Operation detection method for self-walking crawler-type multi-loop hydraulic power station

Abstract

The invention relates to the technical field of fault detection of hydraulic systems, in particular to an operation detection method for a self-walking crawler-type multi-loop hydraulic power station, which comprises the following steps of: acquiring rotating speed data of an engine in the hydraulic power station, oil temperature data at an outlet of a hydraulic oil tank and output flow data at an outlet of a hydraulic pump; oil liquid cleanliness data at an oil return opening of the hydraulic oil tank are obtained; obtaining each flow sub-sequence and each cleanliness sub-sequence; acquiring a fluctuation consistency index between the cleanliness sub-sequence and the flow sub-sequence in each same time period; obtaining an overall change coefficient of the oil cleanliness data; the trend difference degree of the hydraulic power station is obtained; acquiring a temperature drop coefficient of the oil temperature data; and the fault confidence of the hydraulic power station is obtained, and whether the hydraulic power station breaks down or not is judged. The invention aims to ensure the stable operation of the hydraulic power station by improving the fault detection precision of the hydraulic power station.

Description

Technical Field

[0001] The present application relates to the technical field of fault detection of hydraulic systems, and in particular to an operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station. Background Art

[0002] In modern industry and engineering, self-propelled crawler multi-circuit hydraulic power stations are widely used in various complex environments due to their high efficiency and flexibility. In order to ensure the long-term and stable operation of self-propelled crawler multi-circuit hydraulic power stations, it is very important to detect and solve potential faults in a timely manner.

[0003] Among the existing methods for fault detection of hydraulic power stations, some methods directly use data comparison to detect whether the hydraulic power station has a fault. However, the working conditions of the hydraulic power station need to change according to the actual situation, which causes changes in the relevant parameters of the hydraulic power station, which can easily lead to false detection problems. Although some methods take into account the changes in working conditions, they focus on improving the cleaning ability of the hydraulic power station and switch the working state by setting thresholds, without conducting an in-depth analysis of the fault conditions of the hydraulic power station.

[0004] Therefore, the existing method for fault detection of the hydraulic power station during operation still has limitations. The coupling relationship between the internal parameters of the hydraulic power station is not fully utilized during the fault detection process, resulting in low detection accuracy and easy misdetection. Summary of the invention

[0005] In view of the above, it is necessary to provide an operation detection method for a self-propelled crawler multi-circuit hydraulic power station. Compared with the traditional operation detection method of a self-propelled crawler multi-circuit hydraulic power station, the fault detection accuracy of the hydraulic power station is improved, and the stable operation of the hydraulic power station can be ensured.

[0006] The operation detection method for the self-propelled crawler multi-circuit hydraulic power station of the present application adopts the following technical solution: An embodiment of the present application provides an operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station, the method comprising the following steps: Collect the speed data of the engine in the hydraulic power station, the oil temperature data at the outlet of the hydraulic oil tank, the output flow data at the outlet of the hydraulic pump, and the oil cleanliness data at the oil return port of the hydraulic oil tank within a preset time period; Based on the change characteristics of the rotation speed data at all acquisition moments, the preset time period is divided to obtain each flow subsequence and each cleanliness subsequence; Based on the correlation between the cleanliness subsequence and the flow subsequence in each same time period and the consistency of data fluctuation, the fluctuation consistency index between the cleanliness subsequence and the flow subsequence in each same time period is obtained; Based on the local growth of the data in each cleanliness subsequence and the overall growth of the data in all cleanliness subsequences, the overall variation coefficient of the oil cleanliness data is obtained; Based on the similarity of the changing trends between the speed data and the output flow data at all the collection moments, combined with the similarity of the changing trends between the speed data and the oil temperature data at all the collection moments, the trend difference of the hydraulic power station is obtained; Based on the decrease of the oil temperature data at all the acquisition moments, the temperature drop coefficient of the oil temperature data is obtained; Based on the distribution of the fluctuation consistency index between the cleanliness subsequences and the flow subsequences in all the same time periods, and in combination with the overall variation coefficient, trend difference and temperature drop coefficient, the fault confidence of the hydraulic power station is obtained; Based on the fault confidence, it is determined whether a fault occurs in the hydraulic power station.

[0007] In one embodiment, the process of obtaining each flow subsequence and each cleanliness subsequence is as follows: Arrange all the collected speed data in time sequence to form a speed sequence; use a mutation point detection algorithm to obtain the mutation point in the speed sequence, and divide the preset time period into various time intervals according to the time of the mutation point; The output flow data and oil cleanliness data of all acquisition moments in each time interval are arranged in time series to form flow subsequences and cleanliness subsequences.

[0008] In one embodiment, the process of obtaining the volatility consistency index is as follows: For each cleanliness subsequence, the discreteness of each oil cleanliness data and the oil cleanliness data at multiple adjacent moments are calculated; all the discreteness corresponding to the cleanliness subsequence are arranged in time sequence to form a local discrete sequence of the cleanliness subsequence; all peaks in the local discrete sequence are obtained, and the discreteness of all peaks in the local discrete sequence is used as the peak fluctuation index of the cleanliness subsequence; The local discrete sequence and peak fluctuation index of each flow subsequence are calculated respectively by using the same calculation method as the local discrete sequence and peak fluctuation index of each cleanliness subsequence; The fluctuation consistency index is further determined by the correlation and the similarity of the local discrete sequences between the cleanliness subsequences and the flow subsequences in the same time period, combined with the peak fluctuation index of the cleanliness subsequences and the peak fluctuation index of the flow subsequences in the same time period; the consistency of the data fluctuation is reflected by the similarity.

[0009] In one embodiment, the expression of the fluctuation consistency index is: ; In the formula, is the fluctuation consistency index between the i-th cleanliness subsequence and the i-th flow subsequence; is the mean of the peak fluctuation index of the i-th cleanliness subsequence and the i-th flow subsequence; is the correlation coefficient between the ith cleanliness subsequence and the ith flow rate subsequence; exp( ) is an exponential function with a natural constant as the base; N is the number of data in the ith cleanliness subsequence; are the tth data in the local discrete sequence of the i-th cleanliness subsequence and the i-th flow subsequence respectively; is a preset value greater than 0; wherein all flow subsequences and cleanliness subsequences are numbered in chronological order.

[0010] In one embodiment, the process of obtaining the overall variation coefficient is: Obtain the fitted straight line of all data points in each cleanliness subsequence, and calculate the mean distance between all data points in each cleanliness subsequence and the fitted straight line; Mapping the slope of each fitting straight line to a positive number, recorded as a first positive number, calculating the product of the distance mean of each cleanliness subsequence and the first positive number, and the local growth situation is reflected by the product; Calculate the average value of all data in each cleanliness subsequence, arrange the average values ​​of all cleanliness subsequences in time sequence to form a stage change sequence, map the sum of all elements in the first-order difference sequence of the stage change sequence to a positive number, recorded as the second positive number; the overall growth situation is reflected by the second positive number; The overall variation coefficient is further determined by the second positive number and the distribution of the products of all cleanliness subsequences.

[0011] In one embodiment, the overall variation coefficient is the product of the mean of the products of all cleanliness subsequences and the second positive number.

[0012] In one embodiment, the process of obtaining the trend difference is: Arrange all the collected oil temperature data and output flow data in time sequence to form oil temperature sequence and flow sequence; The DTW distance between the speed sequence and the flow sequence, and the DTW distance between the speed sequence and the oil temperature sequence are recorded as the first distance and the second distance respectively; The trend difference is the average of the first distance and the second distance.

[0013] In one embodiment, the process of obtaining the temperature drop coefficient is: The mutation point detection algorithm is used to obtain the mutation points in the oil temperature sequence, and the oil temperature sequence is divided into various oil temperature subsequences according to the mutation points; Obtain the range of all data in each oil temperature subsequence, and use the threshold segmentation algorithm to obtain the segmentation threshold of the range of all oil temperature subsequences; obtain the fitting straight line of all data points in each oil temperature subsequence; and take the temperature change subsequence whose range is greater than the segmentation threshold and the slope of the fitting straight line is less than or equal to 0 as the temperature drop subsequence; Calculate the discreteness of all elements in the first-order difference sequence of each temperature drop subsequence; The temperature drop coefficient is the product of the mean of the discrete degrees of all temperature drop subsequences and the discrete degree.

[0014] In one embodiment, the expression of the fault confidence is: ; In the formula, F is the fault confidence of the hydraulic power station; C is the overall variation coefficient of the oil cleanliness data; D is the trend difference of the hydraulic power station; W is the temperature drop coefficient of the oil temperature data; It is the mean of the fluctuation consistency index between the cleanliness subsequences and the flow subsequences in all the same time periods.

[0015] In one embodiment, the method for determining whether a hydraulic power station fails is: If the normalized value of the fault confidence is greater than a preset threshold, it is determined that the hydraulic power station has failed; otherwise, it is determined that the hydraulic power station has not failed.

[0016] This application has at least the following beneficial effects: This application obtains output flow data and oil cleanliness data under the same working condition through the change characteristics of the speed data, analyzes the output flow data and oil cleanliness data under the same working condition, and obtains the fluctuation consistency index, which is used to reflect the degree of fluctuation consistency between the oil cleanliness and the oil delivery volume under the same working condition, and preliminarily evaluates the operating status of the hydraulic power station; Furthermore, by analyzing the local and overall growth of oil cleanliness, the overall change coefficient is obtained to reflect the degree of change of oil cleanliness over time, and the operating status of the hydraulic power station is evaluated from the perspective of oil cleanliness change; Furthermore, by analyzing the changing relationship between the speed, output flow rate and oil temperature when the working conditions change, the trend difference is obtained to reflect whether the changing trends between the speed, output flow rate and oil temperature are similar, and the possibility of accurately evaluating whether the changing relationship between the parameters conforms to the normal operating state can be accurately evaluated; Furthermore, the fault confidence of the hydraulic power station is obtained by comprehensively considering the change in the drop rate of the oil temperature, the fluctuation consistency index, the overall variation coefficient and the trend difference. By analyzing from multiple angles and utilizing the coupling relationship between the internal parameters of the hydraulic power station, the fault condition of the hydraulic power station can be evaluated more comprehensively and accurately, thereby improving the fault detection accuracy of the hydraulic power station and ensuring the stable operation of the hydraulic power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A flowchart of the steps of the operation detection method for the self-propelled crawler multi-circuit hydraulic power station provided in this application; Figure 2 FIG. 1 is a flowchart of obtaining fault confidence. FIG. DETAILED DESCRIPTION

[0019] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. It should be understood that, unless otherwise specified, " / " means or.

[0021] It should also be noted that the terms "first" and "second" in the present application are used to distinguish similar objects rather than to describe a specific order or sequence.

[0022] The specific scheme of the operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station provided by the present application is described in detail below with reference to the accompanying drawings.

[0023] An embodiment of the present application provides an operation detection method for a self-propelled crawler type multi-circuit hydraulic power station. Specifically, the following operation detection method for a self-propelled crawler type multi-circuit hydraulic power station is provided. Figure 1 , the method comprises the following steps: Step 1: collect the speed data of the engine in the hydraulic power station, the oil temperature data at the outlet of the hydraulic oil tank, the output flow data at the outlet of the hydraulic pump, and the oil cleanliness data at the oil return port of the hydraulic oil tank within a preset time period.

[0024] The hydraulic power station is an independent hydraulic device, also known as a hydraulic pump station. It is suitable for various hydraulic machines where the main engine and the hydraulic device can be separated. It can supply oil according to the requirements of the drive device and can well control the flow, direction and pressure of the oil flow. The hydraulic power station provides power to the load equipment through the circulation of oil. After completing the work, the hydraulic oil returns to the oil tank through the hydraulic valve to form a cycle.

[0025] There are engines, hydraulic oil tanks and hydraulic pumps inside the hydraulic power station. This application collects engine speed data by installing a speed sensor at the engine crankshaft; collects oil temperature data by installing a temperature sensor at the outlet of the hydraulic oil tank; collects output flow data by installing a flow sensor at the outlet of the hydraulic pump; and collects oil cleanliness data by installing an extinction particle counter at the oil return port of the hydraulic oil tank.

[0026] The engine speed data in the hydraulic power station, the oil temperature data at the hydraulic oil tank outlet, the output flow data at the hydraulic pump outlet, and the oil cleanliness data at the hydraulic oil tank return port are collected within a preset time period.

[0027] In this embodiment, the collection frequency of the speed data, oil temperature data, output flow data and oil cleanliness data is 1s, and the length of the preset time period is 30 minutes. The values ​​of the collection frequency and collection time are preset manually, and the implementer can set them according to the actual situation. This application does not impose any special restrictions.

[0028] All the collected speed data, oil temperature data, output flow data, and oil cleanliness data are arranged in time sequence to form a speed sequence, an oil temperature sequence, a flow sequence, and a cleanliness sequence. In order to eliminate the dimensional influence between different data, the data in the speed sequence, the oil temperature sequence, the flow sequence, and the cleanliness sequence are normalized. In this embodiment, the Z-Score normalization method is used to normalize the data in the speed sequence, the oil temperature sequence, the flow sequence, and the cleanliness sequence.

[0029] Step 2: Obtain the fluctuation consistency index to evaluate the fluctuation consistency between the oil cleanliness and the output flow; obtain the overall variation coefficient to reflect the overall variation of the oil cleanliness; obtain the trend difference to analyze the changing relationship between the speed and the output flow and the oil temperature when the working conditions change; obtain the temperature drop coefficient to reflect the drop in the oil temperature; and then obtain the fault confidence to comprehensively evaluate the operating status of the hydraulic power station.

[0030] When the load equipment demand of the hydraulic power station does not change, that is, when the working condition of the hydraulic power station is stable, the speed of the engine in the hydraulic power station has been relatively stable, and the oil is stably supplied to the load equipment. At this time, since the speed has not changed significantly, the oil delivery volume, oil temperature, and oil cleanliness of the hydraulic power station are also relatively stable. Considering that if the demand of the load equipment changes, the hydraulic power station will adjust the engine speed to change the oil delivery volume in order to respond to the load demand. If the speed is higher, the oil delivery volume will increase, and the flow rate of the oil will increase accordingly, resulting in increased friction between the oil and the inner wall of the pipeline, causing the oil temperature to rise.

[0031] Based on the above analysis, the operating data under the same working condition can be extracted through the changing characteristics of the speed data. By conducting in-depth analysis of the operating data under different working conditions, the purpose of accurately detecting the operating status of the hydraulic power station can be achieved.

[0032] Step 2.1, based on the variation characteristics of the rotation speed data at all acquisition moments, the preset time period is divided to obtain each flow subsequence and each cleanliness subsequence.

[0033] The mutation point detection algorithm is used to obtain the mutation point in the speed sequence, and the moment of the mutation point is used as the segmentation point to segment the preset time period into time intervals. The output flow data and oil cleanliness data of all the acquisition moments in each time interval are arranged in time sequence to form each flow subsequence and each cleanliness subsequence. Each time interval corresponds to an operating condition of the hydraulic power station.

[0034] In this embodiment, the Bernaola Galvan segmentation algorithm is used to obtain the mutation points in the speed sequence. The Bernaola Galvan segmentation algorithm is a well-known technology and will not be described in detail in this application. As other implementation methods, on the basis of being able to obtain the mutation points in the speed sequence, the implementer may adopt other existing technologies, such as the Mann-Kendall mutation point detection algorithm, the Pettitt mutation point detection algorithm, etc., and this application does not make any special restrictions.

[0035] Take the i-th flow subsequence and the i-th cleanliness subsequence as examples.

[0036] Under stable working conditions, the fluctuation degree of the delivery flow and oil cleanliness of the hydraulic power station is relatively stable. However, if the hydraulic pump inside the hydraulic power station is worn, the seal is aged, and other faults occur, then even under the premise of stable working conditions, due to the reduction of the volumetric efficiency of the hydraulic pump, the system will not be able to reach the predetermined working pressure, resulting in unstable oil delivery of the hydraulic pump and large fluctuations in the output flow. At the same time, damage to the hydraulic pump, especially aging of the seal and internal wear, will also cause metal particles or other wear materials to enter the oil, thereby increasing the pollutants in the oil. Since the oil is flowing, it will also cause large fluctuations in the oil cleanliness. Therefore, the operating status of the hydraulic power station can be reflected by analyzing the stability of the output flow and oil cleanliness.

[0037] Taking the oil cleanliness data in the ith cleanliness subsequence as the center, a window of preset size is constructed, the discreteness of all data in the window is calculated, and all the discreteness corresponding to the ith cleanliness subsequence is arranged in time sequence to form a local discrete sequence of the ith cleanliness subsequence, which is used to reflect the local fluctuation of each data in the ith cleanliness subsequence and the data at multiple neighboring moments. It should be noted that if the center of the window is located at both ends of the cleanliness subsequence, causing the window to exceed the range of the cleanliness subsequence, the mean filling method is used according to the data in the cleanliness subsequence to fill the data in the window.

[0038] In this embodiment, the window size is 1 The size of the window is preset manually, and the implementer can set it according to the actual situation. This application does not impose any special restrictions.

[0039] In this embodiment, the discreteness of all data in the window is the coefficient of variation. The coefficient of variation is a well-known technology and will not be described in detail in this application. As other implementation methods, on the basis of being able to measure the degree of uneven distribution of all data in the window, the implementer may adopt other existing technologies, such as standard deviation, variance, etc., and this application does not make any special restrictions.

[0040] All peaks in the local discrete sequence of the i-th cleanliness subsequence are obtained through an automatic multi-scale peak search algorithm, and the discreteness of all peaks in the local discrete sequence of the i-th cleanliness subsequence is used as the peak fluctuation index of the i-th cleanliness subsequence; the larger the peak fluctuation index, the more inconsistent the instantaneous mutation degree of the peak in the local fluctuation sequence of the i-th cleanliness subsequence, and the more severe the fluctuation degree within the i-th cleanliness subsequence.

[0041] In this embodiment, the discreteness of all peak values ​​is the coefficient of variation, and the coefficient of variation is a well-known technology and will not be described in detail in this application. As other implementation methods, on the basis of being able to measure the degree of uneven distribution of all peak values, the implementer may adopt other existing technologies, such as standard deviation, variance, etc., and this application does not impose any special restrictions.

[0042] The local discrete sequence and peak fluctuation index of the i-th flow subsequence are calculated respectively by using the same calculation method as the local discrete sequence and peak fluctuation index of the i-th cleanliness subsequence.

[0043] Based on the similarity of the local discrete sequences between the cleanliness subsequences and the flow subsequences in the same time period, combined with the peak fluctuation index of the cleanliness subsequences and the peak fluctuation index of the flow subsequences in the same time period, and the correlation between the cleanliness subsequences and the flow subsequences in the same time period, the fluctuation consistency index between the cleanliness subsequences and the flow subsequences in the same time period is obtained, and the expression is: ; In the formula, is the fluctuation consistency index between the i-th cleanliness subsequence and the i-th flow subsequence; is the mean of the peak fluctuation index of the i-th cleanliness subsequence and the i-th flow subsequence; is the correlation coefficient between the ith cleanliness subsequence and the ith flow subsequence; exp( ) is an exponential function with a natural constant as the base, the purpose of which is to map the correlation coefficient to a positive number; N is the number of data in the ith cleanliness subsequence; are the tth data in the local discrete sequence of the i-th cleanliness subsequence and the i-th flow subsequence respectively; A value greater than 0 is preset to avoid the denominator being 0. The value of is preset by humans and can be set by the implementer. The value of is 0.01. All the flow subsequences and cleanliness subsequences are numbered in time sequence.

[0044] In this embodiment, the correlation coefficient between the i-th cleanliness subsequence and the i-th flow subsequence is the Pearson correlation coefficient. As other implementation methods, on the basis of being able to measure the correlation between the i-th cleanliness subsequence and the i-th flow subsequence, the implementer may adopt other existing technologies, such as the Spearman correlation coefficient, the Kendall rank correlation coefficient, etc., and this application does not impose any special restrictions.

[0045] It should be noted that: when the hydraulic power station operates normally and the working conditions are stable, the output flow and oil cleanliness of the hydraulic power station are relatively stable, with small fluctuations and strong synchronization. At this time, the difference between the data at the same position in the local discrete sequence of the i-th flow subsequence and the i-th cleanliness subsequence is small; If the hydraulic power station has faults such as wear and tear or aging of seals, the output flow and oil cleanliness of the hydraulic power station will fluctuate greatly even under stable working conditions. And because the impact of the fault on the output flow and oil cleanliness is not consistent, the fluctuation degree between the output flow and oil cleanliness will no longer be synchronized at the same time. Therefore, if the average volatility difference The larger the value is, the greater the change degree of the peak values ​​of the two local discrete sequences is, which reflects that the internal fluctuation of the i-th cleanliness subsequence and the i-th flow subsequence may be more drastic; if The smaller is, the more inconsistent the data change trend between the i-th cleanliness subsequence and the i-th flow subsequence is; if The larger the value is, the greater the fluctuation difference between the output flow of the hydraulic power station and the oil cleanliness is, and the greater the possibility that the output flow and the oil cleanliness no longer have the same stable characteristics. The smaller it is, the more likely it is that the data fluctuations within the i-th cleanliness subsequence and the i-th flow subsequence are more drastic, and they no longer have stable characteristics.

[0046] According to the calculation method of the fluctuation consistency index between the i-th cleanliness subsequence and the i-th flow subsequence, the fluctuation consistency index between the cleanliness subsequence and the flow subsequence in each same time period is calculated.

[0047] Step 2.2, based on the local growth of the data in each cleanliness subsequence and the overall growth of the data in all cleanliness subsequences, obtain the overall variation coefficient of the oil cleanliness data.

[0048] Furthermore, if the hydraulic power station is in good condition, the cleanliness of the oil will be high and stable even if the engine speed is increased. The reason is that in the absence of wear, there are fewer metal particles and other contaminants in the oil, and generally no additional wear particles will be generated due to the increase in flow rate. If the hydraulic power station has faults such as wear or seal aging, more metal particles and other wear products will gradually accumulate in the oil as the hydraulic power station continues to operate. These contaminants not only come from the wear of internal components, but also from the aging of seals that cannot effectively block the invasion of external impurities, resulting in a further decrease in the cleanliness of the oil. At the same time, since damage is irreversible, if the hydraulic power station fails, the cleanliness of its oil will gradually decrease over time, and the concentration of particulate matter in the oil will gradually increase. Therefore, the operating status of the hydraulic power station can be further detected by analyzing the changes in the cleanliness of the oil.

[0049] Still taking the i-th cleanliness subsequence as an example, a straight line is fitted for all data points in the i-th cleanliness subsequence, the mean distance between all data points in the i-th cleanliness subsequence and the fitting straight line is calculated, the slope of the fitting straight line is mapped to a positive number, recorded as the first positive number, and the product of the mean distance of the i-th cleanliness subsequence and the first positive number is calculated; the larger the product, the greater the overall fluctuation of the i-th cleanliness subsequence, and the greater the rate of increase of the oil concentration, the faster the decrease in the oil cleanliness. Among them, the distance between the data point and the fitting straight line is the Euclidean distance, and the data points in the cleanliness subsequence are composed of each acquisition time and its oil cleanliness data. The calculation of the slope of the fitting straight line is a well-known technology and will not be repeated in this application.

[0050] In this embodiment, the least squares method is used to perform straight-line fitting for all data points in the cleanliness subsequence. The least squares method is a well-known technology and will not be described in detail in this application. As other implementation methods, on the basis of being able to perform straight-line fitting for all data points in the cleanliness subsequence, the implementer may adopt other existing technologies, such as linear regression analysis, weighted least squares method, etc., and this application does not make any special restrictions.

[0051] In this embodiment, the method of mapping the slope of the fitting straight line to a positive number is: taking the slope of the fitting straight line as the exponent of an exponential function with a natural constant as the base.

[0052] Calculate the average value of all data in each cleanliness subsequence, arrange the average values ​​of all cleanliness subsequences in time sequence to form a phase change sequence, and map the sum of all elements in the first-order difference sequence of the phase change sequence to a positive number, which is recorded as the second positive number; if the hydraulic power station has not failed, the average values ​​of all data in each cleanliness subsequence are relatively consistent, the difference between the elements in the first-order difference sequence is small and there are positive and negative elements, then the second positive number is small. If a failure occurs and the concentration of the oil gradually increases, then all the elements in the first-order difference sequence are positive numbers, so the second positive number is large, and the larger the second positive number is, the greater the degree of decline in the cleanliness of the oil, and the greater the possibility of failure of the hydraulic power station.

[0053] In this embodiment, the method for mapping the sum of all elements in the first-order difference sequence to a positive number is: taking the sum of all elements in the first-order difference sequence as the exponent of an exponential function with a natural constant as the base.

[0054] Furthermore, the product of the mean of the products of all cleanliness subsequences and the second positive number is used as the overall variation coefficient of the oil cleanliness data, and the expression is: ; Where C is the overall variation coefficient of oil cleanliness data; is the mean of the products of all cleanliness subsequences; and Z is the second positive number.

[0055] It should be noted that the larger the overall variation coefficient C is, the greater the degree of decline in oil cleanliness is, and the more it gradually decreases over time, the greater the possibility of failure of the hydraulic power station is.

[0056] Step 2.3, based on the similarity of the changing trends between the rotational speed data and the output flow data at all acquisition moments, combined with the similarity of the changing trends between the rotational speed data and the oil temperature data at all acquisition moments, the trend difference of the hydraulic power station is obtained.

[0057] Furthermore, when the speed of the hydraulic power station increases, the oil delivery volume increases, and the output flow rate increases, causing the oil temperature to rise; when the speed decreases, the output flow rate will also decrease immediately, and the oil temperature will gradually decrease. Therefore, by analyzing the changing relationship between the speed, output flow rate, and oil temperature when the working conditions change, the operating status of the hydraulic power station can be more accurately reflected.

[0058] Considering that the change in temperature has a lag compared to the change in speed, the correlation between the oil temperature sequence and the speed sequence is analyzed through DTW (Dynamic TimeWarping) distance to overcome the problem caused by the temperature response lag.

[0059] The DTW distance between the speed sequence and the flow sequence, and the DTW distance between the speed sequence and the oil temperature sequence are recorded as the first distance and the second distance respectively, and the average of the first distance and the second distance is taken as the trend difference of the hydraulic power station; the smaller the trend difference is, the stronger the correlation between the speed and the output flow, and between the speed and the oil temperature is, and the data change trend is still relatively consistent, and the greater the possibility that the hydraulic power station has not failed.

[0060] Step 2.4, based on the drop of the oil temperature data at all acquisition moments, obtain the temperature drop coefficient of the oil temperature data.

[0061] Furthermore, if a fault occurs in the hydraulic power station, the heat transfer and dissipation process becomes slow due to the high concentration of the oil, resulting in a slower drop in temperature when the speed decreases, and the drop rate is no longer stable.

[0062] The mutation point detection algorithm is used to obtain the mutation points in the oil temperature sequence, and the mutation points are used as segmentation points to divide the oil temperature sequence into oil temperature subsequences. Obtain the range of all data in each oil temperature subsequence, and use the threshold segmentation algorithm to obtain the segmentation threshold of the range of all oil temperature subsequences; obtain the fitting straight line of all data points in each oil temperature subsequence; take the temperature change subsequence whose range is greater than the segmentation threshold and the slope of the fitting straight line is less than or equal to 0 as the temperature drop subsequence; calculate the discreteness of all elements in the first-order difference sequence of each temperature drop subsequence, and take the product of the mean of the discreteness of all temperature drop subsequences and the discreteness as the temperature drop coefficient of the oil temperature data; the larger the temperature drop coefficient, the more inconsistent the temperature change degree of each temperature drop subsequence, and the greater the change in the drop rate. It should be noted that: when the temperature drop subsequence cannot be obtained, 0 is used as the temperature drop coefficient of the oil temperature data. Among them, the data points in the oil temperature subsequence are composed of each acquisition time and its oil temperature data. The calculation of the slope of the fitting straight line is a well-known technology and will not be repeated in this application.

[0063] In this embodiment, the Bernaola Galvan segmentation algorithm is used to obtain each mutation point in the oil temperature sequence. The Bernaola Galvan segmentation algorithm is a well-known technology and will not be described in detail in this application. As other implementation methods, on the basis of being able to obtain each mutation point in the oil temperature sequence, the implementer may adopt other existing technologies, such as the Mann-Kendall mutation point detection algorithm, the Pettitt mutation point detection algorithm, etc., and this application does not make any special restrictions.

[0064] In this embodiment, the Otsu threshold segmentation algorithm is used to obtain the segmentation threshold of the extreme difference of all oil temperature subsequences. The Otsu threshold segmentation algorithm is a well-known technology and will not be described in detail in this application. As other implementation methods, on the basis of being able to obtain the segmentation threshold of the extreme difference of all oil temperature subsequences, the implementer may adopt other existing technologies, such as global threshold segmentation, iterative threshold segmentation, etc., and this application does not impose any special restrictions.

[0065] In this embodiment, the least squares method is used to obtain the fitting straight line for all data points in each oil temperature subsequence. The least squares method is a well-known technology and will not be described in detail in this application. As other implementation methods, on the basis of being able to obtain the fitting straight line for all data points in each oil temperature subsequence, the implementer may adopt other existing technologies, such as linear regression analysis, weighted least squares method, etc., and this application does not make any special restrictions.

[0066] In this embodiment, the degree of discreteness of all elements in the first-order difference sequence is the variance, and the degree of discreteness of the discreteness of all temperature drop subsequences is the variance. As other implementation methods, on the basis of being able to measure the uneven distribution of all elements in the first-order difference sequence and the uneven distribution of the discreteness of all temperature drop subsequences, the implementer may adopt other existing technologies, such as standard deviation, coefficient of variation, etc., and this application does not impose any special restrictions.

[0067] Step 2.5, based on the distribution of the fluctuation consistency index between the cleanliness subsequences and the flow subsequences in all the same time periods, and combined with the overall variation coefficient, trend difference and temperature drop coefficient, the fault confidence of the hydraulic power station is obtained.

[0068] Furthermore, the distribution of the fluctuation consistency index between the cleanliness subsequence and the flow subsequence in all the same time periods, the overall variation coefficient, the trend difference and the temperature drop coefficient are comprehensively considered to obtain the fault confidence of the hydraulic power station, and the expression is: ; In the formula, F is the fault confidence of the hydraulic power station; C is the overall variation coefficient of the oil cleanliness data; D is the trend difference of the hydraulic power station; W is the temperature drop coefficient of the oil temperature data; It is the mean of the fluctuation consistency index between the cleanliness subsequences and the flow subsequences in all the same time periods.

[0069] It should be noted that if the mean The smaller it is, the more likely it is that the data fluctuations between the cleanliness subsequence and the flow subsequence in the same time period are no longer synchronous; if the overall change coefficient C is larger, the greater the overall decrease in oil cleanliness; if the trend difference D is larger, the more likely it is that the change trends between the speed and output flow, and the speed and oil temperature are no longer consistent; if the temperature drop coefficient W is larger, the greater the fluctuation in the rate of decrease of the oil temperature when it decreases. Therefore, the greater the fault confidence, the greater the possibility of a fault in the hydraulic power station. The schematic diagram of the fault confidence acquisition process is as follows: Figure 2 shown.

[0070] Step 3: Based on the fault confidence, determine whether the hydraulic power station fails.

[0071] The fault confidence of the hydraulic power station is normalized. If the normalized value of the fault confidence is greater than a preset threshold, it is determined that the hydraulic power station has a wear or seal aging failure, and the hydraulic power station needs to be repaired in time; if the normalized value of the fault confidence is less than or equal to the preset threshold, it is determined that the hydraulic power station has not failed and can continue to operate and use.

[0072] In this embodiment, a hyperbolic tangent function is used to normalize the fault confidence of the hydraulic power station.

[0073] In this embodiment, the value of the preset threshold is 0.5. The value of the preset threshold is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0074] In summary, the present application obtains the output flow data and oil cleanliness data under the same working condition through the change characteristics of the speed data, analyzes the output flow data and oil cleanliness data under the same working condition, and obtains the fluctuation consistency index, which is used to reflect the degree of fluctuation consistency between the oil cleanliness and the oil delivery volume under the same working condition, and preliminarily evaluates the operating status of the hydraulic power station; Furthermore, by analyzing the local and overall growth of oil cleanliness, the overall change coefficient is obtained to reflect the degree of change of oil cleanliness over time, and the operating status of the hydraulic power station is evaluated from the perspective of oil cleanliness change; Furthermore, by analyzing the changing relationship between the speed, output flow rate and oil temperature when the working conditions change, the trend difference is obtained to reflect whether the changing trends between the speed, output flow rate and oil temperature are similar, and the possibility of accurately evaluating whether the changing relationship between the parameters conforms to the normal operating state can be accurately evaluated; Furthermore, the fault confidence of the hydraulic power station is obtained by comprehensively considering the change in the drop rate of the oil temperature, the fluctuation consistency index, the overall variation coefficient and the trend difference. By analyzing from multiple angles and utilizing the coupling relationship between the internal parameters of the hydraulic power station, the fault condition of the hydraulic power station can be evaluated more comprehensively and accurately, thereby improving the fault detection accuracy of the hydraulic power station and ensuring the stable operation of the hydraulic power station.

[0075] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0076] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive.

Claims

1. An operation detection method for a self-propelled crawler multi-circuit hydraulic power station, characterized in that: The method comprises the following steps: Collect the speed data of the engine in the hydraulic power station, the oil temperature data at the outlet of the hydraulic oil tank, the output flow data at the outlet of the hydraulic pump, and the oil cleanliness data at the oil return port of the hydraulic oil tank within a preset time period; Based on the change characteristics of the rotation speed data at all acquisition moments, the preset time period is divided to obtain each flow subsequence and each cleanliness subsequence; Based on the correlation between the cleanliness subsequence and the flow subsequence in each same time period and the consistency of data fluctuation, the fluctuation consistency index between the cleanliness subsequence and the flow subsequence in each same time period is obtained; Based on the local growth of the data in each cleanliness subsequence and the overall growth of the data in all cleanliness subsequences, the overall variation coefficient of the oil cleanliness data is obtained; Based on the similarity of the changing trends between the speed data and the output flow data at all the collection moments, combined with the similarity of the changing trends between the speed data and the oil temperature data at all the collection moments, the trend difference of the hydraulic power station is obtained; Based on the decrease of the oil temperature data at all the acquisition moments, the temperature drop coefficient of the oil temperature data is obtained; Based on the distribution of the fluctuation consistency index between the cleanliness subsequences and the flow subsequences in all the same time periods, and in combination with the overall variation coefficient, trend difference and temperature drop coefficient, the fault confidence of the hydraulic power station is obtained; Based on the fault confidence, it is determined whether a fault occurs in the hydraulic power station.

2. The operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station according to claim 1, characterized in that: The acquisition process of each flow subsequence and each cleanliness subsequence is as follows: Arrange all the collected speed data in time sequence to form a speed sequence; use a mutation point detection algorithm to obtain the mutation point in the speed sequence, and divide the preset time period into various time intervals according to the time of the mutation point; The output flow data and oil cleanliness data of all acquisition moments in each time interval are arranged in time series to form flow subsequences and cleanliness subsequences.

3. The operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station according to claim 1, characterized in that: The process of obtaining the volatility consistency index is as follows: For each cleanliness subsequence, the discreteness of each oil cleanliness data and the oil cleanliness data at multiple adjacent moments are calculated; all the discreteness corresponding to the cleanliness subsequence are arranged in time sequence to form a local discrete sequence of the cleanliness subsequence; all peaks in the local discrete sequence are obtained, and the discreteness of all peaks in the local discrete sequence is used as the peak fluctuation index of the cleanliness subsequence; The local discrete sequence and peak fluctuation index of each flow subsequence are calculated respectively by using the same calculation method as the local discrete sequence and peak fluctuation index of each cleanliness subsequence; The fluctuation consistency index is further determined by the correlation and the similarity of the local discrete sequences between the cleanliness subsequences and the flow subsequences in the same time period, combined with the peak fluctuation index of the cleanliness subsequences and the peak fluctuation index of the flow subsequences in the same time period; the consistency of the data fluctuation is reflected by the similarity.

4. The operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station according to claim 3, characterized in that: The expression of the volatility consistency index is: ; In the formula, is the fluctuation consistency index between the i-th cleanliness subsequence and the i-th flow subsequence; is the mean of the peak fluctuation index of the i-th cleanliness subsequence and the i-th flow subsequence; is the correlation coefficient between the ith cleanliness subsequence and the ith flow rate subsequence; exp( ) is an exponential function with a natural constant as the base; N is the number of data in the ith cleanliness subsequence; are the tth data in the local discrete sequence of the i-th cleanliness subsequence and the i-th flow subsequence respectively; is a preset value greater than 0; wherein all flow subsequences and cleanliness subsequences are numbered in chronological order.

5. The operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station according to claim 1, characterized in that: The process of obtaining the overall coefficient of variation is as follows: Obtain the fitted straight line of all data points in each cleanliness subsequence, and calculate the mean distance between all data points in each cleanliness subsequence and the fitted straight line; Mapping the slope of each fitting straight line to a positive number, recorded as a first positive number, calculating the product of the distance mean of each cleanliness subsequence and the first positive number, and the local growth situation is reflected by the product; Calculate the average value of all data in each cleanliness subsequence, arrange the average values ​​of all cleanliness subsequences in time sequence to form a stage change sequence, map the sum of all elements in the first-order difference sequence of the stage change sequence to a positive number, recorded as the second positive number; the overall growth situation is reflected by the second positive number; The overall variation coefficient is further determined by the second positive number and the distribution of the products of all cleanliness subsequences.

6. The operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station according to claim 5, characterized in that: The overall variation coefficient is the product of the mean of the products of all cleanliness subsequences and the second positive number.

7. The operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station according to claim 2, characterized in that: The process of obtaining the trend difference is as follows: Arrange all the collected oil temperature data and output flow data in time sequence to form oil temperature sequence and flow sequence; The DTW distance between the speed sequence and the flow sequence, and the DTW distance between the speed sequence and the oil temperature sequence are recorded as the first distance and the second distance respectively; The trend difference is the average of the first distance and the second distance.

8. The operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station according to claim 7, characterized in that: The process of obtaining the temperature drop coefficient is as follows: The mutation point detection algorithm is used to obtain the mutation points in the oil temperature sequence, and the oil temperature sequence is divided into various oil temperature subsequences according to the mutation points; Obtain the range of all data in each oil temperature subsequence, and use the threshold segmentation algorithm to obtain the segmentation threshold of the range of all oil temperature subsequences; obtain the fitting straight line of all data points in each oil temperature subsequence; and take the temperature change subsequence whose range is greater than the segmentation threshold and the slope of the fitting straight line is less than or equal to 0 as the temperature drop subsequence; Calculate the discreteness of all elements in the first-order difference sequence of each temperature drop subsequence; The temperature drop coefficient is the product of the mean of the discrete degrees of all temperature drop subsequences and the discrete degree.

9. The operation detection method for a self-propelled crawler-type multi-circuit hydraulic power station according to claim 1, characterized in that: The expression of the fault confidence is: ; In the formula, F is the fault confidence of the hydraulic power station; C is the overall variation coefficient of the oil cleanliness data; D is the trend difference of the hydraulic power station; W is the temperature drop coefficient of the oil temperature data; It is the mean of the fluctuation consistency index between the cleanliness subsequences and the flow subsequences in all the same time periods.

10. The operation detection method for a self-propelled crawler type multi-circuit hydraulic power station according to claim 1, characterized in that: The method for determining whether a hydraulic power station fails is as follows: If the normalized value of the fault confidence is greater than a preset threshold, it is determined that the hydraulic power station has failed; otherwise, it is determined that the hydraulic power station has not failed.

Images