Intelligent Coordinated Control Method for Multiple Magnetic Levitation Compressors Used in Central Heating

Abstract

This application discloses an intelligent collaborative control method and a magnetic levitation compressor system for centralized heating using multiple magnetic levitation compressors. The method includes: acquiring equipment identification information and real-time operating parameters for each magnetic levitation compressor; determining a target compressor performance model for each magnetic levitation compressor from a preset compressor performance model based on the equipment identification information, the target compressor performance model including a first energy efficiency model, a first power model, and a first heating capacity model; determining a multi-machine collaborative optimization model for the magnetic levitation compressor system based on the real-time operating parameters, the first energy efficiency model, the first power model, and the first heating capacity model; analyzing the multi-machine collaborative optimization model with the goal of minimizing total system energy consumption and based on preset constraints to obtain a target scheduling scheme; generating control commands based on the target scheduling scheme and issuing the control commands to each magnetic levitation compressor for execution.

Description

Technical Field

[0001] This application relates to the field of intelligent monitoring and control technology for magnetic levitation compressors, and in particular to an intelligent collaborative control method for multiple magnetic levitation compressors used in centralized heating, a magnetic levitation compressor system, and a computer-readable storage medium. Background Technology

[0002] In related technologies, the scheduling methods for parallel systems of multiple magnetic levitation compressors typically follow the control strategies of traditional magnetic levitation compressors, namely, using fixed threshold start / stop, even load distribution, or manually set scheduling parameters. However, this mode mainly relies on local control logic and static allocation rules, failing to consider the performance differences of different magnetic levitation compressors and their highly sensitive operating characteristics to speed and load. It is difficult to achieve dynamic optimal load distribution from a global system perspective, which can easily lead to some magnetic levitation compressors operating in the inefficient range for extended periods or excessively high total system energy consumption. This results in the inability to fully utilize the high efficiency advantages of magnetic levitation compressors and increased losses due to frequent start / stop operations, while also making it difficult to ensure the system's operational stability under dynamic load changes. Summary of the Invention

[0003] This application provides an intelligent collaborative control method for multiple magnetic levitation compressors for centralized heating, a magnetic levitation compressor system, and a computer-readable storage medium.

[0004] This application provides an intelligent collaborative control method for multiple magnetic levitation compressors used in centralized heating systems, the method comprising: Obtain the equipment identification information and real-time operating parameters of each magnetic levitation compressor; Based on the device identification information, a target compressor performance model corresponding to each magnetic levitation compressor is determined from the preset compressor performance model. The target compressor performance model includes a first energy efficiency model, a first power model, and a first heating capacity model. Based on the real-time operating parameters, the first energy efficiency model, the first power model, and the first heating capacity model, the multi-machine collaborative optimization model of the magnetic levitation compressor system is determined. With the goal of minimizing total system energy consumption and based on preset constraints, the multi-machine collaborative optimization model is analyzed to obtain the target scheduling scheme; Control commands are generated according to the target scheduling scheme, and the control commands are sent to each of the magnetic levitation compressors for execution.

[0005] Thus, by matching the compressor performance model corresponding to each magnetic levitation compressor, the differentiated efficiency characteristics of different magnetic levitation compressors under different operating conditions can be fully considered. Furthermore, by constructing and solving a multi-machine collaborative optimization model, each magnetic levitation compressor can be guided to operate within its own optimal efficiency range, effectively alleviating the technical problems of high energy consumption and low efficiency. This provides technical support for the efficient and stable operation of multi-machine parallel magnetic levitation compressor systems, improving the overall energy efficiency of the system. In some embodiments, the real-time operating condition parameters include system-side operating status data, equipment-side real-time operating condition parameters, and system real-time heat load. Obtaining the equipment identification information and real-time operating condition parameters for each magnetic levitation compressor includes: Based on the sensor system in the magnetic levitation compressor system, the equipment identification information, the system-side operating status data, and the equipment-side real-time operating condition parameters are collected. The system-side operating status data includes water supply temperature, return water temperature, and / or circulating water mass flow rate. The equipment-side real-time operating condition parameters include the input power, operating speed, guide vane opening, operating status, and / or rotor vibration amplitude of each magnetic levitation compressor. The real-time heat load of the system is calculated based on the supply water temperature, the return water temperature, and the circulating water mass flow rate.

[0006] Thus, by deploying sensor systems on both the system and equipment sides, all key operating parameters affecting scheduling decisions are collected synchronously. Based on the principle of thermal balance, the actual heat demand of users is accurately calculated, providing precise and sufficient data support for subsequent status identification, compressor performance model calculation, and optimized scheduling. Furthermore, by calculating the system's heat load in real time, matching heating capacity with user demand can be achieved, effectively avoiding user experience degradation due to insufficient heating and energy waste caused by excessive heating. Simultaneously, comprehensive equipment-side parameter collection allows for real-time monitoring of the operating status of individual magnetic levitation compressors, laying the foundation for subsequent stability assessment and refined scheduling, and improving the accuracy and timeliness of scheduling decisions.

[0007] In some embodiments, the method further includes: The system-side operating status data and the equipment-side real-time operating condition parameters are filtered to remove or correct abnormal data.

[0008] In this way, by eliminating or correcting abnormal data, the prediction deviation of compressor performance models and scheduling decision errors caused by data distortion can be reduced, thereby ensuring the stability of system operation and the effectiveness of scheduling schemes.

[0009] In some implementations, the preset compressor performance model is established in advance in the following manner: Based on the obtained historical operating parameters, a performance sample dataset of magnetic levitation compressors is generated. The historical operating parameters include the input power, flow rate, temperature and corresponding heating capacity of each magnetic levitation compressor under different operating speeds, different guide vane openings and / or different temperature conditions. The performance sample dataset of the magnetic levitation compressor is fitted with a function to establish the preset compressor performance model, wherein the preset compressor performance model includes a second energy efficiency model, a second power model, and a second heating capacity model.

[0010] Thus, based on a pre-defined compressor performance model, the heating capacity, energy efficiency ratio, and input power characteristics of each magnetic levitation compressor can be accurately characterized across the entire operating range, establishing a precise mapping relationship between operating parameters and performance indicators. Furthermore, this pre-defined compressor performance model can provide a reliable quantitative calculation basis for multi-machine collaborative optimization models, enabling load allocation to be finely designed based on the actual efficiency characteristics of the magnetic levitation compressors, achieving differentiated optimal operation for different magnetic levitation compressors.

[0011] In some implementations, the multi-machine collaborative optimization model includes an objective function, which may be the following relation: ; in, Let N be the input power of the i-th magnetic levitation compressor, and N be the total number of magnetic levitation compressors in the magnetic levitation compressor system. Let i represent the current operating state of the i-th magnetic levitation compressor. This represents the previous operating state of the i-th magnetic levitation compressor. The degree to which the i-th magnetic levitation compressor deviates from its optimal operating range. This refers to the start / stop weighting coefficient. This represents the state penalty weight coefficient.

[0012] In this way, a multi-objective weighted optimization system integrating total energy consumption, start-up and shutdown costs, and equipment operational stability can be constructed, overcoming the shortcomings of traditional single-objective optimization. Furthermore, the start-up and shutdown weight coefficient can effectively suppress the frequent start-up and shutdown behavior of the magnetic levitation compressor, reducing the additional energy consumption during startup and the mechanical impact on the equipment, thus extending the equipment's service life. Simultaneously, the state penalty weight coefficient can constrain the magnetic levitation compressor to operate within its optimal efficiency range, further improving the system's energy efficiency.

[0013] In some embodiments, the preset constraints include a first constraint, a second constraint, a third constraint, and / or a fourth constraint, wherein the first constraint indicates that the sum of the heating capacity of each magnetic levitation compressor is equal to the real-time heat load of the system; the second constraint indicates that the operating speed of each magnetic levitation compressor is between the minimum speed and the maximum speed; the third constraint indicates that the guide vane opening of each magnetic levitation compressor is between the minimum opening and the maximum opening; and the fourth constraint indicates that each magnetic levitation compressor needs to run continuously for a minimum time after startup and needs to be shut down for a minimum downtime after shutdown.

[0014] Thus, by constructing a multi-dimensional constraint system covering supply and demand matching, equipment safety, and operational stability, reasonable boundary conditions can be provided for optimization solutions.

[0015] In some implementations, the step of minimizing the total system energy consumption and analyzing the multi-machine collaborative optimization model based on preset constraints to obtain a target scheduling scheme includes: Generate candidate magnetic levitation compressor operation schemes, each candidate magnetic levitation compressor operation scheme including the operation status, operation speed and / or guide vane opening of each candidate magnetic levitation compressor; Under the preset constraints, based on the multi-machine collaborative optimization model, the input power and heating capacity of each candidate magnetic levitation compressor under each candidate magnetic levitation compressor operation scheme are calculated; Substituting the input power and the heating capacity into the multi-machine collaborative optimization model, the objective function value of each candidate magnetic levitation compressor operation scheme is calculated; The candidate magnetic levitation compressor operation scheme that minimizes the objective function value is selected as the target scheduling scheme. The target scheduling scheme includes the operating status, operating speed and / or guide vane opening of each target magnetic levitation compressor.

[0016] Thus, by generating candidate magnetic levitation compressor operation schemes and comparing the objective function values ​​calculated for each candidate scheme, the target scheduling scheme can be determined, thereby obtaining a globally approximate optimal scheduling solution and avoiding the problem of getting trapped in local optima.

[0017] In some embodiments, the step of sending the control command to each of the magnetic levitation compressors for execution includes: The control commands are sent to each of the magnetic levitation compressors using a gradual adjustment method to avoid impacting the magnetic levitation compressor system.

[0018] In this way, by using a gradual adjustment method, a smooth transition between the speed of the magnetic levitation compressor and the opening of the guide vanes can be achieved, thereby effectively avoiding drastic fluctuations in system parameters such as pressure and temperature, ensuring the stable operation of the heating system and the heating quality at the user end.

[0019] In some embodiments, the method further includes: After the control command is executed, system-side operating status data and equipment-side real-time operating condition parameters are collected. When the magnetic levitation compressor system is in operation, if the system load of the magnetic levitation compressor system changes beyond a preset threshold, or the operating status of the magnetic levitation compressor changes, or the operating cycle of the magnetic levitation compressor system reaches a preset optimization cycle, the equipment identification information and real-time operating condition parameters of each magnetic levitation compressor are obtained again. Based on the real-time operating parameters, the first energy efficiency model, the first power model, and the first heating capacity model, the multi-machine collaborative optimization model of the magnetic levitation compressor system is determined again. With the goal of minimizing total system energy consumption and based on preset constraints, the multi-machine collaborative optimization model is analyzed to obtain the target scheduling scheme; Control commands are generated again based on the target scheduling scheme, and the control commands are sent to each of the magnetic levitation compressor controllers for execution.

[0020] In this way, by constructing a closed-loop feedback optimization system, it is possible to respond in real time to system load fluctuations, equipment status changes and periodic operating requirements, ensuring that the system always maintains its optimal operating state during the operating cycle.

[0021] This application provides a magnetic levitation compressor system, which includes a central dispatch controller, multiple magnetic levitation compressors, and a sensor system. The central dispatch controller is communicatively connected to multiple magnetic levitation compressors and the sensor system, respectively. The sensor system is configured to collect system-side operating status data and equipment-side real-time operating condition parameters, and feed the data back to the central dispatch controller. The system-side operating status data includes water supply temperature, return water temperature and / or circulating water mass flow rate, and the equipment-side real-time operating condition parameters include the input power, operating speed, guide vane opening, operating status and / or rotor vibration amplitude of each magnetic levitation compressor. The central dispatch controller is configured to execute the aforementioned intelligent collaborative control method for multiple magnetic levitation compressors used for centralized heating.

[0022] In this way, by matching the compressor performance model corresponding to each magnetic levitation compressor, the magnetic levitation compressor system can fully consider the differentiated efficiency characteristics of different magnetic levitation compressors under different operating conditions. Furthermore, by constructing and solving a multi-machine collaborative optimization model, the magnetic levitation compressor system can guide each magnetic levitation compressor to operate within its own optimal efficiency range, effectively alleviating the technical problems of high energy consumption and low efficiency. This provides technical support for the efficient and stable operation of the multi-machine parallel magnetic levitation compressor system, improving the overall energy efficiency of the system.

[0023] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described above.

[0024] Additional aspects and advantages of embodiments of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of this application. Attached Figure Description

[0025] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, wherein: Figure 1 This is one of the flowcharts illustrating the intelligent collaborative control method of certain embodiments of this application; Figure 2 This is a second flowchart illustrating the intelligent collaborative control method according to certain embodiments of this application; Figure 3 This is the third flowchart illustrating the intelligent collaborative control method of certain embodiments of this application; Figure 4 This is the fourth flowchart of an intelligent collaborative control method according to certain embodiments of this application; Figure 5 This is the fifth flowchart illustrating the intelligent collaborative control method of certain embodiments of this application; Figure 6 This is the sixth flowchart illustrating the intelligent collaborative control method of certain embodiments of this application; Figure 7 This is the seventh flowchart of an intelligent collaborative control method according to certain embodiments of this application; Figure 8 This is a structural schematic diagram of a magnetic levitation compressor system according to certain embodiments of this application. Detailed Implementation

[0026] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of this application, and should not be construed as limiting the embodiments of this application.

[0027] In related technologies, in high-load application scenarios such as district heating systems, large commercial complex heating systems, and industrial waste heat recovery, a system architecture with multiple magnetic levitation compressors operating in parallel is typically adopted to meet the large-scale and dynamically changing heat load demands. However, the current scheduling methods for multiple magnetic levitation compressor parallel systems generally still follow the control strategies of traditional fixed-frequency or variable-frequency magnetic levitation compressors, namely, using fixed threshold start / stop, even load distribution, or manually set scheduling parameters.

[0028] Specifically, the fixed threshold start-stop strategy pre-sets upper and lower limits for the system's heat load. When the heat load exceeds the upper limit, the standby magnetic levitation compressor is activated; when it falls below the lower limit, the operating magnetic levitation compressor is shut down. The evenly distributed load strategy distributes the total system heat load evenly among all operating magnetic levitation compressors, without distinguishing between their performance differences. Manually setting scheduling parameters relies on the on-site experience of maintenance personnel, who manually adjust the number of operating magnetic levitation compressors and the load distribution ratio based on seasonal changes or historical operating data.

[0029] However, this approach, relying on the local control logic of a single magnetic levitation compressor and pre-set static allocation rules, lacks a global optimization perspective. Each magnetic levitation compressor maintains local stability only through its own speed control or guide vane adjustment, failing to coordinate the operating states of multiple compressors to achieve overall system optimization. Furthermore, this static allocation rule does not consider the individual performance differences of different magnetic levitation compressors. Magnetic levitation compressors of different models, with different service lives and maintenance conditions, exhibit significant differences in core performance parameters such as optimal load rate, energy efficiency degradation coefficient, and rated power. Traditional strategies treat all magnetic levitation compressors as homogeneous devices with identical performance. Moreover, this static allocation rule cannot match the operating characteristics of magnetic levitation compressors. Magnetic levitation compressors are highly sensitive to speed and load; their energy efficiency coefficient reaches its peak only within a narrow optimal load rate range. Once deviating from this range, energy efficiency exhibits exponential degradation, unlike the relatively stable energy efficiency of traditional magnetic levitation compressors over a wide load range.

[0030] This can easily lead to some magnetic levitation compressors operating in an inefficient range for extended periods, while others operate under light or overload conditions, preventing the full realization of the high efficiency and energy-saving advantages that magnetic levitation compressors should possess. Furthermore, the fixed threshold start-stop strategy is highly susceptible to triggering frequent start-stop cycles of the magnetic levitation compressors during heat load fluctuations. This can not only generate significant starting-up energy consumption but also cause repeated mechanical and electrical shocks to core components such as magnetic bearings and motor windings, exacerbating equipment wear and shortening the lifespan of the magnetic levitation compressors. Simultaneously, the static load distribution method cannot quickly respond to dynamic changes in heat load. When user heating demand changes abruptly, it can easily lead to oversupply or undersupply, resulting in excessive fluctuations in water supply temperature, affecting the user's heating experience, and making it difficult to guarantee the system's operational stability under extreme conditions.

[0031] Based on the above issues, please refer to Figure 1 This application provides an intelligent collaborative control method for multiple magnetic levitation compressors used in centralized heating systems. The method includes: 011: Obtain the equipment identification information and real-time operating parameters of each magnetic levitation compressor; 012: Based on the equipment identification information, determine the target compressor performance model corresponding to each magnetic levitation compressor from the preset compressor performance models; 013: Based on real-time operating parameters, the first energy efficiency model, the first power model, and the first heating capacity model, determine the multi-machine collaborative optimization model for the magnetic levitation compressor system; 014: With the goal of minimizing the total energy consumption of the system, and based on preset constraints, the multi-machine collaborative optimization model is analyzed to obtain the target scheduling scheme; 015: Generate control commands based on the target scheduling scheme and send the control commands to each magnetic levitation compressor for execution.

[0032] This application also provides an electronic device, including a memory and a processor. The intelligent collaborative control method for multiple magnetic levitation compressors used in centralized heating according to this application can be implemented by the electronic device of this application. Specifically, the memory stores a computer program, and the processor is used to acquire the device identification information and real-time operating condition parameter set of each magnetic levitation compressor. Based on the device identification information, it determines the target compressor performance model corresponding to each magnetic levitation compressor from a preset compressor performance model. It also determines the multi-machine collaborative optimization model of the magnetic levitation compressor system based on the real-time operating condition parameters, a first energy efficiency model, a first power model, and a first heating capacity model. The processor is further used to analyze the multi-machine collaborative optimization model with the goal of minimizing the total system energy consumption, based on preset constraints, to obtain a target scheduling scheme. Finally, it generates control commands according to the target scheduling scheme and sends the control commands to each magnetic levitation compressor for execution.

[0033] This application also provides a system scheduling device. The intelligent collaborative control method for multiple magnetic levitation compressors used in centralized heating according to this application can be implemented by the system scheduling device of this application. Specifically, the system scheduling device includes an acquisition module, a determination module, an analysis module, and an instruction distribution module. The acquisition module is used to acquire the equipment identification information and real-time operating parameters of each magnetic levitation compressor. The determination module is used to determine the target compressor performance model corresponding to each magnetic levitation compressor from a preset compressor performance model based on the equipment identification information, and to determine the multi-machine collaborative optimization model of the magnetic levitation compressor system based on the real-time operating parameters, a first energy efficiency model, a first power model, and a first heating capacity model. The analysis module is used to analyze the multi-machine collaborative optimization model with the goal of minimizing the total system energy consumption and based on preset constraints to obtain a target scheduling scheme. The instruction distribution module is used to generate control instructions according to the target scheduling scheme and send the control instructions to each magnetic levitation compressor for execution.

[0034] Specifically, this application also provides a magnetic levitation compressor system, which includes a parallel operation system consisting of multiple magnetic levitation compressors, a central dispatch controller, a heating system, and a sensor system. This system provides stable heating capacity to the load side, adapting to dynamically changing heat load demands. The heating system, which provides heat, includes heat exchangers, piping networks, and user-end equipment.

[0035] A magnetic levitation compressor refers to a centrifugal magnetic levitation compressor that uses magnetic levitation bearing technology. It can achieve high-speed levitation operation of the rotor without lubrication oil. It has the characteristics of high speed, high efficiency, low vibration and low maintenance. Its operating performance is highly sensitive to speed and load rate, and there is a relatively narrow optimal efficiency operating range.

[0036] Equipment identification information refers to the identification code used to identify each magnetic levitation compressor, including equipment number, model code, and factory serial number. It is an index that links the magnetic levitation compressor to its dedicated compressor performance model.

[0037] Real-time operating parameters refer to physical quantities that reflect the current operating status of the system and the magnetic levitation compressor. These parameters are divided into system-side operating status data, equipment-side real-time operating parameters, and calculated real-time system heat load. System-side parameters include supply water temperature, return water temperature, and circulating water mass flow rate. Equipment-side parameters include input power, operating speed, guide vane opening, start / stop status, and rotor vibration amplitude.

[0038] The preset compressor performance model refers to a set of mathematical models that are established in advance through bench tests or fitting long-term historical operating data. These models are usually stored in the model library of the central dispatch controller. Each magnetic levitation compressor corresponds to a set of exclusive model parameters, which are used to predict its performance under different operating conditions.

[0039] The target compressor performance model refers to a dedicated compressor performance model corresponding one-to-one with a specific magnetic levitation compressor to be scheduled. It includes three interrelated sub-models: the first energy efficiency model, the first power model, and the first heating capacity model. The first energy efficiency model describes the nonlinear relationship between the magnetic levitation compressor's coefficient of performance (COP) and load rate. The first power model describes the relationship between input power and load rate, operating speed, and guide vane opening. The first heating capacity model describes the product of output heating capacity, input power, and COP.

[0040] The multi-machine collaborative optimization model refers to a mathematical optimization model that integrates the system's heat load demand, the performance characteristics of each magnetic levitation compressor, and operational constraints. It is used to transform the actual multi-machine scheduling problem into a solvable mathematical problem.

[0041] Preset constraints refer to the hard restrictions set to ensure the safe and stable operation of the system and meet the heating demand, including the first constraint, the second constraint, the third constraint and / or the fourth constraint.

[0042] The target scheduling scheme refers to the globally optimal operating strategy obtained by solving the multi-machine collaborative optimization model, which clarifies the start-stop status, optimal operating speed, optimal guide vane opening, and corresponding load distribution ratio of each magnetic levitation compressor.

[0043] Control commands refer to standardized digital commands that are generated and can be directly recognized and executed by the local controller of the magnetic levitation compressor, including start / stop commands, speed setting commands, guide vane opening adjustment commands, etc.

[0044] First, during the initial power-on startup, restart, or system parameter reset of the magnetic levitation compressor system, the central dispatch controller performs global initialization and parameter configuration operations. Specifically, this includes configuring the system's core operating targets, including the user-side target water supply temperature, the system's rated heat load, and the system's minimum operating heat load. Furthermore, based on the factory technical parameters of each magnetic levitation compressor, its operating constraint boundaries are set, such as speed boundaries, guide vane opening boundaries, and start-stop protection boundaries.

[0045] After global initialization and parameter configuration are completed, the magnetic levitation compressor system synchronously collects all operating data from the system side and the equipment side, and reads the main equipment identifier of each magnetic levitation compressor to ensure that the correct compressor performance model can be matched for each magnetic levitation compressor in the future.

[0046] Subsequently, based on the equipment identification information, the target compressor performance model corresponding to each magnetic levitation compressor is determined from the preset compressor performance models. Since different magnetic levitation compressors have individual performance differences, a uniform model would lead to prediction errors. Therefore, the module retrieves the specific compressor performance model for the corresponding magnetic levitation compressor from the preset model library using the equipment identification, providing a basis for subsequent performance prediction.

[0047] Next, the real-time operating parameters are substituted into the target compressor performance model of each magnetic levitation compressor to calculate the predicted input power and heating capacity of each magnetic levitation compressor under all feasible candidate operating conditions. Combined with the current heat load demand of the system, a multi-machine collaborative optimization model including an objective function is constructed.

[0048] Then, all start-stop combination schemes of magnetic levitation compressors that meet the constraints are generated. Then, the optimal load allocation is performed on each scheme to make each magnetic levitation compressor operate in its own optimal efficiency range as much as possible. Then, the objective function value of each scheme is calculated, and finally the scheme with the smallest objective function value is selected as the target scheduling scheme.

[0049] Finally, the abstract target scheduling scheme is transformed into standardized control commands and sent to each magnetic levitation compressor. Each magnetic levitation compressor then receives the commands and executes the corresponding control commands.

[0050] In summary, the intelligent collaborative control method and magnetic levitation compressor system for centralized heating provided in this application, by matching the compressor performance model corresponding to each magnetic levitation compressor, can fully consider the differentiated efficiency characteristics of different magnetic levitation compressors under different operating conditions. Furthermore, by constructing and solving a multi-machine collaborative optimization model, each magnetic levitation compressor can be guided to operate within its own optimal efficiency range, effectively alleviating the technical problems of high energy consumption and low efficiency. This provides technical support for the efficient and stable operation of the multi-machine parallel magnetic levitation compressor system, improving the overall energy efficiency of the system.

[0051] Please see Figure 2 In some embodiments, real-time operating condition parameters include system-side operating status data, equipment-side real-time operating condition parameters, and system real-time heat load. Step 011 includes: 0111: Based on the sensor system in the magnetic levitation compressor system, collect equipment identification information, system-side operating status data and equipment-side real-time operating condition parameters; 0112: Calculate the real-time heat load of the system based on the supply water temperature, return water temperature, and circulating water mass flow rate.

[0052] In some implementations, the processor is used in a sensor system within the magnetic levitation compressor system to collect system-side operating status data and real-time equipment-side operating parameters. It also calculates the system's real-time heat load based on the supply water temperature, return water temperature, and circulating water mass flow rate.

[0053] In some implementations, the acquisition module is also used to collect system-side operating status data and equipment-side real-time operating condition parameters based on the sensor system in the magnetic levitation compressor system, and to calculate the system's real-time heat load based on the supply water temperature, return water temperature, and circulating water mass flow rate.

[0054] Specifically, the sensor system refers to a distributed data acquisition network composed of various sensors distributed on the heating system and each magnetic levitation compressor. It is the perception layer of the entire scheduling system and is responsible for converting the operating status of the physical world into digital signals that can be processed by the central scheduling controller. All sensors can communicate with the central scheduling controller through the industrial bus.

[0055] System-side operational status data refers to physical quantities that reflect the overall operational status of the heating system. These quantities characterize the actual heat demand on the user side and the system's thermal conditions, serving as the basis for calculating the system's heat load. In some implementations, system-side operational status data includes supply water temperature, return water temperature, and / or circulating water mass flow rate.

[0056] Among them, the water supply temperature refers to the temperature of the circulating water in the main water supply pipe of the heating system in the magnetic levitation compressor system. It is an indicator for measuring the output capacity of the heating system and directly affects the user's indoor temperature experience.

[0057] The return water temperature refers to the temperature of the circulating water in the return water main of the heating system. It reflects the remaining heat after the user side absorbs heat. Combined with the supply water temperature, the actual heat supply of the system can be calculated.

[0058] The circulating water mass flow rate refers to the mass of circulating water passing through the main pipe of the heating system per unit time. It is a key parameter for heat load calculation and is usually measured by an electromagnetic flow meter or an ultrasonic flow meter.

[0059] Real-time operating parameters on the equipment side refer to physical quantities that reflect the operating status of a single magnetic levitation compressor. They are used to characterize the workload, energy efficiency level, and operational stability of the magnetic levitation compressor and serve as the basis for compressor performance model calculations and magnetic levitation compressor status assessments. In some implementations, real-time operating parameters on the equipment side include the input power, operating speed, guide vane opening, operating status, and / or rotor vibration amplitude of each magnetic levitation compressor.

[0060] Input power refers to the total active power consumed by a single magnetic levitation compressor during operation, including the power of the magnetic levitation compressor main unit, the power of the frequency converter, and the power of the auxiliary system. It is an indicator for calculating the total energy consumption of the system.

[0061] Operating speed refers to the real-time rotational speed of the rotor of a magnetic levitation compressor. The speed range of a magnetic levitation compressor is typically much wider than that of a traditional magnetic levitation compressor. The operating speed of a magnetic levitation compressor is one of the key parameters affecting its heating capacity and energy efficiency.

[0062] Guide vane opening refers to the opening angle of the inlet guide vanes of the magnetic levitation compressor. By adjusting the guide vane opening, the intake volume of the magnetic levitation compressor can be changed, thereby adjusting the output heating capacity of the magnetic levitation compressor. It is an important means of load regulation for magnetic levitation compressors.

[0063] Operating status refers to the binary parameter that characterizes whether the magnetic levitation compressor is currently running or stopped. It is usually obtained from the auxiliary contact signal in the control cabinet of the magnetic levitation compressor and is the basis for determining decision variables when constructing a multi-machine collaborative optimization model.

[0064] Rotor vibration amplitude refers to the radial and axial vibration displacement of the rotor of a magnetic levitation compressor, and is an indicator reflecting the operational stability of the compressor. Excessive rotor vibration amplitude indicates problems such as imbalance, misalignment, or bearing failure in the magnetic levitation compressor.

[0065] The real-time heat load of the system refers to the total heat required by the user side per unit time. It is a constraint condition of the multi-machine collaborative optimization model and determines the total capacity of the magnetic levitation compressors that need to be put into operation.

[0066] In some implementations, the formula for calculating the real-time heat load of the system can be:

[0067] in, The circulating water mass flow rate, Specific heat capacity of the fluid For water supply temperature, This refers to the return water temperature.

[0068] Thus, by deploying sensor systems on both the system and equipment sides, all key operating parameters affecting scheduling decisions are collected synchronously. Based on the principle of thermal balance, the actual heat demand of users is accurately calculated, providing precise and sufficient data support for subsequent status identification, compressor performance model calculation, and optimized scheduling. Furthermore, by calculating the system's heat load in real time, matching heating capacity with user demand can be achieved, effectively avoiding user experience degradation due to insufficient heating and energy waste caused by excessive heating. Simultaneously, comprehensive equipment-side parameter collection allows for real-time monitoring of the operating status of individual magnetic levitation compressors, laying the foundation for subsequent stability assessment and refined scheduling, and improving the accuracy and timeliness of scheduling decisions.

[0069] Please see Figure 3 In some implementations, the method further includes: 0113: Filter the system-side operating status data and the equipment-side real-time operating condition parameters to remove or correct abnormal data.

[0070] In some implementations, the acquisition module is also used to filter the system-side operating status data and the equipment-side real-time operating condition parameters to remove or correct abnormal data.

[0071] In some implementations, the processor is also used to filter system-side operating status data and device-side real-time operating condition parameters to remove or correct abnormal data.

[0072] Specifically, filtering refers to a signal processing technique used to remove noise interference from raw data, extract useful signal components, and make the data smoother and more accurate. In some implementations, commonly used filtering algorithms include moving average filtering, median filtering, and Kalman filtering.

[0073] Abnormal data refers to measured values ​​that deviate from the normal data distribution range. It is usually caused by sensor failure, electromagnetic interference, signal transmission errors, etc. Abnormal data can seriously affect the accuracy of subsequent calculations and decisions.

[0074] In some implementations, the possible methods for filtering system-side operating status data and equipment-side real-time operating parameters are as follows: First, a moving average filtering algorithm is used to filter continuously changing signals such as temperature, flow rate, power, and speed, with a window size set to 5 sampling points to remove high-frequency noise interference and make the signal smoother. Then, the 3σ criterion is used to identify abnormal data, that is, the average value and standard deviation of a certain parameter over the past minute are calculated, and data exceeding the average value ± 3 times the standard deviation are judged as abnormal data. For single-point abnormal data, linear interpolation of two adjacent normal data is used for correction. For three or more consecutive abnormal data, it is judged as a sensor fault, triggering the corresponding alarm signal, and the average value of the previous normal cycle is used to replace the abnormal data, while the sensor is marked as pending maintenance.

[0075] In this way, by eliminating or correcting abnormal data, the prediction deviation of compressor performance models and scheduling decision errors caused by data distortion can be reduced, thereby ensuring the stability of system operation and the effectiveness of scheduling schemes.

[0076] Please see Figure 4 In some implementations, the preset compressor performance model is established in advance in the following manner: 021: Generate a performance sample dataset of the magnetic levitation compressor based on the obtained historical operating parameters; 022: Perform function fitting on the performance sample dataset of magnetic levitation compressors to establish a preset compressor performance model.

[0077] In some implementations, the system scheduling device further includes a model training module, which generates a magnetic levitation compressor performance sample dataset based on the acquired historical operating parameters, and performs function fitting on the magnetic levitation compressor performance sample dataset to establish a preset compressor performance model.

[0078] In some implementations, the processor is also used to generate a performance sample dataset of the magnetic levitation compressor based on the acquired historical operating parameters, and to perform function fitting on the performance sample dataset of the magnetic levitation compressor to establish a preset compressor performance model.

[0079] Specifically, historical operating parameters refer to the full-dimensional raw data collected during the bench testing phase before the magnetic levitation compressor leaves the factory or during actual field operation, under different operating conditions. This data forms the foundation for establishing the compressor performance model and comprehensively reflects the inherent performance characteristics of the magnetic levitation compressor. Specifically, historical operating parameters include the input power, flow rate, temperature, and corresponding heating capacity of each magnetic levitation compressor under different operating speeds, guide vane openings, and / or temperature conditions.

[0080] Among them, the operating speed refers to the real-time rotational speed of the magnetic levitation compressor rotor, which is a core parameter affecting the output capacity and energy efficiency of the magnetic levitation compressor.

[0081] Guide vane opening refers to the opening angle of the inlet guide vanes of the magnetic levitation compressor. By changing the inlet cross-sectional area, the refrigerant circulation flow rate is adjusted. It is another key load regulation method besides speed, and together with speed, it determines the actual operating load rate of the magnetic levitation compressor.

[0082] Temperature conditions mainly refer to the intake temperature of the magnetic levitation compressor, the supply water temperature and return water temperature of the heating system. Ambient temperature and system water temperature will significantly affect the phase change process of the refrigerant, thereby changing the operating performance of the magnetic levitation compressor.

[0083] Flow rate refers to the refrigerant circulation mass flow rate of the magnetic levitation compressor, which directly determines the amount of heat that the magnetic levitation compressor can transfer per unit time and is an intermediate parameter for calculating heating capacity.

[0084] Heating capacity refers to the effective heat provided by the magnetic levitation compressor to the heating system per unit time. It is an indicator for measuring the heating capacity of the magnetic levitation compressor and can be calculated from the supply and return water temperatures and circulating water flow rate on the system side through the principle of heat balance.

[0085] The magnetic levitation compressor performance sample dataset refers to a standardized dataset formed by cleaning, filtering and structuring the collected historical operating parameters. Each sample corresponds to a set of stable operating conditions and the corresponding performance indicators under those conditions, and serves as the input data for function fitting.

[0086] Function fitting is a classic mathematical modeling method that finds one or a set of continuous functions that approximate known discrete data points as closely as possible, thereby establishing a quantitative relationship between independent and dependent variables. Commonly used fitting algorithms include least squares, polynomial fitting, and exponential fitting.

[0087] The second energy efficiency model refers to a sub-model in the preset compressor performance model, which is used to describe the nonlinear relationship between the coefficient of performance (COP) of the magnetic levitation compressor and the load rate, speed, guide vane opening and temperature conditions, and reflects the energy utilization efficiency of the magnetic levitation compressor under different operating conditions.

[0088] The second power model refers to a sub-model in the preset compressor performance model. It is used to describe the functional relationship between the input power of the magnetic levitation compressor and the load rate, speed, and guide vane opening, and serves as the basis for calculating the total energy consumption of the system.

[0089] The second heating capacity model refers to a sub-model in the preset compressor performance model. It is used to describe the quantitative relationship between the output heating capacity of the magnetic levitation compressor and the input power and energy efficiency coefficient. It is the core foundation of the heat load balance constraint in the multi-machine collaborative optimization model.

[0090] It should be noted that the second energy efficiency model and the aforementioned first energy efficiency model are different stages of the same compressor performance model. The second energy efficiency model is a baseline model established offline through fitting experimental data and stored in a pre-set compressor performance model library. The first energy efficiency model is a running instance of this baseline model loaded and called from the model library based on the device identification information during system runtime. Both are identical in mathematical expressions, fitting parameters, and performance characterization capabilities. The different numbering is merely to clearly distinguish between the pre-establishment and online calling of the model; there is no substantial difference. Similarly, the second power model and the first power model, and the second heating model and the first heating model, also follow the above correspondence.

[0091] First, during the model building phase, a full-condition traversal test is required for each magnetic levitation compressor, covering its entire permissible speed range, guide vane opening range, and common temperature ranges encountered at the project site. After maintaining stable operation of the magnetic levitation compressor for a sufficient period at each operating point, parameters such as input power, refrigerant flow rate, inlet air temperature, supply water temperature, and return water temperature are collected synchronously, and the actual heating capacity under that operating condition is calculated using the heat balance formula. After data collection, the raw data undergoes preliminary preprocessing to remove unstable data during the acceleration and deceleration of the magnetic levitation compressor, abnormal data caused by sensor interference, and duplicate data. Then, the operating parameters and corresponding performance indicators for each stable operating point are organized into structured sample entries, ultimately forming a performance sample dataset of the magnetic levitation compressor covering all operating conditions.

[0092] Subsequently, due to the nonlinear coupling relationship between the performance and operating parameters of the magnetic levitation compressor, the three core indicators of energy efficiency, power, and heating capacity need to be fitted independently. Among them, the energy efficiency coefficient exhibits a single-peak characteristic of first rising and then falling with the load rate, reaching its maximum value at the optimal load rate. Therefore, an exponential function or a quadratic polynomial can be used for fitting.

[0093] The change in input power with load rate is approximately a quadratic function, so a quadratic polynomial can be used for fitting.

[0094] The heating capacity is the product of the input power and the energy efficiency coefficient, which can be derived from the first two models, or it can be directly fitted independently based on sample data to improve accuracy. The fitting process can use the least squares method, which minimizes the sum of squared errors between the model's predicted values ​​and the actual sample values ​​to obtain the undetermined coefficients in each sub-model. Finally, a complete preset compressor performance model including the second energy efficiency model, the second power model, and the second heating capacity model is obtained. The model parameters are then bound to the corresponding magnetic levitation compressor's equipment identification information and stored in the model library of the central dispatch controller.

[0095] In some implementations, the second energy efficiency model can be expressed by the following relationship:

[0096] in, For the first The load rate of the magnetic levitation compressor. For the first The optimal load rate of the magnetic levitation compressor. For the first The energy efficiency coefficient corresponding to the optimal load rate of the magnetic levitation compressor. The energy efficiency degradation coefficient is used to characterize the degree of performance degradation of a magnetic levitation compressor when it deviates from its optimal load rate. The value of can be determined based on experimental data from different models of magnetic levitation compressors.

[0097] The second power model can be expressed by the following relationship:

[0098] in, Let be the input power of the i-th magnetic levitation compressor; Let be the operating speed of the i-th magnetic levitation compressor; Let be the guide vane opening of the i-th magnetic levitation compressor; The medium temperature of the magnetic levitation compressor, specifically the intake temperature of the magnetic levitation compressor or the return water temperature of the system; - The specific fitting coefficients for the power model of the i-th magnetic levitation compressor are obtained by fitting offline experimental data using the least squares method and stored in the preset compressor performance model library.

[0099] The second heating capacity model can be expressed by the following relationship:

[0100] in, The actual heating capacity of the i-th magnetic levitation compressor; Let be the operating speed of the i-th magnetic levitation compressor; Let be the guide vane opening of the i-th magnetic levitation compressor; The medium temperature of the magnetic levitation compressor, specifically the intake temperature of the magnetic levitation compressor or the return water temperature of the system; - The fitting coefficients are specific to the thermal model of the i-th magnetic levitation compressor. They are obtained by fitting offline experimental data in sync with the power model coefficients. The fitting coefficients of each magnetic levitation compressor are independent of each other to characterize the performance differences of different magnetic levitation compressors.

[0101] Thus, based on a pre-defined compressor performance model, the heating capacity, energy efficiency ratio, and input power characteristics of each magnetic levitation compressor can be accurately characterized across the entire operating range, establishing a precise mapping relationship between operating parameters and performance indicators. Furthermore, this pre-defined compressor performance model can provide a reliable quantitative calculation basis for multi-machine collaborative optimization models, enabling load allocation to be finely designed based on the actual efficiency characteristics of the magnetic levitation compressors, achieving differentiated optimal operation for different magnetic levitation compressors.

[0102] In some implementations, the multi-machine cooperative optimization model includes an objective function, which may be expressed as the following relationship: ; in, Let be the input power of the i-th magnetic levitation compressor, and N be the total number of magnetic levitation compressors in the system. Let i represent the current operating state of the i-th magnetic levitation compressor. This represents the previous operating state of the i-th magnetic levitation compressor. The degree to which the i-th magnetic levitation compressor deviates from its optimal operating range. This refers to the start / stop weighting coefficient. This represents the state penalty weight coefficient.

[0103] Specifically, the objective function refers to a mathematical expression used to measure the merits of different scheduling schemes. In the implementation of this application, it is in the form of minimization. The smaller the value of the objective function, the better the corresponding scheduling scheme.

[0104] Input power refers to the total active power consumed by the i-th magnetic levitation compressor under the current operating conditions, including the power consumption of the magnetic levitation compressor main unit, frequency converter and auxiliary system, and is a direct component of the total energy consumption of the system.

[0105] Current running status This refers to a binary variable representing the start-stop state of the i-th magnetic levitation compressor in the k-th scheduling cycle. The running state has a value of 0 indicating shutdown and a value of 1 indicating operation. In the above relationship, when... When it is on, it means there is no start / stop; otherwise, it means there is no start / stop. The time indicates whether it starts or stops.

[0106] The start-stop weighting coefficient refers to the weighting parameter used to quantify the equivalent energy consumption corresponding to one start-stop of the magnetic levitation compressor. Its value reflects the importance the system attaches to the start-stop loss of the magnetic levitation compressor. The larger the value, the more inclined the system is to avoid frequent start-stop of the magnetic levitation compressor.

[0107] The state penalty weighting coefficient refers to the weighting parameter used to quantify the energy efficiency loss caused by the magnetic levitation compressor deviating from the optimal operating area. Its value reflects the importance the system attaches to the magnetic levitation compressor operating in the high-efficiency range. The larger the value, the more inclined it is to guide the magnetic levitation compressor to operate near the optimal load rate.

[0108] In some implementations, the start-stop weight coefficient and the state penalty weight coefficient can be dynamically and adaptively adjusted based on the system state identification results. These system state identification results include the system load change trend, load fluctuation amplitude, and the operational stability of a single magnetic levitation compressor. For example, when the system load fluctuation amplitude is detected to exceed a preset threshold (e.g., a load change rate greater than 15% within 10 minutes), the start-stop weight coefficient can be increased from the initial value of 5-10 to 10-20 to suppress frequent start-stop behavior of the magnetic levitation compressor and reduce additional energy consumption and mechanical impact on the equipment during startup. When the power fluctuation, speed fluctuation, or rotor vibration amplitude of any magnetic levitation compressor is detected to exceed a preset stability threshold, the state penalty weight coefficient can be increased from the initial value of 1-3 to 3-10. In this case, the optimization algorithm will prioritize ensuring that the magnetic levitation compressor operates within a safe and stable range, rather than simply pursuing the lowest energy consumption, thus preventing equipment damage due to operation beyond its operating conditions.

[0109] It should be noted that the start-stop weighting coefficient and the state penalty weighting coefficient can be preset with initial baseline values ​​based on the system's application scenario. For example, for heating systems in small commercial buildings, the initial value of the start-stop weighting coefficient can be set to 2-5. For medium to large-scale district heating systems, the initial value can be set to 5-15. For industrial waste heat recovery systems that emphasize the protection of the entire equipment lifecycle, the initial value can be set to 10-20. For combined heating and cooling systems in large commercial complexes with extreme energy-saving requirements, the initial value of the state penalty weighting coefficient can be set to 3-5.

[0110] The degree of deviation from the optimal operating area refers to the index that measures the deviation between the current operating load rate of the i-th magnetic levitation compressor and its own optimal load rate. It is usually represented by the square of the deviation. The larger the deviation, the larger the value, which indicates that the energy efficiency loss is more serious.

[0111] In this way, a multi-objective weighted optimization system integrating total energy consumption, start-up and shutdown costs, and equipment operational stability can be constructed, overcoming the shortcomings of traditional single-objective optimization. Furthermore, the start-up and shutdown weight coefficient can effectively suppress the frequent start-up and shutdown behavior of the magnetic levitation compressor, reducing the additional energy consumption during startup and the mechanical impact on the equipment, thus extending the equipment's service life. Simultaneously, the state penalty weight coefficient can constrain the magnetic levitation compressor to operate within its optimal efficiency range, further improving the system's energy efficiency.

[0112] In some implementations, the preset constraints include a first constraint, a second constraint, a third constraint, and / or a fourth constraint. The first constraint indicates that the sum of the heating capacity of each magnetic levitation compressor is equal to the real-time heat load of the system. The second constraint indicates that the operating speed of each magnetic levitation compressor is between the minimum speed and the maximum speed. The third constraint indicates that the guide vane opening of each magnetic levitation compressor is between the minimum opening and the maximum opening. The fourth constraint indicates that each magnetic levitation compressor needs to run continuously for a minimum time after startup and needs to be shut down for a minimum time after shutdown.

[0113] Specifically, the first constraint, also known as the heat load balance constraint, requires that the total heating capacity of all operating magnetic levitation compressors equal the real-time heat load of the system. It is the core constraint to ensure the quality of heating and avoid problems such as insufficient or excessive heating.

[0114] The second constraint, also known as the speed boundary constraint, requires that the operating speed of each magnetic levitation compressor be between the specified minimum speed and the maximum speed. Running below the minimum speed will cause the magnetic levitation compressor to surge, while running above the maximum speed will cause excessive centrifugal force on the rotor, damaging the equipment.

[0115] The third constraint, also known as the guide vane opening boundary constraint, requires that the guide vane opening of each magnetic levitation compressor be between the minimum and maximum opening. If the guide vane opening is too small, the intake volume will be insufficient; if it is too large, the adjustment capability will be lost.

[0116] The fourth constraint, also known as the minimum running / stopping time constraint, requires that the magnetic levitation compressor must run continuously for at least a minimum running time after starting and must remain in a stopped state for at least a minimum stopping time after stopping, in order to avoid repeated start-stop cycles in a short period of time that could impact the equipment.

[0117] Thus, by constructing a multi-dimensional constraint system covering supply and demand matching, equipment safety, and operational stability, reasonable boundary conditions can be provided for optimization solutions.

[0118] Please see Figure 5 In some implementations, step 014 includes: 0141: Generate candidate magnetic levitation compressor operation schemes; 0142: Under preset constraints, based on a multi-machine collaborative optimization model, calculate the input power and heating capacity of each candidate magnetic levitation compressor under each candidate magnetic levitation compressor operation scheme; 0143: Substitute the input power and heating capacity into the multi-machine collaborative optimization model to calculate the objective function value of each candidate magnetic levitation compressor operation scheme; 0144: Select the candidate magnetic levitation compressor operation scheme that minimizes the objective function value as the objective scheduling scheme.

[0119] In some implementations, the analysis model is also used to generate candidate magnetic levitation compressor operation schemes. Under preset constraints, based on a multi-machine collaborative optimization model, the input power and heating capacity of each candidate magnetic levitation compressor under each candidate magnetic levitation compressor operation scheme are calculated. The input power and heating capacity are then substituted into the multi-machine collaborative optimization model to calculate the objective function value for each candidate magnetic levitation compressor operation scheme. The analysis model is also used to select the candidate magnetic levitation compressor operation scheme that minimizes the objective function value as the target scheduling scheme.

[0120] In some implementations, the processor is further configured to generate candidate magnetic levitation compressor operation schemes. Under preset constraints, based on a multi-machine cooperative optimization model, it calculates the input power and heating capacity of each candidate magnetic levitation compressor under each candidate magnetic levitation compressor operation scheme. It then substitutes the input power and heating capacity into the multi-machine cooperative optimization model to calculate the objective function value for each candidate magnetic levitation compressor operation scheme. The processor is also configured to select the candidate magnetic levitation compressor operation scheme that minimizes the objective function value as the target scheduling scheme.

[0121] The candidate magnetic levitation compressor operation scheme refers to all possible combinations of magnetic levitation compressor operation that meet the constraints. Each scheme includes a combination of the start-stop state, operating speed and guide vane opening of each magnetic levitation compressor.

[0122] The objective function value refers to the numerical value obtained by substituting the running parameters of a candidate solution into the objective function. It is the main criterion for evaluating the merits of the solution.

[0123] In one example, if candidate magnetic levitation compressor A has a maximum heating capacity of 300 kW, an optimal load factor of 0.8, and an optimal COP of 6.0; if candidate magnetic levitation compressor B has a maximum heating capacity of 250 kW, an optimal load factor of 0.75, and an optimal COP of 5.8; and if candidate magnetic levitation compressor C has a maximum heating capacity of 250 kW, an optimal load factor of 0.75, and an optimal COP of 5.7, the current system load is: =450KW. At the previous moment, the system was running with magnetic levitation compressors A and B, while magnetic levitation compressor C was stopped. Settings , .

[0124] Candidate magnetic levitation compressor operation scheme 1 can be generated: Candidate magnetic levitation compressor A runs alone; Candidate magnetic levitation compressor operation scheme 2: Candidate magnetic levitation compressor A and candidate magnetic levitation compressor B; Candidate magnetic levitation compressor operation scheme 3: Candidate magnetic levitation compressor A and candidate magnetic levitation compressor C; Candidate magnetic levitation compressor operation scheme 4: Candidate magnetic levitation compressor B and candidate magnetic levitation compressor C; Candidate magnetic levitation compressor operation scheme 5: Candidate magnetic levitation compressor A, candidate magnetic levitation compressor B and candidate magnetic levitation compressor C.

[0125] Among them, for candidate magnetic levitation compressor operation scheme 1: the maximum heating capacity of magnetic levitation compressor A is 300KW, which is less than the current system load of 450KW, and does not meet the total heat load constraint, so this scheme is directly eliminated.

[0126] For candidate magnetic levitation compressor operation scheme 2: while meeting the total heat load constraint Given a load factor of 450, the load distribution for each magnetic levitation compressor is optimized. The load distribution aims to minimize the deviation of each compressor's load rate from its optimal load rate, ensuring that each compressor's operating point is as close as possible to its efficient operating range. This load distribution can be solved using a system of equations:

[0127] Solving the above equation, we can obtain , .

[0128] The offset penalty is calculated as follows: ; Load allocation is as follows: , ; COP calculation: , ; Power calculation: , , .

[0129] Similarly, based on the same calculation method, it can be determined that: Candidate magnetic levitation compressor operation scheme 2: power is 78.85KW, start-stop penalty is 0, deviation penalty is 0.072, and objective function value is 78.92.

[0130] Candidate magnetic levitation compressor operation scheme 3: power is 79.99KW, start-stop penalty is 5, deviation penalty is 0.072, and objective function value is 85.06.

[0131] Candidate magnetic levitation compressor operation scheme 4: power is 81.09KW, start-stop penalty is 10, deviation penalty is 0.225, and objective function value is 91.32.

[0132] Candidate magnetic levitation compressor operation scheme 5: power is 86.63KW, start-stop penalty is 5, deviation penalty is 0.425, and objective function value is 92.06.

[0133] Ultimately, it can be determined that candidate magnetic levitation compressor operation scheme 2 (joint operation of magnetic levitation compressor A and magnetic levitation compressor B) has the smallest objective function value and is the optimal scheme for this scheduling. This scheme does not require starting or stopping any magnetic levitation compressors, has the lowest total energy consumption, and the operating load rates of both magnetic levitation compressors are close to their respective optimal ranges, resulting in the highest system operational stability.

[0134] Thus, by generating candidate magnetic levitation compressor operation schemes and comparing the objective function values ​​calculated for each candidate scheme, the target scheduling scheme can be determined, thereby obtaining a globally approximate optimal scheduling solution and avoiding the problem of getting trapped in local optima.

[0135] Please see Figure 6 In some implementations, step 015 includes: 0151: A gradual adjustment method is used to send control commands to each magnetic levitation compressor for execution, so as to avoid impacting the magnetic levitation compressor system.

[0136] In some implementations, the processor is also used to issue control commands to each magnetic levitation compressor in a gradual adjustment manner to avoid impacting the magnetic levitation compressor system.

[0137] In some implementations, the instruction distribution module is also used to send control instructions to each magnetic levitation compressor for execution using a gradual adjustment method, so as to avoid impacting the magnetic levitation compressor system.

[0138] Specifically, the gradual adjustment method refers to a smooth closed-loop parameter adjustment method, which decomposes the target operating parameter from the current actual value into multiple continuous small steps at a preset constant rate or optimized nonlinear rate to gradually adjust it to the target value, so that the system state always maintains a smooth transition during the adjustment process and avoids parameter abrupt changes.

[0139] Impact refers to the instantaneous force or disturbance generated on equipment, pipelines, or power grids when system operating parameters change abruptly. In some implementations, impacts are mainly classified into four types: mechanical impact, fluid impact, hydraulic impact, and power grid impact.

[0140] Mechanical shock refers to the instantaneous alternating force generated on the magnetic levitation bearing caused by a sudden change in rotation speed, which leads to the loss of dynamic balance of the high-speed rotating rotor. Over a long period of time, this can cause bearing wear, rotor displacement, and in severe cases, equipment damage.

[0141] Fluid shock refers to the phenomenon where a sudden change in the guide vane opening causes a sharp change in the intake volume of a magnetic levitation compressor, resulting in turbulent flow and violent pressure fluctuations inside the compressor. In extreme cases, it can develop into surge.

[0142] Hydraulic shock refers to the pressure impact on equipment such as pipe networks, valves, and heat exchangers caused by the sudden change in the output heating capacity of a magnetic levitation compressor, which leads to a sharp change in the flow rate and temperature of the circulating water in the heating system. This can cause problems such as pipe network vibration and interface leakage.

[0143] Grid impact refers to the sudden change in the input power of a magnetic levitation compressor, which causes a large instantaneous change in the grid load and disrupts the voltage and frequency of the grid, affecting the normal operation of other electrical equipment on the same grid.

[0144] In some implementations, the command issuance process can be as follows: First, after receiving the control command from the central dispatch controller, the local controller of the magnetic levitation compressor verifies the command's legality and validity. Then, it reads the current actual speed and guide vane opening of the magnetic levitation compressor and calculates the difference between the current value and the target value. Next, according to a preset adjustment rate, the total adjustment is decomposed into multiple consecutive small adjustment steps, each step corresponding to an adjustment much smaller than the total adjustment. Finally, at fixed time intervals, adjustment commands of each small step are sequentially issued to the variable frequency drive system and the guide vane electric actuator, causing the speed and guide vane opening to rise or fall smoothly until the target value is reached.

[0145] In this way, by using a gradual adjustment method, a smooth transition between the speed of the magnetic levitation compressor and the opening of the guide vanes can be achieved, thereby effectively avoiding drastic fluctuations in system parameters such as pressure and temperature, ensuring the stable operation of the heating system and the heating quality at the user end.

[0146] Please see Figure 7 In some implementations, the method further includes: 016: After the control command is executed, collect system-side operating status data and equipment-side real-time operating condition parameters; 017: When the magnetic levitation compressor system is in operation, if the system load of the magnetic levitation compressor system changes beyond the preset threshold, or the operating status of the magnetic levitation compressor changes, or the operating cycle of the magnetic levitation compressor system reaches the preset optimization cycle, the equipment identification information and real-time operating condition parameters of each magnetic levitation compressor are obtained again. 018: Based on real-time operating parameters, the first energy efficiency model, the first power model, and the first heating capacity model, the multi-machine collaborative optimization model of the magnetic levitation compressor system is determined again; 019: With the goal of minimizing the total system energy consumption, and based on preset constraints, the multi-machine collaborative optimization model is analyzed to obtain the target scheduling scheme; 020: Generate control commands again based on the target scheduling scheme, and send the control commands to each magnetic levitation compressor controller for execution.

[0147] In some implementations, the acquisition module is further used to collect system-side operating status data and equipment-side real-time operating condition parameters after the control command is executed. Also, when the magnetic levitation compressor system is in operation, if the system load change of the magnetic levitation compressor system exceeds a preset threshold, or the operating status of the magnetic levitation compressor changes, or the operating cycle of the magnetic levitation compressor system reaches a preset optimization cycle, the module again acquires the equipment identification information and real-time operating condition parameters of each magnetic levitation compressor. The determination module is used to determine the multi-machine collaborative optimization model of the magnetic levitation compressor system again based on the real-time operating condition parameters, the first energy efficiency model, the first power model, and the first heating capacity model. The analysis module is used to analyze the multi-machine collaborative optimization model with the goal of minimizing the total system energy consumption and based on preset constraints to obtain a target scheduling scheme. The command distribution module is used to generate control commands again according to the target scheduling scheme and distribute the control commands to each magnetic levitation compressor controller for execution.

[0148] The processor is used to collect system-side operating status data and equipment-side real-time operating condition parameters after the control command is executed. When the magnetic levitation compressor system is in operation, it determines whether the optimization trigger conditions are met. Optimization trigger conditions include the system load change of the magnetic levitation compressor system exceeding a preset threshold, a change in the operating status of the magnetic levitation compressor, or the operating cycle of the magnetic levitation compressor system reaching a preset optimization cycle. If the optimization trigger conditions are met, it again acquires the equipment identification information and real-time operating condition parameters of each magnetic levitation compressor. The processor is also used to determine the multi-machine collaborative optimization model of the magnetic levitation compressor system again based on the real-time operating condition parameters, the first energy efficiency model, the first power model, and the first heating capacity model. With the goal of minimizing the total system energy consumption and based on preset constraints, it solves the multi-machine collaborative optimization model to obtain a target scheduling scheme. Finally, it generates control commands again based on the target scheduling scheme and sends the control commands to each magnetic levitation compressor controller for execution.

[0149] Specifically, the preset threshold refers to the upper limit of the system heat load change rate set in advance, which can usually be set to 3%-8% of the system's rated heat load. When the heat load change rate exceeds this value, it is considered that the user demand has changed significantly and scheduling optimization needs to be carried out again.

[0150] Changes in operating status refer to the magnetic levitation compressor deviating from its normal operating range, including excessive power fluctuations, excessive speed fluctuations, increased rotor vibration amplitude, and abnormal exhaust temperature, indicating that the performance of the magnetic levitation compressor has changed or that there is a potential fault.

[0151] The preset optimization cycle refers to the time interval between two fixed optimizations, which is usually set to 3-10 minutes. It is used to optimize the system periodically to compensate for the slow decline in the performance of the magnetic levitation compressor. Even without significant load changes or abnormal conditions, it can ensure the timeliness of the scheduling scheme.

[0152] In some implementations, whether the magnetic levitation compressor system is in operation can be determined in the following ways: when the central dispatch controller does not receive a system shutdown command and preset conditions are met, the preset conditions include at least one magnetic levitation compressor being in operation or the system's real-time heat load being greater than a preset minimum operating threshold, the system is determined to be in operation; conversely, when the central dispatch controller receives a system shutdown command or all magnetic levitation compressors are in shutdown state and the system's real-time heat load is zero or lower than a preset minimum operating threshold, the system is determined to be in non-operational state.

[0153] The system load change of a magnetic levitation compressor system can be calculated in the following way: when When, it is determined that the load is increasing; when If the load decreases, it is considered a load decrease; otherwise, it is considered a load stability. ; .

[0154] The operating status of a magnetic levitation compressor can be determined by comprehensively considering the power fluctuation, speed fluctuation, and rotor vibration amplitude of a single magnetic levitation compressor. The specific calculation method is as follows: Power fluctuation value calculation: Speed ​​fluctuation calculation: .in, Let be the average power fluctuation value of the i-th magnetic levitation compressor. Let be the input power of the i-th magnetic levitation compressor at time k. Let be the input power of the i-th magnetic levitation compressor at time k-1. Let be the rotational speed fluctuation value of the i-th magnetic levitation compressor. Let be the operating speed of the i-th magnetic levitation compressor at time k. Let be the operating speed of the i-th magnetic levitation compressor at time k-1.

[0155] The rotor vibration amplitude is directly acquired by a vibration sensor installed on the rotor of the i-th magnetic levitation compressor.

[0156] When the power fluctuation value of the i-th magnetic levitation compressor Less than the preset power fluctuation threshold, speed fluctuation value When the speed fluctuation is less than the preset threshold and the rotor vibration amplitude is less than the preset vibration threshold, the magnetic levitation compressor is determined to be in a stable operating state; otherwise, the magnetic levitation compressor is determined to be in an unstable operating state.

[0157] In this way, by constructing a closed-loop feedback optimization system, it is possible to respond in real time to system load fluctuations, equipment status changes and periodic operating requirements, ensuring that the system always maintains its optimal operating state during the operating cycle.

[0158] This application provides a magnetic levitation compressor system, which includes a central dispatch controller, multiple magnetic levitation compressors, and a sensor system. The central dispatch controller is connected to multiple magnetic levitation compressors and sensor systems. The sensor system is configured to collect system-side operating status data and equipment-side real-time operating condition parameters, and feed the data back to the central dispatch controller. The system-side operating status data includes supply water temperature, return water temperature and / or circulating water mass flow rate, and the equipment-side real-time operating condition parameters include the input power, operating speed, guide vane opening, operating status and / or rotor vibration amplitude of each magnetic levitation compressor. The central dispatch controller is configured to implement the aforementioned intelligent collaborative control method for multiple magnetic levitation compressors used for centralized heating.

[0159] Specifically, the central dispatch controller refers to the control and computing unit of the magnetic levitation compressor system. It can usually be implemented using an industrial-grade PLC or an embedded industrial control computer. It has high-speed data processing capabilities and the ability to solve complex mathematical models. It is responsible for receiving sensor data, executing scheduling algorithms, and generating and issuing control commands.

[0160] Multiple magnetic levitation compressors refer to the heating execution units of a magnetic levitation compressor system. Each magnetic levitation compressor is equipped with an independent local controller, variable frequency drive system and magnetic levitation bearing control system, and can receive instructions from the central dispatch controller to complete start-up, shutdown, speed regulation and guide vane opening regulation.

[0161] The sensor system refers to the sensing layer of the magnetic levitation compressor system. It consists of various sensors distributed on the heating system and each magnetic levitation compressor. It is responsible for converting the operating status of the physical world into digital signals and is the main channel for the central dispatch controller to obtain system information.

[0162] Communication connection refers to the bidirectional data transmission link established between components through an industrial bus. It typically uses industrial communication protocols such as Modbus RTU, Profinet, or Ethernet to ensure the real-time performance and reliability of data transmission.

[0163] Please see Figure 8 In some implementations, the magnetic levitation compressor system also includes a heating system, and the central dispatch controller also includes an optimization dispatch module, an AI prediction module, and a data processing module.

[0164] The heating system includes circulating water pumps, a heating pipe network, and terminal heat exchange equipment, which are connected to the output ends of multiple magnetic levitation compressors to deliver the heat generated by the compressors to the user end. Temperature and flow sensors are installed on the supply and return water pipes of the heating system to collect data on supply water temperature, return water temperature, and circulating water mass flow rate, and feed this data back to the data processing module of the central dispatch controller in real time.

[0165] The data processing module is configured to: receive system-side operating status data and real-time operating parameters from the equipment side collected by the sensor system; filter the raw data to remove or correct abnormal data caused by electromagnetic interference and sensor drift; calculate the real-time heat load of the system based on the supply water temperature, return water temperature, and circulating water mass flow rate; perform system status identification, including judging the system load change trend based on the heat load change rate within a preset time window, and judging the operating stability of the magnetic levitation compressor based on the power fluctuation value, speed fluctuation value, and rotor vibration amplitude of a single magnetic levitation compressor; and synchronously send the preprocessed data and status identification results to the optimization scheduling module and the AI ​​prediction module.

[0166] The optimized scheduling module is configured to: load the corresponding energy efficiency model, power model, and heating capacity model from a preset compressor performance model library based on the equipment identification information of each magnetic levitation compressor; dynamically adjust the values ​​of the start-stop weight coefficient λ1 and the state penalty weight coefficient λ2 based on the system state identification results; construct a multi-machine collaborative optimization model including total energy consumption, start-stop penalty, and state penalty terms, and combine preset constraints such as total heat load matching, operating parameter range, and minimum operation / downtime; generate all feasible candidate magnetic levitation compressor operation schemes; calculate the input power and heating capacity of each magnetic levitation compressor under each scheme; substitute them into the objective function to obtain the optimal scheduling scheme with the minimum objective function value; generate gradual adjustment control commands based on the optimal scheduling scheme and issue them to each magnetic levitation compressor controller and the heating system circulating water pump for execution.

[0167] The AI ​​prediction module is configured to use time-series forecasting algorithms to make short-term predictions of the system's heat load over a certain period of time, based on historical operating data and meteorological data. The load prediction results are then sent to the optimization scheduling module to assist in generating pre-scheduling plans and improving the system's response speed to load fluctuations. When the system load changes rapidly, the module adjusts the operating status of the magnetic levitation compressor in advance to avoid user experience degradation or energy waste caused by delayed heat supply.

[0168] In this way, by matching the compressor performance model corresponding to each magnetic levitation compressor, the magnetic levitation compressor system can fully consider the differentiated efficiency characteristics of different magnetic levitation compressors under different operating conditions. Furthermore, by constructing and solving a multi-machine collaborative optimization model, the magnetic levitation compressor system can guide each magnetic levitation compressor to operate within its own optimal efficiency range, effectively alleviating the technical problems of high energy consumption and low efficiency. This provides technical support for the efficient and stable operation of the multi-machine parallel magnetic levitation compressor system, improving the overall energy efficiency of the system.

[0169] This application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the steps of the intelligent coordinated control method for multiple magnetic levitation compressors for centralized heating as described above.

[0170] It is understood that a computer program includes computer program code. Computer program code can be in the form of source code, object code, executable files, or some intermediate form. Computer-readable storage media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0171] In this specification, the terms "specifically," "furthermore," "particularly," "understandably," etc., refer to specific features, structures, materials, or characteristics described in connection with embodiments or examples that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0172] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of executable request code comprising one or more steps for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0173] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for intelligent coordinated control of multiple magnetic levitation compressors for centralized heating, characterized in that, The method includes: Obtain the equipment identification information and real-time operating parameters of each magnetic levitation compressor; Based on the device identification information, a target compressor performance model corresponding to each magnetic levitation compressor is determined from the preset compressor performance model. The target compressor performance model includes a first energy efficiency model, a first power model, and a first heating capacity model. Based on the real-time operating parameters, the first energy efficiency model, the first power model, and the first heating capacity model, the multi-machine collaborative optimization model of the magnetic levitation compressor system is determined. With the goal of minimizing total system energy consumption and based on preset constraints, the multi-machine collaborative optimization model is analyzed to obtain the target scheduling scheme; Control commands are generated according to the target scheduling scheme, and the control commands are sent to each of the magnetic levitation compressors for execution.

2. The method according to claim 1, characterized in that, The real-time operating condition parameters include system-side operating status data, equipment-side real-time operating condition parameters, and system real-time heat load. Obtaining the equipment identification information and real-time operating condition parameters for each magnetic levitation compressor includes: Based on the sensor system in the magnetic levitation compressor system, the equipment identification information, the system-side operating status data, and the equipment-side real-time operating condition parameters are collected. The system-side operating status data includes water supply temperature, return water temperature, and / or circulating water mass flow rate. The equipment-side real-time operating condition parameters include the input power, operating speed, guide vane opening, operating status, and / or rotor vibration amplitude of each magnetic levitation compressor. The real-time heat load of the system is calculated based on the supply water temperature, the return water temperature, and the circulating water mass flow rate.

3. The method according to claim 2, characterized in that, The method further includes: The system-side operating status data and the equipment-side real-time operating condition parameters are filtered to remove or correct abnormal data.

4. The method according to claim 1, characterized in that, The preset compressor performance model is established in advance in the following way: Based on the obtained historical operating parameters, a performance sample dataset of magnetic levitation compressors is generated. The historical operating parameters include the input power, flow rate, temperature and corresponding heating capacity of each magnetic levitation compressor under different operating speeds, different guide vane openings and / or different temperature conditions. The performance sample dataset of the magnetic levitation compressor is fitted with a function to establish the preset compressor performance model, wherein the preset compressor performance model includes a second energy efficiency model, a second power model, and a second heating capacity model.

5. The method according to claim 1, characterized in that, The multi-machine collaborative optimization model includes an objective function, which can be expressed as the following relationship: ； in, Let N be the input power of the i-th magnetic levitation compressor, and N be the total number of magnetic levitation compressors in the magnetic levitation compressor system. Let i represent the current operating state of the i-th magnetic levitation compressor. This represents the previous operating state of the i-th magnetic levitation compressor. The degree to which the i-th magnetic levitation compressor deviates from its optimal operating range. This refers to the start / stop weighting coefficient. This represents the state penalty weight coefficient.

6. The method according to claim 5, characterized in that, The preset constraints include a first constraint, a second constraint, a third constraint, and / or a fourth constraint. The first constraint indicates that the sum of the heating capacity of each magnetic levitation compressor is equal to the real-time heat load of the system. The second constraint indicates that the operating speed of each magnetic levitation compressor is between the minimum speed and the maximum speed. The third constraint indicates that the guide vane opening of each magnetic levitation compressor is between the minimum opening and the maximum opening. The fourth constraint indicates that each magnetic levitation compressor needs to run continuously for a minimum time after startup and needs to be shut down for a minimum time after shutdown.

7. The method according to claim 1 or 6, characterized in that, The process of minimizing total system energy consumption and analyzing the multi-machine collaborative optimization model based on preset constraints to obtain a target scheduling scheme includes: Generate candidate magnetic levitation compressor operation schemes, each candidate magnetic levitation compressor operation scheme including the operation status, operation speed and / or guide vane opening of each candidate magnetic levitation compressor; Under the preset constraints, based on the multi-machine collaborative optimization model, the input power and heating capacity of each candidate magnetic levitation compressor under each candidate magnetic levitation compressor operation scheme are calculated; Substituting the input power and the heating capacity into the multi-machine collaborative optimization model, the objective function value of each candidate magnetic levitation compressor operation scheme is calculated; The candidate magnetic levitation compressor operation scheme that minimizes the objective function value is selected as the target scheduling scheme. The target scheduling scheme includes the operating status, operating speed and / or guide vane opening of each magnetic levitation compressor.

8. The method according to claim 1, characterized in that, The step of sending the control command to each of the magnetic levitation compressors for execution includes: The control commands are sent to each of the magnetic levitation compressors using a gradual adjustment method to avoid impacting the magnetic levitation compressor system.

9. The method according to claim 1, characterized in that, The method further includes: After the control command is executed, system-side operating status data is collected; When the magnetic levitation compressor system is in operation, if the system load of the magnetic levitation compressor system changes beyond a preset threshold, or the operating status of the magnetic levitation compressor changes, or the operating cycle of the magnetic levitation compressor system reaches a preset optimization cycle, the equipment identification information and real-time operating condition parameters of each magnetic levitation compressor are obtained again. Based on the real-time operating parameters, the first energy efficiency model, the first power model, and the first heating capacity model, the multi-machine collaborative optimization model of the magnetic levitation compressor system is determined again. With the goal of minimizing total system energy consumption and based on preset constraints, the multi-machine collaborative optimization model is analyzed to obtain the target scheduling scheme; Control commands are generated according to the target scheduling scheme, and the control commands are sent to each of the magnetic levitation compressor controllers for execution.

10. A magnetic levitation compressor system, characterized in that, The magnetic levitation compressor system includes a central dispatch controller, multiple magnetic levitation compressors, and a sensor system. The central dispatch controller is communicatively connected to multiple magnetic levitation compressors and the sensor system, respectively. The sensor system is configured to collect system-side operating status data and equipment-side real-time operating condition parameters, and feed the data back to the central dispatch controller. The system-side operating status data includes water supply temperature, return water temperature and / or circulating water mass flow rate, and the equipment-side real-time operating condition parameters include the input power, operating speed, guide vane opening, operating status and / or rotor vibration amplitude of each magnetic levitation compressor. The central dispatch controller is configured to execute the intelligent collaborative control method for multiple magnetic levitation compressors for centralized heating as described in any one of claims 1-9.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by one or more processors, implements the method as described in any one of claims 1-9.

Images