16, based on the training set and the test set, the random forest model is trained, and the test set prediction accuracy is obtained; S17, based on the test set prediction accuracy, the test set accuracy is determined; S18, based on the random forest model, sensitive parameters are extracted; In step S2, the diesel engine bench destructive damage early warning includes: S21, diesel engine full working condition data preparation; S22, based on the diesel engine full working condition data, the test data working condition is classified; S23, based on the test data working condition of step S22, the random forest model is constructed and trained, and the random forest prediction model is output; S24, based on the random forest prediction model of step S23, the test bench model is deployed; S25, collecting the warning set during diesel engine operation; S26, whether the warning set is equal to the damage knowledge set, if yes, jump to step S25, otherwise, proceed to the next step; S27, warning and driving the bench emergency action position.

[0006] Further, in step S11, the thermal data collection and arrangement form a data resource, including: Collecting historical stock fault process segment data, including test bench synchronous acquisition data and auxiliary explosion pressure, supercharger speed and smoke data collected by mobile detection instruments; Based on the damage site combination when the fault occurs, classification is performed to form a data resource.

[0007] Further, in step S12, based on the data resource, data preprocessing is performed to form a data sample, including: Unit transformation is performed on the data resource, abnormal values are removed using the median value method, missing data items are supplemented with linear interpolation, and a data sample is formed.

[0008] Further, in step S13, based on the thermal data, the destructive failure reflection time is constructed, including: Thermal data on destructive failure reflection time multiplied by a set of multiple, as the initial size of the window; The classification function is constructed with the median of the window as the classification boundary.

[0009] Further, in step S14, based on the data sample, the characteristic value is calculated, and the data sample matrix is formed, including: The data sample of step S12 is extracted according to the time increment, the value change speed and the value change acceleration, and combined with the original data to form a data set; Each thermal parameter in the data set is segmented according to the constructed window size; The segmentation process is intercepted according to the set sliding window, forming a data sample matrix.

[0010] Further, in step S15, based on the moving window function and the data sample matrix, the data set is divided to form the training set and the test set, including: Based on the moving window function, the target training data is obtained, combined with the data sample matrix, the sample order sequence is shuffled, and the training set and the test set are divided according to the set mode.

[0011] Further, in step S16, based on the training set and the test set, the random forest model is trained, and the test set prediction accuracy is obtained, including: The thermal parameter data in the training set and the test set is normalized; The normalized training set data is substituted into the random forest model, and the moving window function is trained as the training target; The test set is tested to obtain the test set prediction accuracy.

[0012] Further, in step S17, based on the test set prediction accuracy, the test set accuracy is determined, including: Based on the test set prediction accuracy, the adaptability of the moving window function is determined; if the accuracy is less than the set value, the window size is increased, and the process is restarted from step S14 until the accuracy is equal to the set value.

[0013] Further, in step S18, based on the random forest model, the sensitive parameter is extracted, including: Based on the random forest model, the significant parameter is extracted as the monitoring sensitive parameter of subsequent damage; the time sequence significance deviation is set as the sign of damage.

[0014] Further, in step S21, the diesel engine full working condition data is prepared, including: Arrange a set of diesel engine historical operation universal characteristic data; In step S22, the test data working condition is classified, including: According to the form of the speed-load map, a certain number of divided working conditions are divided; In step S23, the random forest model is constructed and trained, including: Random model construction; training data set construction; output prediction model; In step S24, the test bench model is deployed, including: Random forest prediction model deployment; Working condition classification map query; Arrange a certain number of parallel loop random forest prediction models; Arrange the working condition classification query map of the running process.

[0015] Compared with the prior art, the diesel engine destructive damage monitoring and early warning method based on thermal data driving has the following beneficial effects: (1) The present application provides a diesel engine destructive damage monitoring and early warning method based on thermal data driving, which is used for rapid monitoring and early warning of diesel engine destructive failure in a test bench, improves the safety of the diesel engine test bench, and solves the problem that in the traditional verification process, the operator with rich verification experience as the test master system main test, due to the personnel fatigue factor in the continuous monitoring process, as well as the difference in personnel perception and operation timeliness, and the mechanical load of the main working parts of the diesel engine is generally high, the fault occurs in a short time, and it is difficult for the personnel to make effective action response from monitoring experience judgment to meet the rapid disposal of the test process.

[0016] (2) In order to advance the test bench early warning opportunity and accurately determine the sensitivity of the thermal parameter, avoid the influence of artificial experience marking on parameter determination, a sliding window function and a random forest model are constructed, the index is evaluated to determine the position of the destructive damage detection opportunity marker, and the sensitive parameters under the corresponding detection opportunity are further determined, so as to avoid the problem that the light weight, high strength and high value diesel engine verification appears failure and is scrapped.

[0017] (3) In order to deploy the early warning strategy in the test bench and have the destructive damage early warning push function, the present application provides a diesel engine bench destructive damage early warning method, which combines and encodes the thermal parameter detection knowledge and the deviation amount, and reports the early warning in real time through the test bench wheel monitoring mode, so that the subsequent expanded identification model can be continuously increased, and the test bench process control system is used.

[0018] (4) In order to solve the problem of needing more state abnormal data training in the traditional process, the abnormal state warning process is realized by using the deviation characteristics of normal working parameters and combining the known destructive damage knowledge, the prediction data source is relatively easy to obtain, the abnormal state warning process has combination, avoids the misoperation caused by single parameter abnormality, reduces the false alarm rate of the test bench, and provides a reliable method for reliable test process.

[0019] (5) The application provides a diesel engine destructive damage monitoring and early warning method based on thermal data driving, solves the conversion of inventory thermal parameters to the test bench monitoring and early warning, reduces the demand of high risk on the working strength of test personnel, has the warning coding process, meets the test bench process control deployment and positioning information pushing function, makes the operator quickly remove the abnormal state according to the warning information, and decides the subsequent test progress, has a positive effect on the diesel engine performance and reliability verification work. Meanwhile, based on the sliding window marking fault process, the prediction accuracy criterion is used to accurately grasp the abnormal state generation opportunity and sensitive parameters, reduce the artificial experience dependence, and the abnormal state identification knowledge has obvious effect. BRIEF DESCRIPTION OF DRAWINGS

[0020] The drawings that form a part of the present application are used to provide further understanding of the present application, the schematic embodiments of the present application and the description thereof are used to explain the present application, and do not constitute improper limitation on the present application. In the drawings: Figure 1 The flowchart of the diesel engine test bench destructive damage symptom opportunity capture and sensitive parameter identification process based on thermal data driving described in the embodiment of the present application; Figure 2 The work flowchart of the diesel engine test bench destructive damage early warning described in the embodiment of the present application; Figure 3 The schematic diagram of the non-destructive damage warning (heat exchanger leakage shutdown) described in the embodiment of the present application; Figure 4 The schematic diagram of the destructive damage warning (burning and shaft holding shutdown) described in the embodiment of the present application; Figure 5 The schematic diagram of the abnormal data point collection of the collection system described in the embodiment of the present application; Figure 6 The schematic diagram of the IQR criterion rejection and re-linear interpolation described in the embodiment of the present application; Figure 7 The result schematic diagram of the moving window function described in the embodiment of the present application; Figure 8 The schematic diagram of the new sequence constructed by the sliding window described in the embodiment of the present application; Figure 9 The schematic diagram of the merged target sequence described in the embodiment of the present application; Figure 10 Effect diagram of initial default window size described in embodiments of the present application; Figure 11 Effect diagram of adjusted window size described in embodiments of the present application; Figure 12 Optimal recognition timing diagram described in embodiments of the present application; Figure 13 Sensitive parameter recognition diagram described in embodiments of the present application; Figure 14 Diesel engine normal operation universal characteristic oil consumption rate curve diagram described in embodiments of the present application; Figure 15 Test data working condition classification diagram described in embodiments of the present application; Figure 16 Oil consumption rate training parameter diagram described in embodiments of the present application; Figure 17 Bench normal working oil consumption rate data verification parameter diagram described in embodiments of the present application. DETAILED DESCRIPTION

[0021] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0022] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application. In addition, the terms "first", "second" and the like are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features limited by "first", "second" and the like can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0023] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connection", "linking" should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integrally connected; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through intermediate medium, or the internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0024] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0025] As shown in Figure 1 A method for capturing the sign of diesel engine bench destructive damage based on thermal data driving and sensitive parameter identification, specifically as follows: A1: Thermal data collection and arrangement with state Collect historical inventory fault process segment data, including test bench synchronous acquisition data and auxiliary explosion pressure, supercharger speed, smoke data collected by mobile detection instrument, based on the damage site combination when the fault occurs, classify, form data resources for subsequent identification.

[0026] A2: Data preprocessing Unit conversion is performed on the data resources collected in step A1 to avoid parameter variables less than 1, data outliers are removed using the median value method, deviations introduced by unstable acquisition equipment or detection personnel reading during the test process are solved, missing data items are supplemented with linear interpolation to ensure data integrity.

[0027] A3: Constructing a moving window function The 3 times of the reflection time of the destructive failure of the diesel engine thermal data is taken as the initial size of the window, and a 2-class function is constructed with the median of the window as the classification boundary. The normal operation process before the fault occurs is marked as 0, and the fault occurs after the thermal data with the sensing feature is marked as 1.

[0028] A4: Feature value calculation The data sample after data preprocessing in step A2 is extracted according to the time increment, the value change speed and the value change acceleration, and is combined with the original data in step A2 to form a data set. Based on the constructed window size, each thermal parameter in the data set formed in step A2 is segmented. The segmentation process is intercepted according to the sliding window of step A1, forming a data sample matrix of each thermal parameter.

[0029] A5: Data set division The result of the moving window function is taken as the target training data, combined with the data sample matrix constructed in step A4, the sample order sequence is shuffled, and according to the 7:3 mode, the training set and the test set of the random forest model are divided.

[0030] A6: Random forest model training The thermal parameter data in the training set and test set data obtained in step A5 is normalized, the normalized training set data is substituted into the random forest model, and the data of the moving window function is trained as the training target, and the test set is further tested to obtain the prediction accuracy of the test set; A7: Test set accuracy determination According to the test set accuracy obtained in step A6, the window function adaptability is determined, if the accuracy is less than 100%, the window function window size of step A3 is increased, and the processing is restarted to step A4 until the accuracy is equal to 100%, then the next step is performed.

[0031] A8: Sensitive parameter extraction The significance parameter after the random forest model prediction of step A7 is extracted, and the time sequence significance deviation of not more than ±3s is taken as the sign opportunity of damage and injury, and the significance parameter is extracted as the monitoring sensitive parameter of subsequent damage and injury.

[0032] The specific implementation is as follows: B1, in the process of collecting and arranging thermal data with state, the original test stand working condition data record increment needs to meet the 1s recording interval, at the same time, the manual asynchronous recording data such as explosion pressure, supercharger speed and smoke degree are aligned according to time label, forming relatively complete thermal parameter data resources; The data is arranged based on the time of each fault shutdown, and the thermal data within 2min before shutdown is extracted. If the 2min before shutdown does not include diesel engine normal working data, it is considered that the arranged data does not meet the damage and injury judgment criterion, and the test bench equipment can be warned and the data is excluded.

[0033] B2, in the data preprocessing process, unit conversion is carried out according to the judgment criterion that the data sample is less than 1, to prevent inaccurate identification of training model, and after sorting the 2min data results of each set according to time increment, since the thermal parameters of diesel engine have damping, the order of each parameter is calculated by 7 points IQR, and the abnormal value is removed based on Q1-IQR and Q3+IQR, which does not cause abnormal judgment. After data removal, linear interpolation is carried out on the missing results, and the expression is as follows: ; In the formula, is the data to be interpolated at t time, is the data of the last recording time, is the time that needs to be linearly interpolated, is the last time of the data to be interpolated at t time, is the next time of the data to be interpolated at t time; Further, the date and time series are deleted; B3, in the moving window function, the window size N is initially defined as N=30, and the window function expression is as follows: ; In the formula, i is the serial number in the window (the value range is 1 to 30); The function expression of the target result in the window is as follows: ; In the formula, is the serial number in the window, is the size of the window (N=30); B4, in the characteristic value calculation, based on the data samples obtained in step B2, the change speed and change acceleration of each variable are extracted, and the step B2 result is combined into a data set, further, the data set is divided by the moving window size, and each variable in the 2min sample is taken as a sample in step B3. N samples are taken at an interval of 1 sample, forming M New sequence matrix.

[0034] B5, in the data set division, first, each variable sequence matrix generated in step B4 is taken as training data, the window data constructed in step B3 is taken as target data, the total data set is synthesized, and the sample sequence is randomly shuffled. According to the sample amount of 7:3, the data set is divided, and N×7 / 10 samples are taken as the training set and N×3 / 10 samples are taken as the test set.

[0035] B6, in the random forest model training, the training set and test set obtained in step B5 are normalized using the following expression: ; In the formula, is the normalized feature, is the minimum value in the feature , is the maximum value in the feature ; According to the number of 50 decision trees and 1 minimum leaf number, a random forest model is constructed, the training set is trained using the normalized result, the test set is further predicted using the normalized result, and the accuracy of the model prediction result and the actual result is extracted.

[0036] B7, in the accuracy rate determination of the test set, the accuracy of the identification of the damage failure symptom identification opportunity is focused on. Based on the accuracy rate of the model prediction result and the actual result extracted after the random forest training in step B6, if the accuracy rate is less than 100%, the window size N of the window function in step B3 is increased, and step B4 is restarted for processing. The model prediction result and the actual result extracted in step B6 are used as the target, and the last N value is determined after multiple iterations. In order to reduce the number of iterations, the 2 classification dividing point of the window function in step B3 is manually intervened to be placed at the normal time 10s before the damage of the diesel engine.

[0037] B8, in the sensitive parameter extraction, the importance output result of the random forest model prediction accuracy of 100% is used to find the results with adjacent importance indicators greater than 0.3 and the corresponding moving window time sequence, and the parameter is determined as no less than 2 as the criterion to determine the best marking opportunity of the 2 classification dividing point of the window function in B3. In the full flux random forest test, the parameters and indicators with importance greater than 0.3 are extracted.

[0038] As shown in Figure 2 , a diesel engine bench destructive damage early warning method is as follows: C1, diesel engine full working condition data preparation including arranging a set of historical operating universal characteristic data of the verification target diesel engine.

[0039] C2, test data working condition classification including dividing into 16 segmented working conditions according to the speed-load map.

[0040] C3: random forest model construction and training including random model construction, training data set construction and output prediction model; in matlab, 24 sensitive thermal parameters are used to form a speed, torque, classification mark, and are used as a classification mark training target for model training, and 24 trained model codes are output.

[0041] C4: test bench model deployment including random forest prediction model deployment and working condition classification map query; in the real-time host of the test bench process control, 24 parallel loop random forest prediction models are arranged, and the running process working condition classification query map is arranged.

[0042] C5: collecting warning set in diesel engine operation including warning code, which is used to form the control system in the quick identification logic.

[0043] C6: Determine if the warning set is equal to the damage knowledge set Including damage knowledge encoding, warning encoding, and damage knowledge encoding comparison to determine if there is an alarm condition.

[0044] C7: Set the warning and drive the emergency action position of the test bench Including setting method, to determine if the predicted drive and test bench action logic are the same.

[0045] The specific implementation is as follows: D1, in the diesel engine full working condition data preparation, a set of diesel engine historical operation universal characteristic data is sorted out, including working condition change process and stable working process, data recording interval is 1s, each working condition point includes entering process and working condition value within 5min of stable process.

[0046] D2, in the test data working condition classification, according to the speed-load map, it is divided into 16 sub-working conditions, among which, in the vehicle characteristic, the maximum torque speed to the idle working speed is divided into independent working conditions, the maximum torque speed to the rated point speed range is divided into 5 speed gears, the load is divided into three zones according to 0%-50%, 50%-75%, 75%-100%, and the speed is classified and identified from small to large-load from small to large; In the propulsion characteristic, the (highest speed-lowest speed) / 2 to the idle working speed is divided into an independent sub-working speed, and the other working condition classification is the same as the vehicle.

[0047] D3: In the random forest model construction and training, set the parameters, use each sensitive parameter of 24 thermal parameters combined with speed and torque as a data set, perform normalized data processing, merge with the classification mark formed in step D2, and take step D2 as the training target, monitor whether the error of each combined parameter after training reaches 100%, if the training accuracy is insufficient, adjust the classification range, and finally output the 24 random forest models after training as C code; D4: In the random forest model deployment of the test bench, first perform normalization processing, and in real-time species construction, 24 random forest model codes are parallel round seeking, and at the round seeking time, the normalized data of the corresponding sensitive thermal parameters in the previous 7 are input to carry out prediction; Synchronously deploy the working condition classification query map of step D2 in the test bench; At the same time, compare the random forest prediction classification and the working condition query classification, if the prediction mark is the same as the running working condition classification mark, it is recorded as "0", if it is different, it is recorded as "1".

[0048] D5: Collect the warning set during diesel engine operation; Step D4 is sorted in sequence to form a 16-bit numerical code.

[0049] D6: In the determination of whether the warning set is equal to the damage knowledge set, the 24 thermal parameters are sorted according to the warning set collection order in step D5, converted into knowledge codes, and marked with damage annotations. When the warning set and the knowledge set are the same, the warning indication is output, and the emergency setting symbol is pushed; if the warning set and the knowledge set are different, step D5 is continued to collect the warning set; D7: In the warning and driving setting of the emergency action platform, the warning action word is associated with the platform soft emergency stop, and the execution process is consistent. If the platform is determined to be in the emergency stop state with "1", the warning in step D6 is unchanged; if the platform is determined to be in the emergency stop state with "0", the output result is inverted.

[0050] Embodiment one: E1, thermal data collection and arrangement with state, data compliance identification for diesel engine damage identification, with 2min or more slow parking process, including diesel engine cooling parking operation specification, diesel engine abnormal fault damage degree is not high, not consistent with transient history, test bench original control process warning or diesel engine controller warning action, specific screening comparison as shown in Figures 3-4 .

[0051] E2, in the data preprocessing process, the problem of data quality is solved, including parameter jump introduced by unstable test bench acquisition instrument, and data acquisition label alignment and data interpolation of external mobile device under insufficient test bench integration capability, specific solution before and after data quality solution comparison as shown in Figures 5-6 .

[0052] E3, in the construction of moving window function, the problem of inaccurate detection time and subsequent use of parameters is solved, the moving window is constructed, the label time position is determined according to the classification accuracy, and the window data is as shown in Figure 7 .

[0053] E4, in the feature value calculation, the sliding window size is used to control the construction of new sequence under the combination of E2 and parameter change speed and acceleration data, and the new sequence matrix is as shown in Figure 8 .

[0054] E5, in the data set division, the variable sequence matrix generated in step E4 is combined with the window data constructed in step E3, as shown in Figure 9 , the total data set is synthesized, and the sample sequence is randomly shuffled. According to the sample size of 7:3, the data set is divided, N×7 / 10 samples are used as training set, and N×3 / 10 samples are used as test set.

[0055] E6, in the random forest model training, the effect before sliding window size adjustment is as shown in Figure 10 .

[0056] E7、In the accuracy determination of the test set, the effect of the adjusted sliding window size is as shown in Figure 11

[0057] E8、In the sensitive parameter extraction, the importance output result with 100% prediction accuracy of the random forest model is used to find the result with importance index greater than 0.3 and the sequence corresponding to the moving window time, and the criterion that the number of parameters is not less than 2 is used to determine the 2-class demarcation point of the window function in step E3, as shown in Figure 12 ; In the full sample input without sliding window processing, the training targets of all samples before the best marking opportunity are set to 0, the training targets of all samples after the best opportunity are set to 1, the full flux random forest test is performed, and the parameters and indexes with importance greater than 0.3 are extracted, as shown in Figure 13 .

[0058] After the identification by the random forest model, the sensitive identification parameter table corresponding to the destructive damage shown in the following table is as shown in Table 1: Table 1

[0059] Example Two: F1、In the diesel engine full working condition data preparation, the continuous recording of the working condition change process is adopted, as shown in Figure 14

[0060] F2、In the test data working condition classification, 16 segmented working conditions are divided according to the speed-load map, as shown in Figure 15

[0061] F3: In the random forest model construction and training, the 16 working condition classifications of each parameter are predicted as shown in Figure 16

[0062] F4: In the collection of the warning set during the operation of the diesel engine, the sequence of each thermal parameter and the warning code is shown in Table 2.

[0063] Table 2 ID bit 24 23 22 21 20 19 18 17 Parameter RPM Output load Oil temperature Coolant pressure Main gallery pressure Boost pressure Diesel pressure Exhaust pressure ID bit 16 15 14 13 12 11 10 9 Parameter Exhaust pressure Water temperature difference Oil temperature difference Exhaust temperature Camshaft pressure Intake pressure Exhaust pressure rate Exhaust rate of change ID bit 8 7 6 5 4 3 2 1 Parameter Water temperature difference delta acceleration Oil pressure delta acceleration Exhaust temperature acceleration Camshaft pressure rate Main gallery pressure rate Diesel pressure rate RPM fluctuation rate Output load fluctuation rate F5: In the determination of whether the warning set is equal to the destructive damage knowledge set, the warning knowledge code table is shown in Table 3.

[0064] Table 3 Serial number Damage event Status flag bit Warning code 1 Piston ring breakage 011000001000000100000000 608100 2 Cylinder liner damage 000100001100000010000000 10A080 3 Main bearing bush burn 010010000010000001000000 682040 4 Piston scuffing 000010010010000001000000 092040 5 Rocker arm damage 000010000001100000010000 081810 6 Connecting rod big end drop 010010000000100000001000 480808 7 Oil pump gear breakage 000000100001010000000100 021404 8 Intermediate idler breakage 100110000000000000000010 980002 9 Valve clatter 010000010000001000000001 610201 Advantages and beneficial effects of the present application: ​​​​(1) The application provides a diesel engine destructive damage monitoring and early warning method based on thermal data driving, which is used for rapid monitoring and early warning of diesel engine destructive failure in a test bench, improves the working safety of the diesel engine test bench, and solves the problem that in the traditional verification process, the operator with rich verification experience is used as the test master system, due to the personnel fatigue factor in the continuous monitoring process, and the difference in the timeliness of personnel perception and operation, and the fact that the mechanical load of the main working parts of the diesel engine is generally high, the failure occurs instantaneously, the duration time is short, and it is difficult for personnel to meet the rapid disposal of the test process from monitoring experience judgment to effective action response.

[0065] (2) In order to advance the early warning time of the test bench, accurately determine the sensitivity of the thermal parameter, avoid the influence of artificial experience marking on the determination of the parameter, a sliding window function and a random forest model are constructed, the destructive damage detection time is marked according to the index, and the sensitive parameter under the corresponding detection time is further determined, so that the problem that the light, high-strength and high-value diesel engine is scrapped as soon as a fault occurs in the verification process is avoided.

[0066] (3) In order to deploy the early warning strategy in the test bench and have the destructive damage early warning pushing function, the application provides a diesel engine bench destructive damage early warning method, which encodes the thermal parameter detection knowledge and the deviation amount in combination, and reports the early warning in real time through the test bench round monitoring mode, so that the subsequent identification model can be continuously increased, and the test bench process control system is used.

[0067] (4) In order to solve the problem that more state abnormal data training is needed in the traditional process, the application utilizes the deviation characteristics of normal working parameters, combines the known destructive damage knowledge to realize the abnormal state early warning process, the training prediction data is relatively easy to obtain, the generated abnormal state early warning process also has combination, avoids the misoperation caused by single parameter abnormality, reduces the false alarm rate of the test bench, and provides a reliable method for reliable development of the test process.

[0068] (5) The application provides a diesel engine destructive damage monitoring and early warning method based on thermal data driving, solves the conversion of the inventory thermal parameter to the test bench monitoring and early warning, reduces the demand for high-risk work intensity of test personnel, has the early warning coding process, meets the test bench process control deployment and positioning information pushing function, makes the operator quickly remove the abnormal state according to the early warning information, and decides the subsequent test progress, has a positive effect on the performance and reliability verification of the diesel engine. At the same time, based on the sliding window marking fault process, the prediction accuracy determination criterion can accurately grasp the abnormal state generation time and the sensitive parameter, reduce the artificial experience dependence, and the generated abnormal state identification knowledge has remarkable effect.

[0069] The above merely provides the preferred embodiment of the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for monitoring and early warning of destructive damage in diesel engines based on thermal data, characterized in that: Includes the following steps: S1. Capturing the signs and identifying sensitive parameters of destructive damage to diesel engine test benches; S2, Early warning of destructive damage to diesel engine test bench; In step S1, the timing of signs of destructive damage to the diesel engine test bench and the identification of sensitive parameters include: S11. Collect and organize thermal data to form data resources; S12. Based on data resources, perform data preprocessing to form data samples; S13. Construct a moving window function based on the response time of destructive failures using thermal data; S14. Based on the data samples, calculate the feature values ​​and form a data sample matrix; S15. Based on the moving window function and the data sample matrix, the dataset is divided into training set and test set; S16. Based on the training set and the test set, train the random forest model and obtain the prediction accuracy of the test set; S17. Determine the accuracy of the test set based on the prediction accuracy of the test set. S18. Based on the random forest model, extract sensitive parameters; In step S2, the diesel engine test bench destructive damage warning includes: S21. Preparation of full-condition data for diesel engine; S22. Based on the full operating condition data of the diesel engine, classify the operating conditions of the test data; S23. Based on the experimental data from step S22, construct and train a random forest model, and output a random forest prediction model. S24. Based on the random forest prediction model in step S23, deploy the test bench model; S25. During diesel engine operation, collect warning signals; S26. Are the warning set and the damage knowledge set equal? ​​If yes, jump to step S25; otherwise, proceed to the next step. S27, issue an alarm and activate the emergency action position on the test bench.

2. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S11, thermal data is collected and organized to form data resources, including: Collect historical data on existing fault processes, including data collected synchronously on the test bench and data on auxiliary burst pressure, booster speed and smoke opacity collected by mobile testing instruments; Based on the combination of damaged parts at the time of the fault, data resources are formed by classification.

3. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S12, based on the data resources, data preprocessing is performed to form data samples, including: The data resources are transformed by unit conversion, outliers are removed using the median method, and missing data items are supplemented using linear interpolation to form a data sample.

4. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S13, a moving window function is constructed based on the thermal data regarding the response time to destructive failures, including: The thermal data response time to destructive failures is multiplied by a set factor and used as the initial size of the form; Construct a classification function using the center of the form as the classification boundary.

5. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S14, based on the data samples, feature values ​​are calculated to form a data sample matrix, including: Extract the rate of change and acceleration of change of values ​​from the data sample in step S12 according to the time increment, and merge them with the original data to form a dataset. The dataset is segmented by the size of the constructed window for each thermal parameter; The segmentation process involves moving a sliding window to capture data, forming a data sample matrix.

6. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S15, based on the moving window function and the data sample matrix, the dataset is divided into a training set and a test set, including: Based on the moving window function, the target training data is obtained, merged with the data sample matrix, the sample sorting sequence is shuffled, and divided into training set and test set according to the set method.

7. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S16, a random forest model is trained based on the training and test sets, and the prediction accuracy on the test set is obtained, including: The thermal parameter data in the training and test sets are normalized. The normalized training set data is substituted into the random forest model, and the model is trained using a moving window function as the training objective. Use the test set to test and obtain the test set prediction accuracy.

8. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S17, the test set accuracy is determined based on the test set prediction accuracy, including: Based on the prediction accuracy of the test set, the adaptability of the moving window function is determined; if the accuracy is less than the set value, the window size is increased and the process jumps to step S14 to reprocess until the accuracy equals the set value.

9. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S18, sensitive parameters are extracted based on the random forest model, including: Based on the random forest model, a significance parameter is extracted as a sensitive parameter for monitoring subsequent damage; a time-series significance bias is set as the timing of signs of damage.

10. The method for monitoring and early warning of destructive damage to diesel engines based on thermal data as described in claim 1, characterized in that: In step S21, the diesel engine full-condition data is prepared, including: Compile a set of historical operating universal characteristic data for diesel engines; In step S22, the test data condition classification includes: Divide the operating conditions into a set number of segments according to the speed-load map format; In step S23, the random forest model is constructed and trained, including: Random model construction; training dataset construction; output prediction model; In step S24, the test bench model is deployed, including: Deployment of random forest prediction models; Working condition classification map query; Deploy a set number of parallel cyclic random forest prediction models; Deploy a map to categorize and query operating conditions during the deployment process.

Images