Reciprocating compressor gas valve leakage fault self-diagnosis method and device

Abstract

The present application provides a self-diagnosis method for a reciprocating compressor air valve leakage fault, comprising: obtaining the working condition data of the reciprocating compressor; processing the working condition data in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the reciprocating compressor; extracting characteristic elements in the air pressure-volume diagram; performing a difference comparison between the numerical value of the characteristic element and the numerical value of the corresponding normal characteristic element to obtain a characteristic set; matching the characteristic set with the characteristic set stored in the characteristic library to obtain a target characteristic set; querying the mapping relationship library according to the target characteristic set to obtain the current air valve state of the reciprocating compressor; when the current air valve state is not the air valve fault-free state, issuing a prompt message, the prompt message is used to prompt that the air valve of the reciprocating compressor has a leakage fault. The present application solves the problem in the prior art that the reciprocating compressor air valve leakage fault diagnosis process requires human input and there is artificial interference, resulting in low accuracy of the diagnosis result.

Description

Technical Field

[0001] The present invention relates to the technical field of reciprocating compressor fault detection, and in particular to a reciprocating compressor air valve leakage fault self-diagnosis method, a reciprocating compressor air valve leakage fault self-diagnosis device, a computer-readable storage medium and a reciprocating compressor air valve leakage fault self-diagnosis system. Background Art

[0002] Reciprocating compressors are core equipment in the coal chemical production process. Many compressor media are flammable and explosive gases, and they work under high pressure. Once a failure occurs, it may cause serious casualties. The gas valve is the most critical component in the reciprocating compressor and has the highest failure rate. Therefore, it is of great significance to study the fault diagnosis technology of the reciprocating compressor gas valve, detect abnormalities as early as possible, and take corresponding preventive measures. At present, the fault diagnosis of reciprocating compressor gas valves mainly relies on experts to judge through mechanism changes. However, the reciprocating compressor gas valves are subjected to complex forces, the faults are diverse, and the correlation and complexity between faults are strong, which increases the difficulty of the manual diagnosis process, making the diagnosis process not timely enough, and the accuracy of the diagnosis results depends largely on the experience and knowledge of the diagnosis experts. If the diagnosis experts are not experienced enough, misjudgment may occur. Therefore, reducing manual participation in the diagnosis process and improving the efficiency and accuracy of diagnosis are urgent needs for the diagnosis of reciprocating compressor gas valve faults. Summary of the invention

[0003] The main purpose of the present application is to provide a reciprocating compressor valve leakage fault self-diagnosis method, a reciprocating compressor valve leakage fault self-diagnosis device, a computer-readable storage medium and a reciprocating compressor valve leakage fault self-diagnosis system, so as to at least solve the problem of low accuracy of diagnosis results due to human interference and manpower input in the reciprocating compressor valve leakage fault diagnosis process in the prior art.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a self-diagnosis method for a reciprocating compressor valve leakage fault is provided, comprising: obtaining the operating data of the reciprocating compressor, the operating data at least including the crank angle and the gas pressure in the cylinder of the reciprocating compressor; processing the operating data in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the reciprocating compressor, the abscissa of the pressure-volume diagram representing the working volume of the cylinder, and the ordinate of the pressure-volume diagram representing the gas pressure; extracting characteristic elements from the pressure-volume diagram, the characteristic elements including the variable angles and working volumes of the reciprocating compressor during the compression process and the expansion process, the variable angles representing the changing speed of the gas in the cylinder during the working process; comparing the values ​​of the characteristic elements with the values ​​of the corresponding normal characteristic elements. The difference is compared to obtain a feature set, wherein the normal feature element is the feature element corresponding to the valve of the reciprocating compressor in a non-fault state stored in the feature library; the feature set is matched with the feature set stored in the feature library to obtain a target feature set, wherein the target feature set is a feature set in the feature library that successfully matches the feature set; a mapping relationship library is queried according to the target feature set to obtain the current valve state of the reciprocating compressor, wherein the current valve state is one of the following: the valve non-fault state, suction valve leakage, exhaust valve leakage and piston ring leakage, wherein the mapping relationship library is a set formed by mapping relationships between feature sets and valve states; when the current valve state is not the valve non-fault state, a prompt message is issued, wherein the prompt message is used to prompt that a leakage fault occurs in the valve of the reciprocating compressor.

[0005] Optionally, the operating condition data is processed in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the reciprocating compressor, including: calculating the working volume of the cylinder according to the compressor parameters and the crank angle in combination with a first formula, wherein the compressor parameters at least include the cylinder inner diameter, the crank radius, the clearance volume and the crank radius-connecting rod ratio, and the first formula is V0 is the clearance volume, Di is the inner diameter of the cylinder of the i-th stage, r is the crank radius, θ is the crank angle, and λ is the crank radius connecting rod ratio; the image processing technology is used to process the relationship change curve between the gas pressure and the working volume to generate the gas pressure-volume diagram during the working cycle.

[0006] Optionally, the characteristic elements include a first starting point variable angle, a first end point variable angle, a first working volume, a second starting point variable angle, a second end point variable angle and a second working volume, the first starting point variable angle is the variable angle of the reciprocating compressor at the starting point of the compression process, the first end point variable angle is the variable angle of the reciprocating compressor at the end point of the compression process, the first working volume is the working volume when the exhaust pressure is reached, the second starting point variable angle is the variable angle of the reciprocating compressor at the starting point of the expansion process, the second end point variable angle is the variable angle of the reciprocating compressor at the end point of the expansion process, and the second working volume is the working volume when the suction pressure is reached. The working volume of the gas pressure volume map, before extracting the characteristic elements in the gas pressure volume map, the method further includes: obtaining a first gas volume map, a second gas volume map, a third gas volume map and a normal gas volume map, the first gas volume map is a gas volume map when the intake valve leaks, the second gas volume map is a gas volume map corresponding to the exhaust valve leaks, the third gas volume map is a gas volume map corresponding to the piston ring leaks, and the normal gas volume map is a gas volume map corresponding to the gas valve in a fault-free state; comparing the first gas volume map with the normal gas volume map, and analyzing the compression process and the expansion process to determine a first multi-angle The first multi-angle change is the multi-angle change in the case of leakage of the intake valve, and the first working volume change is the working volume change in the case of leakage of the intake valve; the second gas volume diagram is compared with the normal gas volume diagram, and the compression process and the expansion process are analyzed to determine the second multi-angle change and the second working volume change, the second multi-angle change is the multi-angle change in the case of leakage of the exhaust valve, and the second working volume change is the working volume change in the case of leakage of the exhaust valve; the third gas volume The diagram is compared with the normal gas volume diagram, and the compression process and the expansion process are analyzed to determine the third multi-variable angle change and the third working volume change, wherein the third multi-variable angle change is the multi-angle change in the case of piston ring leakage, and the third working volume change is the working volume change in the case of piston ring leakage; a comprehensive analysis is performed based on the first multi-variable angle change, the first working volume change, the second multi-variable angle change, the second working volume change, the third multi-variable angle change and the third working volume change to determine the characteristic elements of the gas volume diagram.

[0007] Optionally, before performing a difference comparison between the numerical values ​​of the characteristic elements and the numerical values ​​of the corresponding normal characteristic elements to obtain a characteristic set, the method also includes: obtaining historical operating data of the valves of all the reciprocating compressors at different valve states, the historical operating data including historical gas pressure and historical crank angle; generating a corresponding historical gas volume graph based on the historical operating data; extracting historical characteristic elements of the historical gas volume graph; performing a difference comparison between all the historical characteristic elements and the normal historical characteristic elements to form a historical characteristic set, and storing the historical characteristic set in the characteristic library; mapping the historical characteristic set with the corresponding valve states to form the mapping relationship library, and storing it in the characteristic library.

[0008] Optionally, the numerical values ​​of the characteristic elements are compared with the numerical values ​​of the corresponding normal characteristic elements by difference to obtain a feature set, including: performing difference operations on the first starting point multi-variable angle, the first end point multi-variable angle, the first working volume, the second starting point multi-variable angle, the second end point multi-variable angle and the second working volume with the corresponding normal characteristic elements respectively to obtain characteristic difference values, the characteristic difference values ​​include the first starting point multi-variable angle difference value, the first end point multi-variable angle difference value, the first working volume difference value, the second starting point multi-variable angle difference value, the second end point multi-variable angle difference value and the second working volume difference value; the feature set is determined according to the change direction of the characteristic difference values, the change direction includes an increasing direction and a decreasing direction, and the feature set characterizes the change direction of each of the characteristic elements.

[0009] Optionally, the first gas volume diagram is compared with the normal gas volume diagram, and the compression process and the expansion process are analyzed to determine the first multi-variable angle change and the first working volume change, including: when the gas valve state is the intake valve leakage and it is the compression process, the starting multi-variable angle, the end multi-variable angle and the working volume of the compression process in the first gas volume diagram are compared with those in the normal gas volume diagram, and it is determined that the first multi-variable angle change includes that in the compression process of the intake valve leakage, the first starting multi-variable angle is smaller than the normal compression starting multi-variable angle and the first end multi-variable angle is smaller than the normal compression end multi-variable angle, and the first working volume change includes that the first working volume is smaller than the first normal working volume, the normal compression starting multi-variable angle is the first starting multi-variable angle in the normal gas volume diagram, and the normal compression end multi-variable angle is the first end multi-variable angle in the normal gas volume diagram. degree, the first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram; when the gas valve state is the intake valve leakage and it is the expansion process, the starting multivariable angle, the end multivariable angle and the working volume of the expansion process in the first gas volume diagram are compared with those in the normal gas volume diagram, and it is determined that the change of the first multivariable angle also includes that in the expansion process of the intake valve leakage, the second starting multivariable angle is larger than the normal expansion starting multivariable angle and the second end multivariable angle is larger than the normal expansion end multivariable angle, and the change of the first working volume also includes that the second working volume is smaller than the second normal working volume, the normal expansion starting multivariable angle is the second starting multivariable angle in the normal gas volume diagram, the normal expansion end multivariable angle is the second end multivariable angle in the normal gas volume diagram, and the second normal working volume is the working volume when the intake pressure is reached in the normal working volume diagram.

[0010] Optionally, the third gas volume diagram is compared with the normal gas volume diagram, and the compression process and the expansion process are analyzed to determine the third multi-variable angle change and the third working volume change, including: when the valve state is the piston ring leakage and the compression process, the starting multi-variable angle, the end multi-variable angle and the working volume of the compression process in the third gas volume diagram are compared with those in the normal gas volume diagram, and it is determined that the third multi-variable angle change includes that in the compression process of the piston ring leakage, the first starting multi-variable angle is larger than the normal compression starting multi-variable angle and the first end multi-variable angle is smaller than the normal compression end multi-variable angle, and the third working volume change includes that the first working volume is smaller than the first normal working volume, the normal compression starting multi-variable angle is the first starting multi-variable angle in the normal gas volume diagram, and the normal compression end multi-variable angle is the first end multi-variable angle in the normal gas volume diagram. angle, the first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram; when the valve state is the piston ring leakage and the expansion process, the starting multivariable angle, the end multivariable angle and the working volume of the expansion process in the third gas volume diagram are compared with those in the normal gas volume diagram, and it is determined that the change of the third multivariable angle also includes that the second starting multivariable angle is larger than the normal expansion starting multivariable angle and the second end multivariable angle is smaller than the normal expansion end multivariable angle in the expansion process of the piston ring leakage, and the third working volume change also includes that the second working volume is smaller than the second normal working volume, the normal expansion starting multivariable angle is the second starting multivariable angle in the normal gas volume diagram, the normal expansion end multivariable angle is the second end multivariable angle in the normal gas volume diagram, and the second normal working volume is the working volume when the suction pressure is reached in the normal working volume diagram.

[0011] According to another aspect of the present application, a reciprocating compressor valve leakage fault self-diagnosis device is provided, the device comprising: a first acquisition unit, used to acquire the working condition data of the reciprocating compressor, the working condition data at least including the crank angle and the gas pressure in the cylinder of the reciprocating compressor; a data processing unit, used to process the working condition data in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the reciprocating compressor, the abscissa of the pressure-volume diagram represents the working volume of the cylinder, and the ordinate of the pressure-volume diagram represents the gas pressure; a feature element extraction unit, used to extract feature elements in the pressure-volume diagram, the feature elements including the variable angles and working volumes of the reciprocating compressor during the compression process and the expansion process, the variable angles representing the changing speed of the gas in the cylinder during the working process; a feature comparison unit, used to compare the numerical values ​​of the feature elements with the corresponding normal feature elements. The normal feature elements are compared with the values ​​of the elements to obtain a feature set, wherein the normal feature elements are the feature elements of the air valve of the reciprocating compressor stored in the feature library when the air valve is in a normal state; a feature matching unit is used to match the feature set with the feature set stored in the feature library to obtain a target feature set, wherein the target feature set is a feature set in the feature library that successfully matches the feature set; a query unit is used to query a mapping relationship library according to the target feature set to obtain the current air valve state of the reciprocating compressor, wherein the current air valve state is one of the following: the normal state of the air valve, leakage of the intake valve, leakage of the exhaust valve and leakage of the piston ring, wherein the mapping relationship library is a set formed by the mapping relationship between the feature set and the air valve state; an issuing unit is used to issue a prompt message when the current air valve state is not the normal state of the air valve, wherein the prompt message is used to prompt that a leakage fault occurs in the air valve of the reciprocating compressor.

[0012] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0013] According to another aspect of the present application, a reciprocating compressor gas valve leakage fault self-diagnosis system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0014] Applying the technical solution of the present application, in a self-diagnosis method for a reciprocating compressor valve leakage fault, first, the operating data of the reciprocating compressor is obtained, the above operating data at least including the crank angle and the gas pressure in the cylinder of the above reciprocating compressor; then, the above operating data is processed in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the above reciprocating compressor, the abscissa of the above pressure-volume diagram represents the working volume of the above cylinder, and the ordinate of the above pressure-volume diagram represents the above gas pressure; then, characteristic elements in the above pressure-volume diagram are extracted, the above characteristic elements include the variable angles and working volume of the above reciprocating compressor during the compression process and the expansion process, and the above variable angles represent the changing speed of the gas in the above cylinder during the working process; then, the value of the above characteristic element is compared with the value of the corresponding normal characteristic element by difference, to obtain To the feature set, the above normal feature elements are the above feature elements corresponding to the valve of the above reciprocating compressor in the valve fault-free state stored in the feature library; then, the above feature set is matched with the feature set stored in the above feature library to obtain the target feature set, and the above target feature set is the feature set in the above feature library that successfully matches the above feature set; then, according to the above target feature set, the mapping relationship library is queried to obtain the current valve state of the above reciprocating compressor, and the above current valve state is one of the following: the above valve fault-free state, suction valve leakage, exhaust valve leakage and piston ring leakage, and the above mapping relationship library is a set formed by the mapping relationship between the feature set and the valve state; finally, when the above current valve state is not the above valve fault-free state, a prompt message is issued, and the above prompt message is used to prompt that the valve of the above reciprocating compressor has a leakage fault. The present application obtains the pressure-volume diagram of the working process of the reciprocating compressor by preprocessing the dynamic pressure and crank angle in the compressor cylinder collected in real time, and extracts the feature elements of the key points according to the pressure-volume diagram of the compressor working process. When a compressor valve leaks, the pressure-volume diagram will change due to the influence of the pressure change in the cylinder. Therefore, analyzing the changes in the characteristic elements of the key points in the pressure-volume diagram can automatically detect valve leakage defects. The values ​​of the extracted characteristic elements are compared with the characteristic elements of the corresponding compressor valve in the feature library when the valve is in a fault-free state, and the results are formed into a feature set. The obtained feature set is matched in the feature library, and the compressor valve state is obtained and output based on the mapping relationship between the matched feature set and the valve state. The above scheme can monitor the working state of the reciprocating compressor valve in real time, and automatically judge and output the diagnostic results. The present application solves the problem in the prior art that the fault diagnosis process of the reciprocating compressor valve leakage requires manpower input and the presence of artificial interference leads to low accuracy of the diagnostic results. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1A hardware structure block diagram of a mobile terminal for executing a self-diagnosis method for a reciprocating compressor gas valve leakage fault provided in an embodiment of the present application is shown;

[0016] Figure 2 A schematic flow chart of a reciprocating compressor gas valve leakage fault self-diagnosis method provided according to an embodiment of the present application is shown;

[0017] Figure 3 A schematic flow chart of a specific reciprocating compressor gas valve leakage fault self-diagnosis method provided according to an embodiment of the present application is shown;

[0018] Figure 4 A PV diagram of a cyclic working process of a reciprocating compressor provided according to an embodiment of the present application is shown;

[0019] Figure 5 A PV diagram for self-diagnosis of an intake valve leakage fault provided according to an embodiment of the present application is shown;

[0020] Figure 6 A PV diagram for self-diagnosis of exhaust valve leakage fault provided according to an embodiment of the present application is shown;

[0021] Figure 7 A PV diagram for self-diagnosis of a piston ring leakage fault provided according to an embodiment of the present application is shown;

[0022] Figure 8 A structural block diagram of a reciprocating compressor air valve leakage fault self-diagnosis device provided according to an embodiment of the present application is shown.

[0023] The above drawings include the following reference numerals:

[0024] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] As introduced in the background technology, in the prior art, the reciprocating compressor valves are subjected to complex forces, and the faults are diverse. In addition, the faults are highly correlated and complex, which increases the difficulty of the manual diagnosis process, making the diagnosis process not timely enough, and the accuracy of the diagnosis results largely depends on the experience and knowledge of the diagnosis experts. If the diagnosis experts are not experienced enough, misjudgments may occur. Therefore, reducing manual participation in the diagnosis process and improving the efficiency and accuracy of diagnosis are urgent needs for the diagnosis of reciprocating compressor valve faults. In order to solve the problem that the diagnosis process of reciprocating compressor valve leakage faults in the prior art requires human input and there is human interference, resulting in low accuracy of the diagnosis results, the embodiments of the present application provide a reciprocating compressor valve leakage fault self-diagnosis method, a reciprocating compressor valve leakage fault self-diagnosis device, a computer-readable storage medium, and a reciprocating compressor valve leakage fault self-diagnosis system.

[0029] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0030] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for a reciprocating compressor valve leakage fault self-diagnosis method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1More or fewer components as shown, or with Figure 1 Different configurations shown.

[0031] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the self-diagnosis method for reciprocating compressor gas valve leakage fault in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] In this embodiment, a self-diagnosis method for reciprocating compressor valve leakage fault running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] Figure 2 FIG. 1 is a flow chart of a reciprocating compressor valve leakage fault self-diagnosis method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0034] Step S201, obtaining the operating data of the reciprocating compressor, wherein the operating data at least includes the crank angle and the gas pressure in the cylinder of the reciprocating compressor.

[0035] Specifically, Figure 3As shown, the existing high-speed data acquisition card in the coal chemical park is used to simultaneously perform multi-channel acquisition of the signals output by the pressure sensor, encoder and displacement sensor, thereby realizing the synchronous acquisition of the cylinder pressure (i.e. the above-mentioned gas pressure) and crank angle of the reciprocating compressor.

[0036] Step S202, processing the operating data in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the reciprocating compressor, wherein the abscissa of the pressure-volume diagram represents the working volume of the cylinder, and the ordinate of the pressure-volume diagram represents the gas pressure.

[0037] Specifically, by preprocessing the real-time collected gas pressure and crank angle in the compressor cylinder, the pV diagram of the compressor working cycle can be obtained by using image processing technology according to the relationship curve between the gas pressure in the cylinder and the working volume, that is, the gas volume diagram mentioned above, such as Figure 4 shown.

[0038] It should also be noted that the actual cycle of a typical reciprocating compressor can be divided into four processes: suction process, compression process, exhaust process, and expansion process: (1) Suction process: This is the first process of the compressor. The piston moves from the Figure 4 The piston moves from position 1 to position 2. After the intake valve opens, low-pressure gas is sucked into the cylinder until the piston reaches the bottom dead center 2 and the intake valve closes. (2) Compression process: The piston moves from position 1 to position 2. Figure 4 The piston moves from position 2 to position 3. After the intake valve is closed, the low-pressure gas in the cylinder is compressed until the exhaust pressure Pd is reached for the first time. The compression process ends and the exhaust valve opens. (3) Exhaust process: The piston moves from position 2 to position 3. Figure 4 The piston moves from position 3 to position 4. After the exhaust valve opens, high-pressure gas is continuously discharged from the exhaust pipe until the piston reaches the top dead center position 4. The exhaust process ends and the exhaust valve closes. (4) Expansion process: The piston moves from position 3 to position 4. Figure 4 The middle position 4 moves to position 1. After the exhaust valve is closed, the high-pressure gas in the clearance volume expands due to the increase in volume, thereby causing the gas pressure in the cylinder to drop until the gas pressure in the cylinder reaches the suction pressure Ps for the first time. The expansion process ends, the suction valve opens, and the suction process begins again, and the second cycle begins.

[0039] Step S203, extracting characteristic elements from the above-mentioned pressure-volume diagram, wherein the above-mentioned characteristic elements include the variable angles and working volumes of the above-mentioned reciprocating compressor during the compression process and the expansion process, and the above-mentioned variable angles represent the changing speed of the gas in the above-mentioned cylinder during the working process.

[0040] Specifically, when a reciprocating compressor valve leaks, the pV diagram will change due to the influence of the pressure change in the cylinder. Therefore, analyzing the changes in the characteristic elements of the key points in the pV diagram can automatically detect valve leakage defects. The "compression process" and "expansion process" in the working process of the reciprocating compressor are in the state where the compression chamber is sealed. The impact of valve leakage on these two stages is the most obvious, which is very suitable for automatic detection of valve leakage defects. Therefore, the four key points are determined as follows: Figure 4 The starting point 2 of the compression process, the end point 3 of the compression process, the starting point 4 of the expansion process, and the end point 1 of the expansion process. The acute angle β between the pressure curves of the "compression" and "expansion" processes and the suction pressure line and the exhaust pressure line in the pV diagram represents the speed of change of the gas during the working process. The larger the angle, the faster the gas changes during the working process, and the smaller the angle, the slower the gas changes during the working process. Therefore, the state of the gas valve can be judged by comparing the changes in β. β is defined as a variable angle, such as Figure 5 β1, β2, β3, and β4 represent the variable angles of the valve at the key points. In addition, the working volume is also used as a characteristic element. Therefore, according to the pV diagram of the working process of the reciprocating compressor, the characteristic elements of the key points, namely the variable angle and the working volume, are extracted.

[0041] Step S204, performing a difference comparison between the values ​​of the above-mentioned characteristic elements and the values ​​of the corresponding normal characteristic elements to obtain a characteristic set, wherein the above-mentioned normal characteristic elements are the above-mentioned characteristic elements corresponding to the air valve of the above-mentioned reciprocating compressor in a non-faulty state of the air valve stored in the characteristic library.

[0042] Specifically, the extracted characteristic elements are compared with the characteristic elements of the corresponding compressor valve in the normal state in the characteristic library to obtain a feature set, which indicates whether the value of the characteristic elements increases or decreases, and further determines whether the valve fails.

[0043] Step S205, matching the feature set with the feature set stored in the feature library to obtain a target feature set, where the target feature set is a feature set in the feature library that successfully matches the feature set.

[0044] Specifically, the obtained feature set is matched in the feature library to obtain a corresponding successfully matched feature set.

[0045] Step S206, query the mapping relationship library according to the above-mentioned target feature set to obtain the current valve state of the above-mentioned reciprocating compressor, and the above-mentioned current valve state is one of the following: the above-mentioned valve fault-free state, suction valve leakage, exhaust valve leakage and piston ring leakage. The above-mentioned mapping relationship library is a set formed by the mapping relationship between the feature set and the valve state.

[0046] Specifically, the mapping relationship library is queried according to the matched feature set to obtain the current valve state of the reciprocating compressor. The mapping relationship library is a reciprocating compressor valve feature library formed through automatic algorithm processing and a large amount of training, and a mapping relationship between the feature set and the valve state is established.

[0047] Step S207: When the current valve state is not the valve fault-free state, a prompt message is issued, wherein the prompt message is used to prompt that a leakage fault occurs in the valve of the reciprocating compressor.

[0048] Specifically, when the current valve state is not the valve fault-free state, a prompt message is issued to remind the staff to further inspect the valve of the reciprocating compressor to reduce faults.

[0049] In this embodiment, the dynamic pressure and crank angle in the compressor cylinder collected in real time are preprocessed to obtain the pressure-volume diagram of the working process of the reciprocating compressor, and the characteristic elements of the key points are extracted according to the pressure-volume diagram of the working process of the compressor. When the compressor valve leaks, the pressure-volume diagram will change accordingly due to the influence of the pressure change in the cylinder. Therefore, the change of the characteristic elements of the key points in the pressure-volume diagram can automatically detect the valve leakage defect. The value of the extracted characteristic element is compared with the characteristic element of the corresponding compressor valve in the feature library when the valve is in a fault-free state, and the result is formed into a feature set. The obtained feature set is matched in the feature library, and the compressor valve state is obtained and output according to the mapping relationship between the matched feature set and the valve state. Through the above scheme, the working state of the reciprocating compressor valve can be monitored in real time, and the diagnosis result can be automatically judged and output. The present application solves the problem that the diagnosis process of the reciprocating compressor valve leakage fault in the prior art requires human input and there is artificial interference, resulting in low accuracy of the diagnosis result.

[0050] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the reciprocating compressor valve leakage fault self-diagnosis method of the present application will be described in detail below in combination with specific embodiments.

[0051] In order to generate a pV map and thus reduce manual involvement in the diagnosis process, in an optional implementation, the above step S202 includes:

[0052] S2021, calculating the working volume of the cylinder according to the compressor parameters and the crank angle in combination with a first formula, wherein the compressor parameters at least include a cylinder inner diameter, a crank radius, a clearance volume, and a crank radius-connecting rod ratio, and the first formula is: V0 is the clearance volume, Di is the cylinder inner diameter of the i-th stage, r is the crank radius, θ is the crank angle, and λ is the crank radius connecting rod ratio;

[0053] S2022, using the above-mentioned image processing technology to process the relationship change curve between the above-mentioned gas pressure and the above-mentioned working volume, and generate the above-mentioned gas pressure-volume diagram during the above-mentioned working cycle.

[0054] In the above embodiment, the cylinder working volume is calculated based on the corresponding relationship between the compressor cylinder working volume and the crank angle, that is, the above first formula. According to the relationship curve between the gas pressure in the cylinder and the working volume, the pV diagram of the compressor working cycle process can be obtained by using image processing technology ( Figure 4 ), the vertical axis of the pV graph represents pressure, and the horizontal axis represents working volume. In order to automatically detect valve leakage faults by reversely analyzing the pV graph according to the influence of the reciprocating compressor valve on the pressure curve (pV graph) under different states.

[0055] In order to reduce manual interference and manpower input in the diagnosis process and reduce the diagnosis cost, in an optional implementation manner, before the above step S203, the method further includes:

[0056] Step S301, obtaining a first gas volume diagram, a second gas volume diagram, a third gas volume diagram and a normal gas volume diagram, wherein the first gas volume diagram is a gas volume diagram when the intake valve is leaking, the second gas volume diagram is a gas volume diagram corresponding to when the exhaust valve is leaking, the third gas volume diagram is a gas volume diagram corresponding to when the piston ring is leaking, and the normal gas volume diagram is a gas volume diagram corresponding to when the gas valve is in a fault-free state;

[0057] Step S302, comparing the first gas volume diagram with the normal gas volume diagram, and analyzing the compression process and the expansion process to determine a first multi-angle change and a first working volume change, wherein the first multi-angle change is a multi-angle change when the intake valve leaks, and the first working volume change is a working volume change when the intake valve leaks;

[0058] Step S303, comparing the second gas volume diagram with the normal gas volume diagram, and analyzing the compression process and the expansion process to determine a second multi-angle change and a second working volume change, wherein the second multi-angle change is a multi-angle change when the exhaust valve leaks, and the second working volume change is a working volume change when the exhaust valve leaks;

[0059] Step S304, comparing the third gas volume diagram with the normal gas volume diagram, and analyzing the compression process and the expansion process to determine a third multi-angle change and a third working volume change, wherein the third multi-angle change is a multi-angle change when the piston ring leaks, and the third working volume change is a working volume change when the piston ring leaks;

[0060] Step S305, performing a comprehensive analysis based on the first multi-variable angle change, the first working volume change, the second multi-variable angle change, the second working volume change, the third multi-variable angle change and the third working volume change to determine the characteristic elements of the gas volume diagram.

[0061] In the above embodiment, the above characteristic elements include a first starting point multi-variable angle, a first end point multi-variable angle, a first working volume, a second starting point multi-variable angle, a second end point multi-variable angle and a second working volume. The first starting point multi-variable angle is the multi-variable angle of the reciprocating compressor at the starting point of the compression process, the first end point multi-variable angle is the multi-variable angle of the reciprocating compressor at the end point of the compression process, the first working volume is the working volume when the exhaust pressure is reached, the second starting point multi-variable angle is the multi-variable angle of the reciprocating compressor at the starting point of the expansion process, the second end point multi-variable angle is the multi-variable angle of the reciprocating compressor at the end point of the expansion process, and the second working volume is the working volume when the suction pressure is reached. The above first gas volume diagram, the above second gas volume diagram and the above third gas volume diagram are all analyzed with the above normal gas volume diagram to determine whether the suction valve leakage, exhaust valve leakage and piston ring leakage occur respectively. The specific analysis diagrams are as follows. Figure 5 , Figure 6 and Figure 7 All processes from data collection, pV map formation, feature element extraction and analysis, feature library establishment and judgment result output are automatically realized through algorithms, reducing manual interference and manpower input in the diagnosis process, improving the accuracy of diagnosis results and reducing diagnosis costs.

[0062] For example, in order to improve the accuracy of detecting exhaust valve leakage failure, Figure 6 As shown in FIG. 1 , when the exhaust valve leaks, the compression process becomes faster, so the variable angle β2 at the starting point of the compression process (i.e., the first starting point variable angle) is larger than the β when the exhaust valve is normal. 2a The variable angle β3 at the end of the compression process (i.e., the first end variable angle) will be larger than the β 3a(i.e. the above-mentioned normal compression end variable angle) will increase, and the working volume V3 (i.e. the above-mentioned first working volume) when the exhaust pressure is reached is larger than V 3a On the contrary, when the exhaust valve leaks, the pressure curve of the expansion process is flatter than normal, and the expansion process slows down. Therefore, the multivariable angle β4 at the starting point of the expansion process (i.e. the multivariable angle of the second starting point) is larger than the β 4a The variable angle β1 at the end of the expansion process (i.e., the variable angle at the second end point) will be smaller than the β 1a (i.e. the above-mentioned normal expansion end variable angle) will decrease, and the working volume V1 (i.e. the above-mentioned second working volume) when the suction pressure is reached is greater than V 1a The first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram, and the second normal working volume is the working volume when the suction pressure is reached in the normal working volume diagram.

[0063] In order to improve the refined management level of the reciprocating compressor, in an optional implementation manner, before the above step S204, the above method further includes:

[0064] Step S401, obtaining historical operating data of the gas valves of all the reciprocating compressors at different gas valve states, wherein the historical operating data includes historical gas pressure and historical crank angle;

[0065] Step S402, generating a corresponding historical gas volume graph according to the above historical operating condition data;

[0066] Step S403, extracting historical characteristic elements of the historical gas volume graph;

[0067] Step S404, performing a difference comparison between all the above historical feature elements and normal historical feature elements to form a historical feature set, and storing the above historical feature set in the above feature library;

[0068] Step S405, mapping the historical feature set with the corresponding valve state to form the mapping relationship library, and storing it in the feature library.

[0069] In the above embodiment, the feature library defined in the present invention is obtained by collecting the cylinder pressure and crank angle of the suction valve and exhaust valve of each reciprocating compressor in the coal chemical park in different states, and repeatedly performing pV diagram generation, feature element extraction, feature element difference comparison and feature set matching. Through a large amount of training, the feature elements of the valves of the reciprocating compressors in the coal chemical park in normal states and the feature sets of the valves in different states are obtained to form a feature library, and a mapping relationship between the valve states and the feature sets is established to generate a mapping relationship library, thereby improving the level of refined management of reciprocating compressors.

[0070] In order to improve the accuracy of gas valve fault detection, in an optional implementation manner, the above step S204 includes:

[0071] Step S2041, performing difference operations on the first starting point multivariable angle, the first end point multivariable angle, the first working volume, the second starting point multivariable angle, the second end point multivariable angle and the second working volume respectively with corresponding normal characteristic elements to obtain characteristic difference values, wherein the characteristic difference values ​​include the first starting point multivariable angle difference value, the first end point multivariable angle difference value, the first working volume difference value, the second starting point multivariable angle difference value, the second end point multivariable angle difference value and the second working volume difference value;

[0072] Step S2042, determining the feature set according to the change direction of the feature difference, the change direction includes an increasing direction and a decreasing direction, and the feature set represents the change direction of each of the feature elements.

[0073] In the above embodiment, the result is Δβ1=β1-β 1a , Δβ2=β2-β 2a , Δβ3=β3-β 3a , Δβ4=β4-β 4a , ΔV1=V1-V 1a and ΔV3=V3-V 3a , where β2, β3, β4, and β1 are the variable angles of the valve at the start of the compression process, the variable angle at the end of the compression process, the variable angle at the start of the expansion process, and the variable angle at the end of the expansion process, respectively. V3 represents the working volume when the exhaust pressure is reached, and V1 represents the working volume when the suction pressure is reached. The parameters with the subscript a represent the corresponding normal characteristic elements mentioned above. The feature set is determined as A = {a, b, c, d, e, f}, where the elements a, b, c, d, e, and f of the feature set correspond to the change directions of Δβ2, Δβ3, ΔV3, Δβ4, Δβ1, and ΔV1, respectively. For example Figure 5 , when the suction valve leaks, Δβ2=β2-β 2a <0, Δβ3=β3-β 3a <0,ΔV3=V3-V3a <0, Δβ4=β4-β 4a >0, Δβ1=β1-β 1a >0, ΔV1=V1-V 1a <0, then when the intake valve leaks, the feature set A={↓,↓,↓,↑,↑,↓}.

[0074] In order to improve the accuracy of detecting the air intake valve leakage fault, in an optional implementation manner, the above step S301 includes:

[0075] Step S3011, when the gas valve state is the intake valve leakage and the compression process, compare the starting multivariable angle, the ending multivariable angle and the working volume of the compression process in the first gas volume diagram with those in the normal gas volume diagram, and determine that the change of the first multivariable angle includes that in the compression process of the intake valve leakage, the first starting multivariable angle is smaller than the normal compression starting multivariable angle and the first ending multivariable angle is smaller than the normal compression ending multivariable angle, and the change of the first working volume includes that the first working volume is smaller than the first normal working volume, the normal compression starting multivariable angle is the first starting multivariable angle in the normal gas volume diagram, the normal compression ending multivariable angle is the first ending multivariable angle in the normal gas volume diagram, and the first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram;

[0076] Step S3012, when the above-mentioned valve state is the above-mentioned intake valve leakage and it is the above-mentioned expansion process, compare the starting multivariable angle, the end multivariable angle and the working volume of the above-mentioned expansion process in the above-mentioned first gas volume diagram with those in the above-mentioned normal gas volume diagram, and determine that the above-mentioned first multivariable angle change also includes that in the above-mentioned expansion process of the above-mentioned intake valve leakage, the above-mentioned second starting multivariable angle is larger than the normal expansion starting multivariable angle and the above-mentioned second end multivariable angle is larger than the normal expansion end multivariable angle, and the above-mentioned first working volume change also includes that the above-mentioned second working volume is smaller than the second normal working volume, the above-mentioned normal expansion starting multivariable angle is the second starting multivariable angle in the above-mentioned normal gas volume diagram, the above-mentioned normal expansion end multivariable angle is the second end multivariable angle in the above-mentioned normal gas volume diagram, and the above-mentioned second normal working volume is the working volume when the intake pressure is reached in the above-mentioned normal working volume diagram.

[0077] In the above embodiment, if Figure 5As shown in FIG. 1 , when the suction valve leaks, the gas continues to flow from the compression chamber to the suction pipe side during the compression process, which slows down the pressure rise. The pressure curve of the compression process is flatter than normal, and the compression process slows down. Therefore, the multivariable angle β2 at the starting point of the compression process (i.e., the multivariable angle of the first starting point mentioned above) is larger than the β 2a The variable angle β3 at the end of the compression process (i.e., the first end variable angle) will be smaller than the β 3a (i.e. the above-mentioned normal compression end variable angle) will decrease, and the working volume V3 (i.e. the above-mentioned first working volume) when the exhaust pressure is reached is smaller than V 3a On the contrary, when the intake valve leaks, the gas pressure drops faster during the expansion process, and even drops sharply before the intake valve opens, reaching the intake pressure level in a faster time than usual, and the expansion process becomes faster. Therefore, the multivariable angle β4 at the starting point of the expansion process (i.e., the multivariable angle of the second starting point) is larger than the β 4a The variable angle β1 at the end of the expansion process (i.e., the variable angle at the second end point) will be larger than the β 1a (i.e. the above-mentioned normal expansion end variable angle) will increase, and the working volume V1 (i.e. the above-mentioned second working volume) when the suction pressure is reached is larger than V 1a (ie the second normal working volume mentioned above) will also decrease.

[0078] In order to improve the accuracy of detecting piston ring leakage faults, in an optional implementation manner, the above step S303 includes:

[0079] Step S3031, when the gas valve state is the piston ring leakage and the compression process, compare the starting multivariable angle, the end multivariable angle and the working volume of the compression process in the third gas volume diagram with those in the normal gas volume diagram, and determine that the change of the third multivariable angle includes that in the compression process of the piston ring leakage, the first starting multivariable angle is larger than the normal compression starting multivariable angle and the first end multivariable angle is smaller than the normal compression end multivariable angle, and the change of the third working volume includes that the first working volume is smaller than the first normal working volume, the normal compression starting multivariable angle is the first starting multivariable angle in the normal gas volume diagram, the normal compression end multivariable angle is the first end multivariable angle in the normal gas volume diagram, and the first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram;

[0080] Step S3032, when the above-mentioned valve state is the above-mentioned piston ring leakage and the above-mentioned expansion process, compare the starting multivariable angle, the end multivariable angle and the working volume of the above-mentioned expansion process in the above-mentioned third gas volume diagram with those in the above-mentioned normal gas volume diagram, and determine that the above-mentioned third multivariable angle change also includes that in the above-mentioned expansion process of the above-mentioned piston ring leakage, the above-mentioned second starting multivariable angle is larger than the normal expansion starting multivariable angle and the above-mentioned second end multivariable angle is smaller than the normal expansion end multivariable angle, and the third working volume change also includes that the above-mentioned second working volume is smaller than the second normal working volume, the above-mentioned normal expansion starting multivariable angle is the second starting multivariable angle in the above-mentioned normal gas volume diagram, the above-mentioned normal expansion end multivariable angle is the second end multivariable angle in the above-mentioned normal gas volume diagram, and the above-mentioned second normal working volume is the working volume when the suction pressure is reached in the above-mentioned normal working volume diagram.

[0081] In the above embodiment, if Figure 7 As shown in the figure, when the piston ring leaks, the pressure rise speed in the compression process first accelerates and then slows down, so the variable angle β2 at the starting point of the compression process is larger than the β 2a The variable angle β3 at the end of the compression process is larger than the β 3a The working volume V3 when the exhaust pressure is reached is smaller than the normal V 3a Similarly, when the piston ring leaks, the pressure drop rate during the expansion process will first accelerate and then slow down, so the variable angle β4 at the starting point of the expansion process is larger than the β 4a The variable angle β1 at the end of the expansion process is greater than the β 1a The working volume V1 when the suction pressure is reached is smaller than the normal V 1a It will also decrease.

[0082] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0083] The embodiment of the present application also provides a reciprocating compressor air valve leakage fault self-diagnosis device. It should be noted that the reciprocating compressor air valve leakage fault self-diagnosis device of the embodiment of the present application can be used to execute the reciprocating compressor air valve leakage fault self-diagnosis method provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0084] The following is an introduction to the reciprocating compressor air valve leakage fault self-diagnosis device provided in an embodiment of the present application.

[0085] Figure 8 1 is a structural block diagram of a reciprocating compressor valve leakage fault self-diagnosis device according to an embodiment of the present application. Figure 8 As shown, the device comprises:

[0086] The first acquisition unit 10 is used to acquire the operating data of the reciprocating compressor, wherein the operating data at least includes the crank angle and the gas pressure in the cylinder of the reciprocating compressor.

[0087] Specifically, Figure 3 As shown, the existing high-speed data acquisition card in the coal chemical park is used to simultaneously perform multi-channel acquisition of the signals output by the pressure sensor, encoder and displacement sensor, thereby realizing the synchronous acquisition of the cylinder pressure (i.e. the above-mentioned gas pressure) and crank angle of the reciprocating compressor.

[0088] The data processing unit 20 is used to process the above-mentioned operating data in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the above-mentioned reciprocating compressor, the horizontal axis of the above-mentioned pressure-volume diagram represents the working volume of the above-mentioned cylinder, and the vertical axis of the above-mentioned pressure-volume diagram represents the above-mentioned gas pressure.

[0089] Specifically, by preprocessing the real-time collected gas pressure and crank angle in the compressor cylinder, the pV diagram of the compressor working cycle can be obtained by using image processing technology according to the relationship curve between the gas pressure in the cylinder and the working volume, that is, the gas volume diagram mentioned above, such as Figure 4 shown.

[0090] It should also be noted that the actual cycle of a typical reciprocating compressor can be divided into four processes: suction process, compression process, exhaust process, and expansion process: (1) Suction process: This is the first process of the compressor. The piston moves from the Figure 4The piston moves from position 1 to position 2. After the intake valve opens, low-pressure gas is sucked into the cylinder until the piston reaches the bottom dead center 2 and the intake valve closes. (2) Compression process: The piston moves from position 1 to position 2. Figure 4 The piston moves from position 2 to position 3. After the intake valve is closed, the low-pressure gas in the cylinder is compressed until the exhaust pressure Pd is reached for the first time. The compression process ends and the exhaust valve opens. (3) Exhaust process: The piston moves from position 2 to position 3. Figure 4 The piston moves from position 3 to position 4. After the exhaust valve opens, high-pressure gas is continuously discharged from the exhaust pipe until the piston reaches the top dead center position 4. The exhaust process ends and the exhaust valve closes. (4) Expansion process: The piston moves from position 3 to position 4. Figure 4 The middle position 4 moves to position 1. After the exhaust valve is closed, the high-pressure gas in the clearance volume expands due to the increase in volume, thereby causing the gas pressure in the cylinder to drop until the gas pressure in the cylinder reaches the suction pressure Ps for the first time. The expansion process ends, the suction valve opens, and the suction process begins again, and the second cycle begins.

[0091] The characteristic element extraction unit 30 is used to extract characteristic elements in the above-mentioned pressure-volume diagram, and the above-mentioned characteristic elements include the variable angles and working volumes of the above-mentioned reciprocating compressor during the compression process and the expansion process. The above-mentioned variable angles represent the changing speed of the gas in the above-mentioned cylinder during the working process.

[0092] Specifically, when a reciprocating compressor valve leaks, the pV diagram will change due to the influence of the pressure change in the cylinder. Therefore, analyzing the changes in the characteristic elements of the key points in the pV diagram can automatically detect valve leakage defects. The "compression process" and "expansion process" in the working process of the reciprocating compressor are in the state where the compression chamber is sealed. The impact of valve leakage on these two stages is the most obvious, which is very suitable for automatic detection of valve leakage defects. Therefore, the four key points are determined as follows: Figure 4 The starting point 2 of the compression process, the end point 3 of the compression process, the starting point 4 of the expansion process, and the end point 1 of the expansion process. The acute angle β between the pressure curves of the "compression" and "expansion" processes and the suction pressure line and the exhaust pressure line in the pV diagram represents the speed of change of the gas during the working process. The larger the angle, the faster the gas changes during the working process, and the smaller the angle, the slower the gas changes during the working process. Therefore, the state of the gas valve can be judged by comparing the changes in β. β is defined as a variable angle, such as Figure 5 β1, β2, β3, and β4 represent the variable angles of the valve at the key points. In addition, the working volume is also used as a characteristic element. Therefore, according to the pV diagram of the working process of the reciprocating compressor, the characteristic elements of the key points, namely the variable angle and the working volume, are extracted.

[0093] The feature comparison unit 40 is used to compare the difference between the numerical value of the above-mentioned feature element and the numerical value of the corresponding normal feature element to obtain a feature set. The above-mentioned normal feature element is the above-mentioned feature element corresponding to the valve of the above-mentioned reciprocating compressor in the valve fault-free state stored in the feature library.

[0094] Specifically, the extracted feature elements are compared with the feature elements of the corresponding compressor valve in the normal state in the feature library to obtain the feature element difference, and then a feature set is further obtained according to whether the feature element difference is greater than 0 or less than 0. The above feature set indicates whether the value of the above feature element increases or decreases, and further determines whether the valve fails.

[0095] The feature matching unit 50 is used to match the feature set with the feature set stored in the feature library to obtain a target feature set, where the target feature set is a feature set in the feature library that successfully matches the feature set.

[0096] Specifically, the obtained feature set is matched in the feature library to obtain a corresponding successfully matched feature set.

[0097] The query unit 60 is used to query the mapping relationship library according to the above-mentioned target feature set to obtain the current valve state of the above-mentioned reciprocating compressor. The above-mentioned current valve state is one of the following: the above-mentioned valve fault-free state, suction valve leakage, exhaust valve leakage and piston ring leakage. The above-mentioned mapping relationship library is a set formed by the mapping relationship between the feature set and the valve state.

[0098] Specifically, the mapping relationship library is queried according to the matched feature set to obtain the current valve state of the reciprocating compressor. The mapping relationship library is a reciprocating compressor valve feature library formed through automatic algorithm processing and a large amount of training, and a mapping relationship between the feature set and the valve state is established.

[0099] The sending unit 70 is used to send a prompt message when the current valve state is not the valve fault-free state, and the prompt message is used to prompt that the valve of the reciprocating compressor has a leakage fault.

[0100] Specifically, when the current valve state is not the valve fault-free state, a prompt message is issued to remind the staff to further inspect the valve of the reciprocating compressor to reduce faults.

[0101] In this embodiment, the dynamic pressure and crank angle in the compressor cylinder collected in real time are preprocessed to obtain the pressure-volume diagram of the working process of the reciprocating compressor, and the characteristic elements of the key points are extracted according to the pressure-volume diagram of the working process of the compressor. When the compressor valve leaks, the pressure-volume diagram will change accordingly due to the influence of the pressure change in the cylinder. Therefore, the change of the characteristic elements of the key points in the pressure-volume diagram can automatically detect the valve leakage defect. The value of the extracted characteristic element is compared with the characteristic element of the corresponding compressor valve in the feature library when the valve is in a fault-free state, and the result is formed into a feature set. The obtained feature set is matched in the feature library, and the compressor valve state is obtained and output according to the mapping relationship between the matched feature set and the valve state. Through the above scheme, the working state of the reciprocating compressor valve can be monitored in real time, and the diagnosis result can be automatically judged and output. The present application solves the problem that the diagnosis process of the reciprocating compressor valve leakage fault in the prior art requires human input and there is artificial interference, resulting in low accuracy of the diagnosis result.

[0102] In order to generate a pV map and thus reduce manual involvement in the diagnosis process, in an optional implementation, the data processing unit includes:

[0103] A calculation module is used to calculate the working volume of the cylinder according to the compressor parameters and the crank angle in combination with a first formula. The compressor parameters at least include the cylinder inner diameter, the crank radius, the clearance volume and the crank radius connecting rod ratio. The first formula is: V0 is the clearance volume, Di is the cylinder inner diameter of the i-th stage, r is the crank radius, θ is the crank angle, and λ is the crank radius connecting rod ratio;

[0104] A generating module processes the relationship change curve between the gas pressure and the working volume by using the image processing technology to generate the gas pressure-volume diagram during the working cycle.

[0105] In the above embodiment, the cylinder working volume is calculated based on the corresponding relationship between the compressor cylinder working volume and the crank angle, that is, the above first formula. According to the relationship curve between the gas pressure in the cylinder and the working volume, the pV diagram of the compressor working cycle process can be obtained by using image processing technology ( Figure 4 ), the vertical axis of the pV graph represents pressure, and the horizontal axis represents working volume. In order to automatically detect valve leakage faults by reversely analyzing the pV graph according to the influence of the reciprocating compressor valve on the pressure curve (pV graph) under different states.

[0106] In order to reduce manual interference and manpower input in the diagnosis process and reduce the diagnosis cost, in an optional implementation, the device further includes:

[0107] a second acquisition unit, configured to acquire a first gas volume diagram, a second gas volume diagram, a third gas volume diagram, and a normal gas volume diagram, wherein the first gas volume diagram is a gas volume diagram when the intake valve is leaking, the second gas volume diagram is a gas volume diagram corresponding to when the exhaust valve is leaking, the third gas volume diagram is a gas volume diagram corresponding to when the piston ring is leaking, and the normal gas volume diagram is a gas volume diagram corresponding to when the valve is in a fault-free state;

[0108] a first analyzing unit, used for comparing the first gas volume diagram with the normal gas volume diagram before extracting the characteristic elements in the gas pressure volume diagram, and analyzing the compression process and the expansion process to determine a first multi-angle change and a first working volume change, wherein the first multi-angle change is a multi-angle change when the intake valve leaks, and the first working volume change is a working volume change when the intake valve leaks;

[0109] a second analysis unit, for comparing the second gas volume diagram with the normal gas volume diagram, and analyzing the compression process and the expansion process to determine a second multi-angle change and a second working volume change, wherein the second multi-angle change is a multi-angle change when the exhaust valve leaks, and the second working volume change is a working volume change when the exhaust valve leaks;

[0110] a third analysis unit, for comparing the third gas volume diagram with the normal gas volume diagram, and analyzing the compression process and the expansion process to determine a third multi-angle change and a third working volume change, wherein the third multi-angle change is a multi-angle change when the piston ring leaks, and the third working volume change is a working volume change when the piston ring leaks;

[0111] The fourth analysis unit is used to perform a comprehensive analysis based on the first multi-variable angle change, the first working volume change, the second multi-variable angle change, the second working volume change, the third multi-variable angle change and the third working volume change to determine the above-mentioned characteristic elements of the above-mentioned gas volume diagram.

[0112] In the above embodiment, the above characteristic elements include a first starting point multi-variable angle, a first end point multi-variable angle, a first working volume, a second starting point multi-variable angle, a second end point multi-variable angle and a second working volume. The first starting point multi-variable angle is the multi-variable angle of the reciprocating compressor at the starting point of the compression process, the first end point multi-variable angle is the multi-variable angle of the reciprocating compressor at the end point of the compression process, the first working volume is the working volume when the exhaust pressure is reached, the second starting point multi-variable angle is the multi-variable angle of the reciprocating compressor at the starting point of the expansion process, the second end point multi-variable angle is the multi-variable angle of the reciprocating compressor at the end point of the expansion process, and the second working volume is the working volume when the suction pressure is reached. The above first gas volume diagram, the above second gas volume diagram and the above third gas volume diagram are all analyzed with the above normal gas volume diagram to determine whether the suction valve leakage, exhaust valve leakage and piston ring leakage occur respectively. The specific analysis diagrams are as follows. Figure 5 , Figure 6 and Figure 7 As shown. All processes from data collection, pV diagram formation, feature element extraction and analysis, feature library establishment and judgment result output are automatically realized by algorithms, which reduces manual interference and manpower input in the diagnosis process, improves the accuracy of diagnosis results, and reduces diagnosis costs. Therefore, according to the above reverse analysis, the characteristic elements determined in the present invention are: the variable angle β2 at the starting point of the compression process, the variable angle β3 at the end of the compression process, the working volume V3 when the exhaust pressure is reached, the variable angle β4 at the starting point of the expansion process, the variable angle β1 at the end of the expansion process, and the working volume V1 when the suction pressure is reached.

[0113] For example, in order to improve the accuracy of detecting exhaust valve leakage failure, Figure 6 As shown in FIG. 1 , when the exhaust valve leaks, the compression process becomes faster, so the variable angle β2 at the starting point of the compression process (i.e., the first starting point variable angle) is larger than the β when the exhaust valve is normal. 2a The variable angle β3 at the end of the compression process (i.e., the first end variable angle) will be larger than the β 3a (i.e. the above-mentioned normal compression end variable angle) will increase, and the working volume V3 (i.e. the above-mentioned first working volume) when the exhaust pressure is reached is larger than V 3a On the contrary, when the exhaust valve leaks, the pressure curve of the expansion process is flatter than normal, and the expansion process slows down. Therefore, the multivariable angle β4 at the starting point of the expansion process (i.e. the multivariable angle of the second starting point) is larger than the β 4a The variable angle β1 at the end of the expansion process (i.e., the variable angle at the second end point) will be smaller than the β 1a(i.e. the above-mentioned normal expansion end variable angle) will decrease, and the working volume V1 (i.e. the above-mentioned second working volume) when the suction pressure is reached is greater than V 1a The first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram, and the second normal working volume is the working volume when the suction pressure is reached in the normal working volume diagram.

[0114] In order to improve the refined management level of the reciprocating compressor, in an optional implementation manner, the above-mentioned device further includes:

[0115] a third acquisition unit, configured to obtain historical operating data of the gas valves of all the reciprocating compressors at different gas valve states before performing a difference comparison between the values ​​of the characteristic elements and the values ​​of the corresponding normal characteristic elements to obtain the characteristic set, wherein the historical operating data includes historical gas pressure and historical crank angle;

[0116] A generating unit, used for generating a corresponding historical gas volume graph according to the above historical operating condition data;

[0117] An extraction unit, used for extracting historical characteristic elements of the above historical gas volume graph;

[0118] A difference comparison unit, used for performing difference comparison between all the above historical feature elements and normal historical feature elements to form a historical feature set, and storing the above historical feature set in the above feature library;

[0119] A mapping unit is used to map the above historical feature set with the above corresponding valve state to form the above mapping relationship library, and store it in the above feature library.

[0120] In the above embodiment, the feature library defined in the present invention is obtained by collecting the cylinder pressure and crank angle of the suction valve and exhaust valve of each reciprocating compressor in the coal chemical park in different states, and repeatedly performing pV diagram generation, feature element extraction, feature element difference comparison and feature set matching. Through a large amount of training, the feature elements of the valves of the reciprocating compressors in the coal chemical park in normal states and the feature sets of the valves in different states are obtained to form a feature library, and a mapping relationship between the valve states and the feature sets is established to generate a mapping relationship library, thereby improving the level of refined management of reciprocating compressors.

[0121] In order to improve the accuracy of gas valve fault detection, in an optional implementation manner, the feature comparison unit includes:

[0122] A calculation module, performing difference calculations on the first starting point multivariable angle, the first end point multivariable angle, the first working volume, the second starting point multivariable angle, the second end point multivariable angle and the second working volume respectively with corresponding normal characteristic elements to obtain characteristic difference values, wherein the characteristic difference values ​​include the first starting point multivariable angle difference value, the first end point multivariable angle difference value, the first working volume difference value, the second starting point multivariable angle difference value, the second end point multivariable angle difference value and the second working volume difference value;

[0123] The first determination module determines the feature set according to the change direction of the feature difference, the change direction includes an increasing direction and a decreasing direction, and the feature set represents the change direction of each of the feature elements.

[0124] In the above embodiment, the result is Δβ1=β1-β 1a , Δβ2=β2-β 2a , Δβ3=β3-β 3a , Δβ4=β4-β 4a , ΔV1=V1-V 1a and ΔV3=V3-V 3a , where β2, β3, β4, and β1 are the variable angles of the valve at the start of the compression process, the variable angle at the end of the compression process, the variable angle at the start of the expansion process, and the variable angle at the end of the expansion process, respectively. V3 represents the working volume when the exhaust pressure is reached, and V1 represents the working volume when the suction pressure is reached. The parameters with the subscript a represent the corresponding normal characteristic elements mentioned above. The feature set is determined as A = {a, b, c, d, e, f}, where the elements a, b, c, d, e, and f of the feature set correspond to the change directions of Δβ2, Δβ3, ΔV3, Δβ4, Δβ1, and ΔV1, respectively. For example Figure 5 , when the suction valve leaks, Δβ2=β2-β 2a <0, Δβ3=β3-β 3a <0,ΔV3=V3-V 3a <0, Δβ4=β4-β 4a >0, Δβ1=β1-β 1a >0, ΔV1=V1-V 1a <0, then when the intake valve leaks, the feature set A={↓,↓,↓,↑,↑,↓}.

[0125] In order to improve the accuracy of detecting the leakage fault of the intake valve, in an optional implementation manner, the first analysis unit includes:

[0126] a second determining module, in the case that the gas valve state is the intake valve leakage and the compression process, comparing the starting multivariable angle, the ending multivariable angle and the working volume of the compression process in the first gas volume diagram with those in the normal gas volume diagram, and determining that the change of the first multivariable angle includes that in the compression process of the intake valve leakage, the first starting multivariable angle is smaller than the normal compression starting multivariable angle and the first ending multivariable angle is smaller than the normal compression ending multivariable angle, and the change of the first working volume includes that the first working volume is smaller than the first normal working volume, the normal compression starting multivariable angle is the first starting multivariable angle in the normal gas volume diagram, and the normal compression ending multivariable angle is the first ending multivariable angle in the normal gas volume diagram;

[0127] A third determination module, when the above-mentioned valve state is the above-mentioned intake valve leakage and the above-mentioned expansion process, compares the starting multivariable angle, the end multivariable angle and the working volume of the above-mentioned expansion process in the above-mentioned first gas volume diagram with those in the above-mentioned normal gas volume diagram, and determines that the above-mentioned first multivariable angle change also includes that in the above-mentioned expansion process of the above-mentioned intake valve leakage, the above-mentioned second starting multivariable angle is larger than the normal expansion starting multivariable angle and the above-mentioned second end multivariable angle is larger than the normal expansion end multivariable angle, and the above-mentioned first working volume change also includes that the above-mentioned second working volume is smaller than the second normal working volume, the above-mentioned normal expansion starting multivariable angle is the second starting multivariable angle in the above-mentioned normal gas volume diagram, the above-mentioned normal expansion end multivariable angle is the second end multivariable angle in the above-mentioned normal gas volume diagram, and the above-mentioned second normal working volume is the working volume when the intake pressure is reached in the above-mentioned normal working volume diagram.

[0128] In the above embodiment, if Figure 5 As shown in FIG. 1 , when the suction valve leaks, the gas continues to flow from the compression chamber to the suction pipe side during the compression process, which slows down the pressure rise. The pressure curve of the compression process is flatter than normal, and the compression process slows down. Therefore, the multivariable angle β2 at the starting point of the compression process (i.e., the multivariable angle of the first starting point mentioned above) is larger than the β 2a The variable angle β3 at the end of the compression process (i.e., the first variable angle at the end) will be smaller than the β 3a (i.e. the above-mentioned normal compression end variable angle) will decrease, and the working volume V3 (i.e. the above-mentioned first working volume) when the exhaust pressure is reached is smaller than V 3aOn the contrary, when the intake valve leaks, the gas pressure drops faster during the expansion process, and even drops sharply before the intake valve opens, reaching the intake pressure level in a faster time than usual, and the expansion process becomes faster. Therefore, the multivariable angle β4 at the starting point of the expansion process (i.e., the multivariable angle of the second starting point) is larger than the β 4a The variable angle β1 at the end of the expansion process (i.e., the variable angle at the second end point) will be larger than the β 1a (i.e. the above-mentioned normal expansion end variable angle) will increase, and the working volume V1 (i.e. the above-mentioned second working volume) when the suction pressure is reached is larger than V 1a The first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram, and the second normal working volume is the working volume when the suction pressure is reached in the normal working volume diagram.

[0129] In order to improve the accuracy of detecting piston ring leakage faults, in an optional implementation manner, the third analysis unit in step 3 includes:

[0130] a fourth determination module, in the case where the gas valve state is the piston ring leakage and the compression process, comparing the starting multivariable angle, the ending multivariable angle and the working volume of the compression process in the third gas volume diagram with those in the normal gas volume diagram, and determining that the change of the third multivariable angle includes that in the compression process of the piston ring leakage, the first starting multivariable angle is larger than the normal compression starting multivariable angle and the first ending multivariable angle is smaller than the normal compression ending multivariable angle, and the change of the third working volume includes that the first working volume is smaller than the first normal working volume, the normal compression starting multivariable angle is the first starting multivariable angle in the normal gas volume diagram, and the normal compression ending multivariable angle is the first ending multivariable angle in the normal gas volume diagram;

[0131] A fifth determination module, when the above-mentioned valve state is the above-mentioned piston ring leakage and the above-mentioned expansion process, compares the starting multivariable angle, the end multivariable angle and the working volume of the above-mentioned expansion process in the above-mentioned third gas volume diagram with those in the above-mentioned normal gas volume diagram, and determines that the above-mentioned third multivariable angle change also includes that in the above-mentioned expansion process of the above-mentioned piston ring leakage, the above-mentioned second starting multivariable angle is larger than the normal expansion starting multivariable angle and the above-mentioned second end multivariable angle is smaller than the normal expansion end multivariable angle, and the third working volume change also includes that the above-mentioned second working volume is smaller than the second normal working volume, the above-mentioned normal expansion starting multivariable angle is the second starting multivariable angle in the above-mentioned normal gas volume diagram, the above-mentioned normal expansion end multivariable angle is the second end multivariable angle in the above-mentioned normal gas volume diagram, and the above-mentioned second normal working volume is the working volume when the suction pressure is reached in the above-mentioned normal working volume diagram.

[0132] In the above embodiment, if Figure 7 As shown in the figure, when the piston ring leaks, the pressure rise speed in the compression process first accelerates and then slows down, so the variable angle β2 at the starting point of the compression process is larger than the β 2a The variable angle β3 at the end of the compression process is larger than the β 3a The working volume V3 when the exhaust pressure is reached is smaller than the normal V 3a Similarly, when the piston ring leaks, the pressure drop rate during the expansion process will first accelerate and then slow down, so the variable angle β4 at the starting point of the expansion process is larger than the β 4a The variable angle β1 at the end of the expansion process is greater than the β 1a The working volume V1 when the suction pressure is reached is smaller than the normal V 1a It will also decrease.

[0133] The above-mentioned reciprocating compressor gas valve leakage fault self-diagnosis device includes a processor and a memory, and the above-mentioned first acquisition unit, data processing unit and characteristic element extraction unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions. The above-mentioned modules are all located in the same processor; or, the above-mentioned modules are located in different processors in the form of any combination.

[0134] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters are adjusted to solve the problem that the reciprocating compressor valve leakage fault diagnosis process in the prior art requires human input and there is human interference, resulting in low accuracy of the diagnosis result.

[0135] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0136] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the reciprocating compressor valve leakage fault self-diagnosis method.

[0137] Specifically, the reciprocating compressor valve leakage fault self-diagnosis method includes:

[0138] Step S201, obtaining operating data of a reciprocating compressor, wherein the operating data at least includes a crank angle and a gas pressure in a cylinder of the reciprocating compressor;

[0139] Step S202, processing the working condition data in combination with image processing technology to generate a pressure-volume diagram of the reciprocating compressor during the working cycle, wherein the abscissa of the pressure-volume diagram represents the working volume of the cylinder, and the ordinate of the pressure-volume diagram represents the gas pressure;

[0140] Step S203, extracting characteristic elements from the pressure-volume diagram, the characteristic elements including the variable angle and working volume of the reciprocating compressor during the compression process and the expansion process, the variable angle representing the speed of change of the gas in the cylinder during the working process;

[0141] Step S204, performing a difference comparison between the value of the characteristic element and the value of the corresponding normal characteristic element to obtain a characteristic set, wherein the normal characteristic element is the characteristic element corresponding to the gas valve of the reciprocating compressor in a non-fault state stored in the characteristic library;

[0142] Step S205, matching the feature set with the feature set stored in the feature library to obtain a target feature set, where the target feature set is a feature set in the feature library that successfully matches the feature set;

[0143] Step S206, querying a mapping relationship library according to the target feature set to obtain a current valve state of the reciprocating compressor, wherein the current valve state is one of the following: the valve has no fault, the suction valve is leaking, the exhaust valve is leaking, and the piston ring is leaking, and the mapping relationship library is a set formed by mapping relationships between feature sets and valve states;

[0144] Step S207: When the current valve state is not the valve fault-free state, a prompt message is issued, wherein the prompt message is used to prompt that a leakage fault occurs in the valve of the reciprocating compressor.

[0145] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes the reciprocating compressor air valve leakage fault self-diagnosis method when running.

[0146] An embodiment of the present invention provides a reciprocating compressor air valve leakage fault self-diagnosis system, the reciprocating compressor air valve leakage fault self-diagnosis system comprises a processor, a memory and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0147] Step S201, obtaining operating data of a reciprocating compressor, wherein the operating data at least includes a crank angle and a gas pressure in a cylinder of the reciprocating compressor;

[0148] Step S202, processing the working condition data in combination with image processing technology to generate a pressure-volume diagram of the reciprocating compressor during the working cycle, wherein the abscissa of the pressure-volume diagram represents the working volume of the cylinder, and the ordinate of the pressure-volume diagram represents the gas pressure;

[0149] Step S203, extracting characteristic elements from the pressure-volume diagram, the characteristic elements including the variable angle and working volume of the reciprocating compressor during the compression process and the expansion process, the variable angle representing the speed of change of the gas in the cylinder during the working process;

[0150] Step S204, performing a difference comparison between the value of the characteristic element and the value of the corresponding normal characteristic element to obtain a characteristic set, wherein the normal characteristic element is the characteristic element corresponding to the gas valve of the reciprocating compressor in a non-fault state stored in the characteristic library;

[0151] Step S205, matching the feature set with the feature set stored in the feature library to obtain a target feature set, where the target feature set is a feature set in the feature library that successfully matches the feature set;

[0152] Step S206, querying a mapping relationship library according to the target feature set to obtain a current valve state of the reciprocating compressor, wherein the current valve state is one of the following: the valve has no fault, the suction valve is leaking, the exhaust valve is leaking, and the piston ring is leaking, and the mapping relationship library is a set formed by mapping relationships between feature sets and valve states;

[0153] Step S207: When the current valve state is not the valve fault-free state, a prompt message is issued, wherein the prompt message is used to prompt that a leakage fault occurs in the valve of the reciprocating compressor.

[0154] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0155] Step S201, obtaining operating data of a reciprocating compressor, wherein the operating data at least includes a crank angle and a gas pressure in a cylinder of the reciprocating compressor;

[0156] Step S202, processing the working condition data in combination with image processing technology to generate a pressure-volume diagram of the reciprocating compressor during the working cycle, wherein the abscissa of the pressure-volume diagram represents the working volume of the cylinder, and the ordinate of the pressure-volume diagram represents the gas pressure;

[0157] Step S203, extracting characteristic elements from the pressure-volume diagram, the characteristic elements including the variable angle and working volume of the reciprocating compressor during the compression process and the expansion process, the variable angle representing the speed of change of the gas in the cylinder during the working process;

[0158] Step S204, performing a difference comparison between the value of the characteristic element and the value of the corresponding normal characteristic element to obtain a characteristic set, wherein the normal characteristic element is the characteristic element corresponding to the gas valve of the reciprocating compressor in a non-fault state stored in the characteristic library;

[0159] Step S205, matching the feature set with the feature set stored in the feature library to obtain a target feature set, where the target feature set is a feature set in the feature library that successfully matches the feature set;

[0160] Step S206, querying a mapping relationship library according to the target feature set to obtain a current valve state of the reciprocating compressor, wherein the current valve state is one of the following: the valve has no fault, the suction valve is leaking, the exhaust valve is leaking, and the piston ring is leaking, and the mapping relationship library is a set formed by mapping relationships between feature sets and valve states;

[0161] Step S207: When the current valve state is not the valve fault-free state, a prompt message is issued, wherein the prompt message is used to prompt that a leakage fault occurs in the valve of the reciprocating compressor.

[0162] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0163] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0164] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0165] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0166] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0167] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0168] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0169] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0170] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0171] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0172] 1) The self-diagnosis method for reciprocating compressor valve leakage fault of the present application obtains the pressure-volume diagram of the working process of the reciprocating compressor by pre-processing the dynamic pressure and crank angle in the compressor cylinder collected in real time, and extracts the characteristic elements of the key points according to the pressure-volume diagram of the working process of the compressor. When the compressor valve leaks, the pressure-volume diagram will change accordingly due to the influence of the pressure change in the cylinder. Therefore, the change of the characteristic elements of the key points in the pressure-volume diagram can automatically detect the valve leakage defect. The value of the extracted characteristic element is compared with the characteristic element of the corresponding compressor valve in the feature library when the valve is in a fault-free state, and the result is formed into a feature set. The obtained feature set is matched in the feature library, and the compressor valve state is obtained and output according to the mapping relationship between the matched feature set and the valve state. Through the above scheme, the working state of the reciprocating compressor valve can be monitored in real time, and the diagnosis result can be automatically judged and output. The present application solves the problem that the diagnosis process of the reciprocating compressor valve leakage fault in the prior art requires human input and there is artificial interference, resulting in low accuracy of the diagnosis result.

[0173] 2) The reciprocating compressor valve leakage fault self-diagnosis device of the present application obtains the pressure-volume diagram of the working process of the reciprocating compressor by pre-processing the dynamic pressure and crank angle in the compressor cylinder collected in real time, and extracts the characteristic elements of the key points according to the pressure-volume diagram of the compressor working process. When the compressor valve leaks, the pressure-volume diagram will change accordingly due to the influence of the pressure change in the cylinder. Therefore, the change of the characteristic elements of the key points in the pressure-volume diagram can automatically detect the valve leakage defect. The value of the extracted characteristic element is compared with the characteristic element of the corresponding compressor valve in the feature library when the valve is in a fault-free state, and the result is formed into a feature set. The obtained feature set is matched in the feature library, and the compressor valve state is obtained and output according to the mapping relationship between the matched feature set and the valve state. Through the above scheme, the working state of the reciprocating compressor valve can be monitored in real time, and the diagnosis result can be automatically judged and output. The present application solves the problem that the diagnosis process of the reciprocating compressor valve leakage fault in the prior art requires human input and there is artificial interference, resulting in low accuracy of the diagnosis result.

[0174] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A self-diagnosis method for reciprocating compressor valve leakage fault, characterized in that: include: Acquiring operating data of a reciprocating compressor, wherein the operating data at least includes a crank angle and a gas pressure in a cylinder of the reciprocating compressor; Processing the working condition data in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the reciprocating compressor, wherein the abscissa of the pressure-volume diagram represents the working volume of the cylinder, and the ordinate of the pressure-volume diagram represents the gas pressure; Extracting characteristic elements from the pressure-volume diagram, the characteristic elements including the variable angle and working volume of the reciprocating compressor during the compression process and the expansion process, the variable angle representing the speed of change of the gas in the cylinder during the working process; Compare the difference between the value of the characteristic element and the value of the corresponding normal characteristic element to obtain a characteristic set, wherein the normal characteristic element is the characteristic element corresponding to the gas valve of the reciprocating compressor in a non-fault state stored in the characteristic library; Matching the feature set with the feature set stored in the feature library to obtain a target feature set, where the target feature set is a feature set in the feature library that successfully matches the feature set; According to the target feature set, a mapping relationship library is queried to obtain a current valve state of the reciprocating compressor, wherein the current valve state is one of the following: the valve has no fault, the suction valve is leaking, the exhaust valve is leaking, and the piston ring is leaking, and the mapping relationship library is a set formed by mapping relationships between feature sets and valve states; In the case that the current gas valve state is not the gas valve non-fault state, a prompt message is issued, wherein the prompt message is used to prompt that a leakage fault occurs in the gas valve of the reciprocating compressor.

2. The method according to claim 1, characterized in that The working condition data is processed in combination with image processing technology to generate a pressure-volume diagram during the working cycle of the reciprocating compressor, including: The working volume of the cylinder is calculated according to the compressor parameters and the crank angle in combination with a first formula, wherein the compressor parameters at least include the cylinder inner diameter, the crank radius, the clearance volume and the crank radius connecting rod ratio, and the first formula is: V0 is the clearance volume, Di is the cylinder inner diameter of the i-th stage, r is the crank radius, θ is the crank angle, and λ is the crank radius connecting rod ratio; The image processing technology is used to process the relationship change curve between the gas pressure and the working volume to generate the gas pressure-volume diagram during the working cycle.

3. The method according to claim 1, characterized in that: The characteristic elements include a first starting point multi-variable angle, a first end point multi-variable angle, a first working volume, a second starting point multi-variable angle, a second end point multi-variable angle and a second working volume. The first starting point multi-variable angle is a multi-variable angle of the reciprocating compressor at the starting point of the compression process, the first end point multi-variable angle is a multi-variable angle of the reciprocating compressor at the end point of the compression process, the first working volume is a working volume when the exhaust pressure is reached, the second starting point multi-variable angle is a multi-variable angle of the reciprocating compressor at the starting point of the expansion process, the second end point multi-variable angle is a multi-variable angle of the reciprocating compressor at the end point of the expansion process, and the second working volume is a working volume when the suction pressure is reached. Before extracting the characteristic elements in the pressure-volume diagram, the method further includes: Obtaining a first gas volume diagram, a second gas volume diagram, a third gas volume diagram and a normal gas volume diagram, wherein the first gas volume diagram is a gas volume diagram when the intake valve is leaking, the second gas volume diagram is a gas volume diagram corresponding to when the exhaust valve is leaking, the third gas volume diagram is a gas volume diagram corresponding to when the piston ring is leaking, and the normal gas volume diagram is a gas volume diagram corresponding to when the gas valve is in a fault-free state; Comparing the first gas volume diagram with the normal gas volume diagram, and analyzing the compression process and the expansion process, determining a first multi-angle change situation and a first working volume change situation, wherein the first multi-angle change situation is a multi-angle change situation when the intake valve leaks, and the first working volume change situation is a working volume change situation when the intake valve leaks; The second gas volume diagram is compared with the normal gas volume diagram, and the compression process and the expansion process are analyzed to determine a second multi-angle change situation and a second working volume change situation, wherein the second multi-angle change situation is a multi-angle change situation when the exhaust valve leaks, and the second working volume change situation is a working volume change situation when the exhaust valve leaks; The third gas volume diagram is compared with the normal gas volume diagram, and the compression process and the expansion process are analyzed to determine a third multi-angle change situation and a third working volume change situation, wherein the third multi-angle change situation is a multi-angle change situation when the piston ring leaks, and the third working volume change situation is a working volume change situation when the piston ring leaks; The characteristic elements of the gas volume diagram are determined by performing a comprehensive analysis based on the first multi-variable angle change, the first working volume change, the second multi-variable angle change, the second working volume change, the third multi-variable angle change and the third working volume change.

4. The method according to claim 1, characterized in that: Before performing a difference comparison between the value of the characteristic element and the value of the corresponding normal characteristic element to obtain the characteristic set, the method further includes: Acquire historical operating condition data of the gas valves of all the reciprocating compressors at different gas valve states, wherein the historical operating condition data includes historical gas pressure and historical crank angle; generating a corresponding historical gas volume graph according to the historical operating condition data; Extracting historical characteristic elements of the historical gas volume map; Comparing the differences between all the historical feature elements and normal historical feature elements to form a historical feature set, and storing the historical feature set in the feature library; The historical feature set is mapped with the corresponding valve state to form the mapping relationship library, and is stored in the feature library.

5. The method according to claim 3, characterized in that: Compare the difference between the value of the characteristic element and the value of the corresponding normal characteristic element to obtain a characteristic set, including: Performing difference operations on the first starting point multivariable angle, the first end point multivariable angle, the first working volume, the second starting point multivariable angle, the second end point multivariable angle and the second working volume respectively with corresponding normal characteristic elements to obtain characteristic difference values, wherein the characteristic difference values ​​include the first starting point multivariable angle difference value, the first end point multivariable angle difference value, the first working volume difference value, the second starting point multivariable angle difference value, the second end point multivariable angle difference value and the second working volume difference value; The feature set is determined according to a change direction of the feature difference, wherein the change direction includes an increasing direction and a decreasing direction, and the feature set represents a change direction of each of the feature elements.

6. The method according to claim 3, characterized in that Comparing the first gas volume diagram with the normal gas volume diagram, and analyzing the compression process and the expansion process to determine a change in the first multi-variable angle and a change in the first working volume, includes: In the case where the gas valve state is the intake valve leakage and the compression process, the starting multivariable angle, the end multivariable angle and the working volume of the compression process in the first gas volume diagram are compared with those in the normal gas volume diagram, and it is determined that the change of the first multivariable angle includes that in the compression process of the intake valve leakage, the first starting multivariable angle is smaller than the normal compression starting multivariable angle and the first end multivariable angle is smaller than the normal compression end multivariable angle, and the change of the first working volume includes that the first working volume is smaller than the first normal working volume, the normal compression starting multivariable angle is the first starting multivariable angle in the normal gas volume diagram, the normal compression end multivariable angle is the first end multivariable angle in the normal gas volume diagram, and the first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram; When the gas valve state is the intake valve leakage and the expansion process, the starting multivariable angle, the end multivariable angle and the working volume of the expansion process in the first gas volume diagram are compared with those in the normal gas volume diagram to determine that the change of the first multivariable angle also includes that in the expansion process of the intake valve leakage, the second starting multivariable angle is larger than the normal expansion starting multivariable angle and the second end multivariable angle is larger than the normal expansion end multivariable angle, and the change of the first working volume also includes that the second working volume is smaller than the second normal working volume, the normal expansion starting multivariable angle is the second starting multivariable angle in the normal gas volume diagram, the normal expansion end multivariable angle is the second end multivariable angle in the normal gas volume diagram, and the second normal working volume is the working volume when the intake pressure is reached in the normal working volume diagram.

7. The method according to claim 3, characterized in that Comparing the third gas volume diagram with the normal gas volume diagram, and analyzing the compression process and the expansion process to determine the change of the third variable angle and the change of the third working volume, including: In the case where the valve state is the piston ring leakage and the compression process, the starting multivariable angle, the end multivariable angle and the working volume of the compression process in the third gas volume diagram are compared with those in the normal gas volume diagram, and it is determined that the change of the third multivariable angle includes that in the compression process of the piston ring leakage, the first starting multivariable angle is larger than the normal compression starting multivariable angle and the first end multivariable angle is smaller than the normal compression end multivariable angle, and the change of the third working volume includes that the first working volume is smaller than the first normal working volume, the normal compression starting multivariable angle is the first starting multivariable angle in the normal gas volume diagram, the normal compression end multivariable angle is the first end multivariable angle in the normal gas volume diagram, and the first normal working volume is the working volume when the exhaust pressure is reached in the normal working volume diagram; When the valve state is the piston ring leakage and the expansion process, the starting multivariable angle, the end multivariable angle and the working volume of the expansion process in the third gas volume diagram are compared with those in the normal gas volume diagram to determine that the third multivariable angle change also includes that the second starting multivariable angle is larger than the normal expansion starting multivariable angle and the second end multivariable angle is smaller than the normal expansion end multivariable angle in the expansion process of the piston ring leakage, and the third working volume change also includes that the second working volume is smaller than the second normal working volume, the normal expansion starting multivariable angle is the second starting multivariable angle in the normal gas volume diagram, the normal expansion end multivariable angle is the second end multivariable angle in the normal gas volume diagram, and the second normal working volume is the working volume when the suction pressure is reached in the normal working volume diagram.

8. A reciprocating compressor valve leakage fault self-diagnosis device, characterized in that: The device comprises: A first acquisition unit, configured to acquire operating data of a reciprocating compressor, wherein the operating data at least includes a crank angle and a gas pressure in a cylinder of the reciprocating compressor; a data processing unit, configured to process the working condition data in combination with an image processing technique to generate a pressure-volume diagram during a working cycle of the reciprocating compressor, wherein the abscissa of the pressure-volume diagram represents the working volume of the cylinder, and the ordinate of the pressure-volume diagram represents the gas pressure; a characteristic element extraction unit, used to extract characteristic elements from the pressure-volume diagram, wherein the characteristic elements include a variable angle and a working volume of the reciprocating compressor during a compression process and an expansion process, wherein the variable angle represents a speed of change of the gas in the cylinder during the working process; A feature comparison unit, used for performing a difference comparison between the value of the feature element and the value of the corresponding normal feature element to obtain a feature set, wherein the normal feature element is the feature element of the gas valve of the reciprocating compressor stored in the feature library when the gas valve is in a non-fault state; A feature matching unit, used for matching the feature set with a feature set stored in the feature library to obtain a target feature set, wherein the target feature set is a feature set in the feature library that successfully matches the feature set; A query unit, configured to query a mapping relationship library according to the target feature set to obtain a current valve state of the reciprocating compressor, wherein the current valve state is one of the following: a non-fault state of the valve, a suction valve leakage, an exhaust valve leakage, and a piston ring leakage, and the mapping relationship library is a set formed by mapping relationships between feature sets and valve states; The issuing unit is used to issue a prompt message when the current gas valve state is not the gas valve fault-free state, wherein the prompt message is used to prompt that the gas valve of the reciprocating compressor has a leakage fault.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A reciprocating compressor valve leakage fault self-diagnosis system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Images