Search

CN-122015240-A - Fuzzy prediction-based energy-saving control method and system for ventilation system

CN122015240ACN 122015240 ACN122015240 ACN 122015240ACN-122015240-A

Abstract

The application discloses a ventilation system energy-saving control method and system based on fuzzy prediction, which are characterized in that the heat storage state of an enclosure structure is captured in real time through a nonlinear observation technology and vectorized into a thermal momentum characteristic representing the evolution trend of a temperature field, so that the fuzzy controller is endowed with physical pre-sensing capability for the evolution of a physical environment, and response hysteresis compensation caused by the thermal capacitance effect of a building structure is realized. The scheme breaks through the limitation of simplifying the inertia of the system by the traditional algorithm, and combines the pressure and flow characteristics of the fan and the surge boundary to perform physical energy efficiency verification by introducing multidimensional self-adaptive fuzzy reasoning of thermal momentum compensation, thereby not only remarkably improving the prediction precision under the dynamic fluctuation working condition of the temperature field, but also effectively eliminating the temperature overshoot and the energy consumption loss caused by response time sequence mismatch. Finally, the deep coupling of the control logic and the thermodynamic characteristics of the building is realized, and the dynamic robustness and the comprehensive energy-saving efficiency of the ventilation system are greatly optimized while the indoor comfort level is ensured.

Inventors

  • LI BAILIN
  • LI JIANMING

Assignees

  • 中山市奥创通风设备有限公司

Dates

Publication Date
20260512
Application Date
20260325

Claims (10)

  1. 1. The energy-saving control method for the ventilation system based on fuzzy prediction is characterized by comprising the following steps of: S1, denoising smoothing and time sequence hard alignment are carried out on collected air supply temperature, return air temperature, indoor temperature gradient and air supply quantity to obtain a working condition data set; S2, carrying out nonlinear observation on heat storage states of air supply temperature, return air temperature, air supply quantity and indoor temperature gradient in the working condition data set to obtain energy mismatch characteristics; S3, carrying out vectorization extraction of heat accumulation evolution trend on the historical time sequence temperature segments and the energy mismatch degree features in the working condition data set to obtain a thermal momentum feature vector; S4, extracting a temperature setting error and an error change rate thereof from the working condition data set as basic addressing input of the fuzzy controller, and performing multi-dimensional self-adaptive fuzzy reasoning based on thermal momentum compensation on the thermal momentum characteristic vector to obtain a ventilation demand reference; and S5, inputting a ventilation demand standard into the nonlinear constraint module, and calling a pressure flow characteristic curve and a surge boundary threshold matrix of the ventilator unit to perform physical energy efficiency boundary check so as to obtain an optimized control instruction.
  2. 2. The fuzzy prediction based ventilation system power saving control method of claim 1, wherein step S1 comprises: respectively performing sliding median filtering on the collected air supply temperature, air return temperature, indoor temperature gradient and air supply quantity to obtain a filtering signal set; performing multi-source data clock hard alignment and resampling on the filtered signal set to obtain an aligned time sequence; Vertically arranging the air supply temperature, the air return temperature, the indoor temperature gradient and the air supply quantity in the aligned time sequence according to the space dimension to obtain an original feature matrix; and performing extremely poor standardization on the original feature matrix to obtain a working condition data set.
  3. 3. The fuzzy prediction based ventilation system power saving control method of claim 1, wherein step S2 includes: based on the resampled air supply temperature, the resampled air return temperature, the resampled air supply sequence, the resampled air density and the resampled air pressure specific heat capacity in the working condition data set, calculating the instantaneous sensible heat power input into the building space at the current moment of the ventilation system to obtain the sensible heat power of the system; determining the air internal energy change rate based on the indoor temperature gradient sequence in the working condition data set and the effective ventilation volume of the controlled area; and performing state estimation based on residual observation on the sensible heat power and the air internal energy change rate of the system to obtain the energy mismatch degree characteristic.
  4. 4. The fuzzy prediction based energy saving control method of a ventilating system according to claim 3, wherein calculating the instantaneous sensible heat power of the ventilating system input to the building space at the current moment based on the resampled supply air temperature, return air temperature, supply air volume sequence, air density and constant pressure specific heat capacity in the working condition data set to obtain the system sensible heat power comprises calculating the system sensible heat power according to the following formula: Wherein, the For the sensible heat power of the system, In order to achieve an air density of the air, The specific heat capacity is fixed for the air, Is that The air supply amount at the moment, Is that Return air temperature at moment and Is that Air supply temperature at the moment.
  5. 5. The fuzzy prediction based energy efficient ventilation system control method of claim 3, wherein determining the air internal energy rate of change based on the sequence of indoor temperature gradients in the operating mode dataset and the effective ventilation volume of the controlled area comprises determining the air internal energy rate of change by the following equation: Wherein, the In order to achieve an air density of the air, The specific heat capacity is fixed for the air, For an effective ventilation volume of the controlled area, Is the gradient of the average indoor temperature with time.
  6. 6. The fuzzy prediction based ventilation system power saving control method of claim 3, wherein step S3 includes: extracting an indoor temperature time sequence segment in a current observation window from a working condition data set, and calculating a time derivative of the indoor temperature at the current moment relative to a previous time window to obtain a temperature field evolution rate; performing heat storage charge-discharge potential evaluation on the energy mismatch degree characteristics to obtain heat storage charge-discharge potential; and carrying out thermal momentum orthogonal synthesis and vectorization extraction on the temperature field evolution rate and the heat storage charge-discharge potential to obtain a thermal momentum characteristic vector.
  7. 7. The fuzzy prediction based ventilation system power saving control method of claim 1, wherein step S4 includes: Extracting an indoor environment temperature value at the current observation time from a working condition data set, calling an indoor target control temperature preset by a system to calculate a temperature setting error at the current time and the change rate of the temperature setting error along with time, and carrying out combined encapsulation on the calculated temperature setting error and the error change rate to obtain basic addressing input; performing fuzzy membership function self-adaptive deformation processing on the thermal momentum characteristic vector to obtain a deformation membership function set; And injecting basic addressing input into the deformation membership function set to perform multidimensional fuzzy rule reasoning and defuzzification so as to obtain a ventilation requirement standard.
  8. 8. The fuzzy prediction based ventilation system power saving control method of claim 1, wherein step S5 includes: invoking a preset fan pressure flow characteristic curve matrix to extract a high-efficiency operation interval and a surge critical threshold value at the current rotating speed, and judging whether a ventilation demand benchmark falls in a low-efficiency area or an unstable surge area of the fan to obtain a boundary check state; Responding to the state value of the boundary checking state as 1, and performing energy efficiency gestation optimization smoothing on the ventilation requirement standard to obtain an optimizing adjustment value; Mapping the optimizing adjustment value to the output frequency of the frequency converter, and calling a communication protocol stack to package the output frequency into a specific register write instruction packet to obtain an optimizing control instruction.
  9. 9. The fuzzy prediction based energy saving control method of a ventilation system of claim 8, wherein in response to a state value of 1 of the boundary check state, performing energy efficiency, gestation and optimization smoothing on the ventilation demand reference to obtain the optimizing adjustment value, comprising: In response to the state value of the boundary check state being 1, constructing a thermal inertia sensitivity coefficient based on the modulo length component and the argument component in the thermal momentum feature vector; determining a heat storage compensation weight based on the energy mismatch degree characteristics; performing amplitude limiting treatment on the ventilation demand standard to obtain a preliminary optimizing air quantity value; Based on the thermal inertia sensitivity coefficient and the heat accumulation compensation weight, carrying out self-adaptive nonlinear time-area equivalent optimization on the preliminary optimizing air quantity value to obtain an optimizing adjustment value.
  10. 10. A fuzzy prediction based energy saving control system for a ventilation system, comprising: The data preprocessing module is used for carrying out denoising smoothing and time sequence hard alignment on the collected air supply temperature, air return temperature, indoor temperature gradient and air supply quantity so as to obtain a working condition data set; the heat storage state nonlinear observation module is used for carrying out heat storage state nonlinear observation on air supply temperature, return air temperature, air supply quantity and indoor temperature gradient in the working condition data set so as to obtain energy mismatch characteristics; The vectorization extraction module is used for carrying out vectorization extraction of heat accumulation evolution trend on the historical time sequence temperature segments and the energy mismatch degree features in the working condition data set so as to obtain a thermal momentum feature vector; The multidimensional self-adaptive fuzzy reasoning module is used for extracting temperature setting errors and error change rates thereof from the working condition data set as basic addressing input of the fuzzy controller, and carrying out multidimensional self-adaptive fuzzy reasoning based on thermal momentum compensation on the thermal momentum characteristic vector so as to obtain a ventilation demand reference; And the physical energy efficiency boundary checking module is used for inputting the ventilation requirement standard into the nonlinear constraint module, and calling the pressure flow characteristic curve of the ventilator unit and the surge boundary threshold matrix to perform physical energy efficiency boundary checking so as to obtain the optimized control instruction.

Description

Fuzzy prediction-based energy-saving control method and system for ventilation system Technical Field The application relates to the field of intelligent control, in particular to a ventilation system energy-saving control method and system based on fuzzy prediction. Background As modern buildings evolve towards intelligentization and low carbonization, ventilation systems serve as core components for building environment regulation, and energy efficiency management of the ventilation systems directly affects overall energy saving performance of the building. Particularly, under the large commercial and industrial scenes, an accurate ventilation energy-saving control scheme is established, so that the requirements of indoor air quality and thermal comfort are met, and key measures of reducing operation cost and realizing energy consumption fine management are provided. However, existing energy-saving control of ventilation systems is mostly dependent on conventional PID regulation or basic fuzzy control algorithms. When the scheme is used for processing complex dynamic environments, a ventilation system is generally simplified into a first-order inertia link, and dynamic hysteresis effects generated by taking walls, floors and the like in building enclosure structures as thermal capacitors are seriously ignored. Limited by a fixed prediction horizon, existing fuzzy rules tend to address based only on the error at the current time and its rate of change, lacking the ability to quantitatively characterize the thermal decay trend over a period of time in the future. When the system faces the sudden change of load, response time sequence mismatch is extremely easy to be caused by thermal inertia, so that the problems of serious indoor temperature overshoot or delayed shutdown of a fan and the like are caused, and huge energy redundancy waste is directly caused by the failure of prediction precision. In an actual operating scenario, the ventilation system is essentially in a double-operating alternating state of quasi-steady-state operation and high-frequency dynamic load fluctuations. The existing control strategy often lacks of excitation and power parameter self-adaptive adjustment strategies under double working conditions, and a scientific working condition switching flow cannot be established, so that when the evolution direction of a temperature field is reversed or the load is severely disturbed, the control step length and the compensation gain are difficult to correct in real time. Aiming at control defocusing caused by thermal momentum evolution and energy mismatch, how to realize multidimensional self-adaptive fuzzy reasoning based on heat storage state sensing and carry out closed-loop constraint verification by combining a physical energy efficiency boundary of a unit becomes a core technical problem to be solved urgently in improving dynamic control robustness and energy saving efficiency of a ventilation system at present. Accordingly, an optimized fuzzy prediction based energy-saving control method for a ventilation system is desired. Disclosure of Invention In order to solve the technical problems, the application provides an energy-saving control method and system for a ventilation system based on fuzzy prediction. According to an aspect of the present application, there is provided a fuzzy prediction based energy saving control method of a ventilating system, including: S1, denoising smoothing and time sequence hard alignment are carried out on collected air supply temperature, return air temperature, indoor temperature gradient and air supply quantity to obtain a working condition data set; S2, carrying out nonlinear observation on heat storage states of air supply temperature, return air temperature, air supply quantity and indoor temperature gradient in the working condition data set to obtain energy mismatch characteristics; S3, carrying out vectorization extraction of heat accumulation evolution trend on the historical time sequence temperature segments and the energy mismatch degree features in the working condition data set to obtain a thermal momentum feature vector; S4, extracting a temperature setting error and an error change rate thereof from the working condition data set as basic addressing input of the fuzzy controller, and performing multi-dimensional self-adaptive fuzzy reasoning based on thermal momentum compensation on the thermal momentum characteristic vector to obtain a ventilation demand reference; and S5, inputting a ventilation demand standard into the nonlinear constraint module, and calling a pressure flow characteristic curve and a surge boundary threshold matrix of the ventilator unit to perform physical energy efficiency boundary check so as to obtain an optimized control instruction. According to another aspect of the present application, there is provided a fuzzy prediction based energy saving control system for a ventilation system, comprising: The data prepro