Nitrogen-making equipment energy-saving control method, electronic equipment and program product

Abstract

The invention provides a nitrogen generation equipment energy-saving control method, electronic equipment and a program product, and relates to the technical field of equipment control. The method comprises the following steps: acquiring estimated energy consumption, air flow, preset energy consumption corresponding to the air flow, a preset weight coefficient and an energy consumption difference between the estimated energy consumption and the preset energy consumption of the nitrogen making equipment at the current moment; when the energy consumption difference is greater than a preset difference value, according to the estimated energy consumption, the preset energy consumption, the energy consumption difference and a preset weight coefficient, through a preset feedback control strategy, determining an iterative adjustment parameter of the nitrogen generation equipment; according to the iterative adjustment parameters, adjusting the adsorption duration of the nitrogen making equipment so as to adjust the energy consumption required by the nitrogen making equipment for completing nitrogen purification; and repeating the steps until the nitrogen making equipment completes nitrogen purification. Therefore, the adsorption duration of the nitrogen-making equipment can be adjusted according to the energy consumption change of the nitrogen-making equipment under different air flows, so that the nitrogen-making equipment always performs nitrogen-making work with the minimum energy consumption in the nitrogen-making process, and energy waste is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and in particular, to an energy-saving control method, an electronic device and a program product for a nitrogen production device. Background Art

[0002] In existing nitrogen production equipment, the control of a conventional nitrogen generator is to input a fixed adsorption time by an external text or HIM (Human Machine Interface), and the PLC controller of the nitrogen generator switches the adsorption duration of the nitrogen generator according to this fixed time logic. In actual applications, when the air flow rate is small, if the air is still adsorbed and nitrogen is purified for a fixed duration, it will cause the energy consumption of the nitrogen generator to be greater than the energy consumption required for nitrogen purification at this air flow rate, ultimately resulting in energy waste. Summary of the Invention

[0003] In view of this, the purpose of the embodiments of the present application is to provide an energy-saving control method, an electronic device and a program product for a nitrogen production device, which can improve the problem that when the air flow rate is small in the traditional PLC control mode of a nitrogen generator, the energy consumption of the nitrogen generator is greater than the energy consumption required for nitrogen purification at this air flow rate, resulting in energy waste.

[0004] To achieve the above technical purpose, the technical solutions adopted in the present application are as follows:

[0005] In a first aspect, the embodiments of the present application provide an energy-saving control method for a nitrogen production device, and the method includes:

[0006] S1: Obtain the estimated energy consumption, air flow rate, preset energy consumption corresponding to the air flow rate, preset weight coefficient and energy consumption difference between the estimated energy consumption and the preset energy consumption of the nitrogen production device at the current moment;

[0007] S2: When the energy consumption difference is greater than a preset difference, determine the iterative adjustment parameter of the nitrogen production device through a preset feedback control strategy according to the estimated energy consumption, the preset energy consumption, the energy consumption difference and the preset weight coefficient;

[0008] S3: Adjust the adsorption duration of the nitrogen production device according to the iterative adjustment parameter to adjust the energy consumption required for the nitrogen production device to complete nitrogen purification;

[0009] S4: Repeat steps S1 to S3 until the nitrogen production device completes nitrogen purification.

[0010] Combined with the first aspect, in some optional embodiments, step S2 includes:

[0011] When the energy consumption difference is greater than the preset difference, determine the initial adjustment parameter according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient, where the preset weight coefficient includes a bias vector and preset weight values corresponding to the estimated energy consumption, the preset energy consumption, and the energy consumption difference respectively;

[0012] Adjust the adsorption duration according to the initial adjustment parameter to obtain the estimated energy consumption at the next moment of the current moment;

[0013] Take the energy consumption difference between the estimated energy consumption at the next moment and the preset energy consumption as the energy consumption difference at the next moment, and update the preset weight coefficient according to the energy consumption difference at the next moment to obtain the updated preset weight coefficient;

[0014] Determine the iterative adjustment parameter according to the estimated energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment, and the updated preset weight coefficient.

[0015] Combined with the first aspect, in some alternative embodiments, when the energy consumption difference is greater than the preset difference, determining the initial adjustment parameter according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient includes:

[0016] When the energy consumption difference is greater than the preset difference, determine the unit control parameter according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient, where the unit control parameter includes a proportional parameter, an integral parameter, and a differential parameter:

[0017] y = f(Wx + b)

[0018] In the formula, y represents the output vector composed of the unit control parameters, f(·) represents the activation function, W represents the weight matrix composed of the preset weight values corresponding to the estimated energy consumption, the preset energy consumption, and the energy consumption difference respectively, x represents the input vector composed of the estimated energy consumption, the preset energy consumption, and the energy consumption difference, and b represents the bias vector;

[0019] Determine the initial adjustment parameter according to the unit control parameter through the following formula:

[0020] u(j) = u(j - 1) + K p Δe j +K i e j +K d (Δe j -Δe j-1 )

[0021] Δe j =e j -e j-1 ,e j= r(j) - y(j)

[0022] Wherein, u(k) represents the initial adjustment parameter, j represents the sampling round, K p represents the proportional parameter, K i represents the integral parameter, K d represents the differential parameter, r(j) represents the predicted energy consumption, y(j) represents the preset energy consumption, e j represents the energy consumption difference.

[0023] Combined with the first aspect, in some alternative embodiments, updating the preset weight coefficient according to the energy consumption difference at the next moment to obtain an updated preset weight coefficient, including:

[0024]

[0025] Wherein, W new represents the updated weight matrix in the updated preset weight coefficient, b new represents the updated bias vector in the updated preset weight coefficient, η represents the learning rate for controlling the update step of the preset weight coefficient, E represents the loss function, represents the partial derivative of the loss function with respect to the weight matrix, represents the partial derivative of the loss function with respect to the bias vector, represents the partial derivative of the loss function with respect to the output vector.

[0026] Combined with the first aspect, in some alternative embodiments, determining the iterative adjustment parameter according to the predicted energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment and the updated preset weight coefficient, including:

[0027] Determining an updated unit control parameter according to the predicted energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment and the updated preset weight coefficient through the following formula:

[0028] y new = f(W new x new + b new )

[0029] Wherein, y new represents the updated unit control parameter, x new represents an input vector composed of the predicted energy consumption at the next moment, the preset energy consumption and the energy consumption difference at the next moment;

[0030] Determining the iterative adjustment parameter according to the updated unit control parameter through the following formula:

[0031] u(j + 1) = u(j) + Kpnew Δe j+1 +K inew e j+1 +K dnew (Δe j+1 -Δe j )

[0032] Δe j+1 =e j+1 -e j ,e j+1 =r(j + 1)-y(j)

[0033] In the formula, u(j + 1) represents the iterative adjustment parameter, K pnew represents the updated proportional parameter in the updated unit control parameter, K inew represents the updated integral parameter in the updated unit control parameter, K dnew represents the updated derivative parameter in the updated unit control parameter, e j+1 represents the energy consumption difference at the next moment, and r(j + 1) represents the predicted energy consumption at the next moment.

[0034] Combined with the first aspect, in some alternative embodiments, before determining the unit control parameter according to the predicted energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient when the energy consumption difference is greater than the preset difference, when the energy consumption difference is greater than the preset difference, determining the initial adjustment parameter according to the predicted energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient further includes:

[0035] Determining the value of the preset weight coefficient based on a preset weight optimization strategy.

[0036] Combined with the first aspect, in some alternative embodiments, determining the value of the preset weight coefficient based on a preset weight optimization strategy includes:

[0037] A1. Initialize the optimization parameters, where the optimization parameters include the total population, the maximum number of iterations, the loop constraint, and the initial position;

[0038] A2. Determine the first fitness corresponding to the initial position through a preset fitness function;

[0039] A3. Update the initial position within the range of the total population to obtain the updated position, and determine the second fitness corresponding to the updated position through the preset fitness function;

[0040] A4. When the second fitness is greater than the first fitness, use the updated position as the optimal position;

[0041] A5. Determine the selection probability of the optimal position by using a preset probability calculation formula;

[0042] A6. If the selection probability is greater than a preset random number, repeat steps A3 to A4 to update the optimal position and obtain the updated optimal position;

[0043] A7. Based on the loop constraint and a preset local optimal solution screening strategy, screen the updated optimal position to obtain the current optimal solution;

[0044] A8. Repeat steps A3 to A7 until the number of iterations is greater than or equal to the maximum number of iterations, and take the current optimal solution obtained in the last time as the global optimal solution to obtain the value of the preset weight coefficient.

[0045] In combination with the first aspect, in some alternative embodiments, the preset fitness function is as follows:

[0046]

[0047] In the formula, fit represents fitness, e(k) represents error, u(k) represents control quantity, and ρ ∈ [0, 1].

[0048] In a second aspect, an embodiment of the present application further provides an electronic device, which includes a processor and a memory coupled to each other. The memory stores a computer program. When the computer program is executed by the processor, the electronic device executes the above method.

[0049] In a third aspect, an embodiment of the present application further provides a computer program product, including a computer program, and the computer program realizes the above method when executed by a processor.

[0050] The invention adopting the above technical solution has the following advantages:

[0051] In the technical solution provided by the present application, first, the estimated energy consumption, air flow rate, preset energy consumption corresponding to the air flow rate, preset weight coefficient, and the energy consumption difference between the estimated energy consumption and the preset energy consumption of the nitrogen production device at the current moment are obtained. When the energy consumption difference is greater than a preset difference, according to the estimated energy consumption, preset energy consumption, energy consumption difference, and preset weight coefficient, through a preset feedback control strategy, the iterative adjustment parameter of the nitrogen production device is determined. Then, according to the iterative adjustment parameter, the adsorption duration of the nitrogen production device is adjusted to adjust the energy consumption required for the nitrogen production device to complete nitrogen purification. Finally, the above steps are repeated until the nitrogen production device completes nitrogen purification. In this way, the adsorption duration of the nitrogen production device can be flexibly adjusted according to the energy consumption change of the nitrogen production device under different air flow rates, so that the nitrogen production device always works with the minimum energy consumption sufficient to complete the nitrogen production operation during the nitrogen production process, reducing energy waste. Brief Description of the Drawings

[0052] The present application can be further illustrated by non-limiting embodiments given in the drawings. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0053] Figure 1 It is a structural block diagram of an electronic device provided by an embodiment of the present application.

[0054] Figure 2 It is a schematic flowchart of an energy-saving control method for a nitrogen generation device provided by an embodiment of the present application.

[0055] Icons: 100 - Electronic device; 101 - Processor; 102 - Memory. Detailed Embodiments

[0056] The present application will be described in detail below in combination with the drawings and specific embodiments. It should be noted that in the drawings or the description of the specification, similar or identical parts are all denoted by the same reference numerals, and the implementation manners not shown or described in the drawings are the forms known to those of ordinary skill in the art. In the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0057] Please refer to Figure 1 , an electronic device 100 provided by an embodiment of the present application may include a processor 101 and a memory 102. A computer program is stored in the memory 102. When the computer program is executed by the processor 101, the electronic device 100 can execute the corresponding steps in the following energy-saving control method for a nitrogen generation device.

[0058] In this embodiment, the electronic device 100 can be a personal computer, a laptop computer, a cloud server, a device controller integrated in a nitrogen generation device, etc. It is used to obtain the estimated energy consumption, air flow rate, preset energy consumption corresponding to the air flow rate, preset weight coefficient, and the energy consumption difference between the estimated energy consumption and the preset energy consumption of the nitrogen generation device at the current moment. When the energy consumption difference is greater than the preset difference, according to the estimated energy consumption, preset energy consumption, energy consumption difference, and preset weight coefficient, through a preset feedback control strategy, the iterative adjustment parameter of the nitrogen generation device is determined. Then, according to the iterative adjustment parameter, the adsorption duration of the nitrogen generation device is adjusted to adjust the energy consumption required for the nitrogen generation device to complete nitrogen purification. Finally, the above steps are repeated until the nitrogen generation device completes nitrogen purification.

[0059] In this embodiment, the processor 101 can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 101 can be a general-purpose processor. For example, the processor 101 can be a Central Processing Unit (CPU), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0060] The memory 102 can be, but is not limited to, a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, etc. In this embodiment, the memory 102 can be used to store the estimated energy consumption, air flow rate, preset energy consumption, preset weight coefficient, energy consumption difference, preset interpolation, feedback control strategy, iterative adjustment parameter, adsorption duration, etc. Of course, the memory 102 can also be used to store a program, and after receiving an execution instruction, the processor 101 executes the program.

[0061] It can be understood that Figure 1 the structure of the electronic device 100 shown in Figure 1 is only a schematic structural diagram, and the electronic device 100 may further include more Figure 1 components than those shown.

[0062] Please refer to Figure 2 , the present application also provides a nitrogen production equipment energy-saving control method, which can be applied to the above-mentioned electronic device 100 and executed or implemented by the electronic device 100 for each step of the method. Among them, the nitrogen production equipment energy-saving control method may include the following steps:

[0063] Step S1, obtaining the estimated energy consumption, air flow rate, preset energy consumption corresponding to the air flow rate, preset weight coefficient, and energy consumption difference between the estimated energy consumption and the preset energy consumption of the nitrogen production equipment at the current moment;

[0064] Step S2, when the energy consumption difference is greater than a preset difference, determining an iterative adjustment parameter of the nitrogen production equipment according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient through a preset feedback control strategy;

[0065] Step S3: Adjust the adsorption duration of the nitrogen generation device according to the iterative adjustment parameter, so as to adjust the energy consumption required for the nitrogen generation device to complete nitrogen purification;

[0066] Step S4: Repeat Steps S1 to S3 until the nitrogen generation device completes nitrogen purification.

[0067] In the above embodiment, first, the estimated energy consumption, air flow rate, preset energy consumption corresponding to the air flow rate, preset weight coefficient, and the energy consumption difference between the estimated energy consumption and the preset energy consumption of the nitrogen generation device at the current moment are obtained. When the energy consumption difference is greater than the preset difference, the iterative adjustment parameter of the nitrogen generation device is determined through a preset feedback control strategy according to the estimated energy consumption, preset energy consumption, energy consumption difference, and preset weight coefficient. Then, according to the iterative adjustment parameter, the adsorption duration of the nitrogen generation device is adjusted to adjust the energy consumption required for the nitrogen generation device to complete nitrogen purification. Finally, the above steps are repeated until the nitrogen generation device completes nitrogen purification. In this way, the adsorption duration of the nitrogen generation device can be flexibly adjusted according to the energy consumption change of the nitrogen generation device under different air flow rates, so that the nitrogen generation device always works with the minimum energy consumption sufficient to complete the nitrogen generation operation during the nitrogen generation process, reducing energy waste.

[0068] The following will elaborate on each step of the energy-saving control method for the nitrogen generation device in detail as follows:

[0069] In Step S1, the acquisition of the estimated energy consumption, air flow rate, preset energy consumption, preset weight coefficient, and energy consumption difference can be achieved by monitoring the real-time air flow rate in the nitrogen generation device through a flow meter integrated in the nitrogen generation device, and then querying the minimum energy consumption required for the nitrogen generation device to complete nitrogen generation at this air flow rate from a pre-constructed database as the preset energy consumption. By obtaining the adsorption duration of the nitrogen generation device at the current moment and querying the energy consumption required for the nitrogen generation device to complete nitrogen generation at this adsorption duration from the database as the estimated energy consumption.

[0070] In this embodiment, the minimum energy consumption (i.e., the preset energy consumption) and the estimated energy consumption can be calibrated by users in long-term nitrogen generation experiments. The relationship table between the calibrated adsorption duration and nitrogen generation energy consumption is used as the estimated energy consumption table, and the relationship table between the calibrated air flow rate and the minimum energy consumption is used as the preset energy consumption table. Then, the above database is constructed according to the estimated energy consumption table and the preset energy consumption table.

[0071] In this embodiment, the acquisition of the estimated energy consumption, air flow rate, preset energy consumption, preset weight coefficient, and energy consumption difference can be real-time data obtained during the technical application stage by collecting relevant data through sensors integrated in the nitrogen generation equipment, and performing simple look-up table operations and calculations, and then sending the data to the processor 101 of the electronic device 100 for real-time data processing during the energy-saving control process; or it can be that the user inputs relevant data in advance during the development and testing stage, stores the data in the memory 102 of the above-mentioned electronic device 100, and calls the data based on the instructions issued by the user through the processor 101 during the subsequent energy-saving control process. The specific acquisition method of each data is not limited here.

[0072] In step S2, when the energy consumption difference is greater than the preset difference, according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient, the iterative adjustment parameters of the nitrogen generation equipment are determined through a preset feedback control strategy, which may include:

[0073] When the energy consumption difference is greater than the preset difference, according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient, the initial adjustment parameters are determined. The preset weight coefficient includes a bias vector and preset weights corresponding to the estimated energy consumption, the preset energy consumption, and the energy consumption difference respectively;

[0074] Adjust the adsorption duration according to the initial adjustment parameters to obtain the estimated energy consumption at the next moment of the current moment;

[0075] Take the energy consumption difference between the estimated energy consumption at the next moment and the preset energy consumption as the energy consumption difference at the next moment, and update the preset weight coefficient according to the energy consumption difference at the next moment to obtain the updated preset weight coefficient;

[0076] According to the estimated energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment, and the updated preset weight coefficient, determine the iterative adjustment parameters.

[0077] In this embodiment, when the energy consumption difference is greater than the preset difference, according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient, the initial adjustment parameters are determined, which may include:

[0078] When the energy consumption difference is greater than the preset difference, according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient, the unit control parameters are determined. The unit control parameters include a proportional parameter, an integral parameter, and a differential parameter:

[0079] y = f(Wx + b)

[0080] Wherein, y represents the output vector composed of unit control parameters, f(·) represents the activation function, W represents the weight matrix composed of preset weight values corresponding to the estimated energy consumption, preset energy consumption, and energy consumption difference respectively, x represents the input vector composed of the estimated energy consumption, preset energy consumption, and energy consumption difference, and b represents the bias vector;

[0081] According to the unit control parameters, determine the initial adjustment parameter through the following formula:

[0082] u(j) = u(j - 1) + K p Δe j +K i e j +K d (Δe j -Δe j-1 )

[0083] Δe j =e j -e j-1 ,e j =r(j)-y(j)

[0084] Wherein, u(k) represents the initial adjustment parameter, j represents the sampling round, K p represents the proportional parameter, K i represents the integral parameter, K d represents the differential parameter, r(j) represents the estimated energy consumption, y(j) represents the preset energy consumption, e j represents the energy consumption difference.

[0085] In this embodiment, take the above initial adjustment parameter as the control quantity of the nitrogen production equipment (that is, the adjustment magnitude of the adsorption duration of the nitrogen production equipment), and after adjusting the adsorption duration based on this control quantity, collect the energy consumption required to complete nitrogen production under the adjusted adsorption duration at the next moment as the estimated energy consumption at the next moment. Then take the energy consumption difference between the estimated energy consumption at the next moment and the preset energy consumption as the energy consumption difference at the next moment, and update the preset weight coefficient according to the energy consumption difference at the next moment to achieve the feedback control of the nitrogen production equipment.

[0086] Specifically, in this embodiment, updating the preset weight coefficient according to the energy consumption difference at the next moment to obtain the updated preset weight coefficient may include:

[0087]

[0088]

[0089] Wherein, W new represents the updated weight matrix in the updated preset weight coefficient, b newdenotes the updated bias vector in the updated preset weight coefficient, η denotes the learning rate for controlling the update step size of the preset weight coefficient, and E denotes the loss function. denotes the partial derivative of the loss function with respect to the weight matrix. denotes the partial derivative of the loss function with respect to the bias vector. denotes the partial derivative of the loss function with respect to the output vector.

[0090] In this embodiment, by taking the partial derivatives of the loss function with respect to the weight matrix, bias vector, and output vector, the preset weight coefficient is iteratively updated, enabling the subsequent determination of the iterative adjustment parameter to flexibly adapt to the air flow changes in the nitrogen generation equipment and achieve stable control of the energy consumption of the nitrogen generation equipment.

[0091] In this embodiment, according to the estimated energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment, and the updated preset weight coefficient, determining the iterative adjustment parameter may include:

[0092] According to the estimated energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment, and the updated preset weight coefficient, the updated unit control parameter is determined by the following formula:

[0093] y new =f(W new x new +b new )

[0094] In the formula, y new denotes the updated unit control parameter, and x new denotes the input vector composed of the estimated energy consumption at the next moment, the preset energy consumption, and the energy consumption difference at the next moment;

[0095] According to the updated unit control parameter, the iterative adjustment parameter is determined by the following formula:

[0096] u(j + 1) = u(j) + K pnew Δe j+1 + K inew e j+1 + K dnew (Δe j+1 - Δe j )

[0097] Δe j+1 =e j+1 - e j , e j+1 =r(j + 1) - y(j)

[0098] In the formula, u(j + 1) denotes the iterative adjustment parameter, and K pnewDenote the updated proportional parameter in the updated unit control parameter as K inew Denote the updated integral parameter in the updated unit control parameter as K dnew Denote the updated derivative parameter in the updated unit control parameter as e j+1 Denote the energy consumption difference at the next moment, where r(j + 1) represents the estimated energy consumption at the next moment.

[0099] In this embodiment, after adjusting the adsorption duration of the nitrogen production equipment in the first round (i.e., the current moment) with the above initial adjustment parameters, the input vector for the next round (i.e., the next moment) is collected again, and the preset weight coefficient is updated backward according to this input vector. Then, based on the input vector at the next moment and the updated preset weight coefficient, the iterative adjustment parameters for the second-round adjustment of the nitrogen production equipment are calculated to perform feedback adjustment on the adsorption duration of the nitrogen production equipment. In this way, the adsorption duration of the nitrogen production equipment can flexibly adapt to the change of the air flow rate in the nitrogen production equipment (each parameter in the input vector is directly related to the air flow rate) during the adjustment process, enhancing the universal ability of the adsorption duration adjustment of the nitrogen production equipment.

[0100] In step S3, after determining the iterative adjustment parameters of the nitrogen production equipment, take this adjustment parameter as the adjustment amount of the adsorption duration of the nitrogen production equipment to adjust the adsorption duration, so that when the nitrogen production equipment operates under different air flow rates, nitrogen is prepared with the lowest energy consumption in the formula, achieving the purpose of energy saving.

[0101] In step S4, by repeating steps S1 to S3, flexible adjustment can be made according to the change of the air flow rate during the operation of the nitrogen production equipment, enhancing the adaptability of the nitrogen production equipment to different air flow rates and ensuring that the energy consumption formula is controllable.

[0102] As an alternative implementation, before determining the unit control parameter according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient when the energy consumption difference is greater than the preset difference, when the energy consumption difference is greater than the preset difference, determining the initial adjustment parameter according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient further includes:

[0103] Determine the value of the preset weight coefficient based on the preset weight optimization strategy.

[0104] In this embodiment, determining the value of the preset weight coefficient based on the preset weight optimization strategy may include:

[0105] A1. Initialize the optimization parameters, where the optimization parameters include the total population, the maximum number of iterations, the cycle constraint, and the initial position;

[0106] A2. Determine the first fitness corresponding to the initial position by means of a preset fitness function;

[0107] A3. Update the initial position within the range of the total population to obtain an updated position, and determine the second fitness corresponding to the updated position by means of the preset fitness function;

[0108] A4. When the second fitness is greater than the first fitness, take the updated position as the optimal position;

[0109] A5. Determine the selection probability of the optimal position by means of a preset probability calculation formula;

[0110] A6. If the selection probability is greater than a preset random number, repeat steps A3 to A4 to update the optimal position to obtain an updated optimal position;

[0111] A7. According to the loop constraint, based on a preset local optimal solution screening strategy, screen the updated optimal position to obtain the current optimal solution;

[0112] A8. Repeat steps A3 to A7 until the number of iterations is greater than or equal to the maximum number of iterations, and take the current optimal solution obtained in the last iteration as the global optimal solution to obtain the value of the preset weight coefficient.

[0113] It can be understood that in this embodiment, although the preset weight coefficient can be iteratively updated and corrected in step S2 above, on the one hand, the correction process will occupy the computing power of the processor 101, and on the other hand, the correction of the preset weight coefficient is carried out step by step according to the acquisition frequency of the input vector. Inevitably, the operation efficiency of the nitrogen production equipment will be affected during this process, resulting in waste of energy. Therefore, in this embodiment, by pre-calibrating the initial value of the preset weight coefficient, the correction period of the preset weight coefficient is shortened during the calculation process of the iterative adjustment parameter, the calculation accuracy of the iterative adjustment parameter is improved, and energy waste is reduced.

[0114] Specifically, first initialize each optimization parameter, and randomly generate an initial solution within the population range, that is, the initial position x ij (i = 1, 2, N), where N represents the total population. Then determine the first fitness of this initial position by means of a preset fitness function. Next, update the initial position through the following formula to obtain the updated position:

[0115]

[0116] In the formula, v ij represents the updated position, k ∈ {1, 2, N}, j ∈ {1, 2, D}, and k ≠ i, is a random number between [-1, 1], and D represents the dimension.

[0117] Then, based on the preset fitness function, determine the second fitness of the updated position.

[0118] Then, perform a greedy selection on the initial position and the updated position based on the following rule: when the second fitness is greater than the first fitness, determine the updated position as the optimal position (that is, retain the position with the larger fitness as the optimal position):

[0119]

[0120] In the formula, v i represents the optimal position.

[0121] Then, use the preset probability calculation formula to determine the probability that the optimal position will still be selected as the optimal position in the next iteration:

[0122]

[0123] After determining the selection probability, randomly generate a number between [-1, 1] as the preset random number. If the selection probability is greater than the preset random number, repeat the above steps of position update, fitness calculation, and optimal position determination to update the previous optimal position and obtain the updated optimal position.

[0124] It can be understood that the loop constraint is a constraint condition on the number of loops. When the updated optimal position always maintains an original solution during the iteration to the loop constraint (that is, when updating the position each time, the fitness of the new position is not better than that of the original position, and the optimal position remains unchanged), it is considered that the updated optimal position falls into a local optimal solution. Then, randomly generate a new position as a replacement to obtain the current optimal solution (if there is no local optimal solution, keep the original updated optimal position as the current optimal solution):

[0125] z ij = x minj + rand(0, 1)(x maxj - x minj )

[0126] In the formula, z ij represents the current optimal solution, j ∈ {1, 2, D}, x maxj and x minj , rand(0, 1) is a random number within [0, 1], representing the upper and lower bounds of all solutions in the j-th dimension respectively.

[0127] Finally, continuously loop the above steps until the number of iterations is greater than or equal to the maximum number of iterations, and then use the current optimal solution obtained in the last iteration as the global optimal solution, that is, the initial value of the preset weight coefficient.

[0128] In this embodiment, the preset fitness function is as follows:

[0129]

[0130] In the formula, fit represents the fitness, e(k) represents the error, u(k) represents the control quantity, and ρ ∈ [0, 1].

[0131] In this way, by pre-calibrating the initial value of the preset weight coefficient, the cycle of the subsequent preset weight coefficient in the iterative update process is shortened, thereby achieving the purpose of reducing energy waste.

[0132] It should be noted that those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-mentioned electronic device 100 can refer to the corresponding processes of each step in the foregoing method, and will not be elaborated here too much.

[0133] The embodiment of the present application further provides a computer program product, including a computer program, and the computer program realizes the above-mentioned energy-saving control method for nitrogen production equipment when executed by the processor 101.

[0134] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present application.

[0135] To sum up, the embodiment of the present application provides an energy-saving control method, an electronic device and a program product for nitrogen production equipment. In this technical solution, first, the estimated energy consumption, air flow rate, preset energy consumption corresponding to the air flow rate, preset weight coefficient, and energy consumption difference between the estimated energy consumption and the preset energy consumption of the nitrogen production equipment at the current moment are obtained. When the energy consumption difference is greater than the preset difference, according to the estimated energy consumption, preset energy consumption, energy consumption difference, and preset weight coefficient, through the preset feedback control strategy, the iterative adjustment parameter of the nitrogen production equipment is determined. Then, according to the iterative adjustment parameter, the adsorption duration of the nitrogen production equipment is adjusted to adjust the energy consumption required for the nitrogen production equipment to complete nitrogen purification. Finally, the above steps are repeated until the nitrogen production equipment completes nitrogen purification. In this way, according to the energy consumption change of the nitrogen production equipment under different air flow rates, the adsorption duration of the nitrogen production equipment can be flexibly adjusted, so that the nitrogen production equipment always works with the minimum energy consumption sufficient to complete the nitrogen production operation during the nitrogen production process, reducing energy waste.

[0136] In the embodiments provided in this application, it should be understood that the disclosed method can also be implemented in other ways. The method embodiments described above are only illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the methods and computer program products according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, the various functional modules in the embodiments of this application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0137] The above is only the embodiments of this application and is not intended to limit the protection scope of this application. For those skilled in the art, this application can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this application shall be included in the protection scope of this application.

Claims

1. An energy-saving control method for nitrogen generation equipment, characterized in that, The method includes: S1: Obtain the estimated energy consumption, air flow rate, preset energy consumption corresponding to the air flow rate, preset weight coefficient, and the energy consumption difference between the estimated energy consumption and the preset energy consumption of the nitrogen generation device at the current moment; S2: When the energy consumption difference is greater than a preset difference, determine the iterative adjustment parameter of the nitrogen generation device according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient through a preset feedback control strategy; S3: Adjust the adsorption duration of the nitrogen generation device according to the iterative adjustment parameter to adjust the energy consumption required for the nitrogen generation device to complete nitrogen purification; S4: Repeat steps S1 to S3 until the nitrogen generation device completes nitrogen purification.

2. The method according to claim 1, wherein Step S2 includes: When the energy consumption difference is greater than the preset difference, determine the initial adjustment parameter according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient. The preset weight coefficient includes a bias vector and preset weight values corresponding to the estimated energy consumption, the preset energy consumption, and the energy consumption difference respectively; Adjust the adsorption duration according to the initial adjustment parameter to obtain the estimated energy consumption at the next moment of the current moment; Take the energy consumption difference between the estimated energy consumption at the next moment and the preset energy consumption as the energy consumption difference at the next moment, and update the preset weight coefficient according to the energy consumption difference at the next moment to obtain the updated preset weight coefficient; Determine the iterative adjustment parameter according to the estimated energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment, and the updated preset weight coefficient.

3. The method according to claim 2, wherein When the energy consumption difference is greater than the preset difference, determining the initial adjustment parameter according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient includes: When the energy consumption difference is greater than the preset difference, determine the unit control parameter according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient. The unit control parameter includes a proportional parameter, an integral parameter, and a differential parameter: y = f(Wx + b) In the formula, y represents the output vector composed of unit control parameters, f(·) represents the activation function, W represents the weight matrix composed of preset weight values corresponding to the estimated energy consumption, the preset energy consumption, and the energy consumption difference respectively, x represents the input vector composed of the estimated energy consumption, the preset energy consumption, and the energy consumption difference, and b represents the bias vector; Determine the initial adjustment parameter according to the unit control parameter through the following formula: u(j) = u(j - 1)+K p Δe j +K i e j +K d (Δe j -Δe j-1 ) Δe j = e j - e j-1 , e j = r(j) - y(j) Where, u(k) represents the initial adjustment parameter, j represents the sampling round, K p represents the proportional parameter, K i represents the integral parameter, K d represents the differential parameter, r(j) represents the estimated energy consumption, y(j) represents the preset energy consumption, e j represents the energy consumption difference.

4. The method according to claim 3, wherein Updating the preset weight coefficient according to the energy consumption difference at the next moment to obtain the updated preset weight coefficient includes: Where, W new represents the updated weight matrix in the updated preset weight coefficient, b new represents the updated bias vector in the updated preset weight coefficient, η represents the learning rate for controlling the update step size of the preset weight coefficient, E represents the loss function, represents the partial derivative of the loss function with respect to the weight matrix, represents the partial derivative of the loss function with respect to the bias vector, represents the partial derivative of the loss function with respect to the output vector.

5. The method according to claim 4, characterized in that, Determining the iterative adjustment parameter according to the estimated energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment, and the updated preset weight coefficient includes: Determine the updated unit control parameter through the following formula according to the estimated energy consumption at the next moment, the preset energy consumption, the energy consumption difference at the next moment, and the updated preset weight coefficient: y new = f(W new x new + b new ) where y new represents the updated unit control parameter, and x new represents the input vector composed of the estimated energy consumption at the next moment, the preset energy consumption, and the energy consumption difference at the next moment; Determine the iterative adjustment parameter through the following formula according to the updated unit control parameter: u(j + 1)=u(j)+K pnew Δe j+1 +K inew e j+1 +K dnew (Δe j+1 -Δe j ) Δe j+1 = e j+1 - e j , e j+1 = r(j + 1)-y(j) Wherein, u(j + 1) represents the iterative adjustment parameter, K pnew represents the updated proportional parameter in the updated unit control parameter, K inew represents the updated integral parameter in the updated unit control parameter, K dnew represents the updated differential parameter in the updated unit control parameter, e j+1 represents the energy consumption difference at the next moment, and r(j + 1) represents the estimated energy consumption at the next moment.

6. The method according to claim 3, wherein Before determining the unit control parameters according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient when the energy consumption difference is greater than the preset difference, when the energy consumption difference is greater than the preset difference, determining the initial adjustment parameters according to the estimated energy consumption, the preset energy consumption, the energy consumption difference, and the preset weight coefficient further includes: Determining the value of the preset weight coefficient based on a preset weight optimization strategy.

7. The method according to claim 6, wherein Determining the value of the preset weight coefficient based on a preset weight optimization strategy includes: A1. Initializing the optimization parameters, where the optimization parameters include the total population, the maximum number of iterations, the loop constraint, and the initial position; A2. Determining the first fitness corresponding to the initial position through a preset fitness function; A3. Updating the initial position within the range of the total population to obtain the updated position, and determining the second fitness corresponding to the updated position through the preset fitness function; A4. When the second fitness is greater than the first fitness, taking the updated position as the optimal position; A5. Using a preset probability calculation formula to determine the selection probability of the optimal position; A6. If the selection probability is greater than a preset random number, repeating steps A3 to A4 to update the optimal position to obtain the updated optimal position; A7. Screening the updated optimal position based on a preset local optimal solution screening strategy according to the loop constraint to obtain the current optimal solution; A8. Repeating steps A3 to A7 until the number of iterations is greater than or equal to the maximum number of iterations, and taking the current optimal solution obtained last time as the global optimal solution to obtain the value of the preset weight coefficient.

8. The method according to claim 7, characterized in that, The preset fitness function is as follows: In the formula, fit represents fitness, e(k) represents error, u(k) represents the control amount, and ρ ∈ [0, 1].[[]]END]] 9. An electronic device, characterized in that, The electronic device includes a processor and a memory coupled to each other. The memory stores a computer program. When the computer program is executed by the processor, the electronic device executes the method according to any one of claims 1-8.

10. A computer program product, characterized in that, Including a computer program that implements the method according to any one of claims 1-8 when executed by a processor.

Images