Air compressor control method and equipment of power plant pneumatic system and medium

Abstract

The invention relates to an air compressor control method and device for a power plant pneumatic system and a medium, and belongs to the technical field of power plant control, and the method comprises the following steps: obtaining ash hopper material level data and air compressor operation data of the power plant pneumatic system, constructing an air compressor operation vector based on the operation data, and inputting the air compressor operation vector into a recurrent neural network to obtain an air compressor stability score; the material level trend is calculated according to ash hopper material level data, a material level trend vector is constructed and input into a multi-layer perceptron to output a predicted material level, and then the predicted material level is corrected by combining the stability score of the air compressor to obtain a corrected material level. And the initial ash conveying frequency of the air compressor is obtained according to the corrected material level and the material level trend, then the initial ash conveying frequency is corrected according to the stability score of the air compressor to obtain the corrected ash conveying frequency, and the air compressor conveys ash according to the frequency. A material level trend prediction mechanism is innovatively introduced, the limitation of traditional passive response type control is broken through, the ash conveying strategy can be actively adjusted before the material level is abnormal, and the risk that the ash hopper is blocked or overflows is avoided.

Description

Technical Field

[0001] This invention relates to a method, equipment, and medium for controlling an air compressor in a power plant pneumatic system, belonging to the field of power plant control technology. Background Technology

[0002] With the rapid development of the power industry and increasingly stringent environmental standards, coal-fired power plants have become a crucial component of power supply. In power plant ash removal processes, pneumatic ash conveying systems have become the mainstream gas-solid two-phase flow conveying solution due to their advantages such as flexible layout, high conveying efficiency, and low environmental pollution. This system uses compressed air as a power source to transport fly ash collected by electrostatic precipitators or bag filters to the ash silo via pipelines. The air compressor, as the core compressed air generator, directly determines the ash conveying efficiency, energy consumption level, and system reliability. In practical engineering applications, the proper control of the ash conveying frequency is a key factor affecting the performance of the pneumatic ash conveying system—too low a frequency leads to fly ash accumulation in the ash hopper, causing hopper blockage, electrode short circuits, and even dust collector shutdowns; too high a frequency results in wasted compressed air, accelerated pipeline wear, and frequent compressor start-ups and shutdowns, significantly increasing equipment maintenance costs and energy consumption.

[0003] Traditional control strategies primarily rely on real-time monitoring values ​​from ash hopper level gauges, employing simple threshold logic (such as starting at high levels and stopping at low levels) to adjust the ash conveying frequency. These methods are logically simple and easy to implement, and were widely used in early ash conveying control systems. However, traditional control strategies depend on a single level parameter for decision-making, lacking the ability to verify the validity of data. When faced with instantaneous fluctuations or false signals, they are easily misinterpreted as genuine level changes, leading to frequent fluctuations in the ash conveying frequency or malfunctions. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention proposes a method, equipment, and medium for controlling an air compressor in a power plant pneumatic system.

[0005] The technical solution of the present invention is as follows: On one hand, the present invention provides a method for controlling an air compressor in a power plant pneumatic system, comprising the following steps: Acquire the ash hopper level data and air compressor operation data of the power plant's pneumatic system, and construct the air compressor operation vector based on the operation data; Calculate the material level trend based on the aforementioned ash hopper material level data; Based on the air compressor operating vector, a recurrent neural network is used to obtain the air compressor stability score; Based on the ash hopper level data and level trend, a level trend vector is constructed, and the level trend vector is input into a multilayer sensor to output the predicted level. The predicted material level is corrected based on the air compressor stability score to obtain the corrected material level; The initial ash conveying frequency of the air compressor is obtained based on the corrected material level and material level trend, and the initial ash conveying frequency is corrected according to the air compressor stability score to obtain the corrected ash conveying frequency. The air compressor conveys ash according to the corrected ash conveying frequency.

[0006] Preferably, the method further includes preprocessing the ash hopper level data, expressed by the formula: ; In the formula, express The ash hopper level data after real-time preprocessing. express Real-time ash hopper level data, , This indicates the weighting coefficient for material level pretreatment. Indicates the length of the material level time window. express Real-time ash hopper level data, This represents the time variable for integration.

[0007] Preferably, the material level trend is calculated based on the ash hopper material level data, expressed by the formula: ; In the formula, express The trend of material price at any given moment. Indicates the number of historical data points. Indicates the first Each historical data weight, express The ash hopper level data after real-time preprocessing. Indicates the weight of trend analysis. Represents the time constant. This represents the rate of change of the pre-processed ash hopper level data with respect to time.

[0008] Preferably, the air compressor stability score is obtained using a recurrent neural network based on the air compressor operating vector. The specific steps are as follows: An air compressor operation vector is constructed based on the aforementioned operational data; The operating data includes the air compressor outlet pressure, air compressor operating current, and air compressor exhaust temperature. The air compressor operating vector is expressed by the formula: ; In the formula, express The air compressor's operating vector at any given time. express The air compressor outlet pressure at any given time. express The operating current of the air compressor at any given time. express The air compressor exhaust temperature at any given time. This indicates the reference value for the air compressor outlet pressure. This indicates the reference value for the air compressor's operating current. This indicates the reference value for the air compressor's exhaust temperature; The air compressor operating vector is input into a recurrent neural network, which outputs an air compressor stability score, expressed by the formula: ; ; In the formula, express The hidden state vector at time step 1. This represents the hyperbolic tangent activation function. This represents the weight matrix input to the hidden layer. This represents the weight matrix from hidden layer to hidden layer. express The hidden state vector at time step 1. This represents the hidden layer bias vector. This represents the sigmoid function. This represents the weight vector from the hidden layer to the output layer. This indicates the output layer bias. express The stability score of the air compressor at any given time.

[0009] Preferably, a level trend vector is constructed based on the ash hopper level data and level trend, and the level vector is input into a multilayer perceptron to output the predicted level. The specific steps are as follows: Based on the aforementioned ash hopper level data and level trends, a level trend vector is constructed, expressed by the formula: ; In the formula, express The material level trend vector at any given time. express The ash hopper level data after real-time preprocessing. express The ash hopper level data after real-time preprocessing. Indicates the reference height of the ash hopper material level; The material level vector is input into the multilayer sensor, expressed as a formula: ;

[0010] ; In the formula, express The first hidden layer outputs at all times. This represents the weight matrix of the first hidden layer. This represents the bias vector of the first hidden layer. express The output of the second hidden layer at any given time. This represents the weight matrix of the second hidden layer. This represents the bias vector of the second hidden layer. express Predicted material level at any given time. This represents the output layer weight vector. This indicates the output layer bias.

[0011] Preferably, the predicted material level is corrected based on the air compressor stability score, expressed by the following formula: ; In the formula, express Predicted material level at any given time. express The air compressor stability rating at any given time. express Real-time material level adjustment Describes the minimum value function. Represents the maximum value function. Indicates the maximum allowable ash hopper level. Indicates the minimum allowable ash hopper level. Indicates the stability weight factor. This represents the baseline stability index.

[0012] Preferably, the initial ash conveying frequency of the air compressor is obtained based on the corrected material level and material level trend, expressed by the formula: ; In the formula, Indicates air compressor The initial gray feed frequency at time 1. This represents the material level ratio control coefficient. Indicates the reference ash feeding frequency. This represents the trend differential control coefficient. Indicates the maximum permissible ash conveying frequency. This indicates the minimum permissible ash feeding frequency.

[0013] Preferably, the corrected ash conveying frequency is obtained by correcting the initial ash conveying frequency based on the air compressor stability score, as expressed by the formula: ; In the formula, Indicates air compressor The frequency of the gray feed is adjusted at any time. This represents the deviation compensation coefficient. Indicates the target ash hopper level.

[0014] In another aspect, the present invention also provides an electronic device having a computer program stored thereon, which, when executed by a processor, implements the air compressor control method of the power plant pneumatic system as described in any embodiment of the present invention.

[0015] In another aspect, the present invention also provides a computer-readable storage medium for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the air compressor control method of the power plant pneumatic system as described in any embodiment of the present invention.

[0016] The present invention has the following beneficial effects: 1. This invention constructs a level trend vector that includes operating status and level trend by collecting ash hopper level data and real-time air compressor operating parameters. A recurrent neural network is used to quantitatively evaluate equipment stability, and combined with the level trend prediction results from a multilayer sensor, a dynamic correction mechanism is formed. This dual-verification mode effectively avoids the risk of misjudgment caused by data fluctuations in traditional single-parameter control, ensuring that the air compressor's operating state is always within the optimal range.

[0017] 2. This invention innovatively introduces a material level trend prediction mechanism, breaking through the limitations of traditional passive response control. Through multi-dimensional analysis of historical material level data, it captures the potential patterns of material level changes, forming a forward-looking trend prediction model. This predictive capability enables the control system to proactively adjust the ash conveying strategy before material level anomalies occur, avoiding the risk of ash hopper blockage or overflow. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the implementation of the method in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0021] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0022] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0023] The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0024] Example 1: See Figure 1 This embodiment provides a method for controlling an air compressor in a power plant pneumatic system, including the following steps: Acquire the ash hopper level data and air compressor operation data of the power plant's pneumatic system, and construct the air compressor operation vector based on the operation data; Calculate the material level trend based on the aforementioned ash hopper material level data; Based on the air compressor operating vector, a recurrent neural network is used to obtain the air compressor stability score; Based on the ash hopper level data and level trend, a level trend vector is constructed, and the level trend vector is input into a multilayer sensor to output the predicted level. The predicted material level is corrected based on the air compressor stability score to obtain the corrected material level; The initial ash conveying frequency of the air compressor is obtained based on the corrected material level and material level trend, and the initial ash conveying frequency is corrected according to the air compressor stability score to obtain the corrected ash conveying frequency. The air compressor conveys ash according to the corrected ash conveying frequency.

[0025] There are many interference factors in the process of collecting ash hopper level data (specifically, the height of the material), including signal fluctuations caused by mechanical vibration, sensor measurement errors, noise generated by electromagnetic interference, and random disturbances inherent in the process.

[0026] Preferably, the method further includes preprocessing the ash hopper level data, expressed by the formula: ; In the formula, express The ash hopper level data after real-time preprocessing. express Real-time ash hopper level data, , This indicates the weighting coefficient for material level pretreatment. Indicates the length of the material level time window. express Real-time ash hopper level data, This represents the time variable for integration.

[0027] Based on the filtering concept in signal processing and control theory, a weighted combination method is used to fuse current measurement values ​​with historical trend information. The quality of the preprocessed level data is significantly improved, random noise is effectively suppressed, and abnormal fluctuations are reasonably smoothed, providing a reliable data foundation for subsequent control decisions.

[0028] In the process of controlling the material level in an ash hopper, relying solely on the current material level value for decision-making has significant limitations. When a high material level is detected, the ash hopper is already in a suboptimal state, and this feedback control based on the current value inherently has a lag. However, the trend of material level changes contains information about future developments, and trend analysis can enable proactive prediction, allowing the control system to prevent problems before they occur.

[0029] Preferably, the material level trend is calculated based on the ash hopper material level data, expressed by the formula: ; In the formula, express The trend of material price at any given moment. Indicates the number of historical data points. Indicates the first Each historical data weight, express The ash hopper level data after real-time preprocessing. Indicates the weight of trend analysis. Represents the time constant. This represents the rate of change of the pre-processed ash hopper level data with respect to time.

[0030] By weighted averaging of material level data from multiple historical moments, the basic operating trend of material levels was extracted. This acts like a low-pass filter, reflecting long-term dynamic characteristics. By calculating the approximate derivative using differential calculation, the instantaneous rate of change of material level is captured. This is equivalent to a high-pass filter, reflecting short-term dynamic characteristics.

[0031] Preferably, the air compressor stability score is obtained using a recurrent neural network based on the air compressor operating vector. The specific steps are as follows: An air compressor operation vector is constructed based on the aforementioned operational data; The operating data includes the air compressor outlet pressure, air compressor operating current, and air compressor exhaust temperature. The air compressor operating vector is expressed by the formula: ; In the formula, express The air compressor's operating vector at any given time. express The air compressor outlet pressure at any given time. express The operating current of the air compressor at any given time. express The air compressor exhaust temperature at any given time. This indicates the reference value for the air compressor outlet pressure. This indicates the reference value for the air compressor's operating current. This indicates the reference value for the air compressor's exhaust temperature; The air compressor operating vector is input into a recurrent neural network, which outputs an air compressor stability score, expressed by the formula: ; ; In the formula, express The hidden state vector at time step 1. This represents the hyperbolic tangent activation function. This represents the weight matrix input to the hidden layer. This represents the weight matrix from hidden layer to hidden layer. express The hidden state vector at time step 1. This represents the hidden layer bias vector. This represents the sigmoid function. This represents the weight vector from the hidden layer to the output layer. This indicates the output layer bias. express The stability score of the air compressor at any given time.

[0032] Recurrent neural networks (RNNs) possess unique memory capabilities and temporal processing abilities. Unlike traditional feedforward neural networks, RNNs transmit historical information through their internal hidden states, enabling the network to remember its operating state over a period of time. When a new air compressor operating vector is input into the RNN, it not only performs calculations based on the current input but also incorporates the state information accumulated from all previous time steps. This mechanism is highly suitable for processing time-dependent air compressor operating vectors.

[0033] Preferably, a level trend vector is constructed based on the ash hopper level data and level trend, and the level vector is input into a multilayer perceptron to output the predicted level. The specific steps are as follows: Based on the aforementioned ash hopper level data and level trends, a level trend vector is constructed, expressed by the formula: ; In the formula, express The material level trend vector at any given time. express The ash hopper level data after real-time preprocessing. express The ash hopper level data after real-time preprocessing. Indicates the reference height of the ash hopper material level; The material level vector is input into the multilayer sensor, expressed as a formula: ;

[0034] ; In the formula, express The first hidden layer outputs at all times. This represents the weight matrix of the first hidden layer. This represents the bias vector of the first hidden layer. express The output of the second hidden layer at any given time. This represents the weight matrix of the second hidden layer. This represents the bias vector of the second hidden layer. express Predicted material level at any given time. This represents the output layer weight vector. This indicates the output layer bias.

[0035] As a feedforward artificial neural network, the multilayer perceptron (MLP) possesses powerful nonlinear mapping and pattern recognition capabilities. The construction of the material level trend vector transforms discrete time-series data into a structured input that the neural network can process, containing comprehensive information from historical material level data and current trend indicators. Normalization ensures that all input features are within the same numerical range, preventing certain features from dominating the network training process due to different units of measurement. The first hidden layer of the MLP performs a primary nonlinear transformation of the input features through neurons and activation functions, extracting primary features. The second hidden layer performs deeper feature combination and abstraction based on the primary features, capturing the complex patterns of material level changes. The output layer maps the high-level features to specific predicted material levels.

[0036] Preferably, the predicted material level is corrected based on the air compressor stability score, expressed by the following formula: ; In the formula, express Predicted material level at any given time. express The air compressor stability rating at any given time. express Real-time material level adjustment Describes the minimum value function. Represents the maximum value function. Indicates the maximum allowable ash hopper level. Indicates the minimum allowable ash hopper level. Indicates the stability weight factor. This represents the baseline stability index.

[0037] Preferably, the initial ash conveying frequency of the air compressor is obtained based on the corrected material level and material level trend, expressed by the formula: ; In the formula, Indicates air compressor The initial gray feed frequency at time 1. This represents the material level ratio control coefficient. Indicates the reference ash feeding frequency. This represents the trend differential control coefficient. Indicates the maximum permissible ash conveying frequency. This indicates the minimum permissible ash feeding frequency.

[0038] Preferably, the corrected ash conveying frequency is obtained by correcting the initial ash conveying frequency based on the air compressor stability score, as expressed by the formula: ; In the formula, Indicates air compressor The frequency of the gray feed is adjusted at any time. This represents the deviation compensation coefficient. Indicates the target ash hopper level.

[0039] Example 2: This embodiment provides an electronic device that stores a computer program. When the computer program is executed by a processor, it implements the air compressor control method of the power plant pneumatic system as described in any embodiment of the present invention.

[0040] Example 3: This embodiment provides a computer-readable storage medium for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the air compressor control method of the power plant pneumatic system as described in any embodiment of the present invention.

[0041] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0042] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0043] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0044] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0045] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for controlling an air compressor in a power plant pneumatic system, characterized in that, Includes the following steps: Acquire the ash hopper level data and air compressor operation data of the power plant's pneumatic system, and construct the air compressor operation vector based on the operation data; Calculate the material level trend based on the aforementioned ash hopper material level data; Based on the air compressor operating vector, a recurrent neural network is used to obtain the air compressor stability score; Based on the ash hopper level data and level trend, a level trend vector is constructed, and the level trend vector is input into a multilayer sensor to output the predicted level. The predicted material level is corrected based on the air compressor stability score to obtain the corrected material level; The initial ash conveying frequency of the air compressor is obtained based on the corrected material level and material level trend, and the initial ash conveying frequency is corrected according to the air compressor stability score to obtain the corrected ash conveying frequency. The air compressor conveys ash according to the corrected ash conveying frequency.

2. The air compressor control method for a power plant pneumatic system according to claim 1, characterized in that, The method further includes preprocessing the ash hopper level data, expressed by the formula: ； In the formula, express The ash hopper level data after real-time preprocessing. express Real-time ash hopper level data, , This indicates the weighting coefficient for material level pretreatment. Indicates the length of the material level time window. express Real-time ash hopper level data, This represents the time variable for integration.

3. The air compressor control method for a power plant pneumatic system according to claim 2, characterized in that, The material level trend is calculated based on the aforementioned ash hopper level data, and expressed by the formula: ； In the formula, express The trend of material price at any given moment. Indicates the number of historical data points. Indicates the first Each historical data weight, express The ash hopper level data after real-time preprocessing. Indicates the weight of trend analysis. Represents the time constant. This represents the rate of change of the pre-processed ash hopper level data with respect to time.

4. The air compressor control method for a power plant pneumatic system according to claim 1, characterized in that, Based on the air compressor operating vector, a recurrent neural network is used to obtain the air compressor stability score. The specific steps are as follows: An air compressor operation vector is constructed based on the aforementioned operational data; The operating data includes the air compressor outlet pressure, air compressor operating current, and air compressor exhaust temperature. The air compressor operating vector is expressed by the formula: ； In the formula, express The air compressor's operating vector at any given time. express The air compressor outlet pressure at any given time. express The operating current of the air compressor at any given time. express The air compressor exhaust temperature at any given time. This indicates the reference value for the air compressor outlet pressure. This indicates the reference value for the air compressor's operating current. This indicates the reference value for the air compressor's exhaust temperature; The air compressor operating vector is input into a recurrent neural network, which outputs an air compressor stability score, expressed by the formula: ； ； In the formula, express The hidden state vector at time step 1. This represents the hyperbolic tangent activation function. This represents the weight matrix input to the hidden layer. This represents the weight matrix from hidden layer to hidden layer. express The hidden state vector at time step 1. This represents the hidden layer bias vector. This represents the sigmoid function. This represents the weight vector from the hidden layer to the output layer. This indicates the output layer bias. express The stability score of the air compressor at any given time.

5. The air compressor control method for a power plant pneumatic system according to claim 3, characterized in that, Based on the ash hopper level data and level trend, a level trend vector is constructed. The level vector is then input into a multilayer sensor to output the predicted level. The specific steps are as follows: Based on the aforementioned ash hopper level data and level trends, a level trend vector is constructed, expressed by the formula: ； In the formula, express The material level trend vector at any given time. express The ash hopper level data after real-time preprocessing. express The ash hopper level data after real-time preprocessing. Indicates the reference height of the ash hopper material level; The material level vector is input into the multilayer sensor, expressed as a formula: ； ； In the formula, express The first hidden layer outputs at all times. This represents the weight matrix of the first hidden layer. This represents the bias vector of the first hidden layer. express The output of the second hidden layer at any given time. This represents the weight matrix of the second hidden layer. This represents the bias vector of the second hidden layer. express Predicted material level at any given time. This represents the output layer weight vector. This indicates the output layer bias.

6. The air compressor control method for a power plant pneumatic system according to claim 4 or 5, characterized in that, The predicted material level is corrected based on the air compressor stability score, expressed by the following formula: ； In the formula, express Predicted material level at any given time. express The air compressor stability rating at any given time. express Real-time material level adjustment Describes the minimum value function. Represents the maximum value function. Indicates the maximum allowable ash hopper level. Indicates the minimum allowable ash hopper level. Indicates the stability weight factor. This represents the baseline stability index.

7. The air compressor control method for a power plant pneumatic system according to claim 6, characterized in that, The initial ash conveying frequency of the air compressor is obtained based on the corrected material level and material level trend, expressed by the formula: ； In the formula, Indicates air compressor The initial gray feed frequency at time 1. This represents the material level ratio control coefficient. Indicates the reference ash feeding frequency. This represents the trend differential control coefficient. Indicates the maximum permissible ash conveying frequency. This indicates the minimum permissible ash feeding frequency.

8. The air compressor control method for a power plant pneumatic system according to claim 7, characterized in that, The corrected ash conveying frequency is obtained by correcting the initial ash conveying frequency based on the air compressor stability score, expressed by the formula: ； In the formula, Indicates air compressor The frequency of the gray feed is adjusted at any time. This represents the deviation compensation coefficient. Indicates the target ash hopper level.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the air compressor control method for a power plant pneumatic system as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the air compressor control method for a power plant pneumatic system as described in any one of claims 1 to 8.

Images