Energy consumption management method of multi-stage compression system based on artificial intelligence

Abstract

The present invention relates to the field of electronic digital data processing technology, and specifically to an energy consumption management method for a multi-stage compression system based on artificial intelligence, including obtaining the pressure data of each hydrogen storage tank and converting it to obtain a pressure curve corresponding to each of the hydrogen storage tanks; segmenting the pressure curve to obtain a plurality of segmented interval curves; calculating the evaluation value corresponding to each of the segmented interval curves based on the pressure value change in each of the segmented interval curves; judging the current load state of each of the hydrogen storage tanks based on the evaluation value corresponding to each of the segmented interval curves; and adjusting the air intake rate of the compressor corresponding to the hydrogen storage tank according to the current load state of each of the hydrogen storage tanks. In the present invention, by monitoring the change in the pressure value of each stage of the hydrogen storage tank, the air intake rate of each stage of the compressor is calculated based on the pressure change analysis, so that the overall compression rate of the multi-stage compression system just meets the load requirements, thereby reducing energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical digital data processing, and in particular to an energy consumption management method for a multi-stage compression system based on artificial intelligence. Background Art

[0002] A hydrogen cycle test system includes gas supply system, boosting system and pipeline system. The main component of the gas supply system is the multi-stage compression system, which is generally composed of multi-stage compressors connected in series. Compared with single-stage compressors, multi-stage compressors are more efficient and consume less energy.

[0003] However, in the traditional method, the operation of the multi-stage compressor is mainly judged by the threshold range of the pressure in the hydrogen storage tank. And there are only two operations for the multi-stage compressor: running and pausing. This method causes the multi-stage compressor to start or stop multiple times under load, increasing the overall energy consumption of the multi-stage compression system. In addition, the use of the threshold of the hydrogen storage tank pressure does not take into account the impact of the external environment on the hydrogen storage tank, there are errors in the load judgment of the current system, and there are errors in the control time of the operation and pause of the multi-stage compressor, which further increases the overall energy consumption of the multi-stage compression system. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an energy consumption management method for a multi-stage compression system based on artificial intelligence to solve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] The present application provides an artificial intelligence-based multi-stage compression system energy consumption management method, the method comprising: acquiring pressure data of each hydrogen storage tank in real time; performing curve conversion on the pressure data of each hydrogen storage tank to obtain a pressure curve corresponding to each hydrogen storage tank, wherein the ordinate of the pressure curve is the pressure value and the abscissa is the time; performing segmentation processing according to the extreme points of each pressure curve to obtain a plurality of segmented interval curves; calculating based on the pressure value change in each segmented interval curve to obtain an evaluation value corresponding to each segmented interval curve under the influence of temperature; judging based on the evaluation value corresponding to each segmented interval curve to obtain the current load state of each hydrogen storage tank; adjusting the air intake rate of the compressor corresponding to the hydrogen storage tank according to the current load state of each hydrogen storage tank to reduce the energy consumption of the multi-stage compression system.

[0006] In a possible implementation, segmentation processing is performed according to the extreme point of each pressure curve to obtain multiple segmented interval curves, including: smoothing each pressure curve separately by a preset Douglas Peucker algorithm to obtain multiple smoothed pressure curves; segmenting each smoothed pressure curve one by one to obtain multiple segmented interval curves corresponding to each pressure curve, and the segmentation point between two adjacent segmented interval curves is an extreme point.

[0007] In a possible implementation, an evaluation value corresponding to each segmented interval curve is obtained based on the calculation of the air pressure change within each segmented interval curve, including: calculating the pressure curve slope corresponding to each time point based on the change of the pressure value over time within the segmented interval curve; extracting the maximum pressure and the minimum pressure in the segmented interval curve; calculating the evaluation value corresponding to the segmented interval curve based on the corresponding maximum pressure, minimum pressure and the slope of the pressure curve within the segmented interval curve; normalizing the evaluation value corresponding to the segmented interval curve, and updating the evaluation value to the normalized result.

[0008] In a possible implementation, the load state of each of the hydrogen storage tanks is obtained based on the evaluation value corresponding to each of the segmented interval curves, including: when the evaluation value corresponding to the segmented interval curve is greater than a preset load threshold, the hydrogen storage tank corresponding to the segmented interval curve is in a load state, otherwise the hydrogen storage tank corresponding to the segmented interval curve is in a no-load state.

[0009] In a possible implementation, the preset load threshold is -0.5.

[0010] In one possible implementation, the current load state includes a load state or a no-load state, and the current load state includes load or no-load. The air intake rate of the compressor corresponding to the hydrogen storage tank is adjusted according to the current load state of each hydrogen storage tank to reduce the energy consumption of the multi-stage compression system, including: when the current load state of the hydrogen storage tank is a no-load state, the air intake rate of the compressor corresponding to the hydrogen storage tank is set to a first preset rate.

[0011] In a possible implementation, the current load state includes a load state or a no-load state, and the intake rate of the compressor corresponding to the hydrogen storage tank is adjusted according to the current load state of each hydrogen storage tank to reduce the energy consumption of the multi-stage compression system, including: when the current load state of the hydrogen storage tank is a load state, the intake rate of the compressor corresponding to the hydrogen storage tank is set to a second preset rate, and the second preset rate is calculated by the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the hydrogen storage tank, the first evaluation value and the second evaluation value are the evaluation values ​​corresponding to the first segmented interval curve and the second segmented interval curve, respectively, the cutoff time of the first segmented interval curve is the current time, and the second segmented interval curve is adjacent to the first segmented interval curve.

[0012] In one possible implementation, the calculation method of the second preset rate includes: calculating the overall load evaluation value corresponding to the first segmented interval curve according to the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the n-th stage hydrogen storage tank, wherein the n-th stage hydrogen storage tank is the hydrogen storage tank corresponding to the last stage compressor in the multi-stage compression system, and n is a natural number greater than zero; calculating the m-th level load evaluation value corresponding to the first segmented interval curve according to the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the m-th stage hydrogen storage tank, and m is a natural number less than or equal to n; calculating the second preset rate according to the m-th level load evaluation value and the overall load evaluation value corresponding to the first segmented interval curve.

[0013] In a possible implementation, the number of the hydrogen storage tanks is three.

[0014] In a possible implementation, the pressure data acquisition time interval of each hydrogen storage tank is 10 seconds.

[0015] The present invention has the following beneficial effects:

[0016] In the present invention, by monitoring the change of the pressure value of each stage of the hydrogen storage tank, the evaluation value of the hydrogen storage tank under the influence of the external temperature is obtained according to the pressure change analysis, and the load state of the compressor corresponding to each stage of the hydrogen storage tank is determined according to the size of the evaluation value, and the air intake rate of each stage of the compressor is modified according to the load state of the compressor, so that the overall compression rate of the multi-stage compression system meets the load requirements and achieves the purpose of energy saving; it overcomes the disadvantage of the prior art that only the hydrogen storage tank pressure threshold is set, but the compression rate of the compressor cannot be adjusted in real time according to the hydrogen demand of the hydrogen circulation test system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 This is a schematic structural diagram of a hydrogen circulation test system described in Example 1 of the present invention;

[0019] Figure 2 A schematic flow chart of a multi-stage compression system energy consumption management method based on artificial intelligence provided in Embodiment 2 of the present invention;

[0020] Figure 3 This is a schematic flow chart of step S3 described in Example 2 of the present invention;

[0021] Figure 4 This is a flow chart of step S4 described in Embodiment 2 of the present invention;

[0022] Figure 5 This is a schematic diagram of the process of step S5 described in Embodiment 2 of the present invention;

[0023] Figure 6 This is a schematic flow chart of step S6 described in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0024] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the energy consumption management method of a multi-stage compression system based on artificial intelligence proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0025] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0026] Embodiment 1:

[0027] See also Figure 1 , Figure 1 A schematic diagram of the structure of a hydrogen cycle test system is shown in FIG. The hydrogen cycle test system includes: a gas supply system, a pressurization system, a piping system, an environmental chamber controlled by a temperature control system, a drive system, a recovery system, and a control and data acquisition system.

[0028] In this embodiment, the gas supply system is used to provide initial hydrogen to the pipelines, buffer tanks, boosters and other components in the hydrogen circulation test system before the first cycle after the air replacement is completed. In the subsequent cycles, the gas supply system performs appropriate gas replenishment according to the needs of the hydrogen circulation test system; the boosting system is the core of the hydrogen circulation test system, which is used to pressurize the hydrogen to a set pressure and adjust and control the flow rate of the hydrogen; the pipeline system is used to connect the boosting system and the workpiece under test, and provide the gas with a flow mode that meets the standard requirements; the recovery system is responsible for recovering the gas flowing out of the workpiece under test at the end of each cycle, and providing it to the boosting system for the next cycle; the drive system provides a power source for the boosting system and the pipeline system; the control and data acquisition system measures and collects data such as pressure, temperature, strain, chlorine concentration, oxygen concentration, etc. during the test, and controls the automatic operation of the test according to the measured values.

[0029] Specifically, the boosting device in the boosting system of this embodiment is a piston booster. Taking into account the single-machine compression ratio limitation, displacement matching and other issues, a single-machine boosting system is selected to form a three-stage compression system. Specifically, the technical parameters of the three-stage hydrogen booster are shown in Table 1:

[0030] Table 1

[0031]

[0032] As shown in Table 1, the three-stage compression system is equipped with a total of three hydrogen compressors connected in sequence, and a hydrogen storage tank or buffer is configured after each compressor, that is, in this embodiment, the hydrogen storage tank can also be divided into a primary hydrogen storage tank, a secondary hydrogen storage tank and a tertiary hydrogen storage tank, wherein the tertiary hydrogen storage tank can also be called a final hydrogen storage tank for supplying hydrogen to the hydrogen circulation test system, and can be used as a source of hydrogen for the entire hydrogen circulation test system.

[0033] In the daily use of the above-mentioned multi-stage compression system, the prior art does not consider the load condition of each hydrogen storage tank (the buffer located after each stage of the compressor) to adjust the air intake rate of each stage of the compressor, thus causing energy consumption problems for the entire multi-stage compression system.

[0034] Embodiment 2:

[0035] This embodiment below specifically illustrates a specific solution of a multi-stage compression system energy consumption management method based on artificial intelligence provided by the present invention in conjunction with the accompanying drawings, which is used to solve the technical problems arising in Example 1.

[0036] See also Figure 2 , which shows a flow chart of an artificial intelligence-based multi-stage compression system energy consumption management method provided by an embodiment of the present invention, including step S1, step S2, step S3, step S4, step S5 and step S6.

[0037] S1. Obtain the pressure data of each hydrogen storage tank in real time.

[0038] Specifically, in this embodiment, the pressure data is collected by the pressure monitoring transmitter installed in the hydrogen storage tank. At the same time, each pressure monitoring transmitter records the pressure data once every 10 seconds, and is in a 24-hour real-time monitoring mode.

[0039] S2. Performing curve conversion on the pressure data of each hydrogen storage tank to obtain a pressure curve corresponding to each hydrogen storage tank, wherein the ordinate of the pressure curve is the pressure value and the abscissa is the time. The unit of the pressure value of the pressure curve is megapascal (MPa), and the unit of time is second (s).

[0040] S3. Perform segmentation processing according to the extreme value points of each pressure curve to obtain multiple segmented interval curves.

[0041] To clarify how the segmentation process is performed in this step, see Figure 3 In this step, step S3 includes step S31 and step S32.

[0042] S31. Smoothing each pressure curve using a preset Douglas Peucker algorithm to obtain a plurality of smoothed pressure curves.

[0043] Among them, the Douglas Peucker algorithm mentioned in this step is a prior art, and its use method and principle will not be described in detail in this application.

[0044] S32, segmenting each of the smooth pressure curves one by one to obtain a plurality of segmented interval curves corresponding to each of the pressure curves, wherein a segmentation point between two adjacent segmented interval curves is an extreme point.

[0045] Specifically, the present application will divide the smooth pressure curve corresponding to the last 24 hours into J segmented interval curves, assuming that the hydrogen circulation test system uses hydrogen three times in total within 24 hours, and the corresponding multi-stage compression system works a total of three times and the last time point of the smooth pressure curve just ends, then there are a total of three pressure drop stages and three pressure rise stages. Finally, the smooth pressure curve corresponding to the 24 hours is divided into J=6 segmented interval curves.

[0046] In this embodiment, through the above steps, a pressure curve can be divided into segmented interval curves corresponding to multiple time periods.

[0047] S4. Calculate the pressure value change in each segmented interval curve to obtain an evaluation value corresponding to each segmented interval curve under the influence of temperature.

[0048] In this embodiment, considering that the pressure in the hydrogen storage tank reflects the corresponding compressor load, and the third-stage hydrogen storage tank or the final-stage hydrogen storage tank reflects not only the compressor load but also the load of the entire multi-stage compression system. As the mass of hydrogen in the hydrogen storage tank decreases, the pressure in the hydrogen storage tank will also gradually decrease, and vice versa.

[0049] At the same time, since the pressure in the hydrogen storage tank is affected by the outside temperature, the higher the outside temperature, the greater the pressure in the hydrogen storage tank, making the existing technology's judgment on the quality of hydrogen in the hydrogen storage tank larger than the actual situation. The lower the outside temperature, the smaller the pressure in the hydrogen storage tank, making the existing technology's judgment on the quality of hydrogen in the hydrogen storage tank smaller than the actual situation.

[0050] In order to better show the load condition of the hydrogen storage tank in this embodiment, it is necessary to exclude the influence of temperature and sequentially accurately identify the working load state of the entire multi-stage compression system. Therefore, in this embodiment, the compressor state corresponding to each hydrogen storage tank is first evaluated according to the fluctuation of the segmented interval curve. When there is no load, the compressor does not operate, and the pressure in the hydrogen storage tank is only affected by the external temperature, and the influence of the external temperature on the pressure is relatively small. Therefore, whether the curve is rising or falling, the amplitude change of the curve is small, and the loaded curve is shown as a falling state, and the amplitude is larger. Therefore, in this step, the degree of influence of the evaluation value of the adjacent unloaded segmented interval on the current temperature is analyzed. When the absolute value of the evaluation value of the adjacent unloaded segmented interval is larger, the degree of influence of the external temperature is greater. For details, please refer to Figure 4 , step S4 includes step S41, step S42, step S43 and step S44.

[0051] S41. Calculate the pressure curve slope corresponding to each time point based on the change of the pressure value in the segmented interval curve over time.

[0052] It should be noted that the slope of the pressure curve mentioned in this step can be obtained by performing a differential or interpolation method on each data point in the segmented interval curve. The differential or interpolation method for solving the slope of each point in the curve is an existing technology and will not be repeated in this embodiment.

[0053] S42, extracting the maximum pressure value and the minimum pressure value from the segmented interval curve.

[0054] S43. Calculate the evaluation value corresponding to the segmented interval curve based on the maximum pressure value, the minimum pressure value corresponding to the segmented interval curve and the slope of the pressure curve within the segmented interval curve.

[0055] Specifically, the calculation formula of the evaluation value in this embodiment is as follows:

[0056]

[0057] In the above formula, j∈[1,J], j is an integer, and J represents the total number of segmented interval curves; R j represents the evaluation value corresponding to the jth segment interval curve; k i represents the slope of the pressure curve of the i-th data point in the j-th segment interval curve; ρ j,max represents the maximum value of pressure in the jth segment interval curve; ρ j,min Indicates the minimum value of pressure in the jth segment interval curve; n i Represents the total number of data points in the jth segment interval curve; the 0.01 in the denominator is to prevent the denominator from being zero.

[0058] In the above calculation formula, It represents the sum of the slopes of the pressure curves corresponding to all data points in the jth segmented interval curve. The larger its value is, the closer the overall trend of the current interval curve is to the state without load. j,max -ρ j,min It is the difference between the maximum and minimum pressure values ​​in the jth segment interval curve. The smaller the value, the smaller the overall fluctuation of the data in the current time period, which is consistent with the characteristic that the pressure changes slowly and small when only affected by temperature. is j,max -ρ j,min The reciprocal of , the larger the value, the greater the evaluation value corresponding to the j-th segment interval curve.

[0059] S44, the evaluation value R corresponding to the segmented interval curve j Normalize and update the evaluation value to the normalized result. j The value range of is [-1, 1].

[0060] S5, based on the evaluation value r corresponding to each segment interval curve j Determine and obtain the current load status of each of the hydrogen storage tanks.

[0061] In order to clarify the current load status evaluation method of each hydrogen storage tank, an exemplary judgment method is given in this embodiment. Figure 5 , this step includes step S51.

[0062] S51, when the evaluation value r corresponding to the segmented interval curve j When the load is greater than a preset load threshold, the hydrogen storage tank corresponding to the segmented interval curve is in a loaded state; otherwise, the hydrogen storage tank corresponding to the segmented interval curve is in a non-loaded state.

[0063] Specifically, in this embodiment, the preset load threshold is -0.5. After the current load state is determined, in this embodiment, it is considered that the time period corresponding to the no-load state |r j The larger the value is, the greater the degree to which the load state time period adjacent to the no-load state time period is affected by the outside temperature.

[0064] In this embodiment, it is considered that the smaller the evaluation value corresponding to the load state time period is, the greater the degree of pressure reduction in the current hydrogen storage tank is, the greater the current load is, and the faster the compression rate of the multi-stage compressor should be. At the same time, the longer the maintenance time of the current load state time period is, the greater the consumption of hydrogen in the hydrogen storage tank is, and the greater the load is. In addition, the smaller the pressure value of the current load time period is, the greater the current load is, and the faster the compression rate of the multi-stage compressor should be. Therefore, in this embodiment, the current load situation is also analyzed by the evaluation value of the current load state time period and the fluctuation characteristics of the segmented interval curve, so as to change the compression rate of the multi-stage compressor according to the load. Therefore, see step S6.

[0065] S6. Adjust the air intake rate of the compressor corresponding to each hydrogen storage tank according to the current load state of each hydrogen storage tank to reduce the energy consumption of the multi-stage compression system.

[0066] In this embodiment, each compressor can be adjusted according to the evaluation value. Figure 6 , step S6 includes step S61 and step S62.

[0067] S61: When the current load state of the hydrogen storage tank is a no-load state, setting the air intake rate of the compressor corresponding to the hydrogen storage tank to a first preset rate, wherein the first preset rate is 0.

[0068] In this embodiment, it is considered that the time when the multi-stage compression system is loaded is short relative to the changes in the outside world; in other words, in this embodiment, it is considered that the rate of change of the outside temperature is relatively slow, and the degree of influence of the outside temperature is basically the same as the entire process of the air pressure change caused by the multi-stage compression system being in the load state. Therefore, the degree of influence of the outside air temperature in the time period of the load state is basically the same as the degree of influence of the outside temperature in the adjacent time period of the no-load state, and the degree of influence of the outside temperature in the no-load state time period adjacent to the load state time period can be used as a reference. When the evaluation value r corresponding to the no-load state time period j >0, it proves that the current external temperature is high, making the pressure value in the hydrogen storage tank larger than that under normal temperature. The judgment of the hydrogen quality in the current hydrogen storage tank is larger than the actual situation, and the judgment of the current load situation is smaller. When the evaluation value r of the no-load state time period is j<0, it proves that the current external temperature is low, so that the pressure value in the hydrogen storage tank is smaller than that under normal temperature, the judgment of the current hydrogen quality in the hydrogen storage tank is smaller than the actual situation, and the judgment of the current load situation is too large. Therefore, in order to further clarify how to calculate the compressor intake rate through the evaluation value, please refer to step S62 for details.

[0069] S62. When the current load state of the hydrogen storage tank is the load state, the compressor intake rate corresponding to the hydrogen storage tank is set to a second preset rate, and the second preset rate is calculated by the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the hydrogen storage tank, the first evaluation value and the second evaluation value are the evaluation values ​​corresponding to the first segmented interval curve and the second segmented interval curve respectively, the cutoff time of the first segmented interval curve is the current time, and the second segmented interval curve is adjacent to the first segmented interval curve.

[0070] Specifically, there is a hydrogen storage tank behind each compressor to store the hydrogen compressed by the compressor, and the load size borne by each compressor is different. Therefore, in this embodiment, in order to ensure the normal operation of the three-stage compressor, the hydrogen flow rate of each compressor should be adjusted according to the load size borne by the entire multi-stage compression system and the load size borne by the single-stage compressor. The larger the load of the current compressor, the faster the air intake rate of the current compressor should be. When the overall load of the three-stage compressor is larger, the air intake rate of all compressors should increase. And because the load of the multi-stage compression system as a whole becomes larger, the load borne by the compressor with a smaller level will be larger, so the air intake rate of the compressor with a smaller level should also be faster. Specifically, see step S621, step S622 and step S623.

[0071] S621, calculate the overall load evaluation value W corresponding to the first segmented interval curve according to the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the n-th level hydrogen storage tank j The nth-stage hydrogen storage tank is the hydrogen storage tank corresponding to the last-stage compressor in the multi-stage compression system, and n is a natural number greater than zero, that is, n is equal to 3 in this embodiment.

[0072] Among them, the overall load evaluation value W j The calculation formula is as follows:

[0073]

[0074] In the above formula, j∈[1,J], j is an integer, and J represents the total number of segmented interval curves; W j represents the overall load assessment value corresponding to the jth segment interval curve; R j Indicates the unnormalized evaluation value corresponding to the j-th segment interval curve; n irepresents the total number of data points in the jth segment interval curve; ρ i represents the pressure value corresponding to the i-th data point in the j-th segment interval curve; r j-1 is the normalized evaluation value corresponding to the j-1th segment interval curve; t j is the duration of the jth segment interval curve; The 0.01 in the formula is to prevent the denominator from being zero. The 0.001 in the formula is to prevent the denominator from being zero. It should be noted that, based on the result of the judgment in step S62, the final compressor is in a loaded state in the time period corresponding to the j-th segmented interval curve in step S62, and in contrast, the final compressor is in an unloaded state in the time period corresponding to the j-1-th segmented interval curve.

[0075] In the above calculation formula, It represents the sum of the pressure values ​​of all data points in the jth segment interval curve. It reflects the hydrogen content in the nth stage hydrogen storage tank. The larger the value, the greater the current load, and the faster the compression rate of the multi-stage compressor should be. j It is the duration that the j-th segment interval curve has been maintained. The larger the value is, the greater the hydrogen consumption in the n-th stage hydrogen storage tank is, and the faster the compression rate of the multi-stage compressor should be.

[0076] S622, calculate the m-th level load evaluation value W corresponding to the first segmented interval curve according to the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the m-th level hydrogen storage tank j,m , m is a natural number less than or equal to n, and is 1, 2 or 3 in this embodiment.

[0077] It should be noted that in this step, the m-th level load evaluation value W corresponding to the first segment interval curve is j,m The calculation method is the same as the overall load evaluation value W in step S621 j The calculation method is the same and will not be repeated in this step.

[0078] S623: Calculate the second preset rate v according to the mth level load evaluation value and the overall load evaluation value corresponding to the first segmented interval curve. m,j .

[0079] The second preset rate v m,j The calculation formula is as follows:

[0080]

[0081] Where j∈[1,J], j is an integer, J represents the total number of segmented interval curves; W jrepresents the overall load evaluation value corresponding to the j-th segment interval curve; W j-1 represents the overall load assessment value corresponding to the j-1th segment interval curve; W j,m W represents the mth level load evaluation value corresponding to the jth segment interval curve; j-1,m represents the mth level load assessment value corresponding to the j-1th segment interval curve. m represents the mth level compressor, m∈[1,3], m is a natural number; X norm () represents the normalization function. The value range is [0,1]; v m,j-1 represents the air intake rate of the mth compressor in the j-1th time period of the load state;

[0082] In the above calculation formula, W j -W j-1 Indicates the overall load difference between the time periods of the jth segment interval curve and the j-1th segment interval curve. W j,m -W j-1,m It represents the difference in the load of the mth compressor between the time periods of the jth segmented interval curve and the j-1th segmented interval curve. Indicates the multiple by which the compression rate of the mth compressor should be increased in the current time period. Through the above calculation formula, the intake rate of the compressor is adjusted by combining the load conditions of the multi-stage compression system as a whole and the compressors at each stage, which can better meet the working conditions of the multi-stage compression system.

[0083] In the embodiment, the air intake rate of the compressor is adjusted according to the load of the multi-stage compression system as a whole and the compressors at each stage. The compression rate is adjusted by changing the air intake rate of the compressors at each stage, so that the output of compressed hydrogen meets the system load without causing redundant output, thereby achieving the purpose of reducing energy consumption.

[0084] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A multi-stage compression system energy consumption management method based on artificial intelligence, characterized in that: The method comprises: Obtain pressure data of each hydrogen storage tank in real time; Performing curve conversion on the pressure data of each hydrogen storage tank to obtain a pressure curve corresponding to each hydrogen storage tank, wherein the ordinate of the pressure curve is the pressure value and the abscissa is the time; Performing segmentation processing according to the extreme value points of each of the pressure curves to obtain a plurality of segmented interval curves; Based on the calculation of the pressure value change in each segmented interval curve, an evaluation value corresponding to each segmented interval curve under the influence of temperature is obtained; Based on the evaluation value corresponding to each segmented interval curve, the current load state of each hydrogen storage tank is obtained; According to the current load state of each hydrogen storage tank, the intake rate of the compressor corresponding to the hydrogen storage tank is adjusted to reduce the energy consumption of the multi-stage compression system; Wherein, the current load state includes a load state or a no-load state; The process of adjusting the air intake rate of the compressor corresponding to each hydrogen storage tank according to the current load state of each hydrogen storage tank to reduce the energy consumption of the multi-stage compression system includes: When the current load state of the hydrogen storage tank is a no-load state, setting the air intake rate of the compressor corresponding to the hydrogen storage tank to a first preset rate; When the current load state of the hydrogen storage tank is the load state, the compressor intake rate corresponding to the hydrogen storage tank is set to a second preset rate, and the second preset rate is calculated by the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the hydrogen storage tank, the first evaluation value and the second evaluation value are the evaluation values ​​corresponding to the first segmented interval curve and the second segmented interval curve, respectively, the cutoff time of the first segmented interval curve is the current moment, and the second segmented interval curve is adjacent to the first segmented interval curve.

2. The method for managing energy consumption of a multi-stage compression system based on artificial intelligence according to claim 1 is characterized in that: The extreme value points of each pressure curve are processed in sections to obtain a plurality of section interval curves, including: Each pressure curve is smoothed by a preset Douglas Peucker algorithm to obtain a plurality of smooth pressure curves; Each of the smooth pressure curves is segmented one by one to obtain a plurality of segmented interval curves corresponding to each of the pressure curves, and a segmentation point between two adjacent segmented interval curves is an extreme point.

3. The method for managing energy consumption of a multi-stage compression system based on artificial intelligence according to claim 1, characterized in that: Based on the calculation of the air pressure change in each segmented interval curve, an evaluation value corresponding to each segmented interval curve is obtained, including: Based on the change of the pressure value in the segmented interval curve over time, the slope of the pressure curve corresponding to each time point is obtained; Extracting the maximum pressure value and the minimum pressure value from the segmented interval curve; The evaluation value corresponding to the segmented interval curve is calculated based on the maximum pressure value, the minimum pressure value corresponding to the segmented interval curve and the slope of the pressure curve in the segmented interval curve; The evaluation value corresponding to the segmented interval curve is normalized, and the evaluation value is updated to be the normalized result.

4. The method for managing energy consumption of a multi-stage compression system based on artificial intelligence according to claim 1, characterized in that: Based on the evaluation value corresponding to each segmented interval curve, the load state of each hydrogen storage tank is obtained, including: When the evaluation value corresponding to the segmented interval curve is greater than a preset load threshold, the hydrogen storage tank corresponding to the segmented interval curve is in a loaded state; otherwise, the hydrogen storage tank corresponding to the segmented interval curve is in a non-loaded state.

5. The method for managing energy consumption of a multi-stage compression system based on artificial intelligence according to claim 4 is characterized in that: The preset load threshold is -0.

5.

6. The method for managing energy consumption of a multi-stage compression system based on artificial intelligence according to claim 1, characterized in that: The calculation method of the second preset rate includes: The overall load assessment value corresponding to the first segmented interval curve is calculated according to the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the n-th stage hydrogen storage tank, wherein the n-th stage hydrogen storage tank is a hydrogen storage tank corresponding to the last stage compressor in the multi-stage compression system, and n is a natural number greater than zero; The m-th level load evaluation value corresponding to the first segmented interval curve is calculated according to the first segmented interval curve, the second segmented interval curve, the first evaluation value and the second evaluation value corresponding to the m-th level hydrogen storage tank, where m is a natural number less than or equal to n; The second preset rate is calculated based on the mth level load evaluation value and the overall load evaluation value corresponding to the first segmented interval curve.

7. The method for managing energy consumption of a multi-stage compression system based on artificial intelligence according to claim 1, characterized in that: The number of the hydrogen storage tanks is three.

8. The method for managing energy consumption of a multi-stage compression system based on artificial intelligence according to claim 1, characterized in that: The pressure data acquisition time interval of each hydrogen storage tank is 10 seconds.

Images