A Performance Prediction Method, Electronic Device and Storage Medium for a Variable Condition Screw Compressor Unit

Abstract

The present invention discloses a method for predicting the performance of a variable-condition screw compressor unit, comprising the following steps: S1, build a screw compressor unit and install temperature sensors, pressure sensors and flow sensors at predetermined positions within the screw compressor unit; S2, determine the condition variables that affect the performance of the screw compressor unit. The present invention also discloses an electronic device and a storage medium. By analyzing the condition variables and parameters that affect the performance of the screw compressor unit, the present invention creatively couples multiple condition variables that affect the performance of the air compressor unit together, selects the optimal uniform experiment and combines it with sensors to complete the acquisition of each condition variable and response data, collects relatively stable data, and ensures the accuracy of the data; through the fitting process of the experimental data, the mathematical relationships between the parameters such as temperature, pressure and flow rate of each measuring point of the screw air compressor unit and the condition variables are obtained, so as to accurately complete the performance prediction of the screw compressor unit under different conditions.

Description

Technical Field

[0001] The present invention relates to the field of compressors, and in particular to a performance prediction method, an electronic device and a storage medium for a variable-condition screw unit. Background Art

[0002] Screw air compressor units are one of the most common mechanical devices in industries such as electric power, chemical fiber, and rail transit. With the continuous change of their application scope and scenarios, air compressor units often exhibit different working characteristics. Taking the subway in rail transit as an example, since the distance between stations is short, the braking system, air suspension device, door control, etc. of the train work frequently, the gas consumption increases. When the pressure in the air storage tank at the rear end of the air compressor unit is lower than 750 kpa, the air compressor unit starts to replenish air for the storage tank. When the pressure in the air storage tank reaches 900 kpa, the air compressor unit stops running. This makes the air compressor unit work with variable pressure ratio and frequent start-stop characteristics. In addition, the train operates in different regions (plain, plateau) and in different seasons, and the intake temperature and pressure of the screw unit also change within a wide range, making the screw unit always in an unsteady working mode. The unsteady working conditions present completely different performances from the steady-state operating conditions. The mismatch between the design of the screw air compressor and the actual application conditions will bring a series of faults such as lubricating oil emulsification, carbonization, high exhaust temperature, insufficient exhaust volume, and even ice blockage of the heat exchanger. These faults will pose a serious threat to the safe operation of rail transit. Therefore, to ensure that the screw air compressor can work stably under corresponding working conditions, an effective performance prediction method for the screw air compressor unit must be proposed according to the working characteristics of the air compressor unit when designing the screw unit. Then, based on the prediction of the performance of the air compressor unit, the optimization and improvement of the air compressor unit can be completed.

[0003] Currently, the methods for predicting the performance of screw machines in the industry are generally theoretical calculations based on the mathematical model of the steady-state operation of the unit, and the independent variables are relatively single (such as only changing the intake temperature or intake pressure, etc.). This prediction method does not consider the coupling of intake temperature, pressure, variable exhaust pressure, and frequent start-stop conditions together, and the calculation results have a large error and cannot be applied in engineering. And it is very complex to couple the intake temperature, intake pressure, exhaust pressure, and frequent start-stop of the compressor together. It is very difficult to predict the performance of the air compressor using the above method. Therefore, it is urgent to solve. Summary of the Invention

[0004] In order to avoid and overcome the technical problems existing in the prior art, the present invention provides a performance prediction method for a variable-condition screw unit, which realizes the performance prediction of the variable-condition screw unit; the present invention also provides an electronic device and a storage medium.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A performance prediction method for a variable-condition screw unit, comprising the following steps:

[0007] S1. Set up a screw unit and install temperature sensors, pressure sensors, and flow sensors at predetermined positions within the screw unit;

[0008] S2. Determine the operating condition variables (factors) that affect the performance of the screw unit. Assume there are a total of m, denoted as x i (i = 1, 2, 3,..., m), where the mth operating condition variable x m is defined as the unit operation rate, and its expression is:

[0009]

[0010] t 1 represents the total startup duration of the screw unit within one start-stop cycle, and t 2 represents the total shutdown duration (startup time interval) of the screw unit within one start-stop cycle, with the unit being s;

[0011] S3. When there is no interaction between any factors x i and x j (i ≠ j) and the relationship between the operating condition variables and the response value is linear, the response value can be obtained from the following formula:

[0012]

[0013] where is the response value, x i is the value of the x i operating condition variable during the test, and b i is the coefficient to be determined;

[0014] When there is an interaction between any factors x i and x j (i ≠ j), and the relationship between the operating condition variables and the response value is quadratic, the response value can be obtained from the following formula:

[0015]

[0016] where is the response value, x i is the value of the x i operating condition variable during the test, b i and b ii are the coefficients to be determined. Since the cross term x i x j is considered, so (that is, any two are selected from m factors for combination);

[0017] When it is uncertain whether there is an interaction between factors, with x i and xj (i ≠ j) There is an interaction to determine the number of tests, and the coefficients of the equation are in total ;

[0018] S4. According to the range [a, b] of the working condition variable x i , determine the level variable x ik (k = 1, 2, 3, …, n)

[0019]

[0020] where x ik represents the value taken by the factor x i at the k-th test, and n is the evenly divided number of tests;

[0021] S5. Arrange the tests. When the data collected by the screw compressor unit tends to be stable before shutdown, start continuous sampling, and take the most stable set of data as the final value of this test;

[0022] S6. Perform regression analysis on the test data of the discrete points obtained from the tests, fit to obtain the mathematical relationships between the temperature, pressure, flow rate, etc. of each point of the screw air compressor unit and the working condition variables, and then obtain the expressions of all position parameters under all working conditions of the screw compressor unit, and complete the performance prediction of the screw compressor unit under different working conditions.

[0023] As a further solution of the present invention, in step S3, the equation coefficients should be selected to minimize the sum of squared deviations, that is

[0024]

[0025] To minimize the sum of squared deviations, according to the principle of minimum value in mathematical analysis:

[0026]

[0027] Simplify the above formula to obtain the following normal equations:

[0028] l 11 b 1 + l 12 b 2 +... + l 1m b m = l 1y

[0029] l 21 b 1 + l 22 b 2 +... + l 2m b m = l 2y

[0030] …

[0031] l m1 b 1 +l m2 b 2 +...+l mm b m =l my

[0032]

[0033] The relevant parameters in the formula are calculated as follows:

[0034]

[0035]

[0036]

[0037]

[0038] In the formula, x ik represents the value taken by factor x i at the k-th test, and y k represents the test result of the response value y at the k-th test.

[0039] As a further solution of the present invention: the calculated equation coefficient b i is substituted into the equation in step S3, and then the regression equation is obtained. The significance test of the entire regression equation is carried out by using the F test;

[0040] The total variation sum of squares can be decomposed into the sum of the regression sum of squares U and the residual sum of squares Q:

[0041] L yy =U + Q

[0042] Total variation sum of squares:

[0043]

[0044] Regression sum of squares:

[0045]

[0046] Residual standard deviation:

[0047] S 2 =Q / (n - m - 1)

[0048] Make a test on the total regression equation:

[0049]

[0050] In order to characterize all working condition variables (factors) x 1 , x2 , …, x m For the total linear influence of each factor on y, perform the partial regression sum of squares and its significance test.

[0051] The partial regression sum of squares P i :

[0052]

[0053] In the formula, C ii is the i-th element on the diagonal of the inverse matrix of the regression normal equation coefficient matrix (l ij ); m×m For the i-th factor;

[0054] The partial regression sum of squares P i The larger it is, the more obvious the influence of x i on y. Perform an F i value test for each factor x i :

[0055]

[0056] All factors with a small partial regression sum of squares P i and an insignificant F i test should be excluded from the regression equation;

[0057] After excluding x i , the relationship between the new regression equation coefficients and the original regression coefficients b i is:

[0058]

[0059] In the formula, C ij is the element in the i-th row and j-th column of the inverse matrix C = (C ij ) of the regression normal equation coefficient matrix (l m×m ). ij For the j-th factor;

[0060] As a further solution of the present invention: In step S5, during sampling, set the sampling frequency to f, continuously sample 3t points, and divide the 3t points into three groups of data, denoted as d 1 , d 2 and d 3 , denoted as d i = [x i1 , x i2 , x i3 ... x it , i = 1, 2, 3. Process each group of data respectively in the following manner:

[0061]

[0062]

[0063] If where i = 1 or 2 or 3, then it is considered that the d i th group of data is relatively stable, and the weighted average value of the d i th group of data is taken as the final value of this experiment.

[0064] As a further solution of the present invention: in step S5, according to the determination of the number of test times in step S3, a uniform experimental design table is selected and then according to the corresponding usage table to arrange the experiment.

[0065] As a further solution of the present invention: the total number of test times n should satisfy n > z + 1.

[0066] As a further solution of the present invention: the screw compressor unit is sequentially connected with an intake buffer tank, an air filter, an intake valve, a screw compressor, an oil-gas separator, a first minimum pressure valve, an air cooler, an oil-water separator, a steam-water separator, an exhaust buffer tank, and a minimum pressure valve along the gas flow direction; along the oil pipeline conveying direction, the oil outlet of the oil-gas separator, a temperature control valve, an oil filter, and the oil inlet of the screw compressor are sequentially connected to form a closed-loop oil circuit, and an oil cooler for forced convection heat exchange of the lubricating oil is further installed downstream of the temperature control valve;

[0067] A coarse adjustment valve and a fine adjustment valve are provided at the intake end of the intake buffer tank to achieve fine adjustment of the intake pressure; a second minimum pressure valve is provided at the outlet end of the exhaust buffer tank to achieve fine adjustment of the exhaust pressure; the motor provides power for the screw compressor; the screw compressor is arranged in a high and low temperature environmental chamber to achieve precise adjustment of the intake temperature; the operation rate is adjusted through a plc outside the high and low temperature environmental chamber.

[0068] As a further solution of the present invention: flow sensors are provided at the upstream end of the oil cooler, the downstream end of the oil filter, and the downstream end of the steam-water separator; a temperature sensor is provided at the intake port of the intake buffer tank, a pressure sensor is provided inside the intake buffer tank, a temperature sensor is provided at the downstream end of the screw compressor, and temperature sensors and pressure sensors are provided at the oil inlet of the screw compressor; a pressure sensor is provided inside the oil-gas separator, and temperature sensors and pressure sensors are provided at the downstream ends of the first minimum pressure valve and the air compressor, a pressure sensor is provided at the downstream end of the oil filter, and temperature sensors and pressure sensors are provided at the upstream end and the downstream end of the oil cooler.

[0069] An electronic device: including a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are connected in sequence, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the performance prediction method of a variable-condition screw compressor unit.

[0070] A storage medium: The storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the performance prediction method of a variable-condition screw compressor unit.

[0071] Compared with the prior art, the beneficial effects of the present invention are:

[0072] 1. By analyzing the operating condition variables and parameters affecting the performance of the screw compressor unit, the present invention creatively couples multiple operating condition variables affecting the performance of the air compressor unit, selects the optimal uniform experiment and combines sensors to complete the acquisition of each operating condition variable and response data, and collects relatively stable data, ensuring the accuracy of the data; through the fitting process of the experimental data, the mathematical relationship between the temperature, pressure, flow rate and other parameters of each measuring point of the screw air compressor unit and the operating condition variables is obtained, so as to accurately complete the performance prediction of the screw compressor unit under different operating conditions.

[0073] 2. During the prediction process of the present invention, the significance test of the entire regression equation is carried out through the F test to determine the significance level of the regression equation for prediction; at the same time, the partial regression sum of squares and its significance test are carried out to determine the influence degree of each factor on the response value. The establishment of the screw compressor unit provides strong support for the subsequent prediction experiments. Description of the Drawings

[0074] Figure 1 It is a schematic structural diagram of the screw compressor unit in the present invention.

[0075] In the figure:

[0076] 1. Inlet buffer tank; 101. Coarse adjustment valve; 102. Fine adjustment valve;

[0077] 2. Air filter; 3. Inlet valve; 4. Screw compressor; 401. Motor;

[0078] 5. Oil and gas separator; 6. First minimum pressure valve; 7. Air cooler; 8. Oil-water separator;

[0079] 9. Steam-water separator; 10. Exhaust buffer tank; 11. Second minimum pressure valve;

[0080] 12. Temperature control valve; 13. Oil filter; 14. Oil cooler. Detailed Embodiments

[0081] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0082] Please refer to Figure 1 , in the embodiments of the present invention, a performance prediction method for a variable-condition screw unit includes the following steps:

[0083] S1. Build a screw unit, and install temperature sensors, pressure sensors, and flow sensors at predetermined positions in the screw unit.

[0084] The screw unit is composed of an intake buffer tank 1, an air filter 2, an intake valve 3, a screw compressor 4, an oil-gas separator 5, a first minimum pressure valve 6, an air cooler 7, an oil-water separator 8, a steam-water separator 9, an exhaust buffer tank 10, and a second minimum pressure valve 11 connected in sequence along the gas flow direction. The intake end of the intake buffer tank is provided with a coarse adjustment valve 101 and a fine adjustment valve 102 in parallel, and the intake pressure of the intake buffer tank is accurately controlled through the coarse adjustment and fine adjustment of the two valves; the outlet end of the exhaust buffer tank is provided with a second minimum pressure valve to achieve fine adjustment of the exhaust pressure.

[0085] Along the oil delivery direction, the oil outlet of the oil-gas separator 5, a temperature control valve 12, an oil filter 13, and the oil inlet of the screw compressor 4 are connected in sequence to form a circulating oil circuit. The operation of the screw compressor 4 is powered by a motor 401 or other driving components. The screw compressor 4 is arranged in a high and low temperature environmental chamber to achieve accurate adjustment of the intake temperature; the operation rate is adjusted through PLC settings outside the high and low temperature environmental chamber.

[0086] An oil cooler 14 is installed downstream of the temperature control valve 12 for forced convection heat exchange of the lubricating oil. The valve cover of the temperature control valve 12 is provided with bolt holes, and adjustable hexagon socket head cap screws are installed on the bolt holes. A spring abutting against the valve core is further arranged in the valve cavity of the temperature control valve 12. When adjusting the stroke of the valve core of the temperature control valve, the screw moves towards the inside of the valve cavity, thereby pushing the valve core to move. The movement of the valve core causes the cut-off element to reduce the orifice connecting the oil filter and the valve cavity, increasing the resistance of the lubricating oil in the valve cavity to enter the oil filter, and thereby forcing the lubricating oil to enter the oil cooler with relatively less resistance for forced convection heat exchange.

[0087] Each sensor in the screw unit is set at the corresponding position. Among them, flow sensors are arranged at the upstream end of the oil cooler 14, the downstream end of the oil filter 13, and the downstream end of the steam-water separator 9.

[0088] A temperature sensor is provided at the air inlet of the intake buffer tank 1, a pressure sensor is provided inside the intake buffer tank 1, a temperature sensor is provided at the downstream end of the screw compressor 4, and temperature sensors and pressure sensors are provided at the oil inlet of the screw compressor 4.

[0089] A pressure sensor is provided inside the oil-gas separator 5, temperature sensors and pressure sensors are provided at the downstream ends of the first minimum pressure valve 6 and the air compressor 7, a pressure sensor is provided at the downstream end of the oil filter 13, and temperature sensors and pressure sensors are provided at the upstream and downstream ends of the oil filter 14.

[0090] The flow rate of the screw unit of the present invention is 1 Nm 3 / min, and the rated exhaust pressure is 0.9 MPa. Its flow rate is collected by an LUGB type vortex flowmeter and an NI 9234 board card.

[0091] Combined with the working characteristics of the screw unit, it is determined that the working condition variables affecting the screw unit are the intake pressure x 1 , the intake temperature x 2 , the exhaust pressure x 3 and the operation rate x 4 .

[0092] S2. Determine the working condition variables (factors) affecting the performance of the screw unit. Assume there are a total of m, denoted as x i (i = 1, 2, 3,..., m), where the mth working condition variable x m is defined as the operation rate of the unit, and its expression is:

[0093]

[0094] t 1 represents the total startup duration of the screw unit within a start-stop cycle, and t 2 represents the total shutdown duration (startup time interval) of the screw unit within a start-stop cycle, with the unit being s;

[0095] S3. When there is no interaction between any factor x i and x j (i ≠ j) and the working condition variable and the response value are linearly related, the response value can be obtained from the following formula:

[0096]

[0097] where is the response value, x i is the value of the xth i working condition variable during the test, and b i is the coefficient to be determined;

[0098] When any factor x i and xj When there is an interaction between (i≠j) and the working condition variables and the response value has a quadratic relationship, the response value can be obtained from the following formula:

[0099]

[0100] Where is the response value, x i is the value of the x i working condition variable during the test, b i and b ii are the coefficients to be determined. Since the cross terms x i x j are considered, so (that is, any two are selected from m factors for combination);

[0101] When it is not certain whether there is an interaction between the uncertain factors, taking x i and x j (i≠j) having an interaction to determine the number of tests, the total number of coefficients of the equation is pieces.

[0102] For the working condition parameters, there are intake pressure x 1 , intake temperature x 2 , exhaust pressure x 3 and operating rate x 4 , If it is possible to estimate the coefficients of the equation, the total number of tests n should satisfy n>14 + 1 = 15. Therefore, the number of tests n is taken as 16.

[0103] In step S3, the coefficients of the equation should be selected to minimize the sum of squared deviations, that is

[0104]

[0105] To minimize the sum of squared deviations, according to the principle of minimum value in mathematical analysis:

[0106]

[0107] Simplifying the above formula gives the following normal equations:

[0108] l 11 b 1 +l 12 b 2 +...+l 1m b m =l 1y

[0109] l 21 b 1 +l 22 b 2 +...+l2m b m = l 2y

[0110] …

[0111] l m1 b 1 + l m2 b 2 +... + l mm b m = l my

[0112]

[0113] The relevant parameters in the formula are calculated as follows:

[0114]

[0115]

[0116]

[0117]

[0118] In the formula, x ik represents the value taken by factor x i at the k-th test, and y k represents the test result of the response value y at the k-th test.

[0119] The calculated equation coefficient b i is substituted into the equation in step S3, and then the regression equation is obtained. The significance test of the entire regression equation is carried out by using the F-test;

[0120] The total variation sum of squares can be decomposed into the sum of the regression sum of squares U and the residual sum of squares Q:

[0121] L yy = U + Q

[0122] Total variation sum of squares:

[0123]

[0124] Regression sum of squares:

[0125]

[0126] Residual standard deviation:

[0127] S 2 = Q / (n - m - 1)

[0128] Make a test on the total regression equation:

[0129]

[0130] Record the above calculation results in the following analysis of variance table 1

[0131]

[0132] If F≥F 0.01 (m, n - m - 1), it is considered that the regression is highly significant, denoted as **;

[0133] If F 0.05 (m, n - m - 1) ≤ F ≤ F 0.01 (m, n - m - 1), it is considered that the regression is significant, denoted as *;

[0134] If F 0.1 (m, n - m - 1) ≤ F ≤ F 0.05 (m, n - m - 1), it is considered that the regression significance is general, denoted as ⊙;

[0135] If F < F 0.1 (m, n - m - 1), it is considered that the regression is not significant, denoted as △.

[0136] In order to characterize the linear influence of each factor in all working condition variables (factors) x 1 , x 2 , …, x m on y in total, conduct the partial regression sum of squares and its significance test.

[0137] The partial regression sum of squares P i :

[0138]

[0139] Where C ii is the i-th element on the diagonal of the inverse matrix of the regression normal equation coefficient matrix (l ij ); m×m The larger the partial regression sum of squares P

[0140] i is, the more obvious the influence of x i on y. Conduct an F i i value test for each factor x i :

[0141]

[0142] Any factor with a small partial regression sum of squares P i and an insignificant F i test should be removed from the regression equation;

[0143] After removing x i , the coefficients of the new regression equation and and the original regression coefficient b i The relationship is as follows:

[0144]

[0145] where C ij is the coefficient matrix of the regression normal equation (l ij ) m×m The inverse matrix C = (C ij ) is the element in the i-th row and j-th column.

[0146] According to the determination of the number of tests in step S3, select the uniform experimental design table Then, according to the corresponding usage table to arrange the tests.

[0147] In this embodiment, select the uniform experimental design table Then, according to the corresponding usage table to arrange the tests.

[0148] The following is the uniform experimental design table 2:

[0149]

[0150] The following is the usage table 3 of the uniform design table :

[0151]

[0152] Note: In the table, s represents the number of factors, D represents the deviation characterizing the uniformity, and the smaller its value, the better the uniformity.

[0153] Since there are 4 working condition variables in this test, according to the usage table, the 1st, 4th, 5th, and 6th columns in the design table should be selected to arrange the tests.

[0154] S4. According to the range [a, b] of the working condition variable x i , determine the level variable x ik (k = 1, 2, 3,..., n)

[0155]

[0156] where x ik represents the value taken by the factor x i at the k-th test, and n is the number of equally divided tests;

[0157] The working condition variable intake air temperature x 1 has a range of [-25, 50] °C, then x 2 = [-25, -20, -15,..., 50] °C;

[0158] Operating condition variable intake pressure x 2 Range [79, 101] kPa, then x 1 = [79, 80.47, 81.94, …, 101] kPa;

[0159] Operating condition variable exhaust pressure x 3 Range [750, 900] kPa, x 3 = [750, 760, 770, …, 900] kPa;

[0160] Operating condition variable operating rate range [10%, 40%], corresponding to the shutdown time x within one start-stop cycle 4 = [10% (1620 s), 12% (1320 s), 14% (1105.7), …, 40% (270 s)], the start-up time within one start-stop cycle is uniformly set to 180 s in the operating rate; Note: The time in the parentheses is the shutdown time t within one start-stop cycle corresponding to the operating rate when the start-up time within one start-stop cycle is 180 s 2 .

[0161] S5. Arrange the experiment. When the data collected by the screw compressor unit tends to be stable before shutdown, start continuous sampling, and take the most stable set of data as the final value of this test.

[0162] During sampling, set the sampling frequency as f, continuously sample 3t points, evenly divide the 3t points into three groups of data, denoted as d 1 , d 2 and d 3 , denoted as d i = [x i1 , x i2 , x i3 ……x it , i = 1, 2, 3. Process each group of data respectively in the following way:

[0163]

[0164]

[0165] If where i = 1 or 2 or 3, then it is considered that the d i th group of data is relatively stable, and take the weighted average of the d i th group of data as the final value of this test.

[0166] The final results of the data collected for each test condition after processing are shown in Table 4 below:

[0167]

[0168] Note: The flow rates in the table have been converted to standard conditions using the ideal gas law.

[0169] The sum and average of each variable were calculated, as shown in Table 5 below.

[0170]

[0171] The cross-product sum of each variable (j = 1, 2, 3, …, m) is shown in Table 6 (cross-products and sums of variables):

[0172]

[0173] The coefficients and constant terms of the normal equations l ij and the total sum of squares of y l yy = l 55 , as shown in Table 7:

[0174]

[0175] The expression of the normal matrix equation is then

[0176]

[0177] Solving: b 1 = -4.6595, b 2 = 13.7632, b 3 = -0.3634, b 4 = -0.0303

[0178]

[0179] Substituting the calculated equation coefficients b i into it, the regression equation is obtained:

[0180]

[0181] The significance of this regression equation was tested using the F-test.

[0182] The total sum of squares of variation can be decomposed into the sum of the regression sum of squares U and the residual sum of squares Q:

[0183] L yy = U + Q

[0184] Total sum of squares of variation:

[0185]

[0186] Regression sum of squares:

[0187]

[0188] Residual standard deviation:

[0189] S 2 = Q / (n - m - 1)

[0190] Perform a test on the total regression equation:

[0191]

[0192] Perform a test on the total regression equation. The calculation results are shown in Table 8 below:

[0193]

[0194] From the parameters in the table, look up the F-distribution table for F 0.01 (4, 11) = 5.67, F > F 0.01 (4, 11). The above regression equation is highly significant.**

[0195] In order to characterize the overall linear influence of each factor (independent variable) x 1 , x 2 , …, x m on y, perform a partial regression coefficient test;

[0196] Partial regression sum of squares P i :

[0197]

[0198] where C ii is the i-th element on the diagonal of the inverse matrix of the regression normal equation coefficient matrix (l ij ) m×m ;

[0199] Inverse matrix C of the regression normal equation coefficient matrix:

[0200]

[0201] From this, calculate P 1 = 127471.47, P 2 = 110048.03, P 3 = 3235.96, P 4 = 1639.45

[0202] The larger the partial regression sum of squares P i , the more obvious the influence of x i on y. Perform an F i value test on each factor x i :

[0203]

[0204] F 1 = 209.21, F 2 = 180.61, F 3 = 5.31, F 4 = 2.69, look up the F-distribution table F 0.01 (4, 11) = 5.67,

[0205] F 0.05 (4, 11) = 3.36, F 0.1 (4, 11) = 2.86, F 0.2 (4, 11) = 1.8.

[0206] F 1 = 209.21 > F 0.01 (4, 11) = 5.67, indicating that the intake air temperature has a highly significant impact on the exhaust gas flow rate (**);

[0207] F 2 = 180.61 > F 0.01 (4, 11) = 5.67, indicating that the intake air pressure has a highly significant impact on the exhaust gas flow rate (**);

[0208] F 0.01 (4, 11) = 5.67 > F 3 = 5.31 > F 0.05 (4, 11) = 3.36, indicating that the exhaust gas pressure has a significant impact on the exhaust gas flow rate (*);

[0209] F 0.1 (4, 11) = 2.86 > F 4 = 2.69 > F 0.2 (4, 11) = 1.8, indicating that the operating rate has a certain impact on the exhaust gas flow rate (△);

[0210] In this example, since each operating condition variable has an impact on the exhaust gas volume, no operating condition variable is excluded, and the above regression equation is valid.

[0211] Given any intake air pressure x 1 、intake air temperature x 2 、exhaust gas pressure x 3 、operating rate (start-up time interval) x 4 , the flow rate of the screw compressor unit under this operating condition can be predicted.

[0212] Repeating the above steps can predict the temperature and pressure at any position within the screw compressor unit.

[0213] Another embodiment of this application is an electronic device.

[0214] The electronic device can be the movable device itself or a stand-alone device independent thereof, which can communicate with the movable device to receive the input signals collected therefrom and send the selected target decision-making behaviors thereto.

[0215] The electronic device includes one or more processors and a memory.

[0216] The processor can be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions.

[0217] The memory can include one or more computer program products, and the computer program products can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory can include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory can include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions can be stored on the computer-readable storage media, and the processor can run the program instructions to implement the prediction methods of the various embodiments of the present application described above.

[0218] In one example, the electronic device can further include: an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms. For example, the input device can include various devices such as on-board diagnostic system (OBD), cameras, industrial cameras, etc. The input device can also include, for example, a keyboard, a mouse, and so on. The output device can include, for example, a display, a speaker, a printer, and a communication network and the remote output devices connected thereto, etc.

[0219] In addition, according to specific application scenarios, the electronic device can further include any other appropriate components.

[0220] Another embodiment of the present application can also be a computer program product, which includes computer program instructions that, when run by a processor, cause the processor to execute the steps in the decision-making behavior decision method according to various embodiments of the present application described in the prediction method part of the above description of the present specification.

[0221] The computer program product may be written in any combination of one or more programming languages for executing the program code of the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0222] In addition, an embodiment of the present application may also be a computer-readable storage medium storing computer program instructions, which when run by a processor cause the processor to execute the steps in the decision-making behavior decision method according to various embodiments of the present application described in the above prediction method part of this specification.

[0223] The computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0224] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present application. In addition, the above-disclosed specific details are only for the purposes of illustration and easy understanding, rather than limitations, and the above details do not limit the present application to necessarily adopt the above specific details for implementation.

[0225] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "comprising," "including," "having," etc. are open-ended terms that mean "including but not limited to" and can be used interchangeably with each other. The words "or" and "and" as used herein refer to the phrase "and / or" and can be used interchangeably with it, unless the context clearly indicates otherwise. The phrase "such as" as used herein refers to the phrase "such as but not limited to" and can be used interchangeably with it.

[0226] It should also be noted that in the devices, equipment, and methods of this application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of this application.

[0227] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0228] The above description has been presented for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for predicting the performance of a variable-condition screw unit, characterized in that, it includes the following steps: S1. Set up a screw unit, and install temperature sensors, pressure sensors, and flow sensors at predetermined positions within the screw unit; S2. Determine the operating variables that affect the performance of the screw compressor unit. Assume that there are a total of m of them, denoted as x i ( i = 1, 2, 3, …, m ), where the m th operating variable x m is defined as the unit operation rate, and its expression is: ； t 1 Indicates the total startup duration of the screw compressor unit within one start-stop cycle, t 2 Indicates the total shutdown duration of the screw compressor unit within one start-stop cycle, that is, the startup time interval, with the unit of s ; S3. When any operating condition variable x i and x j ( i ≠ j )have no interaction and the operating condition variable and the response value are linearly related, the response value can be obtained by the following formula: ； Among them is the response value x i is the value of the x i operating condition variable during the test, b i is the coefficient to be determined; When any operating condition variable x i interacts with x j ( i ≠ j ), and the operating condition variable and the response value have a quadratic relationship, the response value can be obtained by the following formula: ； Among them is the response value x i is the value of the x i operating condition variable during the test b i and b ii are the coefficients to be determined. Since cross terms x i x j are considered, so that is, choose any two from m operating condition variables for combination When it is uncertain whether there is an interaction between uncertain working condition variables, use x i and x j ( i≠j ) having an interaction to determine the number of tests. The coefficients of the equation are a total of z = ; S4. According to the operating condition variables x i within the range a , b , determine the horizontal variables x ik ( k = 1, 2, 3, …, n ): ； wherein x ik represents the operating condition variable x i at the k value taken during the n th test, and n is the evenly divided number of tests; S5. Arrange an experiment. Start continuous sampling when the data collected by the screw unit tends to be stable before shutdown, and take the most stable set of data as the final value of this experiment; S6. Perform regression analysis on the experimental data of the discrete points obtained from the experiment, fit to obtain the mathematical relationships between the temperature, pressure, and flow parameters of each point of the screw air compressor unit and the operating condition variables, and then obtain the expressions of all position parameters under all operating conditions of the screw unit, thereby completing the performance prediction of the screw unit under different operating conditions.

2. A method for predicting the performance of a variable-condition screw unit according to claim 1, characterized in that, in step S3, the equation coefficients should be selected to minimize the sum of squared deviations, that is: ； To minimize the sum of squared deviations, according to the principle of minimum value in mathematical analysis: ； Simplify the above formula to obtain the following normal equations: ； ； ； ； The relevant parameters in the formula are calculated as follows: ； ； ； ； wherein x ik represents the operating condition variable x i the value taken at the k th test, and y k represents the response value y the test result at the k th time.

3. A method for predicting the performance of a variable-condition screw unit according to claim 2, characterized in that, Calculated equation coefficients b i Substitute into the equation in step S3, and the regression equation can be obtained. Using F The significance test is performed on the entire regression equation; The total variation sum of squares can be decomposed into the regression sum of squares U and the sum of the residual sum of squares Q as follows: ； Total variation square: ； Regression sum of squares: ； Residual standard deviation: ； Make a test on the total regression equation: ； In order to characterize the linear effects of each operating condition variable x 1 , x 2 ,…, x m on the total y, partial regression sum of squares and its significance test are carried out; Partial regression sum of squares P i : ； where C ii is the -th element on the diagonal of the inverse matrix of the regression normal equation coefficient matrix i ; Partial regression sum of squares P i The larger the x i For y the more obvious the influence is. For each operating condition variable x i perform F i value test: ； All partial regression sums of squares P i that are small and F i operating condition variables with insignificant tests should be removed from the regression equation; Eliminate x i After that, the coefficients of the new regression equation and and the original regression coefficients b i The relationship is as follows: ； In the formula C ij is the regression normal equation coefficient matrix inverse matrix C = ( C ij ) in the i row j column element.

4. A method for predicting the performance of a variable-condition screw unit according to claim 1, characterized in that, In step S5, during sampling, set the sampling frequency as f , continuously sample 3 t points, divide the 3 t points into three groups of data, denoted as d 1 , d 2 and d 3 , denoted as d i = x i1 , x i2 、x i3 ……x it ], i i = 1, 2, 3, process each group of data respectively in the following way: ； ； If , where i = 1 or 2 or 3, then the d i th group of data is considered relatively stable, and the weighted average value of the d i th group of data is taken as the final value of this experiment.

5. A method for predicting the performance of a variable-condition screw unit according to claim 1, characterized in that, In step S5, according to the determination of the number of trials in step S3, a uniform experimental design table is selected , and then according to the corresponding usage table, the experiments are arranged.

6. A method for predicting the performance of a variable-condition screw unit according to claim 1, characterized in that, Total number of tests n shall satisfy n > z + 1 piece 7. An electronic device, characterized in that, it includes a processor, an input device, an output device, and a memory. The processor, input device, output device, and memory are connected in sequence. The memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions to execute a method for predicting the performance of a variable-condition screw unit according to any one of claims 1 to 6.

8. A readable storage medium, characterized in that, this storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor is caused to execute a method for predicting the performance of a variable-condition screw unit according to any one of claims 1 to 6.

Images