Fault detection method and device, computer device and computer readable storage medium

Abstract

The application discloses a kind of fault detection method, device, computer equipment and computer readable storage medium, applied to reliability field, the method comprises: obtaining the structural parameter of compressor, process parameter and pressure change, will be according to structural parameter and process parameter, generate first pressure-gas volume diagram;According to structural parameter and pressure change, generate second pressure-gas volume diagram;Then, first and second pressure-gas volume diagram are superimposed, obtain third pressure-gas volume diagram;Then, third pressure-gas volume diagram is carried out logarithmic coordinate transformation and natural coordinate transformation, obtain fourth pressure-gas volume diagram;Finally, the fault prediction result of fourth pressure-gas volume diagram is obtained using the preset convolutional neural network model.Therefore, the difference between the indicator diagram under the theoretical condition and the indicator diagram under the actual condition can be obviously reflected, so that the model can accurately predict whether the compressor is faulty and the corresponding fault category.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of reliability, in particular to a fault detection method and device, computer equipment and a computer readable storage medium. BACKGROUND

[0002] Because the cylinder pressure distribution of the reciprocating compressor can effectively reflect whether the reciprocating compressor is faulty, at present, the cylinder pressure signal is often converted into an indicator diagram, and the changes of the pressure in the cylinder and the thermodynamic process based on the indicator diagram are displayed to determine the operation of the reciprocating compressor.

[0003] However, the indicator diagrams corresponding to different fault conditions of the reciprocating compressor have differences in shape, but also have similarities, thus leading to the error detection of the fault detection method based on the indicator diagram. SUMMARY

[0004] Therefore, the present application provides a fault detection method and device, computer equipment and a computer readable storage medium to improve the current situation of error detection of the fault detection method based on the indicator diagram.

[0005] In a first aspect, the present application provides a fault detection method, comprising:

[0006] obtaining the structure parameters, process parameters and pressure changes of the reciprocating compressor within a preset working time;

[0007] generating a first pressure-gas volume diagram of the reciprocating compressor under a theoretical condition according to the structure parameters and the process parameters;

[0008] generating a second pressure-gas volume diagram of the reciprocating compressor under an actual condition according to the structure parameters and the pressure changes within the preset working time;

[0009] superimposing the first pressure-gas volume diagram and the second pressure-gas volume diagram to obtain a third pressure-gas volume diagram;

[0010] performing logarithmic coordinate transformation on the third pressure-gas volume diagram, and mapping the third pressure-gas volume diagram after coordinate transformation to a natural coordinate system according to a preset shape function to perform isoparametric element normalization to obtain a fourth pressure-gas volume diagram;

[0011] inputting the fourth pressure-gas volume diagram into a preset convolutional neural network model to obtain a fault prediction result of the reciprocating compressor.

[0012] Optionally, in an implementation provided by the embodiment of the present application, the structure parameters include a clearance volume, a piston stroke, and a cylinder radius, and the process parameters include an intake and exhaust pressure, an intake and exhaust temperature, and a composition of the gas.

[0013] The generating the first pressure-gas volume diagram of the reciprocating compressor in a theoretical case according to the structure parameters and the process parameters includes:

[0014] The specific heat capacity at constant pressure and the specific heat capacity at constant volume are calculated by using the intake and exhaust pressure, the intake and exhaust temperature, and the composition of the gas.

[0015] The adiabatic indices of the reciprocating compressor in the expansion and compression processes are calculated based on the specific heat capacity at constant pressure and the specific heat capacity at constant volume.

[0016] The theoretical maximum working volume and the theoretical minimum working volume of the reciprocating compressor are calculated according to the clearance volume, the piston stroke, and the cylinder diameter.

[0017] The first pressure-gas volume diagram of the reciprocating compressor in a theoretical case is generated according to the adiabatic indices, the intake and exhaust pressure, the theoretical maximum working volume, and the theoretical minimum working volume.

[0018] Optionally, in an implementation provided by the embodiment of the present application, the reciprocating compressor is provided with a dynamic pressure sensor, the structure parameters include a piston stroke, a cylinder diameter, a connecting rod length, a crank angle, and a clearance volume, and the pressure change in the preset working time period includes pressure change data detected by the dynamic pressure sensor in the preset working time period.

[0019] The generating the second pressure-gas volume diagram of the reciprocating compressor in an actual case according to the structure parameters and the pressure change in the preset working time period includes:

[0020] The working volume change of the reciprocating compressor in the preset working time period is calculated by using a preset formula based on the piston stroke, the cylinder diameter, the crank angle, the connecting rod length, and the clearance volume.

[0021] The second pressure-gas volume diagram of the reciprocating compressor in an actual case is generated according to the pressure change data and the working volume change.

[0022] Further, in an implementation provided by the embodiment of the present application, the preset formula includes:

[0023]

[0024] In the formula, V represents a working volume, S represents a piston stroke, θ represents a crank angle, l represents a connecting rod length, B represents a cylinder inner diameter, V cl represents a clearance volume.

[0025] Optionally, in an implementation provided by the present application, the preset shape function comprises:

[0026] x=N1x1+N2x2+N3x3+N4x4

[0027] y=N1y1+N2y2+N3y3+N4y4

[0028]

[0029] ξ0=ξ i ξ,i=[1,2,3,4]

[0030] η0=η i η,i=[1,2,3,4]

[0031] wherein x and y represent horizontal and vertical coordinates in a natural coordinate system, x1, x2, x3, x4, y1, y2, y3, y4 represent horizontal and vertical coordinates of four corner points of a first logarithmic pressure-gas volume diagram, N i represents a preset shape function, ξ and η represent dimensionless unit local coordinates of coordinate changes, ξ i and η i represent dimensionless unit local coordinates of the i-th corner point.

[0032] Optionally, in an implementation provided by the present application, the method further comprises:

[0033] storing the fourth pressure-gas volume diagram into a preset database, wherein data in the preset database is used to constitute a training set corresponding to the convolutional neural network model.

[0034] Optionally, in an implementation provided by the present application, the convolutional neural network model comprises a feature extraction module and a classification module connected in sequence, the feature extraction module comprises four convolutional layers connected in sequence, and the classification module comprises three fully connected layers connected in sequence.

[0035] Optionally, in an implementation provided by the present application, the fault prediction result comprises: intake valve leakage, exhaust valve leakage, piston ring leakage, exhaust valve plate jumping off the valve seat, intake valve biting / clogging, exhaust valve biting / clogging, excessive cylinder clearance volume, valve plate vibration, small cross-sectional area of an intake valve or an intake pipe passage, small cross-sectional area of an exhaust valve or an exhaust pipe passage, and no fault.

[0036] In a second aspect, an embodiment of the present application provides a fault detection device, comprising:

[0037] an acquisition module configured to acquire structural parameters and process parameters of the reciprocating compressor and pressure changes of the reciprocating compressor within a preset working time length;

[0038] a first generation module configured to generate a first pressure-gas volume diagram of the reciprocating compressor in a theoretical case according to the structural parameters and the process parameters;

[0039] a second generation module configured to generate a second pressure-gas volume diagram of the reciprocating compressor in an actual case according to the structural parameters and the pressure changes within the preset working time length;

[0040] a superposition module configured to superimpose the first pressure-gas volume diagram and the second pressure-gas volume diagram to obtain a third pressure-gas volume diagram;

[0041] a transformation module configured to perform logarithmic coordinate transformation on the third pressure-gas volume diagram, and map the third pressure-gas volume diagram after coordinate transformation to a natural coordinate system according to a preset shape function to perform isoparametric element normalization, to obtain a fourth pressure-gas volume diagram;

[0042] a prediction module configured to input the fourth pressure-gas volume diagram into a preset convolutional neural network model to obtain a fault prediction result of the reciprocating compressor.

[0043] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the computer program performs the fault detection method disclosed in any one of the first aspect when running on the processor.

[0044] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program performs the fault detection method disclosed in any one of the first aspect when running on the processor.

[0045] In the fault detection method provided by the embodiment of the application, after the computer device obtains the structure parameters and process parameters of the compressor and the pressure change of the compressor within a preset working time, the computer device generates a first pressure-gas volume diagram of the compressor under a theoretical condition according to the structure parameters and the process parameters, to obtain a performance diagram of the compressor under a good condition of each component; and generates a second pressure-gas volume diagram of the compressor under an actual condition according to the structure parameters and the pressure change within the preset working time, to obtain a performance diagram of the compressor under the actual condition after each component of the compressor is worn out / faulty due to actual work; then, the first pressure-gas volume diagram and the second pressure-gas volume diagram are superimposed to obtain a third pressure-gas volume diagram, so that the third pressure-gas volume diagram simultaneously exhibits two curves to reflect the difference between the actual condition and the theoretical condition; then, the third pressure-gas volume diagram is subjected to logarithmic coordinate transformation, and the third pressure-gas volume diagram after coordinate transformation is mapped to a natural coordinate system according to a preset shape function to perform isoparametric element normalization, to obtain a fourth pressure-gas volume diagram, so that the difference between the actual condition and the theoretical condition in the third pressure-gas volume diagram is amplified, and the normalization processing of the performance diagram is realized; finally, the fourth pressure-gas volume diagram is input into a preset convolutional neural network model to obtain a fault prediction result of the compressor.

[0046] Based on this, the embodiment of the application is based on coordinate transformation and coordinate mapping, so that the difference between the performance diagram under the theoretical condition and the performance diagram under the actual condition can be obviously reflected, and then the convolutional neural network model can efficiently capture the image features in the fourth pressure-gas volume diagram, so that whether the reciprocating compressor is faulty and the fault category corresponding to the fault can be accurately predicted. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the protection scope of the present application. In each drawing, similar components are denoted by similar reference numerals.

[0048] Figure 1 A flowchart of a first fault detection method provided by the embodiment of the application is shown;

[0049] Figure 2 A flowchart of a second fault detection method provided by the embodiment of the application is shown;

[0050] Figure 3 A flowchart of a third fault detection method provided by the embodiment of the application is shown;

[0051] Figure 4a and Figure 4bA first curve diagram and a second curve diagram provided by the embodiment of the present application are respectively shown;

[0052] Figure 5 A fourth pressure-gas volume diagram provided by the embodiment of the present application is shown;

[0053] Figure 6 A structure diagram of a fault detection device provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application.

[0055] The components of the embodiments of the present application generally described and illustrated in the accompanying drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0056] Hereinafter, the terms "include", "have", and their conjugates, used in various embodiments of the present application, are merely intended to denote a specific characteristic, number, step, operation, element, component, or a combination thereof, and should not be construed as excluding the existence or possibility of one or more other features, numbers, steps, operations, elements, components, or combinations thereof.

[0057] In addition, the terms "first", "second", "third", and the like are used only to distinguish descriptions, and should not be understood as indicating or implying relative importance.

[0058] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present application belong. The terms (such as terms defined in a generally used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized or overly formal meaning, unless clearly defined in various embodiments of the present application.

[0059] Embodiment 1

[0060] Referring to Figure 1, shows a flowchart of a first fault detection method provided by an embodiment of the present application, and the fault detection method provided by the embodiment of the present application comprises:

[0061] S110, obtaining structure parameters, process parameters of the reciprocating compressor, and pressure changes of the reciprocating compressor within a preset working time length.

[0062] It can be understood that the structure parameters refer to the size, shape and other data of the reciprocating compressor as a whole or in part, such as piston stroke, cylinder diameter, connecting rod length, and clearance volume of the compressor.

[0063] The process parameters refer to the basic data or indicators of a certain process in the process of manufacturing the reciprocating compressor. In the embodiment of the present application, the process parameters include but are not limited to inlet and outlet air pressure, inlet and outlet air temperature, and composition of the gas. It can be understood that the gas in the embodiment of the present application is the gas compressed by the reciprocating compressor, and when the reciprocating compressor is applied in different scenarios, the composition of the gas needs to be confirmed according to the actual situation.

[0064] The pressure changes within the preset working time length represent the pressure change of the cylinder of the reciprocating compressor when the reciprocating compressor is working. In a feasible manner, the embodiment of the present application uses a dynamic pressure sensor installed on each stage of the cylinder of the reciprocating compressor to obtain the pressure change data, that is, the pressure change condition.

[0065] S120, generating a first pressure-gas volume diagram of the reciprocating compressor under a theoretical condition according to the structure parameters and the process parameters.

[0066] That is, the computer device of the embodiment of the present application will determine the pressure change and working volume change of the cylinder of the reciprocating compressor under the theoretical condition according to the received structure parameters and process parameters, so as to generate a PV (Pressure Volume) diagram of the compressor under the theoretical condition, that is, the first pressure-gas volume diagram. Wherein, the cylinder working volume change is the gas volume change.

[0067] It should be understood that the first PV diagram generated by the computer device in the embodiment of the present application is used to indicate the theoretical inlet air pressure, the theoretical outlet air pressure, the theoretical maximum working volume and the theoretical minimum working volume of the cylinder in the reciprocating compressor under the condition that each device / structure is in good condition. It can be understood that in the theoretical working state, the compressor always compresses and discharges the gas with the theoretical inlet air pressure, the theoretical outlet air pressure, the theoretical maximum working volume and the theoretical minimum working volume.

[0068] It can be understood that the process of generating the first pressure-gas volume diagram can be set according to the actual situation, such as in a feasible manner provided by the embodiment of the present application, which can be specifically referred toFigure 2 FIG. 2 shows a flow diagram of a second fault detection method according to an embodiment of the present application, wherein the structure parameters include clearance volume, piston stroke and cylinder radius, and the process parameters include intake and exhaust pressure, intake and exhaust temperature, and gas composition;

[0069] Further, the S120 includes:

[0070] S121, calculating specific heat at constant pressure and specific heat at constant volume based on the intake and exhaust pressure, the intake and exhaust temperature, and the gas composition;

[0071] S122, calculating adiabatic index of the reciprocating compressor in expansion and compression processes respectively based on the specific heat at constant pressure and the specific heat at constant volume;

[0072] S123, calculating theoretical maximum working volume and theoretical minimum working volume of the reciprocating compressor according to the clearance volume, the piston stroke and the cylinder diameter;

[0073] S124, generating a first pressure-gas volume diagram of the reciprocating compressor in a theoretical case according to the adiabatic index, the intake and exhaust pressure, the theoretical maximum working volume and the theoretical minimum working volume.

[0074] That is, the computer device in the embodiment of the present application calculates and determines the pressure and working volume of the cylinder of the reciprocating compressor in a theoretical working case according to the acquired process parameters.

[0075] It can be understood that the intake and exhaust pressure in the process parameters is used to indicate the theoretical intake pressure and the theoretical working exhaust pressure of the cylinder of the reciprocating compressor in the theoretical working case, and also indicates the upper and lower limits of the vertical axis of the first pressure-gas volume diagram.

[0076] It can also be understood that the upper and lower limits of the horizontal axis of the first pressure-gas volume diagram are the maximum and minimum values of the working volume of the cylinder, that is, the working volume of the cylinder when the cylinder is in the intake and exhaust states. It is not difficult to understand that the calculation process of the maximum and minimum values of the working volume of the cylinder can be set according to the actual situation, and in the feasible manner provided by the embodiment of the present application, the calculation process specifically includes:

[0077] First, the specific heat at constant pressure and the specific heat at constant volume are calculated based on the intake and exhaust pressure, the intake and exhaust temperature, and the gas composition. The specific heat at constant pressure indicates that the specific heat of a unit mass of a substance increases by 1K when the pressure is constant; the specific heat at constant volume indicates that a unit mass of a certain substance absorbs heat when the volume of the object does not change. In an example, the composition of the gas is shown in Table 1.

[0078] Table 1

[0079] Mixed gas Mole percentage Molar mass H2O 0.23732 18 CH4 68 16 C2H6 11.8 30 C3H8 8.6 44 C4H10-iso 3 58 C4H10-norm 3.8 58 C5H12-iso 1.6 72 C5H12-norm 0.9 72 C6H14 0.6 86 C7H16 0.13 100 C8H18 0.02 114 C9H20 0.01 128 C10H22 0.1866 142 N2 0.18 28 CO2 0.9 44

[0080] Then, the adiabatic index of the compressor in the expansion and compression processes is calculated based on the following formula:

[0081]

[0082] In the formula, K represents the adiabatic index, c p represents the specific heat capacity at constant pressure, c v represents the specific heat capacity at constant volume.

[0083] Exemplarily, in an example of the embodiment of the present application, the adiabatic indexes corresponding to the cylinders of different levels are shown in Table 2, i.e., the adiabatic index corresponding to the first-level cylinder is 1.45, and the adiabatic index corresponding to the second-level cylinder is 1.59.

[0084] Table 2

[0085]

[0086] Then, according to the piston stroke, the clearance volume, the preset constant, the intake and exhaust gas pressure, and the adiabatic index, the maximum and minimum values of the cylinder working volume, i.e., the theoretical maximum working volume and the theoretical minimum working volume, are calculated by combining the expansion process equation and the compression process equation of the compressor, so as to determine the upper and lower limits of the horizontal axis of the first pressure-gas volume diagram. The relationship among the working volume, the preset constant, the intake and exhaust gas pressure, and the adiabatic index is shown in the following formula:

[0087]

[0088]

[0089] In the formula, K1 and K2 represent the preset constant, P d represents the exhaust gas pressure, P s represents the intake gas pressure, k represents the adiabatic index, V min represents the theoretical minimum working volume, V max represents the theoretical maximum working volume.

[0090] It should be noted that in the process of calculating the theoretical maximum working volume and the theoretical minimum working volume, the clearance volume is also considered, so as to accurately describe the change of the working volume of the compressor cylinder.

[0091] For example, in an example provided by the embodiment of the present application, the theoretical maximum working volume and the theoretical minimum working volume of the cylinders of different levels are shown in Table 3.

[0092] Table 3

[0093]

[0094]

[0095] In the table, V' max , V' min , K'1 and K'2 represent the corresponding maximum working volume, minimum working volume, first preset constant and second preset constant on the cylinder head side respectively; V" max , V" min , K"2 and K"1 represent the corresponding maximum working volume, minimum working volume, first preset constant and second preset constant on the cylinder shaft side respectively. Furthermore, the theoretical maximum working volume in the embodiment of the present application is the maximum working volume, and the theoretical minimum working volume is the clearance volume, such as the maximum working volume V' max on the cylinder head side of the primary cylinder in Table 3.

[0096] Based on this, after the computer device in the embodiment of the present application obtains the intake and exhaust pressures, i.e. the maximum gas pressure and minimum gas pressure of each stage of the cylinder of the compressor under the theoretical condition, and obtains the theoretical maximum working volume and the theoretical minimum working volume of the compressor, i.e. determines the upper and lower limits of the vertical axis and the upper and lower limits of the horizontal axis of the first pressure-gas volume diagram, and obtains four corner points of the first pressure-gas volume diagram, the first pressure-gas volume diagram is drawn according to the four corner points, i.e. the indicator diagram of the cylinder of the reciprocating compressor under the theoretical condition is obtained.

[0097] S130, generating a second pressure-gas volume diagram of the reciprocating compressor under the actual condition according to the structural parameters and the pressure change in the working preset time length.

[0098] That is, the computer device in the embodiment of the present application calculates the working volume change, i.e. the gas volume change of the cylinder of the reciprocating compressor under the actual condition based on the structural parameters; and determines the pressure change when the cylinder generates the working volume change according to the pressure change collected in the working preset time length, and further draws the second pressure-gas volume diagram. Therefore, in the subsequent process, the deviation between the actual condition and the theoretical condition can be accurately determined by comparing the first pressure-gas volume diagram under the theoretical condition and the second pressure-gas volume diagram under the actual condition, and the fault condition of the compressor is determined based on this.

[0099] It should be noted that S120 and S130 can be executed in any order or simultaneously, and the order of S120 and S130 is not limited in the embodiment of the present application.

[0100] In addition, it can be understood that the second pressure-gas volume diagram can be generated in various ways according to actual conditions, for example, in one possible way, a corresponding sensor can be arranged in the compressor to obtain the pressure change and volume change of the cylinder of the compressor.

[0101] In one possible way provided by the embodiment of the present application, referring to Figure 3 , a flowchart of a third fault detection method provided by the embodiment of the present application is shown, that is, in this possible way, the reciprocating compressor of the embodiment of the present application is provided with a dynamic pressure sensor, the structural parameters include piston stroke, cylinder diameter, connecting rod length, crank angle and clearance volume, and the pressure change in the preset working time includes pressure change data detected by the dynamic pressure sensor in the preset working time.

[0102] Further, the S130 includes:

[0103] S131, based on the piston stroke, the cylinder diameter, the crank angle, the connecting rod length and the clearance volume, the working volume change of the reciprocating compressor in the preset working time is calculated by using a preset formula.

[0104] S132, according to the pressure change data and the working volume change, a second pressure-gas volume diagram of the reciprocating compressor under actual conditions is generated.

[0105] That is, the computer device in the embodiment of the present application will calculate the working volume change of the compressor in the preset working time based on the preset formula and the cylinder diameter, the crank angle, the connecting rod length and the clearance volume in the structural parameters.

[0106] Optionally, the preset formula is as follows:

[0107]

[0108] In the formula, V represents the working volume, S represents the piston stroke, θ represents the crank angle, l represents the connecting rod length, B represents the cylinder diameter, and V represents the clearance volume. cl

[0109] Based on the above calculation method of the working volume, the computer device in the embodiment of the present application will determine the working volume change of the compressor cylinder in the preset working time according to the volume change of the cylinder in one cycle of the crank rotation, that is, according to the change of θ.

[0110] ​Further, after obtaining the working volume change of the compressor cylinder within the preset working time length, the computer device determines the pressure change of the working volume of the compressor cylinder when the working volume changes according to the data detected by the dynamic pressure sensor within the preset time length, and then draws an actual indicator diagram of the compressor, i.e., a second pressure-gas volume diagram.

[0111] Optionally, to ensure that the computer device can accurately calculate the working volume change of the compressor cylinder within the preset working time length when obtaining the pressure change data detected by the dynamic pressure sensor within the preset working time length, in an available manner provided by the embodiment of the present application, the compressor is further provided with a key phase sensor, the key phase sensor is used to obtain a key phase signal, and the key phase signal is used to represent the current working time of the compressor.

[0112] Therefore, the computer device of the embodiment of the present application determines the working volume change of the compressor within one working cycle based on the key phase signal, and simultaneously obtains the pressure change data detected by the dynamic pressure sensor within the same working cycle, so that the two kinds of data can be synchronously obtained, and the effectiveness of the second pressure-gas volume diagram is ensured.

[0113] S140, superimpose the first pressure-gas volume diagram and the second pressure-gas volume diagram to obtain a third pressure-gas volume diagram.

[0114] That is, the embodiment of the present application superimposes the curve shown in the first pressure-gas volume diagram and the curve shown in the second pressure-gas volume diagram, so that the curve of the first pressure-gas volume diagram and the curve of the second pressure-gas volume diagram are contained in one image at the same time, i.e., a third pressure-gas volume diagram is obtained.

[0115] It can be understood that, if the deviation of the curve of the second pressure-gas volume diagram and the curve of the first pressure-gas volume diagram in the third pressure-gas volume diagram is large, it indicates that the reciprocating compressor may have a fault; and if the deviation of the two curves is small, it indicates that the reciprocating compressor may have no fault. Therefore, the third pressure-gas volume diagram can directly show the difference between the theoretical situation and the actual situation, and then in the subsequent fault identification process, the computer device can accurately identify the fault condition of the compressor according to the difference reflected by the third pressure-gas volume diagram.

[0116] S150, perform logarithmic coordinate transformation on the third pressure-gas volume diagram, and map the third pressure-gas volume diagram after coordinate transformation to a natural coordinate system according to a preset shape function to perform isoparametric element normalization, to obtain a fourth pressure-gas volume diagram.

[0117] That is, the embodiment of the present application first maps the coordinates of all points of the two curves in the third pressure-gas volume diagram to the logarithmic coordinate system to obtain the closed figure corresponding to the two curves; and then maps the two curves in the logarithmic coordinate system to the natural coordinate system through isoparametric element transformation to obtain the fourth pressure-gas volume diagram, so as to highlight the characteristics of the two curves.

[0118] It can be understood that the geometric characteristics and loads of the curves in the natural coordinate system are from the actual situation in the original coordinate system. It can also be understood that the curves in the second gas volume diagram have a relatively complex shape, while the geometric shapes formed by the curves in the natural coordinate system are simple, so that the characteristics of the curves can be efficiently represented.

[0119] For better illustrating the coordinate transformation process provided by the embodiment of the present application, reference is made to Figure 4a and Figure 4b , which respectively show the first curve schematic diagram and the second curve schematic diagram provided by the embodiment of the present application. Among them, the first curve schematic diagram represents the quadrilateral figure corresponding to the curve of the first pressure-gas volume diagram in the logarithmic coordinate, and the second curve schematic diagram represents the square figure corresponding to the curve of the first pressure-gas volume diagram after isoparametric element normalization transformation in the natural coordinate system.

[0120] It can be known from Figure 4a and Figure 4b that the curve of the first pressure-gas volume diagram in the logarithmic coordinate system presents a quadrilateral, while after mapping the curve in the logarithmic coordinate system to the natural coordinate system through isoparametric element transformation, the curve of the first pressure-gas volume diagram will be changed into a square. It should be understood that compared with the first pressure-gas volume diagram and the second pressure-gas volume diagram without coordinate transformation, the figure formed by the curve of the transformed second pressure-gas volume diagram can form a more obvious difference with the square formed by the curve of the transformed first pressure-gas volume diagram, so as to better reflect the fault condition of the compressor. Moreover, based on the transformation process, the parameters in the third pressure-gas volume diagram are correspondingly normalized through isoparametric element, so as to eliminate the influence of the displacement of the indicator diagram caused by the working condition change of the reciprocating compressor, that is, to eliminate the noise caused by the working condition change of the reciprocating compressor. Based on this, in the image recognition process of the convolutional neural network model, the convolutional neural network model can accurately capture the image features corresponding to different fault types in the fourth pressure-gas volume diagram, so as to accurately identify different fault types under different working conditions.

[0121] For better illustrating the difference between the figures formed by the two curves in the fourth pressure-gas volume diagram in the embodiment of the present application, reference is made to Figure 5 , which shows the fourth pressure-gas volume diagram provided by the embodiment of the present application. Among them, Figure 5The square pattern represents the pressure-gas change curve in the theoretical case, and the irregular pattern represents the pressure-gas change curve in the actual case.

[0122] Therefore, the embodiment of the present application makes the difference between the PV graph in the theoretical case and the PV graph in the actual case more prominent based on the fourth pressure-gas volume graph after coordinate transformation, and then in the subsequent fault identification process, the computer device can accurately identify the fault condition of the compressor according to the obvious difference shown in the fourth pressure-gas volume graph.

[0123] In addition, it can be understood that the form of the preset shape function in the embodiment of the present application can be set according to actual conditions. For example, in a feasible manner provided by the embodiment of the present application, the preset shape function includes:

[0124] x=N1x1+N2x2+N3x3+N4x4

[0125] y=N1y1+N2y2+N3y3+N4y4

[0126]

[0127] ξ0=ξ i ξ,i=[1,2,3,4]

[0128] η0=η i η,i=[1,2,3,4]

[0129] Wherein, x and y represent the horizontal and vertical coordinates in the natural coordinate system, x1, x2, x3, x4, y1, y2, y3, y4 represent the horizontal and vertical coordinates of the four corner points of the first logarithmic pressure-gas volume graph, N i represents the preset shape function, ξ and η represent the dimensionless unit local coordinates of coordinate change, ξ i and η i represent the dimensionless unit local coordinates of the i-th corner point.

[0130] That is, the embodiment of the present application will map the third pressure-gas volume graph to a two-dimensional space, and the value range of the horizontal and vertical coordinates is [-1, 1], and then the graph formed by the pressure-gas change curve representing the theoretical case in the fourth pressure-gas volume graph is a square with a side length of 2.

[0131] S160, input the fourth pressure-gas volume graph into a preset convolutional neural network model to obtain the fault prediction result of the reciprocating compressor.

[0132] That is, the computer device in the embodiment of the present application inputs the fourth pressure-gas volume diagram into the trained convolutional neural network model to predict the image recognition result corresponding to the fourth pressure-gas volume diagram, i.e. the fault prediction result.

[0133] It can be understood that the convolutional neural network model in the embodiment of the present application will be trained through the fourth pressure-gas volume diagrams of multiple labeled categories to ensure that the convolutional neural network model can output the corresponding category prediction result according to the input fourth pressure-gas volume diagram after the training is completed.

[0134] It can also be understood that because the difference between the first pressure-gas volume diagram and the second pressure-gas volume diagram is amplified, the difference between the second pressure-gas volume diagrams corresponding to different compression conditions of the reciprocating compressor can also be reflected, i.e. the difference between the second pressure-gas volume diagrams corresponding to different compression conditions of the reciprocating compressor and the first pressure-gas volume diagram in the embodiment of the present application can be obviously exhibited. Therefore, in addition to being able to effectively determine whether the reciprocating compressor is faulty, the convolutional neural network model in the embodiment of the present application can also determine the specific fault condition corresponding to the fault of the reciprocating compressor, i.e. the category prediction result.

[0135] Optionally, in one feasible manner provided by the embodiment of the present application, the category prediction result output by the convolutional neural network model, i.e. the fault prediction result, includes: intake valve leakage, exhaust valve leakage, piston ring leakage, exhaust valve plate jumping off the valve seat, intake valve sticking / clogging, exhaust valve sticking / clogging, excessive cylinder clearance volume, valve plate vibration, small cross-sectional area of intake valve or intake pipe passage, small cross-sectional area of exhaust valve or exhaust pipe passage, and no fault.

[0136] In the fault detection method provided by the embodiment of the application, after the computer device obtains the structural parameters and process parameters of the compressor and the pressure change of the compressor within a preset working time, the first pressure-gas volume diagram of the compressor under a theoretical condition is generated according to the structural parameters and the process parameters, so as to obtain the indicator diagram of the compressor under a good condition of each component; the second pressure-gas volume diagram of the compressor under an actual condition is generated according to the structural parameters and the pressure change within the preset working time, so as to obtain the indicator diagram of the compressor under the actual condition after each component of the compressor is worn out / faulty due to actual work; then, the first pressure-gas volume diagram and the second pressure-gas volume diagram are superimposed to obtain a third pressure-gas volume diagram, so that the third pressure-gas volume diagram simultaneously exhibits two curves and reflects the difference between the two curves; then, the third pressure-gas volume diagram is subjected to logarithmic coordinate transformation, and the third pressure-gas volume diagram after coordinate transformation is mapped to a natural coordinate system according to a preset shape function to perform isoparametric element normalization, to obtain a fourth pressure-gas volume diagram, so that the difference between the two curves in the third pressure-gas volume diagram is amplified, and the normalization processing of the indicator diagram is realized; finally, the fourth pressure-gas volume diagram is input into a preset convolutional neural network model to obtain a fault prediction result of the compressor.

[0137] Based on this, the embodiment of the application is based on coordinate transformation and coordinate mapping, so that the difference between the indicator diagram under the theoretical condition and the indicator diagram under the actual condition can be obviously reflected, and then the convolutional neural network model can efficiently capture the image features in the fourth pressure-gas volume diagram, so that whether the reciprocating compressor is faulty and the fault category corresponding to the fault can be accurately predicted.

[0138] Optionally, to improve the accuracy of the convolutional neural network model in the embodiment of the application, in a feasible manner corresponding to the embodiment of the application, the method further includes:

[0139] The fourth pressure-gas volume diagram is stored in a preset database, wherein the data in the preset database is used to constitute a training set corresponding to the convolutional neural network model.

[0140] It can be understood that the convolutional neural network model provided by the embodiment of the present application is trained by a large number of fourth pressure-gas volume diagrams, and before the trained convolutional neural network model is put into use, that is, before S160, the embodiment of the present application will continuously generate the second pressure-gas volume diagram of the reciprocating compressor under the actual / simulation condition according to the actual operation of the reciprocating compressor or according to the simulation of the reciprocating compressor, and at the same time, superimposes each second pressure-gas volume diagram on the first pressure-gas volume diagram of the reciprocating compressor under the theoretical condition, and performs coordinate transformation and isoparametric element normalization to obtain and store each fourth pressure-gas volume diagram corresponding to each first pressure-gas volume diagram to the preset database; when the number of fourth pressure-gas volume diagrams in the preset database meets the preset number condition, the computer device in the embodiment of the present application will use the data in the preset database to form a training set, and then train the convolutional neural network model using the training set.

[0141] Further, it can be understood that because the computer device in the embodiment of the present application will record the fourth pressure-gas volume diagram to the preset database for dynamic accumulation of the fourth pressure-gas volume diagram when generating the fourth pressure-gas volume diagram after obtaining the trained convolutional neural network model, the preset database is also used for updating and training the convolutional neural network model.

[0142] It can also be understood that the above-mentioned way of storing the fourth pressure-gas volume diagram to the preset database for training / updating the convolutional neural network model is a feasible way provided by the embodiment of the present application. In a feasible way provided by the embodiment of the present application, because the structure parameters and the process parameters of the reciprocating compressor are unchanged, the first pressure-gas volume diagram is fixed, so the computer device will continuously generate and store the second pressure-gas volume diagram of the reciprocating compressor under the actual / simulation condition according to the actual operation of the reciprocating compressor or according to the simulation of the reciprocating compressor.

[0143] Similarly to the previous feasible way, when the number of second pressure-gas volume diagrams in the preset database meets the preset number condition, the computer device of the embodiment of the present application will generate each corresponding fourth pressure-gas volume diagram by combining each second pressure-gas volume diagram in the preset database with the pre-generated first pressure-gas volume diagram, and then complete the training of the convolutional neural network model according to each fourth pressure-gas volume diagram.

[0144] Further, in the feasible manner of recording the second pressure-gas volume diagram, even if the computer device does not perform fault detection on the reciprocating compressor, that is, the fourth pressure-gas volume diagram is not generated, the computer device can dynamically accumulate the second pressure-gas volume diagram, that is, constantly generate the second pressure-gas volume diagram according to the structural parameters of the reciprocating compressor and the pressure change in the preset working period, and store the generated second pressure-gas volume diagram, so as to generate the fourth pressure-gas volume diagram in cooperation with the first pressure-gas volume diagram at the appropriate time, thereby completing the update training of the convolutional neural network model.

[0145] Optionally, in order to enable the convolutional neural network model provided by the embodiment of the present application to efficiently complete training and prediction, in a feasible manner provided by the embodiment of the present application, the convolutional neural network model comprises a feature extraction module and a classification module connected in sequence, the feature extraction module comprises four convolutional layers connected in sequence, and the classification module comprises three fully connected layers connected in sequence.

[0146] That is, the embodiment of the present application completes extraction of image features based on four convolutional layers connected in sequence, and the three fully connected layers connected in sequence are used for image category prediction based on the extracted image features, so as to obtain a fault prediction result.

[0147] It can be understood that, compared with common deep networks such as VGG (Visual Geometry Group Network) or GoogleNet, the convolutional neural network model provided by the embodiment of the present application requires fewer parameters, and thus can efficiently complete image category prediction. Moreover, because the graph features of the fourth pressure-gas volume diagram are obvious, the convolutional neural network model provided by the embodiment of the present application can effectively ensure the recognition accuracy of image category prediction.

[0148] Optionally, in a feasible manner provided by the embodiment of the present application, the specific structure of the convolutional neural network model is shown in Table 4.

[0149] Table 4

[0150]

[0151] That is, the embodiment of the present application further sets a pooling layer in the convolutional neural network model to change the dimension, and cooperates with a Droupout layer to reduce the training parameter amount of the convolutional neural network model, thereby reducing the load of the computer device for training the model.

[0152] Embodiment 2

[0153] Corresponding to the fault detection method provided by the embodiment of the present application, the embodiment of the present application further provides a fault detection device, which is described with reference to Figure 6Fig. 1 shows a structural schematic diagram of a fault detection device provided by an embodiment of the present application, and the fault detection device 200 provided by the embodiment of the present application comprises:

[0154] The acquisition module 210 is configured to acquire a structural parameter, a process parameter and a pressure change of the reciprocating compressor within a preset time length of work.

[0155] The first generation module 220 is configured to generate a first pressure-gas volume diagram of the reciprocating compressor under a theoretical condition according to the structural parameter and the process parameter.

[0156] The second generation module 230 is configured to generate a second pressure-gas volume diagram of the reciprocating compressor under an actual condition according to the structural parameter and the pressure change within the preset time length of work.

[0157] The superposition module 240 is configured to superimpose the first pressure-gas volume diagram and the second pressure-gas volume diagram to obtain a third pressure-gas volume diagram.

[0158] The transformation module 250 is configured to perform logarithmic coordinate transformation on the third pressure-gas volume diagram, and map the third pressure-gas volume diagram after coordinate transformation to a natural coordinate system according to a preset shape function to perform isoparametric element normalization, to obtain a fourth pressure-gas volume diagram.

[0159] The prediction module 260 is configured to input the fourth pressure-gas volume diagram into a preset convolutional neural network model to obtain a fault prediction result of the reciprocating compressor.

[0160] Optionally, in a feasible manner provided by the embodiment of the present application, the structural parameter comprises a clearance volume, a piston stroke and a cylinder radius, and the process parameter comprises an inlet and outlet gas pressure, an inlet and outlet gas temperature and a composition of gas.

[0161] The first generation module comprises:

[0162] The specific heat capacity calculation sub-module is configured to calculate a constant-pressure specific heat capacity and a constant-volume specific heat capacity by using the inlet and outlet gas pressure, the inlet and outlet gas temperature and the composition of gas.

[0163] The adiabatic exponent calculation sub-module is configured to calculate an adiabatic exponent of the reciprocating compressor under an expansion process and a compression process respectively based on the constant-pressure specific heat capacity and the constant-volume specific heat capacity.

[0164] The working volume calculation sub-module is configured to calculate a theoretical maximum working volume and a theoretical minimum working volume of the reciprocating compressor according to the clearance volume, the piston stroke and the cylinder diameter.

[0165] The theoretical diagram generation submodule is configured to generate a first pressure-gas volume diagram of the reciprocating compressor under a theoretical condition according to the adiabatic index, the intake and exhaust pressures, the theoretical maximum working volume, and the theoretical minimum working volume.

[0166] Optionally, in an implementation provided by the present application, the reciprocating compressor is provided with a dynamic pressure sensor, the structure parameters include a piston stroke, a cylinder diameter, a connecting rod length, a crank angle, and a clearance volume, and the pressure change in the preset working time period includes pressure change data detected by the dynamic pressure sensor in the preset working time period.

[0167] The second generation module includes:

[0168] The volume change calculation submodule is configured to calculate a working volume change of the reciprocating compressor in the preset working time period by using a preset formula based on the piston stroke, the cylinder diameter, the crank angle, the connecting rod length, and the clearance volume.

[0169] The actual diagram generation submodule is configured to generate a second pressure-gas volume diagram of the reciprocating compressor under an actual condition according to the pressure change data and the working volume change.

[0170] Optionally, in an implementation provided by the present application, the preset formula includes:

[0171]

[0172] In the formula, V represents a working volume, S represents a piston stroke, θ represents a crank angle, l represents a connecting rod length, B represents a cylinder inner diameter, and V represents a clearance volume. cl

[0173] Optionally, in an implementation provided by the present application, the preset shape function includes:

[0174] x = N1x1 + N2x2 + N3x3 + N4x4

[0175] y = N1y1 + N2y2 + N3y3 + N4y4

[0176]

[0177] ξ0 = ξ i ξ,i = [1, 2, 3, 4]

[0178] η0 = η i η,i = [1, 2, 3, 4]

[0179] ​Wherein, x and y represent the horizontal coordinate and the vertical coordinate in the natural coordinate system, x1, x2, x3, x4, y1, y2, y3, y4 represent the horizontal coordinate and the vertical coordinate of the four corner points of the first logarithmic pressure-gas volume diagram, N i represents a preset shape function, and ξ and η represent the dimensionless unit local coordinates of coordinate variation, ξ i and η i represent the dimensionless unit local coordinates of the i-th corner point.

[0180] Optionally, in an implementable manner provided by the embodiment of the present application, the device further comprises:

[0181] a storage module, configured to store the fourth pressure-gas volume diagram into a preset database, wherein the data in the preset database is used to constitute a training set corresponding to the convolutional neural network model.

[0182] Optionally, in an implementable manner provided by the embodiment of the present application, the convolutional neural network model comprises a feature extraction module and a classification module connected in sequence, the feature extraction module comprises four convolutional layers connected in sequence, and the classification module comprises three fully connected layers connected in sequence.

[0183] Optionally, in an implementable manner provided by the embodiment of the present application, the fault prediction result comprises: intake valve leakage, exhaust valve leakage, piston ring leakage, exhaust valve plate jumping off the valve seat, intake valve biting / clogging, exhaust valve biting / clogging, excessive cylinder clearance volume, valve plate vibration, small cross-sectional area of intake valve or intake pipe passage, small cross-sectional area of exhaust valve or exhaust pipe passage, and no fault.

[0184] The fault detection device provided by the embodiment of the present application can realize Figures 1 to 3 the same technical effects as the processes of the fault detection method in the corresponding method embodiment, and thus the details are not repeated here.

[0185] The embodiment of the present application further provides a computer device, which comprises a memory and a processor, the memory stores a computer program, and the computer program executes the fault detection method disclosed in the Figures 1 to 3 corresponding method embodiment when running on the processor.

[0186] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program executes the fault detection method disclosed in the Figures 1 to 3 corresponding method embodiment when running on the processor.

[0187] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can also be implemented by other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and structural diagrams in the drawings show the possible implementation architecture, function and operation of the apparatus, method and computer program product according to the embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logic function. It should also be noted that in alternative implementation manners, the functions noted in the blocks can also occur in different order from that noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can also be executed in reverse order, depending on the functions involved. It should also be noted that each block in the structural diagram and / or flowchart, and the combination of blocks in the structural diagram and / or flowchart, can be implemented by a dedicated hardware-based system for executing the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0188] In addition, each functional module or unit in the embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0189] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or the part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0190] The above description is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A fault detection method characterized by, The method comprises the following steps: obtaining structural parameters, process parameters and pressure changes of the reciprocating compressor within a preset working time; generating a first pressure-gas volume diagram of the reciprocating compressor under a theoretical condition according to the structural parameters and the process parameters; generating a second pressure-gas volume diagram of the reciprocating compressor under an actual condition according to the structural parameters and the pressure changes within the preset working time; superimposing the first pressure-gas volume diagram and the second pressure-gas volume diagram to obtain a third pressure-gas volume diagram; performing logarithmic coordinate transformation on the third pressure-gas volume diagram, and mapping the third pressure-gas volume diagram after coordinate transformation to a natural coordinate system according to a preset shape function to perform isoparametric element normalization to obtain a fourth pressure-gas volume diagram; inputting the fourth pressure-gas volume diagram into a preset convolutional neural network model to obtain a fault prediction result of the reciprocating compressor; the preset shape function comprises: in, x and y Representing the x and y coordinates in the natural coordinate system, x 1. x 2. x 3. x 4. y 1. y 2. y 3. y 4 represents the x and y coordinates of the four corner points of the first logarithmic pressure-gas volume plot. N i Represents a predefined shape function. ξ and η Local coordinates of a dimensionless unit representing coordinate changes. ξ i and η i Indicates the first i The dimensionless unit local coordinates of the corner points.

2. The fault detection method according to claim 1, characterized in that, The structural parameters include a clearance volume, a piston stroke and a cylinder radius, and the process parameters include an inlet and outlet gas pressure, an inlet and outlet gas temperature and a composition of the gas; the generating of the first pressure-gas volume diagram of the reciprocating compressor under the theoretical condition according to the structural parameters and the process parameters comprises: calculating the specific heat capacity at constant pressure and the specific heat capacity at constant volume by using the inlet and outlet gas pressure, the inlet and outlet gas temperature and the composition of the gas; calculating the adiabatic index of the reciprocating compressor under the expansion and compression processes respectively based on the specific heat capacity at constant pressure and the specific heat capacity at constant volume; calculating the theoretical maximum working volume and the theoretical minimum working volume of the reciprocating compressor according to the clearance volume, the piston stroke and the cylinder diameter; generating the first pressure-gas volume diagram of the reciprocating compressor under the theoretical condition according to the adiabatic index, the inlet and outlet gas pressure, the theoretical maximum working volume and the theoretical minimum working volume.

3. The fault detection method of claim 1, wherein, The reciprocating compressor is provided with a dynamic pressure sensor, the structural parameters include a piston stroke, a cylinder diameter, a connecting rod length, a crank angle and a clearance volume, and the pressure changes within the preset working time include pressure change data detected by the dynamic pressure sensor within the preset working time; the generating of the second pressure-gas volume diagram of the reciprocating compressor under the actual condition according to the structural parameters and the pressure changes within the preset working time comprises: calculating the working volume change of the reciprocating compressor within the preset working time by using a preset formula based on the piston stroke, the cylinder diameter, the crank angle, the connecting rod length and the clearance volume; generating the second pressure-gas volume diagram of the reciprocating compressor under the actual condition according to the pressure change data and the working volume change.

4. The fault detection method according to claim 3, characterized in that, The preset formula comprises: wherein V represents the working volume, S represents the piston stroke, θ represents the crank angle, l represents the connecting rod length, B represents the cylinder bore, V cl represents the clearance volume.

5. The fault detection method of claim 1, wherein The method further comprises: storing the fourth pressure-gas volume diagram into a preset database, wherein the data in the preset database is used to constitute a training set corresponding to the convolutional neural network model.

6. The fault detection method of claim 1, wherein, The convolutional neural network model comprises a feature extraction module and a classification module connected in sequence, the feature extraction module comprises four convolutional layers connected in sequence, and the classification module comprises three fully connected layers connected in sequence.

7. The fault detection method of claim 1, wherein, The fault prediction result comprises: intake valve leakage, exhaust valve leakage, piston ring leakage, exhaust valve plate jumping off the valve seat, intake valve biting / clogging, exhaust valve biting / clogging, excessive cylinder clearance volume, valve plate vibration, small cross-sectional area of intake valve or intake pipe passage, small cross-sectional area of exhaust valve or exhaust pipe passage, and no fault.

8. A fault detection apparatus characterized by comprising: The method comprises: An acquisition module is configured to acquire structural parameters and process parameters of a reciprocating compressor and pressure changes of the reciprocating compressor within a preset working time length; A first generation module is configured to generate a first pressure-gas volume diagram of the reciprocating compressor in a theoretical case according to the structural parameters and the process parameters; A second generation module is configured to generate a second pressure-gas volume diagram of the reciprocating compressor in an actual case according to the structural parameters and the pressure changes within the preset working time length; An overlay module is configured to overlay the first pressure-gas volume diagram and the second pressure-gas volume diagram to obtain a third pressure-gas volume diagram; A transformation module is configured to perform logarithmic coordinate transformation on the third pressure-gas volume diagram, map the third pressure-gas volume diagram after coordinate transformation to a natural coordinate system according to a preset shape function to perform isoparametric element normalization, and obtain a fourth pressure-gas volume diagram; A prediction module is configured to input the fourth pressure-gas volume diagram into a preset convolutional neural network model to obtain a fault prediction result of the reciprocating compressor. The preset shape function comprises: wherein x and y denote the horizontal and vertical coordinates in the natural coordinate system, x 1, x 2, x 3, x 4, y 1, y 2, y 3, y 4denote the horizontal and vertical coordinates of the four corner points of the first logarithmic pressure-gas volume diagram, N i denote the preset shape functions, ξ and η denote the dimensionless unit local coordinates of the coordinate change, ξ i and η i denote the dimensionless unit local coordinates of the first i corner point.

9. A computer device, comprising: The computer readable storage medium stores a computer program, and the computer program performs the fault detection method of any one of claims 1-7 when running on the processor.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program performs the fault detection method of any one of claims 1-7 when running on the processor.

Images