A Triple-Weighted Approach for Equipment Condition Assessment and Prediction Based on Lubrication Vibration and Temperature

Abstract

This invention discloses a method for comprehensive equipment condition evaluation and prediction based on a triple-weighted approach of lubrication vibration and temperature. The method integrates data from different sources using fusion technology and collects lubrication, temperature, and vibration signals in real time using sensors. The processed data is stored in a database. Vibration signals are filtered and outliers are removed, and all signals are normalized. Key parameters are extracted from time-domain analysis, and the weights of each signal are determined using the analytic hierarchy process (AHP). The comprehensive evaluation model uses Z-score-standardized data and weights to calculate the overall equipment condition evaluation value, which is then compared with a preset value to assess the equipment condition. Finally, a long short-term memory (LSTM) network is used to train a prediction model based on historical data, and the model parameters are optimized through cross-validation to predict the future condition of the equipment.

Description

Technical Field

[0001] This invention relates to the field of equipment evaluation and prediction technology, and more specifically, to a method for comprehensive equipment condition evaluation and prediction based on a triple-weighted approach of lubrication vibration and temperature. Background Technology

[0002] With the rapid development of modern industry, the operating status of mechanical equipment has an increasingly significant impact on production efficiency and safety. Equipment failures can not only lead to production interruptions and increased maintenance costs, but may also cause serious safety accidents. Therefore, equipment condition monitoring and fault diagnosis technology has become an important research direction in the industrial field.

[0003] In recent years, with the rapid development of sensor technology, data processing technology and artificial intelligence, multi-parameter integrated monitoring methods have gradually become a research hotspot. Multi-parameter integrated monitoring can more comprehensively and accurately assess the operating status of equipment by simultaneously collecting and analyzing multiple key parameters. However, how to effectively integrate multiple parameters and conduct comprehensive evaluation remains a challenge.

[0004] However, it still has some drawbacks in actual use. For example, traditional equipment condition monitoring methods mainly rely on a single parameter. These methods have certain limitations in practical applications. Monitoring a single parameter often cannot fully reflect the overall condition of the equipment, which can easily lead to misjudgment or omission. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a method for comprehensive equipment condition evaluation and prediction based on a triple-weighted approach of lubrication vibration and temperature, in order to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] Step A1: Perform data fusion and unification processing on existing systems; for new systems, use sensors to collect lubrication signals, temperature signals, and vibration signals;

[0008] Step A2: Perform missing value and normalization processing on the collected lubrication signal, temperature signal and vibration signal;

[0009] Step A3: Extract key features from the processed lubrication signal, temperature signal, and vibration signal using time-domain analysis;

[0010] Step A4: Determine the weights of lubrication signals, temperature signals, and vibration signals by constructing a hierarchical model;

[0011] Step A5: Construct a comprehensive evaluation model using the monitoring data of lubrication status, vibration status, and temperature status;

[0012] Step A6: Based on the comprehensive evaluation results, predict the future state of the equipment.

[0013] Preferably, in step A1, data is obtained from different systems within the existing system; the extracted data is corrected and deduplicated, and the data cleaning process includes removing duplicate data, filling in missing values, and standardizing data formats; the data formats from different sources are standardized, and the standardized data is analyzed on a unified platform; this includes format conversion of structured data and parsing and extraction of unstructured data; the processed data is stored in a database; the database is a centralized data storage system used to store and manage data extracted from multiple heterogeneous data sources;

[0014] For new systems, lubrication signal acquisition uses a capacitive lubricating oil real-time online monitoring sensor, which obtains lubrication signals by measuring the capacitance value of the lubricating oil;

[0015] Temperature signals are acquired via a circuit board using a temperature sensor.

[0016] Vibration signals are acquired using an eddy current sensor and a high-precision signal converter, and are collected in real time via a DH5928W data acquisition unit.

[0017] Preferably, in step A2, for the vibration signal, anti-aliasing filtering, narrowband filtering, singularity removal, and missing value processing are required to improve the signal-to-noise ratio of the data; then the vibration signal, lubrication signal, and temperature signal are normalized to convert data of different dimensions into the same dimension.

[0018] Identify missing values ​​in the data and use interpolation to fill in the missing data.

[0019] Preferably, in step A3, the signal to be analyzed is selected from the processed lubrication, temperature and vibration signals, and then the basic statistical features, absolute fluctuation amplitude and root mean square value are calculated. The key features of the lubrication signal, temperature signal and vibration signal are extracted by calculating the basic statistical features, absolute fluctuation amplitude and root mean square value.

[0020] Key features extracted from lubrication signals include the viscosity, particle size, and moisture content of the lubricating oil; key features extracted from temperature signals include the rate of temperature change and fluctuation range; and key features extracted from vibration signals include the vibration spectrum, amplitude, and phase.

[0021] Preferably, in step A4, the problem is decomposed into three levels: the target level, the criterion level, and the solution level.

[0022] Among them, the target layer determines the importance assessment of the signal;

[0023] The criteria layer includes lubrication signals, temperature signals, and vibration signals;

[0024] If there are multiple solutions to compare in the solution layer, you can list the different solutions in this layer;

[0025] Next, the signals in the criterion layer are compared pairwise, and a judgment matrix is ​​constructed; the degree of comparison is determined using the 1-9 labeling method.

[0026] Among them, 1 indicates that both are equally important, 3 indicates that one is 60% important, 5 indicates that one is 70% important, 7 indicates that one is 80% important, and 9 indicates that one is 90% important; 2, 4, 6, and 8 are scores between the two above; 2 is between 1 and 3; 4 is between 3 and 5; 6 is between 5 and 7; and 8 is between 7 and 9.

[0027] The specific method for constructing the judgment matrix is ​​as follows:

[0028] Where A represents the judgment matrix, a ij This is represented as the importance score of signal i relative to signal j;

[0029] After constructing the judgment matrix, the sum of the i-th row in the judgment matrix is ​​calculated. The specific method for calculating the sum of the i-th row in the judgment matrix is ​​as follows:

[0030] Among them, B i This is expressed as determining the sum of the i-th row in a matrix, where a ij Let represent the importance score of signal i relative to signal j, and b represent the total number of signals;

[0031] Next, calculate the normalized judgment matrix. The specific method for calculating the normalized judgment matrix is ​​as follows:

[0032] Among them, C ij Represented as the normalized judgment matrix, a ij B represents the importance score of signal i relative to signal j. i This is expressed as determining the sum of the i-th row in the matrix;

[0033] The average value of each row of the normalized judgment matrix is ​​the weight of each factor. The specific method for calculating the weight is as follows:

[0034] Among them, w i Let C represent the weight value of the i-th signal. ij This is represented as the normalized judgment matrix, where b represents the total number of signals;

[0035] After calculating the weights, a consistency check is performed on the judgment matrix. The specific method for calculating the consistency ratio is as follows:

[0036] Where D represents the consistency ratio, E represents the consistency index, and F represents the random consistency index;

[0037] The random consistency index is obtained by looking up the matrix order in a table.

[0038] The specific calculation method for the consistency index is as follows:

[0039] Where E represents the consistency index, α max Let be the largest eigenvalue of the judgment matrix, and b be the total number of signals;

[0040] If the calculated consistency ratio is less than 0.1, the judgment matrix is ​​considered to have acceptable consistency; if the calculated consistency ratio is greater than 0.1, the judgment matrix is ​​considered to have unacceptable consistency and needs to be readjusted.

[0041] Preferably, in step A5, the state indicators are standardized. Since the monitoring data of lubrication state, vibration state and temperature state have different units and dimensions, direct weighted calculation may lead to distorted results. Therefore, it is necessary to perform Z-score standardization on each state indicator. The Z-score standardization method converts the values ​​of each state indicator into a standard normal distribution.

[0042] The standardized state index values ​​are multiplied by their respective weighting coefficients, and then summed using weighted averages to obtain the overall state evaluation value of the equipment. The specific calculation method for the overall state evaluation value is as follows:

[0043] Q = w1G + w2H + w3K, where Q represents the overall state evaluation value, G represents the standardized lubrication state, H represents the standardized vibration state, K represents the standardized temperature state, w1 represents the weight of the lubrication state, w2 represents the weight of the vibration state, and w3 represents the weight of the temperature state.

[0044] Preferably, in step A6, a prediction model is constructed using a long short-term memory network method; during model training, parameters need to be continuously adjusted to improve prediction accuracy; the model's performance is evaluated using methods such as cross-validation, and metrics such as accuracy and recall are calculated; the model is optimized based on the evaluation results, adjusting algorithm parameters and changing the model structure to improve prediction accuracy and stability; the future state of the equipment is predicted based on the output of the prediction model; and corresponding maintenance plans and operation schemes are formulated in conjunction with the equipment's operating status and maintenance strategies to ensure that the equipment operates in optimal condition.

[0045] The technical effects and advantages of this invention are as follows:

[0046] This invention first acquires and merges data from different systems, using sensors to collect lubrication, temperature, and vibration signals. After cleaning, deduplication, and standardization, these signals are stored in a database. Next, missing value processing and normalization are performed on the signals, extracting key features such as viscosity, temperature change rate, and vibration spectrum. Then, the weights of each signal are determined using the analytic hierarchy process (AHP), and a comprehensive evaluation model is constructed. The overall equipment condition evaluation value is calculated using data standardized by Z-score. Finally, a predictive model is built based on a long short-term memory network (LSTM). After evaluating the model's performance, the future condition of the equipment is predicted, and a maintenance plan is formulated. By monitoring these three types of parameters and employing weighted processing and time-series analysis, this method can achieve a comprehensive evaluation of equipment condition, improve equipment operating efficiency and safety, reduce misjudgments, and predict future development. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0049] Please see Figure 1 As shown, this invention provides a method for comprehensive equipment condition evaluation and prediction based on a triple-weighted approach of lubrication vibration and temperature. The method is as follows:

[0050] Step A1: Perform data fusion and unification processing on existing systems; for new systems, use sensors to collect lubrication signals, temperature signals, and vibration signals;

[0051] In step A1, data is obtained from different systems within the existing system; the extracted data is corrected and deduplicated, and the data cleaning process includes removing duplicate data, filling in missing values, and standardizing data formats; the data formats from different sources are standardized, and the standardized data is analyzed on a unified platform; this includes format conversion of structured data and parsing and extraction of unstructured data; the processed data is stored in a database; the database is a centralized data storage system used to store and manage data extracted from multiple heterogeneous data sources;

[0052] For new systems, lubrication signal acquisition uses a capacitive lubricating oil real-time online monitoring sensor, which obtains lubrication signals by measuring the capacitance value of the lubricating oil;

[0053] Temperature signals are acquired via a circuit board using a temperature sensor.

[0054] Vibration signals are acquired using an eddy current sensor and a high-precision signal converter, and are collected in real time via a DH5928W data acquisition unit.

[0055] Step A2: Perform missing value and normalization processing on the collected lubrication signal, temperature signal and vibration signal;

[0056] In step A2, for the vibration signal, anti-aliasing filtering, narrowband filtering, singularity removal, and missing value processing are required to improve the signal-to-noise ratio of the data; then the vibration signal, lubrication signal, and temperature signal are normalized to convert data of different dimensions into the same dimension.

[0057] Identify missing values ​​in the data and use interpolation to fill in the missing data.

[0058] Step A3: Extract key features from the processed lubrication signal, temperature signal, and vibration signal using time-domain analysis;

[0059] In step A3, the signal to be analyzed is selected from the processed lubrication, temperature and vibration signals, and then the basic statistical characteristics, absolute fluctuation amplitude and root mean square value are calculated. The key features of the lubrication signal, temperature signal and vibration signal are extracted by calculating the basic statistical characteristics, absolute fluctuation amplitude and root mean square value.

[0060] Key features extracted from lubrication signals include the viscosity, particle size, and moisture content of the lubricating oil; key features extracted from temperature signals include the rate of temperature change and fluctuation range; key features extracted from vibration signals include the vibration spectrum, amplitude, and phase.

[0061] For shell vibration, narrowband feature extraction is used according to the type of the component being measured, and an alarm threshold for the vibration energy of each narrowband is defined.

[0062] For relative vibration, feature extraction is performed using the characteristic frequency vector and precession component, and an alarm threshold is defined for each feature value; for shaft center position, eccentricity and azimuth are used as feature parameters, and their alarm thresholds are defined.

[0063] Step A4: Determine the weights of lubrication signals, temperature signals, and vibration signals by constructing a hierarchical model;

[0064] In step A4, the problem is decomposed into three levels: the goal level, the criterion level, and the solution level.

[0065] Among them, the target layer determines the importance assessment of the signal;

[0066] The criteria layer includes lubrication signals, temperature signals, and vibration signals;

[0067] If there are multiple solutions to compare in the solution layer, you can list the different solutions in this layer;

[0068] Next, the signals in the criterion layer are compared pairwise, and a judgment matrix is ​​constructed; the degree of comparison is determined using the 1-9 labeling method.

[0069] Among them, 1 indicates that both are equally important, 3 indicates that one is 60% important, 5 indicates that one is 70% important, 7 indicates that one is 80% important, and 9 indicates that one is 90% important; 2, 4, 6, and 8 are scores between the two above; 2 is between 1 and 3; 4 is between 3 and 5; 6 is between 5 and 7; and 8 is between 7 and 9.

[0070] The specific method for constructing the judgment matrix is ​​as follows:

[0071] Where A represents the judgment matrix, a ij This is represented as the importance score of signal i relative to signal j;

[0072] After constructing the judgment matrix, the sum of the i-th row in the judgment matrix is ​​calculated. The specific method for calculating the sum of the i-th row in the judgment matrix is ​​as follows:

[0073] Among them, B i This is expressed as determining the sum of the i-th row in a matrix, where a ij Let represent the importance score of signal i relative to signal j, and b represent the total number of signals;

[0074] Next, calculate the normalized judgment matrix. The specific method for calculating the normalized judgment matrix is ​​as follows:

[0075] Among them, C ij Represented as the normalized judgment matrix, a ij B represents the importance score of signal i relative to signal j. i This is expressed as determining the sum of the i-th row in the matrix;

[0076] The average value of each row of the normalized judgment matrix is ​​the weight of each factor. The specific method for calculating the weight is as follows:

[0077] Among them, w i Let C represent the weight value of the i-th signal. ijThis is represented as the normalized judgment matrix, where b represents the total number of signals;

[0078] After calculating the weights, a consistency check is performed on the judgment matrix. The specific method for calculating the consistency ratio is as follows:

[0079] Where D represents the consistency ratio, E represents the consistency index, and F represents the random consistency index;

[0080] The random consistency index is obtained by looking up the matrix order in a table.

[0081] The specific calculation method for the consistency index is as follows:

[0082] Where E represents the consistency index, α max Let be the largest eigenvalue of the judgment matrix, and b be the total number of signals;

[0083] If the calculated consistency ratio is less than 0.1, the judgment matrix is ​​considered to have acceptable consistency; if the calculated consistency ratio is greater than 0.1, the judgment matrix is ​​considered to have unacceptable consistency and needs to be readjusted.

[0084] Step A5: Construct a comprehensive evaluation model using the monitoring data of lubrication status, vibration status, and temperature status;

[0085] In step A5, the state indicators are standardized. Since the monitoring data of lubrication state, vibration state and temperature state have different units and dimensions, direct weighted calculation may lead to distorted results. Therefore, it is necessary to perform Z-score standardization on each state indicator. The Z-score standardization method converts the values ​​of each state indicator into a standard normal distribution.

[0086] The standardized state index values ​​are multiplied by their respective weighting coefficients, and then summed using weighted averages to obtain the overall state evaluation value of the equipment. The specific calculation method for the overall state evaluation value is as follows:

[0087] Q = w1G + w2H + w3K, where Q represents the overall state evaluation value, G represents the standardized lubrication state, H represents the standardized vibration state, K represents the standardized temperature state, w1 represents the weight of the lubrication state, w2 represents the weight of the vibration state, and w3 represents the weight of the temperature state.

[0088] The calculated overall status evaluation value is compared with the preset overall status evaluation threshold. If the calculated overall status evaluation value is greater than the preset overall status evaluation threshold, it indicates that the operating status of the equipment is gradually deteriorating; if the calculated overall status evaluation value is less than the preset overall status evaluation threshold, it indicates that the operating status of the equipment is normal, and monitoring continues.

[0089] The specific calculation method for the preset overall state evaluation threshold is as follows:

[0090] Where Q0 represents the preset overall state evaluation threshold, and n represents the calculated historical overall state evaluation value. To reduce the error of the calculated value, the value of n is n≥5; G q H represents the standardized lubrication state of the historical data at the q-th time. q K represents the standardized vibration state of the historical data at the q-th time. q This represents the standardized temperature state of the historical data at the q-th time.

[0091] The comprehensive evaluation model is validated and optimized; its accuracy and reliability are verified by comparing it with historical data in practical applications; if deviations are found in the model, its performance is further improved by adjusting the weighting coefficients or optimizing the model structure.

[0092] The lubrication condition is assessed by analyzing parameters such as viscosity, moisture, impurities, acid value, and base value of the lubricating oil. Changes in these parameters can directly reflect the performance of the lubricating oil and the operating condition of the equipment. For example, changes in viscosity can reflect the degree of oxidation and contamination of the lubricating oil, an increase in moisture and impurities can indicate that the lubricating oil is contaminated, and changes in acid value and base value can reflect the anti-oxidation and anti-corrosion properties of the lubricating oil.

[0093] By analyzing the state changes of preset characteristic values ​​of mechanical vibration, the overall operating status level of the equipment and the possible types, severity, and development trends of faults can be evaluated. The definition of characteristic values ​​depends on the type of equipment being measured and the type of signal. For mechanical vibration, the amplitude of different measurement methods reflects the different types of force, and force is the main cause of vibration. The amplitude changes of characteristic components are related to the type and degree of fault and are the main source of information for fault diagnosis. The evaluation parameters include absolute value, rate of change, and distribution.

[0094] Temperature monitoring is a crucial component of equipment condition assessment, effectively reflecting the equipment's operational status. In particular, temperature changes in critical components such as bearings, motors, gearboxes, and hydraulic systems can reveal the equipment's operational condition and potential faults. Evaluation parameters include absolute temperature, temperature rise, rate of temperature change, and temperature distribution. Monitoring absolute temperature reflects the equipment's heat load; excessively high or low absolute temperatures may indicate a fault. Monitoring temperature rise reflects the equipment's heat dissipation; excessively high or low temperature rises may indicate a fault. Monitoring the rate of temperature change reflects the equipment's thermal stability; excessively high or low rates of temperature change indicate a fault. Monitoring temperature distribution reflects the equipment's thermal balance; uneven temperature distribution may indicate a fault.

[0095] Step A6: Based on the comprehensive evaluation results, predict the future state of the equipment.

[0096] In step A6, a prediction model is constructed using a long short-term memory network method. During model training, parameters need to be continuously adjusted to improve prediction accuracy. The model's performance is evaluated using methods such as cross-validation, and metrics such as accuracy and recall are calculated. Based on the evaluation results, the model is optimized by adjusting algorithm parameters and changing the model structure to improve prediction accuracy and stability. The future state of the equipment is predicted based on the output of the prediction model. Combined with the equipment's operating status and maintenance strategies, corresponding maintenance plans and operation schemes are formulated to ensure the equipment operates in optimal condition.

[0097] The specific method for training the prediction model is as follows:

[0098] Step A1: Collect historical power grid equipment data, including the equipment's lubrication status, vibration status, and temperature status;

[0099] Step A2: Clean the collected data, remove outliers and missing values, and perform standardization or normalization; divide the data into training set, validation set and test set;

[0100] Step A3: Construct a Long Short-Term Memory Network to build a prediction model, which includes the settings of the input layer, hidden layer, and output layer;

[0101] Step A4: Iterate through the training data, perform forward propagation, calculate loss, backpropagation, and update parameters;

[0102] Step A5: Select the loss function mean squared error and the coefficient of determination to evaluate the model's predictive performance, and select an optimizer to update the model's weights;

[0103] Step A6: Calculate the predicted overall state evaluation value using the trained model, and compare the predicted overall state evaluation value with the overall state evaluation value;

[0104] If the calculated predicted overall state evaluation value is equal to the overall state evaluation value, then there is no need to continue iterative training; if the calculated predicted overall state evaluation value is not equal to the overall state evaluation value, then iterative training continues until the predicted overall state evaluation value is equal to the overall state evaluation value.

[0105] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for comprehensive equipment condition evaluation and prediction based on a triple-weighted approach of lubrication vibration and temperature, characterized in that, include: Step A1: Perform data fusion and unification processing on the existing system based on data from different systems; For newly installed systems, sensors are used to collect lubrication signals, temperature signals, and vibration signals. Step A2: Perform missing value and normalization processing on the collected lubrication signal, temperature signal and vibration signal; Step A3: Extract key features from the processed lubrication signal, temperature signal, and vibration signal using time-domain analysis; In step A3, the signal to be analyzed is selected from the processed lubrication, temperature and vibration signals, and then the basic statistical characteristics, absolute fluctuation amplitude and root mean square value are calculated. The key features of the lubrication signal, temperature signal and vibration signal are extracted by calculating the basic statistical characteristics, absolute fluctuation amplitude and root mean square value. Key features extracted from lubrication signals include the viscosity, particle size, and moisture content of the lubricating oil; key features extracted from temperature signals include the rate of temperature change and fluctuation range; key features extracted from vibration signals include the vibration spectrum, amplitude, and phase. Step A4: Determine the weights of lubrication signals, temperature signals, and vibration signals by constructing a hierarchical model; In step A4, the problem is decomposed into three levels: the target level, the criterion level, and the solution level; the signals in the criterion level are compared pairwise, and a judgment matrix is ​​constructed; the degree of comparison is determined using the 1-9 labeling method. The specific method for constructing the judgment matrix is ​​as follows: Where A represents the judgment matrix. This is represented as the importance score of signal i relative to signal j; After constructing the judgment matrix, the sum of the i-th row in the judgment matrix is ​​calculated. The specific method for calculating the sum of the i-th row in the judgment matrix is ​​as follows: ,in, This is expressed as determining the sum of the i-th row in a matrix. Let represent the importance score of signal i relative to signal j, and b represent the total number of signals; The normalized judgment matrix is ​​calculated as follows: ,in, Represented as the normalized judgment matrix, This is represented as the importance score of signal i relative to signal j. This is expressed as determining the sum of the i-th row in the matrix; The average value of each row of the normalized judgment matrix is ​​the weight of each factor. The specific method for calculating the weight is as follows: ,in, This is represented as the weight value of the i-th signal. This is represented as the normalized judgment matrix, where b represents the total number of signals; After calculating the weights, a consistency check is performed on the judgment matrix. The specific method for calculating the consistency ratio is as follows: Where D represents the consistency ratio, E represents the consistency index, and F represents the random consistency index; Step A5: Construct a comprehensive evaluation model using the monitoring data of lubrication status, vibration status, and temperature status; In step A5, each state index is standardized; each state index is then standardized using Z-score, which converts the values ​​of each state index into a standard normal distribution. The specific method for calculating the overall condition evaluation value is as follows: Where Q represents the overall condition evaluation value, G represents the standardized lubrication condition, H represents the standardized vibration condition, and K represents the standardized temperature condition. The weights are represented as those for the lubrication state. The weights are represented as vibrational states. The weights are represented as temperature states; The calculated overall status evaluation value is compared with the preset overall status evaluation threshold. If the calculated overall status evaluation value is greater than the preset overall status evaluation threshold, it indicates that the operating status of the equipment is gradually deteriorating; if the calculated overall status evaluation value is less than the preset overall status evaluation threshold, it indicates that the operating status of the equipment is normal, and monitoring continues. Step A6: Based on the comprehensive evaluation results, predict the future state of the equipment; A prediction model is constructed using a long short-term memory network method; parameters need to be continuously adjusted during model training; the model's performance is evaluated using cross-validation, and accuracy and recall metrics are calculated; the model is optimized based on the evaluation results, adjusting algorithm parameters and changing the model structure; and the future state of the device is predicted based on the output of the prediction model.

2. The method for comprehensive equipment condition evaluation and prediction based on a triple-weighted approach of lubrication vibration and temperature as described in claim 1, characterized in that: In step A1, data is obtained from different systems within the existing system; the extracted data is corrected and deduplicated, and the data cleaning process includes removing duplicate data, filling in missing values, and standardizing data formats; the data formats from different sources are standardized, and the standardized data is analyzed on a unified platform; this includes format conversion of structured data and parsing and extracting unstructured data; the processed data is then stored in a database. A database is a centralized data storage system used to store and manage data extracted from multiple heterogeneous data sources; For new systems, lubrication signal acquisition uses a capacitive lubricating oil real-time online monitoring sensor, which obtains lubrication signals by measuring the capacitance value of the lubricating oil; Temperature signals are acquired via a circuit board using a temperature sensor. Vibration signals are acquired using an eddy current sensor and a high-precision signal converter, and are collected in real time via a DH5928W data acquisition unit.

3. The method for comprehensive equipment condition evaluation and prediction based on a triple-weighted approach of lubrication vibration and temperature as described in claim 1, characterized in that: In step A2, for the vibration signal, anti-aliasing filtering, narrowband filtering, singularity removal, and missing value processing are required to improve the signal-to-noise ratio of the data; then the vibration signal, lubrication signal, and temperature signal are normalized to convert data of different dimensions into the same dimension. Identify missing values ​​in the data and use interpolation to fill in the missing data.

Images