Diesel engine equipment state evaluation method, device, equipment, medium and product

Abstract

The invention discloses a state evaluation method, device and equipment of diesel engine equipment, a medium and a product. The method comprises the following steps: acquiring operation condition information of to-be-evaluated diesel engine equipment; when the operation working condition information reaches a stable working condition, symmetric characteristic parameters of symmetric structural components in the to-be-evaluated diesel engine equipment are obtained; and determining a health state assessment result of the diesel engine equipment to be assessed according to the symmetric characteristic parameters and a pre-training trend prediction model. By introducing a data screening mechanism of a working condition, data interference in unstable states such as starting and shutdown is effectively eliminated, the accuracy of subsequent state evaluation is improved, symmetric characteristic parameters are constructed based on operation characteristics of symmetric structural components in equipment, health state evaluation is performed based on the symmetric characteristic parameters, and the reliability of health state evaluation is improved. And early-stage structure imbalance abnormity can be effectively identified. Compared with a traditional single-channel monitoring mode, local performance deviation can be more sensitively reflected, and the accuracy of diesel engine equipment health state evaluation is improved.

Description

Technical Field

[0001] This invention relates to the field of fault detection technology, and in particular to a method, apparatus, equipment, medium and product for assessing the condition of diesel engine equipment. Background Technology

[0002] With the increasing demands for equipment reliability and intelligent operation and maintenance in the industrial sector, condition monitoring and fault prediction technologies for key power equipment such as diesel engines have received widespread attention. In such systems, the turbocharger, as a crucial component ensuring intake efficiency and output power, has a significant impact on the overall performance of the diesel engine.

[0003] In diesel engine health monitoring technology, a common practice is to use single-point sensor data (such as turbocharger speed, temperature, and pressure) to construct fixed threshold judgment models or statistical analysis models to monitor whether operating parameters exceed normal ranges. Furthermore, in some existing rail transit or construction machinery applications, trend analysis algorithms, such as moving averages or simple linear regression, are also used to predict short-term fluctuation trends of certain key parameters in order to detect abnormal behavior.

[0004] However, current methods only set thresholds or model for a single turbocharger channel, failing to fully utilize the mirror symmetry characteristics of symmetrical structures. This results in insufficient ability to identify performance degradation and imbalance-type faults on one side. Furthermore, abnormal disturbances in some characteristics often affect both turbochargers simultaneously, making it impossible to accurately determine whether single-channel data fluctuations are the source of a fault. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, medium, and product for assessing the condition of diesel engine equipment, so as to effectively identify early structural imbalance-type anomalies and achieve accurate assessment of the health status of diesel engine equipment.

[0006] According to a first aspect of the present invention, a condition assessment method for diesel engine equipment is provided, comprising:

[0007] Obtain operating condition information of the diesel engine equipment to be evaluated;

[0008] When the operating condition information reaches a stable operating condition, the symmetry characteristic parameters of the symmetrical structural components in the diesel engine equipment to be evaluated are obtained;

[0009] Based on the symmetric feature parameters and the pre-trained trend prediction model, the health status assessment result of the diesel engine equipment to be evaluated is determined.

[0010] According to a second aspect of the present invention, a condition assessment apparatus for diesel engine equipment is provided, comprising:

[0011] The information acquisition module is used to acquire the operating condition information of the diesel engine equipment to be evaluated.

[0012] The parameter filtering module is used to obtain the symmetry characteristic parameters of the symmetrical structural components in the diesel engine equipment to be evaluated when the operating condition information reaches the stable operating condition.

[0013] The status assessment module is used to determine the health status assessment result of the diesel engine equipment to be assessed based on the symmetric feature parameters and the pre-trained trend prediction model.

[0014] According to a third aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the condition assessment method for diesel engine equipment according to any embodiment of the present invention.

[0018] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the state assessment method for diesel engine equipment according to any embodiment of the present invention.

[0019] According to a fifth aspect of the present invention, embodiments of the present invention also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the state assessment method for diesel engine equipment according to any embodiment of the present invention.

[0020] The technical solution of this invention involves acquiring the operating condition information of the diesel engine equipment to be evaluated; when the operating condition information reaches stable operating conditions, acquiring the symmetrical characteristic parameters of the symmetrical structural components in the diesel engine equipment; and determining the health status assessment result of the diesel engine equipment based on the symmetrical characteristic parameters and a pre-trained trend prediction model. By introducing a data filtering mechanism for operating conditions, data interference under unstable states such as start-up and shutdown is effectively eliminated, improving the accuracy of subsequent status assessments. Symmetrical characteristic parameters are constructed based on the operating characteristics of the symmetrical structural components in the equipment, and health status assessments are performed based on these symmetrical characteristic parameters, effectively identifying early structural imbalance anomalies. Compared with traditional single-channel monitoring methods, this approach can more sensitively reflect local performance deviations, improving the accuracy of diesel engine equipment health status assessments.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a condition assessment method for diesel engine equipment provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is an example flowchart of a condition assessment method for diesel engine equipment provided in Embodiment 1 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of a condition assessment device for diesel engine equipment according to Embodiment 2 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device that implements an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a condition assessment method for diesel engine equipment provided in Embodiment 1 of the present invention. This embodiment is applicable to the condition assessment of symmetrical structural components of diesel engine equipment. The method can be executed by a condition assessment method for diesel engine equipment, which can be implemented in hardware and / or software, and can be configured in electronic devices. Figure 1 As shown, the method includes:

[0031] S110. Obtain the operating condition information of the diesel engine equipment to be evaluated.

[0032] In this embodiment, the diesel engine equipment to be evaluated can be understood as a diesel engine equipment with a symmetrical structure. Operating condition information can be understood as parameters characterizing the operating state of the diesel engine to be evaluated, such as key parameters like engine speed, load fluctuations, and power output change rate.

[0033] Specifically, the processor can obtain operating condition information that affects the stable operation of the diesel engine equipment to be evaluated through monitoring equipment. This operating condition information includes, but is not limited to, operating speed, load fluctuation, and power output change rate, which can be set according to actual monitoring needs.

[0034] S120. When the operating condition information reaches a stable operating condition, obtain the symmetrical characteristic parameters of the symmetrical structural components in the diesel engine equipment to be evaluated.

[0035] In practical applications, diesel engines are affected by factors such as load fluctuations and environmental changes during operation, leading to significant fluctuations in sensor signals. Therefore, the scientific selection of stable operating condition data is crucial before conducting structural symmetry analysis and intelligent diagnostic modeling. Stable operating conditions refer to the conditions used to determine whether the diesel engine under evaluation is in a steady-state operating state. For example, it is necessary to determine whether key parameters such as engine speed, load, and power output remain stable without significant fluctuations or abrupt changes within a certain time window.

[0036] In this embodiment, a symmetrical structural component can be understood as two or more channels or components symmetrically arranged in the diesel engine to be evaluated, such as left and right cylinder blocks, twin turbochargers, and symmetrical cooling systems. Symmetrical characteristic parameters refer to two or more operational characteristic parameters of the symmetrical structural component.

[0037] Specifically, the processor can compare the predetermined stable operating conditions with the operating condition information. When the operating condition information reaches the stable operating conditions, the diesel engine to be evaluated is in a stable operating state. At this time, the processor can obtain the symmetrical characteristic parameters of the symmetrical structural components in the diesel engine equipment to be evaluated.

[0038] For example, taking the low-pressure turbochargers symmetrically arranged in a diesel engine as an example of symmetrical structural components, and taking the speed sensor as an example of symmetrical characteristic parameters, the operating speed of the diesel engine to be evaluated is used as the operating condition information. When the operating speed of the diesel engine to be evaluated is in the medium-high load stable range (including but not limited to the diesel engine speed between 1430-1800 rpm), the equipment load fluctuation is lower than a specific threshold and the sensor data remains complete and stable, the stable operating condition is met. At this time, the processor can obtain the operating speed data of the two low-pressure turbochargers as symmetrical characteristic parameters.

[0039] S130. Based on the symmetric characteristic parameters and the pre-trained trend prediction model, determine the health status assessment results of the diesel engine equipment to be evaluated.

[0040] In this embodiment, the pre-trained trend prediction model can be understood as a model used to predict the trend of parameter changes, such as a machine learning model. The health status assessment result can be understood as an assessment result reflecting whether the diesel engine equipment to be assessed is healthy.

[0041] Specifically, symmetrical structural components should exhibit highly consistent performance parameters during normal operation, thus the theoretical difference between corresponding sensor signals should be close to zero. When the diesel engine under evaluation exhibits localized deterioration, structural inhomogeneity, or a failure trend, this symmetry will be broken, causing the difference between similar parameters to deviate significantly from zero. The processor can then determine the difference sequence based on the symmetrical characteristic parameters, input this sequence into a pre-trained trend prediction model for data smoothing and trend prediction analysis, and obtain the prediction result of the pre-trained trend prediction model. If the difference sequence exceeds the prediction result for several consecutive periods, the health status assessment result of the diesel engine under evaluation is determined to be sub-healthy, and a sub-health warning signal is output to relevant personnel; otherwise, the health status assessment result is determined to be healthy. Furthermore, by plotting the characteristic fitting lines of the symmetrical characteristic parameters and outputting the data fluctuations, data visualization can be achieved through graphical trend displays and structured report outputs, providing clear guidance for subsequent maintenance and positioning.

[0042] The technical solution of this invention involves acquiring the operating condition information of the diesel engine equipment to be evaluated; when the operating condition information reaches stable operating conditions, acquiring the symmetrical characteristic parameters of the symmetrical structural components in the diesel engine equipment; and determining the health status assessment result of the diesel engine equipment based on the symmetrical characteristic parameters and a pre-trained trend prediction model. By introducing a data filtering mechanism for operating conditions, data interference under unstable states such as start-up and shutdown is effectively eliminated, improving the accuracy of subsequent status assessments. Symmetrical characteristic parameters are constructed based on the operating characteristics of the symmetrical structural components in the equipment, and health status assessments are performed based on these symmetrical characteristic parameters, effectively identifying early structural imbalance anomalies. Compared with traditional single-channel monitoring methods, this approach can more sensitively reflect local performance deviations, improving the accuracy of diesel engine equipment health status assessments.

[0043] Furthermore, the diagnostic process in this embodiment pre-sets a difference feature variable interface, which can be widely applied to symmetrical structures on other diesel engines. In actual deployment, users only need to adjust the variable pairs for difference calculation (such as pressure difference, temperature difference, or vibration amplitude difference) to quickly realize the migration and deployment of new equipment. The diagnostic process and framework do not need to be redesigned or modified.

[0044] Furthermore, based on the above embodiments, the steps for determining the health status assessment result of the diesel engine equipment to be evaluated based on symmetric feature parameters and a pre-trained trend prediction model can be refined as follows:

[0045] Based on the symmetric feature parameters, the difference sequence is determined; based on the difference sequence and the pre-trained trend prediction model, the prediction interval is determined; if the difference sequence exceeds the prediction interval in a continuously set period, the health status assessment result of the diesel engine to be evaluated is determined to be sub-healthy; otherwise, the health status assessment result is determined to be healthy.

[0046] In this embodiment, the difference sequence can be understood as a sequence of differences in symmetrical characteristic parameters over a period of time. The prediction interval can be understood as the upper and lower limits of the predicted dynamic changes in the difference. The set period is the length of the period used to determine whether it is stable. The sub-healthy state can be understood as a state used to characterize the failure trend of the components of the diesel engine equipment to be evaluated.

[0047] Specifically, the processor can determine a difference sequence by calculating the hourly differences of symmetric feature parameters over a period of time, forming a "difference sequence" that characterizes the inconsistencies within the equipment. This difference serves as the core input feature for subsequent state assessment and can be used for trend modeling, anomaly detection, and symmetry failure identification. The processor can input the difference sequence into a pre-trained trend prediction model to dynamically predict the short-term trend of the difference changes and determine the prediction interval. The processor can compare the difference sequence with the prediction interval. If the difference sequence exceeds the prediction interval for a continuous set period, the health status assessment result of the diesel engine under evaluation is determined to be sub-healthy; otherwise, the health status assessment result is determined to be healthy.

[0048] This invention achieves dynamic assessment and early warning of sub-health conditions of equipment through difference feature sequences, aiming to standardize the capture of continuous trend deviations caused by slight performance degradation during the operation of diesel engine equipment. Its core idea is that the internal symmetrical structure of the equipment does not suddenly fail during operational degradation, but rather manifests as a slow drift and increasing difference in the difference sequence. Therefore, by trend modeling and dynamic comparison, potential anomalies can be identified in advance.

[0049] For example, continuing the description in the above example, the turbocharger speed data collected by the left and right speed sensors are obtained, and the speed difference is calculated by pairing the data at the same time. The specific expression is as follows:

[0050] ΔN(t) = N_left(t) - N_right(t)

[0051] Wherein, N_left(t) represents the rotational speed of the left turbocharger at time t; N_right(t) represents the rotational speed of the right turbocharger at time t; ΔN(t) represents the instantaneous speed difference between the left and right turbochargers, i.e., the difference value, which is an important dynamic characteristic for measuring the operational consistency of a symmetrical structure.

[0052] Under normal operating conditions, the left and right low-pressure turbochargers should maintain synchronized speeds with a difference close to zero. When either the left or right turbocharger malfunctions or experiences a performance degradation, the difference will deviate significantly from zero, reflecting an imbalance in the performance of the symmetrical structure.

[0053] Based on the above embodiments, the step of determining the prediction interval according to the difference sequence and the pre-trained trend prediction model can be refined as follows:

[0054] Obtain historical data corresponding to the difference sequence; input the difference sequence into the pre-trained trend prediction model to determine the model's predicted value; and determine the prediction range under the fluctuation of the model's predicted value based on the historical data using the pre-trained trend prediction model.

[0055] In this embodiment, historical data can be understood as data from historical moments corresponding to the time of the difference sequence. Model predictions can be understood as the predicted differences.

[0056] Specifically, the processor retrieves historical data corresponding to the time points of the difference sequence from the storage medium. The processor can input both the difference sequence and the historical data into a pre-trained trend prediction model. Through the pre-trained trend prediction model, the model predicts the value corresponding to each time point of the difference sequence. Based on the historical data, the pre-trained trend prediction model determines the prediction range for the fluctuation of each model prediction value.

[0057] For example, since turbocharger component damage or wear typically manifests as continuous, minor performance degradation, a persistent trend in the difference anomaly can capture this gradual deterioration, enabling early warning and diagnosis. The processor can predict short-term difference trends based on a dynamically pre-trained trend prediction model and calculate the dynamic upper and lower limits of each model's predicted value, i.e., the prediction interval, based on historical data. The real-time observed difference is calculated within each monitoring period (the period corresponding to the difference sequence) and compared with the prediction interval. As shown in the table below, including the measured values ​​at five times t1-t5 and the maximum / minimum value in the prediction interval, it can be seen that from time t1 onwards, the measured value has exceeded the maximum model predicted value in the prediction interval, and the measured values ​​at times t1-t5 all exceed the maximum value in the prediction interval. That is, the actual observed difference value exceeds the prediction interval for multiple consecutive periods. Starting at time t3, the diesel engine equipment to be evaluated is determined to have entered a sub-healthy state, and a sub-healthy warning signal is output.

[0058] Table 1 Example of Results

[0059]

[0060] In this embodiment of the invention, stable operating conditions are introduced to screen the operating state before obtaining symmetry feature parameters. Only when the diesel engine equipment to be evaluated is operating in a stable phase without significant disturbances is the detection data of the symmetrical structural components at that moment extracted for difference calculation. This minimizes the impact of operating condition changes, eliminates the interference of dynamic disturbances on the analysis results, and ensures that the difference features truly reflect the performance differences and trends within the structure. By introducing symmetry feature parameters to determine the difference sequence, dynamic evaluation of the equipment status is achieved. Compared to traditional methods, this approach no longer relies on fixed threshold judgments of single variables. Instead, it utilizes the synchronous deviation of symmetrical structural components to construct a difference sequence and perform trend prediction, thereby enabling the identification of early sub-health states. The difference variable interface also gives the method good structural transferability and versatility.

[0061] As a first optional embodiment of this embodiment, based on the above embodiment, it further includes:

[0062] The pre-trained trend prediction model is updated based on the difference sequence to obtain the updated pre-trained trend prediction model.

[0063] Specifically, after each prediction, the processor can calculate the prediction error by comparing the measured values ​​of the difference sequence with the model prediction values. When the prediction error exceeds a preset threshold for several consecutive periods, the processor can verify the prediction accuracy of the pre-trained trend prediction model and update the model parameters to obtain the updated pre-trained trend prediction model.

[0064] To quantitatively evaluate the performance of the pre-trained trend prediction model in each validation window, this invention designs a difference scoring mechanism to statistically analyze the difference between the model output and the actual measured value. Furthermore, based on the above embodiments, the steps for updating the pre-trained trend prediction model based on the difference sequence to obtain the updated pre-trained trend prediction model can be refined as follows:

[0065] Based on the difference sequence and the model prediction value determined by the pre-trained trend prediction model, an error score is determined. If the error score reaches the model update condition, the state evaluation is stopped and historical running data under a fixed-length time window is obtained. The pre-trained trend prediction model is iteratively trained based on the historical running data to obtain the updated pre-trained trend prediction model. Otherwise, the pre-trained trend prediction model is not updated.

[0066] In this embodiment, the error score can be understood as a result used to characterize the deviation between the measured value and the predicted value. The model update condition can be understood as a condition used to determine whether the error is too large; for example, a preset error threshold or range can be set. The fixed-length time window can be understood as a time period set for acquiring data. Historical operating data can be understood as historical differences and historical predicted values.

[0067] Specifically, based on the difference sequence and the model prediction values ​​determined by the pre-trained trend prediction model, an error score is determined. The processor can calculate multiple error metrics, including but not limited to mean absolute error (MAE), maximum absolute error (Max Error), and root mean square error (RMSE), as references for measuring model accuracy. According to set weights and scoring criteria, these metrics can be uniformly converted into score values ​​to measure whether the model's current predictive ability meets diagnostic requirements. When the error score continuously falls below a certain threshold or the error consistently exceeds a defined range, i.e., the error score reaches the model update condition, the model performance deteriorates. The processor can then control a halt to evaluate and record model anomalies. The processor can acquire historical running data within a fixed-length time window; iteratively train the pre-trained trend prediction model based on the historical running data to obtain an updated pre-trained trend prediction model or prompt for manual intervention; otherwise, the pre-trained trend prediction model is not updated.

[0068] Based on the above embodiments, the steps for iteratively training the pre-trained trend prediction model using historical operational data to obtain an updated pre-trained trend prediction model can be refined as follows:

[0069] Historical data is divided into multiple training and validation sub-segments according to different time windows to obtain a cross-validation structure dataset. The pre-trained trend prediction model is iteratively trained using the cross-validation structure dataset to obtain an updated pre-trained trend prediction model.

[0070] In this embodiment, the training sub-segment set can be understood as the training set divided according to a time window. The validation sub-segment set can be understood as the validation set divided according to the time window corresponding to the training sub-segment set. The cross-validation structure dataset can be understood as the dataset used for cross-validation, including the training sub-segment set and the validation sub-segment set under the corresponding time window.

[0071] For example, the training sub-segment can be divided according to the historical time periods corresponding to the historical operation data: Monday to Sunday is the training sub-segment set, and the following Monday is the validation sub-segment set; the following Tuesday to the following Monday is the training sub-segment set, and the following Tuesday is the validation sub-segment set, etc.

[0072] Specifically, to continuously verify its predictive ability under dynamic operating conditions, a sliding window cross-validation mechanism is introduced. Within each monitoring cycle, the processor can automatically extract a fixed-length time window from the latest historical operating data and further divide the historical operating data within this time window into multiple training-validation sub-segments, forming a cross-validation structure dataset. Within each sub-segment, model prediction and result comparison operations are repeatedly performed. By advancing window by window, the generalization ability and adaptability of the pre-trained trend prediction model in the current time period are comprehensively evaluated, and the parameters of the model whose performance does not meet expectations are optimized and tuned for iterative training to obtain an updated pre-trained trend prediction model.

[0073] In the first optional embodiment of this example, a difference scoring mechanism is used to statistically analyze the difference between the model output and the actual measured value, and a sliding window cross-validation mechanism is introduced to update the model. This enables continuous monitoring of model performance. Compared with traditional single-point validation methods, this method can effectively capture the consistency of the model's response to data in different time periods, avoid the influence of occasional deviations on the overall judgment, ensure the stability of the model, and thus improve the model's subsequent prediction performance.

[0074] For example, a specific example will be shown. Figure 2 This is an example flowchart of a condition assessment method for diesel engine equipment provided in Embodiment 1 of the present invention, as shown below. Figure 2As shown, the processor can first perform operating condition analysis on the diesel engine equipment to be evaluated. By acquiring historical operating condition information, it determines whether the diesel engine equipment has reached stable operating conditions, obtains the symmetrical characteristic parameters of symmetrical structural components under stable operating conditions, and determines the difference sequence. A pre-trained trend prediction model is used to determine the prediction interval, and it is determined whether the difference exceeds the prediction interval for multiple consecutive detection cycles. If so, the health status assessment result of the diesel engine equipment is judged to be in a sub-healthy state; otherwise, it is judged to be in a healthy state. The processor can feed the predicted values ​​and data back to the model verification mechanism. Combining historical data with the aforementioned model error scoring and cross-validation methods, the predictive effect of the model is verified and iteratively trained to obtain an updated pre-trained trend prediction model. The processor can plot the difference sequence as a feature fitting line and determine the data fluctuation value through the prediction interval to graphically display the data. It can also push the health status assessment results to the user through the corresponding API.

[0075] Example 2

[0076] Figure 3 This is a schematic diagram of the condition assessment device for a diesel engine provided in Embodiment 2 of the present invention. Figure 3 As shown, the device includes: an information acquisition module 31, a parameter filtering module 32, and a status evaluation module 33.

[0077] Information acquisition module 31 is used to acquire operating condition information of the diesel engine equipment to be evaluated;

[0078] The parameter filtering module 32 is used to obtain the symmetry characteristic parameters of the symmetrical structural components in the diesel engine equipment to be evaluated when the operating condition information reaches the stable operating condition.

[0079] The status assessment module 33 is used to determine the health status assessment result of the diesel engine equipment to be assessed based on the symmetric feature parameters and the pre-trained trend prediction model.

[0080] The technical solution of this invention involves acquiring the operating condition information of the diesel engine equipment to be evaluated; when the operating condition information reaches stable operating conditions, acquiring the symmetrical characteristic parameters of the symmetrical structural components in the diesel engine equipment; and determining the health status assessment result of the diesel engine equipment based on the symmetrical characteristic parameters and a pre-trained trend prediction model. By introducing a data filtering mechanism for operating conditions, data interference under unstable states such as start-up and shutdown is effectively eliminated, improving the accuracy of subsequent status assessments. Symmetrical characteristic parameters are constructed based on the operating characteristics of the symmetrical structural components in the equipment, and health status assessments are performed based on these symmetrical characteristic parameters, effectively identifying early structural imbalance anomalies. Compared with traditional single-channel monitoring methods, this approach can more sensitively reflect local performance deviations, improving the accuracy of diesel engine equipment health status assessments.

[0081] Furthermore, the state assessment module includes:

[0082] The first determining unit is used to determine the difference sequence based on the symmetry feature parameters;

[0083] The second determining unit is used to determine the prediction interval based on the difference sequence and the pre-trained trend prediction model;

[0084] The third determining unit is used to determine that the health status assessment result of the diesel engine to be evaluated is a sub-healthy state if the difference sequence exceeds the prediction interval in a continuously set period.

[0085] The fourth determining unit is used to determine, otherwise, that the health status assessment result is a healthy state.

[0086] Specifically, the second determining unit is used for:

[0087] Obtain historical data corresponding to the difference sequence;

[0088] The difference sequence is input into the pre-trained trend prediction model to determine the model's predicted value;

[0089] Based on the historical data, the pre-trained trend prediction model determines the prediction range under the fluctuation of the model's predicted value.

[0090] Furthermore, the device also includes:

[0091] The model update module is used to update the pre-trained trend prediction model based on the difference sequence to obtain the updated pre-trained trend prediction model.

[0092] Furthermore, the model update module includes:

[0093] The fifth determining unit is used to determine the error score based on the difference sequence and the model prediction value determined by the pre-trained trend prediction model;

[0094] The sixth determining unit is used to stop the state evaluation and obtain historical running data under a fixed-length time window if the error score reaches the model update condition;

[0095] The seventh determining unit is used to iteratively train the pre-trained trend prediction model based on the historical operating data to obtain an updated pre-trained trend prediction model.

[0096] The eighth determining unit is used to, otherwise, not update the pre-trained trend prediction model.

[0097] Specifically, the seventh determining unit is used for:

[0098] The historical running data is divided into multiple training sub-segments and validation sub-segments according to different time windows to obtain a cross-validation structure dataset.

[0099] The pre-trained trend prediction model is iteratively trained using a cross-validation structured dataset to obtain an updated pre-trained trend prediction model.

[0100] The diesel engine equipment condition assessment device provided in the embodiments of the present invention can execute the diesel engine equipment condition assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0101] Example 3

[0102] Figure 4 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0103] like Figure 4 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0104] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0105] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as the condition assessment methods for diesel engine equipment.

[0106] In some embodiments, the condition assessment method for diesel engine equipment may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the condition assessment method for diesel engine equipment described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the condition assessment method for diesel engine equipment by any other suitable means (e.g., by means of firmware).

[0107] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0109] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer 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.

[0110] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0111] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0112] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0113] In one embodiment, the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements the condition assessment method for diesel engine equipment according to any embodiment of the present invention.

[0114] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0115] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0116] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A condition assessment method for diesel engine equipment, characterized in that, include: Obtain operating condition information of the diesel engine equipment to be evaluated; When the operating condition information reaches a stable operating condition, the symmetry characteristic parameters of the symmetrical structural components in the diesel engine equipment to be evaluated are obtained; Based on the symmetric feature parameters and the pre-trained trend prediction model, the health status assessment result of the diesel engine equipment to be evaluated is determined.

2. The method according to claim 1, characterized in that, The step of determining the health status assessment result of the diesel engine equipment to be evaluated based on the symmetric feature parameters and the pre-trained trend prediction model includes: Determine the difference sequence based on the symmetric feature parameters; The prediction interval is determined based on the difference sequence and the pre-trained trend prediction model; If the difference sequence exceeds the prediction interval for a continuous set period, the health status assessment result of the diesel engine to be evaluated is determined to be a sub-healthy state. Otherwise, the health status assessment result is determined to be a healthy state.

3. The method according to claim 2, characterized in that, The step of determining the prediction interval based on the difference sequence and the pre-trained trend prediction model includes: Obtain historical data corresponding to the difference sequence; The difference sequence is input into the pre-trained trend prediction model to determine the model's predicted value; Based on the historical data, the pre-trained trend prediction model determines the prediction range under the fluctuation of the model's predicted value.

4. The method according to claim 2, characterized in that, Also includes: The pre-trained trend prediction model is updated based on the difference sequence to obtain the updated pre-trained trend prediction model.

5. The method according to claim 4, characterized in that, The step of updating the pre-trained trend prediction model based on the difference sequence to obtain the updated pre-trained trend prediction model includes: Based on the difference sequence and the model prediction value determined by the pre-trained trend prediction model, an error score is determined. If the error score reaches the model update condition, the state evaluation is stopped and historical running data under a fixed-length time window is obtained; The pre-trained trend prediction model is iteratively trained based on the historical operating data to obtain an updated pre-trained trend prediction model. Otherwise, the pre-trained trend prediction model will not be updated.

6. The method according to claim 5, characterized in that, The step of iteratively training the pre-trained trend prediction model based on the historical operating data to obtain an updated pre-trained trend prediction model includes: The historical running data is divided into multiple training sub-segments and validation sub-segments according to different time windows to obtain a cross-validation structure dataset. The pre-trained trend prediction model is iteratively trained using a cross-validation structured dataset to obtain an updated pre-trained trend prediction model.

7. A condition assessment device for diesel engine equipment, characterized in that, include: The information acquisition module is used to acquire the operating condition information of the diesel engine equipment to be evaluated. The parameter filtering module is used to obtain the symmetry characteristic parameters of the symmetrical structural components in the diesel engine equipment to be evaluated when the operating condition information reaches the stable operating condition. The status assessment module is used to determine the health status assessment result of the diesel engine equipment to be assessed based on the symmetric feature parameters and the pre-trained trend prediction model.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the condition assessment method for the diesel engine equipment according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the condition assessment method for the diesel engine equipment as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the condition assessment method for diesel engine equipment according to any one of claims 1-6.

Images