Hydroelectric generating set guide bearing performance evaluation method, device, equipment and medium

Abstract

The invention relates to the technical field of hydropower station operation and maintenance, and discloses a hydroelectric generating set guide bearing performance evaluation method and device, equipment and a medium. The operation time sequence of the unit is segmented, time sequences of different operation time periods are determined, and the operation time periods comprise the stable operation time period and the transient operation time period; extracting state features of the time sequences in different operation periods to determine the operation state of the unit; and determining a performance evaluation result of the guide bearing based on the unit operation state. According to the method, the unit operation states including steady-state operation and transient-state operation can be identified in the real-time monitoring data, so that the performance of the guide bearing is evaluated based on the monitoring data in the steady-state operation state, manual intervention is not needed in the process, the monitoring precision of the states of key equipment such as the unit guide bearing is improved, and the working efficiency is improved. The downtime caused by equipment faults is reduced, the operation reliability of the hydropower station is enhanced, and the operation monitoring efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower station operation and maintenance, and in particular to a method, device, equipment and medium for evaluating the performance of a guide bearing of a hydropower unit. Background Art

[0002] With the large-scale integration of renewable energy into the grid, the stability and reliability of the power grid are facing challenges. The role of hydropower units has shifted from power generation to frequency regulation and grid support, resulting in increasingly stringent requirements for the performance of guide bearings, which are key rotating support components in hydropower units. As core components supporting the rotating parts of hydropower generator units, performance degradation of guide bearings can lead to faults such as increased vibration, abnormal temperature rise, and even unit shutdown. Therefore, assessing the performance degradation of guide bearings in hydropower units is a crucial step in ensuring the safe and stable operation of the units. Currently, guide bearing performance is assessed by collecting variable speed test data from stability tests or operational monitoring data under stable operating conditions, using limit value assessment methods and expert knowledge bases for evaluation and early warning. This method typically performs post-analysis of offline data, which is difficult to meet the application scenario requirements of guide bearing performance assessment. Summary of the Invention

[0003] In view of this, the present invention provides a method, device, equipment and medium for evaluating the performance of a guide bearing of a hydropower unit to solve the problem of low adaptability of current guide bearing performance evaluation methods.

[0004] In a first aspect, the present invention provides a method for evaluating the performance of a guide bearing of a machine set, the method comprising:

[0005] Obtain the time series of unit operation;

[0006] Segmenting the time series of the unit operation to determine time series of different operation periods, wherein the operation periods include stable operation periods and transient operation periods;

[0007] Extracting state features of the time series of the different operating time periods to determine the operating state of the unit;

[0008] The performance evaluation results of the guide bearing are determined based on the monitoring data during the steady-state operation period.

[0009] In some optional implementations, segmenting the time series of the unit operation to determine the time series of different operation periods includes:

[0010] Preprocessing the time series to obtain a preprocessed time series;

[0011] The change points in the time series are detected, and the time series are segmented based on the change points to determine the time series of different operating time periods, wherein the change points are used to represent the boundaries of different operating time periods.

[0012] In some optional implementations, detecting a change point in the time series includes:

[0013] An objective function is determined based on the penalty factor, and a change point in the time series is determined based on the objective function.

[0014] In some optional implementations, the objective function is determined according to the following formula:

[0015]

[0016] Where G(n) represents the objective function. Suppose there are m change points, and the position of the change point is represented by τ=(τ 1, τ2,…,τ m ) represents, β represents the penalty factor;

[0017] The penalty factor β is determined according to the following formula:

[0018] β=(0.25n) (1-S) 2log(n)

[0019] Wherein, n represents the length of the time series, and S represents the sensitivity parameter.

[0020] In some optional implementations, extracting the state features of the time series of the different operating time periods to determine the unit operating state includes:

[0021] Extract features from time series in different operating periods to obtain features corresponding to the time series in each operating period;

[0022] Clustering processing is performed on the features, and the unit operation status is determined based on the result of the clustering processing, where the unit operation status includes an identification result of a stable operation period.

[0023] In some optional implementations, extracting features from time series of different operating periods to obtain features corresponding to the time series of each operating period includes:

[0024] The mean and standard deviation of the time series in different operating periods are calculated, and the features corresponding to the time series in each operating period are generated based on the mean and standard deviation.

[0025] In some optional embodiments, determining the performance evaluation result of the guide bearing based on the monitoring data during the steady-state operation period includes:

[0026] Performing data screening based on the operating status of the unit to obtain monitoring data marked as steady-state operation;

[0027] Calculating a root mean square value of the monitoring data, and calculating, based on the root mean square value, an average value and a standard deviation of vibration in each working cycle of the unit when in a stable operating state;

[0028] The guide bearing is subjected to a performance evaluation based on the average value and the standard deviation to obtain a performance evaluation result of the guide bearing.

[0029] In a second aspect, the present invention provides a device for evaluating the performance of a guide bearing of a machine set, the device comprising:

[0030] Data acquisition module, used to obtain the time series of unit operation;

[0031] A time series determination module is used to segment the time series of the unit operation and determine the time series of different operation periods, wherein the operation periods include stable operation periods and transient operation periods;

[0032] A state determination module is used to extract the state characteristics of the time series of different operating time periods to determine the operating state of the unit;

[0033] The performance evaluation module is used to determine the performance evaluation result of the guide bearing based on the monitoring data during the steady-state operation period.

[0034] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the unit guide bearing performance evaluation method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the unit guide bearing performance evaluation method of the first aspect or any corresponding embodiment thereof.

[0036] The method for evaluating the performance of a generator set guide bearing provided in this embodiment includes obtaining a time series of generator set operation; segmenting the time series to determine time series for different operating periods, wherein the operating periods include stable operating periods and transient operating periods; extracting state characteristics of the time series for different operating periods to determine the generator set operating status; and determining a performance evaluation result for the guide bearing based on the generator set operating status. This method can identify the generator set operating status, including steady-state operation and transient operation, in implementation data, thereby evaluating the performance of the guide bearing based on monitoring data under steady-state operation. This process requires no human intervention, improves the monitoring accuracy of the status of key equipment such as the generator set guide bearing, reduces downtime caused by equipment failure, enhances the operational reliability of the hydropower station, and improves the efficiency of operation monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 1 is a flow chart of a method for evaluating the performance of a guide bearing of a hydropower unit according to an embodiment of the present invention;

[0039] Figure 2 is a structural block diagram of a device for evaluating the performance of a guide bearing of a hydropower unit according to an embodiment of the present invention;

[0040] Figure 3 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0042] The grid stability challenges caused by the large-scale integration of renewable energy have prompted the transformation of the role of hydropower units from traditional power generation to frequency regulation and grid support, which in turn has placed higher requirements on the performance of guide bearings. Their performance degradation assessment has become a core link in ensuring the safe operation of the units. Guide bearings are the key radial support structure of the rotating components of hydropower generator units. Once performance degradation occurs, it will directly lead to chain failures such as increased vibration, abnormal temperature rise, and even unplanned shutdown of the unit. The difference between stable and transient states during unit operation has a significant impact on guide bearing degradation assessment and maintenance strategies. Transient processes (such as start-up and shutdown, power regulation) will accelerate bearing fatigue and performance degradation, while stable operation is more conducive to capturing reliable state characteristics due to the smooth power output. Therefore, real-time evaluation of guide bearing vibration data under stable operating conditions can not only identify potential faults in advance to support predictive maintenance, but also improve operational reliability and energy efficiency through long-term performance trend analysis. However, current assessment methods primarily rely on variable speed data from stability tests or stable operating condition monitoring data at specific points (e.g., new unit commissioning or after maintenance), and perform manual offline judgments. This model, due to the discrete nature of the tests, cannot provide online early warning of faults. Furthermore, due to the limitations of manual rules, it struggles to meet the requirements for quantifying real-time performance degradation. Therefore, the present invention provides a method for evaluating the performance of guide bearings in turbine units.

[0043] According to an embodiment of the present invention, an embodiment of a method for evaluating the performance of a guide bearing of a machine unit is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] In this embodiment, a method for evaluating the performance of a guide bearing of a unit is provided. Figure 1 FIG. 1 is a flow chart of a method for evaluating the performance of a guide bearing of a machine set according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0045] Step S101: Acquire the time series of the unit operation.

[0046] Collecting time series data from hydropower stations during the operation of hydropower units involves using specific data acquisition equipment or systems to continuously record relevant data during the operation of the hydropower units at regular intervals. This data is then arranged in chronological order to form time series data for the units' operation. This time series includes power output data, as well as other relevant parameters such as unit speed, guide vane opening, and guide bearing vibration.

[0047] Step S102 , dividing the time series of the unit operation to determine the time series of different operation periods.

[0048] The operating period includes a stable operating period and a transient operating period. After collecting the time series of the unit operation, the time series data can be preprocessed. The preprocessing includes smoothing the collected power output time series data and removing noise.

[0049] Based on the power output time series, the key time nodes for switching the unit operating conditions are identified, so that the continuous operation data can be divided into several independent time periods, and different operating periods can be clearly distinguished, including stable operation periods and transient operation periods, so as to determine the number of stable operation periods and transient operation periods in each working cycle.

[0050] Specifically, based on the characteristics of parameter changes during unit operation, such as whether the parameters remain relatively stable within a certain range or whether there are significant rapid fluctuations, the entire time series is divided into different operating periods, thereby clearly distinguishing the time series corresponding to stable operation periods and the time series corresponding to transient operation periods. Stable operation periods are periods of relatively stable operation, with relatively small changes in unit parameters. Transient operation periods are periods of rapid changes in unit parameters and a transitional operating state.

[0051] Step S103 : extracting the state features of the time series of different operating periods to determine the operating state of the unit.

[0052] For the time series of each defined operating period, feature extraction is performed on each time series, including the statistical features of the power data, which include the mean value and standard deviation within the period. Features reflecting operational smoothness, such as the mean value and standard deviation, are extracted from the time series of stable operating periods. Features reflecting the severity of operational changes, such as the rate of change and peak value, are extracted from the time series of transient operating periods. By analyzing these state features, the specific operating status of the unit in different operating periods can be accurately determined.

[0053] Specifically, when analyzing state characteristics, a density clustering algorithm can be used to cluster the state characteristics, thereby classifying the time period as a stable operating state or a transient operating state. Different operating states can be characterized by defining characteristics, and only when the defined characteristics are met can the time series be marked as the corresponding operating state.

[0054] Step S104: determining a performance evaluation result of the guide bearing based on the monitoring data during the steady-state operation period.

[0055] Before evaluating the guide bearing's performance, we first screened the data corresponding to the steady-state operating period identified earlier. Transient data often contains a large amount of impact noise and transient response unrelated to the bearing's actual condition. If these are included in the analysis, the determination of interference degradation trends will be affected. Therefore, in this step, the guide bearing's performance is evaluated only based on the steady-state data.

[0056] Based on step S103, the operating state of each operating period has been calibrated, and the steady-state operating period within each operating cycle is screened out. Based on the data of the screened steady-state operating period, for each stable working cycle, an indicator that can reflect the vibration energy level, such as the root mean square value (RMS) of the vibration acceleration, is calculated. The root mean square value is an integral representation of the energy intensity of the vibration acceleration signal in the time domain, which can reflect the overall level of vibration energy during bearing operation and is directly related to the mechanical forces inside the bearing (such as oil film pressure fluctuations between the journal and the bearing shell, metal contact friction, and impact caused by loose components). Compared with indicators such as peak or kurtosis, RMS has a higher monitoring sensitivity for early, slow-changing wear degradation and can more stably capture the effects of small energy accumulation.

[0057] Dynamic statistical analysis is performed on indicators reflecting vibration energy levels over multiple working cycles. Specifically, a dynamic statistical model can be constructed to analyze the evolution trend and fluctuation range of indicators reflecting vibration energy levels, thereby determining the performance changes of the guide bearings during the operation of the unit, including the performance degradation trend.

[0058] Taking the root mean square value as an example, the root mean square value of the vibration in each working cycle under the stable operation state of the unit is statistically analyzed, and then the changes in the mean value and standard deviation are determined based on the root mean square value, so as to evaluate the performance of the guide bearing.

[0059] The method for evaluating the performance of a generator set guide bearing provided in this embodiment includes obtaining a time series of generator set operation; segmenting the time series to determine time series for different operating periods, wherein the operating periods include stable operating periods and transient operating periods; extracting state characteristics of the time series for different operating periods to determine the generator set operating status; and determining a performance evaluation result for the guide bearing based on the generator set operating status. This method can identify the generator set operating status, including steady-state operation and transient operation, in implementation data, thereby evaluating the performance of the guide bearing based on monitoring data under steady-state operation. This process requires no human intervention, improves the monitoring accuracy of the status of key equipment such as the generator set guide bearing, reduces downtime caused by equipment failure, enhances the operational reliability of the hydropower station, and improves the efficiency of operation monitoring.

[0060] In this embodiment, a method for evaluating the performance of a guide bearing of a machine set is provided, and the method comprises the following steps:

[0061] Step S201, obtain the time series of the unit operation. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0062] Step S202 , dividing the time series of the unit operation to determine the time series of different operation periods.

[0063] Specifically, step S202 includes:

[0064] Step S2021: preprocess the time series to obtain a preprocessed time series.

[0065] Step S2022 , detecting the change points in the time series, and segmenting the time series based on the change points to determine the time series of different operating periods.

[0066] The collected power output time series data is preprocessed. First, a sliding average or low-pass filtering technique is used for smoothing and denoising, effectively filtering out high-frequency random noise introduced by sensor drift and electromagnetic interference, while retaining the low-frequency trend component that represents the actual load change of the unit. Based on the start-stop logic signal of the thrust bearing pump (the pump start signifies the unit is put into operation, and the stop sign indicates the unit is out of operation), the complete working cycle interval is accurately extracted, and non-power generation state data such as cold standby and phase adjustment mode are strictly excluded to ensure that the analyzed data comes from the effective power generation process. Finally, for each independent working cycle, the statistical characteristics of its power data are calculated separately, including the mean and standard deviation of all power values ​​in the cycle. Among them, the mean value can reflect the steady-state load level, and the standard deviation can reflect the stability of operation. The two together constitute the core feature vector that describes the operating conditions of the unit, providing standardized input for subsequent operating state segmentation and degradation assessment.

[0067] Detect the change points in the unit power output time series. The change points are used to represent the boundaries of different operating periods. The generator active power output time series is recorded as: y = (y1, y2, ..., y n ), assuming that there are m change points, their respective positions are represented by τ=(τ1,τ2,…,τ m ) indicates that each change point is an integer between 1 and (n-1), such that 0 = τ0﹤τ1﹤τ2﹤…﹤τ m ﹤τ m+1 =n, and the order of the change points satisfies τ if and only if i﹤j i ﹤τ j Therefore, m change points can divide the power output time series y into m+1 segments, where the jth segment is expressed as

[0068] In some optional implementations, detecting a change point in the time series includes determining an objective function based on a penalty factor, and determining the change point in the time series based on the objective function.

[0069] Change point detection is formulated as an optimization problem for a sequence segmentation τ, where the segmentation τ is given by a function.

[0070]

[0071] Where C represents the cost function of a certain segment, β represents the penalty factor, and m represents the number of change points.

[0072] The objective function G(n) is:

[0073]

[0074] Where G(n) represents the objective function. Suppose there are m change points, and the position of the change point is represented by τ=(τ 1,τ2,…,τ m )express.

[0075] Select L2 norm as the cost function:

[0076]

[0077] in, express The mean of the series.

[0078] The penalty factor β is determined by the sensitivity parameter S and the length n of the power output time series. The penalty factor β is determined according to the following formula:

[0079] β=(0.25n) (1-S) 2log(n)

[0080] Wherein, n represents the length of the time series, S represents the sensitivity parameter, and the sensitivity parameter can be set to 1, that is, β = 2log(n).

[0081] Step S203 : extracting the state features of the time series of different operating periods to determine the operating state of the unit.

[0082] Specifically, step S203 includes:

[0083] Step S2031 , extracting features from the time series of different operating time periods to obtain features corresponding to the time series of each operating time period.

[0084] Furthermore, step S2031 includes: calculating the mean and standard deviation of the time series of different operating time periods, and generating features corresponding to the time series of each operating time period based on the mean and standard deviation.

[0085] Select each non-overlapping time window T s The mean (μ) and standard deviation (σ) of are used as input features. The sampling frequency is f s , the time window is T, then each time window includes x=f s T data points. Features f of the i-th time window i Defined as:

[0086]

[0087] If the final data window contains less than x data points, it is excluded from the consideration range. The clustering features of each time window are combined into features F = [f1, f2, ...], which are used as the input parameters for subsequent clustering. For example, take f s =0.1Hz, T s =60s, each time window includes 6 data points.

[0088] Step S2032: cluster the features and determine the unit operation status based on the clustering results.

[0089] The unit operating status includes the identification results of stable operation periods. The adaptive DBSCAN algorithm is used to identify stable and transient operation processes. DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based clustering algorithm that can identify clusters of arbitrary shapes and effectively handle noisy data. The DBSCAN algorithm is an unsupervised machine learning clustering algorithm.

[0090] Given that the changes in the two key parameters will significantly affect the clustering results of the DBSCAN algorithm, and the frequent switching of unit operating conditions will cause the fixed MinPts and Eps parameters to be unable to effectively cluster all working periods, it is impractical to select more appropriate parameters through manual combination iteration. Therefore, given Eps = [Eps1, Eps2,…, Eps k ] set, the number of clusters based on DBSCAN is fine-tuned by Eps, thus proposing an adaptive DBSCAN algorithm that can adapt to the identification of variable operating conditions of the unit. The present invention takes the Eps range as [0.1, 10] with an interval of 0.01.

[0091] In this embodiment, a power output data time series lasting 3 minutes or longer is classified as a stable operation process, and thus MinPts=3.

[0092] The process is as follows:

[0093] (1) Find the number of segments whose duration exceeds MinPts among the N segments determined by the PELT algorithm and record it as M;

[0094] (2) Initialize Eps opt Any element Eps in the Eps set j , e min is infinite (e min is an error, which can be set based on actual conditions and is a positive integer);

[0095] (3) Use EPS j Execute the DBSCAN algorithm with MinPts to cluster the feature F and return the number of clusters T;

[0096] (4) Determine whether T is equal to M. If |TM| = e min , then set Eps opt =Eps j , end clustering; if |TM|=<e min , Update Eps opt For EPSj , e min for |TM|;

[0097] (5) Repeat steps (3) and (4) until |TM| = e min End clustering;

[0098] (6) Output the identification results of the unit’s stable operation process.

[0099] Step S204: determining a performance evaluation result of the guide bearing based on the monitoring data during the steady-state operation period.

[0100] Specifically, step S204 includes:

[0101] Step S2041: filtering data based on the unit's operating status to obtain monitoring data marked as steady-state operation;

[0102] Step S2042, calculating the root mean square value of the monitoring data, and calculating the average value and standard deviation of the vibration of the computer group in each working cycle when the computer group is in a stable operating state based on the root mean square value;

[0103] Step S2043: Perform performance evaluation on the guide bearing based on the average value and the standard deviation to obtain a performance evaluation result of the guide bearing.

[0104] Taking the upper guide bearing as an example, the performance of the upper guide bearing is evaluated. Based on the real-time vibration monitoring data of the upper guide bearing obtained by the acceleration sensor, the root mean square value of each working cycle under the stable operating state is obtained. Specifically, the vibration signal data generated by the upper guide bearing during operation is first collected in real time by the acceleration sensor, and then the time period when the unit is in a stable operating state is screened out. The vibration data in these time periods are divided according to the preset working cycle (such as per minute, per hour, etc.), and then the root mean square value (RMS) of the vibration data in each working cycle is calculated. This value can effectively reflect the energy of the vibration, thereby obtaining the vibration RMS value sequence corresponding to each working cycle.

[0105] After obtaining the RMS vibration values ​​for each operating cycle, statistical analysis is performed on the RMS values ​​to calculate the average value of the RMS vibration values ​​for all stable operating cycles. This average value represents the average level of vibration of the upper guide bearing during stable operation of the unit. The standard deviation of the RMS values ​​is also calculated. The standard deviation reflects the degree of dispersion of the RMS vibration values ​​during different operating cycles, that is, the fluctuation of the vibration amplitude. The average value and standard deviation can provide a preliminary understanding of the vibration characteristics and stability of the upper guide bearing during stable operation.

[0106] Arrange the vibration RMS values ​​of each working cycle in chronological order and observe their changing trends over time. If the RMS value shows a continuous increase, an increased fluctuation amplitude, or an abnormal peak value, it indicates that the vibration energy of the upper guide bearing is increasing, and there may be performance degradation phenomena such as increased wear, poor lubrication, or loose components. Combined with the statistical results of the mean and standard deviation, if the RMS value gradually deviates from the mean in the later period and the standard deviation continues to increase, it can be further confirmed that the performance degradation trend is accelerating, thus providing a basis for predicting bearing failures and formulating maintenance plans.

[0107] The guide bearing performance evaluation method provided in this embodiment dynamically detects change points and adaptively adjusts algorithm parameters based on the detection results, improving adaptability to different operating modes of the hydropower unit. This allows accurate identification of steady-state and transient operating states, providing data support for evaluating guide bearing performance degradation. Guide bearing performance evaluation based on data from steady-state operation enables predictive maintenance, reduces maintenance costs, improves the monitoring accuracy of key equipment such as guide bearings, reduces downtime caused by equipment failure, enhances the operational reliability of hydropower stations, provides technical support for intelligent operation and maintenance of hydropower stations, and promotes the development of hydropower stations towards intelligence and automation.

[0108] This embodiment also provides a unit guide bearing performance evaluation device for implementing the aforementioned embodiments and implementations. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. While the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0109] This embodiment provides a device for evaluating the performance of a guide bearing of a unit. Figure 2 Shown, including:

[0110] Data acquisition module, used to obtain the time series of unit operation;

[0111] A time series determination module is used to segment the time series of the unit operation and determine the time series of different operation periods, wherein the operation periods include stable operation periods and transient operation periods;

[0112] A state determination module is used to extract the state characteristics of the time series of different operating time periods to determine the operating state of the unit;

[0113] The performance evaluation module is used to determine the performance evaluation result of the guide bearing based on the monitoring data during the steady-state operation period.

[0114] In some optional implementations, the time series determination module includes:

[0115] A preprocessing unit, configured to preprocess the time series to obtain a preprocessed time series;

[0116] The change point detection unit is used to detect the change points in the time series, and segment the time series based on the change points to determine the time series of different operating time periods, wherein the change points are used to represent the boundaries of different operating time periods.

[0117] In some optional implementations, the change point detection unit includes:

[0118] The change point determination subunit is configured to determine an objective function based on a penalty factor, and determine a change point in the time series based on the objective function.

[0119] In some optional implementations, the objective function is determined according to the following formula:

[0120]

[0121] Where G(n) represents the objective function. Suppose there are m change points, and the positions of the change points are represented by τ=(τ1,τ2,…,τ m ) represents, β represents the penalty factor;

[0122] The penalty factor β is determined according to the following formula:

[0123] β=(0.25n) (1-S) 2log(n)

[0124] Wherein, n represents the length of the time series, and S represents the sensitivity parameter.

[0125] In some optional implementations, the state determination module includes:

[0126] A feature extraction unit is used to extract features from time series in different operating periods to obtain features corresponding to the time series in each operating period;

[0127] The unit operation state determination unit is used to perform clustering processing on the features and determine the unit operation state based on the result of the clustering processing, wherein the unit operation state includes the identification result of the stable operation period.

[0128] In some optional implementations, the feature extraction unit includes:

[0129] The feature extraction subunit is used to calculate the mean and standard deviation of the time series of different operating time periods, and generate the features corresponding to the time series of each operating time period based on the mean and standard deviation.

[0130] In some optional implementations, the performance evaluation module includes:

[0131] a data screening unit, configured to screen data based on the operating status of the unit to obtain monitoring data marked as steady-state operation;

[0132] a root mean square value calculation unit, configured to calculate a root mean square value of the monitoring data, and based on the root mean square value, calculate an average value and a standard deviation of vibration in each working cycle of the unit when in a stable operating state;

[0133] The performance evaluation unit is used to perform performance evaluation on the guide bearing based on the average value and the standard deviation to obtain a performance evaluation result of the guide bearing.

[0134] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0135] The unit guide bearing performance evaluation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0136] The embodiment of the present invention also provides a computer device having the above Figure 2 The device shown.

[0137] See also Figure 3 , Figure 3 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 3 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0138] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0139] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0140] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0141] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0142] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0143] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0144] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0145] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the present invention.

Claims

1. A method for evaluating the performance of a guide bearing of a unit, characterized in that: The method comprises: Obtain the time series of unit operation; Segmenting the time series of the unit operation to determine time series of different operation periods, wherein the operation periods include stable operation periods and transient operation periods; Extracting state features of the time series of the different operating time periods to determine the operating state of the unit; The performance evaluation results of the guide bearing are determined based on the monitoring data during the steady-state operation period.

2. The method according to claim 1, characterized in that The step of segmenting the time series of the unit operation to determine the time series of different operation periods includes: Preprocessing the time series to obtain a preprocessed time series; The change points in the time series are detected, and the time series are segmented based on the change points to determine the time series of different operating time periods, wherein the change points are used to represent the boundaries of different operating time periods.

3. The method according to claim 2, characterized in that The detecting a change point in the time series includes: An objective function is determined based on the penalty factor, and a change point in the time series is determined based on the objective function.

4. The method according to claim 3, characterized in that The objective function is determined according to the following formula: Where G(n) represents the objective function. Suppose there are m change points, and the positions of the change points are represented by τ=(τ1,τ2,…,τ m ) represents, β represents the penalty factor; The penalty factor β is determined according to the following formula: β=(0.25n) (1-S) ·2log(n) Wherein, n represents the length of the time series, and S represents the sensitivity parameter.

5. The method according to claim 1, wherein The extracting the state features of the time series of the different operating time periods to determine the unit operating state includes: Extract features from time series in different operating periods to obtain features corresponding to the time series in each operating period; Clustering processing is performed on the features, and the unit operation status is determined based on the result of the clustering processing, where the unit operation status includes an identification result of a stable operation period.

6. The method according to claim 5, characterized in that The feature extraction of the time series of different operating periods to obtain the features corresponding to the time series of each operating period includes: The mean and standard deviation of the time series in different operating periods are calculated, and the features corresponding to the time series in each operating period are generated based on the mean and standard deviation.

7. The method according to claim 1, characterized in that The determining of the performance evaluation result of the guide bearing based on the monitoring data during the steady-state operation period includes: Performing data screening based on the operating status of the unit to obtain monitoring data marked as steady-state operation; Calculating a root mean square value of the monitoring data, and calculating, based on the root mean square value, an average value and a standard deviation of vibration in each working cycle of the unit when in a stable operating state; The guide bearing is subjected to a performance evaluation based on the average value and the standard deviation to obtain a performance evaluation result of the guide bearing.

8. A unit guide bearing performance evaluation device, characterized in that: The device comprises: Data acquisition module, used to obtain the time series of unit operation; A time series determination module is used to segment the time series of the unit operation and determine the time series of different operation periods, wherein the operation periods include stable operation periods and transient operation periods; A state determination module is used to extract the state characteristics of the time series of different operating time periods to determine the operating state of the unit; The performance evaluation module is used to determine the performance evaluation result of the guide bearing based on the monitoring data during the steady-state operation period.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the unit guide bearing performance evaluation method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the unit guide bearing performance evaluation method according to any one of claims 1 to 7.

Images