A method and system for detecting non-return performance of a one-way valve

Abstract

The present application relates to the field of one-way valve check detection technology, and specifically to a one-way valve check performance detection method and system, which specifically includes: obtaining the first and second check fluctuation sets of each local check sequence by classifying the data in the neighborhood of the air pressure difference at each moment, and constructing the local check fluctuation value based on the data discreteness in the first and second check fluctuation sets; classifying the elements in the local check sequence based on the data anomaly and data discreteness of the local check fluctuation value, and obtaining the replacement value of the central element of the local check sequence based on the classification result; obtaining the pressure difference correction sequence based on the sequence composed of the replacement values; and performing the one-way valve check performance detection based on the difference between the pressure difference correction sequences under all kinds of air pressure. The influence of vibration noise on the pressure difference data is suppressed, the accuracy of the air pressure difference data at both ends of the one-way valve is improved, and the accuracy of the one-way valve check performance detection is thereby improved.

Description

Technical Field

[0001] The present application relates to the technical field of one-way valve check performance detection, and in particular to a one-way valve check performance detection method and system. Background Art

[0002] A one-way valve, also known as a non-return valve or check valve, is a valve device that allows liquid or gas to flow in only one direction. Its main function is to prevent the backflow of liquid or gas and ensure the one-way flow of fluid in the pipeline system. For the braking system of rail transit vehicles, the function of the one-way valve is to ensure that compressed air enters the brake cylinder and ensures that the brake cylinder can quickly and safely supply air to the brake control system.

[0003] During the braking process of a rail transit vehicle, the rail transit vehicle will shake, causing the one-way valve to vibrate. Therefore, for the one-way valve used on the rail transit vehicle, it is necessary to test the non-return ability of the one-way valve during the vibration process to ensure the stability of the one-way valve during use.

[0004] The non-return performance of a one-way valve is generally tested by analyzing the difference in air pressure between the inlet and outlet ends of the one-way valve. However, since the one-way valve is used in the braking system of a rail vehicle, the rail vehicle will vibrate during braking, causing the one-way valve to vibrate, which can easily generate a large amount of vibration noise. In addition, the vibration of the one-way valve can easily cause the rubber seal of the one-way valve to loosen, affecting the detection of the non-return performance of the one-way valve, resulting in inaccurate detection of the non-return performance of the one-way valve. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of this application is to provide a one-way valve check performance detection method and system, and the technical solutions adopted are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for detecting the check performance of a one-way valve, the method comprising the following steps:

[0007] Collect the pressure data of the inlet and outlet of the one-way valve at each time under various air pressure conditions in the oscillating environment;

[0008] Under any air pressure, the difference between the pressure data of the air inlet and the air outlet at each moment is taken as the pressure difference at each moment; in the pressure difference sequence composed of the pressure differences at all moments, the sequence composed of all data in the neighborhood window centered on each element is taken as the local non-return sequence of each element;

[0009] Classifying the data size in the local check sequence of each element to obtain the first and second check fluctuation sets of each local check sequence, and obtaining the local check fluctuation value of each local check sequence based on the degree of data dispersion in the first and second check fluctuation sets;

[0010] Based on the data anomalies of the local check fluctuation values, the orbital vibration influence of the pressure difference sequence is constructed, and the fluctuation deviation of the pressure difference sequence is constructed in combination with the data discreteness of all local check fluctuation values ​​in the pressure difference sequence; based on the fluctuation deviation, the elements in the local check sequence are classified, and the replacement value of the central element of the local check sequence is obtained based on the classification result;

[0011] A pressure difference correction sequence is obtained based on the sequence composed of the replacement values; and a one-way valve check performance test is performed based on the difference between the pressure difference correction sequences under all kinds of gas pressures.

[0012] In one embodiment, the process of obtaining the first and second non-return fluctuation sets is as follows:

[0013] The mean of all data in each local stop-return sequence is recorded as the first mean; in each local stop-return sequence, the set consisting of data greater than the first mean is recorded as the first stop-return fluctuation set, and the set consisting of data less than or equal to the first mean is recorded as the second stop-return fluctuation set.

[0014] In one embodiment, the process of obtaining the local non-return fluctuation value is as follows:

[0015] Record the mean of all data in the first stop-return fluctuation set as the second mean, calculate the difference between each data in the first stop-return fluctuation set and the second mean, and record it as the first difference; and use the fusion value of all the first differences as the first stop-return fluctuation value of the local stop-return sequence;

[0016] Based on the second stop-return fluctuation set, the second stop-return fluctuation value of the local stop-return sequence is calculated using the same acquisition method as the first stop-return fluctuation value; the fusion value of the first stop-return fluctuation value and the second stop-return fluctuation value is used as the local stop-return fluctuation value of the local stop-return sequence.

[0017] In one embodiment, the process of obtaining the orbital vibration influence is as follows:

[0018] All the local check-return fluctuation values ​​in the pressure difference sequence are used as the input of the anomaly detection algorithm, and the output is the local anomaly factor of each local check-return fluctuation value; the orbital vibration influence of the pressure difference sequence is recorded as F, and the calculation expression of F is: , where The discrete coefficient of the local anomaly factor representing the local stop fluctuation value corresponding to all elements in the pressure difference sequence, Represents the mean of the local stop fluctuation values ​​corresponding to all elements in the pressure difference series.

[0019] In one embodiment, the calculation expression of the fluctuation deviation is:

[0020] , where R represents the fluctuation deviation of the pressure difference sequence, and F represents the orbital vibration influence of the pressure difference sequence. Represents the standard deviation of the local stop fluctuation values ​​corresponding to all elements in the pressure difference series.

[0021] In one embodiment, the process of obtaining the replacement value is:

[0022] Classify the elements in the local non-return sequence based on the fluctuation deviation to obtain the number of groups into which the elements in the local non-return sequence are divided;

[0023] The number of elements in the local check sequence is denoted as n. If the local check sequence is divided into n groups or one group, the replacement value of the central element of the local check sequence is the central element of the local check sequence itself; otherwise, the group with the largest number of elements in the divided groups is selected, and the mean of all elements in the group with the largest number of elements is calculated as the replacement value of the central element of the local check sequence.

[0024] In one embodiment, the process of obtaining the number of groups is as follows:

[0025] The absolute value of the difference between any two elements in the local check sequence is calculated and recorded as the first absolute value of the difference; if the first absolute value of the difference is less than or equal to the fluctuation deviation of the corresponding pressure difference sequence, the any two elements are classified into the same group; the groups with the same elements are merged, and the number of groups finally obtained is counted.

[0026] In one embodiment, the pressure difference correction sequence is a sequence composed of replacement values ​​of pressure difference data at all moments.

[0027] In one embodiment, the process of detecting the check performance of the one-way valve is as follows:

[0028] Calculate the difference distance between the pressure difference correction sequences under any two air pressures by using a time series similarity algorithm, and record it as a first difference distance; use the fusion value of all the first difference distances as the non-return performance of the one-way valve;

[0029] If the non-return performance of the one-way valve is greater than a preset first threshold value, the non-return performance of the one-way valve is abnormal; otherwise, the non-return performance of the one-way valve is normal.

[0030] In a second aspect, an embodiment of the present application also provides a one-way valve check performance detection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0031] The embodiments of the present application have at least the following beneficial effects:

[0032] The present application corrects the pressure difference of the one-way valve at each moment by changing the pressure difference between the air inlet and the air outlet of the one-way valve in a local time, thereby avoiding the problem of inaccurate data collection caused by the pressure sensor being affected by vibration noise during data collection, suppressing the influence of vibration noise on the pressure difference data, improving the accuracy of the pressure difference data at both ends of the one-way valve, and thus improving the accuracy of the one-way valve check performance detection;

[0033] The present application obtains the first and second check fluctuation sets of each local check sequence by classifying the data in the neighborhood according to the data mean value in the neighborhood of the air pressure difference at each moment, and constructs the local check fluctuation value based on the data discreteness in the first and second check fluctuation sets, thereby avoiding the problem of inaccurate calculation of the fluctuation state of the air pressure difference data due to the large difference between noise data and normal data; constructs the fluctuation deviation of the pressure difference sequence based on the data anomaly and the data discreteness of the local check fluctuation value, classifies the elements in the local check sequence based on the fluctuation deviation, obtains the replacement value of the central element of the local check sequence based on the classification result, thereby improving the denoising effect of the air pressure difference data; obtains the pressure difference correction sequence based on the sequence composed of the replacement values; performs one-way valve check performance detection based on the difference between the pressure difference correction sequences under all kinds of air pressures, thereby improving the accuracy of one-way valve check performance detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] 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.

[0035] Figure 1 A flowchart of a method for detecting the check performance of a one-way valve provided in one embodiment of the present application;

[0036] Figure 2 This is a schematic diagram of the installation of the one-way valve air pressure detection component;

[0037] Figure 3 The present invention is a schematic diagram of the specific steps of a one-way valve check performance detection method. DETAILED DESCRIPTION

[0038] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of a one-way valve check performance detection method and system proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0040] The specific scheme of a one-way valve check performance detection method and system provided by the present application is described in detail below with reference to the accompanying drawings.

[0041] See also Figure 1 , which shows a flow chart of a method for detecting the check performance of a one-way valve provided by an embodiment of the present application, the method comprising the following steps:

[0042] Step S1, collecting the inlet pressure data and the outlet pressure data of the one-way valve at each time under various air pressure conditions in an oscillating environment.

[0043] A vibration test bench is used to simulate the vibration environment of a rail transit vehicle during braking. A pressure sensor is then installed at the air inlet of the one-way valve. An air pump is then connected to the air inlet. Finally, a pressure sensor is connected to the air outlet of the one-way valve. The schematic diagram of component installation is shown in the figure. Figure 2 As shown, 1 is an air pump, 2 is a transmission pipeline, 3 is a pressure sensor, 4 is a one-way valve, 5 is the flow direction of the one-way valve, and 6 is a vibration test bench. For the air pump, five kinds of air pressures of 0.3Mpa, 0.4Mpa, 0.5Mpa, 0.6Mpa, and 0.7Mpa are used for testing. First, input gas to the one-way valve, and the pressure test time of each gas is 30s. The frequency of pressure sensor acquisition is 100Hz. The collected pressure data is preprocessed. The pressure data collected by the pressure sensor may have data loss. This application uses linear interpolation to complete the lost data.

[0044] Taking the test under any air pressure condition as an example, the pressure data of the inlet and outlet of the one-way valve are analyzed in steps S2-S4.

[0045] Step S2, constructing a pressure difference sequence based on the pressure difference at each moment; in the pressure difference sequence, constructing a local non-return sequence of each element based on the neighborhood data of each element.

[0046] (1) A one-way valve only allows fluid to enter from the air inlet and exit from the air outlet, preventing the fluid from flowing in the opposite direction. The check performance of a one-way valve refers to its ability to prevent the reverse flow of fluid. A one-way valve with good check performance has the same amount of gas flow through the one-way valve at the air inlet and the air outlet at the same time, ignoring the time delay of the gas flowing inside the one-way valve, so that the gas pressure at both ends of the one-way valve is the same at the same time. The difference in pressure data obtained by the pressure sensors at both ends of the one-way valve can show whether there is backflow or leakage of gas in the one-way valve. Therefore, the pressure difference of the gas passing through the one-way valve at each moment is calculated based on the air inlet pressure data and the air outlet pressure data at each moment, and the expression is:

[0047] , where It represents the pressure difference when the gas passes through the one-way valve at the i-th moment, represents the inlet pressure of the one-way valve at the i-th moment, Represents the outlet pressure of the one-way valve at the i-th moment.

[0048] The greater the pressure difference between the inlet and outlet ends of the one-way valve, the greater the possibility that there is a problem with the non-return performance of the one-way valve at that moment.

[0049] (2) Arrange the pressure differences at all times in ascending time order to obtain a pressure difference sequence.

[0050] (3) Construct a neighborhood window of each element with each element in the pressure difference sequence as the center. It should be noted that in the embodiment of the present application, the size of the neighborhood window is set to 1*9. As other implementation methods, the implementer can decide the size of the neighborhood window according to the actual situation. For positions with less than 9 elements in the window, linear interpolation is used to fill the insufficient part. Among them, the linear interpolation method is a well-known technology, and the specific process is not repeated here. The sequence composed of all data in the neighborhood window of each element is recorded as a local non-return sequence.

[0051] Step S3, classifying the data size in the local stop sequence of each element to obtain the first and second stop fluctuation sets of each local stop sequence, and obtaining the local stop fluctuation value of each local stop sequence based on the degree of data discreteness in the first and second stop fluctuation sets.

[0052] There are two situations in testing the check performance of a one-way valve. One is that the one-way valve has problems before the test; the other is that problems occur during the test. For example, when the one-way valve is vibrating in a simulated rail vehicle braking scenario, the rubber sealing ring of the one-way valve is not firmly fixed, resulting in a poor sealing of the rubber sealing ring during the test, which causes problems with the check performance of the one-way valve.

[0053] When the one-way valve to be tested has the first problem, the pressure difference of the one-way valve is generally larger than that of the one-way valve with good non-return performance; when the one-way valve to be tested has the second problem, the pressure difference of the one-way valve changes with time and shows a state of first normal and then abnormal. However, since the one-way valve and the pressure sensor are in a vibrating environment, the pressure sensor generates a lot of vibration noise when measuring the pressure between the inlet and outlet of the one-way valve. When the non-return performance test of the one-way valve is identified by the pressure difference, the vibration noise will affect the test results.

[0054] Therefore, it is necessary to eliminate the influence of noise data on the pressure difference data. Considering the situation that the check performance of the one-way valve has problems during the measurement of the check performance, the pressure difference has a large fluctuation, so that the fluctuation is identified as noise:

[0055] (1) Since the vibration noise caused by the vibration of the one-way valve has an outlier property, it will cause the data mean to deviate from the normal range. The deviation of the mean can make the mean used as a segmentation threshold to segment the data into normal range data and abnormal range data. After the segmentation, the calculated volatility will return to the normal data volatility. Therefore, for each element in the pressure difference sequence, that is, the pressure difference data at each moment, the mean of all data in the local check sequence of the element is calculated and recorded as the first mean; the set of data greater than the first mean in the local check sequence of the element is recorded as the first check fluctuation set, and the set of data less than or equal to the first mean is recorded as the second check fluctuation set.

[0056] (2) Calculating the local stop-return fluctuation value of each element based on the first stop-return fluctuation set and the second stop-return fluctuation set of each element:

[0057] For each element in the pressure difference sequence, calculate the mean of all data in the first non-return fluctuation set of the element, recorded as the second mean;

[0058] Calculate the difference between each data in the first stop fluctuation set of the element and the second mean, and record it as the first difference;

[0059] Using the fused value of all the first differences of the element as the first non-return fluctuation value of the local non-return sequence of the element;

[0060] Based on the second stop fluctuation set of the element, the second stop fluctuation value of the local stop fluctuation sequence of the element is calculated in the same way as the first stop fluctuation value is obtained;

[0061] The fusion value of the first stop-return fluctuation value and the second stop-return fluctuation value of the local stop-return sequence of the element is used as the local stop-return fluctuation value of the element.

[0062] It should be noted that the fusion described in this application is to combine multiple variables, which can be specifically addition, multiplication, etc. The specific fusion method can be determined according to actual conditions during the application process, and this application does not impose any special restrictions.

[0063] Preferably, in an embodiment of the present application, the first difference may be the absolute value of the difference between each data in the first stop fluctuation set of the element and the second mean value; the first stop fluctuation value may be the average value of all the first differences of the element; the local stop fluctuation value may be the average value of the first stop fluctuation value and the second stop fluctuation value of the local stop sequence of the element;

[0064] In other embodiments of the present application, the first difference may be the square of the difference between each data in the first stop-return fluctuation set of the element and the second mean; the first stop-return fluctuation value may be the sum of all the first differences of the element; the local stop-return fluctuation value may be the square root of the product of the first stop-return fluctuation value and the second stop-return fluctuation value of the local stop-return sequence of the element.

[0065] When there is noise in the local check sequence, the mean of the local check sequence can divide the elements in the local check sequence into two categories, one of which is normal elements and the other is abnormal elements. For the pressure difference of the one-way valve of rail transit, the fluctuation characteristics between normal elements are small, while the appearance of noise data is usually one data, which makes the fluctuation characteristics of the noise data small, thus making the first check fluctuation value and the second check fluctuation value of the local check sequence smaller, thereby making the local check fluctuation value of the local check sequence smaller.

[0066] Step S4, constructing the fluctuation deviation of the pressure difference sequence based on the data anomaly and data discreteness of the local check fluctuation value; classifying the elements in the local check sequence based on the fluctuation deviation, and obtaining the replacement value of the central element of the local check sequence based on the classification result.

[0067] (1) Furthermore, the local non-return fluctuation value of the pressure difference data at all times is used as the input of the LOF anomaly detection algorithm (Local outlier factor), the neighborhood parameter area is set to 10, and the output is the local anomaly factor of each local non-return fluctuation value.

[0068] It is understandable that for the anomaly detection of local stop fluctuation values, the present application only provides one anomaly detection method. There are many existing anomaly detection methods, and implementers may also use other anomaly detection algorithms to perform anomaly detection on local stop fluctuation values. The present application does not make any specific restrictions.

[0069] The local check fluctuation value can represent the local fluctuation characteristics of the pressure difference after the data is locally segmented. The local abnormal factor can effectively identify abnormal data. The larger the local abnormal factor of the local check fluctuation value, the more abnormal the data is, and the greater the impact of the local check fluctuation value on the track vibration.

[0070] (2) The orbital vibration influence of the pressure difference sequence is calculated by the local check fluctuation value and its local abnormal factor. The expression is:

[0071] , where F represents the orbital vibration influence of the pressure difference sequence; SE represents the discrete coefficient of the local abnormal factor of the local non-return fluctuation value of all elements in the pressure difference sequence; Represents the mean of the local stop fluctuation values ​​of all elements in the pressure difference series.

[0072] The greater the influence of orbital vibration on the pressure difference sequence, the more abnormal values ​​there are in the local check fluctuation values, the larger the mean of all local check fluctuation values, and the larger the discrete coefficient of the local abnormal factor of the local check fluctuation value, thereby causing the value of the orbital vibration influence degree F of the calculated pressure difference sequence to be larger.

[0073] (3) Furthermore, the fluctuation deviation of the pressure difference sequence is calculated based on the orbital vibration influence of the pressure difference sequence:

[0074] , where R represents the fluctuation deviation of the pressure difference sequence; F represents the orbital vibration influence of the pressure difference sequence; Represents the standard deviation of the local stop fluctuation values ​​of all elements in the pressure difference series.

[0075] When the fluctuation characteristics of all pressure differences in their local area are stronger, the value of the local non-return fluctuation value is larger, making the standard deviation of all local non-return fluctuation values ​​larger; the stronger the fluctuation, the more abnormal data, so the orbital vibration influence F of the pressure difference sequence is larger, resulting in a larger value of the fluctuation deviation R of the pressure difference sequence. Therefore, when using the fluctuation deviation R, the fluctuation data with the same characteristics can be classified into the same category, and the data can be better denoised.

[0076] (4) For the local check sequence of pressure difference data at each moment, calculate the absolute value of the difference between any two elements in the local check sequence, which is recorded as the first absolute value of the difference; if the absolute value of the difference between any two elements is less than or equal to the fluctuation deviation of the pressure difference sequence, the two elements are classified into the same group; merge the groups with the same elements, and count the number of groups finally obtained;

[0077] The number of elements in the local check sequence of the pressure difference data at this moment is recorded as n. If the local check sequence of the pressure difference data at this moment is divided into n groups or one group, it means that the elements in the local check sequence of the pressure difference data at this moment have the same fluctuation characteristics or the fluctuation characteristics of each element are different. The pressure difference data at this moment can represent the fluctuation characteristics of the position, so the pressure difference data at this moment itself is used as the replacement value at this moment;

[0078] If the local check sequence of the pressure difference data at that moment is not divided into n groups or one group, then the group with the largest number of elements among the divided groups is selected. This is because the group with the largest number of elements is the group in which normal data exists, and can represent the main fluctuation characteristics of the local check sequence of the pressure difference data at that moment. Therefore, the mean of all elements in the group with the largest number of elements is calculated as the replacement value of the pressure difference data at that moment.

[0079] Step S5, obtaining a pressure difference correction sequence based on the sequence composed of the replacement values; and performing a non-return performance test of the one-way valve based on the difference between the pressure difference correction sequences under all kinds of air pressures.

[0080] The replacement values ​​of the pressure difference data at each moment are used to replace the corresponding pressure difference data in the pressure difference sequence, and the replaced pressure difference sequence is recorded as a pressure difference correction sequence.

[0081] The DTW distance between the pressure difference correction sequences under any two air pressures is calculated by the dynamic time warping algorithm and recorded as the first difference distance. The dynamic time warping algorithm is a well-known technology and the specific process will not be repeated here. It should be noted that for the calculation of the similarity between the pressure difference correction sequences, this application only provides a time series similarity calculation method. There are many existing time series similarity algorithms. Implementers can also use other time series similarity algorithms to calculate the similarity between the pressure difference correction sequences. This application does not make specific restrictions.

[0082] The fusion value of all the first difference distances is used as the non-return performance of the one-way valve.

[0083] Preferably, in one embodiment of the present application, the non-return performance of the one-way valve may be an average value of all the first difference distances;

[0084] In other embodiments of the present application, the non-return performance of the one-way valve may be the sum of all the first difference distances.

[0085] If the check performance of the one-way valve is smaller, it means that the check performance of the one-way valve is better. This is because in an ideal state, the pressure difference at both ends of the one-way valve under one air pressure is 0, so that all elements in the pressure difference correction sequence of the air pressure are 0. Therefore, in an ideal state, the dtw value of the pressure difference correction sequence under two air pressures is 0, so the value of the check performance Y of the one-way valve is 0.

[0086] For the above results, a first threshold is set. Preferably, in one embodiment of the present application, the first threshold is set to 1. In other embodiments of the present application, the implementer can set the value of the first threshold according to the actual situation. If the non-return performance of the one-way valve is greater than the first threshold, it means that the non-return performance of the one-way valve is abnormal; if it is less than or equal to the first threshold, it means that the non-return performance of the one-way valve in the vibration environment of rail transit is normal.

[0087] The specific steps of the above method are shown in the schematic diagram Figure 3 shown.

[0088] Based on the same inventive concept as the above method, an embodiment of the present application also provides a one-way valve check performance detection system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned one-way valve check performance detection methods are implemented.

[0089] In summary, the embodiment of the present application provides a one-way valve check performance detection method, which corrects the pressure difference of the one-way valve at each moment by the change of the pressure difference between the air inlet and the air outlet of the one-way valve in a local time, thereby avoiding the problem of inaccurate data collection caused by the pressure sensor being affected by vibration noise during data collection, suppressing the influence of vibration noise on pressure difference data, improving the accuracy of the pressure difference data at both ends of the one-way valve, and thus improving the accuracy of the one-way valve check performance detection;

[0090] The present application obtains the first and second check fluctuation sets of each local check sequence by classifying the data in the neighborhood according to the data mean value in the neighborhood of the air pressure difference at each moment, and constructs the local check fluctuation value based on the data discreteness in the first and second check fluctuation sets, thereby avoiding the problem of inaccurate calculation of the fluctuation state of the air pressure difference data due to the large difference between noise data and normal data; constructs the fluctuation deviation of the pressure difference sequence based on the data anomaly and the data discreteness of the local check fluctuation value, classifies the elements in the local check sequence based on the fluctuation deviation, obtains the replacement value of the central element of the local check sequence based on the classification result, thereby improving the denoising effect of the air pressure difference data; obtains the pressure difference correction sequence based on the sequence composed of the replacement values; performs one-way valve check performance detection based on the difference between the pressure difference correction sequences under all kinds of air pressures, thereby improving the accuracy of one-way valve check performance detection.

[0091] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0093] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for detecting the non-return performance of a one-way valve, characterized in that: The method comprises the following steps: Collect the pressure data of the inlet and outlet of the one-way valve at each time under various air pressure conditions in the oscillating environment; Under any air pressure, the difference between the pressure data of the air inlet and the air outlet at each moment is taken as the pressure difference at each moment; in the pressure difference sequence composed of the pressure differences at all moments, the sequence composed of all data in the neighborhood window centered on each element is taken as the local non-return sequence of each element; Classifying the data size in the local check sequence of each element to obtain the first and second check fluctuation sets of each local check sequence, and obtaining the local check fluctuation value of each local check sequence based on the degree of data dispersion in the first and second check fluctuation sets; Based on the data anomalies of the local check fluctuation values, the orbital vibration influence of the pressure difference sequence is constructed, and the fluctuation deviation of the pressure difference sequence is constructed in combination with the data discreteness of all local check fluctuation values ​​in the pressure difference sequence; based on the fluctuation deviation, the elements in the local check sequence are classified, and the replacement value of the central element of the local check sequence is obtained based on the classification result; Based on the sequence composed of the replacement values, a pressure difference correction sequence is obtained; based on the difference between the pressure difference correction sequences under all kinds of air pressure, a one-way valve non-return performance test is performed; The process of obtaining the first and second non-return fluctuation sets is as follows: The mean of all data in each local check sequence is recorded as the first mean; in each local check sequence, the set consisting of data greater than the first mean is recorded as the first check fluctuation set, and the set consisting of data less than or equal to the first mean is recorded as the second check fluctuation set; The process of obtaining the orbit vibration influence is as follows: All the local check-return fluctuation values ​​in the pressure difference sequence are used as the input of the anomaly detection algorithm, and the output is the local anomaly factor of each local check-return fluctuation value; the orbital vibration influence of the pressure difference sequence is recorded as F, and the calculation expression of F is: , where The discrete coefficient of the local anomaly factor representing the local stop fluctuation value corresponding to all elements in the pressure difference sequence, Represents the mean of the local stop fluctuation values ​​corresponding to all elements in the pressure difference series.

2. A one-way valve non-return performance detection method as claimed in claim 1, characterized in that: The process of obtaining the local non-return fluctuation value is as follows: Record the mean of all data in the first stop-return fluctuation set as the second mean, calculate the difference between each data in the first stop-return fluctuation set and the second mean, and record it as the first difference; and use the fusion value of all the first differences as the first stop-return fluctuation value of the local stop-return sequence; Based on the second stop-return fluctuation set, the second stop-return fluctuation value of the local stop-return sequence is calculated using the same acquisition method as the first stop-return fluctuation value; the fusion value of the first stop-return fluctuation value and the second stop-return fluctuation value is used as the local stop-return fluctuation value of the local stop-return sequence.

3. A one-way valve non-return performance detection method as claimed in claim 1, characterized in that: The calculation expression of the fluctuation deviation is: , where R represents the fluctuation deviation of the pressure difference sequence, and F represents the orbital vibration influence of the pressure difference sequence. Represents the standard deviation of the local stop fluctuation values ​​corresponding to all elements in the pressure difference series.

4. A one-way valve non-return performance detection method as claimed in claim 1, characterized in that: The process of obtaining the replacement value is as follows: Classify the elements in the local non-return sequence based on the fluctuation deviation to obtain the number of groups into which the elements in the local non-return sequence are divided; The number of elements in the local check sequence is denoted as n. If the local check sequence is divided into n groups or one group, the replacement value of the central element of the local check sequence is the central element of the local check sequence itself; otherwise, the group with the largest number of elements in the divided groups is selected, and the mean of all elements in the group with the largest number of elements is calculated as the replacement value of the central element of the local check sequence.

5. A one-way valve non-return performance detection method as claimed in claim 4, characterized in that: The process of obtaining the number of groups is as follows: The absolute value of the difference between any two elements in the local check sequence is calculated and recorded as the first absolute value of the difference; if the first absolute value of the difference is less than or equal to the fluctuation deviation of the corresponding pressure difference sequence, the any two elements are classified into the same group; the groups with the same elements are merged, and the number of groups finally obtained is counted.

6. A one-way valve non-return performance detection method as claimed in claim 1, characterized in that: The pressure difference correction sequence is a sequence composed of replacement values ​​of pressure difference data at all times.

7. A one-way valve non-return performance detection method as claimed in claim 1, characterized in that: The process of the one-way valve non-return performance detection is as follows: Calculate the difference distance between the pressure difference correction sequences under any two air pressures by using a time series similarity algorithm, and record it as a first difference distance; use the fusion value of all the first difference distances as the non-return performance of the one-way valve; If the non-return performance of the one-way valve is greater than a preset first threshold value, the non-return performance of the one-way valve is abnormal; otherwise, the non-return performance of the one-way valve is normal.

8. A one-way valve non-return performance detection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images