Fault monitoring method and device of range extender, range extender and storage medium

Abstract

The present disclosure relates to a fault monitoring method and device of a range extender, the range extender and a storage medium, and relates to the technical field of fault diagnosis. The fault monitoring method of the range extender comprises: determining first features corresponding to dynamic response signals of various modal types based on the dynamic response signals of various modal types collected for the range extender; calibrating the first features based on a current working condition of the range extender to obtain second features after calibration; determining a fault type corresponding to the first features by using a fault diagnosis model; and determining a health state of the range extender based on the second features and the fault type. The technical solution of the present disclosure can improve the reliability of fault identification and monitoring of the range extender.

Description

Technical Field

[0001] This disclosure relates to the field of fault diagnosis technology, and in particular to a fault monitoring method, fault monitoring device, range extender, computer-readable storage medium, and computer program product for a range extender. Background Technology

[0002] As a key component of the hybrid vehicle, fault monitoring of the range extender is beneficial for the timely detection of early potential faults, thereby avoiding impacts on the overall safety and operational economy of the vehicle. Furthermore, the shaft system of the range extender, as an important structural element, is crucial for its stable operation.

[0003] In related technologies, the working status of the couplings in the shaft system of the range extender is monitored, and the range extender is monitored for malfunctions based on the actual change curve of the monitoring signal. Summary of the Invention

[0004] This disclosure provides a fault monitoring method, a fault monitoring device, a range extender, a computer-readable storage medium, and a computer program product.

[0005] According to a first aspect of this disclosure, a fault monitoring method is provided, comprising: determining a first feature corresponding to the dynamic response signals of various modal types based on the dynamic response signals of various modal types collected from a range extender; calibrating the first feature based on the current operating condition of the range extender to obtain a calibrated second feature; determining a fault type corresponding to the first feature using a fault diagnosis model; and determining the health status of the range extender based on the second feature and the fault type.

[0006] Optionally, calibrating the first feature based on the current operating condition of the range extender to obtain the calibrated second feature includes: calibrating the first feature based on the current operating condition and standard operating condition of the range extender, as well as the feature reference value under the standard operating condition.

[0007] Optionally, calibrating the first feature based on the current operating condition and standard operating condition of the range extender, and the feature reference value under the standard operating condition, includes: performing a preliminary calibration of the first feature based on the operating condition deviation between the current operating condition and the standard operating condition; and performing a secondary calibration on the preliminary calibration result of the first feature based on the feature reference value under the standard operating condition to determine the second feature.

[0008] Optionally, the operating conditions of the range extender include operational conditions and environmental conditions, wherein the environmental conditions include the engine oil pressure of the range extender, the engine coolant temperature, and the generator coolant temperature of the range extender.

[0009] Optionally, the preliminary calibration of the first feature based on the operating condition deviation between the current operating condition and the standard operating condition includes: determining a calibration coefficient based on the operating condition deviation between the current operating condition and the standard operating condition, and the operating condition deviation between the current environmental operating condition and the standard operating condition; and performing preliminary calibration of the first feature based on the calibration coefficient.

[0010] Optionally, the step of performing a secondary calibration on the preliminary calibration result of the first feature based on the feature reference value under the standard operating conditions to determine the second feature includes: normalizing the preliminary calibration result of the first feature based on the feature reference value to determine the second feature.

[0011] Optionally, determining the fault type corresponding to the first feature using the fault diagnosis model includes: using the fault diagnosis model to determine historical features in the fault database that match the first feature; and based on the matched historical features, determining the fault type using the mapping relationship between different historical features and different fault types stored in the fault database.

[0012] Optionally, determining the health status of the range extender based on the second feature and the fault type includes: determining the weights corresponding to the second features of each modal type based on the degree of influence of the fault type on the dynamic response signals of each modal type, wherein the value of the weights is positively correlated with the degree of influence; and determining the health status based on the second feature and the weights.

[0013] Optionally, determining the health status based on the second feature and the weight includes: determining a health index based on the weighted geometric mean of the second feature and the weight, which is used to characterize the health status.

[0014] Optionally, the fault monitoring method further includes: determining the fault level based on the relationship between the health index and the warning threshold, wherein the warning threshold includes multi-level warning thresholds, and the health index is positively correlated with the fault level and negatively correlated with the severity of the fault.

[0015] Optionally, the fault monitoring method further includes: generating a fault code based on the fault type, the health status, and the fault level; and sending the fault code to a terminal device for fault warning and maintenance of the range extender.

[0016] Optionally, determining the first feature corresponding to the dynamic response signals of various modal types based on the dynamic response signals of various modal types collected from the range extender includes: collecting dynamic response signals of various modal types at various components of the range extender; and determining the first feature corresponding to the dynamic response signals of various modal types, wherein the number of the first features is multiple.

[0017] Optionally, the dynamic response signal includes at least two of the following: rotational speed signal, acceleration signal, and noise signal.

[0018] Optionally, the step of acquiring dynamic response signals of multiple modal types at various components of the range extender includes: determining dynamic response signals of various modal types based on the root mean square of dynamic response signals of the same modal type acquired at different components.

[0019] According to a second aspect of this disclosure, a fault monitoring device is provided, comprising: a first determining module configured to determine a first feature corresponding to various modal types of dynamic response signals collected from a range extender; a calibration module configured to calibrate the first feature based on the current operating condition of the range extender to obtain a calibrated second feature; a second determining module configured to determine a fault type corresponding to the first feature using a fault diagnosis model; and a third determining module configured to determine the health status of the range extender based on the second feature and the fault type.

[0020] According to a third aspect of this disclosure, a fault monitoring apparatus is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the fault monitoring method described above based on instructions stored in the memory.

[0021] According to a fourth aspect of this disclosure, a range extender is provided, comprising: the fault monitoring device as described above.

[0022] According to a fifth aspect of this disclosure, a computer-readable storage medium is provided that stores computer instructions thereon, which, when executed by a processor, implement the fault monitoring method described above.

[0023] According to a sixth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the fault monitoring method as described above.

[0024] The fault monitoring method, fault monitoring device, range extender, computer-readable storage medium, and computer program product disclosed herein monitor the range extender for faults based on dynamic response signals of multiple modal types collected on the range extender, thereby improving the reliability of the monitoring data source. Furthermore, considering the potentially significant differences in dynamic response signals under different operating conditions, the first characteristic corresponding to the dynamic response signal is calibrated based on the current operating condition of the range extender, further improving the reliability and accuracy of the monitoring data. Determining the health status of the range extender based on the fault type and the calibrated second characteristic facilitates the identification of the impact of different fault types on the range extender, thus achieving reliable monitoring and early warning of various faults in the range extender. Attached Figure Description

[0025] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The accompanying drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. The above and other objects and advantages of this disclosure will be further described below with reference to specific embodiments and the accompanying drawings. In the drawings, the same or corresponding technical features or components will be represented by the same or corresponding reference numerals.

[0026] Figure 1 Flowcharts showing some embodiments of the fault monitoring method for range extenders according to this disclosure;

[0027] Figure 2 This is a schematic diagram of the structure of a range extender according to some embodiments of the fault monitoring method for range extenders according to this disclosure;

[0028] Figure 3 A schematic diagram illustrating the principle of some embodiments of the fault monitoring method for range extenders according to this disclosure;

[0029] Figures 4a-4b This is a block diagram of some embodiments of a fault monitoring device for a range extender according to the present disclosure;

[0030] Figure 5 This is a block diagram of yet another embodiment of the fault monitoring device for a range extender according to the present disclosure. Detailed Implementation

[0031] Exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings. For clarity and brevity, not all features of the embodiments are described in the specification. However, it should be understood that many implementation-specific settings must be made in carrying out the embodiments to achieve the developer's specific goals, such as complying with constraints related to the device and business, and these constraints may vary depending on the implementation. Furthermore, it should be understood that while development work can be very complex and time-consuming, such development work is merely a routine task for those skilled in the art who benefit from the present disclosure.

[0032] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0033] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0034] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0035] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0036] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0037] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0038] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0039] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0040] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0041] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0042] Furthermore, to avoid obscuring this disclosure with unnecessary detail, only processing steps and / or apparatus structures closely related to at least the solutions according to this disclosure are shown in the accompanying drawings, while other details less relevant to this disclosure are omitted. It should also be noted that similar reference numerals and letters in the drawings indicate similar items, and therefore once an item is defined in one drawing, it need not be discussed again in subsequent drawings.

[0043] In related technologies, the shafting system of a range extender typically includes high-speed rotating components such as the internal combustion engine crankshaft, generator rotor, and couplings. Shafting system faults can include various types such as imbalance, misalignment, bearing wear, and gear damage. If shafting system faults are not detected in time, they may lead to severe vibrations and decreased efficiency in the range extender, and in severe cases, even damage to the entire machine, thus seriously threatening the safety of the entire system.

[0044] However, current technologies only monitor the flexible couplings in the shaft system online, resulting in a limited monitoring range and limited monitoring signals for the range extender shaft system, failing to cover all components. For example, the monitoring signals in these technologies only include engine speed and vibration signals from the side of the range extender housing near the flexible coupling, leading to a limited number of collected monitoring signals and an inability to handle shaft system fault monitoring under complex operating conditions. Moreover, based on the difference between the actual and preset variation curves of the monitoring signals, the methods for monitoring whether the range extender has malfunctioned suffer from low efficiency, high computational load, and low level of intelligence. The results of fault monitoring are highly dependent on the accuracy of the preset variation curves, resulting in low accuracy in fault monitoring.

[0045] In response to at least one of the above problems, this disclosure proposes a fault monitoring method for range extenders, which can improve the reliability of fault identification and monitoring of range extenders and extend the service life of range extenders.

[0046] For example, the technical solution of this disclosure can be implemented through the following embodiments.

[0047] Figure 1 Flowcharts are shown for some embodiments of the fault monitoring method for range extenders according to this disclosure. Figure 1 As shown, the fault monitoring method may include at least steps 110 to 140.

[0048] In step 110, based on the dynamic response signals of various modal types collected from the range extender, a first feature corresponding to the dynamic response signals of various modal types is determined.

[0049] For example, sensors can be installed on the shaft system of the range extender to collect dynamic response signals of various modes. Based on the collected dynamic response signals, a first feature corresponding to the dynamic response signal of each mode type can be determined. The dynamic response signal of each mode type can correspond to one or more first features.

[0050] In step 120, the first feature is calibrated based on the current operating condition of the range extender to obtain the calibrated second feature.

[0051] For example, since the dynamic response signals collected for the range extender may differ under different operating conditions, the first characteristic can be calibrated to the standard operating condition based on the current operating condition of the range extender to unify the monitoring basis under different operating conditions.

[0052] In step 130, the fault diagnosis model is used to determine the fault type corresponding to the first feature.

[0053] Fault diagnosis models can be deep learning models built based on machine learning algorithms. For example, fault diagnosis models can be built using deep learning model architectures such as Transformer or CNN (Convolutional Neural Network).

[0054] Fault diagnosis models can be supervised models. For example, a fault diagnosis model can be trained using historical monitoring data, enabling the model to learn the mapping relationship between the fault characteristic parameters of the range extender shaft system and the health status of the shaft system.

[0055] For example, the fault characteristic parameters of the range extender shaft system may include the first characteristic before calibration for each modal type. Historical monitoring data may include the fault characteristic parameters of the range extender shaft system collected during historical monitoring, the fault types corresponding to each fault characteristic parameter, and the fault characteristic parameters of the range extender shaft system associated with each fault type. The correlation between fault type and fault characteristic parameters of the range extender shaft system is used to indicate that when a certain fault type occurs, the range extender shaft system fault characteristic parameters related to that fault type are more affected.

[0056] In step 140, the health status of the range extender is determined based on the second feature and the fault type.

[0057] For example, health status can be represented by a status code or a health index. When using a health index to represent health status, a higher health index indicates a better health status for the range extender and a lower severity of potential faults.

[0058] For example, health status can be used to determine whether early warnings and reports should be issued for detected potential faults.

[0059] The fault monitoring method disclosed herein not only considers that the shaft system of the range extender contains multiple important components, and that a failure in one component may simultaneously manifest in dynamic response signals of multiple modal types, but also that different fault types in different components may have varying degrees of impact on the overall normal operation of the range extender. Furthermore, it considers that the dynamic response signals of the range extender may differ under different operating conditions during normal operation. This fault monitoring method uses the first characteristics of multiple modal types corresponding to the dynamic response signals of multiple modal types as the monitoring basis, and further calibrates the first characteristics of multiple modal types based on the current operating condition of the range extender, thereby improving the reliability of the monitoring basis and enhancing the accuracy of subsequent fault monitoring. Moreover, based on an intelligent fault diagnosis model, it identifies early potential faults in the range extender, improving the efficiency and intelligence level of fault identification and monitoring. By judging the impact of early potential faults on the range extender and determining its health status, it can provide timely warnings of serious fault types, avoiding potential catastrophic accidents such as damage to the range extender or the entire machine, and ensuring vehicle operational safety.

[0060] The following examples will illustrate how to determine the first feature in step 110.

[0061] In some embodiments, the dynamic response signal includes at least two of the following: rotational speed signal, acceleration signal, noise signal, etc.

[0062] For example, the dynamic response signal may include the shaft instantaneous speed signal ω. shaft (t), instantaneous acceleration vibration signal of the shell a housing (t), and the assembly instantaneous noise signal p noise (t) and other signals.

[0063] In some embodiments, dynamic response signals of multiple modal types can be acquired at various components of the range extender; and first features corresponding to the dynamic response signals of various modal types can be determined, wherein the number of first features is multiple.

[0064] The shafting system of a range extender typically includes high-speed rotating components such as the internal combustion engine crankshaft, generator rotor, and couplings. The internal combustion engine crankshaft includes the engine flywheel end. The generator rotor includes the motor resolver end, which can serve as a critical signal terminal, allowing for the measurement of the generator rotor's real-time position and speed via the resolver. In the event of a coupling failure, the crankshaft and generator rotor signals will also exhibit abnormalities. Therefore, by monitoring the crankshaft and generator rotor, the condition of the coupling can be indirectly monitored, thereby achieving comprehensive monitoring of the range extender's shafting system.

[0065] For example, speed sensors can be installed at the engine flywheel end and the motor resolver end to collect the instantaneous speed signal ω of the shaft system in real time. shaft (t). Accelerometers can be installed in the engine block, flywheel housing, and generator housing to collect instantaneous acceleration vibration signals a in real time. housing (t). Microphone sensors can be installed at the engine oil pan and alternator housing to collect instantaneous noise signals p of the assembly in real time. noise (t).

[0066] For example, the speed sensor installed at the flywheel end of the engine (which can be referred to as the first speed sensor) can be a magnetoelectric speed sensor, and the speed sensor installed at the resolver end of the motor (which can be referred to as the second speed sensor) can be a photoelectric encoder.

[0067] In some embodiments, dynamic response signals of various modal types are determined based on the root mean square of dynamic response signals of the same modal type collected at different components.

[0068] For example, in the above embodiments, sensors of the same mode type (e.g., speed sensors) are installed at two different components of the range extender: the engine flywheel end and the motor resolver end. During the actual operation of the range extender, due to shaft torsional vibration, the dynamic response signals collected by the first and second speed sensors may differ. Similar issues may exist with the dynamic response signals collected by the acceleration sensor and microphone sensor, which will not be elaborated upon here.

[0069] In this case, the root mean square (RMS) processing can be performed on multiple dynamic response signals of the same modal type collected by multiple sensors of the same modal type to obtain a unique dynamic response signal under each modal type.

[0070] In the above embodiments, by installing various types of sensors at different components of the range extender shaft system, instantaneous physical signals of the range extender during operation are collected in real time as dynamic response signals. This enables real-time, high-precision online measurement of key parameters such as shaft speed, acceleration, and vibration noise. Furthermore, the sensor installation locations cover all components of the shaft system, improving the reliability and accuracy of shaft fault monitoring.

[0071] After acquiring dynamic response signals of various modal types in real time, the dynamic response signals can be processed in the time domain and / or frequency domain to determine the first feature corresponding to the dynamic response signals of various modal types.

[0072] For example, the instantaneous rotational speed signal ω of the shaft system shaft The first characteristic corresponding to (t) may include: shaft speed fluctuation characteristic ω var Angular displacement order characteristics of shaft system θ order Angular acceleration order characteristics α order The instantaneous acceleration signal a of the shell housing The corresponding first feature may include: the magnitude of the shell acceleration order A. shell The instantaneous noise signal p of the assembly noise The first feature corresponding to (t) may include: assembly near-field noise spectrum feature N spect Sharpness characteristics of near-field noise in the assembly shaft system S noise Near-field noise and roughness characteristics of the assembly shaft system R noise .

[0073] Among them, the shaft speed fluctuation characteristic ω var It can be calculated using the instantaneous rotational speed fluctuation method. Shaft system angular displacement order characteristic θ order Angular acceleration order characteristics α order , shell acceleration order amplitude A shell The near-field noise spectrum characteristics of the assembly can be calculated using the order tracking analysis method. spect This can be calculated using FFT (Fast Fourier Transform) spectral analysis. The near-field noise sharpness characteristic S of the assembly shaft system... noise Near-field noise and roughness characteristics of the assembly shaft system R noise It can be calculated based on the Zwicker model.

[0074] The calculation method for the first feature described above is merely illustrative. Those skilled in the art should understand that for instantaneous physical signals such as dynamic response signals, other frequency domain / time domain analysis methods can also be used to convert instantaneous physical signals into physical characteristic parameters.

[0075] In this way, based on the dynamic response signal, time-domain / frequency-domain analysis methods are used to convert the signal into various types of features, which can more comprehensively and holistically characterize the operating status of the range extender. Moreover, converting the signal into features not only reduces computational complexity but also facilitates the subsequent fault diagnosis model's analysis and processing of the features, thereby improving the intelligence level of range extender fault monitoring.

[0076] After calculating the first feature of each modality type, the following will illustrate how to calibrate the calculated first feature to obtain the second feature in step 120 through some exemplary embodiments.

[0077] In some embodiments, the first feature is calibrated based on the current operating condition and standard operating condition of the range extender, as well as the feature reference value under the standard operating condition.

[0078] For example, a reference value for each first feature under standard operating conditions can be configured. The reference value can be configured as the feature value corresponding to the initial value of the dynamic response signal under standard operating conditions.

[0079] In some embodiments, the operating conditions of the range extender include operational conditions and environmental conditions, the environmental conditions including the engine oil pressure, engine coolant temperature, and generator coolant temperature of the range extender.

[0080] For example, the type of operating condition can include startup condition M. start Idle condition M idle Steady-state power generation condition M steady 100% power operation condition M up Reduced power operation mode M down Shutdown Condition M stop Etc. Environmental operating conditions include engine state parameters, which can be expressed as the engine oil pressure P. oil Engine coolant temperature T eng Generator water temperature T gen .

[0081] For example, this can be achieved by identifying the engine's speed signal ω. eng (t), Generator torque signal T gen (t) is used to identify the current operating condition M of the range extender. re .

[0082] In some embodiments, a first feature is initially calibrated based on the deviation between the current operating condition and the standard operating condition; a second calibration is performed on the initial calibration result of the first feature based on the feature reference value under the standard operating condition to determine the second feature.

[0083] For example, the first feature can be initially calibrated using the method described in the following embodiments.

[0084] In some embodiments, calibration coefficients can be determined based on the deviation between the current operating conditions and the standard operating conditions, and the deviation between the current environmental conditions and the standard operating conditions; based on the calibration coefficients, the first feature is initially calibrated.

[0085] For example, the characteristic of shaft speed fluctuation ω var For example, the shaft speed fluctuation characteristics after preliminary calibration can be expressed as ω var_k The shaft speed fluctuation characteristic ω can be calculated using the following formula (1). var Perform preliminary calibration.

[0086]

[0087] Here, k1 can represent the calibration coefficient.

[0088] For example, a compensation function f can be constructed based on the deviation between the current operating conditions and the standard operating conditions, as well as the deviation between the current environmental conditions and the standard operating conditions. The compensation function f can be obtained by fitting experimental data. After the compensation function f is constructed in advance, the current operating conditions and the current environmental conditions can be used as inputs to determine the values ​​of the calibration coefficients. For example, it can be expressed by the following formula (2).

[0089]

[0090] Based on the calibration coefficient k1, the preliminary calibration results of each first feature can be calculated.

[0091] For each primary characteristic, the range extender can be calibrated differently based on the current operating conditions and environmental conditions. By converting it to standard operating conditions through calibration coefficients, the impact of boundary conditions such as operating condition switching and temperature differences on fault diagnosis accuracy can be mitigated when operating conditions and environmental conditions differ.

[0092] Furthermore, secondary calibration can be performed based on characteristic reference values ​​under standard operating conditions. The process of secondary calibration will be illustrated below through several examples.

[0093] In some embodiments, the preliminary calibration results of the first feature are normalized based on the feature reference value to determine the second feature.

[0094] For example, the preliminary calibration result of the first feature can be divided by the feature reference value corresponding to each first feature to obtain the normalized second feature. For example, the preliminary calibration result ω of the shaft speed fluctuation feature... var_k For example, a secondary calibration can be performed using the following formula (3).

[0095]

[0096] ω var_ healthy This represents the characteristic reference value corresponding to the shaft speed fluctuation characteristic. The characteristic value of the second characteristic obtained after normalization is around 1.

[0097] Based on the first feature, a fault diagnosis model can be used to determine the early potential fault type. Below, several embodiments will be used to illustrate how to determine the fault type in step 130.

[0098] In some embodiments, a fault diagnosis model is used to determine historical features in the fault database that match the first feature; based on the matched historical features, the fault type is determined by using the mapping relationship between different historical features and different fault types stored in the fault database.

[0099] For example, the historical features in the fault database that match the first feature can be determined by calculating the similarity between the first feature and historical features in the fault database.

[0100] Based on the matching results and combined with historical failure patterns in the failure database, the failure type is determined. For example, historical failure patterns can include mapping relationships between different historical features and different failure types.

[0101] By establishing a mapping relationship between speed signal characteristics, acceleration signal characteristics, and noise signal characteristics and fault types, potential early faults in the shaft system (such as loosening, misalignment, and damper performance degradation) can be quickly identified, issuing early warnings before serious faults or damage occur in the range extender. This not only improves the intelligence level of fault monitoring but also enhances the overall reliability of the machine.

[0102] Since different fault types have varying degrees of impact on the normal operation of the range extender and even the entire machine, step 140 can be further executed to comprehensively identify the health status of the range extender based on the fault type and the characteristics corresponding to the calculated dynamic response signal. Below, some embodiments will be used to illustrate how to determine the health status in step 140.

[0103] In some embodiments, the weights corresponding to the second features of various modal types are determined based on the degree of influence of the fault type on the dynamic response signals of various modal types, and the values ​​of the weights are positively correlated with the degree of influence; the health status is determined based on the second features and the weights.

[0104] For example, bearing wear primarily affects the shaft speed fluctuation characteristics and the order and amplitude of housing acceleration. Therefore, the calibrated shaft speed fluctuation characteristic ω can be set. var_norm and the order amplitude of the shell acceleration A shell_normThe weight of the second feature is greater than the weights of the other second features.

[0105] Similarly, misalignment of the coupling primarily affects the order characteristics of the shaft system's angular displacement and the sharpness characteristics of the assembly's near-field noise. Therefore, the calibrated order characteristic θ of the shaft system's angular displacement can be set. order_norm and the sharpness characteristics of near-field noise in the assembly shaft system S noise_norm The weight of the second feature is greater than the weights of the other second features.

[0106] Similarly, in the case of shaft system cracks, the main effects are on the shaft system angular acceleration order characteristics and the near-field noise roughness characteristics of the assembly shaft system. Therefore, the calibrated shaft system angular acceleration order characteristic α can be set. order_norm and assembly shaft system near-field noise roughness characteristics R noise_norm The weight of the second feature is greater than the weights of the other second features.

[0107] Similarly, gear damage primarily affects the near-field noise spectrum characteristics of the assembly. Therefore, the calibrated near-field noise spectrum characteristics N of the assembly can be set. spect_norm The weight of the second feature is greater than the weights of the other second features.

[0108] Because the shaft system of a range extender contains multiple critical components, a failure in one component may manifest in dynamic response signals of multiple modalities simultaneously. Conversely, different failure types in different components may have varying degrees of impact on the overall operation of the range extender. Based on the failure type, flexibly determining the weights of various failure characteristic parameters (e.g., secondary characteristics) can improve the reliability and interpretability of fault detection and health status identification, thereby enabling reliable early warning and intervention for potential faults.

[0109] After determining the weights of each second feature under this fault type, the health status of the range extender can be calculated through the following embodiments.

[0110] In some embodiments, a health index is determined based on the weighted geometric mean of the second feature and weights to characterize health status.

[0111] The weighted geometric mean is a type of geometric mean used to perform weighted analysis on independent variables when their importance varies, in order to measure the composite proportion of the independent variables.

[0112] The geometric mean can be defined as the nth root of the product of n independent variable values. Similarly, in response to the different weights of the n independent variables, the weighted geometric mean can be defined as the root of the sum of the weights of the product of the n independent variable values ​​raised to the power of their respective weights.

[0113] For example, the second feature can be used as the independent variable of the weighted geometric mean. Based on the second feature and the weights corresponding to each second feature, the dependent variable H of the weighted geometric mean can be calculated using the formula for the weighted geometric mean, which can be used as the health index of the range extender.

[0114] For example, based on the definition of the weighted geometric mean, formula (4) can be constructed to calculate the health index H based on the second feature and the weights corresponding to each second feature.

[0115]

[0116] In some embodiments, the fault level can also be determined based on the relationship between the health index and the warning threshold. The warning threshold includes multi-level warning thresholds. The health index is positively correlated with the fault level and negatively correlated with the severity of the fault.

[0117] For example, multi-level warning thresholds can include 0.6, 0.7, 0.85, etc. Based on the relationship between the health index H and the multi-level warning thresholds, the fault level can be determined. A higher fault level indicates a more severe fault, thus attracting the attention of maintenance personnel.

[0118] For example, a fault level of H < 0.6 can be determined as a Level 1 fault; a fault level of 0.6 ≤ H < 0.7 can be determined as a Level 2 fault; and a fault level of 0.7 ≤ H < 0.85 can be determined as a Level 3 fault.

[0119] The higher the health index, the better the health status of the range extender, the lower the severity of the fault, and the lower the probability of early potential faults.

[0120] In some embodiments, fault codes can be generated based on fault type, health status, and fault level; the fault codes can be sent to the terminal device for fault warning and maintenance of the range extender.

[0121] For example, terminal devices may include vehicle controllers, dashboards, or remote monitoring platforms.

[0122] Fault codes can be generated based on fault type, health status, and fault level. These fault codes are transmitted in real time to terminal devices such as vehicle controllers, instrument panels, or remote monitoring platforms via in-vehicle networks (e.g., CAN bus) to provide early warnings of faults and prompt operators or maintenance personnel to repair early potential faults.

[0123] In this way, by monitoring torsional vibration and vibration noise signals at various components of the shaft system, early potential faults in the range extender shaft system can be monitored and warned. This can provide a basis for optimizing the control strategy of the range extender (such as torque compensation, start-stop smoothness control, etc.), thereby suppressing excessive torsional vibration, improving the NVH (Noise, Vibration, Harshness) performance of the whole vehicle, and extending the service life of the range extender shaft system and related components.

[0124] Figure 2 This is a schematic diagram of the structure of a range extender according to some embodiments of the fault monitoring method for range extenders disclosed herein.

[0125] like Figure 2 As shown, the range extender may include an engine block 210, a first acceleration sensor 220, a second acceleration sensor 230, a third acceleration sensor 240, an engine flywheel 250, a motor resolver 260, a second speed sensor 270, a first speed sensor 280, a generator housing 290, a second microphone sensor 2100, a flywheel housing 2110, an engine oil pan 2120, and a first microphone sensor 2130. The motor resolver 260 is located at the center of the rear end of the motor; the generator housing 290 is located circumferentially to the motor.

[0126] In some embodiments, a first speed sensor 280 is arranged at the engine flywheel end; a second speed sensor 270 is arranged at the motor resolver end; a first acceleration sensor 220 is arranged in the engine block; a second acceleration sensor 230 is arranged in the flywheel housing; a third acceleration sensor 240 is arranged in the generator housing; a first microphone sensor 2130 is arranged in the engine oil pan; and a second microphone sensor 2100 is arranged in the generator housing.

[0127] Figure 3 This is a schematic diagram illustrating some embodiments of the fault monitoring method for range extenders according to the present disclosure.

[0128] like Figure 3 As shown, in some embodiments, the fault monitoring method in any of the embodiments of this disclosure can be implemented based on the signal sensing unit 310, the signal processing and calculation unit 320, the status assessment and fault diagnosis unit 330, and the output unit 340. The signal processing and calculation unit 320 and the status assessment and fault diagnosis unit 330 can be integrated into the range extender controller.

[0129] In some embodiments, the signal sensing unit 310 is arranged at a key position in the range extender shaft system and uses a high-precision angle sensor to collect the instantaneous physical signals of the shaft system in real time as dynamic response signals.

[0130] The signal sensing unit 310 can utilize Figure 2 The first speed sensor 280, the second speed sensor 270, the first acceleration sensor 220, the second acceleration sensor 230, the third acceleration sensor 240, the first microphone sensor 2130, and the second microphone sensor 2100 shown in the figure collect analog / digital signals as dynamic response signals.

[0131] In some embodiments, the signal processing and calculation unit 320 is used to receive the dynamic response signal collected by the signal sensing unit 310, and to perform signal conditioning on the dynamic response signal using signal processing methods such as filtering, amplification, and anti-interference processing. It also uses feature extraction methods based on time domain and / or frequency domain analysis, such as instantaneous speed fluctuation method, order tracking analysis method, and FFT spectrum analysis, to calculate the first feature corresponding to the dynamic response signal of each modality.

[0132] In some embodiments, the condition assessment and fault diagnosis unit 330 incorporates a fault diagnosis model built on machine learning algorithms and trained using historical monitoring data. This model is used to identify the mapping relationship between the range extender shaft system fault characteristic parameters and the shaft system health status (e.g., normal, slight instability, severe instability, component loosening, shaft misalignment, damper failure, flywheel or coupling failure, etc.). The range extender shaft system fault characteristic parameters may include a first feature. The condition assessment and fault diagnosis unit 330 receives the first feature sent by the signal processing and calculation unit 320 in real time, and, in conjunction with the current operating condition of the range extender, uses the fault diagnosis model to perform health status assessment and fault type identification.

[0133] In some embodiments, the output unit 340 determines the current fault level (e.g., Level 1 fault, Level 2 fault, Level 3 fault) based on the health status assessment and fault type identification results sent by the status assessment and fault diagnosis unit 330 and according to a preset multi-level warning threshold. The lower the fault level, the greater the severity and the more attention the operator needs to pay.

[0134] In some embodiments, the output unit 340 may also generate a corresponding fault code based on the fault type, health status, and fault level, and send the fault code to the terminal device.

[0135] For example, the output unit 340 can transmit fault codes in real time to the vehicle controller, instrument panel, or remote monitoring platform via an in-vehicle network (e.g., CAN (Controller Area Network) bus) to prompt the operator or maintenance personnel to intervene.

[0136] Figures 4a-4b This is a block diagram of some embodiments of a fault monitoring device for a range extender according to the present disclosure.

[0137] like Figure 4a As shown, this disclosure provides a fault monitoring device 400 for a range extender, including a first determining module 410, a calibration module 420, a second determining module 430, and a third determining module 440. The first determining module 410 is configured to determine a first feature corresponding to various modal types of dynamic response signals collected from the range extender; the calibration module 420 is configured to calibrate the first feature based on the current operating condition of the range extender to obtain a calibrated second feature; the second determining module 430 is configured to determine the fault type corresponding to the first feature using a fault diagnosis model; and the third determining module 440 is configured to determine the health status of the range extender based on the second feature and the fault type.

[0138] In some embodiments, the calibration module 420 is configured to calibrate the first feature based on the current operating condition and standard operating condition of the range extender, as well as the feature reference value under the standard operating condition.

[0139] For example, the calibration module 420 is configured to perform preliminary calibration on the first feature based on the deviation between the current operating condition and the standard operating condition; and to perform secondary calibration on the preliminary calibration result of the first feature based on the feature reference value under the standard operating condition to determine the second feature.

[0140] For example, the operating conditions of a range extender include both operational conditions and environmental conditions. Environmental conditions include the engine oil pressure, engine coolant temperature, and generator coolant temperature of the range extender.

[0141] For example, the calibration module 420 is configured to determine calibration coefficients based on the deviation between the current operating conditions and the standard operating conditions, and the deviation between the current environmental conditions and the standard operating conditions; and to perform preliminary calibration on the first feature based on the calibration coefficients.

[0142] For example, calibration module 420 is configured to normalize the preliminary calibration results of the first feature based on the feature reference value to determine the second feature.

[0143] In some embodiments, the second determining module 430 is configured to use a fault diagnosis model to determine historical features in the fault database that match the first feature; and based on the matched historical features, to determine the fault type by using the mapping relationship between different historical features and different fault types stored in the fault database.

[0144] In some embodiments, the third determining module 440 is configured to determine the weights corresponding to the second features of various modal types based on the degree of influence of the fault type on the dynamic response signals of various modal types, wherein the value of the weights is positively correlated with the degree of influence; and determine the health status based on the second features and the weights.

[0145] For example, the third determining module 440 is configured to determine a health index based on the weighted geometric mean of the second features and weights, which is used to characterize health status.

[0146] In some embodiments, the first determining module 410 is configured to acquire dynamic response signals of multiple modal types at various components of the range extender; and determine a first feature corresponding to the dynamic response signals of various modal types, wherein the number of the first features is multiple.

[0147] In some embodiments, the dynamic response signal includes at least two of the following: rotational speed signal, acceleration signal, and noise signal.

[0148] For example, the first determining module 410 is configured to determine the dynamic response signals of various modal types based on the root mean square of the dynamic response signals of the same modal type collected at different components.

[0149] In some embodiments, such as Figure 4b As shown, this disclosure also provides a fault monitoring device 400 for a range extender, which, in addition to including the first determining module 410, calibration module 420, second determining module 430, and third determining module 440 as described above, may also include a fourth determining module 450 and a fault warning module 460. The fault monitoring method performed by the first determining module 410, calibration module 420, second determining module 430, and third determining module 440 is similar to... Figure 4a Similar to the case in China, I will not repeat it here.

[0150] In some embodiments, the fourth determining module 450 is configured to determine the fault level based on the relationship between the health index and the warning threshold, wherein the warning threshold includes multi-level warning thresholds, and the health index is positively correlated with the fault level and negatively correlated with the severity of the fault.

[0151] In some embodiments, the fault warning module 460 is configured to generate a fault code based on the fault type, health status, and fault level; and send the fault code to the terminal device for fault warning and maintenance of the range extender.

[0152] Figure 5 This is a block diagram of yet another embodiment of the fault monitoring device for a range extender according to the present disclosure.

[0153] like Figure 5 As shown, the range extender fault monitoring device 500 includes a memory 510 and a processor 520 coupled to the memory 510. The processor 520 is configured to execute the range extender fault monitoring method in various embodiments based on instructions stored in the memory 510. Specific implementations can be found in the foregoing embodiments and will not be repeated here.

[0154] The fault monitoring device 500 for the range extender may also include an input / output interface 530, a network interface 540, a storage interface 550, etc. These interfaces 530, 540, 550, as well as the memory 510 and the processor 520, can be connected, for example, via a bus 560.

[0155] The memory 510 may include, for example, system memory, fixed non-volatile storage media, etc. The system memory may store, for example, the operating system, application programs, boot loader, and other programs.

[0156] The processor 520 can be implemented using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates, or transistors, or other discrete hardware components.

[0157] The input / output interface 530 provides a connection interface for input / output devices such as monitors, mice, keyboards, and touchscreens. The network interface 540 provides a connection interface for various networked devices. The storage interface 550 provides a connection interface for external storage devices such as SD cards and USB flash drives. The bus 560 can use any bus architecture from a variety of bus structures. For example, bus architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, and Peripheral Component Interconnect (PCI) bus.

[0158] In some embodiments, this disclosure provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the fault monitoring method for the range extender as described in any of the foregoing embodiments.

[0159] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (not an exhaustive list) of readable storage media may include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0160] Embodiments of this disclosure may also be computer program products, including computer program instructions that, when executed by a processor, cause the processor to perform steps in a fault monitoring method for a range extender according to various embodiments of this disclosure.

[0161] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0162] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0163] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0164] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0165] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0166] The above description has been given for illustrative and descriptive purposes. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although several exemplary aspects and embodiments have been discussed above, those skilled in the art will understand that the above embodiments are illustrative only and do not limit the scope of this disclosure. Those skilled in the art will understand that the above embodiments can be combined, modified, or replaced without departing from the scope and spirit of this disclosure.

Claims

1. A fault monitoring method for a range extender, comprising: Based on the dynamic response signals of various modal types collected from the range extender, the first feature corresponding to the dynamic response signals of various modal types is determined; Based on the current operating condition of the range extender, the first feature is calibrated to obtain the calibrated second feature; Using a fault diagnosis model, determine the fault type corresponding to the first feature; Based on the second feature and the fault type, the health status of the range extender is determined.

2. The fault monitoring method according to claim 1, wherein, The step of calibrating the first feature based on the current operating condition of the range extender to obtain the calibrated second feature includes: Based on the current operating condition and standard operating condition of the range extender, and the characteristic reference value under the standard operating condition, the first feature is calibrated.

3. The fault monitoring method according to claim 2, wherein, The calibration of the first feature based on the current operating condition and standard operating condition of the range extender, and the characteristic reference value under the standard operating condition, includes: Based on the deviation between the current operating condition and the standard operating condition, the first feature is initially calibrated. Based on the characteristic reference value under the standard operating conditions, the preliminary calibration result of the first characteristic is calibrated a second time to determine the second characteristic.

4. The fault monitoring method according to claim 3, wherein, The operating conditions of the range extender include both operational conditions and environmental conditions. The environmental conditions include the engine oil pressure, engine coolant temperature, and generator coolant temperature of the range extender.

5. The fault monitoring method according to claim 4, wherein, The preliminary calibration of the first feature based on the deviation between the current operating condition and the standard operating condition includes: The calibration coefficient is determined based on the deviation between the current operating conditions and the standard operating conditions, as well as the deviation between the current environmental conditions and the standard operating conditions. Based on the calibration coefficient, the first feature is initially calibrated.

6. The fault monitoring method according to claim 3, wherein, The step of performing a secondary calibration on the preliminary calibration result of the first feature based on the feature reference value under the standard operating conditions to determine the second feature includes: Based on the feature benchmark value, the preliminary calibration result of the first feature is normalized to determine the second feature.

7. The fault monitoring method according to any one of claims 1 to 6, wherein, The step of using a fault diagnosis model to determine the fault type corresponding to the first feature includes: Using the fault diagnosis model, historical features in the fault database that match the first feature are determined; Based on the matched historical features, the fault type is determined by utilizing the mapping relationship between different historical features and different fault types stored in the fault database.

8. The fault monitoring method according to any one of claims 1 to 6, wherein, Determining the health status of the range extender based on the second feature and the fault type includes: Based on the degree of influence of the fault type on the dynamic response signals of the various modal types, the weights corresponding to the second features of the various modal types are determined, and the values ​​of the weights are positively correlated with the degree of influence. The health status is determined based on the second feature and the weight.

9. The fault monitoring method according to claim 8, wherein, Determining the health status based on the second feature and the weight includes: A health index is determined based on the weighted geometric mean of the second feature and the weight, which is used to characterize the health status.

10. The fault monitoring method according to claim 9, further comprising: Based on the relationship between the health index and the warning threshold, the fault level is determined. The warning threshold includes multiple warning thresholds. The health index is positively correlated with the fault level and negatively correlated with the severity of the fault.

11. The fault monitoring method according to claim 10, further comprising: Based on the fault type, the health status, and the fault level, a fault code is generated; The fault code is sent to the terminal device for fault warning and maintenance of the range extender.

12. The fault monitoring method according to any one of claims 1 to 6, wherein, The determination of the first feature corresponding to the dynamic response signals of various modal types based on the dynamic response signals collected from the range extender includes: Multiple modal dynamic response signals are collected at various components of the range extender; A first feature is determined corresponding to the dynamic response signal of each modal type, and the number of the first features is multiple.

13. The fault monitoring method according to claim 12, wherein, The dynamic response signal includes at least two of the following: rotational speed signal, acceleration signal, and noise signal.

14. The fault monitoring method according to claim 12, wherein, The method involves acquiring dynamic response signals of multiple modal types at various components of the range extender, including: The dynamic response signals of various modal types are determined based on the root mean square of the dynamic response signals of the same modal type collected from different components.

15. A fault monitoring device for a range extender, comprising: The first determining module is configured to determine a first feature corresponding to the dynamic response signals of various modal types based on the dynamic response signals of various modal types collected from the range extender. The calibration module is configured to calibrate the first feature based on the current operating conditions of the range extender to obtain a calibrated second feature. The second determining module is configured to use a fault diagnosis model to determine the fault type corresponding to the first feature. The third determining module is configured to determine the health status of the range extender based on the second feature and the fault type.

16. A fault monitoring device for a range extender, comprising: Memory; and A processor coupled to the memory, the processor being configured to execute the fault monitoring method of any one of claims 1 to 14 based on instructions stored in the memory.

17. A range extender, comprising: The fault monitoring device according to claim 15 or claim 16.

18. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the fault monitoring method according to any one of claims 1 to 14.

19. A computer program product comprising instructions that, when executed by a processor, cause the processor to perform the fault monitoring method according to any one of claims 1 to 14.

Images