An intelligent detection method, device and system for oil leakage of a hydraulic support cylinder

Abstract

The present application relates to the technical field of data processing, and specifically relates to an intelligent detection method, device and system for oil leakage of hydraulic support cylinders, which specifically includes: dividing data for changes in each parameter, regarding each parameter as a target parameter respectively, and determining corresponding time intervals according to the data division results of the target parameters; through the determined time intervals, the asynchronous response characteristics of the target parameter compared with other parameters in the face of different degrees of cylinder leakage can be accurately extracted; based on the asynchronous response characteristics and the current values of various parameters, oil leakage detection of hydraulic support cylinders is carried out; the accuracy of extracting the asynchronous response characteristics of each parameter for oil leakage of the cylinder is improved, the accuracy of the oil leakage detection result of the hydraulic support cylinder is improved, and the interference caused by different degrees of leakage to the intelligent detection of oil leakage of the cylinder is effectively avoided.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to an intelligent detection method, device, and system for oil leakage in hydraulic support cylinders. Background Art

[0002] As a key device commonly used in coal mining operations, hydraulic supports are widely used for roof support work in underground coal mines. It mainly relies on hydraulic cylinders to convert hydraulic energy into mechanical energy to effectively support the roof. However, in actual application scenarios, the coal mining environment is extremely harsh and complex, with variable factors such as temperature, humidity, and pressure, which cause the cylinders of hydraulic supports to frequently experience oil leakage problems during long-term use.

[0003] Once oil leakage occurs in the hydraulic support cylinder, it will have a serious impact on the normal operation of the equipment, not only significantly shortening the service life of the equipment, but even potentially causing equipment damage in extreme cases. Therefore, during the use of hydraulic supports, realizing intelligent detection of oil leakage in cylinders is of great significance for extending the service life of the equipment, ensuring coal mine safety production, and improving the mine operation environment.

[0004] Currently, for monitoring the sealing performance of cylinders during the use of hydraulic supports, sensors are generally used for data collection and detection. Among them, the relatively common detection method is the threshold judgment detection method. For example, in the "A Remote Wireless Control Method and System for Mining Equipment and Electronic Equipment" with the publication number CN117145551A, it is mentioned that the oil leakage of the hydraulic support cylinder is judged by collecting pressure and temperature thresholds. Although this method avoids the complex algorithm modeling process and is relatively easy to operate, due to the intricate working environment of the hydraulic support, it is extremely vulnerable to many interference factors during data collection. At the same time, the reasons for oil leakage in hydraulic support cylinders are diverse, and when leakage occurs, the characteristic changes of the monitoring data in the cylinder are extremely complex. Relying solely on the threshold judgment method while improving the detection efficiency may result in large errors, leading to generally low accuracy of the current intelligent detection for oil leakage in hydraulic support cylinders and being difficult to meet the actual production requirements. Summary of the Invention

[0005] To solve the above technical problems, the purpose of this application is to provide an intelligent detection method, device, and system for oil leakage in hydraulic support cylinders, and the specific technical solutions adopted are as follows:

[0006] In the first aspect, an embodiment of this application provides an intelligent detection method for oil leakage in a hydraulic support cylinder, and this method includes the following steps:

[0007] Real-time collect various parameter data of the cylinder, including pressure, temperature, flow rate, and piston rod displacement data, and construct various parameter sequences;

[0008] Take any one of the parameters as the target parameter, and divide the sequence through the data mutation situation in the target parameter sequence to obtain each subsequence of the target parameter sequence; obtain the time interval corresponding to each subsequence, and divide each of the other parameter sequences through each time interval to obtain each subsequence of each of the other parameter sequences.

[0009] Calculate the characteristic value of the change of each parameter in each time interval based on the data dispersion degree and data change trend in each subsequence; calculate the characteristic weight value of the change of each parameter in each time interval based on the data change smoothness degree in each subsequence.

[0010] Calculate the characteristic extraction result of the asynchronous response of the target parameter in each time interval based on the characteristic value and the characteristic weight value; calculate the first monitoring coefficient of the target parameter based on the characteristic extraction results of all time intervals.

[0011] Based on the first monitoring coefficient, combined with various parameters at the current moment, perform oil leakage detection on the hydraulic support cylinder.

[0012] In one embodiment, the process of obtaining each subsequence of the target parameter sequence is as follows: take the target parameter sequence as the input of the segmentation algorithm, and the output is each subsequence of the target parameter sequence.

[0013] In one embodiment, each subsequence of each of the other parameter sequences is the sequence of each of the other parameter sequences in each time interval.

[0014] In one embodiment, the process of obtaining the characteristic value of the change of each parameter in each time interval is as follows:

[0015] In each time interval, calculate the coefficient of variation of all data in the parameter subsequence, obtain the trend statistic of the parameter subsequence through the trend verification algorithm, and take the product of the coefficient of variation and the trend statistic as the characteristic value of the change of each parameter in the time interval.

[0016] In one embodiment, the process of obtaining the characteristic weight value of the change of each parameter in each time interval is as follows:

[0017] Obtain the first-order difference sequence of each parameter subsequence in each time interval, and take the normalized value of the entropy of all elements in the first-order difference sequence as the characteristic weight value of the change of each parameter in each time interval.

[0018] In one embodiment, the expression of the characteristic extraction result is:

[0019] , where represents the Feature extraction results of asynchronous responses within a time interval; and respectively represent the feature value and the feature weight of the k-th parameter within the k-th time interval; represents the number of parameter types.

[0020] In one embodiment, the process of obtaining the first monitoring coefficient of the target parameter is as follows:

[0021] For the time intervals divided from the target parameter sequence, the mean of the normalized values of the feature extraction results within all time intervals is used as the first monitoring coefficient of the target parameter.

[0022] In one embodiment, the detection of oil leakage in the hydraulic support cylinder is specifically as follows:

[0023] Set the response threshold and the abnormal threshold for each parameter; calculate the mean of the first monitoring coefficients of all types of parameters. If the mean of the first monitoring coefficients is greater than or equal to the preset response threshold, or the value of any parameter at the current moment is greater than or equal to the corresponding abnormal threshold, it is determined that the current hydraulic support cylinder has leaked.

[0024] Second, the embodiment of the present application also provides an intelligent detection device for oil leakage in a hydraulic support cylinder, including:

[0025] Data acquisition module: Real-time collect various parameter data of the cylinder, including pressure, temperature, flow rate, and piston rod displacement data, and construct various parameter sequences;

[0026] Data analysis module: Take any parameter as the target parameter, divide the sequence through the data mutation situation in the target parameter sequence to obtain each subsequence of the target parameter sequence; obtain the time intervals corresponding to each subsequence, and divide each other parameter sequence through each time interval to obtain each subsequence of each other parameter sequence;

[0027] Feature extraction module: Calculate the feature value of the change of each parameter within each time interval based on the data dispersion degree and the data change trend in each subsequence; calculate the feature weight of the change of each parameter within each time interval based on the data change smoothness degree in each subsequence;

[0028] Data detection module: Calculate the feature extraction results of the asynchronous response of the target parameter within each time interval based on the feature value and the feature weight; calculate the first monitoring coefficient of the target parameter based on the feature extraction results of all time intervals;

[0029] Oil leakage monitoring module: Based on the first monitoring coefficient, combined with various parameters at the current moment, perform oil leakage detection on the hydraulic support cylinder.

[0030] In a third aspect, an embodiment of the present application further provides an intelligent detection system for oil leakage of a hydraulic support cylinder, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method described in the first aspect above are implemented.

[0031] The embodiment of the present application has at least the following beneficial effects:

[0032] When oil leakage occurs in the hydraulic support cylinder, different degrees of leakage will cause different changes in each parameter; based on this, the present application divides the data of the change of each parameter, regards each parameter as a target parameter respectively, and determines the corresponding time interval according to the data division result of the target parameter; through the determined time interval, the asynchronous response characteristics of the target parameter compared with other parameters in the face of different degrees of cylinder leakage can be accurately extracted; different from the traditional analysis methods of overall and local data feature changes, the present application fully considers the complexity of the associated changes between parameters in the case of different degrees of oil leakage in the cylinder; in this way, the asynchronous response characteristics of each parameter facing oil leakage in the cylinder can be extracted more accurately, thereby significantly improving the accuracy of the detection result of oil leakage in the hydraulic support cylinder and effectively avoiding the interference caused by different degrees of leakage to the intelligent detection of oil leakage in the cylinder. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0034] Figure 1 It is a flowchart of the steps of an intelligent detection method for oil leakage of a hydraulic support cylinder provided by an embodiment of the present application;

[0035] Figure 2 It is a schematic diagram of the acquisition process of the characteristic value of parameter change;

[0036] Figure 3 It is a schematic diagram of the structure of an intelligent detection device for oil leakage of a hydraulic support cylinder. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] In order to further elaborate on the technical means and effects adopted by the present application to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, an intelligent detection method, device, and system for oil leakage in a hydraulic support cylinder according to the present application, including its specific implementation manner, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0039] The following specifically describes the specific solutions of an intelligent detection method, device, and system for oil leakage in a hydraulic support cylinder provided by the present application in conjunction with the accompanying drawings.

[0040] Please refer to Figure 1 , which shows a flowchart of the steps of an intelligent detection method for oil leakage in a hydraulic support cylinder provided by an embodiment of the present application. The method includes the following steps:

[0041] Step S1, collect various parameter data of the cylinder in real time, including pressure, temperature, flow rate, and piston rod displacement data, and construct various parameter sequences.

[0042] Automatically collect data through pressure sensors, temperature sensors, flow sensors, and displacement sensors respectively installed at key parts of the hydraulic support cylinder, including the cylinder inlet and outlet, piston seal, and cylinder barrel position; specifically, collect the pressure, temperature, flow rate, and piston rod displacement data of the cylinder in real time at a preset time interval (set to collect data once per second in this application). Considering that the complex electromagnetic environment in the coal mine may interfere with data collection, sensors with strong anti-interference ability are selected, and shielded cables are used for data transmission to ensure the accuracy and stability of the collected data and provide a reliable data basis for subsequent analysis work.

[0043] Sort each preprocessed parameter in the order of collection time to form a sequence, and obtain each parameter sequence, namely the pressure sequence, temperature sequence, flow rate sequence, and piston rod displacement sequence respectively.

[0044] Step S2, take any one of the parameters as the target parameter, divide the target parameter sequence through the data mutation situation in the target parameter sequence to obtain each subsequence of the target parameter sequence; obtain the time interval corresponding to each subsequence, and divide each of the other parameter sequences through each time interval to obtain each subsequence of each of the other parameter sequences.

[0045] Due to the extremely complex working environment of hydraulic supports, during actual operation, they are extremely vulnerable to various environmental interference factors, resulting in significant noise in the collected data. Therefore, it is necessary to preprocess the collected data. Specifically, the collected data is used as input, and the Kalman filter algorithm is applied in the data acquisition and preprocessing module to perform noise reduction processing on the pressure, temperature, flow rate, and piston rod displacement data respectively, so as to obtain more accurate and reliable denoised data.

[0046] When there is a leakage in the hydraulic cylinder of a hydraulic support, different degrees of leakage will cause different parameter change characteristics. If it is a minor oil leak, the pressure usually shows a slow downward trend and is difficult to detect within a certain period of time. Once the pressure changes, the support effect of the hydraulic support on the roof will also be affected accordingly. When the support bears the roof pressure, the piston may show a slow retraction phenomenon, which will in turn cause a change in the piston displacement. In addition, the oil leak will increase the internal leakage of the hydraulic system, and the friction of the oil during circulation in the system will intensify, resulting in an increase in the oil temperature. Moreover, due to factors such as unstable pressure in the system, additional friction and impact may occur in the components within the system, further promoting the rise in the oil temperature. As the leakage situation continues to develop, abnormal fluctuations will also occur in the inlet or outlet flow rate of the hydraulic cylinder of the hydraulic support. Due to the change in the flow rate within the cylinder, the extension speed of the piston rod will slow down or even fail to extend normally.

[0047] If there is a serious leakage in the hydraulic cylinder of a hydraulic support, during actual monitoring, drastic changes will occur in the pressure, flow rate, temperature, and displacement of the piston. In this case, using the threshold judgment method to intelligently monitor the oil leakage situation of the hydraulic cylinder of the hydraulic support can obtain detection results more efficiently and accurately. However, during actual use, when there is a minor leakage in the hydraulic support, there are two problems when using the threshold judgment method for detection. On the one hand, the data changes caused by minor leakage are relatively slow. Relying solely on the set monitoring data threshold for judgment cannot detect the leakage situation in a timely and effective manner. On the other hand, if the monitoring data threshold is set smaller for optimization and adjustment, due to the influence of interference factors, minor interference changes in the data may trigger the threshold alarm, thereby reducing the accuracy of the oil leakage detection of the hydraulic cylinder of the hydraulic support.

[0048] In order to be able to judge in a timely and effective manner whether there is an oil leak in the hydraulic cylinder of a hydraulic support, this application conducts an in-depth analysis of the change characteristics among various detection parameters when the hydraulic cylinder of the hydraulic support leaks in different degrees during the actual intelligent detection process. The specific process is as follows:

[0049] (1) First, considering that during the operation of the hydraulic support, there are differences in the changes of various parameters for detecting oil leakage in the cylinder over time. Take any one parameter as the target parameter, and use the target parameter sequence as the input of the Bernaola Galvan segmentation algorithm to divide the target parameter sequence and obtain each subsequence of the target parameter sequence. Generally, when the cylinder leaks, due to different usage conditions of the hydraulic support, there will be different degrees of lag differences in the time periods when the parameters change during the actual data acquisition process. Therefore, in view of the complexity of the oil leakage situation in the cylinder, for each parameter in the intelligent detection process of cylinder oil leakage, based on the division results of the corresponding parameter sequence, determine the time interval corresponding to each subsequence, and divide the other parameter sequences based on this time interval. The purpose of doing this is to consider that under normal circumstances, in the face of changes in the state of the hydraulic support, the changes of various parameters are generally synchronous. Therefore, for the changes of the current parameter in different time periods, perform asynchronous response analysis on other parameters in the same time period. Among them, the Bernaola Galvan segmentation algorithm is a well-known technology, and the specific process will not be elaborated.

[0050] It should be noted that for the division of the target parameter sequence, this application only provides one segmentation method. There are many existing segmentation methods, and implementers can also use other segmentation methods to divide the target parameter sequence. This application does not make specific restrictions.

[0051] (2) Taking any one parameter as an example, use this parameter as the target parameter. For each subsequence of the target parameter sequence, take the interval between the first data acquisition moment and the last data acquisition moment in this subsequence as the time interval of this subsequence; further, for each parameter sequence other than the target parameter sequence, take the sequence of other parameter sequences within each time interval as each subsequence of other parameter sequences;

[0052] Step S3, calculate the characteristic value of the change of each parameter within each time interval based on the data dispersion degree and data change trend in each subsequence; calculate the characteristic weight value of the change of each parameter within each time interval based on the data change smoothness degree in each subsequence.

[0053] Further, within each time interval, calculate the coefficient of variation of all data in each parameter subsequence, and obtain the trend statistic of each parameter subsequence through the MK trend verification algorithm. Calculate the product of the coefficient of variation of each subsequence and the trend statistic, and take this product as the characteristic value of the change of each parameter within this time interval. This characteristic value can reflect the change characteristics of each parameter data within each time interval determined by the target parameter. Among them, the coefficient of variation and the MK trend verification algorithm are both well-known technologies, and the specific process will not be elaborated.

[0054] Considering that within each time interval, the significance of data changes of different parameters for the oil leakage situation of the oil cylinder is different; for example, when slight leakage occurs, the impact on the stability of the flow rate is relatively large. Then, within the current time period, compared with other parameters, the flow rate data characteristics can more accurately reflect the oil leakage situation of the oil cylinder. Therefore, obtain the first-order difference sequence of the parameter sequences of various parameters within each time interval, and calculate the entropy of all elements in this first-order difference sequence. The larger the entropy value, the worse the data change smoothness of the current parameter data within this time interval, and the more significant the parameter response change characteristics caused by the leakage situation. Further, use the Softmax function to normalize the entropy calculated for all parameters within this time interval, and use the obtained normalization result as the characteristic weight value of the data change of each parameter within each time interval. The larger the characteristic weight value, the greater the significance of the asynchronous characteristics of the parameter data change for the oil leakage situation of the oil cylinder. Among them, the Softmax function is a well-known technology, and the specific process will not be elaborated here.

[0055] Step S4, calculate the feature extraction result of the asynchronous response of the target parameter within each time interval based on the eigenvalue and the feature weight value; calculate the first monitoring coefficient of the target parameter based on the feature extraction results of all time intervals.

[0056] After the above analysis, for the time interval division result of the target parameter in the intelligent detection process of hydraulic cylinder oil leakage, perform feature analysis on the asynchronous difference of each parameter compared with the target parameter change in different time intervals. Specifically, for each time interval divided from the target parameter sequence, according to the eigenvalue and the feature weight value corresponding to each parameter data within each time interval, calculate the feature extraction result of the asynchronous response for the oil leakage impact of the oil cylinder within each time interval, and the expression is:

[0057] , where represents the feature extraction result of the asynchronous response for the oil leakage impact of the oil cylinder within the th time interval of the target parameter; and respectively represent the eigenvalue and the feature weight value of the th time interval of the th parameter data; represents the number of parameter types.

[0058] Based on the asynchronous response feature extraction results for the oil leakage of the hydraulic cylinder in each of the above time intervals, comprehensively evaluate the asynchronous response features of the target parameters in the intelligent detection process of hydraulic cylinder oil leakage, and construct the first monitoring coefficient. Specifically, for the time intervals divided for the target parameter sequence, use the feature extraction results in all time intervals as the input of the Z-score normalization algorithm, normalize all the feature extraction results, then calculate the mean of the normalization results, and use this mean as the first monitoring coefficient for the intelligent detection of oil leakage of the hydraulic cylinder of the target parameter.

[0059] Step S5, based on the first monitoring coefficient, combined with various parameters at the current moment, conduct the detection of oil leakage of the hydraulic support cylinder.

[0060] After the above processing, for the situation where there is a slight leakage in the hydraulic support cylinder, although each parameter data may show the characteristics of slow change, in the actual operation process, due to the complex operation of the hydraulic support and the significant asynchronous change characteristics of the correlation between various parameters caused by oil leakage. This application conducts a comparative analysis for each time interval of parameter change, and based on the change time interval of one parameter, that is, the target parameter, analyzes its asynchronous response stage change characteristics for the intelligent detection of oil leakage of the hydraulic cylinder. Different from the existing overall and local data feature change analysis methods, this application fully combines the complexity of the correlation change between different parameters under different degrees of oil leakage of the hydraulic cylinder, accurately extracts the asynchronous response features of each parameter for oil leakage of the hydraulic cylinder, and then obtains the first monitoring coefficient to accurately reflect the data change characteristics under different degrees of leakage.

[0061] Calculate the mean of the first monitoring coefficients of all parameters, and set the response threshold for the slight leakage situation; since the significance of the asynchronous response features of different parameters in the case of minor leakage increases with time, the value range of the response threshold is 0.3 - 0.6. In order to further improve the detection accuracy of oil leakage of the hydraulic support cylinder, this application sets the response threshold to 0.3. If in the intelligent monitoring process of the hydraulic support cylinder, this mean is greater than or equal to the response threshold, it indicates that the hydraulic support cylinder has leaked.

[0062] Furthermore, use the standard lines of various parameters required by the engineering during the operation of the hydraulic support cylinder as the abnormal thresholds of various parameters, and use the pressure, flow, temperature, and piston rod displacement data collected at the current moment as the second monitoring coefficient. If any one of the second monitoring coefficients is greater than or equal to the corresponding abnormal threshold, it indicates that the hydraulic cylinder may have leaked and needs to be repaired in time. It should be noted that when making a judgment through the first monitoring coefficient or the second monitoring coefficient above, if the judgment result of any one of the monitoring coefficients is that the hydraulic cylinder has leaked, it is determined that the current hydraulic support cylinder has leaked.

[0063] The schematic diagram of the process for obtaining the characteristic values of parameter changes is as Figure 2 shown.

[0064] Please refer to Figure 3 , Figure 3 which is the schematic structural diagram of an intelligent detection device for hydraulic support cylinder oil leakage provided by an embodiment of the present application. In this embodiment, each unit included in the terminal is used to execute each step in the corresponding embodiment of an intelligent detection method for hydraulic support cylinder oil leakage. Refer to Figure 3 , the intelligent detection device includes:

[0065] Data acquisition module: Real-time collect various parameter data of the cylinder, including pressure, temperature, flow rate, and piston rod displacement data, and construct various parameter sequences;

[0066] Data analysis module: Take any one of the parameters as the target parameter, divide the sequence through the data mutation situation in the target parameter sequence to obtain each subsequence of the target parameter sequence; obtain the time interval corresponding to each subsequence, and divide each other parameter sequence through each time interval to obtain each subsequence of each other parameter sequence;

[0067] Feature extraction module: Calculate the characteristic values of each parameter change in each time interval based on the data dispersion degree and data change trend in each subsequence; calculate the characteristic weight values of each parameter change in each time interval based on the data change smoothness degree in each subsequence;

[0068] Data detection module: Calculate the characteristic extraction result of the asynchronous response of the target parameter in each time interval based on the characteristic values and the characteristic weight values; calculate the first monitoring coefficient of the target parameter based on the characteristic extraction results of all time intervals;

[0069] Oil leakage monitoring module: Based on the first monitoring coefficient, combine various parameters at the current moment to perform oil leakage detection on the hydraulic support cylinder.

[0070] Based on the same inventive concept as the above method, an embodiment of the present application also provides an intelligent detection system for hydraulic support cylinder oil leakage, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above methods of an intelligent detection method for hydraulic support cylinder oil leakage.

[0071] In summary, the embodiment of the present application provides an intelligent detection method for oil leakage of a hydraulic support cylinder. When the hydraulic support cylinder leaks, different leakage degrees will cause different changes in each parameter. Based on this, the present application divides the data of the change of each parameter, regards each parameter as a target parameter respectively, and determines the corresponding time interval according to the data division result of the target parameter. Through the determined time interval, the asynchronous response characteristics of the target parameter compared with other parameters in the face of different degrees of cylinder leakage can be accurately extracted. Different from the traditional analysis methods of overall and local data feature changes, the present application fully considers the complexity of the associated changes between parameters in the case of different degrees of cylinder oil leakage. In this way, the asynchronous response characteristics of each parameter facing cylinder oil leakage can be more accurately extracted, thereby significantly improving the accuracy of the detection result of cylinder oil leakage of the hydraulic support and effectively avoiding the interference caused by different degrees of leakage to the intelligent detection of cylinder oil leakage.

[0072] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above specific embodiments of the present application have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] Each embodiment in the present application is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0074] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent detection method for oil leakage of hydraulic support cylinder, characterized in that: The method comprises the following steps: Collect various parameter data of the oil cylinder in real time, including pressure, temperature, flow and piston rod displacement data, and construct various parameter sequences; Take any parameter as the target parameter, divide the sequence according to the data mutation in the target parameter sequence, and obtain each subsequence of the target parameter sequence; obtain the time interval corresponding to each subsequence, divide the other parameter sequences according to each time interval, and obtain each subsequence of the other parameter sequences; In each time interval, the coefficient of variation of all data in each parameter subsequence is calculated, and the trend statistic of each parameter subsequence is obtained through a trend verification algorithm, and the product of the coefficient of variation and the trend statistic is used as the characteristic value of each parameter change in the time interval; the first-order difference sequence of each parameter subsequence in each time interval is obtained, and the normalized value of the entropy of all elements in the first-order difference sequence is used as the characteristic weight of each parameter change in each time interval; Calculate the target parameter The feature extraction result of the asynchronous response in the time interval is recorded as , The expression is: , where and Respectively represent In the time interval The characteristic value and the characteristic weight of the parameter; Indicates the number of parameter types; for the time interval divided by the target parameter sequence, the normalized mean value of the feature extraction results in all time intervals is used as the first monitoring coefficient of the target parameter; Based on the first monitoring coefficient and in combination with various parameters at the current moment, the hydraulic support cylinder oil leakage detection is performed.

2. The intelligent detection method for oil leakage of hydraulic support cylinder according to claim 1, characterized in that: The process of acquiring each subsequence of the target parameter sequence is as follows: taking the target parameter sequence as the input of the segmentation algorithm, and outputting each subsequence of the target parameter sequence.

3. The intelligent detection method for oil leakage of hydraulic support cylinder according to claim 1, characterized in that: Each subsequence of the other parameter sequences is a sequence of the other parameter sequences in each time interval.

4. The intelligent detection method for oil leakage of hydraulic support cylinder according to claim 1, characterized in that: The oil leakage detection of the hydraulic support cylinder is specifically performed as follows: Set response thresholds and abnormal thresholds for various parameters; calculate the first monitoring coefficient mean of all parameters. If the first monitoring coefficient mean is greater than or equal to the preset response threshold, or if the value of any parameter at the current moment is greater than or equal to the corresponding abnormal threshold, it is determined that a leak has occurred in the current hydraulic support cylinder.

5. An intelligent detection device for oil leakage of hydraulic support cylinder, realizing the method as claimed in claim 1, characterized in that: The device comprises: Data acquisition module: real-time collection of various parameter data of the oil cylinder, including pressure, temperature, flow and piston rod displacement data, to build various parameter sequences; Data analysis module: taking any parameter as the target parameter, dividing the sequence according to the data mutation in the target parameter sequence to obtain each subsequence of the target parameter sequence; obtaining the time interval corresponding to each subsequence, dividing the other parameter sequences according to each time interval, and obtaining each subsequence of the other parameter sequences; Feature extraction module: Calculate the feature value of each parameter change in each time interval based on the data dispersion degree and data change trend in each subsequence; Calculate the feature weight of each parameter change in each time interval based on the stability of data change in each subsequence; Data detection module: calculates the feature extraction result of the asynchronous response of the target parameter in each time interval based on the feature value and the feature weight; calculates the first monitoring coefficient of the target parameter based on the feature extraction results of all time intervals; Oil leakage monitoring module: Based on the first monitoring coefficient and in combination with various parameters at the current moment, the oil leakage detection of the hydraulic support cylinder is performed.

6. An intelligent detection system for oil leakage of a hydraulic support cylinder, 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 4 are implemented.

Images