Air compressor health degree assessment method and electronic equipment

Abstract

The invention discloses an air compressor health degree assessment method and electronic equipment. The method comprises the following steps that the numerical value of a selected assessment index of an air compressor is collected; calculating the deterioration degree Degj (t) of the selected evaluation index according to the numerical value of the selected evaluation index, and obtaining a first group of weight values wp and a second group of weight values wq based on the selected evaluation index by using two different weight assignment methods; performing weighted calculation on the first group of weight values wp and the second group of weight values wq to obtain a combined weight value wj; and calculating the comprehensive health degree of the air compressor at t based on the deterioration degree Degj (t) and the combined weight value wj of the selected evaluation index in combination with the aging degree of the air compressor. According to the invention, dependence on artificial experience and prior knowledge is reduced through a modeling technology, and rapid, low-cost and high-precision health assessment is realized in combination with real-time data acquisition and an efficient algorithm, so that the process is significantly simplified, the maintenance period is shortened, and manual intervention is reduced.

Description

Technical Field

[0001] The present invention relates to a method for evaluating the health of an air compressor, and more specifically, to a method for evaluating the health of an air compressor based on fuzzy comprehensive evaluation and an electronic device. Background Art

[0002] With the rapid development of technologies such as Internet of Things communication technology, big data, and machine learning, industrial big data technology and data visualization technology have made great progress in all walks of life. In the air compression industry, compressed air, as the most widely used environmental protection power source and raw material, plays an indispensable role in the industrial field. In terms of equipment management, how to evaluate the health of the air compression system is an urgent need, because the health evaluation can be used as a pre-work for fault prediction, and the fault trend of air compressors with low health can be predicted. Therefore, how to conduct health evaluation is a very valuable research.

[0003] Currently, the methods for evaluating the health of air compressors mainly include regular maintenance based on experience and real-time monitoring based on sensor data, but both of these methods have deficiencies. Among them, regular maintenance based on experience or post-fault repair depends on the experience and intuition of air compressor maintenance personnel, has a long cycle, high cost, and is not accurate enough, resulting in air compressors not operating at the best state all year round. Among them, real-time monitoring based on sensor data collects the operating data of air compressors in real time through sensors for monitoring and alarming, but most of them only provide post-alarm functions and cannot give the health evaluation status in advance. Summary of the Invention

[0004] In view of this, the present invention proposes a method for evaluating the health of an air compressor. This method is based on fuzzy comprehensive evaluation. By collecting the numerical values of the selected evaluation indicators of the air compressor, calculating the deterioration degree of each indicator, using two weight assignment methods to generate the first set of weights and the second set of weights respectively, and weighted fusion to obtain the combined weights. Finally, combining the deterioration degree, the combined weights and the aging degree of the air compressor, calculate its comprehensive health at a certain time. This method overcomes the following problems of the prior art: dependence on the experience of maintenance personnel, long cycle, high cost and lack of accuracy, and only providing post-alarm functions. The present invention further discloses an electronic device for implementing the above method.

[0005] As the first aspect of the present invention, there is provided a method for evaluating the health of an air compressor, including the following steps: collecting the numerical values of the selected evaluation indicators of the air compressor; according to the numerical values of the selected evaluation indicators, calculating the deterioration degree Deg j (t) of the selected evaluation indicators, and obtaining the first set of weight values w p and the second set of weight values wq ; perform weighted calculation on the first set of weight values w p and the second set of weight values w q to obtain a combined weight value w j ; based on the degradation degree Deg j (t) of the selected evaluation indicators and the combined weight value w j , combined with the aging degree of the air compressor, calculate the comprehensive health degree of the air compressor at time t.

[0006] In one embodiment of the present invention, the selected evaluation indicators include one or more of the following: main engine exhaust temperature, main engine oil injection temperature, unit exhaust pressure, head exhaust pressure, oil separation pressure difference, oil injection pressure, air filter pressure difference, oil filter pressure difference, main engine vibration, motor vibration, motor current, and motor input power.

[0007] In one embodiment of the present invention, the motor current and motor input power in the selected evaluation indicators are converted into a motor service factor SF by the following formula (1) to replace the two evaluation indicators of motor current and motor input power:

[0008]

[0009] where P represents the instantaneous input power of the motor, η represents the motor efficiency, and P 0 represents the rated power.

[0010] In one embodiment of the present invention, the air compressor health degree evaluation method further includes preprocessing the numerical values of the selected evaluation indicators, including normalizing the numerical values of the selected evaluation indicators, interpolating or deleting the missing numerical values of the selected evaluation indicators, and smoothing the numerical values of the selected evaluation indicators.

[0011] In one embodiment of the present invention, calculating the degradation degree Deg j (t) of the selected evaluation indicators further includes: for the air compressor, using the following formula (2) to calculate the degradation degree Deg j (t) of the j-th evaluation indicator in the selected evaluation indicators:

[0012]

[0013] where x maxj , x minj are the maximum and minimum values of the j-th evaluation indicator respectively, x j (t) is the value of the j-th evaluation indicator at time t, and x aj , x bj are the endpoint values of the optimal range of the j-th evaluation indicator respectively.

[0014] In one embodiment of the present invention, two different weight assignment methods are used to obtain a first set of weight values w based on the selected evaluation indicators p and a second set of weight values w q Further comprising: obtaining a first set of weight values w based on the interval analytic hierarchy process weighting method for the selected evaluation indicators p , and obtaining a second set of weight values w based on the entropy weight method for the selected evaluation indicators q .

[0015] In one embodiment of the present invention, the first set of weight values w p and the second set of weight values w q are weighted to obtain a combined weight value w j Including: based on the moment estimation theory, using the following formula (3) to weight the first set of weight values w p and the second set of weight values w q to obtain a combined weight w j :

[0016]

[0017] where the relative importance of the weight values w p and w q of the evaluation indicators are defined as a and b respectively, w pj is the first weight of the j-th evaluation indicator, w qj is the second weight of the j-th evaluation indicator, a j is the importance of w pj relative to w qj for the j-th evaluation indicator, b j is the importance of w qj relative to w pj for the j-th evaluation indicator, and m is the number of evaluation indicators;

[0018] A controllable variable δ is defined to evaluate the technical ability of experts, and its value range is [0, 1]. Thus, the relative importance a and b of the weight values w p and w q are expressed by the following formula (4):

[0019]

[0020] In one embodiment of the present invention, based on the degradation degree Deg j (t) of the selected evaluation indicators and the combined weight value w j , combined with the aging degree of the air compressor, to calculate the comprehensive health degree of the air compressor at time t includes:

[0021] Use the following formula (5) to calculate the basic health value HV(t) of the air compressor at time t:

[0022]

[0023] where hv j (t) = 1 - Deg j (t), which is the basic health value of the j-th evaluation index of the air compressor at time t, and w j is the combined weight of the j-th evaluation index;

[0024] Use the following formula (6) to consider the aging factor:

[0025] HV a (t) = 1 - (1 - HV 0 )e Bt (6)

[0026] where B is the aging coefficient, HV 0 is the health value when the device is put into operation, and HV a (t) is the health value of the air compressor at time t considering only aging, and t is the time from the initial operation of the air compressor to the current evaluation;

[0027] Define the health factor u(t) = HV a (t) / HV 0 , and based on this health factor u(t), use the following formula (7) to calculate the comprehensive health value HV of the air compressor:

[0028] HV = u(t)·HV(t) (7).

[0029] In an embodiment of the present invention, the method for evaluating the health value of the air compressor of the present invention further includes: dividing the comprehensive health value of the air compressor into four grades: healthy, sub-healthy, potential hazard, and failure.

[0030] As a second aspect of the present invention, there is provided an electronic device, which includes a processor and a memory, and instructions are stored on the memory, and when the instructions are executed by the processor, they are used to implement the above-mentioned method for evaluating the health value of the air compressor.

[0031] The beneficial effects of this application are as follows: By using modeling technology, the dependence on manual experience is reduced. Combining real-time data collection and efficient algorithms, rapid, low-cost, and high-precision health evaluation is achieved, significantly simplifying the process and shortening the maintenance cycle, and reducing manual intervention. Brief Description of the Drawings

[0032] Figure 1It is the flowchart of the air compressor health assessment method based on fuzzy comprehensive evaluation of the present invention.

[0033] Figure 2 It is the logic block diagram for implementing the air compressor health assessment method of the present invention.

[0034] Figure 3 It is the calculation process of the entropy weight method in the air compressor health assessment method of the present invention. Detailed implementation manners

[0035] Hereinafter, embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0036] Refer to Figure 1 , in an embodiment of the present invention, a method for assessing the health of an air compressor based on fuzzy comprehensive evaluation is provided. The method includes the following steps: collecting the values of selected evaluation indexes of the air compressor; calculating the deterioration degree Deg j (t) of the selected evaluation indexes according to the values of the selected evaluation indexes, and obtaining a first set of weight values w p and a second set of weight values w q based on the selected evaluation indexes by using two different weight assignment methods; performing weighted calculation on the first set of weight values w p and the second set of weight values w q to obtain a combined weight value w j ; calculating the comprehensive health of the air compressor at time t based on the deterioration degree Deg j (t) of the selected evaluation indexes and the combined weight value w j , in combination with the aging degree of the air compressor.

[0037] In an embodiment of the present invention, the selected evaluation indexes include one or more of the following: main engine exhaust temperature, main engine oil injection temperature, unit exhaust pressure, head exhaust pressure, oil separation pressure difference, oil injection pressure, air filter pressure difference, oil filter pressure difference, main engine vibration, motor vibration, motor current, and motor input power.

[0038] Refer to Figure 2 , Figure 2 is the logic block diagram for implementing the air compressor health assessment method of the present invention. The present invention can collect the real-time operation data of the selected evaluation indexes of the air compressor in real time through an industrial Internet of Things system via devices and various sensors. Taking the oil-injected screw air compressor as an example of the air compressor involved in the present invention, the evaluation indexes collected thereof are shown in Table 1 below.

[0039] Table 1

[0040]

[0041] In one embodiment of the present invention, the method for evaluating the health of an air compressor of the present invention further includes preprocessing the values of the selected evaluation indicators, including normalizing the values of the selected evaluation indicators, interpolating or deleting the missing values of the selected evaluation indicators, and smoothing the values of the selected evaluation indicators. By performing normalization processing on the data of the collected evaluation indicators, the influence of dimensions and magnitudes can be eliminated.

[0042] In one embodiment of the present invention, the motor current and motor input power in the selected evaluation indicators are converted into the motor service factor SF by the following formula (1) to replace the two evaluation indicators of motor current and motor input power:

[0043]

[0044] where P represents the instantaneous input power of the motor, η represents the motor efficiency, and P 0 represents the rated power. By introducing the motor service factor SF, the data set can be studied more accurately.

[0045] In one embodiment of the present invention, after replacing the motor current and motor power parameters with the motor service factor, finally, the 11 evaluation indicators are symbolized using the symbols {X1, X2, X3…, X11}, as shown in Table 2 below.

[0046] Table 2

[0047]

[0048] Table 2 (continued)

[0049]

[0050] where Xmin and Xmax represent the minimum and maximum values of the evaluation indicators respectively, and Xa and Xb represent the endpoint values of the optimal range of the evaluation indicators.

[0051] In one embodiment of the present invention, calculating the deterioration degree Deg j (t) further includes:

[0052] For the deterioration degree f(x) of the benefit type (the larger the value, the better) evaluation indicators:

[0053]

[0054] For the deterioration degree f(x) of the consumption type (the smaller the value, the better) evaluation indicators:

[0055]

[0056] Deterioration degree f(x) of the evaluation index for the intermediate type:

[0057]

[0058] where x max and x min are the maximum and minimum values of the evaluation index respectively, and x a and x b are the endpoint values of the optimal range of the evaluation index.

[0059] Specifically, for an air compressor, if its normal operation is to be ensured, all evaluation indexes must be within a reasonable interval range. Thus, we derive the following formula (2) to calculate the deterioration degree Deg j (t) of the j-th evaluation index among the selected evaluation indexes:

[0060]

[0061] where x maxj and x minj are the maximum and minimum values of the j-th evaluation index respectively, x j (t) is the value of the j-th evaluation index at time t, and x aj and x bj are the endpoint values of the optimal range of the j-th evaluation index.

[0062] In the present invention, the concept of combined weights is introduced. The combined weights can effectively combine subjective and objective weight assignment methods. In an embodiment of the present invention, the subjective judgment of the decision maker or expert using the interval analytic hierarchy process weight assignment method is used to construct a judgment matrix based on the pairwise interval numbers of each evaluation index to obtain the first set of weight values w p , and the entropy weight assignment method is used to obtain the second set of weight values w q based on the parameter value deviation within each evaluation index based on the selected evaluation indexes. Then, the two sets of weight values are weighted and calculated to obtain the combined weights, avoiding excessive subjective judgment of the interval analytic hierarchy process method and making the weight assignment more objective, fully integrating the advantages of the two weight assignment methods.

[0063] Compared with the traditional analytic hierarchy process weight assignment method, the interval analytic hierarchy process weight assignment method constructs a judgment matrix by replacing point values with interval numbers, improving the accuracy of the evaluation mainly relying on subjective judgment and also improving the information integrity when comparing pairwise evaluation indexes. Due to the ease of use of the interval analytic hierarchy process weight assignment method, including convenient model establishment and simple calculation, the interval analytic hierarchy process weight assignment method is increasingly used in various management decisions.

[0064] The main steps of the interval analytic hierarchy process (AHP) weight assignment method adopted in this invention are as follows:

[0065] (1) Establish an interval number judgment matrix

[0066] According to the importance levels of the reciprocal 1-9 scale method shown in Table 3 below, pairwise comparison and scoring are performed on the evaluation indicators, and an interval number is used to represent the scoring value, where and Then, based on this, an interval judgment matrix A = (α ij ) n×n is formed, where n is the number of evaluation indicators.

[0067] Table 3

[0068]

[0069] (2) Calculate the weight vector

[0070] Matrix A is decomposed into two matrices according to and , and then the maximum eigenvalues of the two decomposed matrices are calculated respectively, as well as the normalized eigenvectors λ - and λ + . Finally, the weight vector is obtained according to formulas (2-1) and (2-2):

[0071] w - =αλ - (2-1)

[0072] w + =αλ + (2-2)

[0073] where

[0074] (3) Consistency test

[0075] The interval analytic hierarchy process (AHP) weight assignment method can refer to the analytic hierarchy process (AHP) weight assignment method to conduct a consistency test on the interval matrix. First, calculate the consistency evaluation index CI:

[0076]

[0077] For n = 1,..., 12, the value of the average random consistency evaluation index RI can be found in Table 4 below, which is used as a comparison table of n and RI. The RI value is related to the matrix order and is an empirical value calculated through a large number of random judgment matrices.

[0078] Table 4

[0079]

[0080] Then calculate the consistency ratio CR.

[0081]

[0082] If the final verification value CR < 0.1, the consistency test is satisfied. If CR ≥ 0.1, the interval matrix needs to be modified. When modifying, the decision maker needs to re-examine the importance relationship between various factors. The elements in the interval judgment matrix can be adjusted by further collecting information, consulting expert opinions or rethinking the essence of the decision problem, and then the consistency test is carried out again until CR < 0.1.

[0083] (4) Calculate the final weight w p

[0084] w p =(w - +w + ) / 2 (2-5)

[0085] As Figure 3 shown, Figure 3 is the calculation process of the entropy weight method in the air compressor health assessment method of the present invention. Compared with the interval analytic hierarchy process weight method, the entropy weight method objectively obtains the weight value according to the change range of each evaluation index, and can avoid the excessive subjective judgment that may exist in the interval analytic hierarchy process weight method. The entropy weight method solves the weight by constructing an evaluation matrix based on the parameters of each standardized evaluation index, and determines the difference system by calculating the entropy value of each evaluation index to obtain a relatively objective evaluation index weight.

[0086] (1) Standardize the original values of each evaluation index

[0087]

[0088] where x i is the original sequence of the evaluation index, and y i is the standardized sequence. The standardized new sequence is within the range of [0,1], thus playing the role of eliminating the dimension and magnitude.

[0089] (2) Determine the characteristic graph of the evaluation index

[0090] Calculate the proportion P ij

[0091]

[0092] of the evaluation index value of the jth evaluation index in the ith group, and thus obtain a standardized matrix composed of the proportions of each evaluation index in different data groups.

[0093] Y={pij} m×n (2 - 8)

[0094] (3) Calculate the entropy value of the evaluation index

[0095] The entropy value e of the j-th evaluation index j , is calculated according to formula (2 - 9).

[0096]

[0097] Where K is a constant, related to the number m of data groups in the evaluation system, and the calculation formula is:

[0098]

[0099] Substituting (2 - 10) into (2 - 9), we get:

[0100]

[0101] (4) Determine the difference coefficient g of the evaluation index j

[0102] g j = 1 - e j (2 - 12)

[0103] (5) Calculate the weight w of the j-th evaluation index qj

[0104] From And substituting (2 - 12) into the calculation, we get:

[0105]

[0106] From j w qj constitute the second set of weight values w q . In the context of the present invention, the weight calculated based on the j-th evaluation index using the interval analytic hierarchy process for weight assignment is called the first weight, and the weight calculated based on the j-th evaluation index using the entropy weight method is called the second weight.

[0107] In an embodiment of the present invention, based on the moment estimation theory, the following formula (3) can be used to perform weighted calculation on the first set of weight values w p and the second set of weight values w q to obtain the combined weight w of the j-th evaluation index j :

[0108]

[0109] Where the weight value w of the evaluation index p and w qThe relative importance levels are respectively defined as a, b, and w pj is the first weight of the j-th evaluation index, w qj is the second weight of the j-th evaluation index, a j is the w of the j-th evaluation index pj relative to w qj importance level, b j is the w of the j-th evaluation index qj relative to w pj importance level, m is the number of evaluation indexes;

[0110] Define a controllable variable δ to evaluate the technical ability of experts, with a value range of [0, 1]. The larger the value, the stronger the technical ability of the expert. The weight w p will be larger, and vice versa. Thus, the weight values w p and w q relative importance levels a and b are expressed by the following formula (4):

[0111]

[0112] In an embodiment of the present invention, the following formula (5) can be used to calculate the basic health degree HV(t) of the air compressor at time t:

[0113]

[0114] where hv j (t) = 1 - Deg j (t), which is the basic health degree of the j-th evaluation index of the air compressor at time t, w j is the combined weight of the j-th evaluation index;

[0115] Considering the performance aging caused by the long-term operation of the air compressor and environmental factors, etc., the following formula (6) is used to consider the aging factor:

[0116] HV a (t) = 1 - (1 - HV 0 )e Bt (6)

[0117] where B is the aging coefficient, HV 0 is the health degree value when the equipment is put into operation, HV a (t) is the health degree of the air compressor at time t considering only aging, and t is the time from the initial operation of the air compressor to the current evaluation;

[0118] Define the health factor u(t) = HV a (t) / HV 0, and based on this health factor u(t), the following formula (7) is used to calculate the comprehensive health value HV of the air compressor:

[0119] HV = u(t)·HV(t) (7).

[0120] In an embodiment of the present invention, the correspondence between the health value range of the air compressor and the state and failure incidence rate of the air compressor can be defined. The comprehensive health of the air compressor can be divided into four levels: healthy, sub-healthy, potential hazard, and failure. The correspondence between the health range and the state of the air compressor is shown in Table 5 below.

[0121] Table 5

[0122]

[0123] As Figure 2 shown, after evaluating the health of the air compressor, in the case where the evaluation result is a potential hazard, the equipment failure trend analysis and prediction can be carried out by methods known now or developed in the future.

[0124] The present invention also provides an electronic device, which includes a processor and a memory. Instructions are stored on the memory, and when executed by the processor, these instructions are used to implement the air compressor health evaluation method of the present invention.

[0125] The following provides a specific embodiment of using the air compressor health evaluation method of the present invention to evaluate the health of the air compressor and implement fault warning.

[0126] In Table 6 below, 11 evaluation indicators are defined: X1_ Main engine exhaust temperature °C, X2_ Main engine oil injection temperature °C,..., X9_ Main engine vibration mm / s, X10_ Motor vibration mm / s, X11_ Motor service factor, and symbols will be used for reference in the following discussion and calculation.

[0127] Select the oil-injected screw air compressors A1, A2 in an air compressor station and the oil-injected screw air compressors A3, A4 in another air compressor station as examples. The real-time operation data and the time since the last maintenance of these four oil-injected screw air compressors during stable loading are shown in Table 6 below. We will conduct an example verification using the air compressor health evaluation method based on fuzzy comprehensive evaluation described above.

[0128] Table 6

[0129]

[0130] Table 6 (continued)

[0131]

[0132] 1. Composite Weight Calculation

[0133] (1) Interval Analytic Hierarchy Process for Weight Assignment

[0134] For a total of 11 evaluation indicators from X1 to X11, by means of the interval scale rules shown in Table 3, first compare the importance of these evaluation indicators pairwise, and only need to record the scoring data in the triangular shaded area of Table 7 below. The remaining part can be calculated.

[0135] Table 7

[0136]

[0137]

[0138] Split the above interval scoring results into two matrices A - and A + , and solve the normalized eigenvectors λ - and λ + for these two split matrices respectively, as shown below.

[0139]

[0140]

[0141] λ - = [0.0646, 0.0828, 0.1335, 0.1239, 0.1149, 0.1093, 0.1082, 0.0820, 0.0644,

[0142] 0.0802, 0.035]

[0143] λ + = [0.0704, 0.0734, 0.1141, 0.1037, 0.1169, 0.0969, 0.1409, 0.0880, 0.0685,

[0144] 0.0850, 0.0416]

[0145] Taking δ = 0.5, calculate α = 0.6761939 and β = 1.2743919 and substitute them into formulas (2-1), (2-2) and (2-5) to obtain:[[]]

[0146] w p = [0.0667, 0.0747, 0.1178, 0.1080, 0.1134, 0.0987, 0.1264, 0.0840, 0.0654, 0.0813, 0.0384]

[0147] (2) Entropy value weighting method

[0148] First, algebraize the evaluation indexes of the oil-injected screw air compressor as shown in Table 8 below.

[0149] Table 8

[0150]

[0151] Table 8 (continued)

[0152]

[0153] Then, according to formula (2-10), the value of K is obtained as 0.7213, and the weight w is obtained according to formula (2-13) q :

[0154] w q = [0.0674, 0.081, 0.0744, 0.0784, 0.1091, 0.0587, 0.1120, 0.1145, 0.1236,

[0155] 0.1236, 0.0565]

[0156] (3) Combined weight calculation

[0157] According to the obtained w p and w q , and formula (3), the combined weight can be obtained

[0158] w = [0.0659, 0.0767, 0.0993, 0.0938, 0.1093, 0.0823, 0.1175, 0.0998, 0.1016, 0.1049, 0.0483]

[0159] 2. Air compressor health degree calculation

[0160] According to formula (2), the deterioration degree of each evaluation index is obtained, as shown by X_Deg in Table 9.

[0161] According to the air compressor aging coefficient B = 0.005, and the unit has been running for about 3 years, the initial health degree HV 0 of the air compressor is given as 0.95. According to formula (7), the health degrees of the four air compressors are obtained, as shown in the HV column of Table 9.

[0162] Table 9

[0163]

[0164] Table 9 (continued)

[0165]

[0166] According to the health assessment values of A1 to A4 and Table 5, the health of A3 and A4 being less than 0.7 can be determined as a potential hazard state. Combining the actual situation comparison of the time since the last maintenance of the 4 air compressors in Table 6, the judgment results of the health status of the 4 air compressors are consistent with the actual situation. It verifies that the air compressor health assessment method based on fuzzy comprehensive evaluation of the present invention is accurate and effective.

[0167] The above description is only some preferred embodiments of the present disclosure and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept.

Claims

1. A method for evaluating the health of an air compressor, characterized in that: The following steps are involved: S1. Collecting the values ​​of the selected evaluation indicators of the air compressor; S2. Calculate the degradation degree Deg of the selected evaluation index according to the value of the selected evaluation index. j (t), and using two different weight assignment methods to obtain a first set of weight values ​​w based on the selected evaluation index p and the second set of weights w q ; S3, the first group of weight values ​​w p and the second set of weights w q Perform weighted calculation to obtain the combined weight value w j ; S4. Degradation Deg based on the selected evaluation index j (t) and the combined weight value w j , combined with the aging degree of the air compressor, to calculate the comprehensive health of the air compressor at time t.

2. The air compressor health assessment method according to claim 1, characterized in that: The selected evaluation indicators include one or more of the following: main engine exhaust temperature, main engine injection temperature, unit exhaust pressure, head exhaust pressure, oil pressure difference, injection pressure, air filter pressure difference, oil filter pressure difference, main engine vibration, motor vibration, motor current and motor input power.

3. The air compressor health assessment method according to claim 2, characterized in that: The motor current and motor input power in the selected evaluation index are converted into the motor service factor SF by the following formula (1) to replace the two evaluation indexes of motor current and motor input power: Where P represents the instantaneous input power of the motor, η represents the motor efficiency, and P0 represents the rated power.

4. The air compressor health assessment method according to claim 1, characterized in that: It also includes preprocessing the values ​​of the selected evaluation indicators, including standardizing the values ​​of the selected evaluation indicators, interpolating or deleting missing values ​​of the selected evaluation indicators, and smoothing the values ​​of the selected evaluation indicators.

5. The air compressor health assessment method according to claim 1, characterized in that: Step S2 further includes: for the air compressor, using the following formula (2) to calculate the degradation degree Deg of the jth evaluation index in the selected evaluation index: j (t): where x max j 、x min j are the maximum and minimum values ​​of the jth evaluation index, respectively, x j (t) is the value of the jth evaluation indicator at time t, x aj 、x bj is the endpoint value of the optimal range of the j-th evaluation metric.

6. The air compressor health assessment method according to claim 1, characterized in that: Step S2 further includes: using the interval hierarchy analysis weighting method to obtain a first set of weight values ​​w based on the selected evaluation index p , and use the entropy weighting method to obtain a second set of weight values ​​w based on the selected evaluation index q .

7. The air compressor health assessment method according to claim 1, characterized in that: In step S3, the first set of weight values ​​w p and the second set of weights w q Perform weighted calculation to obtain the combined weight value w j include: Based on the moment estimation theory, the first set of weight values ​​w is calculated using the following formula (3): p and the second set of weights w q Perform weighted calculation to obtain the combined weight w j : The weight value w of the evaluation index is p and w q The relative importance of is defined as a, b, w pj is the first weight of the jth evaluation indicator, w qj is the second weight of the jth evaluation indicator, a j is the w of the jth evaluation indicator pj Relative to w qj The importance of b j is the w of the jth evaluation indicator qj Relative to w pj The importance of, m is the number of evaluation indicators; Define a controllable variable δ to evaluate the expert technical ability, with a value range of [0, 1], and thus the weight value w is expressed by the following formula (4): p and w q The relative importance of a and b:

8. The air compressor health assessment method according to claim 1, characterized in that: Step S4 includes: Use the following formula (5) to calculate the basic health of the air compressor at time t HV(t): where hv j (t) = 1-Deg j (t), is the basic health of the jth evaluation index of the air compressor at time t, w j is the combined weight of the jth evaluation indicator; The aging factor is taken into account using the following formula (6): What? a (t)=1-(1-HV0)e Bt (6) Where B is the aging coefficient, HV0 is the health value of the equipment when it is put into operation, and HV a (t) is the health of the air compressor at time t when only aging is considered, where t is the time from the first operation of the air compressor to the current time of evaluation; Define health factor u(t) = HV a (t) / HV0, and based on this health factor u(t) use the following formula (7) to calculate the comprehensive health of the air compressor HV: HV=u(t)·HV(t) (7).

9. The air compressor health assessment method according to any one of claims 1 to 8, characterized in that: The method further includes step S5, dividing the comprehensive health of the air compressor into four levels: healthy, sub-healthy, hidden danger, and fault.

10. An electronic device, comprising a processor and a memory, wherein instructions are stored in the memory, characterized in that: When the instructions are executed by the processor, they are used to implement the air compressor health assessment method according to any one of claims 1 to 9.

Images