Balancing test method and system for diesel generator set

Abstract

The present application relates to diesel generating set detection technical field, specifically to a kind of diesel generating set balancing test method and system;Method includes: constructing full-dimension operating signal acquisition network, the original operating signal of diesel generating set under different operating conditions is collected, and original operating signal is handled, and effective feature set is obtained;Effective feature set is respectively judged to single parameter threshold value, frequency domain feature association is judged and weighted multi-parameter fusion calculation is carried out, and the balance state of diesel generating set is confirmed, and balance state data is output;According to balance state data and vibration amplitude distribution, lock fault core area and positioning position, final fault positioning result is obtained by diesel generating set balancing fault feature library matching verification;System includes: operating signal processing module, balance state multi-parameter fusion module, balancing fault positioning module;Through above-mentioned mode, the specific position of unbalance quality is determined, and fault positioning precision is improved.

Description

Technical Field

[0001] This invention relates to the field of diesel generator set testing technology, and in particular to a method and system for balancing diesel generator sets. Background Technology

[0002] Diesel generator sets are core emergency power supply equipment in industrial production, construction, medical and health, and communication base stations. Their operational stability directly determines the continuity and safety of production and operation in these fields. To ensure stable operation of diesel generator sets, balancing testing is an indispensable core testing step. Existing diesel generator set balancing testing technologies are mainly divided into two categories: offline testing and online testing. Offline testing requires disassembling the unit from the operating site and transporting it to a specialized testing site for testing using specialized equipment. This method has significant drawbacks: firstly, the disassembly and transportation process is cumbersome, consuming a large amount of manpower and time, and the disassembly process can easily cause secondary damage to the unit's precision components; secondly, the offline testing environment differs significantly from the actual operating environment of the unit, making it difficult for the test results to accurately reflect the unit's balance state under actual operating conditions, resulting in insufficient test relevance and accuracy.

[0003] While existing online testing technologies have solved the problem of scenario adaptation for offline testing, they still have the following technical shortcomings: low fault location accuracy, which can only locate the general fault area and cannot accurately determine the specific location of the unbalanced mass. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for testing the balance of diesel generator sets, aiming to solve the technical problem in the prior art of low fault location accuracy, which can only locate the general fault area and cannot accurately determine the specific location of the unbalance mass.

[0005] To achieve the above objectives, the present invention provides a diesel generator set balance test method, comprising the following steps:

[0006] Multiple types of sensors are deployed at key parts of the diesel generator set to construct a full-dimensional operation signal acquisition network. This network collects the original operation signals of the diesel generator set under different operating conditions and extracts the time-domain and frequency-domain features of the vibration signals from the original operation signals to obtain an effective feature set. The sensors include vibration sensors, speed sensors, torque sensors, and temperature sensors.

[0007] The effective feature set is subjected to single-parameter threshold judgment, frequency domain feature correlation judgment and weighted multi-parameter fusion calculation respectively to confirm the balance state of the diesel generator set and output the balance state data.

[0008] The pre-built diesel generator set balance fault feature library is retrieved. This feature library is constructed by collecting and analyzing the operating signal feature data of diesel generator sets with known imbalance faults. Based on the balance state data and vibration amplitude distribution, the core area and location of the fault are locked. The final fault location result is obtained by matching and verifying the diesel generator set balance fault feature library.

[0009] This process involves deploying various types of sensors at key locations within the diesel generator set to construct a comprehensive operational signal acquisition network. This network collects raw operational signals from the generator set under different operating conditions and extracts the time-domain and frequency-domain features of vibration signals from these raw signals to obtain an effective feature set. The sensors include vibration sensors, speed sensors, torque sensors, and temperature sensors.

[0010] Sensors are deployed at key monitoring points of the diesel generator set to build a comprehensive operational signal acquisition network.

[0011] Start the diesel generator set, switch it to no-load and rated load conditions in sequence, and use the constructed signal acquisition network to synchronously collect the original operating signals under each condition; the original operating signals include vibration signals, speed signals, torque signals and temperature signals.

[0012] The time-domain and frequency-domain features of the vibration signal are extracted from the original operating signal to form an effective feature set.

[0013] Among the steps, the following steps involve deploying sensors at key monitoring points of the diesel generator set to construct a comprehensive operational signal acquisition network:

[0014] Key monitoring areas include the bearing housings at both ends of the generator rotor, the bearing housings at both ends of the diesel engine crankshaft, the generator set frame, the generator output shaft, the coupling between the diesel engine and the generator, as well as the bearing housings and the generator set windings.

[0015] The arrangement is as follows: vibration sensors are placed on the bearing housings at both ends of the generator rotor, the bearing housings at both ends of the diesel engine crankshaft, and the engine frame; speed sensors are placed on the generator output shaft; torque sensors are placed on the coupling; and temperature sensors are placed on each bearing housing and the unit windings.

[0016] In the step of extracting the time-domain and frequency-domain features of the vibration signal from the original operating signal to form an effective feature set:

[0017] The original operating signal is processed by filtering and noise reduction, hierarchical amplification and normalization, detrending and feature extraction, in order to remove external environmental noise and sensor interference, unify the signal magnitude to eliminate dimensional differences, and eliminate the linear trend component of the signal.

[0018] Among them, in the steps of performing single-parameter threshold judgment, frequency domain feature correlation judgment and weighted multi-parameter fusion calculation on the effective feature set to confirm the balance state of the diesel generator set and output the balance state data:

[0019] Retrieve the preset threshold values ​​for various parameters, including vibration amplitude threshold, speed fluctuation threshold, torque stability threshold, and temperature threshold. Compare the vibration time-domain characteristic parameters, speed fluctuation range, torque stability data, and temperature data in the effective feature set with the corresponding thresholds to initially screen out abnormal parameters that exceed the thresholds and their corresponding monitoring locations.

[0020] The fundamental frequency of the diesel generator set is calculated based on the speed signal in the effective feature set. The fundamental frequency component of the vibration signal frequency domain characteristics in the effective feature set is analyzed. It is determined whether the amplitude of the fundamental frequency component exceeds the set threshold and whether the phase is stable. Combined with the core characteristic of unbalanced vibration being dominated by the fundamental frequency, it is preliminarily determined whether there is a potential imbalance in the unit.

[0021] The influence weights of each parameter on the equilibrium state judgment are set, and the feature values ​​of various parameters in the effective feature set are weighted and fused based on the set weights to obtain the fused decision value.

[0022] The process includes setting the influence weights of each parameter on the equilibrium state judgment, and then performing a weighted fusion calculation on the feature values ​​of various parameters in the effective feature set based on the set weights to obtain the fused decision value:

[0023] The fusion decision value is compared with the preset equilibrium state judgment threshold.

[0024] In the step of comparing the fused decision value with the preset equilibrium state determination threshold:

[0025] If the fusion decision value exceeds the judgment threshold, the unit has an imbalance problem;

[0026] If the error does not exceed the limit, the signal processing procedure needs to be rechecked and unbalanced faults need to be investigated before outputting balanced state data.

[0027] The steps include: retrieving a pre-built diesel generator set balance fault feature library, which is constructed by collecting and analyzing the operating signal feature data of diesel generator sets with known imbalance faults; locking the core area and location of the fault based on balance state data and vibration amplitude distribution; and obtaining the final fault location result through matching and verification with the diesel generator set balance fault feature library.

[0028] By retrieving the abnormal parameter correlation information from the equilibrium state data and combining it with the vibration amplitude characteristics of each monitoring location in the effective feature set, the peak value and effective value amplitude data of the vibration signal at different monitoring locations are compared, and the monitoring location with the largest vibration amplitude is locked as the core area of ​​the imbalance fault.

[0029] The circumferential angle and axial distance of the unbalanced mass are calculated to accurately locate the fault.

[0030] The pre-built diesel generator set balance fault feature library is retrieved, and the effective feature set obtained from the test is matched with the feature data in the fault feature library for similarity. The fault type and location corresponding to the feature data with the highest matching degree are then selected.

[0031] In the step of calculating the circumferential angle and axial distance of the unbalanced mass to accurately locate the fault:

[0032] Using the speed signal from the effective feature set as a reference, the phase angle of the vibration signal at the core area and surrounding monitoring locations is determined. Combined with the structural parameters of the diesel generator set, including rotor diameter, bearing spacing, and coupling size, a mapping relationship between the phase angle and the location of the unbalanced mass is established.

[0033] This invention also provides a diesel generator set balance testing system, including an operating signal processing module, a balance state multi-parameter fusion module, and a balance fault location module; wherein:

[0034] The operation signal processing module is used to deploy various types of sensors in key parts of the diesel generator set, construct a full-dimensional operation signal acquisition network, collect the original operation signals of the diesel generator set under different operating conditions, and extract the time domain features and frequency domain features of the vibration signal from the original operation signals to obtain an effective feature set.

[0035] The equilibrium state multi-parameter fusion module is used to perform single-parameter threshold judgment, frequency domain feature correlation judgment and weighted multi-parameter fusion calculation on the effective feature set respectively, to confirm the equilibrium state of the diesel generator set and output the equilibrium state data.

[0036] The balance fault location module is used to retrieve a pre-built diesel generator set balance fault feature library. This feature library is constructed by collecting and analyzing the operating signal feature data of diesel generator sets with known imbalance faults. Based on the balance state data and vibration amplitude distribution, the core area and location of the fault are locked. The final fault location result is obtained by matching and verifying the diesel generator set balance fault feature library.

[0037] The present invention discloses a diesel generator set balance testing method and system, which employs the aforementioned operating signal processing module, the aforementioned balance state multi-parameter fusion module, and the aforementioned balance fault location module to perform the following steps: Multiple types of sensors are deployed at key parts of the diesel generator set to construct a full-dimensional operating signal acquisition network, collecting raw operating signals of the diesel generator set under different operating conditions, and extracting the time-domain and frequency-domain features of vibration signals from the raw operating signals to obtain an effective feature set; single-parameter threshold judgment, frequency-domain feature correlation judgment, and weighted multi-parameter fusion calculation are performed on the effective feature set to confirm the balance state of the diesel generator set and output the balance state data; based on the balance state data and vibration amplitude distribution, the core fault area and location are locked, and the final fault location result is obtained through matching and verification with the diesel generator set balance fault feature library; through the above method, the specific location of the unbalanced mass is determined, thereby improving the fault location accuracy. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0039] Figure 1 This is a flowchart of the steps of the diesel generator set balance test method of the present invention.

[0040] Figure 2 This is a flowchart of steps S100 of the present invention.

[0041] Figure 3 This is a flowchart of steps S200 of the present invention.

[0042] Figure 4 This is a flowchart of steps S300 of the present invention.

[0043] Figure 5 This is a schematic diagram of the diesel generator set balance test system of the present invention.

[0044] Figure 6 This is a schematic diagram of the electronic device of the present invention.

[0045] 401 - Operation signal processing module, 402 - Balanced state multi-parameter fusion module, 403 - Balanced fault location module. Detailed Implementation

[0046] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0047] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0048] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0049] Please see Figures 1-4 This invention provides a method for balancing diesel generator sets, comprising the following steps:

[0050] S100: Various types of sensors are deployed in key parts of the diesel generator set to build a full-dimensional operation signal acquisition network, collect the original operation signals of the diesel generator set under different operating conditions, and extract the time-domain and frequency-domain features of the vibration signal from the original operation signal to obtain an effective feature set; among them, the sensors include vibration sensors, speed sensors, torque sensors and temperature sensors.

[0051] In this embodiment, various types of sensors are deployed at key parts of the diesel generator set to construct a comprehensive operational signal acquisition network. This network collects raw operational signals from the diesel generator set under different operating conditions and extracts the time-domain and frequency-domain features of the vibration signals from these raw signals to obtain an effective feature set. The specific process is as follows:

[0052] S101: Sensors are deployed at key monitoring locations of the diesel generator set to construct a comprehensive operational signal acquisition network. Key monitoring locations include the bearing housings at both ends of the generator rotor, the bearing housings at both ends of the diesel engine crankshaft, the generator set frame, the generator output shaft, the coupling between the diesel engine and the generator, and the bearing housings and winding locations of the generator set. The deployment method is as follows: vibration sensors are deployed at the bearing housings at both ends of the generator rotor, the bearing housings at both ends of the diesel engine crankshaft, and the generator set frame; speed sensors are deployed at the generator output shaft; torque sensors are deployed at the coupling; and temperature sensors are deployed at each bearing housing and winding locations of the generator set.

[0053] S102: Start the diesel generator set, switch to no-load and rated load conditions in sequence and run it, and use the constructed signal acquisition network to synchronously collect the original operating signals under each condition; the original operating signals include vibration signal, speed signal, torque signal and temperature signal;

[0054] S104: The original operating signal is filtered and denoised, amplified and normalized in stages, detrended and feature extracted. This process removes external environmental noise and sensor interference, unifies the signal magnitude to eliminate dimensional differences, eliminates the linear trend component of the signal, and extracts the time-domain and frequency-domain features of the vibration signal to form an effective feature set.

[0055] In the above process, sensors are deployed at key monitoring points of the diesel generator set to construct a comprehensive operational signal acquisition network. These key monitoring points include the bearing housings at both ends of the generator rotor, the bearing housings at both ends of the diesel engine crankshaft, the generator set frame, the generator output shaft, the coupling between the diesel engine and generator, and the bearing housings and winding sections of the generator set. The deployment method is as follows: vibration sensors are piezoelectric accelerometers, which are fixedly attached to the flat surfaces of the bearing housings at both ends of the generator rotor, the diesel engine crankshaft, and the generator set frame, ensuring close contact between the sensors and the monitored areas to guarantee accurate vibration signal acquisition; speed sensors are photoelectric sensors, installed aligned with pre-defined reflective markings on the generator output shaft, ensuring the distance between the sensor and the output shaft meets detection requirements; torque sensors are connected in series on the coupling between the diesel engine and generator to ensure stable signal acquisition during torque transmission; temperature sensors are patch sensors, attached to the outer rings of each bearing housing and the surface of the generator set windings, completing the construction of the comprehensive operational signal acquisition network.

[0056] Start the diesel generator set and first control the unit to run under no-load. After the speed stabilizes, continue running for 15-20 minutes. Then gradually adjust the load to the rated load and run it stably for another 20-30 minutes. Throughout the operation, a constructed full-dimensional operation signal acquisition network is used to synchronously collect raw operation signals under various working conditions through data acquisition equipment. The raw operation signals include vibration signals in the horizontal, vertical and axial directions collected by vibration sensors, real-time speed signals collected by speed sensors, dynamic torque signals collected by torque sensors, and real-time temperature signals collected by temperature sensors. The signal transmission status is monitored in real time during the acquisition process to ensure that there is no signal loss or interruption.

[0057] The acquired raw operating signals undergo multi-step processing to obtain an effective feature set. Specifically, the process is as follows: First, an adaptive filtering algorithm is used to filter and reduce noise in the raw signal, focusing on removing external environmental noise, vibration interference from other equipment, and interference signals from the sensor itself. Next, the filtered signal is amplified in stages to adjust the signal amplitude to a range suitable for data processing. Then, a linear normalization method is used to convert different types of signals to the same magnitude, eliminating dimensional differences. Next, the least squares method is used to detrend the normalized signal, eliminating linear drift components. Finally, the time-domain and frequency-domain features of the vibration signal are extracted. Time-domain features include peak value, peak-to-peak value, and RMS value, while frequency-domain features are obtained through Fourier transform. These features are then integrated to form an effective feature set.

[0058] S200: Perform single-parameter threshold judgment, frequency domain feature correlation judgment and weighted multi-parameter fusion calculation on the effective feature set respectively, confirm the balance state of the diesel generator set, and output the balance state data.

[0059] In this embodiment, single-parameter threshold judgment, frequency domain feature correlation judgment, and weighted multi-parameter fusion calculation are performed on the effective feature set to confirm the balance state of the diesel generator set and output the balance state data. The specific process is as follows:

[0060] S201: Retrieve the preset threshold values ​​for various parameters, including vibration amplitude threshold, speed fluctuation threshold, torque stability threshold, and temperature threshold. Compare the vibration time-domain characteristic parameters, speed fluctuation range, torque stability data, and temperature data in the effective feature set with the corresponding thresholds to initially screen out abnormal parameters that exceed the thresholds and their corresponding monitoring locations.

[0061] S202: Calculate the fundamental frequency of the diesel generator set based on the speed signal in the effective feature set, analyze the fundamental frequency component of the vibration signal frequency domain characteristics in the effective feature set, determine whether the amplitude of the fundamental frequency component exceeds the set threshold and whether the phase is stable, and combine the core characteristic of unbalanced vibration with the fundamental frequency as the main component to preliminarily determine whether there is a potential imbalance in the unit.

[0062] S203: Set the influence weight of each parameter on the equilibrium state judgment, and perform weighted fusion calculation on the feature values ​​of various parameters in the effective feature set based on the set weights to obtain the fusion decision value;

[0063] S204: Compare the fused decision value with the preset balance state judgment threshold; if the fused decision value exceeds the judgment threshold, the unit has an imbalance problem; if it does not exceed the threshold, the signal processing process needs to be re-checked and unbalanced faults need to be investigated, and balance state data is output.

[0064] In the above process, threshold values ​​for various parameters are pre-set based on the model and rated power of the diesel generator set, including vibration amplitude threshold, speed fluctuation threshold, torque stability threshold, and temperature threshold. The preset threshold values ​​are retrieved, and vibration time-domain characteristic parameters, speed fluctuation range, torque stability data, and temperature data from the effective feature set are extracted one by one. The extracted data are compared with the corresponding thresholds, the comparison results are recorded, abnormal parameters exceeding the thresholds are initially screened, and the monitoring parts corresponding to the abnormal parameters are accurately located to form a preliminary list of anomalies.

[0065] The rotational speed signal is extracted from the effective feature set, and the fundamental frequency of the diesel generator set, i.e., the rotational frequency of the unit, is calculated based on the rotational speed signal. The frequency domain characteristics of the vibration signal in the effective feature set are analyzed in a targeted manner, focusing on the amplitude and phase stability of the fundamental frequency component. It is determined whether the amplitude of the fundamental frequency component exceeds the preset fundamental frequency amplitude threshold, and at the same time, it is observed whether the phase remains stable. Combined with the core characteristics of unbalanced vibration, the vibration signal is mainly composed of the fundamental frequency component. If the amplitude of the fundamental frequency component exceeds the standard and the phase is stable, it is preliminarily determined that there is a potential imbalance in the unit, and other types of vibration faults such as resonance and loose components are ruled out.

[0066] Weights are assigned based on the degree of influence of each parameter on the equilibrium state judgment. Among them, the vibration parameter has the greatest impact on the equilibrium state and is assigned the highest weight. The speed parameter, torque parameter, and temperature parameter are assigned corresponding weights in sequence. Based on the set weight values, a weighted summation method is used to fuse the feature values ​​of various parameters in the effective feature set. The process is as follows:

[0067] The weights for vibration parameters are set to 0.5, rotational speed parameters to 0.2, torque parameters to 0.2, and temperature parameters to 0.1. Assuming the effective feature set has a vibration time-domain characteristic parameter value of 0.8, a rotational speed fluctuation range parameter value of 0.6, a torque stability data parameter value of 0.7, and a temperature data parameter value of 0.5, the weighted fusion calculation process is: Fusion decision value = 0.8 × 0.5 + 0.6 × 0.2 + 0.7 × 0.2 + 0.5 × 0.1 = 0.67.

[0068] During the calculation process, it is ensured that the characteristic values ​​of various parameters have been normalized to avoid the impact of magnitude differences on the calculation results, and finally, a fusion decision value that comprehensively reflects the unit's balance state is obtained.

[0069] A preset balance state judgment threshold is retrieved, and the calculated fusion decision value is compared with the judgment threshold. If the fusion decision value exceeds the judgment threshold, it is clear that the unit has an imbalance problem. If the fusion decision value does not exceed the judgment threshold, the signal processing process in step S104 needs to be re-checked to confirm whether there is a signal processing error, and at the same time, the unit needs to be checked for unbalanced faults. Regardless of the comparison result, detailed balance state data is generated and output, including the comparison results of various parameters, fusion decision value, whether there is an imbalance problem and the initial abnormal location.

[0070] S300: Retrieve the pre-built diesel generator set balance fault feature library. This feature library is constructed by collecting and analyzing the operating signal feature data of diesel generator sets with known imbalance faults. Based on the balance state data and vibration amplitude distribution, the core area and location of the fault are locked. The final fault location result is obtained by matching and verifying the diesel generator set balance fault feature library.

[0071] In this embodiment, the core fault area and location are determined based on the balance state data and vibration amplitude distribution. The final fault location result is obtained through matching and verification with the diesel generator set balance fault feature database. The specific process is as follows:

[0072] S301: Retrieve abnormal parameter association information from the balance state data, combine it with the vibration amplitude characteristics of each monitoring location in the effective feature set, compare the peak value and effective value amplitude data of vibration signals at different monitoring locations, and lock the monitoring location with the largest vibration amplitude as the core area of ​​the imbalance fault.

[0073] S302: Using the speed signal in the effective feature set as a reference, determine the phase angle of the vibration signal in the core area and surrounding monitoring positions. Combined with the structural parameters of the diesel generator set, including rotor diameter, bearing spacing, and coupling size, establish the mapping relationship between the phase angle and the location of the unbalanced mass, calculate the circumferential angle and axial distance of the unbalanced mass, and complete the accurate location of the fault.

[0074] S303: Retrieve the pre-built diesel generator set balance fault feature library, perform similarity matching between the effective feature set obtained from the test and the feature data in the fault feature library, and filter out the fault type and location corresponding to the feature data with the highest matching degree.

[0075] In the above process, abnormal parameter correlation information is retrieved from the output equilibrium state data to identify the preliminary abnormal location; at the same time, vibration amplitude characteristics of each monitoring location in the effective feature set are extracted, including the peak value and effective value of the vibration signal; the vibration amplitude data of different monitoring locations are compared one by one to analyze the amplitude distribution pattern; the monitoring location with the largest vibration amplitude is locked as the core area of ​​the imbalance fault, and the specific location information of this area is recorded to lay the foundation for subsequent accurate positioning.

[0076] The rotational speed signal is extracted from the effective feature set and used as a reference signal. The phase angle of the vibration signal at the core area and surrounding key monitoring locations is determined by phase analysis tools. The structural parameters of the diesel generator set are collected, including rotor diameter, bearing spacing, coupling size, etc. Based on these structural parameters, a mapping relationship model between the phase angle and the location of the unbalanced mass is established. The determined phase angle is substituted into the model to calculate the circumferential angle and axial distance of the unbalanced mass, thereby completing the accurate location of the fault and clarifying the specific location of the unbalanced mass.

[0077] The system retrieves a pre-built diesel generator set balance fault feature library. This library contains signal feature data corresponding to different types (such as rotor imbalance, coupling imbalance, etc.) and different locations of imbalance faults, including vibration amplitude, phase angle, frequency components, etc. The construction process of the diesel generator set balance fault feature library is as follows:

[0078] In actual operation, the operation of diesel generator sets under different unbalanced fault conditions is simulated, including but not limited to rotor imbalance, coupling imbalance, and bearing wear.

[0079] High-precision sensors (such as vibration sensors, speed sensors, torque sensors, and temperature sensors) are used to collect raw operating signals under various working conditions, including vibration signals, speed signals, torque signals, and temperature signals.

[0080] Data preprocessing: The acquired raw operating signals are filtered and denoised to remove environmental noise and sensor interference. The signals are then amplified and normalized in stages to unify the signal magnitude and eliminate dimensional differences. Detrending techniques are used to eliminate linear drift components in the signal.

[0081] Feature extraction: Time-domain and frequency-domain features are extracted from the preprocessed signal. Time-domain features include, but are not limited to, peak value, peak-to-peak value, and RMS value; frequency-domain features are obtained through Fourier transform, focusing on the amplitude and phase of the fundamental frequency component. Discriminative feature parameters are extracted for different types of faults (such as rotor imbalance, coupling imbalance, etc.).

[0082] Fault Classification: Based on the extracted feature parameters, different types of faults are classified. For example, the feature data of rotor imbalance faults are grouped into one category, and the feature data of coupling imbalance faults are grouped into another category. A unique identifier is assigned to each fault category to facilitate subsequent feature matching and fault localization.

[0083] Feature library construction: The categorized feature data is organized into a feature library according to a preset format. The feature library should include information such as fault type, feature parameters, and fault location. The feature library should be updated and maintained regularly to ensure the timeliness and accuracy of the data.

[0084] Data storage: Use a database management system (such as MySQL, Oracle, etc.) to store and manage the feature library to ensure data security and reliability and prevent data loss or damage.

[0085] Feature library validation: The feature library is validated using an independent test dataset to evaluate its accuracy in fault matching and fault location. Based on the validation results, the feature library is optimized and adjusted to improve its performance and stability.

[0086] Feature library application: In actual operation, the features of real-time acquired operating signals are matched with the feature data in the feature library based on similarity. The fault type and location are determined according to the matching results, providing maintenance personnel with accurate fault information.

[0087] The effective feature set obtained in this test is compared one by one with the feature data in the fault feature library, and the similarity between the two is calculated. The feature data with the highest similarity is selected to determine the fault type and location corresponding to the feature data. This result is compared and verified with the accurate positioning result in step S302, and finally an accurate final fault positioning result is obtained.

[0088] Corresponding to the aforementioned embodiments of the diesel generator set balancing test method, this application also provides embodiments of the diesel generator set balancing test system.

[0089] Figure 5 This is a block diagram of a diesel generator set balancing test system according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a signal processing module 401, a multi-parameter fusion module for balanced state 402, and a balanced fault location module 403; wherein:

[0090] The operation signal processing module 401 is used to deploy various types of sensors in key parts of the diesel generator set, construct a full-dimensional operation signal acquisition network, collect the original operation signals of the diesel generator set under different operating conditions, and extract the time domain features and frequency domain features of the vibration signal from the original operation signal to obtain an effective feature set.

[0091] The equilibrium state multi-parameter fusion module 402 is used to perform single-parameter threshold judgment, frequency domain feature correlation judgment and weighted multi-parameter fusion calculation on the effective feature set respectively, to confirm the equilibrium state of the diesel generator set and output the equilibrium state data.

[0092] The balance fault location module 403 is used to retrieve a pre-built diesel generator set balance fault feature library. This feature library is constructed by collecting and analyzing the operating signal feature data of diesel generator sets with known imbalance faults. Based on the balance state data and vibration amplitude distribution, the core area and location of the fault are locked. The final fault location result is obtained by matching and verifying the diesel generator set balance fault feature library.

[0093] In this embodiment, the operation signal processing module 401 deploys various types of sensors at key parts of the diesel generator set to construct a full-dimensional operation signal acquisition network. It collects raw operation signals from the diesel generator set under different operating conditions and extracts the time-domain and frequency-domain features of the vibration signal from the raw operation signals to obtain an effective feature set. The balance state multi-parameter fusion module 402 performs single-parameter threshold judgment, frequency-domain feature correlation judgment, and weighted multi-parameter fusion calculation on the effective feature set to confirm the balance state of the diesel generator set and output balance state data. The balance fault location module 403 locks the core fault area and location based on the balance state data and vibration amplitude distribution. The final fault location result is obtained through matching and verification with the diesel generator set balance fault feature library. Through the above methods, the specific location of the unbalanced mass is determined, thereby improving fault location accuracy.

[0094] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0095] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0096] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the diesel generator set balancing test method as described above. Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities within a diesel generator set balancing test system provided in an embodiment of the present invention, except... Figure 6 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0097] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the diesel generator set balancing test method described above. The computer-readable storage medium can be an internal storage unit of any data processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing device, and can also be used to temporarily store data that has been output or will be output.

[0098] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0099] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method of balancing testing a diesel generator set, characterized by, Includes the following steps: Multiple types of sensors are deployed at key parts of the diesel generator set to construct a full-dimensional operation signal acquisition network. This network collects the original operation signals of the diesel generator set under different operating conditions and extracts the time-domain and frequency-domain features of the vibration signals from the original operation signals to obtain an effective feature set. The sensors include vibration sensors, speed sensors, torque sensors, and temperature sensors. The effective feature set is subjected to single-parameter threshold judgment, frequency domain feature correlation judgment, and weighted multi-parameter fusion calculation to confirm the balance state of the diesel generator set and output the balance state data; the specific process is as follows: Retrieve the preset threshold values ​​for various parameters, including vibration amplitude threshold, speed fluctuation threshold, torque stability threshold, and temperature threshold. Compare the vibration time-domain characteristic parameters, speed fluctuation range, torque stability data, and temperature data in the effective feature set with the corresponding thresholds to initially screen out abnormal parameters that exceed the thresholds and their corresponding monitoring locations. The fundamental frequency of the diesel generator set is calculated based on the speed signal in the effective feature set. The fundamental frequency component of the vibration signal frequency domain characteristics in the effective feature set is analyzed. It is determined whether the amplitude of the fundamental frequency component exceeds the set threshold and whether the phase is stable. Combined with the core characteristic of unbalanced vibration being dominated by the fundamental frequency, it is preliminarily determined whether there is a potential imbalance in the unit. The influence weights of each parameter on the equilibrium state judgment are set, and the feature values ​​of various parameters in the effective feature set are weighted and fused based on the set weights to obtain the fused decision value. The fusion decision value is compared with the preset balance state judgment threshold. If the fusion decision value exceeds the judgment threshold, the unit has an imbalance problem. If it does not exceed the threshold, the signal processing process needs to be re-checked and unbalanced faults need to be investigated. Balance state data is then output. The pre-built diesel generator set balance fault feature database is retrieved. This database is constructed by collecting and analyzing the operating signal feature data of diesel generator sets with known imbalance faults. Based on the balance state data and vibration amplitude distribution, the core area and location of the fault are identified. The final fault location result is obtained through matching and verification with the diesel generator set balance fault feature database. The specific process is as follows: By retrieving the abnormal parameter correlation information from the equilibrium state data and combining it with the vibration amplitude characteristics of each monitoring location in the effective feature set, the peak value and effective value amplitude data of the vibration signal at different monitoring locations are compared, and the monitoring location with the largest vibration amplitude is locked as the core area of ​​the imbalance fault. The circumferential angle and axial distance of the unbalanced mass are calculated to accurately locate the fault. The pre-built diesel generator set balance fault feature library is retrieved, and the effective feature set obtained from the test is matched with the feature data in the fault feature library for similarity. The fault type and location corresponding to the feature data with the highest matching degree are then selected.

2. The method of claim 1, wherein, Multiple types of sensors are deployed at key parts of the diesel generator set to construct a comprehensive operational signal acquisition network. This network collects raw operational signals from the diesel generator set under different operating conditions and extracts the time-domain and frequency-domain features of vibration signals from these raw signals to obtain an effective feature set. The sensors include vibration sensors, speed sensors, torque sensors, and temperature sensors. Sensors are deployed at key monitoring points of the diesel generator set to build a comprehensive operational signal acquisition network. Start the diesel generator set, switch it to no-load and rated load conditions in sequence, and use the constructed signal acquisition network to synchronously collect the original operating signals under each condition; the original operating signals include vibration signals, speed signals, torque signals and temperature signals. The time-domain and frequency-domain features of the vibration signal are extracted from the original operating signal to form an effective feature set.

3. The method of claim 2, wherein, In the step of deploying sensors at key monitoring points of diesel generator sets to construct a comprehensive operational signal acquisition network: Key monitoring areas include the bearing housings at both ends of the generator rotor, the bearing housings at both ends of the diesel engine crankshaft, the generator set frame, the generator output shaft, the coupling between the diesel engine and the generator, as well as the bearing housings and the generator set windings. The arrangement is as follows: vibration sensors are placed on the bearing housings at both ends of the generator rotor, the bearing housings at both ends of the diesel engine crankshaft, and the engine frame; speed sensors are placed on the generator output shaft; torque sensors are placed on the coupling; and temperature sensors are placed on each bearing housing and the unit windings.

4. The method of claim 2, wherein, In the step of extracting the time-domain and frequency-domain features of the vibration signal from the original operating signal to form an effective feature set: The original operating signal is processed by filtering and noise reduction, hierarchical amplification and normalization, detrending and feature extraction, in order to remove external environmental noise and sensor interference, unify the signal magnitude to eliminate dimensional differences, and eliminate the linear trend component of the signal.

5. The method of claim 1, wherein, In the step of calculating the circumferential angle and axial distance of the unbalanced mass to accurately locate the fault: Using the speed signal from the effective feature set as a reference, the phase angle of the vibration signal at the core area and surrounding monitoring locations is determined. Combined with the structural parameters of the diesel generator set, including rotor diameter, bearing spacing, and coupling size, a mapping relationship between the phase angle and the location of the unbalanced mass is established.

6. A diesel generator set balancing test system employing the diesel generator set balancing test method according to claim 1, characterized by, This includes a signal processing module, a multi-parameter fusion module for balanced states, and a balanced fault location module; among which: The operation signal processing module is used to deploy various types of sensors at key parts of the diesel generator set to construct a full-dimensional operation signal acquisition network, collect the original operation signals of the diesel generator set under different operating conditions, and extract the time-domain and frequency-domain features of the vibration signal from the original operation signals to obtain an effective feature set; wherein, the sensors include vibration sensors, speed sensors, torque sensors, and temperature sensors. The equilibrium state multi-parameter fusion module is used to perform single-parameter threshold judgment, frequency domain feature correlation judgment and weighted multi-parameter fusion calculation on the effective feature set respectively, to confirm the equilibrium state of the diesel generator set and output the equilibrium state data. The balance fault location module is used to retrieve a pre-built diesel generator set balance fault feature library. This feature library is constructed by collecting and analyzing the operating signal feature data of diesel generator sets with known imbalance faults. Based on the balance state data and vibration amplitude distribution, the core area and location of the fault are locked. The final fault location result is obtained by matching and verifying the diesel generator set balance fault feature library.

Images