Control method and equipment of air compressor unit, storage medium and program product

Abstract

The invention provides a control method and equipment of an air compressor unit, a storage medium and a program product, and relates to the technical field of industrial automation. The method comprises the following steps: obtaining operation data of industrial equipment, and determining weighted excitation intensity of each fuzzy rule through a multi-working-condition model based on the operation data; and the weighted excitation intensity is input into the state prediction model, an operation parameter adjustment strategy of the air compressor unit is obtained, and the air compressor unit is controlled to operate according to the operation parameter adjustment strategy. According to the method, working condition boundary uncertainty is quantified through interval three-type fuzzy logic, so that a multi-working-condition model can be dynamically matched with a multi-unit start-stop combination and a load fluctuation scene, and control misalignment caused by working condition division fuzziness of a traditional model is avoided; the problems of energy consumption optimization, supply and demand balance and safe and stable operation of the air compressor unit under the complex and changeable working conditions are solved, energy consumption minimization and air supply pressure stability of the air compressor unit under the complex working conditions are achieved, and the comprehensive requirements of industrial scenes for energy efficiency and continuity are met.

Description

Technical Field

[0001] This application relates to the field of industrial automation technology, and in particular to a control method, device, storage medium and program product for an air compressor unit. Background Technology

[0002] Air compressor units are key energy-consuming equipment in the industrial sector, and their energy efficiency directly affects industrial energy conservation goals. Due to their reliable operation and high efficiency, air compressor units are widely used in industrial parks where multiple units are connected in parallel for energy supply.

[0003] However, in existing industrial scenarios, the operation of air compressor units faces complex and dynamic load demands. Traditional manual control relies on the experience of operators and is difficult to respond to load changes in real time, resulting in an imbalance between the unit's air supply and actual demand, which in turn leads to reduced production efficiency and exacerbates energy waste. Summary of the Invention

[0004] This application provides a control method, equipment, storage medium, and program product for an air compressor unit to solve the technical problem that traditional manual control relies on the operator's experience and is difficult to respond to load changes in real time, resulting in an imbalance between the unit's air supply and actual demand, which in turn leads to reduced production efficiency and increased energy waste.

[0005] In a first aspect, this application provides a control method for an air compressor unit, comprising:

[0006] Acquire operational data from industrial equipment;

[0007] Based on the operational data, the weighted excitation intensity of each fuzzy rule is determined through a multi-condition model. The multi-condition model is used to identify the operating conditions of industrial equipment, and the weighted excitation intensity is used to reflect the degree of matching between the operational data and different operating conditions.

[0008] The weighted excitation intensity is input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit, and the air compressor unit is controlled to operate according to the operating parameter adjustment strategy. The state prediction model is used to predict the operating parameters of industrial equipment under different operating conditions.

[0009] In one possible implementation, the method further includes:

[0010] A multi-condition model is constructed based on a three-type interval fuzzy logic system. The three-type interval fuzzy logic system is used to quantify the fuzzy boundaries between operating conditions under different loads. The multi-condition model includes an upper membership function and a lower membership function. The upper membership function is used to quantify the uncertainty of the upper boundary of the operating condition, and the lower membership function is used to quantify the uncertainty of the lower boundary of the operating condition.

[0011] Based on the operational data, the upper membership function and the lower membership function are updated, and the multi-condition model is updated based on the updated upper membership function and the lower membership function.

[0012] The determination of the weighted excitation intensity of each fuzzy rule based on the operational data and through a multi-condition model includes:

[0013] Based on the operational data, the weighted excitation intensity of each fuzzy rule is determined using the updated multi-condition model.

[0014] In one possible implementation, updating the upper membership function and the lower membership function based on the operational data includes:

[0015] Determine the prediction error of the operating data, wherein the prediction error is used to represent the deviation between the actual gas production and the predicted gas production corresponding to the operating data of the industrial equipment;

[0016] If the prediction error of the running data exceeds a preset error threshold, increase the parameter value of the upper membership function and decrease the parameter value of the lower membership function.

[0017] Specifically, increasing the parameter value of the upper membership function includes raising the inflection point of the upper membership function and expanding the interval width; decreasing the parameter value of the lower membership function includes lowering the inflection point of the lower membership function and compressing the interval width.

[0018] In one possible implementation, the step of inputting the weighted excitation intensity into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit includes:

[0019] Under the multidimensional constraints of the industrial equipment, the weighted excitation intensity is input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit with the goal of minimizing energy consumption.

[0020] In one possible implementation, the multidimensional constraints include safe operation constraints, supply and demand matching constraints, and operating mechanism constraints;

[0021] The safety operation constraints are used to ensure the physical boundary safety of the industrial equipment; the supply and demand matching constraints are used to maintain the balance between the output of the air compressor unit and the load demand; the operation mechanism constraints are used to constrain the start-up and shutdown frequency and operating time of the industrial equipment.

[0022] In one possible implementation, the method further includes:

[0023] Based on the weighted excitation intensity output by the multi-condition model, the start-up and shutdown candidate strategies for the air compressor unit are determined.

[0024] The step of inputting the weighted excitation intensity into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit further includes:

[0025] The weighted excitation intensity and the candidate start-stop strategies of the air compressor unit are input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit.

[0026] In one possible implementation, the start-up and shutdown candidate strategies for the air compressor unit specifically include at least one of the following:

[0027] Select a high-efficiency unit combination under high-load conditions based on the weighted excitation intensity;

[0028] Select the energy-saving unit combination under low load conditions based on the weighted excitation intensity.

[0029] Secondly, this application provides a control device for an air compressor unit, comprising:

[0030] The acquisition module is used to acquire operating data from industrial equipment.

[0031] The processing module is used to determine the weighted excitation intensity of each fuzzy rule based on the operating data and through a multi-condition model. The multi-condition model is used to identify the operating conditions of industrial equipment, and the weighted excitation intensity is used to reflect the degree of matching between the operating data and different operating conditions.

[0032] The processing module is further configured to input the weighted excitation intensity into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit, and control the air compressor unit to operate according to the operating parameter adjustment strategy. The state prediction model is used to predict the operating parameters of industrial equipment under different operating conditions.

[0033] In one possible implementation, the processing module is further configured to construct a multi-condition model based on an interval-type three-dimensional fuzzy logic system. The interval-type three-dimensional fuzzy logic system is used to quantify the fuzzy boundaries between operating conditions under different loads. The multi-condition model includes an upper membership function and a lower membership function. The upper membership function is used to quantify the uncertainty of the upper boundary of the operating condition, and the lower membership function is used to quantify the uncertainty of the lower boundary of the operating condition.

[0034] The processing module is further configured to update the upper membership function and the lower membership function based on the running data, and update the multi-condition model based on the updated upper membership function and the lower membership function.

[0035] The processing module is further configured to determine the weighted excitation intensity of each fuzzy rule based on the running data and the updated multi-condition model.

[0036] In one possible implementation, the processing module is further configured to determine the prediction error of the operating data, the prediction error representing the deviation between the actual gas production and the predicted gas production corresponding to the industrial equipment operating data.

[0037] The processing module is further configured to, when the prediction error of the running data exceeds a preset error threshold, increase the parameter value of the upper membership function and decrease the parameter value of the lower membership function.

[0038] Specifically, increasing the parameter value of the upper membership function includes raising the inflection point of the upper membership function and expanding the interval width; decreasing the parameter value of the lower membership function includes lowering the inflection point of the lower membership function and compressing the interval width.

[0039] In one possible implementation, the processing module is further configured to input the weighted excitation intensity into the state prediction model under the multidimensional constraints of the industrial equipment to obtain an operating parameter adjustment strategy for the air compressor unit with the goal of minimizing energy consumption.

[0040] In one possible implementation, the processing module is further configured to determine the start-up and shutdown candidate strategies of the air compressor unit based on the weighted excitation intensity output by the multi-condition model.

[0041] The processing module is further configured to input the weighted excitation intensity and the start-stop candidate strategies of the air compressor unit into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit.

[0042] In one possible implementation, the processing module is further configured to select a high-efficiency unit combination under high-load conditions based on the weighted excitation intensity.

[0043] The processing module is also used to select energy-saving unit combinations under low-load conditions based on the weighted excitation intensity.

[0044] Thirdly, this application provides an electronic device, comprising:

[0045] Memory, processor;

[0046] The memory stores computer-executed instructions;

[0047] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0048] Fourthly, this application provides a computer storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0049] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0050] The air compressor control method provided in this application acquires the operating data of industrial equipment; constructs a multi-condition model based on a three-type interval fuzzy logic system; updates the upper and lower membership functions based on the operating data, and updates the multi-condition model based on the updated upper and lower membership functions; determines the weighted excitation intensity of each fuzzy rule based on the operating data and the updated multi-condition model; and, under the multi-dimensional constraints of the industrial equipment, inputs the weighted excitation intensity into the state prediction model to obtain an operating parameter adjustment strategy for the air compressor unit with the goal of minimizing energy consumption, and controls the air compressor unit to operate according to the operating parameter adjustment strategy. This method quantifies the uncertainty of the working condition boundary through three types of fuzzy logic in the interval, enabling the multi-working-condition model to dynamically match the start-up and shutdown combinations of multiple units and load fluctuation scenarios. It avoids the control inaccuracies caused by the fuzzy division of working conditions in traditional models, and solves the problems of energy consumption optimization, supply and demand balance and safe and stable operation of air compressor units under complex and variable working conditions. It can quickly respond to dynamic load changes, minimize the energy consumption of air compressor units and stabilize the air supply pressure under complex working conditions, and meet the comprehensive requirements of industrial scenarios for energy efficiency and continuity. Attached Figure Description

[0051] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0052] Figure 1 Flowchart of the control method for the air compressor unit provided in this application Figure 1 ;

[0053] Figure 2 Flowchart of the control method for the air compressor unit provided in this application Figure 2 ;

[0054] Figure 3 A schematic diagram of the control device for the air compressor unit provided in this application;

[0055] Figure 4 This is a schematic diagram of the structure of the electronic device provided in this application.

[0056] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0057] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0059] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0060] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0061] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0062] First, let me explain the terms used in this application:

[0063] Interval Type 3 Fuzzy Logic System: This is a higher-order extension of fuzzy logic systems, belonging to the category of uncertain fuzzy systems. It is based on interval type 3 fuzzy sets and processes complex uncertain information through fuzzification, rule-based reasoning, and defuzzification. Its core feature is that the membership degree of the fuzzy set itself is an interval value (rather than a precise value or a single-point / interval membership degree of type 1 / type 2 fuzzy sets), which can more accurately characterize multi-level and high-dimensional uncertainties (such as measurement noise, fuzziness of expert knowledge, and fluctuations in system parameters).

[0064] Neural networks are machine learning models that mimic the connection structure of neurons in the biological brain. They consist of artificial neurons (nodes) connected by weights in the input layer, hidden layer, and output layer. They can learn complex nonlinear mapping relationships through data training and are the core foundation of deep learning.

[0065] Regression analysis is a statistical modeling method used to explore the quantitative relationship between independent variables (explanatory variables) and dependent variables (response variables). Its core is to construct a mapping function from independent variables to dependent variables, so as to achieve prediction of dependent variables or quantitative analysis of the influence of independent variables.

[0066] Mechanism analysis is an analytical method that starts from the essential laws and causal relationships within a system, and uses theoretical deduction and principles from disciplines such as physics, chemistry, and biology to reveal the internal mechanisms that produce system behavior or phenomena, thereby constructing a deterministic model.

[0067] Q-learning algorithm: It is a model-free reinforcement learning algorithm that learns the value of "state-action" pairs (Q-value, i.e. the cumulative expected reward obtained after performing an action in a certain state) to guide the agent to choose the optimal action in the Markov decision process and maximize the long-term benefits of interacting with the environment.

[0068] Air compressor units are indispensable core equipment in industrial production. Their main function is to provide a stable supply of compressed air that meets the pressure requirements of the production line through the parallel operation of multiple air compressors. The energy efficiency level of air compressor units directly affects industrial energy conservation goals. Currently, due to their reliable operation and high efficiency, air compressor units are widely used in multi-unit parallel power supply scenarios in industrial parks.

[0069] In existing technologies, the operation of air compressors in industrial settings faces complex and dynamic load demands: for example, factors such as production plan adjustments, raw material composition fluctuations, and changes in equipment start-up and shutdown cycles can cause compressed air demand to fluctuate periodically, intermittently, or even suddenly.

[0070] Therefore, air compressor units need to dynamically adjust operating parameters (such as speed, load distribution, start-stop strategy, etc.) under a wide range of changing operating conditions (such as high load operation, low load energy-saving mode, unit start-stop combination, etc.) in order to achieve stable air supply pressure, minimize energy consumption and ensure safe system operation.

[0071] However, traditional manual control relies on the operator's experience and is difficult to respond to load changes in real time. This can easily lead to "oversupply" (energy wasted by air venting) or "undersupply" (affecting production progress), resulting in reduced production efficiency and exacerbating energy waste. Furthermore, when multiple units are controlled in coordination, problems such as low efficiency and a surge in energy consumption are likely to occur.

[0072] In addition, the operation of air compressor units involves complex equipment coupling relationships (such as start-stop interlocks between units and load distribution constraints) and safety boundaries (such as avoiding surge and overload), which further increases the difficulty of control.

[0073] Therefore, there is an urgent need for an intelligent control method that can adapt to multiple operating conditions and has high-precision dynamic response capabilities to solve the problem of energy efficiency optimization and stable operation of air compressor units in complex industrial scenarios.

[0074] To address the aforementioned issues, this application provides a control method for air compressor units. Based on historical industrial data and equipment mechanisms, it quantifies the uncertainty of operating condition boundaries using three types of fuzzy logic, and optimizes the control strategy of the air compressor unit using a pre-trained model combined with fuzzy reinforcement learning, thereby achieving dynamic load tracking and multi-unit collaborative control. This method quantifies the uncertainty of operating condition boundaries using three types of fuzzy logic within an interval, enabling the model to dynamically match start-stop combinations of multiple units and load fluctuation scenarios. This avoids control inaccuracies caused by fuzzy operating condition divisions in traditional models, solving the problems of energy consumption optimization, supply-demand balance, and safe and stable operation of air compressor units under complex and variable operating conditions.

[0075] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0076] Figure 1 A flowchart illustrating the control method for the air compressor unit provided in the embodiments of this application. Figure 1 The executing entity in this embodiment can be, for example, an industrial automation system equipped with multi-condition models and state prediction models. For example... Figure 1 As shown, the control method for the air compressor unit provided in this embodiment includes:

[0077] S101: Acquire operating data of industrial equipment.

[0078] Among them, operational data is a set of dynamic parameters generated by industrial equipment during operation, used to describe the real-time status of the equipment.

[0079] Understandably, industrial equipment refers to a collection of equipment in an industrial setting that requires multi-condition control, such as air compressor units and production line equipment. Operational data describes the real-time status of industrial equipment in the current industrial setting, and this operational data includes, for example, air production, unit start-up and shutdown status, load demand, and pressure values.

[0080] In this application embodiment, under the control scenario of the air compressor unit, industrial equipment refers to the air compressor unit itself, as well as the supporting equipment (subordinate and related equipment) that form a complete air supply system with the air compressor unit and need to participate in the control in a coordinated manner. That is to say, the industrial equipment includes a set of equipment that directly participates in the operation control and operating condition adjustment of the air compressor unit. This application does not impose special restrictions on the operating data.

[0081] For example, the industrial equipment for data acquisition includes: for air compressor units and supporting air supply systems, specifically including: 2 screw air compressor bodies (unit 1, unit 2), 1 refrigerated dryer, 1 vertical air tank, and terminal air pressure sensor; the operating data acquired includes: "Air compressor body 1 - operating status: loaded operation, exhaust pressure: 0.75MPa, motor operating power: 185kW, lubricating oil temperature: 78℃", "Air compressor body 2 - operating status: unloaded standby, exhaust pressure: 0.72MPa", "Refrigerated dryer - operating status: normal operation, inlet air temperature: 32℃", "Air tank - tank pressure: 0.73MPa", "Terminal air sensor - real-time air pressure at the air consumption end: 0.68MPa", "Air compressor unit and supporting air supply system - real-time air production: 28 m³ / min, current load demand (air consumption end): 30 m³ / min".

[0082] S102: Based on operational data, determine the weighted excitation intensity of each fuzzy rule through a multi-condition model.

[0083] Among them, the multi-condition model is used to identify the operating conditions of industrial equipment, and the weighted excitation intensity is used to reflect the degree of matching between the operating data and different operating conditions.

[0084] The currently acquired operating data is input into the multi-condition model, and the operating data is mapped to different conditions (such as high load, low load, and start-stop combination) through fuzzy rules. The weighted excitation intensity of each fuzzy rule is calculated to reflect the degree of matching between the data and the operating conditions.

[0085] In this embodiment, the multi-condition model is a mathematical model constructed for different operating conditions (such as high load, low load, start-stop combination, etc.) of industrial equipment (such as air compressor units). It integrates fuzzy logic rules, operating condition feature parameters and matching algorithms, and can identify the current operating condition category of the equipment based on the input real-time operating data, and quantify the correlation between the data and each operating condition. Specifically, the multi-condition model maps unstructured operating data to a structured operating condition classification system through preset fuzzy rules, thereby achieving accurate identification of the operating conditions of industrial equipment.

[0086] The multi-condition model is built on a fuzzy logic system. Fuzzy rules are the core reasoning units in the fuzzy logic system. They are constructed in the form of "IF-THEN" to map the fuzzy features of industrial equipment operation data (such as "high gas production" and "moderate pressure") to specific operating condition categories (such as high load and low load). The "THEN" conclusion of each fuzzy rule corresponds to an operating condition of the industrial equipment (such as high load condition, low load condition, start-stop transition condition, etc.). The "IF" precondition of the rule is the feature set of the operating data under that condition (such as "high gas production, high exhaust pressure, and high motor power" corresponding to the high load condition).

[0087] Fuzzy rules correspond one-to-one (or many-to-one) to different operating conditions. That is, the conclusion of each fuzzy rule in the multi-condition model directly points to the corresponding specific operating condition. The fuzzy rule is a logical description of the characteristics of different operating conditions. There is a clear mapping relationship between the fuzzy rule and the operating condition. In other words, fuzzy rules establish a mapping relationship between operating data and operating conditions. For example, "gas production greater than 80%" is a high-load condition, and "gas production less than 30%" is a low-load condition.

[0088] In addition, since the operating parameters of industrial equipment (such as gas production) often fluctuate due to changes in gas demand, fuzzy rules allow parameters to match within a range, avoiding the misjudgment of "jump" in traditional threshold rules (such as when gas production increases from 29 m³ / min to 31 m³ / min, traditional rules directly jump from "medium load" to "high load", while fuzzy rules can achieve a smooth transition).

[0089] For example, if the fuzzy rules in the current multi-condition model include: "Rule 1: IF gas production ∈ high gas production AND exhaust pressure ∈ high pressure AND motor power ∈ high power, THEN condition = high load, that is, Rule 1 corresponds to high load condition", "Rule 2: IF gas production ∈ low gas production AND exhaust pressure ∈ low pressure AND motor power ∈ low power, THEN condition = low load, that is, Rule 2 corresponds to low load condition", "Rule 3: IF operating status ∈ mixed mode AND gas tank pressure ∈ fluctuation range AND gas consumption pressure ∈ low demand, THEN condition = start-stop transition, that is, Rule 3 corresponds to start-stop transition condition"; the currently acquired operating data is input into the multi-condition model, and the output of the multi-condition model is determined as the weighted excitation intensity of each fuzzy rule. The resulting weighted excitation intensity of each fuzzy rule is: "High load condition -0.72, low load condition -0, start-stop transition condition -0.82".

[0090] S103: Input the weighted excitation intensity into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit, and control the air compressor unit to operate according to the operating parameter adjustment strategy.

[0091] Among them, the state prediction model is used to predict the operating parameters of industrial equipment under different operating conditions.

[0092] In this embodiment, the state prediction model is a decision model built based on machine learning (such as neural networks, regression analysis) or mechanism analysis. The input is the weighted excitation intensity of each fuzzy rule (reflecting the matching degree of the current working condition), and the output is the operating parameter adjustment strategy of the air compressor unit. The state prediction model can predict the operating state of the equipment under different parameter adjustment schemes (such as energy consumption, stability, and air supply efficiency) according to the current working condition characteristics, and select the optimal adjustment strategy to achieve precise control of the air compressor unit.

[0093] The operating parameter adjustment strategy refers to the specific parameter adjustment scheme formulated for the air compressor unit and its supporting equipment. It includes operations such as unit start-up and shutdown control, speed regulation, load distribution, and linkage of supporting equipment. By implementing this operating parameter adjustment strategy, the operating efficiency of the equipment can be optimized, the overall energy consumption can be reduced, and the stability of the air supply can be ensured (such as "maintaining unit 1 under load, unit 2 in standby mode, and increasing the dryer speed by 10%").

[0094] For example, the weighted excitation intensities of the fuzzy rules output by the multi-condition model are as follows: 0.72 for high load condition, 0 for low load condition, and 0.82 for start-stop transition condition. The condition with the highest current matching degree is the "start-stop transition condition." In this case, it is necessary to prioritize maintaining the current operating state of the air compressor unit and fine-tune the parameters of the supporting equipment to avoid pressure fluctuations caused by frequent start-stops. Based on this, the state prediction model generates the currently available operating parameter adjustment strategy, which includes: "Maintaining unit 1 under load operation (maintaining 0.75MPa exhaust pressure and 185kW operating power)..." Group 2 remains in unloaded standby mode and will not be started for the time being (to avoid new unit start-up and shutdown disturbances to the system pressure); the operating speed of the refrigerated dryer is increased by 10% (from the current reference speed to 1100 r / min), so that the inlet air temperature drops from 32℃ to 28℃ to ensure the dryness of the compressed air, while matching the current air supply flow; the loading trigger threshold of Unit 2 is increased from 0.70MPa to 0.78MPa, that is, Unit 2 will automatically load only when the air tank pressure is lower than 0.78MPa, further reducing unnecessary start-up and shutdown operations, and the operation of the air compressor unit is controlled according to this operating parameter adjustment strategy.

[0095] The air compressor control method provided in this embodiment acquires the operating data of industrial equipment and, based on this data, determines the weighted excitation intensity of each fuzzy rule through a multi-condition model. The weighted excitation intensity is then input into a state prediction model to obtain the air compressor's operating parameter adjustment strategy, and the air compressor is controlled to operate according to this strategy. This method quantifies the uncertainty of the operating condition boundary through interval-type three-dimensional fuzzy logic, enabling the multi-condition model to dynamically match the start-stop combinations of multiple units and load fluctuation scenarios. This avoids the control inaccuracies caused by the fuzzy division of operating conditions in traditional models, solving the problems of energy consumption optimization, supply-demand balance, and safe and stable operation of air compressors under complex and variable operating conditions. It achieves energy minimization and stable air supply pressure under complex operating conditions, meeting the comprehensive requirements of industrial scenarios for energy efficiency and continuity.

[0096] Figure 2 A flowchart illustrating the control method for the air compressor unit provided in the embodiments of this application. Figure 2 .like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, the control method of the air compressor unit is described in detail, and the method includes:

[0097] S201: Obtain operating data of industrial equipment.

[0098] Steps S201-S202 are similar to steps S101-S102 above, and will not be repeated here.

[0099] S202: Constructing a multi-condition model based on a three-type interval fuzzy logic system.

[0100] S203: Based on the running data, update the upper and lower membership functions, and update the multi-condition model based on the updated upper and lower membership functions.

[0101] Among them, the interval three-type fuzzy logic system is used to quantify the fuzzy boundaries between operating conditions under different loads; the multi-condition model includes an upper membership function and a lower membership function. The upper membership function is used to quantify the uncertainty of the upper boundary of the operating condition, and the lower membership function is used to quantify the uncertainty of the lower boundary of the operating condition.

[0102] Understandably, in the multi-condition model constructed by the interval three-type fuzzy logic system, the fuzzy rule base is the core component of the multi-condition model. The multi-condition model is a complete system that integrates the fuzzy rule base and combines real-time condition data to complete inference and decision-making. The fuzzy rule base defines the decision logic under different conditions. The multi-condition model realizes the adaptation and decision-making of complex dynamic conditions by calling, matching, and weighting the fuzzy rules in the fuzzy rule base.

[0103] The fuzzy rules in this multi-condition model together constitute a fuzzy rule library, which covers all typical operating conditions of the industrial equipment. This ensures that after any real-time operating data is input, the most suitable operating condition (i.e. the operating condition corresponding to the rule with the highest weighted excitation intensity) can be found by matching the corresponding fuzzy rules.

[0104] In this embodiment, membership degree is a core concept in fuzzy logic, used to quantify the degree to which a specific element (such as the operating parameter value of industrial equipment) belongs to a certain fuzzy subset (such as "high gas production" or "high pressure"), and its value range is [0,1]. Among them, a value of 1 indicates that the element completely belongs to the fuzzy subset (such as the gas production of 30m³ / min completely belonging to "high gas production"); a value of 0 indicates that the element does not belong to the fuzzy subset at all (such as the gas production of 10m³ / min not belonging to "high gas production" at all); a value between 0 and 1 indicates that the element partially belongs to the fuzzy subset (such as the degree to which the gas production of 28m³ / min belongs to "high gas production" is 0.6). Membership degree uses continuous numerical values ​​to describe the degree of association between the element (the operating parameter value of industrial equipment) and the fuzzy concept, and is the key to the realization of fuzzy rule matching of working conditions.

[0105] Membership degrees are typically calculated using membership functions, such as the triangular, trapezoidal, and Gaussian functions. This application does not impose any special restrictions on membership degrees.

[0106] For example, in the preset fuzzy subset of "high gas production" corresponding to a gas production range of 25~35 m³ / min, the membership degree is calculated using a triangular membership function; if the gas production is 25 m³ / min, the membership degree is 0 (lower limit of the interval, not belonging at all); if the gas production is 30 m³ / min, the membership degree is 1 (midpoint of the interval, completely belonging); if the gas production is 35 m³ / min, the membership degree is 0 (upper limit of the interval, not belonging at all).

[0107] The upper and lower membership functions are used to define the fuzzy set membership intervals corresponding to each operating condition. They are function pairs used to describe the uncertainty of the operating condition boundaries, representing the upper and lower bounds of the membership degree, respectively. They reflect changes in the operating condition through parameter adjustments. In other words, the upper membership function represents the maximum probability that the operating parameter value belongs to a fuzzy subset, reflecting the upper bound of the membership degree; the lower membership function represents the minimum probability that the operating parameter value belongs to a fuzzy subset, reflecting the lower bound of the membership degree. For example, the upper membership function describes the upper boundary of the operating condition as the upper limit of gas production under high load conditions, and the lower membership function describes the lower boundary of the operating condition as the lower limit of gas production under low load conditions.

[0108] A multi-condition model is constructed based on the interval three-type fuzzy logic system. The upper and lower membership functions of the multi-condition model are updated in combination with the currently acquired operating data. The multi-condition model is then updated based on the updated upper and lower membership functions.

[0109] For example, multi-condition modeling of air compressor groups based on interval three-type fuzzy identification can be carried out. Specifically, it can combine industrial historical data and equipment mechanism, and use interval three-type fuzzy logic system to construct multi-condition model to solve the problem of uncertainty in the boundary of operating conditions.

[0110] The fuzzy rules are defined as follows:

[0111]

[0112]

[0113] in, For the first The air output of the air compressor. Indicates the air compressor status (0 indicates running, 1 indicates stopped, 2 indicates started). It is a three-type fuzzy set of intervals (describing the fuzzy boundary of the working condition). , , These are the operating parameters identified through the output error model.

[0114] In some embodiments, updating the upper membership function and the lower membership function based on runtime data includes:

[0115] Determine the prediction error of the running data; if the prediction error of the running data exceeds the preset error threshold, increase the parameter value of the upper membership function and decrease the parameter value of the lower membership function.

[0116] The prediction error is used to represent the deviation between the actual gas production and the predicted gas production corresponding to the industrial equipment operation data; the preset error threshold is used to determine the error limit of whether the multi-condition model needs to be updated, and the preset error threshold can be, for example, 3%.

[0117] Increasing the parameter value of the upper membership function includes raising the inflection point of the upper membership function and widening the interval width; decreasing the parameter value of the lower membership function includes lowering the inflection point of the lower membership function and compressing the interval width.

[0118] Understandably, prediction error is the difference between actual operating data and model prediction values, used to measure the accuracy of the corresponding prediction model. The model corresponding to this prediction error is a dedicated prediction model used to predict the operating parameters of industrial equipment (such as gas production), or it can be the parameter prediction branch in the state prediction model (which can predict gas production).

[0119] Specifically, the model corresponding to this prediction error is a parametric prediction model. This parametric prediction model predicts key operating parameters (such as gas production) of industrial equipment based on historical operating data or real-time operating conditions. For example, this parametric prediction model can be a gas production prediction model based on time series or machine learning. This application does not impose any special restrictions on the parametric prediction model.

[0120] For example, historical operating data of industrial equipment and current operating characteristics (such as pressure and power) are input into the parameter prediction model to obtain predicted values ​​of key parameters such as the current air compressor unit's gas production. The deviation between the actual collected gas production (the true value in the operating data) and the predicted value output by the model is calculated. If the actual gas production is 28 m³ / min and the model's predicted value is 25 m³ / min, then the prediction error is 3 m³ / min.

[0121] For example, during the multi-condition model update phase, the industrial automation system calculates the prediction error of the current operating data (such as the difference between the actual value of gas production and the model's predicted value). If the error exceeds a preset threshold (such as 3%), the parameter adjustment mechanism of the membership function is triggered. Specifically, the industrial automation system increases the parameter value of the upper membership function of the multi-condition model (such as expanding the interval width and raising the inflection point position) to enhance the model's adaptability to high-load conditions, while decreasing the parameter value of the lower membership function (such as compressing the interval width and lowering the inflection point position) to more strictly define low-load conditions. In this way, by dynamically adjusting the parameters of the membership function, the multi-condition model can adapt to changes in operating data in real time, thereby improving the model's accuracy and the flexibility of condition division.

[0122] In some embodiments, increasing the parameter value of the upper membership function enhances its fuzzy descriptive capability by adjusting the inflection point position or interval width; decreasing the parameter value of the lower membership function compresses its fuzzy descriptive range by adjusting the inflection point position or interval width.

[0123] Understandably, the inflection point is the key point where the slope of the membership function curve changes, and it is used to define the fuzziness of the working condition boundary; the interval width is the numerical range covered by the fuzzy boundary in the membership function, and it is used to describe the degree of fuzziness of the working condition.

[0124] For example, the inflection point of the upper membership function can be raised and the interval width expanded to cover higher load conditions. Specifically, the inflection point of the upper membership function can be adjusted from 80% to 85% of the gas production to adapt to higher load conditions. Conversely, the inflection point of the lower membership function can be lowered and the interval width compressed to more strictly define low load conditions. Specifically, the interval width of the lower membership function can be compressed from 5% to 3% to more strictly define low load conditions.

[0125] S204: Based on operational data, determine the weighted excitation intensity of each fuzzy rule using the updated multi-condition model.

[0126] The currently acquired operating data is input into the updated multi-condition model. The operating data is then mapped to different operating conditions (such as high load, low load, and start-stop combination) through fuzzy rules. The weighted excitation intensity of each fuzzy rule is calculated to reflect the degree of matching between the data and the operating conditions.

[0127] For example, the currently acquired real-time operating data is substituted into the membership function (triangular membership) to calculate the membership degree of the fuzzy subset corresponding to each parameter. Specifically, this includes: "The membership degree of real-time gas production of 28 m³ / min (high gas production range) is (28-25) / (30-25)=0.6", "The membership degree of exhaust pressure of air compressor 1 of 0.75 MPa (high pressure range) is 1", "The membership degree of motor power of air compressor 1 of 185 kW (high power range) is (200-185) / (200-175)=0.6", "The membership degree of operating status (1 unit loaded and 1 unit in standby) is..." The membership degree is 1 (fully matched mixed mode), the membership degree of the gas tank pressure of 0.73MPa (fluctuation range) is (0.75-0.73) / (0.75-0.725)=0.8, and the membership degree of the gas consumption pressure of 0.68MPa (low demand range) is (0.68-0.65) / (0.7-0.65)=0.6; and the weight information in rule 1 is: gas production -0.4, exhaust pressure -0.3, motor power -0.3; the weight information in rule 3 is: operating status -0.4, gas tank pressure -0.3, gas consumption pressure -0.3.

[0128] Based on this, the weighted excitation intensity of Rule 1 (high load condition) is the weighted sum of the membership degree of gas production, exhaust pressure, and motor power, which is 0.72; in Rule 2 (low load condition), none of the parameters fall into the corresponding fuzzy subset of low load (gas production 28m³ / min > 15m³ / min, exhaust pressure 0.75MPa > 0.6MPa, motor power 185kW > 100kW), and all have a membership degree of 0, so the weighted excitation intensity is 0; the weighted excitation intensity of Rule 3 (start-stop transition condition) is the weighted sum of the membership degree of operating status, gas tank pressure, and gas consumption end pressure, which is 0.82.

[0129] Therefore, the weighted excitation intensity of each fuzzy rule is: -0.72 for high load condition, -0 for low load condition, and -0.82 for start-stop transition condition. This indicates that the current air compressor unit operating data has the highest matching degree with the start-stop transition condition, providing a quantitative basis for subsequent control decisions (such as maintaining the standby state of unit 2 and monitoring changes in the gas consumption load).

[0130] In some embodiments, after determining the weighted excitation strength of each fuzzy rule, the fuzzy rules are weighted and summed, and the operating condition of the current industrial equipment is determined based on the resulting sum.

[0131] The output value of the multi-condition model is an understandable weighted value based on the weighted excitation intensity of each fuzzy rule, which is also a weighted value of the degree of matching of each operating condition. This weighted value integrates the matching situation of all rules and can more accurately reflect the current operating condition (mainly start-stop transition, supplemented by high load), avoiding the one-sidedness of single rule judgment.

[0132] For example, the output of the multi-condition model is a weighted sum of the outputs of each fuzzy rule. The weights are calculated by the membership function (considering the upper and lower boundary means) to improve the adaptability of the conditions. The specific calculation formula is as follows:

[0133]

[0134]

[0135] in, For the intensity of rule incentives, This is the membership function.

[0136] S205: Under the multidimensional constraints of industrial equipment, the weighted excitation intensity is input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit with the goal of minimizing energy consumption.

[0137] S206: Control the air compressor unit to operate according to the operating parameter adjustment strategy.

[0138] Among them, the operating parameter adjustment strategy includes optimization schemes for unit combination, load allocation, controller parameters, etc.; for example, under low load conditions, the operating parameter adjustment strategy may include shutting down some units to reduce energy consumption.

[0139] In this embodiment of the application, the state prediction model is a prediction model built based on a fuzzy reinforcement learning strategy. The model guides the reinforcement learning process through fuzzy rules (such as expert experience) to generate an operating parameter adjustment strategy (such as unit combination and load allocation) with the goal of minimizing energy consumption.

[0140] Under the current multidimensional constraints of the industrial equipment, the weighted excitation intensity is input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit with the goal of minimizing energy consumption, and the air compressor unit is controlled to operate according to the operating parameter adjustment strategy.

[0141] In some embodiments, the weighted values ​​of the weighted excitation intensities corresponding to different operating conditions are calculated to determine the operating condition that best matches the current operating data, and the weighted values ​​of the weighted excitation intensities corresponding to the operating condition are input into the state prediction model to generate an operating parameter adjustment strategy.

[0142] In some embodiments, multidimensional constraints include safe operation constraints, supply and demand matching constraints, and operating mechanism constraints;

[0143] Among them, safe operation constraints are used to ensure the physical boundary safety of industrial equipment; supply and demand matching constraints are used to maintain the balance between the output of air compressor units and load demand; and operating mechanism constraints are used to constrain the start-up and shutdown frequency and operating duration of industrial equipment.

[0144] Understandably, safety operation constraints can be, for example, controlling the speed and gas output of the air compressor unit within safe boundaries; supply and demand matching constraints limit the deviation between the predicted output and the demand to an allowable range; and operating mechanism constraints prevent frequent start-ups and shutdowns of the air compressor unit and ensure that the operating time of each unit is within a defined range.

[0145] For example, after obtaining the weighted excitation intensity output by the multi-condition model, the industrial automation system uses the weighted excitation intensity output by the model as input and passes it to the fuzzy reinforcement learning strategy module, i.e. the state prediction model. The model guides the reinforcement learning process through fuzzy rules (such as expert experience) to generate operating parameter adjustment strategies (such as unit combination and load allocation) with the goal of minimizing energy consumption.

[0146] Specifically, with the goal of minimizing energy consumption, and in conjunction with constraints, reinforcement learning is guided by fuzzy rules to output the optimal unit combination, load, and controller parameters.

[0147] In reinforcement learning, the objective function is the sum of energy cost and specific power (SP), and the weight coefficients are... Adjustments based on station building requirements For the single-unit energy efficiency model of the air compressor, the specific objective function is as follows:

[0148]

[0149] For example, under low-load conditions, fuzzy rules will prioritize energy-saving unit combinations and optimize load allocation parameters through Q-learning algorithms. By combining the uncertainty handling capabilities of fuzzy logic with the strategy optimization capabilities of reinforcement learning, the control strategy can adapt to the current operating conditions and minimize energy consumption.

[0150] The decision-making logic of the state prediction model in this application embodiment is based on preset rules and machine learning models.

[0151] Specifically, the preset core decision rules may include, for example: if the excitation intensity of the "start-stop transition condition" is not less than 0.8, then the current unit operation status should be maintained first, and the parameters of the supporting equipment should be fine-tuned to avoid pressure fluctuations caused by frequent start-stops; if the excitation intensity of the "high load condition" is not less than 0.8, then the standby unit (unit 2) should be started, and 20% of the load should be allocated to improve the gas supply capacity; if the excitation intensity of the "low load condition" is not less than 0.8, then the speed of unit 1 should be reduced and the dryer should be switched to energy-saving mode.

[0152] The optimization using machine learning models includes: the machine learning model is trained based on historical data, and after inputting the excitation intensity, it predicts the energy consumption value under different adjustment strategies (such as the energy consumption of "maintaining unit 1 load and increasing dryer speed by 10%" is 180kW / h, and the energy consumption of "starting unit 2" is 220kW / h), and selects the scheme with the lowest energy consumption that meets the gas supply demand.

[0153] For example, after obtaining the operating parameter adjustment strategy output by the state prediction model, the adjustment strategy is converted into control signals that the equipment can execute and sent to each industrial device through the industrial automation system. For example, a "maintain current loading state" command is sent to the controller of unit 1; a "frequency increase of 10Hz (corresponding to a 10% speed increase)" command is sent to the dryer frequency converter; and a "keep standby, pressure threshold set to 0.78MPa (automatic loading when this value is reached)" command is sent to the controller of unit 2.

[0154] After the control command is executed, real-time operating data of industrial equipment (such as dryer inlet air temperature and air tank pressure) is collected. When the parameters deviate from the expected values ​​(such as air tank pressure dropping below 0.7 MPa), the state prediction model is re-inputted with the updated weighted excitation intensity to generate a new adjustment strategy.

[0155] In other embodiments, the start-up and shutdown candidate strategies of the air compressor unit can be determined based on the weighted excitation intensity output by the multi-condition model; the weighted excitation intensity and the start-up and shutdown candidate strategies of the air compressor unit are input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit.

[0156] By using the weighted excitation intensity output from the multi-condition model, a candidate strategy for unit start-up and shutdown combinations matching the current condition is generated. The weighted excitation intensity and the candidate start-up and shutdown strategies of the air compressor are then input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor.

[0157] For example, when the operating condition corresponding to the incentive intensity is "high-efficiency operation", the candidate strategy may include "three high-efficiency units in parallel"; when the operating condition corresponding to the incentive intensity is "inefficient operation", the candidate strategy may include "one high-efficiency unit + one inefficient unit in parallel". In this way, the operating condition and unit combination are matched by a fuzzy rule base to provide candidate solutions for subsequent strategy optimization.

[0158] In this embodiment, the start-stop candidate strategy of the air compressor unit can be converted into the constraint conditions of the state prediction model, thereby achieving more precise control of the air compressor unit.

[0159] In some embodiments, the start-up and shutdown candidate strategies for the air compressor unit specifically include at least one of the following:

[0160] Select high-efficiency unit combinations under high-load conditions based on weighted excitation intensity;

[0161] Select the energy-saving unit combination under low load conditions based on the weighted excitation intensity.

[0162] Understandably, high-load operating conditions refer to scenarios where industrial equipment operates under high loads. For example, during peak production periods in a chemical plant, air compressor units need to meet an air supply demand of 1200 m³ / min.

[0163] Energy-saving unit combination refers to the strategy of prioritizing the use of low-energy-consumption units under low-load conditions; for example, when the air compressor is running at low load, "one high-efficiency unit + one low-efficiency unit in parallel" is used to reduce energy consumption.

[0164] Understandably, under high-load conditions, efficient unit combinations can quickly respond to demand; under low-load conditions, energy-saving combinations can reduce unit energy consumption, thereby improving the scenario adaptability of candidate strategies and providing more accurate input for subsequent optimization.

[0165] The unit combination strategy is matched under different operating conditions by weighted incentive intensity. For example, under high load conditions, "3 high-efficiency units in parallel" is selected to maximize gas supply capacity; under low load conditions, "1 high-efficiency unit + 1 low-efficiency unit in parallel" is selected to optimize energy consumption. This process ensures that the candidate strategy is highly matched with the actual operating conditions through weight allocation of the fuzzy rule base.

[0166] The air compressor control method provided in this embodiment acquires the operating data of industrial equipment; constructs a multi-condition model based on a three-type interval fuzzy logic system; updates the upper and lower membership functions based on the operating data; and updates the multi-condition model based on the updated upper and lower membership functions; determines the weighted excitation intensity of each fuzzy rule based on the operating data and the updated multi-condition model; and, under the multi-dimensional constraints of the industrial equipment, inputs the weighted excitation intensity into the state prediction model to obtain an operating parameter adjustment strategy for the air compressor unit with the goal of minimizing energy consumption, and controls the air compressor unit to operate according to the operating parameter adjustment strategy. This method quantifies the uncertainty of the working condition boundary through three types of fuzzy logic in the interval, enabling the multi-working-condition model to dynamically match the start-up and shutdown combinations of multiple units and load fluctuation scenarios. It avoids the control inaccuracies caused by the fuzzy division of working conditions in traditional models, and solves the problems of energy consumption optimization, supply and demand balance and safe and stable operation of air compressor units under complex and variable working conditions. It can quickly respond to dynamic load changes, minimize the energy consumption of air compressor units and stabilize the air supply pressure under complex working conditions, and meet the comprehensive requirements of industrial scenarios for energy efficiency and continuity.

[0167] Figure 3 This is a schematic diagram of the control device for the air compressor unit provided in this application. Figure 3As shown, this application provides a control device for an air compressor unit. The control device 300 for the air compressor unit includes:

[0168] The acquisition module 301 is used to acquire the operating data of industrial equipment.

[0169] The processing module 302 is used to determine the weighted excitation intensity of each fuzzy rule based on the operating data and through a multi-condition model. The multi-condition model is used to identify the operating conditions of industrial equipment, and the weighted excitation intensity is used to reflect the degree of matching between the operating data and different operating conditions.

[0170] The processing module 302 is also used to input the weighted excitation intensity into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit, and control the air compressor unit to operate according to the operating parameter adjustment strategy. The state prediction model is used to predict the operating parameters of industrial equipment under different operating conditions.

[0171] In one possible implementation, the processing module 302 is further configured to construct a multi-condition model based on an interval three-type fuzzy logic system. The interval three-type fuzzy logic system is used to quantify the fuzzy boundaries between operating conditions under different loads. The multi-condition model includes an upper membership function and a lower membership function. The upper membership function is used to quantify the uncertainty of the upper boundary of the operating condition, and the lower membership function is used to quantify the uncertainty of the lower boundary of the operating condition.

[0172] The processing module 302 is also used to update the upper membership function and the lower membership function based on the running data, and to update the multi-condition model based on the updated upper membership function and the lower membership function.

[0173] The processing module 302 is also used to determine the weighted excitation intensity of each fuzzy rule based on the running data and the updated multi-condition model.

[0174] In one possible implementation, the processing module 302 is further configured to determine the prediction error of the operating data, the prediction error being used to represent the deviation between the actual gas production and the predicted gas production corresponding to the operating data of the industrial equipment.

[0175] The processing module 302 is also used to increase the parameter value of the upper membership function and decrease the parameter value of the lower membership function when the prediction error of the running data exceeds a preset error threshold.

[0176] Specifically, increasing the parameter value of the upper membership function includes raising the inflection point of the upper membership function and expanding the interval width; decreasing the parameter value of the lower membership function includes lowering the inflection point of the lower membership function and compressing the interval width.

[0177] In one possible implementation, the processing module 302 is further configured to input the weighted excitation intensity into the state prediction model under the multidimensional constraints of the industrial equipment to obtain an operating parameter adjustment strategy for the air compressor unit with the goal of minimizing energy consumption.

[0178] In one possible implementation, the processing module 302 is further configured to determine the start-up and shutdown candidate strategies for the air compressor unit based on the weighted excitation intensity output by the multi-condition model.

[0179] The processing module 302 is also used to input the weighted excitation intensity and the candidate start-stop strategies of the air compressor unit into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit.

[0180] In one possible implementation, the processing module 302 is also configured to select a high-efficiency unit combination under high load conditions based on the weighted excitation intensity.

[0181] The processing module 302 is also used to select the energy-saving unit combination under low load conditions based on the weighted excitation intensity.

[0182] The control device for the air compressor unit provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0183] Figure 4 A schematic diagram of the structure of the electronic device provided in this application. Figure 4 As shown, the electronic device 400 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device 400 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus.

[0184] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0185] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0186] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0187] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0188] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0189] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0190] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0191] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0192] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0193] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0194] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0195] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0196] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, 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 of the various embodiments of this invention. 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.

[0197] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0198] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A control method for an air compressor unit, characterized in that, include: Acquire operational data from industrial equipment; Based on the operational data, the weighted excitation intensity of each fuzzy rule is determined through a multi-condition model. The multi-condition model is used to identify the operating conditions of industrial equipment, and the weighted excitation intensity is used to reflect the degree of matching between the operational data and different operating conditions. The weighted excitation intensity is input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit, and the air compressor unit is controlled to operate according to the operating parameter adjustment strategy. The state prediction model is used to predict the operating parameters of industrial equipment under different operating conditions.

2. The method according to claim 1, characterized in that, The method further includes: A multi-condition model is constructed based on a three-type interval fuzzy logic system. The three-type interval fuzzy logic system is used to quantify the fuzzy boundaries between operating conditions under different loads. The multi-condition model includes an upper membership function and a lower membership function. The upper membership function is used to quantify the uncertainty of the upper boundary of the operating condition, and the lower membership function is used to quantify the uncertainty of the lower boundary of the operating condition. Based on the operational data, the upper membership function and the lower membership function are updated, and the multi-condition model is updated based on the updated upper membership function and the lower membership function. The determination of the weighted excitation intensity of each fuzzy rule based on the operational data and through a multi-condition model includes: Based on the operational data, the weighted excitation intensity of each fuzzy rule is determined using the updated multi-condition model.

3. The method according to claim 2, characterized in that, The step of updating the upper membership function and the lower membership function based on the running data includes: Determine the prediction error of the operating data, wherein the prediction error is used to represent the deviation between the actual gas production and the predicted gas production corresponding to the operating data of the industrial equipment; If the prediction error of the running data exceeds a preset error threshold, increase the parameter value of the upper membership function and decrease the parameter value of the lower membership function. Specifically, increasing the parameter value of the upper membership function includes raising the inflection point of the upper membership function and expanding the interval width; decreasing the parameter value of the lower membership function includes lowering the inflection point of the lower membership function and compressing the interval width.

4. The method according to claim 1, characterized in that, The step of inputting the weighted excitation intensity into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit includes: Under the multidimensional constraints of the industrial equipment, the weighted excitation intensity is input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit with the goal of minimizing energy consumption.

5. The method according to claim 4, characterized in that, The multidimensional constraints include safe operation constraints, supply and demand matching constraints, and operating mechanism constraints. The safety operation constraints are used to ensure the physical boundary safety of the industrial equipment; the supply and demand matching constraints are used to maintain the balance between the output of the air compressor unit and the load demand; the operation mechanism constraints are used to constrain the start-up and shutdown frequency and operating time of the industrial equipment.

6. The method according to claim 1, characterized in that, The method further includes: Based on the weighted excitation intensity output by the multi-condition model, the start-up and shutdown candidate strategies for the air compressor unit are determined. The step of inputting the weighted excitation intensity into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit further includes: The weighted excitation intensity and the candidate start-stop strategies of the air compressor unit are input into the state prediction model to obtain the operating parameter adjustment strategy of the air compressor unit.

7. The method according to claim 6, characterized in that, The candidate start-up and shutdown strategies for the air compressor unit specifically include at least one of the following: Select a high-efficiency unit combination under high-load conditions based on the weighted excitation intensity; Select the energy-saving unit combination under low load conditions based on the weighted excitation intensity.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images