Clean room air compression system energy consumption system construction method and device

Abstract

The invention provides a construction method and device for an energy consumption system of an air compression system of a clean room. The method relates to acquisition of data such as pressure fluctuation, positive pressure deviation, sound energy loss of a dust removal fan and switching frequency of cold and hot coils of an air conditioning box. Calculating the dynamic energy consumption of the pipe network through an LSTM time sequence prediction model, and determining an air volume balance adjustment coefficient; generating a coil function conversion critical temperature value based on the cold and hot coil switching frequency; and determining a silencing gradient parameter according to the sound energy loss value. The fresh air volume is controlled through the adjusting coefficient, and real-time positive pressure compensation data is generated; according to the critical temperature value, a cold and hot coil pipe switching instruction set is generated; and sound attenuation parameters are deployed, and acoustic parameters of the sound insulation wall plate are constructed. And comprehensively detecting the data and the parameters to generate an energy efficiency improvement index. According to the method, multiple parameters of the air compression system are comprehensively optimized, the problems of high energy consumption, unstable positive pressure, loud noise and the like are effectively solved, and the energy efficiency and the overall performance of the clean room system are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of air compressor energy consumption, and in particular to a method and device for constructing an energy consumption system for a clean room air compressor system. Background Art

[0002] In cleanroom systems, the air compression system accounts for a considerable proportion of energy consumption. Traditional air compression systems lack intelligent energy management, resulting in serious energy waste. At the same time, positive pressure control in cleanrooms is crucial for maintaining the cleanliness of the indoor environment, but traditional positive pressure control methods often rely on manual experience and are difficult to achieve precise control. In addition, the noise problem of dust removal fans is also a difficulty in cleanroom systems. High noise not only affects the comfort of workers, but may also have an adverse effect on the stable operation of equipment. In addition, the switching of hot and cold coils in outdoor air conditioning boxes is also a significant factor affecting energy consumption and stability. Traditional switching methods lack intelligence, resulting in high energy consumption and insufficient stability. Summary of the Invention

[0003] The purpose of this application is to overcome the above-mentioned defects in the prior art and provide a method and device for constructing an energy consumption system of a clean room air compression system.

[0004] The present application provides a method for constructing an energy consumption system for a clean room air compression system, comprising:

[0005] Obtain the pressure fluctuation data of the clean room air compression system, the clean room positive pressure deviation sequence, the dust removal fan sound energy loss value and the switching frequency of the hot and cold coils of the outdoor air conditioning box;

[0006] Calculate the pipeline network dynamic energy consumption prediction data using the LSTM time series prediction model based on the pressure fluctuation data;

[0007] Determining an air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence;

[0008] Based on the switching frequency of the hot and cold coils of the outdoor air conditioning box, a critical temperature value for coil function conversion is generated through a proportional two-way valve;

[0009] Determining the muffler gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan;

[0010] The MIAU fresh air volume is controlled by the air volume balance adjustment coefficient to generate real-time positive pressure compensation data;

[0011] Generating a hot and cold coil switching instruction set according to the coil function conversion critical temperature value;

[0012] Deploying the noise reduction gradient parameters to construct acoustic parameters of the sound insulation wall panel assembly;

[0013] A clean room control system is generated according to the real-time positive pressure compensation data, the hot and cold coil switching instruction set, and the acoustic parameters of the sound insulation wall panel assembly.

[0014] Optionally, the LSTM time series prediction model includes: adopting a sliding time window mechanism;

[0015] The steps of the sliding time window mechanism include: dividing the pressure fluctuation data into time windows according to a 24-hour period, constructing a pipeline network energy consumption time series training set with a step size of 15 minutes, and outputting dynamic energy consumption forecast data for the next 2 hours.

[0016] Optionally, determining the air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence includes:

[0017] The NSGA-II multi-objective processing algorithm is used to simultaneously optimize the three objective functions of the air compressor unit energy consumption index, the clean room positive pressure stability index, and the equipment life attenuation index to obtain the air volume balance adjustment coefficient.

[0018] Optionally, when the proportional two-way valve generates the coil function conversion critical temperature value, it includes:

[0019] When the outside air temperature is detected to be ≤5℃, the PID control algorithm is used to adjust the opening of the two-way valve to 30-45%, so that the water flow rate of the cooling coil is not less than 1.2m / s.

[0020] Optionally, based on the sound energy loss value of the dust removal fan, the muffler gradient parameters of the double volute resonance cavity are determined, including: setting a 30-100 kg / m³ gradient density glass fiber layer on the inner side of the dust removal fan volute, and integrating a Helmholtz resonator array, the resonance frequency covering the 500-4000 Hz noise frequency band.

[0021] The present application also provides a clean room air compression system energy consumption system construction device, comprising:

[0022] Acquisition module, which obtains the pressure fluctuation data of the clean room air compression system, the positive pressure deviation sequence of the clean room, the sound energy loss value of the dust removal fan, and the switching frequency of the hot and cold coils of the external air conditioning box;

[0023] The pipeline network module calculates the pipeline network dynamic energy consumption prediction data based on the pressure fluctuation data through the LSTM time series prediction model;

[0024] An air volume module determines an air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence;

[0025] A conversion module, based on the switching frequency of the hot and cold coils of the outdoor air conditioning box, generates a coil function conversion critical temperature value through a proportional two-way valve;

[0026] A silencer module, which determines a silencer gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan;

[0027] A compensation module controls the MIAU fresh air volume through the air volume balance adjustment coefficient and generates real-time positive pressure compensation data;

[0028] An instruction module, converting a critical temperature value according to the coil function, and generating a hot and cold coil switching instruction set;

[0029] an acoustic module, deploying the noise reduction gradient parameters to construct acoustic parameters of the sound insulation wall panel assembly;

[0030] The indicator module generates a clean room control system according to the real-time positive pressure compensation data, the hot and cold coil switching instruction set and the acoustic parameters of the sound insulation wall panel assembly.

[0031] Optionally, the LSTM time series prediction model includes: adopting a sliding time window mechanism;

[0032] The steps of the sliding time window mechanism include: dividing the pressure fluctuation data into time windows according to a 24-hour period, constructing a pipeline network energy consumption time series training set with a step size of 15 minutes, and outputting dynamic energy consumption forecast data for the next 2 hours.

[0033] Optionally, the air volume module determines the air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence, including:

[0034] The NSGA-II multi-objective processing algorithm is used to simultaneously optimize the three objective functions of the air compressor unit energy consumption index, the clean room positive pressure stability index, and the equipment life attenuation index to obtain the air volume balance adjustment coefficient.

[0035] Optionally, when the proportional two-way valve in the conversion module generates a coil function conversion critical temperature value, the conversion module includes:

[0036] When the outside air temperature is detected to be ≤5℃, the PID control algorithm is used to adjust the opening of the two-way valve to 30-45%, so that the water flow rate of the cooling coil is not less than 1.2m / s.

[0037] Optionally, the acoustic module determines the muffler gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan, including:

[0038] A 30-100kg / m³ gradient density glass fiber layer is set on the inner side of the dust removal fan volute, and a Helmholtz resonator array is integrated, with the resonance frequency covering the 500-4000Hz noise frequency band.

[0039] The beneficial effects of this application are:

[0040] Invention point:

[0041] 1. Design an LSTM neural network with a composite loss function for dynamic energy consumption prediction of pipeline networks.

[0042] 2. Multi-objective optimization equation and dynamic adjustment coefficient matrix based on energy-pressure dual constraints.

[0043] 3. Design multi-layer composite sound insulation wall panels, combining micro-perforated panels with damping treatment technology.

[0044] 4. Multi-dimensional energy efficiency improvement index calculation model.

[0045] The present application provides a method for constructing an energy consumption system for a clean room air compression system, comprising: obtaining pressure fluctuation data of the clean room air compression system, a clean room positive pressure deviation sequence, a dust removal fan acoustic energy loss value, and a switching frequency of hot and cold coils of an outdoor air conditioning box; calculating dynamic energy consumption prediction data of a pipe network using an LSTM time series prediction model based on the pressure fluctuation data; determining an air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence; generating a coil function conversion critical temperature value using a proportional two-way valve based on the switching frequency of the hot and cold coils of the outdoor air conditioning box; determining a mute gradient parameter of a double-volute resonant cavity based on the dust removal fan acoustic energy loss value; controlling the MIAU fresh air volume using the air volume balance adjustment coefficient to generate real-time positive pressure compensation data; generating a hot and cold coil switching instruction set based on the coil function conversion critical temperature value; deploying the mute gradient parameters to construct acoustic parameters of a sound insulation wall panel assembly; and generating a clean room control system based on the real-time positive pressure compensation data, the hot and cold coil switching instruction set, and the acoustic parameters of the sound insulation wall panel assembly. This application effectively solves the problems of high energy consumption, unstable positive pressure control, and high noise in the clean room air compression system by comprehensively considering and optimizing multiple parameters of the air compression system, and significantly improves the energy efficiency and overall performance of the clean room system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a schematic diagram of the process for constructing the energy consumption index of the clean room air compression system in this application;

[0047] Figure 2 This is a schematic diagram of the device for constructing the energy consumption index of the clean room air compression system in this application. DETAILED DESCRIPTION

[0048] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that various forms of implementation of the present disclosure are not limited to the embodiments set forth herein. Rather, the embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0049] The present application provides a method for constructing an energy consumption system for a clean room air compression system, comprising:

[0050] S101. Obtain the pressure fluctuation data of the clean room air compression system, the positive pressure deviation sequence of the clean room, the acoustic energy loss value of the dust removal fan, and the switching frequency of the hot and cold coils of the external air conditioning box;

[0051] Pressure Fluctuation Data Collection: Pressure sensors are deployed at key points in the air compression system, including the compressor outlet, air tank inlet and outlet, dryer front and rear ends, and the front end of terminal gas-consuming equipment, to collect pressure fluctuation data. The pressure sensors are set to a sampling frequency of 10Hz and transmit data via the RS485 bus.

[0052] Use sliding average filtering, for example, with a window width of 50 sampling points, to eliminate high-frequency noise and calculate the standard deviation as a volatility indicator. The expression is as follows:

[0053]

[0054] in, is a volatility indicator, is the number of sampling points, i is the sampling point, is the pressure value, is the average pressure.

[0055] Positive pressure deviation sequence acquisition:

[0056] In each area of ​​the clean room, including the production area, buffer area, and dressing area, micro differential pressure transmitters are installed to collect pressure differential data and establish a positive pressure deviation sequence. The expression is as follows:

[0057]

[0058] Where k is the number of sampling times and p is the pressure difference.

[0059] Calculation of sound energy loss value:

[0060] Install an IEC 61672 sound level meter on the inlet and outlet ducts of the dust removal fan, measure the sound pressure level in the 63Hz-8kHz frequency range, and calculate the sound power:

[0061] = ×A×t

[0062] Where A is the cross-sectional area of ​​the pipe, t is the measurement time, is the sound pressure level.

[0063] Hot and cold coil switching frequency monitoring:

[0064] Install an electromagnetic flowmeter and a PT100 temperature sensor in the water circuit of the air-conditioning box to record the inlet and outlet water temperature difference ΔT (°C).

[0065] Switching frequency calculation:

[0066]

[0067] S102: Calculate the pipeline network dynamic energy consumption prediction data using the LSTM time series prediction model based on the pressure fluctuation data;

[0068] A three-layer LSTM neural network was constructed, with the input layer containing 32 neurons corresponding to time series parameters such as pressure, flow, and temperature. A time window of 60 minutes and a sliding step of 5 minutes were set to create a time series sample set. The loss function used was a combination of MAE (mean absolute error) and MAPE (mean absolute percentage error).

[0069] Training dataset construction:

[0070] 576 training samples are generated in 24-hour cycles with a step size of 15 minutes. Min-Max normalization is used to the interval [0, 1]. The composite loss function (MAE + 0.3×MAPE) is:

[0071]

[0072] in, is the actual energy consumption value, To predict the energy consumption value, N is the number of samples.

[0073] By introducing a 24-hour sliding window (with a 15-minute step), the diurnal, trend, and residual components of the pipeline network pressure can be separated. This sliding window mechanism is equivalent to performing a local weighted regression on the cyclical components, enhancing the model's ability to capture diurnal pressure fluctuations.

[0074] At the same time, pipeline network energy consumption forecasting focuses on both the absolute energy consumption deviation (MAE) and the relative fluctuation ratio (MAPE). Specifically, when the energy consumption base is large, MAE dominates the optimization, potentially ignoring small abnormal fluctuations. MAPE, on the other hand, can lead to gradient explosion during low energy consumption periods (such as nighttime). Therefore, a linear combination (MAE + 0.3MAPE) is used to ensure stable model convergence under both high and low load conditions.

[0075] Model training and validation:

[0076] Historical running data was loaded for supervised learning, using the Adam optimizer with an initial learning rate of 0.001 and a batch size of 128. Model performance was evaluated through cross-validation, with a test set RMSE of ≤3.5%.

[0077] By balancing the absolute error and relative error through the composite loss function (MAE+0.3×MAPE), the accuracy of the test set is effectively improved compared with the traditional single loss function model.

[0078] The sliding window mechanism enhances the ability to capture local features of time series data, effectively reducing the deviation between the predicted value and the actual energy consumption.

[0079] S103, determining an air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence;

[0080] First, multi-objective optimization problem modeling is performed:

[0081] If the decision variable is set to the air supply volume Qsupply, the objective function is:

[0082]

[0083]

[0084]

[0085] Constraints: 2000≤Qsupply≤5000 (upper and lower limits of air volume).

[0086] in, is the daily energy consumption objective function of the air compressor unit, is the mean objective function of positive pressure deviation, is the equipment life attenuation rate objective function, is the predicted energy consumption value for the tth hour, is the positive pressure deviation of the i-th sampling.

[0087] NSGA-II algorithm parameter settings:

[0088] Population size: 100; crossover probability: 0.8; mutation probability: 0.1; maximum number of iterations: 200.

[0089] Dynamic weight allocation strategy:

[0090] Normal operating conditions: weights ω1=0.5, ω2=0.3, ω3=0.2.

[0091] When the positive pressure deviation is greater than 5 Pa: it is automatically adjusted to ω1=0.3, ω2=0.5, and ω3=0.2.

[0092] Pareto solution set screening rules:

[0093] Keep non-dominated solutions that simultaneously satisfy the following conditions:

[0094]

[0095]

[0096]

[0097] in, is the rated energy consumption.

[0098] Adjustment coefficient matrix:

[0099] Calculation of partition adjustment coefficient: , (i=1,2,...,n).

[0100] Matrix format: T, (n: number of air supply branches).

[0101] This application uses the NSGA-II algorithm to simultaneously optimize the three energy consumption objectives f1, f2, and f3, generating the air volume balance adjustment coefficient matrix K. The NSGA-II algorithm's Pareto solution set screening rules (f1, f2) ensure that both energy consumption and stability are met. Optimizing the equipment life decay rate (f3) reduces compressor starts and stops and increases life expectancy.

[0102] There is a nonlinear coupling relationship between f1 and f2, and traditional single-objective optimization cannot balance the contradiction between the two. This application retains the non-inferior solution set that meets the constraints of f1, f2, and f3 through non-dominated sorting, ensuring that the solution set approaches the optimal value of the three objectives at the same time, rather than compromising a single objective. Independent calculation for different air supply branches , to solve the problem of local positive pressure imbalance caused by traditional global unified regulation.

[0103] S104, generating a coil function conversion critical temperature value through a proportional two-way valve based on the switching frequency of the hot and cold coils of the outdoor air conditioning box;

[0104] Critical temperature calculation model, including: based on heat balance equation, basic PID control, fuzzy rule base and low temperature protection mechanism.

[0105] Based on the heat balance equation:

[0106]

[0107] =20℃ (set temperature)

[0108] =3℃ (safety margin)

[0109] : Wall heat loss (real-time measurement by infrared thermal imaging camera)

[0110] UA=1.2kW / ℃ (coil heat transfer coefficient × area)

[0111] PID-Fuzzy compound control algorithm

[0112] Basic PID control:

[0113] u(k)=2.5e(k)+0.8 +1.2 , (Ts=5s)

[0114] Fuzzy rule base:

[0115] Temperature deviation (℃) Valve position change rate (% / s) >3 +15 1-3 +5 -1~1 0 <-3 -15

[0116] Low temperature protection mechanism:

[0117] when When the temperature is ≤5℃: the heating coil mode is forced to be turned on; the opening of the two-way valve is limited to 30-45% to ensure that the water flow rate is ≥1.2m / s; the water flow rate calculation formula is:

[0118] v=

[0119] in, is the volume flow rate, is the cross-sectional area of ​​the pipe.

[0120] Step S105: determining the muffler gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan;

[0121] Helmholtz resonator design, including: single resonator parameters, array layout scheme and gradient density muffler layer structure.

[0122] Single resonator parameters:

[0123] =

[0124] Here, d is the diameter of the neck, L is the neck length, and V is the cavity volume.

[0125] Array layout scheme:

[0126] Frequency band (Hz) Number of resonators Installation location 500-800 12 The volute inlet is evenly distributed around the circumference 800-2000 8 Spiral arrangement behind the impeller 2000-4000 6 Matrix arrangement of outlet diffuser section

[0127] Gradient density sound-absorbing layer structure:

[0128] Material parameters:

[0129] sequence Material Density (kg / m³) Thickness (mm) Inner layer fiberglass 80 30 Middle level Ceramic cotton 50 20 Outer layer polyester fiber 30 10

[0130] Acoustic performance verification, including: insertion loss calculation, the expression is as follows:

[0131] IL=10 ( )≥12dB, (500−4000Hz)

[0132] S106, controlling the MIAU fresh air volume by the air volume balance adjustment coefficient to generate real-time positive pressure compensation data;

[0133] Feedforward-feedback composite control model:

[0134] Compensation calculation:

[0135] ΔQ=0.35× +0.65×∫( − )dt

[0136] Dynamic limiting strategy:

[0137] Pressure deviation (Pa) Adjustment range Response time >5 ±20% <10s 2-5 ±10% <20s <2 ±5% <30s

[0138] MIAU fresh air volume control execution:

[0139] PID parameter tuning:

[0140] =1.2, =0.5, =0.8 \quad.

[0141] Among them, the dead zone is ±2Pa, and the overshoot is ≤5%.

[0142] In this application, feedforward control quickly offsets sudden pressure disturbances, the feedback integral term eliminates steady-state errors, the dynamic limiting strategy prevents overshoot, and the pressure recovery time is shortened.

[0143] S107, generating a hot and cold coil switching instruction set according to the coil function conversion critical temperature value;

[0144] Based on the critical temperature value generated in step S104 , build dynamic switching logic:

[0145]

[0146] Set a 1°C hysteresis bandwidth to avoid frequent switching (switching interval ≥ 10 minutes)

[0147] Control logic flow:

[0148] Read the outside air temperature and critical temperature, and calculate the temperature difference deviation e= − ;

[0149] Determine the valve position adjustment rate through the fuzzy rule table (see step S104);

[0150] Generate instructions including target opening, execution time, and flow rate constraints.

[0151] Abnormal working condition handling:

[0152] Exception Type Treatment measures Water temperature ≤ 3℃ Forced switch to the heating coil and start the electric heating system Water flow rate <1.0m / s Close the corresponding coil and trigger the alarm Switch >6 times within 1 hour Lock current mode for 2 hours

[0153] Instruction set deployment and execution:

[0154] Instruction storage format: Redis real-time database, sorted by timestamp; execution cycle: scan the instruction queue every 30 seconds; interface with the BMS system: send control signals to the air conditioner PLC via the OPC UA protocol.

[0155] S108. Deploy the noise reduction gradient parameters to construct acoustic parameters of the sound insulation wall panel assembly;

[0156] The sound insulation wall panel adopts a three-layer structure: galvanized steel plate + centrifugal glass wool + micro-perforated aluminum plate, with a gradient density glass fiber layer of 80→50→30kg / m³ on the inside, and a Helmholtz resonator array.

[0157] The Helmholtz resonator covers the frequency band of 500-4000Hz, and the insertion loss is ≥12dB.

[0158] Sound insulation wall panel structural parameters:

[0159] Structural layer Material Density / Thickness Acoustic treatment Outer layer galvanized steel sheet 1.5mm + 2mm damping paint Constrained Layer Damping (CLD) Middle layer Centrifugal glass wool 50mm / 50kg / m³ Covered with non-woven fabric to prevent fiber shedding Inner layer Micro-perforated aluminum sheet 0.8mm / aperture 0.6mm Perforation rate 2%, hole spacing 15mm

[0160] Helmholtz resonator array deployment:

[0161] Resonance cavity design parameters, based on the calculation results of step S105:

[0162] Target frequency band Number of resonators Volume (L) Neck size (mm) 500-800Hz 12 8.2 Φ20×30 800-2000Hz 8 3.5 Φ15×25 2000-4000Hz 6 1.2 Φ10×20

[0163] Gradient density sound-absorbing layer:

[0164] Density gradient of glass fiber layer: linearly decreases from 80→50→30kg / m³ from inside to outside; interlayer bonding: high temperature resistant silicone (shear strength ≥0.8MPa); joint treatment: board seam width ≤2mm, filled with polyurethane sealant (attenuation ≥3dB / seam).

[0165] Acoustic performance verification and adjustment:

[0166] Test Method: Sound intensity sweep method (ISO 9614-2): Measurement at a grid point 1m apart (0.5m intervals); Reverberation chamber method (ISO 354): Measurement of sound transmission loss (TL) of sound insulation panels; Acceptance criteria: TLavg ≥ 25dB (500-4000Hz) ILmax ≥ 12dB (resonator target frequency band).

[0167] In this application, the gradient density layer effectively absorbs mid- and high-frequency noise, the Helmholtz resonator reduces noise at low-frequency peaks, and the micro-perforated plate suppresses high-frequency airflow regeneration noise.

[0168] S109: Generate a clean room control system based on the real-time positive pressure compensation data, the hot and cold coil switching instruction set, and the acoustic parameters of the sound insulation wall panel assembly.

[0169] Create a multidimensional data matrix: X= ; Use principal component analysis to extract eigenvectors and retain components with cumulative contribution rates ≥ 85%, where X is the original data matrix of energy efficiency evaluation, is the positive pressure deviation sequence, is the real-time air supply volume, is the sound pressure level, is the number of switching between hot and cold coils, is the mean value of the air volume balance adjustment coefficient.

[0170] Construct comprehensive evaluation function: η=0.3· + 0.25 + 0.2 +0.15 + 0.1 MTBF, where is the energy saving rate, is the pressure stability index, is the noise reduction amount, For cost saving, MTBF is mean time between failures.

[0171] Energy saving rate =( - ) / ×100%; pressure stability =1 - σ(ΔP) / μ(ΔP); noise reduction = - Cost savings = + ; System reliability MTBF = operating time / number of failures; where, 、 are the baseline energy consumption value and the actual energy consumption value, σ(ΔP) and μ(ΔP) are the standard deviation and the mean of the positive pressure deviation, respectively; 、 They are the equivalent continuous A sound level before and after the transformation; 、 They are initial investment savings and cumulative operation and maintenance savings respectively.

[0172] The traditional method only has a single indicator (such as energy consumption), and this application adds other indicators. Further, as mentioned above, each indicator is and The covariance is adjusted in real time to effectively improve the system energy efficiency and reduce costs.

[0173] In this application, principal component analysis is used to extract key features to avoid the one-sidedness of a single indicator, energy efficiency indicators are used to monitor and warn of equipment degradation in real time, and cost saving indicators are used to quantify the initial investment and operation and maintenance benefits.

[0174] The present application also provides a clean room air compression system energy consumption system construction device, comprising:

[0175] Acquisition module 201 acquires pressure fluctuation data of the clean room air compression system, clean room positive pressure deviation sequence, dust removal fan sound energy loss value and external air conditioning box hot and cold coil switching frequency;

[0176] The pipeline network module 202 calculates the pipeline network dynamic energy consumption prediction data through the LSTM time series prediction model based on the pressure fluctuation data;

[0177] The air volume module 203 determines an air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence;

[0178] The conversion module 204 generates a coil function conversion critical temperature value through a proportional two-way valve based on the switching frequency of the hot and cold coils of the outdoor air conditioning box;

[0179] The muffler module 205 determines the muffler gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan;

[0180] The compensation module 206 controls the MIAU fresh air volume through the air volume balance adjustment coefficient to generate real-time positive pressure compensation data;

[0181] Instruction module 207 generates a set of instructions for switching between hot and cold coils according to the critical temperature value of the coil function conversion;

[0182] an acoustic module 208 that deploys the noise reduction gradient parameters to construct acoustic parameters of the sound insulation wall panel assembly;

[0183] The indicator module 209 generates a clean room control system according to the real-time positive pressure compensation data, the hot and cold coil switching instruction set, and the acoustic parameters of the sound insulation wall panel assembly.

[0184] Furthermore, the LSTM time series prediction model includes: adopting a sliding time window mechanism;

[0185] The steps of the sliding time window mechanism include: dividing the pressure fluctuation data into time windows according to a 24-hour period, constructing a pipeline network energy consumption time series training set with a step size of 15 minutes, and outputting dynamic energy consumption forecast data for the next 2 hours.

[0186] Furthermore, the air volume module determines the air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence, including:

[0187] The NSGA-II multi-objective processing algorithm is used to simultaneously optimize the three objective functions of the air compressor unit energy consumption index, the clean room positive pressure stability index, and the equipment life attenuation index to obtain the air volume balance adjustment coefficient.

[0188] Furthermore, when the proportional two-way valve in the conversion module generates a critical temperature value for coil function conversion, it includes:

[0189] When the outside air temperature is detected to be ≤5℃, the PID control algorithm is used to adjust the opening of the two-way valve to 30-45%, so that the water flow rate of the cooling coil is not less than 1.2m / s.

[0190] Furthermore, the acoustic module determines the muffler gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan, including:

[0191] A 30-100kg / m³ gradient density glass fiber layer is set on the inner side of the dust removal fan volute, and a Helmholtz resonator array is integrated, with the resonance frequency covering the 500-4000Hz noise frequency band.

[0192] The above description of the embodiments is intended to facilitate understanding and application of the present invention by those skilled in the art. It will be readily apparent to those skilled in the art that various modifications to the above embodiments can be made, and the general principles described herein can be applied to other embodiments without requiring inventive effort. Therefore, the present invention is not limited to the above embodiments, and improvements and modifications made by those skilled in the art based on the present disclosure are intended to fall within the scope of protection of the present invention.

Claims

1. A method for constructing an energy consumption system for a clean room air compression system, characterized in that: include: Obtain the pressure fluctuation data of the clean room air compression system, the clean room positive pressure deviation sequence, the dust removal fan sound energy loss value and the switching frequency of the hot and cold coils of the outdoor air conditioning box; Calculate the pipeline network dynamic energy consumption prediction data using the LSTM time series prediction model based on the pressure fluctuation data; Determining an air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence; Based on the switching frequency of the hot and cold coils of the outdoor air conditioning box, a critical temperature value for coil function conversion is generated through a proportional two-way valve; Determining the muffler gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan; The MIAU fresh air volume is controlled by the air volume balance adjustment coefficient to generate real-time positive pressure compensation data; Generating a hot and cold coil switching instruction set according to the coil function conversion critical temperature value; Deploying the noise reduction gradient parameters to construct acoustic parameters of the sound insulation wall panel assembly; A clean room control system is generated according to the real-time positive pressure compensation data, the hot and cold coil switching instruction set, and the acoustic parameters of the sound insulation wall panel assembly.

2. A method for constructing an energy consumption system for a clean room air compression system according to claim 1, characterized in that: The LSTM time series prediction model includes: adopting a sliding time window mechanism; The steps of the sliding time window mechanism include: dividing the pressure fluctuation data into time windows according to a 24-hour period, constructing a pipeline network energy consumption time series training set with a step size of 15 minutes, and outputting dynamic energy consumption forecast data for the next 2 hours.

3. A method for constructing an energy consumption system for a clean room air compression system according to claim 1, characterized in that: Determining an air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence includes: The NSGA-II multi-objective processing algorithm is used to simultaneously optimize the three objective functions of the air compressor unit energy consumption index, the clean room positive pressure stability index, and the equipment life attenuation index to obtain the air volume balance adjustment coefficient.

4. A method for constructing an energy consumption system for a clean room air compression system according to claim 1, characterized in that: When the proportional two-way valve generates the coil function conversion critical temperature value, it includes: When the outside air temperature is detected to be ≤5℃, the PID control algorithm is used to adjust the opening of the two-way valve to 30-45%, so that the water flow rate of the cooling coil is not less than 1.2m / s.

5. The method for constructing an energy consumption system of a clean room air compression system according to claim 1, characterized in that: According to the sound energy loss value of the dust removal fan, the muffler gradient parameters of the double volute resonance cavity are determined, including: setting a 30-100 kg / m³ gradient density glass fiber layer on the inner side of the dust removal fan volute and integrating a Helmholtz resonator array, with the resonance frequency covering the 500-4000 Hz noise frequency band.

6. A clean room air compression system energy consumption system construction device, characterized in that: include: Acquisition module, which obtains the pressure fluctuation data of the clean room air compression system, the positive pressure deviation sequence of the clean room, the sound energy loss value of the dust removal fan, and the switching frequency of the hot and cold coils of the external air conditioning box; The pipeline network module calculates the pipeline network dynamic energy consumption prediction data based on the pressure fluctuation data through the LSTM time series prediction model; An air volume module determines an air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence; A conversion module, based on the switching frequency of the hot and cold coils of the outdoor air conditioning box, generates a coil function conversion critical temperature value through a proportional two-way valve; A silencer module, which determines a silencer gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan; A compensation module controls the MIAU fresh air volume through the air volume balance adjustment coefficient and generates real-time positive pressure compensation data; An instruction module, converting a critical temperature value according to the coil function, and generating a hot and cold coil switching instruction set; an acoustic module, deploying the noise reduction gradient parameters to construct acoustic parameters of the sound insulation wall panel assembly; The indicator module generates a clean room control system according to the real-time positive pressure compensation data, the hot and cold coil switching instruction set and the acoustic parameters of the sound insulation wall panel assembly.

7. A clean room air compression system energy consumption system construction device according to claim 6, characterized in that: The LSTM time series prediction model includes: adopting a sliding time window mechanism; The steps of the sliding time window mechanism include: dividing the pressure fluctuation data into time windows according to a 24-hour period, constructing a pipeline network energy consumption time series training set with a step size of 15 minutes, and outputting dynamic energy consumption forecast data for the next 2 hours.

8. A clean room air compression system energy consumption system construction device according to claim 6, characterized in that: The air volume module determines the air volume balance adjustment coefficient based on the network dynamic energy consumption prediction data and the clean room positive pressure deviation sequence, including: The NSGA-II multi-objective processing algorithm is used to simultaneously optimize the three objective functions of the air compressor unit energy consumption index, the clean room positive pressure stability index, and the equipment life attenuation index to obtain the air volume balance adjustment coefficient.

9. A clean room air compression system energy consumption system construction device according to claim 6, characterized in that: When the proportional two-way valve in the conversion module generates a coil function conversion critical temperature value, it includes: When the outside air temperature is detected to be ≤5℃, the PID control algorithm is used to adjust the opening of the two-way valve to 30-45%, so that the water flow rate of the cooling coil is not less than 1.2m / s.

10. A clean room air compression system energy consumption system construction device according to claim 6, characterized in that: The acoustic module determines the muffler gradient parameter of the double volute resonance cavity according to the sound energy loss value of the dust removal fan, including: A 30-100kg / m³ gradient density glass fiber layer is set on the inner side of the dust removal fan volute, and a Helmholtz resonator array is integrated, with the resonance frequency covering the 500-4000Hz noise frequency band.

Images