Flow regulation and control method and device, equipment, storage medium and computer program product

Abstract

The invention relates to the technical field of intelligent regulation and control, and discloses a flow regulation and control method, device and equipment, a storage medium and a computer program product.The method comprises the steps that real-time electric signals in equipment operation are collected, current multi-dimensional characteristic parameters are extracted based on the real-time electric signals, and a parameter comparison matrix is constructed to obtain a parameter comparison matrix; the current multi-dimensional characteristic parameter is compared with a preset threshold range, a detection result is obtained, the preset threshold range is a value obtained based on an electric signal during normal operation of the equipment, and when the detection result is that the current multi-dimensional characteristic parameter exceeds the preset threshold range, the current multi-dimensional characteristic parameter is detected. And the flow is regulated and controlled by reducing the rotating speed of a motor of the equipment to a low speed according to a preset curve. According to the method, the multi-dimensional characteristic parameters are extracted by collecting the real-time electric signals of the equipment, the parameter comparison matrix is constructed to be compared with the preset threshold range, the flow is regulated and controlled according to the preset curve in a speed reduction mode when abnormity occurs, and the detection response speed is high and the misjudgment rate is low.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent regulation, and particularly to a flow regulation method, device, equipment, storage medium and computer program product. Background Art

[0002] In the technical field of intelligent regulation, the existing technology relies on mechanical switches or fixed thresholds to control the flow rate, resulting in fundamental delays: the water pump still idles after the handle is closed, and the water flow cannot be instantaneously cut off or restored, causing the user to be unable to achieve true instant control (for example, waiting for several seconds when pausing the water flow during brushing), weakening the real-time performance and reliability of flow control. Summary of the Invention

[0003] The main purpose of the present application is to provide a flow regulation method, device, equipment, storage medium and computer program product, aiming to solve the technical problem that the existing technology cannot instantaneously regulate the flow rate.

[0004] To achieve the above object, the present application proposes a flow regulation method, and the method includes:

[0005] Collect the real-time electrical signal during the operation of the equipment, and extract the current multi-dimensional characteristic parameters based on the real-time electrical signal;

[0006] By constructing a parameter comparison matrix, compare the current multi-dimensional characteristic parameters with a preset threshold range to obtain a detection result, where the preset threshold range is a value obtained based on the electrical signal during the normal operation of the equipment;

[0007] When the detection result is that the current multi-dimensional characteristic parameters exceed the preset threshold range, regulate the flow rate by reducing the motor speed of the equipment to low speed according to a preset curve.

[0008] In an embodiment, the current multi-dimensional characteristic parameters include the half-wave period, peak slope and amplitude. After the step of regulating the flow rate by reducing the motor speed of the equipment to low speed according to a preset curve when the detection result is that the current multi-dimensional characteristic parameters exceed the preset threshold range, the method further includes:

[0009] If any one of the half-wave period, peak slope and amplitude returns to the preset threshold range, control the motor speed to return to the rated speed during the normal operation of the equipment;

[0010] If the continuous over-limit time of any one of the half-wave period, peak slope and amplitude exceeds the preset threshold range, control the motor speed to perform stepped deceleration.

[0011] In one embodiment, before the step of collecting real-time electrical signals and extracting current characteristic parameters based on the real-time electrical signals, the following steps are further included:

[0012] Obtain the electrical signals during normal operation of the device through multi-cycle sampling, perform filtering processing on the electrical signals, and obtain the main waveform;

[0013] Extract a multi-dimensional feature set based on the main waveform;

[0014] Adopt a sliding window algorithm to perform feature extraction on the continuously obtained multi-dimensional feature set, and generate a multi-dimensional feature vector including time domain, frequency domain, and time-frequency domain;

[0015] Establish a kernel density estimation probability curve according to the multi-dimensional feature vector, and determine a reference threshold based on the kernel density estimation probability curve;

[0016] Combine the seasonal adjustment factor, correct the threshold drift of the reference threshold according to the device usage frequency, and obtain a preset threshold range.

[0017] In one embodiment, after the step of regulating the flow rate by reducing the motor speed of the device to low speed according to a preset curve when the detection result is that the current multi-dimensional characteristic parameter exceeds the preset threshold range, the following steps are further included:

[0018] Obtain the execution result of the flow rate regulation;

[0019] By feeding back the execution result to the kernel density estimation model, adjust the kernel density estimation probability curve and the seasonal adjustment factor, and obtain an updated probability curve and an updated seasonal adjustment factor;

[0020] Based on the updated probability curve and the updated seasonal adjustment factor, obtain an updated preset threshold range;

[0021] According to the updated preset threshold range, obtain the detection result of the current multi-dimensional characteristic parameter.

[0022] In one embodiment, the step of comparing the current multi-dimensional characteristic parameter with the preset threshold range by constructing a parameter comparison matrix to obtain a detection result includes:

[0023] By constructing a parameter comparison matrix, compare the current multi-dimensional characteristic parameter with the preset threshold range to generate a feature deviation index;

[0024] According to the feature deviation index, determine the collaborative deviation coefficient of the current multi-dimensional characteristic parameter;

[0025] Based on the neural network algorithm and the collaborative deviation coefficient, obtain the detection result.

[0026] In one embodiment, the step of obtaining a detection result based on the neural network algorithm and the collaborative deviation coefficient includes:

[0027] Based on the neural network algorithm, input the current multi-dimensional feature parameters, the collaborative deviation coefficient, and the time series features into the spatio-temporal attention model to obtain an anomaly probability;

[0028] Obtain the detection result of the real-time electrical signal according to the anomaly probability.

[0029] In addition, to achieve the above object, the present application also proposes a flow regulation device, which includes:

[0030] A data acquisition module for collecting real-time electrical signals during device operation and extracting current multi-dimensional feature parameters based on the real-time electrical signals;

[0031] A data comparison module for comparing the current multi-dimensional feature parameters with a preset threshold range by constructing a parameter comparison matrix to obtain a detection result, where the preset threshold range is obtained based on the electrical signals during normal device operation;

[0032] A flow regulation module for regulating the flow by reducing the motor speed to low speed operation according to a preset curve when the detection result indicates that the current multi-dimensional feature parameters exceed the preset threshold range.

[0033] In addition, to achieve the above object, the present application also proposes a flow regulation device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the flow regulation method as described above.

[0034] In addition, to achieve the above object, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the flow regulation method as described above.

[0035] In addition, to achieve the above object, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the flow regulation method as described above.

[0036] The technical solution proposed in this application collects the real-time electrical signals during the operation of the device, extracts the current multi-dimensional characteristic parameters based on the real-time electrical signals, constructs a parameter comparison matrix, compares the current multi-dimensional characteristic parameters with a preset threshold range, and obtains a detection result. The preset threshold range is a value obtained based on the electrical signals during the normal operation of the device. When the detection result indicates that the current multi-dimensional characteristic parameters exceed the preset threshold range, the flow rate is regulated by reducing the motor speed of the device to a low speed according to a preset curve. This application extracts multi-dimensional characteristic parameters by collecting the real-time electrical signals of the device, constructs a parameter comparison matrix and compares it with the preset threshold range, and reduces the speed according to the preset curve to regulate the flow rate when abnormal, achieving a fast detection response speed and a low false judgment rate. Brief Description of the Drawings

[0037] The drawings herein are incorporated into the specification and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0039] Figure 1 It is a schematic flowchart provided for the first embodiment of the flow rate regulation method of this application;

[0040] Figure 2 It is a schematic flowchart provided for the second embodiment of the flow rate regulation method of this application;

[0041] Figure 3 It is a schematic module structure diagram of the flow rate regulation device for the embodiment of this application;

[0042] Figure 4 It is a schematic device structure diagram of the hardware operating environment involved in the flow rate regulation method for the embodiment of this application.

[0043] The implementation, functional features, and advantages of the purpose of this application will be further described with reference to the embodiments and the drawings. Detailed Description of the Embodiments

[0044] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of this application and are not used to limit this application.

[0045] To better understand the technical solutions of this application, the following will be described in detail in combination with the drawings in the specification and the specific implementation manners.

[0046] In the field of intelligent regulation technology, the existing technology relies on mechanical switches or fixed thresholds to control the flow rate, resulting in a fundamental delay: the water pump continues to run idly after the handle is closed, and the water flow cannot be instantaneously cut off or restored, causing the user to be unable to achieve true instant control (for example, when pausing the water flow during brushing teeth, one has to wait for several seconds), weakening the real-time performance and reliability of flow control.

[0047] Therefore, in order to overcome the above defects, this application provides a solution. By collecting the real-time electrical signals of the device, multi-dimensional characteristic parameters are extracted, a parameter comparison matrix is constructed and compared with a preset threshold range. When an abnormality occurs, the flow rate is regulated by decelerating according to a preset curve, achieving a fast detection response speed and a low false judgment rate.

[0048] It should be noted that the execution subject of each embodiment of this application can be a computing service system with data processing, network communication, and program running functions, such as an electronic system, a flow rate regulation system, etc. that can implement the above functions. Hereinafter, taking the flow rate regulation system as an example (hereinafter referred to as "system"), the following embodiments will be described.

[0049] Based on this, the embodiments of this application provide a flow rate regulation method, referring to Figure 1 , Figure 1 which is the flowchart of the first embodiment of the flow rate regulation method of this application.

[0050] In this embodiment, the flow rate regulation method includes steps S10 to S30:

[0051] Step S10, collect the real-time electrical signals during the operation of the device, and extract the current multi-dimensional characteristic parameters based on the real-time electrical signals.

[0052] In the field of device health status monitoring and intelligent control, taking the dental irrigator as an example, traditional desktop devices control the water flow through mechanical switches, resulting in problems such as cumbersome operation, resource waste, and noise pollution: users need to repeatedly start and stop the main machine switch, and the water pump still runs idly after the handle is closed, causing the internal water pressure to increase and the noise to intensify. Long-term operation may damage the sealing structure. Existing improvement solutions (such as integrating a water flow switch on the handle) only cut off part of the water flow channel and do not stop the water pump from running, and fail to fundamentally solve the problems of energy consumption and noise.

[0053] In view of the above defects, after the water flosser applies the flow rate regulation method of the present application, it can collect the electrical signals during the operation of the water flosser in real time, extract multi-dimensional characteristic parameters, and construct a dynamic threshold model to replace the rigid control of the traditional mechanical switch. When the handle is closed or the nozzle is blocked, the system triggers the motor to automatically decelerate or stop through multi-parameter collaborative determination (such as extended half-wave period, decreased peak slope, and excessive amplitude fluctuation), completely eliminating the problem of pump idling, thereby realizing the function of temporary water blockage with no noise and zero energy consumption. At the same time, the threshold is dynamically calibrated through kernel density estimation and seasonal adjustment factors to adapt to equipment aging and environmental changes, fundamentally solving the defects of the traditional solution such as cumbersome operation, resource waste, and damage to the sealing structure.

[0054] Specifically, it is first necessary to collect real-time electrical signals. High-sensitivity sensors (such as Hall effect sensors or shunt resistor current sensors) can be selected based on the equipment type (such as water flosser motors, industrial pump sets) to collect the current waveform or voltage fluctuation signals during the operation of the equipment in real time, and the sampling frequency is set to capture transient anomalies (such as early cavitation noise). In complex equipment, accelerometers or vibration sensors can be integrated to synchronously collect mechanical vibration signals and form multi-source data comparison with the electrical signals.

[0055] It should be noted that the flow rate regulation method of the present application has cross-field universality and can be widely applied to scenarios such as industrial equipment monitoring, household appliances, medical equipment, and energy management systems. For example, in industrial pump sets, early warning and adaptive deceleration of bearing wear or impeller blockage are realized by monitoring the characteristic parameters of current / voltage signals (such as half-wave period, harmonic distortion rate); in the field of household appliances, vacuum cleaners or coffee machines can operate energy-efficiently and reduce noise through similar methods; in medical equipment such as infusion pumps, the flow rate stability can be accurately controlled and pipeline blockage can be detected; in energy management systems, smart meters and grid equipment can also optimize power distribution and fault diagnosis through real-time electrical signal analysis.

[0056] As an implementation manner, before the above step S10 in this embodiment, it may further include: obtaining the electrical signals during the normal operation of the equipment through multi-period sampling, filtering the electrical signals to obtain the main waveform; extracting a multi-dimensional feature set based on the main waveform; using a sliding window algorithm to extract features from the continuously obtained multi-dimensional feature set to generate a multi-dimensional feature vector including time domain, frequency domain, and time-frequency domain; establishing a kernel density estimation probability curve according to the multi-dimensional feature vector, and determining a reference threshold based on the kernel density estimation probability curve; combining seasonal adjustment factors to correct the threshold drift of the reference threshold according to the equipment usage frequency to obtain a preset threshold range.

[0057] It should be understood that the system obtains the electrical signals during the normal operation of the device through multi-cycle sampling. The multi-cycle sampling refers to continuously collecting multiple complete working cycles during the operation of the device to ensure that the data covers the full operating conditions characteristics of the device. The original signal is processed by filtering, and a wavelet filter is used to eliminate power frequency noise and high-frequency interference. The wavelet filter is a filtering tool based on mathematical transformation. By separating different frequency components, the effective signals in the key frequency band of 0.1 Hz - 1 kHz are retained, and the main waveform reflecting the true operating state of the device is obtained.

[0058] Extract a multi-dimensional feature set based on the main waveform, including time-domain features, frequency-domain features, and time-frequency domain features. Time-domain features refer to the timing parameters directly extracted from the signal waveform, such as the half-wave period (the duration of half a cycle of the signal, reflecting the change in rotor load) and the peak slope (the slope of the rise or fall of the waveform peak, characterizing the steepness of the signal); frequency-domain features refer to the parameters obtained by analyzing the frequency components of the signal through Fourier transform, such as the fundamental frequency harmonic ratio, that is, the ratio of the second harmonic to the fundamental frequency amplitude, used to detect abnormalities in bearings or impellers; time-frequency domain features capture the transient changes of the signal in the time and frequency dimensions through time-frequency analysis techniques such as short-time Fourier transform, such as the local energy mutation in the early stage of cavitation.

[0059] The continuously obtained multi-dimensional feature set is segmented by the sliding window algorithm. The sliding window algorithm divides the signal into windows of a fixed duration (for example, each 100 ms is a window), and multi-dimensional feature parameters are extracted from each window to generate a multi-dimensional feature vector including the time domain, frequency domain, and time-frequency domain. Based on the multi-dimensional feature vector, a Kernel Density Estimation (KDE) probability curve is established. The kernel density estimation is a non-parametric statistical method. By fitting the distribution of historical feature data through a kernel function (such as a Gaussian kernel), a continuous probability density curve is generated, and the benchmark threshold range of each parameter is determined accordingly. For example, the half-wave period threshold is set to the mean ± 1.5 times the standard deviation.

[0060] To adapt to equipment aging or environmental changes, such as load fluctuations caused by increased fluid viscosity in winter, a seasonal adjustment factor is introduced. The seasonal adjustment factor dynamically corrects the threshold drift according to external parameters such as the historical usage frequency and temperature of the device. For example, under low-temperature operating conditions, the half-wave period threshold may be increased by 5% to ensure that the detection results always match the current operating conditions. The finally generated preset threshold range will be used as the comparison benchmark for real-time feature parameters to achieve dynamic identification and adaptive control of abnormal states.

[0061] It should be noted that the traffic control method of this application can also obtain a preset threshold range by performing discrete analysis on multiple main waveforms. For example, multiple waveforms of half-wave period data are obtained, and multiple half-wave period data are analyzed. After discrete analysis and processing, a half-wave period threshold range is obtained.

[0062] Step S20: Compare the current multi-dimensional characteristic parameters with the preset threshold range by constructing a parameter comparison matrix to obtain a detection result, where the preset threshold range is a value obtained based on the electrical signal during normal operation of the device.

[0063] It should be noted that the parameter comparison matrix is a multi-dimensional array used to quantify the deviation degree of the current characteristic parameters from the preset threshold. The rows of the matrix represent the characteristic parameters (such as half-wave period, peak slope, amplitude), and the columns represent the preset threshold range (such as mean ± 1.5σ).

[0064] It can be understood that in real-time detection, by constructing a parameter comparison matrix and comparing the current multi-dimensional characteristic parameters with the preset threshold range item by item, the overall abnormal degree can be quantified by calculating the collaborative deviation coefficient (such as the deviation degree of weighted fusion of half-wave period, peak slope, etc.) to obtain the detection result.

[0065] By collecting the electrical signal during the operation of the device in real time, extracting the multi-dimensional characteristic parameters of the half-wave period, and constructing a parameter comparison matrix and a dynamic threshold model. For example, in the scenario of a dental irrigator, when the user presses the handle switch to cut off the water flow, the physical blockage of the nozzle causes a sudden change in the motor load, the half-wave period is extended, the peak slope drops, and the amplitude fluctuation exceeds the limit. The system determines the water blockage state accordingly and immediately reduces the motor speed to a low gear, making the water pump enter a near-stop state, the flow rate approaches zero, and at the same time, the noise and energy consumption are eliminated.

[0066] Step S30: When the detection result is that the current multi-dimensional characteristic parameters exceed the preset threshold range, regulate the flow rate by reducing the motor speed of the device to low speed according to a preset curve.

[0067] It can be understood that if all the current multi-dimensional characteristic parameters exceed the preset threshold range, it means that the device has an abnormality (such as the nozzle is blocked, the handle switch is closed, etc.). At this time, the flow rate can be reduced by reducing the motor speed to a preset low-speed operation state. At this time, the water pump hardly works (or can be directly shut down), thereby avoiding further damage or improving the user experience (such as reducing noise). If the characteristic parameters are all within the preset threshold range, it indicates that the device is operating normally, and the normal speed of the motor can be maintained.

[0068] As an implementation manner, after the above step S30 in this embodiment, the following steps may further be included: If any one of the half-wave period, the peak slope, and the amplitude is restored to within the preset threshold range, the motor speed is controlled to be restored to the rated speed when the device operates normally; if any one of the half-wave period, the peak slope, and the amplitude continuously exceeds the limit for a time exceeding the preset threshold range, the motor speed is controlled to perform a stepped speed reduction.

[0069] It should be understood that by continuously monitoring the three core parameters of the half-wave period, the peak slope, and the amplitude of the electrical signal of the device, and dynamically adjusting the motor speed in combination with the preset threshold range and the over-limit duration, the dual goals of accurate flow control and device protection are achieved.

[0070] Specifically, when any parameter (such as the shortening or extension of the half-wave period, the abnormal peak slope, or the deviation of the amplitude from the reference) is restored to within the preset threshold range, the system determines that the operating state of the device returns to normal, and automatically triggers the speed restoration process. This process gradually increases the motor speed to the rated value (or starts up) through a preset acceleration curve, and at the same time combines the real-time characteristic parameter feedback optimization model to ensure that the flow rate is stable within the target range. During this process, the system continuously monitors the parameter fluctuations. If new abnormal signs (such as a short-term over-limit during the restoration process) are detected, the restoration will be immediately suspended and the state will be re-evaluated to avoid flow disturbances caused by misjudgment.

[0071] If any parameter continuously exceeds the limit for a time exceeding the preset threshold (such as 30 seconds), it indicates that the device has a persistent abnormality (such as impeller blockage or severe bearing wear), and the system starts a stepped speed reduction mechanism. For example, in the initial stage, the flow rate load is reduced through linear speed reduction (such as 70%-90% of the rated speed). If the abnormality is not eliminated, it is further reduced to a lower speed gear (such as 30%-50%), and finally the shutdown protection is triggered to prevent device damage. During this process, the system dynamically adjusts the speed reduction rate according to the weight of the over-limit parameter (such as the weight of the half-wave period is higher than the peak slope).

[0072] In this embodiment, by collecting the real-time electrical signal of the device to extract multi-dimensional characteristic parameters, constructing a parameter comparison matrix and comparing it with the preset threshold range, and when an abnormality occurs, the flow rate is regulated by reducing the speed according to the preset curve, the detection response speed is fast and the misjudgment rate is low. Moreover, when the parameter is restored, the speed is automatically reset, and when it exceeds the limit, the speed is stepped down to reduce the risk of equipment failure. Based on multi-period sampling, a kernel density estimation probability model is constructed, and the seasonal adjustment factor and the equipment usage frequency are fused to solve the problem of threshold drift caused by environmental fluctuations, and the threshold stability is maintained under different working conditions.

[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as in the above-mentioned embodiment one can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 2, step S20 may include steps S201 to S203:

[0074] Step S201, by constructing a parameter comparison matrix, compare the current multi-dimensional feature parameters with a preset threshold range to generate a feature deviation index.

[0075] By calculating the relative deviation of each feature parameter from its threshold range (such as a 20% reduction in the half-wave period or a 15% increase in the amplitude), a corresponding feature deviation index is generated, and this index is standardized (such as Z-score) to eliminate the dimension difference.

[0076] Step S202, according to the feature deviation index, determine the collaborative deviation coefficient of the current multi-dimensional feature parameters.

[0077] It should be noted that the collaborative deviation coefficient is a weighted fusion value based on the deviation degrees of each feature parameter, and is used to comprehensively evaluate the overall health status of the device.

[0078] Step S203, based on the neural network algorithm and the collaborative deviation coefficient, obtain the detection result.

[0079] It can be understood that the neural network algorithm receives the collaborative deviation coefficient and the original feature parameters as inputs, and outputs the detection result through multi-layer non-linear transformation, which may include: using a deep neural network including an input layer, a hidden layer (such as 3 - 5 layers of fully connected nodes), and an output layer. The input layer integrates the collaborative deviation coefficient and the feature parameters, and the output layer outputs the failure probability (such as 0 - 1 indicating normal / abnormal);

[0080] Training mechanism: Based on a historical data set (such as 100,000 sets of normal / abnormal samples) for supervised learning, optimize the network weights to minimize the classification error (such as the cross-entropy loss function);

[0081] Dynamic adaptation: Continuously update the network parameters through an online learning mechanism to adapt to long-term changes such as equipment aging and working condition fluctuations, and avoid model drift.

[0082] As an implementation manner, in this embodiment, step S203 above may include: Based on the neural network algorithm, input the current multi-dimensional feature parameters, the collaborative deviation coefficient, and the time series features into a spatio-temporal attention model to obtain the anomaly probability; according to the anomaly probability, obtain the detection result of the real-time electrical signal.

[0083] It is understandable that a spatio-temporal attention model can be used to perform fusion analysis on multi-dimensional feature parameters, collaborative deviation coefficients, and temporal features to achieve a quantitative assessment of the abnormal state of the device. The specific process is as follows: First, the current multi-dimensional feature parameters (such as half-wave period, peak slope, amplitude), collaborative deviation coefficients (weighted values that comprehensively measure the deviation of each feature), and temporal features (correlation of adjacent time window features extracted by the sliding window algorithm, such as the short-term change rate of the half-wave period) are input into the model to form multi-modal input data.

[0084] The spatio-temporal attention model focuses on key feature dimensions through the spatial attention mechanism. For example, it is sensitive to local anomalies in the frequency-domain harmonic ratio. At the same time, it uses the time attention mechanism to capture temporal correlations, such as the progressive evolution law of cavitation faults, so as to achieve the collaborative recognition of global and local anomalies in the device state. The model is trained based on a historical data set (including normal / abnormal samples), and outputs an abnormal probability (within the range of 0-1) through non-linear transformation, which represents the possibility that the current working condition belongs to the abnormal state. For example, if the model outputs a probability of 0.9, it indicates that the device has a high risk of abnormality.

[0085] When the probability exceeds the preset threshold, it is determined as abnormal and the control logic is triggered; otherwise, it is regarded as a normal working condition. To adapt to equipment aging or environmental changes, the threshold can be dynamically calibrated through kernel density estimation (for example, the threshold is lowered by 10% in winter to improve sensitivity) to ensure that the detection results always match the actual working conditions. This process continuously optimizes the model parameters through an online learning mechanism, forming a closed loop of "data input - feature fusion - probability output - dynamic adjustment".

[0086] This embodiment proposes a collaborative deviation coefficient algorithm, which combines a neural network to improve the abnormal recognition ability under complex working conditions, enhance the sensitivity to early faults, constructs a spatio-temporal attention model, inputs multi-dimensional features and temporal information, focuses on key features through learnable weight allocation, outputs an abnormal probability value, and achieves high-precision abnormal detection, adapting to complex scenarios such as equipment start-stop transients.

[0087] As an implementation method, after the step S30, it may further include:

[0088] Obtain the execution result of the flow regulation;

[0089] By feeding back the execution result to the kernel density estimation model, adjust the kernel density estimation probability curve and the seasonal adjustment factor to obtain an updated probability curve and an updated seasonal adjustment factor;

[0090] Based on the updated probability curve and the updated seasonal adjustment factor, obtain an updated preset threshold range;

[0091] According to the updated preset threshold range, obtain the detection result of the current multi-dimensional feature parameters.

[0092] It should be noted that this application realizes the adaptive optimization of the detection model through a feedback mechanism. After the device performs flow regulation (for example, the motor speed drops to a low gear), the execution result data is collected in real time (including but not limited to the actual flow rate, the deviation between the rotation speed and the expected value, the regulation time consumption, etc.), and these data are fed back to the kernel density estimation model. The feedback mechanism realizes dynamic calibration through the following steps:

[0093] Model parameter update: The kernel density estimation model adjusts the shape and position of the probability density curve according to the feedback regulation result data (such as flow deviation, rotation speed deviation). For example, if the actual flow rate is always lower than the target value after multiple regulations, the model will reduce the threshold standard deviation of the flow parameter, making the detection of small deviations more sensitive.

[0094] Seasonal adjustment factor synchronous update: Combining the changes in environmental parameters (such as temperature, humidity, equipment usage frequency), the seasonal factor weight is corrected through time series analysis (such as the Autoregressive Integrated Moving Average Model (ARIMA model)). For example, in the scenario of high-viscosity fluid in winter, the actual flow rate recovers slowly after flow regulation, and the model will increase the seasonal factor coefficient by 10% to compensate for the influence of fluid viscosity on the threshold.

[0095] Dynamic threshold reconstruction: The updated probability curve and the seasonal adjustment factor jointly generate a new preset threshold range. For example, the threshold mean of the half-wave period may be adjusted from the original 1.2 ms to 1.25 ms (due to increased rotor load caused by equipment aging), and the standard deviation is narrowed from 0.15 ms to 0.12 ms (reflecting the decline in equipment state stability).

[0096] Threshold drift compensation: Through the dynamic calibration of kernel density estimation, the system can automatically correct the threshold offset caused by equipment wear, lubrication state change, or external working condition fluctuations (such as day-night temperature difference), avoiding false alarms and missed alarms under the fixed threshold method.

[0097] Real-time detection result update: Based on the updated threshold range, the system recalculates the feature deviation index and the collaborative deviation coefficient for the current multi-dimensional characteristic parameters (such as half-wave period, peak slope). For example, if the half-wave period is extended to 1.3 ms due to equipment aging (the original threshold range is 0.99 - 1.41 ms), the adjusted threshold may become 1.25 - 1.47 ms, and it is still determined to be in normal working conditions.

[0098] Iteration of detection results: The comparison results between the new threshold range and the characteristic parameters form a new round of detection conclusions. If the anomaly persists (such as the half-wave period continuously exceeding the limit), a more stringent regulation strategy (such as stepped speed reduction) is triggered; if the parameters return to normal, the rotational speed is restored and the model is optimized to adapt to the latest state of the device.

[0099] For ease of understanding, an example scenario of applying the flow rate regulation method of this application to a water flosser device is described. The specific steps for real-time monitoring of the motor electrical signal and dynamically adjusting the rotational speed are as follows:

[0100] Step 1: Multidimensional characteristic parameter modeling

[0101] Signal acquisition and preprocessing: After the water flosser is turned on, the current sensor continuously acquires the motor electrical signal at a sampling rate of 1 kHz and captures the waveforms of 10 complete working cycles; a Daubechies 4th-order wavelet filter is used to filter out power frequency noise (50 / 60 Hz) and high-frequency interference, and the main waveform of 0.1 Hz - 1 kHz is retained.

[0102] Feature extraction and threshold establishment: Perform a sliding window analysis (100 ms / window) on the filtered waveform, and extract three parameters: half-wave period (reflecting the rotor load), peak slope (signal steepness), and amplitude (signal intensity); collect 100 sets of normal operating condition data, and generate a dynamic threshold range (such as the mean of the half-wave period ±1.5σ) through kernel density estimation.

[0103] Step 2: Real-time water blockage determination

[0104] Monitoring during operation: When the water flosser is running, repeat signal acquisition and feature extraction in real time to obtain the current half-wave period (T1), peak slope (S1), and amplitude (A1);

[0105] Multi-parameter comparison: If T1 > 1.41 ms (exceeding the limit by 24%), S1 < 0.7 V / μs (decreasing by 30%), and A1 fluctuates > 20% (all three are abnormal), it is determined that the handle is closed or the nozzle is blocked; if any parameter returns to the threshold range, it is determined that the water flow is unobstructed.

[0106] Step 3: Dynamic regulation and closed-loop optimization

[0107] First-level response: After the water blockage determination is triggered, the motor rotational speed is reduced to 30% - 50% according to a preset curve (such as 3000 rpm → 900 rpm), the flow rate is reduced to ±10% of the target value, and at the same time, the solenoid valve is closed to stop the water flow; Second-level response: If the water blockage persists for more than 30 seconds, trigger shutdown protection and push a user reminder; Model update: Feed the regulated flow rate, rotational speed deviation, and time data back to the kernel density estimation model to optimize the threshold range and seasonal factors (such as winter viscosity compensation) to improve long-term adaptability.

[0108] User usage scenario:

[0109] Normal use: The user turns on the water flosser, and the water flow runs at the rated speed (3000 rpm). The half-wave period is stable at 1.2 ms, the peak slope is 0.8 V / μs, and the amplitude fluctuation < 5%; Temporary shutdown: The user presses the handle switch, and the nozzle physically cuts off the water flow, but the water pump is still idling. At this time, the signal is abnormal. Due to the sudden change in the rotor load caused by the nozzle intercepting the flow, the half-wave period is extended to 1.45 ms (exceeding the limit by 20%), the peak slope drops to 0.5 V / μs (exceeding the limit by 37.5%), and the amplitude fluctuation increases to 25%;

[0110] Water blockage determination: When all three parameters exceed the threshold range, the system determines that the handle is closed or the nozzle is blocked, and immediately reduces the motor speed to 900 rpm. The flow rate is almost zero, the water pump stops working and there is no noise; Recovery operation: The user releases the handle switch, and the nozzle resumes water flow. At this time: Signal regression: The half-wave period resumes to 1.1 ms (within the normal range), the peak slope rises to 0.75 V / μs, and the amplitude fluctuation < 10%; Automatic recovery: The system determines that the water flow is unobstructed, and the motor speed linearly rises to 3000 rpm, and the flow rate returns to normal, with the whole process taking < 5 seconds.

[0111] Compared with the traditional fixed-threshold method, this application generates a dynamic threshold range through kernel density estimation and compensates for parameter drift caused by environmental factors (such as increased fluid viscosity in winter) by combining seasonal adjustment factors, significantly improving detection accuracy and adaptability. In addition, the multi-parameter collaborative determination mechanism (such as all three of the half-wave period, peak slope, and amplitude being abnormal to trigger regulation) effectively avoids misjudgment of a single parameter and ensures the robustness of the system. The flow rate regulation method of this application can achieve millisecond-level response (< 5 seconds) in the water flosser scenario, reduce noise by > 30 dB, reduce energy consumption by > 60%, and at the same time support the user to temporarily turn off the water flow with one key on the handle, significantly improving the operation convenience and equipment reliability.

[0112] This embodiment optimizes the model and seasonal factors in real time through execution result feedback, establishes a "detection - execution - learning" closed loop, enables the system to have self-adaptive ability, and gradually improves the accuracy of abnormal detection and reduces energy consumption.

[0113] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the flow rate regulation method of this application. Based on this technical concept, more simple transformations in various forms are within the protection scope of this application.

[0114] This application also provides a flow rate regulation device. Please refer to Figure 3 , and the flow rate regulation device includes:

[0115] A data acquisition module 10, configured to collect real-time electrical signals during the operation of the device and extract current multi-dimensional characteristic parameters based on the real-time electrical signals;

[0116] A data comparison module 20, configured to compare the current multi-dimensional characteristic parameters with a preset threshold range by constructing a parameter comparison matrix to obtain a detection result, where the preset threshold range is obtained based on the electrical signal when the device is operating normally;

[0117] A flow rate regulation module 30, configured to regulate the flow rate by reducing the motor speed to a low speed according to a preset curve when the detection result indicates that the current multi-dimensional characteristic parameters exceed the preset threshold range.

[0118] The flow rate regulation device provided in this application adopts the flow rate regulation method in the above embodiment, and can solve the technical problem that the prior art cannot regulate the flow rate immediately. Compared with the prior art, the beneficial effects of the flow rate regulation device provided in this application are the same as those of the flow rate regulation method provided in the above embodiment, and other technical features in the flow rate regulation device are the same as those disclosed in the method of the above embodiment, and will not be elaborated here.

[0119] This application provides a flow rate regulation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the flow rate regulation method in the first embodiment above.

[0120] Refer to the following Figure 4 , which shows a schematic structural diagram of a flow rate regulation device suitable for implementing the embodiments of this application. The flow rate regulation device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Desctions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The flow rate regulation device shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of this application.

[0121] As shown in Figure 4As shown in the figure, the traffic regulation device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to the program stored in the read-only memory 1002 or the program loaded from the storage device 1003 into the random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the traffic regulation device are also stored. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. The input / output interface 1006 is also connected to the bus. Generally, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the traffic regulation device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a traffic regulation device having various systems, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems may be implemented or had.

[0122] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device, or installed from the storage device 1003, or installed from the read-only memory 1002. When the computer program is executed by the processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0123] The traffic regulation device provided by the present application adopts the traffic regulation method in the above embodiments, and can solve the technical problem that the prior art cannot instantaneously regulate traffic. Compared with the prior art, the beneficial effects of the traffic regulation device provided by the present application are the same as those of the traffic regulation method provided by the above embodiments, and other technical features in the traffic regulation device are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated herein.

[0124] It should be understood that the various parts disclosed in the present application may be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0125] As described above, it is only the specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

[0126] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the traffic regulation method in the above embodiments.

[0127] The computer-readable storage medium provided by the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM) or a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0128] The above computer-readable storage medium may be included in the traffic regulation device; or it may exist separately without being assembled into the traffic regulation device.

[0129] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the traffic regulation device, the traffic regulation device is caused to: collect real-time electrical signals during device operation, extract current multi-dimensional characteristic parameters based on the real-time electrical signals, obtain a detection result by constructing a parameter comparison matrix and comparing the current multi-dimensional characteristic parameters with a preset threshold range, where the preset threshold range is a value obtained based on the electrical signals during normal device operation, and when the detection result is that the current multi-dimensional characteristic parameters exceed the preset threshold range, regulate the traffic by reducing the motor speed of the device to low speed according to a preset curve.

[0130] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN: Local Area Network) or a wide area network (WAN: Wide Area Network), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0132] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0133] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned traffic regulation method, and can solve the technical problem that the prior art cannot instantaneously regulate traffic. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the traffic regulation method provided by the above embodiments, and will not be elaborated here.

[0134] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the traffic regulation method as described above.

[0135] The computer program product provided by the present application can solve the technical problem that the prior art cannot instantaneously regulate traffic. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the traffic regulation method provided by the above embodiments, and will not be elaborated herein.

[0136] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural transformation made by using the content of the specification and drawings of the present application under the technical concept of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A flow regulation method, characterized in that, The method includes the following steps: Collect the real-time electrical signals during the operation of the device, and extract the current multi-dimensional characteristic parameters based on the real-time electrical signals; By constructing a parameter comparison matrix, compare the current multi-dimensional characteristic parameters with a preset threshold range to obtain a detection result, where the preset threshold range is a value obtained based on the electrical signals during the normal operation of the device; When the detection result is that the current multi-dimensional characteristic parameters exceed the preset threshold range, regulate the flow rate by reducing the motor speed of the device to a low speed according to a preset curve.

2. The flow rate regulation method according to claim 1, wherein The current multi-dimensional characteristic parameters include the half-wave period, the peak slope, and the amplitude. After the step of regulating the flow rate by reducing the motor speed of the device to a low speed according to a preset curve when the detection result is that the current multi-dimensional characteristic parameters exceed the preset threshold range, it further includes: If any one of the half-wave period, the peak slope, and the amplitude returns to within the preset threshold range, control the motor speed to return to the rated speed during the normal operation of the device; If the continuous over-limit time of any one of the half-wave period, the peak slope, and the amplitude exceeds the preset threshold range, control the motor speed to perform a stepped speed reduction.

3. The flow rate regulation method according to claim 1, characterized in that Before the step of collecting the real-time electrical signals and extracting the current characteristic parameters based on the real-time electrical signals, it further includes: Obtain the electrical signals during the normal operation of the device through multi-period sampling, perform filtering processing on the electrical signals to obtain the main waveform; Extract a multi-dimensional feature set based on the main waveform; Adopt a sliding window algorithm to extract features from the continuously obtained multi-dimensional feature set to generate a multi-dimensional feature vector including the time domain, the frequency domain, and the time-frequency domain; Establish a kernel density estimation probability curve according to the multi-dimensional feature vector, and determine a reference threshold based on the kernel density estimation probability curve; Combine the seasonal adjustment factor to correct the threshold drift of the reference threshold according to the device usage frequency to obtain a preset threshold range.

4. The flow rate regulation method according to any one of claims 1 to 3, characterized in that After the step of regulating the flow rate by reducing the motor speed of the device to a low speed according to a preset curve when the detection result is that the current multi-dimensional characteristic parameters exceed the preset threshold range, it further includes: Obtain the execution result of the flow rate regulation; By feeding back the execution result to the kernel density estimation model, adjust the kernel density estimation probability curve and the seasonal adjustment factor to obtain an updated probability curve and an updated seasonal adjustment factor; Based on the updated probability curve and the updated seasonal adjustment factor, obtain an updated preset threshold range; According to the updated preset threshold range, obtain the detection result of the current multi-dimensional characteristic parameters.

5. The flow rate regulation method according to any one of claims 1 to 3, characterized in that The step of comparing the current multi-dimensional characteristic parameters with a preset threshold range by constructing a parameter comparison matrix to obtain a detection result includes: By constructing a parameter comparison matrix, compare the current multi-dimensional characteristic parameters with a preset threshold range to generate a feature deviation index; Determine the collaborative deviation coefficient of the current multi-dimensional characteristic parameters according to the feature deviation index; Based on the neural network algorithm and the collaborative deviation coefficient, obtain the detection result.

6. The flow rate regulation method according to claim 5, wherein The steps of obtaining the detection result based on the neural network algorithm and the collaborative deviation coefficient include: Based on the neural network algorithm, input the current multi-dimensional feature parameters, the collaborative deviation coefficient, and the time series feature into the spatio-temporal attention model to obtain the anomaly probability; Obtain the detection result of the real-time electrical signal according to the anomaly probability.

7. A flow regulation device, characterized in that, The flow rate control device includes: A data acquisition module, configured to collect the real-time electrical signal during device operation, and extract the current multi-dimensional feature parameters based on the real-time electrical signal; A data comparison module, configured to compare the current multi-dimensional feature parameters with a preset threshold range by constructing a parameter comparison matrix to obtain a detection result, where the preset threshold range is obtained based on the electrical signal during normal device operation; A flow rate control module, configured to, when the detection result is that the current multi-dimensional feature parameters exceed the preset threshold range, control the flow rate by reducing the motor speed to a low speed according to a preset curve.

8. A flow control device, characterized in that, The flow rate control device includes: a memory, a processor, and a flow rate control program stored on the memory and executable on the processor. When the flow rate control program is executed by the processor, it implements the flow rate control method according to any one of claims 1 to 6.

9. A storage medium, characterized in that, A flow rate control program is stored on the storage medium. When the flow rate control program is executed by a processor, it implements the flow rate control method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a flow rate control program. When the flow rate control program is executed by a processor, it implements the flow rate control method according to any one of claims 1 to 6.

Images