Dust collector multi-motor cooperative speed regulation and energy efficiency optimization control method and device

Abstract

The invention relates to the technical field of dust collector control, and discloses a multi-motor cooperative speed regulation and energy efficiency optimization control method and device for a dust collector, and the method comprises the steps: monitoring the rotating speed, current, voltage, temperature and other operation parameters of a plurality of motors in real time, and determining the working load state of each motor through a load recognition model. Different cooperative speed regulation strategies are matched according to load states, such as PID control for low loads, fuzzy logic control for medium loads and model prediction control for high loads. A dynamic weight distribution algorithm is used for adjusting the target rotating speed, and an energy efficiency optimization algorithm is used for optimizing power distribution. Meanwhile, environmental parameters are considered, and control parameters are optimized through a self-adaptive parameter adjustment model. And the system also has the functions of adjusting strategies according to load fluctuation and power consumption, motor priority ranking during high load, energy efficiency algorithm parameter optimization, rotating speed adjustment during filter screen blockage, motor state monitoring and prediction and the like, so that accurate speed regulation and efficient energy conservation are realized, and the performance and the intelligent level of the dust collector are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vacuum cleaner control, and particularly to a method and device for multi-motor collaborative speed regulation and energy efficiency optimization control of a vacuum cleaner. Background Art

[0002] With the improvement of living quality, people's requirements for the performance of vacuum cleaners are becoming increasingly stringent, which promotes the continuous innovation of vacuum cleaner technology. The multi-motor technology has emerged accordingly. It enables multiple motors to work collaboratively, respectively responsible for functions such as dust suction, driving the brush head, and controlling the air flow, significantly improving the cleaning effect and user experience. However, when multiple motors work together, they face many challenges, resulting in obvious deficiencies in the speed regulation control and energy efficiency optimization of existing vacuum cleaners.

[0003] In terms of speed regulation control, the load conditions faced by different motors during the operation of a vacuum cleaner vary greatly. Taking a common household vacuum cleaner as an example, when cleaning the floor, the motor responsible for driving the brush head to rotate may bear different degrees of frictional resistance due to different floor materials (such as carpets and wooden floors), and the load changes frequently; while the motor responsible for generating suction will experience load fluctuations due to the amount of dust suction and the change in the degree of filter clogging. However, the traditional speed regulation control methods are too single, mostly only using simple open-loop or closed-loop control, and cannot accurately identify the real-time load state of the motor. When the motor load changes, it is difficult to quickly and accurately adjust the speed, thereby affecting the cleaning effect. For example, when cleaning a thick carpet, if the motor cannot increase the speed in time, the cleaning power of the brush head will be insufficient, resulting in difficult removal of dirt; while when cleaning a relatively smooth wooden floor, if the motor speed is not reduced in time, it will not only cause energy waste, but also may damage the floor due to the too-fast rotation speed of the brush head.

[0004] From the perspective of energy efficiency optimization, the energy issue has become a global focus of attention. As a commonly used household appliance, the energy efficiency optimization of a vacuum cleaner is of great importance. However, many current vacuum cleaners do not fully consider the reasonable distribution of motor power during design. On the one hand, when each motor operates under different loads, it fails to dynamically adjust the power according to the actual demand, resulting in unnecessary consumption of energy. For example, in a low-load working condition, the motor still operates at a high power, wasting a large amount of electric energy. On the other hand, the influence of working environment factors (such as environmental temperature, power supply voltage fluctuation, air flow resistance coefficient, etc.) on the energy efficiency of the motor is ignored. When the environmental temperature is too high, it is difficult for the motor to dissipate heat, the internal resistance increases, and the proportion of electric energy converted into heat increases, resulting in a decrease in energy efficiency; the power supply voltage fluctuation will make the actual input power of the motor unstable, deviating from the optimal working point, also leading to a decrease in energy efficiency. This not only increases the user's usage cost but also does not conform to the development trend of energy conservation and environmental protection.

[0005] In a complex scenario where multiple motors work together, there is a lack of an effective coordination mechanism. When multiple motors are simultaneously in a high-load state, the existing technology cannot reasonably allocate resources and determine the priority of the motors, which easily causes some key motors to fail to work properly due to insufficient power, affecting the overall performance of the vacuum cleaner. Moreover, the means for monitoring and predicting the motor state are limited, and potential motor failures cannot be detected in time, nor can the control strategy be adjusted in advance to cope with load changes, reducing the reliability and intelligence level of the vacuum cleaner. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and device for coordinated speed regulation and energy efficiency optimization control of multiple motors in a vacuum cleaner to solve the problems raised in the above background technology.

[0007] To achieve the above purpose, the present invention provides the following technical solution: A method for coordinated speed regulation and energy efficiency optimization control of multiple motors in a vacuum cleaner, the method comprising:

[0008] Real-time monitoring of the operating parameters of multiple motors in the vacuum cleaner, including speed, current, voltage, and temperature; based on the real-time monitored operating parameters, identifying the current working load state of each motor through a load identification model, the load identification model using a regression algorithm and being trained and generated through the motor operating data with historical labeled load states;

[0009] Matching the corresponding coordinated speed regulation strategy according to the identified working load state, the coordinated speed regulation strategy including: PID proportional-integral-derivative control matched with a low-load state, fuzzy logic control matched with a medium-load state, and model predictive control matched with a high-load state;

[0010] Based on the matched coordinated speed regulation strategy, respectively using a dynamic weight allocation algorithm to dynamically adjust the target speed of each motor, and using an energy efficiency optimization algorithm to constrain and optimize the motor power distribution.

[0011] Preferably, the method further comprises:

[0012] The formula for adopting the PID control strategy is as follows:

[0013]

[0014] wherein, u(t) is the control output, e(t) is the speed error, K p 、K i 、K d are weight coefficients; the membership function for adopting the fuzzy logic control strategy is a triangular distribution function, and the input variables are load deviation and deviation change rate;

[0015] The optimization objective function for adopting the model predictive control is:

[0016]

[0017] Among them, Δr(k) is the rotational speed deviation at the k-th prediction step, P(k) is the power distribution vector, N is the length of the prediction time domain, representing the upper limit of the number of future optimization steps in model predictive control, and λ is the weight factor; the deviation between the actual rotational speed and the target rotational speed of each motor is updated through a real-time feedback mechanism, and the cooperative speed regulation strategy and energy efficiency optimization parameters are iteratively adjusted.

[0018] The environmental parameters of the vacuum cleaner working environment are collected in real time, including environmental temperature, power supply voltage fluctuation value, and air flow resistance coefficient.

[0019] The current environmental parameters, load status, and the matching cooperative speed regulation strategy are input into the adaptive parameter adjustment model, and the optimal control parameters under the current environment are output. The PID weight coefficient, fuzzy logic rule base, or model predictive weight factor is adjusted according to the optimal control parameters; the adaptive parameter adjustment model is generated by training with the optimal parameters marked under historical environmental parameters, load status, and cooperative speed regulation strategy.

[0020] Preferably, the method further includes:

[0021] The historical load data of each motor within a preset time period is statistically analyzed, and the load fluctuation variance and average power consumption are calculated.

[0022] If the load fluctuation variance exceeds the preset threshold, the response speed of the cooperative speed regulation strategy is dynamically adjusted based on the sliding window algorithm; if the average power consumption is higher than the preset energy consumption limit, the power constraint weight in the energy efficiency optimization algorithm is increased.

[0023] Preferably, the method further includes:

[0024] When it is recognized that at least two motors are in a high-load state, the fuzzy logic decision module is used to sort the priorities of each motor.

[0025] The input variables of the fuzzy logic decision module include the motor temperature rise rate, current overshoot, and task urgency, and the output is the scheduling priority of each motor. The target rotational speed is adjusted by dynamically assigning weight coefficients based on the priority.

[0026] Preferably, the method further includes:

[0027] The genetic algorithm is used to globally search and optimize the power distribution parameters of the energy efficiency optimization algorithm, specifically including:

[0028] Initialize the population, and the encoded parameter is the power distribution ratio of each motor.

[0029] Define the fitness function as the weighted sum of the total energy consumption and the rotational speed tracking error.

[0030] Iteratively update the population through selection, crossover, and mutation operations until the convergence condition is met or the maximum number of iterations is reached.

[0031] Preferably, the method further includes:

[0032] Introduce Pareto front analysis in the multi-objective optimization process to screen the non-dominated solution set that simultaneously satisfies the lowest energy consumption, the smallest rotational speed error, and the slowest temperature rise;

[0033] Determine the final power distribution scheme from the non-dominated solution set based on the entropy weight method.

[0034] Preferably, the method further includes:

[0035] Real-time monitor the clogging degree of the vacuum cleaner filter, and dynamically adjust the rotational speed upper limit of each motor according to the clogging degree level;

[0036] If the clogging degree reaches the preset threshold, reduce the target rotational speed of the high-load motor and increase the rotational speed compensation amount of the low-load motor.

[0037] Preferably, the method further includes:

[0038] Construct the state space model of each motor, and based on the Kalman filter, perform real-time estimation on the actual rotational speed and load state of the motor;

[0039] Use the residual between the estimated value and the measured value as a feedback signal to correct the control output in the cooperative speed regulation strategy.

[0040] Preferably, the method further includes:

[0041] Use a long short-term memory neural network to predict the load change trend within a future time window;

[0042] Based on the prediction result, adjust the target rotational speed setting value and power distribution parameters in the cooperative speed regulation strategy in advance.

[0043] Preferably, the present invention further includes a vacuum cleaner multi-motor cooperative speed regulation and energy efficiency optimization control device, and the device includes:

[0044] Operating parameter monitoring module: used to monitor the operating parameters of multiple motors in the vacuum cleaner in real time, including rotational speed, current, voltage, and temperature;

[0045] Load identification module: connected to the operating parameter monitoring module, based on the real-time monitored operating parameters, through the use of a regression algorithm and a load identification model trained with historical motor operating data with labeled load states, identify the current working load state of each motor;

[0046] Speed regulation strategy matching module: Connected to the load identification module, it matches the corresponding cooperative speed regulation strategy according to the identified working load state. The cooperative speed regulation strategy includes PID proportional-integral-derivative control matched with the low-load state, fuzzy logic control matched with the medium-load state, and model predictive control matched with the high-load state;

[0047] Speed regulation and energy efficiency optimization module: Connected to the speed regulation strategy matching module, based on the matched cooperative speed regulation strategy, it dynamically adjusts the target speed of each motor using the dynamic weight allocation algorithm and constrains and optimizes the motor power distribution using the energy efficiency optimization algorithm.

[0048] Compared with the prior art, the beneficial effects of the present invention are:

[0049] In terms of the accuracy of speed regulation control, by real-time monitoring of the operating parameters of the motor such as speed, current, voltage, and temperature, and with the help of a load identification model trained using a regression algorithm, the working load state of each motor can be accurately identified. Whether it is the load difference caused by the complex and changeable floor materials during the cleaning process or the load change of the suction motor caused by the filter clogging, it can be accurately judged. Based on the cooperative speed regulation strategy matched with the load state, PID control is used at low load to quickly and stably adjust the motor speed; fuzzy logic control under medium load can flexibly adjust according to the load deviation and the rate of change of the deviation; model predictive control plays a role at high load, and combined with the real-time feedback mechanism, it iteratively optimizes. This enables the motor to quickly and accurately adjust the speed under various working conditions, ensuring consistent cleaning effects. For example, when cleaning floors of different materials, both the brush head motor and the suction motor can be adjusted to the optimal speed according to the actual load, effectively removing dirt while avoiding damage to the floor.

[0050] At the level of energy efficiency optimization, by adjusting the target speed using the dynamic weight allocation algorithm and constraining the motor power distribution with the energy efficiency optimization algorithm, the power requirements of the motor under different loads are fully considered. The power output is reduced at low load, and the power is reasonably distributed at high load to avoid energy waste. Moreover, environmental parameters such as ambient temperature, power supply voltage fluctuation value, and air flow resistance coefficient are collected in real time, and the adaptive parameter adjustment model is used to optimize the control parameters, enabling the motor to maintain efficient operation in different environments. This not only reduces the user's electricity cost but also responds to the call for energy conservation and environmental protection, conforming to the concept of sustainable development.

[0051] When multiple motors are in a high-load state, the fuzzy logic decision-making module ranks the motors according to the motor temperature rise rate, current overshoot, and task urgency, and reasonably allocates the dynamic weight coefficient to adjust the target speed. Ensure that the key motors can obtain sufficient power first, maintain the overall performance of the vacuum cleaner, and improve the reliability and stability of the system under complex working conditions.

[0052] By constructing a motor state space model, the Kalman filter is used to estimate the actual speed and load state of the motor in real time. The residual error between the estimated value and the measured value is fed back to correct the control output, improving the control accuracy. The long short-term memory neural network predicts the future load change trend, adjusts the target speed setting value and power distribution parameters in advance, making the vacuum cleaner forward-looking, enhancing the intelligent level, and reducing the performance degradation and failure risk caused by sudden load changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is the flowchart of the multi-motor coordinated speed regulation and energy efficiency optimization control method for the vacuum cleaner described in the present invention;

[0054] Figure 2 is the flowchart of the coordinated speed regulation strategy and parameter adjustment;

[0055] Figure 3 is the flowchart of the strategy adjustment flow based on load and energy consumption;

[0056] Figure 4 is the flowchart of the parameter optimization of the energy efficiency optimization algorithm. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] Please refer to Figures 1-4 , the present invention provides a technical solution: a multi-motor coordinated speed regulation and energy efficiency optimization control method for a vacuum cleaner, the method includes:

[0059] Real-time monitor the operating parameters of multiple motors in the vacuum cleaner, including speed, current, voltage and temperature. Use high-precision sensors, such as speed sensors, current sensors, voltage sensors and temperature sensors, which are respectively installed at the corresponding positions of each motor in the vacuum cleaner, continuously collect the operating parameters of the motors, and transmit these data to the control unit in real time.

[0060] Based on the real-time monitored operating parameters, identify the current working load state of each motor through a load identification model. The load identification model uses a regression algorithm and is trained and generated through the motor operating data with historical marked load states. Input the collected operating parameters into the pre-trained load identification model, and the model analyzes and processes the data based on the regression algorithm to determine whether each motor is in a low-load, medium-load or high-load state.

[0061] Match the corresponding collaborative speed regulation strategy according to the recognized workload status. The collaborative speed regulation strategy includes: PID proportional-integral-derivative control matched with the low-load status, fuzzy logic control matched with the medium-load status, and model predictive control matched with the high-load status. When the load recognition model determines that a certain motor is in the low-load status, the control unit calls the PID control strategy; when it is in the medium-load status, it calls the fuzzy logic control strategy; when it is in the high-load status, it calls the model predictive control strategy.

[0062] Based on the matched collaborative speed regulation strategy, the target speed of each motor is dynamically adjusted using the dynamic weight allocation algorithm, and the motor power distribution is constrained and optimized using the energy efficiency optimization algorithm. According to different collaborative speed regulation strategies, the dynamic weight allocation algorithm assigns reasonable target speed weights to each motor based on factors such as the load condition and operating state of the motor, and then adjusts the target speed; the energy efficiency optimization algorithm optimizes the motor power distribution according to the power consumption characteristics and load requirements of the motor to achieve the purpose of energy conservation.

[0063] The present invention will be further described below in conjunction with Embodiments 1 to 5:

[0064] Embodiment 1:

[0065] The function of this embodiment is to enable the vacuum cleaner to better adapt to different working conditions, improve the control accuracy and energy efficiency by adjusting the parameters of different control strategies and collecting and utilizing the working environment parameters of the vacuum cleaner.

[0066] On the basis of the above overall implementation scheme, the following further content is included:

[0067] The formula for adopting the PID control strategy is as follows:

[0068]

[0069] Among them, u(t) is the control output, e(t) is the speed error, and K p 、K i 、K d are weight coefficients. In the low-load status, the PID control strategy can accurately control the motor speed. For example, when the vacuum cleaner is cleaning a relatively empty ground area, the motor load is low. At this time, using PID control, by continuously adjusting the values of K p 、K i 、K d , the motor speed is stabilized near the set value to ensure stable suction of the vacuum cleaner and low energy consumption.

[0070] The membership function of the fuzzy logic control strategy is a triangular distribution function, and the input variables are the load deviation and the deviation change rate. When in the medium load state, the fuzzy logic control comes into play. Suppose when the vacuum cleaner is cleaning a floor with some debris, the motor load is at a medium level. The fuzzy logic control fuzzifies these input variables according to the load deviation and the deviation change rate through the membership function of the triangular distribution function, and then makes inferences based on the pre-set fuzzy rule base to obtain the corresponding control output, so as to realize the reasonable adjustment of the motor speed, which can not only ensure that the suction force meets the cleaning requirements but also take into account energy efficiency.

[0071] The optimization objective function of the model predictive control is:

[0072]

[0073] Among them, Δr(k) is the rotational speed deviation at the k-th prediction step, P(k) is the power distribution vector, N is the prediction horizon length, representing the upper limit of the number of future optimization steps in the model predictive control, and λ is the weight factor; the deviation between the actual rotational speed and the target rotational speed of each motor is updated through a real-time feedback mechanism, and the cooperative speed regulation strategy and the energy efficiency optimization parameters are iteratively adjusted. In the high load state, such as when the vacuum cleaner picks up a large amount of heavy debris, the model predictive control uses this optimization objective function, combined with the real-time feedback rotational speed deviation, to continuously adjust the control strategy and the energy efficiency optimization parameters to minimize energy consumption and improve the motor operation efficiency while meeting the high load working requirements.

[0074] The environmental parameters of the vacuum cleaner working environment are collected in real time, including the environmental temperature, the power supply voltage fluctuation value, and the air flow resistance coefficient. An environmental temperature sensor, a power supply voltage monitoring module, and related devices for detecting the air flow resistance coefficient are installed at appropriate positions on the outer shell or inside of the vacuum cleaner. The environmental temperature sensor monitors the environmental temperature in real time, the power supply voltage monitoring module monitors the power supply voltage fluctuation value, and the air flow resistance coefficient detection device calculates the air flow resistance coefficient by measuring parameters such as the air flow pressure in the vacuum cleaner air duct. These environmental parameters will affect the operation performance and energy consumption of the motor.

[0075] The current environmental parameters, load state, and the matching cooperative speed regulation strategy are input into the adaptive parameter adjustment model, and the optimal control parameters in the current environment are output. The PID weight coefficient, the fuzzy logic rule base, or the model predictive weight factor is adjusted according to the optimal control parameters; the adaptive parameter adjustment model is trained and generated by the optimal parameters marked under the historical environmental parameters, load state, and cooperative speed regulation strategy. For example, when the environmental temperature rises, the heat dissipation condition of the motor becomes worse. At this time, the adaptive parameter adjustment model outputs the corresponding optimal control parameters according to the input environmental temperature, load state, and the current cooperative speed regulation strategy adopted. If the current is the PID control strategy, adjust K p 、K i 、Kd Weight coefficient; if it is a fuzzy logic control strategy, optimize the fuzzy logic rule base; if it is a model predictive control strategy, adjust the weight factor λ, so that the vacuum cleaner can maintain a good operating state in different environments.

[0076] Embodiment 2:

[0077] The function of this embodiment is to dynamically adjust the response speed of the coordinated speed control strategy and the power constraint weight of the energy efficiency optimization algorithm through the statistical analysis of the historical load data of the motor, and further improve the performance and energy efficiency of the vacuum cleaner.

[0078] Statistically analyze the historical load data of each motor within a preset time period, and calculate the load fluctuation variance and average power consumption. The control unit is built-in with a data storage module for storing the load data of the motor within a preset time period (such as the past 10 minutes or 30 minutes). Using statistical methods, calculate the load fluctuation variance to measure the degree of load fluctuation; at the same time, calculate the average power consumption to understand the energy consumption of the motor during this time period.

[0079] If the load fluctuation variance exceeds the preset threshold, dynamically adjust the response speed of the coordinated speed control strategy based on the sliding window algorithm. When the load fluctuation variance is large, it indicates that the motor load changes frequently. For example, when cleaning an area with alternating carpets and floors, the motor load will change frequently. At this time, use the sliding window algorithm, with a certain time window (such as 1 minute) as the unit, to dynamically adjust the response speed of the coordinated speed control strategy. If the load fluctuation variance exceeds the preset threshold, increase the response speed of the control strategy, so that the motor can adapt to the load change more quickly and ensure the stable suction of the vacuum cleaner.

[0080] If the average power consumption is higher than the preset energy consumption limit, increase the power constraint weight in the energy efficiency optimization algorithm. When the average power consumption is too high, it indicates that the motor energy consumption is too large. For example, when cleaning a high-resistance area (such as deep cleaning a carpet) for a long time, the motor power consumption may exceed the preset limit. At this time, increase the power constraint weight in the energy efficiency optimization algorithm, so that the energy efficiency optimization algorithm more strictly controls the motor power distribution, and reduces the motor power consumption on the premise of ensuring the cleaning effect, and improves the energy efficiency of the vacuum cleaner.

[0081] Embodiment 3:

[0082] The function of this embodiment is that when multiple motors are in a high-load state, by sorting the motor priorities and adjusting the target speeds, ensure that the vacuum cleaner can reasonably allocate resources, give priority to ensuring the operation of key motors, and improve the overall working efficiency.

[0083] When at least two motors are identified to be in a high-load state, a fuzzy logic decision-making module is used to sort the priorities of each motor. The fuzzy logic decision-making module is integrated into the control unit of the vacuum cleaner and starts to work when the load identification module detects that at least two motors are in a high-load state. For example, when cleaning a complex environment, the suction motor and the roller brush motor may be in a high-load state simultaneously.

[0084] The input variables of the fuzzy logic decision-making module include the motor temperature rise rate, the current overshoot, and the task urgency. The output is the scheduling priority of each motor. Based on the priority, a dynamic weight coefficient is assigned to adjust the target speed. The motor temperature rise rate reflects the heat generation situation of the motor, the current overshoot reflects the degree of mutation of the motor load, and the task urgency is determined according to the current working mode of the vacuum cleaner and the user settings. The fuzzy logic decision-making module outputs the scheduling priority of each motor according to these input variables through preset fuzzy rules and inference mechanisms. For motors with a high priority, a larger dynamic weight coefficient is assigned to increase their target speed; for motors with a low priority, the target speed is appropriately reduced, so as to reasonably allocate the power and speed resources of the motors.

[0085] Embodiment 4:

[0086] The function of this embodiment is to optimize the power distribution parameters of the energy efficiency optimization algorithm through the genetic algorithm, and introduce the Pareto front analysis and the entropy weight method for multi-objective optimization, so that the vacuum cleaner achieves a better balance in terms of energy consumption, speed error, and temperature rise.

[0087] The genetic algorithm is used to globally search and optimize the power distribution parameters of the energy efficiency optimization algorithm, specifically including:

[0088] Initialize the population, and the coding parameter is the power distribution ratio of each motor. Run the genetic algorithm program in the control unit to randomly generate an initial population. The coding of each individual represents the power distribution ratio of each motor. For example, assuming there are two motors, the coding of an individual may be [0.6, 0.4], indicating that the first motor is allocated 60% of the power and the second motor is allocated 40% of the power.

[0089] Define the fitness function as the weighted sum of the total energy consumption and the speed tracking error. According to the working requirements of the vacuum cleaner, appropriate weights are set for the total energy consumption and the speed tracking error to construct the fitness function. For example, the fitness function can be expressed as: F = w1E + w2S, where F is the fitness value, E is the total energy consumption, S is the speed tracking error, and w1 and w2 are the weight coefficients.

[0090] Iteratively update the population through selection, crossover, and mutation operations until the convergence condition is met or the maximum number of iterations is reached. The genetic algorithm retains individuals with higher fitness through the selection operation; through the crossover operation, it simulates gene exchange in biological inheritance to generate new individuals; through the mutation operation, it randomly changes the genes of individuals with a certain probability to increase the diversity of the population. Continuously iterate these operations until the convergence condition (such as the fitness value no longer changes significantly) is met or the maximum number of iterations is reached, thus obtaining a set of relatively optimal power allocation parameters.

[0091] Introduce Pareto front analysis in the multi-objective optimization process to screen out the non-dominated solution set that simultaneously meets the lowest energy consumption, the smallest rotational speed error, and the slowest temperature rise. In the optimization process of the genetic algorithm, energy consumption, rotational speed error, and temperature rise are used as multiple optimization objectives. Pareto front analysis can find the non-dominated solution set that achieves the optimal balance among these objectives. For example, in a set of solutions, some solutions may have lower energy consumption but larger rotational speed errors, while others are the opposite. Through Pareto front analysis, screen out those solutions that are relatively optimal in terms of energy consumption, rotational speed error, and temperature rise to form a non-dominated solution set.

[0092] Determine the final power allocation scheme from the non-dominated solution set based on the entropy weight method. The entropy weight method is an objective weighting method that determines weights according to the variation degree of each objective data. For the non-dominated solution set obtained by Pareto front analysis, use the entropy weight method to calculate the weights of the three objectives of energy consumption, rotational speed error, and temperature rise, and then select the most suitable solution from the non-dominated solution set as the final power allocation scheme according to these weights, so that the vacuum cleaner can achieve better performance in multiple performance indicators.

[0093] Example 5:

[0094] The function of this embodiment is to monitor and handle the clogging degree of the vacuum cleaner filter, and to estimate the real-time state of the motor and predict the future load change, so as to adjust the motor speed and control strategy in advance, and improve the cleaning effect and operation stability of the vacuum cleaner.

[0095] Real-time monitor the clogging degree of the vacuum cleaner filter, and dynamically adjust the speed limit of each motor according to the clogging degree level. Install a clogging detection sensor, such as a differential pressure sensor, at the filter position of the vacuum cleaner. Judge the clogging degree of the filter by detecting the pressure difference on both sides of the filter, and divide the clogging degree into different levels. For example, mild clogging, moderate clogging, and severe clogging. When the filter is mildly clogged, appropriately reduce the speed limit of the motor; when the clogging degree increases, further reduce the speed limit to avoid damage to the motor due to excessive load, and at the same time ensure the stable suction of the vacuum cleaner.

[0096] If the degree of blockage reaches the preset threshold, the target speed of the high-load motor is reduced and the speed compensation amount of the low-load motor is increased. When the degree of filter screen blockage reaches the preset threshold, it indicates that the working resistance of the vacuum cleaner has increased significantly. At this time, reducing the target speed of the high-load motor can prevent the motor from overloading; at the same time, increasing the speed compensation amount of the low-load motor can maintain the overall cleaning effect. For example, when the suction motor is in a high-load state and other auxiliary motors are in a low-load state, the target speed of the suction motor is reduced and the speed compensation amount of the auxiliary motor is increased to ensure that the vacuum cleaner can still work properly under the condition of filter screen blockage.

[0097] Construct the state space model of each motor, and use the Kalman filter to estimate the actual speed and load state of the motor in real time; take the residual between the estimated value and the measured value as the feedback signal to correct the control output in the coordinated speed control strategy. In the control unit, construct the state space model according to the physical characteristics and operating principles of the motor. The Kalman filter uses this model and combines the measured data of the motor (such as speed, current, etc.) to estimate the actual speed and load state of the motor in real time. Feed the residual between the estimated value and the measured value back to the coordinated speed control strategy to correct the control output and improve the accuracy of the control. For example, when there is a deviation between the motor speed estimated by the Kalman filter and the actual measured speed, adjust the output of the PID control strategy according to the residual to make the motor speed closer to the target value.

[0098] Use the long short-term memory neural network to predict the load change trend within the future time window; based on the prediction result, adjust the target speed setting value and power distribution parameters in the coordinated speed control strategy in advance. Train the long short-term memory neural network (LSTM) in the control unit, and use the historical operation data and load data of the motor as training samples. The LSTM network can learn the time series characteristics of load changes and predict the load change trend within the future time window (such as the next 5 minutes). According to the prediction result, adjust the target speed setting value and power distribution parameters in the coordinated speed control strategy in advance. If it is predicted that the load will increase, increase the target speed of the motor and adjust the power distribution in advance to enable the vacuum cleaner to adapt to the load change in advance and ensure the cleaning effect and energy efficiency.

[0099] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0100] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will appreciate that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for coordinated speed regulation and energy efficiency optimization control of multiple motors in a vacuum cleaner, characterized in that, Including: Real-time monitoring of the operating parameters of multiple motors in the vacuum cleaner, including rotational speed, current, voltage, and temperature; Based on the real-time monitored operating parameters, identifying the current working load status of each motor through a load identification model. The load identification model uses a regression algorithm and is trained with historical motor operating data with labeled load status; According to the identified working load status, matching the corresponding coordinated speed regulation strategy. The coordinated speed regulation strategy includes: PID proportional-integral-derivative control matched with the low load status, fuzzy logic control matched with the medium load status, and model predictive control matched with the high load status; Based on the matched coordinated speed regulation strategy, dynamically adjusting the target rotational speed of each motor using the dynamic weight allocation algorithm, and using the energy efficiency optimization algorithm to optimize and constrain the motor power distribution.

2. The multi-motor collaborative speed regulation and energy efficiency optimization control method for a vacuum cleaner according to claim 1, wherein It also includes: The formula for adopting the PID control strategy is as follows: where, u(t) is the control output, e(t) is the rotational speed error, and K p , K i , K d are weighting coefficients; the membership function adopting the fuzzy logic control strategy is a triangular distribution function, and the input variables are the load deviation and the deviation change rate; The optimization objective function for adopting model predictive control is: Where, Δr(k) is the rotational speed deviation at the k-th prediction step, P(k) is the power distribution vector, N is the prediction time domain length, representing the upper limit of the number of future optimization steps in model predictive control, and λ is the weight factor; updating the deviation between the actual rotational speed and the target rotational speed of each motor through a real-time feedback mechanism, and iteratively adjusting the coordinated speed regulation strategy and the energy efficiency optimization parameters; Real-time collecting the environmental parameters of the vacuum cleaner working environment, including environmental temperature, power supply voltage fluctuation value, and air flow resistance coefficient; Inputting the current environmental parameters, load status, and the matched coordinated speed regulation strategy into an adaptive parameter adjustment model, outputting the optimal control parameters in the current environment, and adjusting the PID weight coefficient, fuzzy logic rule base, or model predictive weight factor according to the optimal control parameters; the adaptive parameter adjustment model is trained with historical environmental parameters, load status, and labeled optimal parameters under the coordinated speed regulation strategy.

3. The method for coordinated speed regulation and energy efficiency optimization control of multiple motors in a vacuum cleaner according to claim 1, characterized in that It also includes: Statistical analysis of the historical load data of each motor within a preset time period, calculating the load fluctuation variance and the average power consumption; If the load fluctuation variance exceeds the preset threshold, dynamically adjusting the response speed of the coordinated speed regulation strategy based on the sliding window algorithm; if the average power consumption is higher than the preset energy consumption limit, increasing the power constraint weight in the energy efficiency optimization algorithm.

4. The multi-motor collaborative speed regulation and energy efficiency optimization control method for a vacuum cleaner according to claim 1, wherein It also includes: When it is identified that at least two motors are in the high load state, using a fuzzy logic decision module to sort the priorities of each motor; The input variables of the fuzzy logic decision module include the motor temperature rise rate, current overshoot, and task urgency, and the output is the scheduling priority of each motor, and dynamically allocating weight coefficients based on the priority to adjust the target rotational speed.

5. The method for collaborative speed regulation and energy efficiency optimization control of multiple motors of a vacuum cleaner according to claim 1, wherein, It also includes: Using a genetic algorithm to globally search and optimize the power distribution parameters of the energy efficiency optimization algorithm, specifically including: Initializing the population, and encoding the parameters as the power distribution ratio of each motor; Defining the fitness function as the weighted sum of the total energy consumption and the rotational speed tracking error; Iteratively updating the population through selection, crossover, and mutation operations until the convergence condition is met or the maximum number of iterations is reached.

6. The method for collaborative speed regulation and energy efficiency optimization control of multiple motors of a vacuum cleaner according to claim 5, characterized in that, It also includes: Introducing Pareto front analysis in the multi-objective optimization process to screen out the non-dominated solution set that simultaneously meets the lowest energy consumption, the smallest rotational speed error, and the slowest temperature rise. Determine the final power distribution scheme from the non-inferior solution set based on the entropy weight method.

7. The method for collaborative speed regulation and energy efficiency optimization control of multiple motors of a vacuum cleaner according to claim 1, wherein It also includes: Real-time monitor the clogging degree of the vacuum cleaner filter, and dynamically adjust the speed upper limit of each motor according to the clogging degree level; If the clogging degree reaches the preset threshold, reduce the target speed of the high-load motor and increase the speed compensation amount of the low-load motor.

8. The method for collaborative speed regulation and energy efficiency optimization control of multiple motors of a vacuum cleaner according to claim 1, wherein It also includes: Construct the state space model of each motor, and based on the Kalman filter, estimate the actual speed and load state of the motor in real time; Take the residual between the estimated value and the measured value as the feedback signal to correct the control output in the cooperative speed regulation strategy.

9. The method for collaborative speed regulation and energy efficiency optimization control of multiple motors of a vacuum cleaner according to claim 1, wherein, It also includes: Use the long short-term memory neural network to predict the load change trend in the future time window; Based on the prediction results, adjust the target speed setting value and power distribution parameters in the cooperative speed regulation strategy in advance.

10. A multi-motor collaborative speed regulation and energy efficiency optimization control device for a vacuum cleaner, characterized in that, It includes: Operation parameter monitoring module: used to monitor the operation parameters of multiple motors in the vacuum cleaner in real time, including speed, current, voltage and temperature; Load identification module: connected to the operation parameter monitoring module, based on the real-time monitored operation parameters, through the use of a regression algorithm and a load identification model generated by training with the motor operation data of the historical labeled load state, identify the current working load state of each motor; Speed regulation strategy matching module: connected to the load identification module, match the corresponding cooperative speed regulation strategy according to the identified working load state, and the cooperative speed regulation strategy includes PID proportional integral differential control matching the low-load state, fuzzy logic control matching the medium-load state, and model predictive control matching the high-load state; Speed regulation and energy efficiency optimization module: connected to the speed regulation strategy matching module, based on the matched cooperative speed regulation strategy, respectively use the dynamic weight distribution algorithm to dynamically adjust the target speed of each motor, and use the energy efficiency optimization algorithm to constrain and optimize the motor power distribution.

Images