Wireless sensor dynamic voltage regulation method and system based on load current prediction

Abstract

The application provides a wireless sensor dynamic voltage regulation method and system based on load current prediction, relates to the technical field of voltage regulation, and comprises the following steps: a load current prediction model is constructed; a feedforward compensation amount of power supply voltage of the wireless sensor under different working conditions is determined according to a load current prediction sequence output by the load current prediction model and response characteristics of output voltage of a direct current-direct current converter in the wireless sensor to the load current under different working conditions; output voltage ripple of the direct current-direct current converter is suppressed to obtain a disturbance suppression degree of the output voltage ripple of the direct current-direct current converter; the power supply voltage of the wireless sensor is closed-loop regulated through the disturbance suppression degree and all the feedforward compensation amounts to obtain a closed-loop gain coefficient of the power supply voltage, and then a voltage regulation instruction of the wireless sensor is generated according to the closed-loop gain coefficient. The application can suppress the output voltage ripple interference of the direct current-direct current converter in the wireless sensor voltage regulation process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of voltage regulation, and more particularly, to a wireless sensor dynamic voltage regulation method and system based on load current prediction. BACKGROUND

[0002] In a wireless sensor system, voltage regulation technology is a key link to ensure stable operation of the sensor and accurate measurement performance. Since wireless sensors are mostly powered by batteries or energy harvesting modules, their voltage supply is greatly affected by environmental and load changes. If the voltage regulation is unstable, it will not only reduce the energy efficiency of the sensor, but also cause sampling errors and communication distortion, affecting the overall reliability of the system. Therefore, it is of great significance to design a voltage control mechanism with adaptive adjustment capability for the power consumption characteristics and dynamic load change law of wireless sensors.

[0003] Existing wireless sensor voltage regulation methods mostly rely on DC-DC converters for stable voltage output. However, under dynamic load changes or sudden conditions, the transient response speed of the converter is limited, and voltage ripple is easily generated at the output end. Voltage ripple will form periodic interference at the sensor power supply end, affecting sensitive analog circuits and radio frequency modules, leading to signal drift or transmission errors, and in severe cases, it may even cause module reset. In addition, traditional feedback voltage regulation methods generally have response lag problems, making it difficult to compensate for output disturbances caused by load current fluctuations in a timely manner, and unable to effectively suppress ripple interference. Therefore, how to suppress the output voltage ripple interference of the DC-DC converter during the wireless sensor voltage regulation process has become a difficult problem in the industry. SUMMARY

[0004] The present application provides a wireless sensor dynamic voltage regulation method and system based on load current prediction, which can suppress the output voltage ripple interference of the DC-DC converter during the wireless sensor voltage regulation process.

[0005] In a first aspect, the present application provides a wireless sensor dynamic voltage regulation method based on load current prediction, which comprises the following steps:

[0006] Obtain historical load current data of the wireless sensor under different working conditions, and then build a load current prediction model;

[0007] Determine the feedforward compensation amount of the power supply voltage of the wireless sensor under different working conditions according to the load current prediction sequence output by the load current prediction model and the response characteristics of the output voltage of the DC-DC converter in the wireless sensor to the load current under different working conditions;

[0008] Collecting load disturbance information of the wireless sensor at the time of load current mutation, suppressing output voltage ripple of the DC-DC converter according to the load disturbance information, and obtaining a disturbance suppression degree of the output voltage ripple of the DC-DC converter;

[0009] Adjusting the supply voltage of the wireless sensor through the disturbance suppression degree and all the feedforward compensation amounts, obtaining a closed-loop gain coefficient of the supply voltage, and further generating a voltage adjustment instruction of the wireless sensor according to the closed-loop gain coefficient.

[0010] In the embodiment, constructing the load current prediction model specifically includes:

[0011] Obtaining historical load current data of the wireless sensor under different working conditions;

[0012] Preprocessing all the historical load current data to obtain different preprocessed load current data;

[0013] Extracting time sequence features and working condition association features from each preprocessed load current data;

[0014] Model training is performed according to all the time sequence features and all the working condition association features to obtain the load current prediction model.

[0015] In the embodiment, determining the feedforward compensation amount of the supply voltage of the wireless sensor under different working conditions according to the load current prediction sequence output by the load current prediction model and the response characteristics of the output voltage of the DC-DC converter in the wireless sensor to the load current under different working conditions specifically includes:

[0016] Obtaining the response characteristics of the output voltage of the DC-DC converter in the wireless sensor to the load current under different working conditions, the response characteristics indicating the delay time and voltage deviation amplitude of the output voltage changing with the load current;

[0017] Determining the voltage change rate of the output voltage changing with the load current under different working conditions according to the response characteristics of the output voltage to the load current under different working conditions;

[0018] Extracting the load current trend value under different working conditions from the load current prediction sequence output by the load current prediction model through the response characteristics of the output voltage to the load current under different working conditions;

[0019] Performing feedforward compensation on the supply voltage of the wireless sensor under different working conditions according to the load current trend value under different working conditions and the voltage change rate of the output voltage changing with the load current under different working conditions, and obtaining the feedforward compensation amount of the supply voltage of the wireless sensor under different working conditions.

[0020] In the embodiment, the output voltage ripple of the DC-DC converter is suppressed according to the load disturbance information, and the disturbance suppression degree of the output voltage ripple of the DC-DC converter specifically comprises:

[0021] The load disturbance information of the wireless sensor when the load current is suddenly changed is collected.

[0022] The load disturbance information is characterized to obtain disturbance mutation characteristics and disturbance time characteristics.

[0023] The output voltage ripple of the DC-DC converter is feedback suppressed by the disturbance mutation characteristics and the disturbance time characteristics, and the feedback suppression index of the output voltage ripple of the DC-DC converter is obtained.

[0024] The disturbance suppression degree of the output voltage ripple of the DC-DC converter is determined according to the feedback suppression index and the output voltage ripple amplitude of the DC-DC converter in the steady state before the load current is suddenly changed.

[0025] In the embodiment, the power supply voltage of the wireless sensor is closed-loop adjusted by the disturbance suppression degree and all the feedforward compensation amounts, and the closed-loop gain coefficient of the power supply voltage specifically comprises:

[0026] The response sensitivity of the closed-loop adjustment is adjusted according to the disturbance suppression degree;

[0027] The power supply voltage deviation of the wireless sensor is determined;

[0028] The power supply voltage of the wireless sensor is closed-loop verified by all the feedforward compensation amounts, and a closed-loop verification sequence of the power supply voltage is obtained.

[0029] The closed-loop gain coefficient of the power supply voltage is determined according to the response sensitivity, the power supply voltage deviation, and the closed-loop verification sequence.

[0030] In the embodiment, the voltage adjustment instruction of the wireless sensor is generated according to the closed-loop gain coefficient, and the voltage adjustment instruction of the wireless sensor specifically comprises:

[0031] The control gain parameter of the power supply voltage of the wireless sensor is determined according to the closed-loop gain coefficient;

[0032] The voltage adjustment instruction of the wireless sensor is generated by the control gain parameter.

[0033] In the embodiment, the feedforward compensation amount represents a compensation voltage that can offset the output voltage fluctuation caused by the change of the load current in advance.

[0034] In this embodiment, the disturbance suppression degree represents the reduction ratio of the output voltage ripple of the DC-DC converter compared to the steady-state ripple before the disturbance.

[0035] In this embodiment, the closed-loop gain coefficient represents the gain coefficient of the response strength to the supply voltage deviation during the closed-loop regulation process.

[0036] Secondly, this application provides a wireless sensor dynamic voltage regulation system based on load current prediction, used to execute a wireless sensor dynamic voltage regulation method based on load current prediction, the wireless sensor dynamic voltage regulation system comprising:

[0037] The model building module is used to acquire historical load current data of wireless sensors under different operating conditions, and then build a load current prediction model.

[0038] The feedforward compensation module is used to determine the feedforward compensation amount of the power supply voltage of the wireless sensor under different operating conditions based on the load current prediction sequence output by the load current prediction model and the response characteristics of the output voltage of the DC-DC converter in the wireless sensor to the load current under different operating conditions.

[0039] The disturbance suppression module is used to collect load disturbance information of the wireless sensor when the load current changes suddenly, and to suppress the output voltage ripple of the DC-DC converter according to the load disturbance information, so as to obtain the disturbance suppression degree of the output voltage ripple of the DC-DC converter.

[0040] The closed-loop adjustment module is used to perform closed-loop adjustment of the power supply voltage of the wireless sensor using the disturbance suppression degree and all feedforward compensation quantities to obtain the closed-loop gain coefficient of the power supply voltage, and then generate the voltage adjustment command of the wireless sensor based on the closed-loop gain coefficient.

[0041] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0042] The historical load current data of the wireless sensor under different working conditions is acquired, and then a load current prediction model is constructed; the feedforward compensation amount of the power supply voltage of the wireless sensor under different working conditions is determined according to the load current prediction sequence output by the load current prediction model and the response characteristic of the output voltage of the DC-DC converter in the wireless sensor to the load current under different working conditions; the load disturbance information of the wireless sensor when the load current suddenly changes is collected, the output voltage ripple of the DC-DC converter is suppressed according to the load disturbance information, and the disturbance suppression degree of the output voltage ripple of the DC-DC converter is obtained; the power supply voltage of the wireless sensor is closed-loop adjusted through the disturbance suppression degree and all the feedforward compensation amounts, and the closed-loop gain coefficient of the power supply voltage is obtained, and then the voltage adjustment instruction of the wireless sensor is generated according to the closed-loop gain coefficient.

[0043] It can be seen that in the present application, the voltage adjustment instruction of the wireless sensor can be generated according to the closed-loop gain coefficient; first, by acquiring the historical load current data of the wireless sensor under different working conditions and constructing a load current prediction model, the load change trend can be predicted in advance, which provides a scientific basis for the feedforward compensation of the power supply voltage. This step not only enhances the adaptability of the voltage regulation system to the dynamic change of the load current, but also significantly improves the transient response speed, avoiding voltage deviation caused by load mutation; secondly, the feedforward compensation amount is determined by using the load current prediction sequence combined with the response characteristic of the output voltage of the DC-DC converter to the load current under different working conditions, so that voltage regulation can be performed before load fluctuation occurs, reducing the voltage ripple amplitude from the source and reducing the interference risk to sensitive analog circuits and radio frequency modules; further, by collecting the disturbance information when the load suddenly changes and suppressing the output voltage ripple, immediate feedback adjustment of the actual disturbance can be realized, compensating for the response lag problem existing in the traditional closed-loop control, and improving the voltage regulation precision and dynamic adjustment ability of the voltage regulation system; finally, by combining the feedforward compensation amount with the disturbance suppression degree, the closed-loop regulation of the power supply voltage of the wireless sensor is realized, and the closed-loop gain coefficient is generated accordingly, and then the voltage adjustment instruction is generated, completing the whole process of dynamic voltage control. This closed-loop mechanism can be adaptively optimized on the basis of feedforward prediction and disturbance suppression, so that the power supply voltage remains stable under different load working conditions, while the response ability of the voltage regulation system to sudden load disturbance is improved, and the precision and reliability of voltage regulation are enhanced as a whole.

[0044] In summary, the technical solution adopted in the present application can suppress the output voltage ripple interference of the DC-DC converter in the wireless sensor voltage regulation process. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only represent some embodiments of the present application, and all other drawings can be obtained by those skilled in the art without any creative effort.

[0046] Figure 1 is an exemplary flow chart of a wireless sensor dynamic voltage regulation method based on load current prediction provided by the present application;

[0047] Figure 2 is a flow chart of determining feedforward compensation provided by the present application;

[0048] Figure 3 is a flow chart of determining disturbance suppression provided by the present application;

[0049] Figure 4 is a module structure diagram of a wireless sensor dynamic voltage regulation system based on load current prediction provided by the present application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments only represent some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort fall within the scope of protection of the present application.

[0051] The embodiments of the present application provide a wireless sensor dynamic voltage regulation method and system based on load current prediction. The core is to obtain historical load current data of the wireless sensor under different working conditions, and then to build a load current prediction model. According to the load current prediction sequence output by the load current prediction model and the response characteristic of the output voltage of the direct current-direct current converter in the wireless sensor to the load current under different working conditions, the feedforward compensation of the power supply voltage of the wireless sensor under different working conditions is determined. The load disturbance information of the wireless sensor when the load current is suddenly changed is collected, and the output voltage ripple of the direct current-direct current converter is suppressed according to the load disturbance information, so as to obtain the disturbance suppression of the output voltage ripple of the direct current-direct current converter. The power supply voltage of the wireless sensor is closed-loop regulated by the disturbance suppression and all the feedforward compensations, so as to obtain the closed-loop gain coefficient of the power supply voltage, and then the voltage regulation instruction of the wireless sensor is generated according to the closed-loop gain coefficient.

[0052] Embodiment one, in order to better understand the above technical solutions, the following will be combined with the description of the drawings and specific embodiments to explain the above technical solutions in detail, reference Figure 1 As shown in the figure, the figure is an exemplary flow chart of a wireless sensor dynamic voltage regulation method based on load current prediction according to the embodiment of the present application, and the wireless sensor dynamic voltage regulation method comprises the following steps:

[0053] In step S1, the historical load current data of the wireless sensor under different working conditions is obtained, and then a load current prediction model is constructed.

[0054] It should be noted that the different working conditions in the present application represent the working mode under different task states, specifically including standby working condition, data acquisition working condition, data processing working condition, data transmission working condition and abnormal working condition; it should also be noted that the historical load current data represents an ordered sequence of load current changes over time.

[0055] In the present embodiment, the construction of the load current prediction model can be realized by the following steps:

[0056] Obtain the historical load current data of the wireless sensor under different working conditions;

[0057] Preprocess all the historical load current data to obtain different preprocessed load current data;

[0058] Extract time sequence features and working condition association features from each preprocessed load current data;

[0059] According to all the time sequence features and all the working condition association features, the model is trained to obtain the load current prediction model.

[0060] It should be noted that the time sequence features in the present application represent data features reflecting the change of load current over time; the working condition association features represent the feature representation of the working state information of the wireless sensor; the load current prediction model represents the time sequence prediction model for predicting future load current changes.

[0061] In a specific implementation, first, historical load current data of a wireless sensor under different working conditions is acquired; second, average values of five consecutive sampling points are calculated for all load current data by using a moving average method to eliminate random noise, abnormal data points exceeding a range of plus or minus three times a standard deviation of the average value are removed by using a 3σ criterion, and load current values are linearly mapped to an interval of [0, 1] by normalization processing, thereby obtaining different preprocessed current data; then, time sequence features and working condition association features are extracted from all preprocessed load current data, the time sequence features are obtained by statistical analysis methods and include an average value, a standard deviation, a maximum value, a minimum value, and a difference between adjacent sampling points in a sliding window, and are used to reflect fluctuation amplitudes and change trends of the load current, and the working condition association features can be obtained by one-hot encoding of working condition labels to convert category type working condition information into numerical type input features, to ensure that the model can simultaneously perceive dynamic characteristics of the current and working condition information; then, the extracted time sequence features and working condition association features are spliced and input into a long short-term memory network model, a load current value at a specific time in the future is taken as a prediction target, an Adam optimization algorithm is used to iteratively update parameters of the model, a mean square error is taken as a loss function to measure prediction accuracy, in a training process, parameters of the long short-term memory network model are gradually adjusted through multiple iterations, and when prediction errors of the long short-term memory network model on a validation set tend to be stable and are lower than a preset threshold, the training is stopped, and a model obtained after the training is stopped is taken as a load current prediction model.

[0062] In step S2, a feedforward compensation amount of a power supply voltage of the wireless sensor under different working conditions is determined according to the load current prediction sequence output by the load current prediction model and response characteristics of output voltages of the DC-DC converter in the wireless sensor under different working conditions to the load current.

[0063] Preferably, in the embodiment, the feedforward compensation amount of the power supply voltage of the wireless sensor under different working conditions is determined according to the load current prediction sequence output by the load current prediction model and the response characteristics of the output voltages of the DC-DC converter in the wireless sensor under different working conditions to the load current, as shown in FIG. 6, which is a flowchart for determining the feedforward compensation amount in some embodiments of the present application. The feedforward compensation amount in the embodiment can be implemented by using the following steps: Figure 2

[0064] In step S21, response characteristics of output voltages of the DC-DC converter in the wireless sensor under different working conditions to the load current are acquired, and the response characteristics represent delay times and voltage deviation amplitudes of the output voltages changing with the load current.

[0065] In step S22, voltage change rates of the output voltages changing with the load current under different working conditions are determined according to the response characteristics of the output voltages of the DC-DC converter in the wireless sensor under different working conditions to the load current.​

[0066] In step S23, the load current trend value under different working conditions is extracted from the load current prediction sequence output by the load current prediction model through the response characteristic of the output voltage to the load current under different working conditions;

[0067] In step S24, the power supply voltage of the wireless sensor under different working conditions is fed forwardly compensated according to the load current trend value under different working conditions and the voltage change rate of the output voltage to the load current under different working conditions, to obtain the feed forward compensation amount of the power supply voltage of the wireless sensor under different working conditions.

[0068] It should be noted that the load current trend value in the present application represents the load current change amplitude within the future compensation time window, and the feed forward compensation amount represents the compensation voltage that can offset the output voltage fluctuation caused by the load current change.

[0069] In specific implementation, first, under different working conditions, a preset load current step signal (for example, from 20 μA to 300 mA) is input to the DC-DC converter in the wireless sensor, the change curve of the output voltage at the current step time is synchronously collected by an oscilloscope, the time difference between the starting point of the current step and the starting point of the voltage change is taken as the delay time under the corresponding working condition, the difference between the voltage before the step and the voltage after the step is taken as the voltage deviation amplitude under the corresponding working condition, and the characteristic composed of the delay time and the voltage deviation amplitude under the corresponding working condition is taken as the response characteristic of the output voltage to the load current of the DC-DC converter in the wireless sensor under the corresponding working condition; second, the voltage deviation amplitude in the response characteristic of the output voltage to the load current of the DC-DC converter in the wireless sensor under different working conditions is divided by the change amount of the load current under the corresponding working condition, and the value obtained by the division is taken as the voltage change rate of the output voltage to the load current under the corresponding working condition; then, the load current prediction sequence output by the load current prediction model is combined with the delay time in the response characteristic of the output voltage to the load current of the DC-DC converter in the wireless sensor under different working conditions to determine the early intervention window (for example, if the delay time is 6 μs, the load current prediction value within the future 6 μs is taken), the difference between the load current starting value and the load current prediction end value within the window is calculated, and the difference is taken as the load current trend value under the corresponding working condition; finally, the load current trend value under different working conditions is multiplied by the voltage change rate under the corresponding working condition, and the value obtained by the multiplication is taken as the feed forward compensation amount of the power supply voltage of the wireless sensor under the corresponding working condition.

[0070] In step S3, load disturbance information of the wireless sensor at the time of load current mutation is collected, and output voltage ripple of the DC-DC converter is suppressed according to the load disturbance information, so as to obtain a disturbance suppression degree of the output voltage ripple of the DC-DC converter.

[0071] Preferably, in the embodiment, the output voltage ripple of the DC-DC converter is suppressed according to the load disturbance information, so as to obtain a disturbance suppression degree of the output voltage ripple of the DC-DC converter, and the disturbance suppression degree is determined with reference to Figure 3 As shown in the figure, the figure is a flow diagram for determining the disturbance suppression degree in some embodiments of the application, and the disturbance suppression degree in the embodiment can be realized by the following steps:

[0072] In step S31, load disturbance information of the wireless sensor at the time of load current mutation is collected.

[0073] In step S32, feature extraction is performed on the load disturbance information, so as to obtain disturbance mutation features and disturbance time features.

[0074] In step S33, feedback suppression is performed on the output voltage ripple of the DC-DC converter by using the disturbance mutation features and the disturbance time features, so as to obtain a feedback suppression index of the output voltage ripple of the DC-DC converter.

[0075] In step S34, the disturbance suppression degree of the output voltage ripple of the DC-DC converter is determined according to the feedback suppression index and an output voltage ripple amplitude of the DC-DC converter in a steady state before load current mutation.

[0076] It should be noted that the load disturbance information in the application represents characteristic information of disturbance to the output voltage of the DC-DC converter when the load current of the wireless sensor is mutated; the disturbance mutation features represent features reflecting the degree of change of the load current; the disturbance time features represent time features of the load current disturbance; the feedback suppression index represents the suppression degree of the feedback control link to the voltage ripple change caused by the load disturbance; and the disturbance suppression degree represents the reduction ratio of the output voltage ripple of the DC-DC converter compared with the steady state ripple before the disturbance.

[0077] In a specific implementation, first, when the load current of the wireless sensor suddenly changes (for example, suddenly increases from 100 μA to 500 mA), the waveform at the moment of the sudden change of the current (including the amplitude of the sudden change and the duration) and the change waveform of the corresponding output voltage ripple are synchronously recorded, and the synchronously collected waveform data are taken as the load disturbance information; second, the peak value detection method (finding the maximum value and the minimum value of the sudden change of the current by traversing the waveform data) is used for the load disturbance information, the peak value difference of the sudden change of the current is taken as the disturbance mutation characteristic, and the time difference between the starting moment and the stable moment of the sudden change of the current is taken as the disturbance time characteristic; third, the proportional-integral feedback control algorithm is used, the disturbance mutation characteristic is taken as the proportional term input (the proportional coefficient is set to 0.01), the disturbance time characteristic is taken as the integral term input (the integral coefficient is set to 0.005), the ratio of the adjustment amount output by the proportional-integral controller to the original ripple amplitude (for example, the adjustment amount 0.08 V ÷ the original ripple amplitude 0.2 V = 0.4) is taken as the feedback suppression index of the output voltage ripple of the DC-DC converter; and finally, the feedback suppression index is multiplied by the output voltage ripple amplitude before the sudden change of the load current in the stable state (for example, 0.2 V) (0.4 × 0.2 V = 0.08 V), the product is subtracted from the stable state ripple amplitude (0.2 V - 0.08 V = 0.12 V), and the percentage of the difference value to the stable state ripple amplitude (0.12 V ÷ 0.2 V × 100% = 60%) is taken as the disturbance suppression degree of the output voltage ripple of the DC-DC converter.

[0078] In step S4, the power supply voltage of the wireless sensor is closed-loop adjusted by the disturbance suppression degree and all the feedforward compensation amounts, to obtain a closed-loop gain coefficient of the power supply voltage, and then the voltage adjustment instruction of the wireless sensor is generated according to the closed-loop gain coefficient.

[0079] In the embodiment, the closed-loop gain coefficient of the power supply voltage obtained by closed-loop adjusting the power supply voltage of the wireless sensor by the disturbance suppression degree and all the feedforward compensation amounts can be realized by the following steps:

[0080] Adjusting the response sensitivity of the closed-loop adjustment according to the disturbance suppression degree;

[0081] Determining the power supply voltage deviation of the wireless sensor;

[0082] Closed-loop verifying the power supply voltage of the wireless sensor by all the feedforward compensation amounts, to obtain a closed-loop verification sequence of the power supply voltage;

[0083] Determining the closed-loop gain coefficient of the power supply voltage according to the response sensitivity, the power supply voltage deviation and the closed-loop verification sequence.

[0084] It should be noted that the response sensitivity in the present application represents the response strength of the closed-loop regulation under the disturbance change; the power supply voltage deviation represents the deviation between the current power supply voltage and the target voltage; the closed-loop check sequence represents the stability check sequence of the power supply voltage of the wireless sensor changing with time in the closed-loop regulation process; and the closed-loop gain coefficient represents the gain coefficient of the response strength of the power supply voltage deviation in the closed-loop regulation process.

[0085] In the implementation, first, the disturbance suppression degree is multiplied by the preset reference sensitivity, and the result is taken as the response sensitivity of the closed-loop regulation; second, the actual value of the current power supply voltage of the wireless sensor is collected in real time, and the target set voltage is differentially calculated to obtain a voltage deviation value, and the obtained voltage deviation value is taken as the power supply voltage deviation; third, the feedforward compensation amounts under various working conditions are arranged in time sequence, and are compared with the actual voltage fluctuation values collected after the compensation is implemented, the actual deviations corresponding to the feedforward compensation amounts are calculated, and the deviation data are combined in time sequence to form a closed-loop check sequence; and finally, a proportional-differential control algorithm is adopted, the response sensitivity is taken as a proportional term coefficient, the power supply voltage deviation is taken as an input signal, the mean value of the closed-loop check sequence is taken as a differential term input, and the closed-loop gain coefficient is calculated according to the linear superposition relationship between the proportional term output and the differential term output.

[0086] In the present embodiment, the voltage regulation instruction of the wireless sensor generated according to the closed-loop gain coefficient can be implemented by the following steps:

[0087] determining a control gain parameter of the power supply voltage of the wireless sensor according to the closed-loop gain coefficient;

[0088] generating the voltage regulation instruction of the wireless sensor through the control gain parameter.

[0089] It should be noted that the control gain parameter in the present application reflects the actual action strength of the closed-loop gain coefficient in the regulation range of the power supply voltage of the wireless sensor; and the voltage regulation instruction represents the instruction for regulating the power supply voltage of the wireless sensor.

[0090] In a specific implementation, first, the closed-loop gain coefficient is multiplied by the feedback voltage division ratio of the DC-DC converter in the wireless sensor (calculated by the circuit resistance parameters, for example, feedback resistance R1=10kΩ, R2=2kΩ, feedback voltage division ratio=R2 / (R1+R2)=2 / 12≈0.167), and then divided by the minimum adjustment step value of the DC-DC converter (i.e., the minimum voltage change amount that can be recognized by the hardware), and then rounded to an integer, and the obtained integer is taken as the control gain parameter of the power supply voltage of the wireless sensor; second, using a common digital-to-analog conversion output method, the current power supply voltage deviation is multiplied by the control gain parameter to obtain the voltage amount that needs to be adjusted, and the current power supply voltage deviation is the difference between the actual voltage and the target voltage, and then the voltage amount is converted into a digital amount, specifically, the voltage amount that needs to be adjusted is divided by the minimum voltage resolution of digital-to-analog conversion, and the minimum voltage resolution of digital-to-analog conversion is obtained by dividing the output range by the total scale number corresponding to the number of bits of digital-to-analog conversion, and the calculated digital amount is taken as the voltage adjustment instruction, which is then sent to the control module of the DC-DC converter.

[0091] As can be seen from the above, in the present application, the voltage adjustment instruction of the wireless sensor can be generated according to the closed-loop gain coefficient; first, by obtaining the historical load current data of the wireless sensor under different working conditions and constructing a load current prediction model, the load change trend can be predicted in advance, which provides a scientific basis for the feedforward compensation of the power supply voltage, this step not only enhances the adaptability of the voltage regulation system to the dynamic change of the load current, but also significantly improves the transient response speed, avoiding the voltage deviation caused by sudden load change; second, the feedforward compensation amount is determined by using the load current prediction sequence in combination with the response characteristics of the output voltage of the DC-DC converter to the load current under different working conditions, so that voltage regulation can be performed before the load fluctuation occurs, thereby reducing the voltage ripple amplitude from the source and reducing the interference risk to sensitive analog circuits and radio frequency modules; further, by collecting disturbance information when the load suddenly changes and suppressing the output voltage ripple, immediate feedback regulation of the actual disturbance can be realized, the response lag problem existing in the traditional closed-loop control is compensated, and the voltage regulation accuracy and dynamic regulation capability of the voltage regulation system are improved; finally, the closed-loop regulation of the power supply voltage of the wireless sensor is realized by combining the feedforward compensation amount with the disturbance suppression amount, and the closed-loop gain coefficient is generated accordingly, and then the voltage adjustment instruction is generated, completing the whole process of dynamic voltage control, and this closed-loop mechanism can be adaptively optimized on the basis of feedforward prediction and disturbance suppression, so that the power supply voltage remains stable under different load working conditions, while the response capability of the voltage regulation system to sudden load disturbance is improved, and the accuracy and reliability of voltage regulation are improved as a whole.

[0092] In summary, the technical solution adopted in the present application can suppress the output voltage ripple interference of the DC-DC converter in the voltage regulation process of the wireless sensor.

[0093] In the second embodiment, the application provides a wireless sensor dynamic voltage regulation system based on load current prediction. Referring to FIG. 1, which is a module structure diagram of a wireless sensor dynamic voltage regulation system based on load current prediction according to the second embodiment of the application, the wireless sensor dynamic voltage regulation system comprises: Figure 4 a model construction module 100, configured to acquire historical load current data of the wireless sensor under different working conditions, and to construct a load current prediction model;

[0094] a feedforward compensation module 200, configured to determine a feedforward compensation amount of supply voltage of the wireless sensor under different working conditions according to a load current prediction sequence output by the load current prediction model and a response characteristic of output voltage of a direct current-direct current converter in the wireless sensor to load current under different working conditions;

[0095] a disturbance suppression module 300, configured to acquire load disturbance information of the wireless sensor when the load current mutates, to suppress output voltage ripple of the direct current-direct current converter according to the load disturbance information, and to obtain a disturbance suppression degree of the output voltage ripple of the direct current-direct current converter;

[0096] a closed-loop regulation module 400, configured to perform closed-loop regulation on the supply voltage of the wireless sensor through the disturbance suppression degree and all the feedforward compensation amounts, to obtain a closed-loop gain coefficient of the supply voltage, and to generate a voltage regulation instruction of the wireless sensor according to the closed-loop gain coefficient.

[0097] The application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in one or more flows or one or more blocks in the flowcharts and / or block diagrams.

[0098] The functions specified in one or more flows or one or more blocks in the flowcharts and / or block diagrams can be implemented by an apparatus. Figure 1 The functions specified in one or more flows or one or more blocks in the flowcharts and / or block diagrams can be implemented by an apparatus. Figure 1 The functions specified in one or more flows or one or more blocks in the flowcharts and / or block diagrams can be implemented by an apparatus.

[0099] Those skilled in the art can understand that all or part of the steps of various methods in the above embodiments can be completed by instructing the relevant hardware by means of a program, and the program can be stored in a computer readable storage medium, including Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk storage, magnetic disk storage, magnetic tape storage, or any other medium that can be used to carry or store data in a computer readable manner.

[0100] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

Claims

1. A wireless sensor dynamic voltage regulation method based on load current prediction, characterized by, The wireless sensor dynamic voltage regulation method comprises the following steps: Obtaining historical load current data of the wireless sensor under different working conditions, and then constructing a load current prediction model; According to the load current prediction sequence output by the load current prediction model and the response characteristics of the output voltage of the DC-DC converter in the wireless sensor to the load current under different working conditions, determining the feedforward compensation amount of the power supply voltage of the wireless sensor under different working conditions; Collecting load disturbance information of the wireless sensor when the load current suddenly changes, and suppressing the output voltage ripple of the DC-DC converter according to the load disturbance information to obtain the disturbance suppression degree of the output voltage ripple of the DC-DC converter; Through the disturbance suppression degree and all feedforward compensation amounts, the power supply voltage of the wireless sensor is closed-loop regulated to obtain the closed-loop gain coefficient of the power supply voltage, and then the voltage regulation instruction of the wireless sensor is generated according to the closed-loop gain coefficient.

2. A wireless sensor dynamic voltage regulation method based on load current prediction as claimed in claim 1, wherein, The construction of the load current prediction model specifically comprises: Obtaining historical load current data of the wireless sensor under different working conditions; Preprocessing all historical load current data to obtain different pretreated load current data; Extracting time sequence features and working condition association features from each pretreated load current data; According to all time sequence features and all working condition association features, the model is trained to obtain the load current prediction model.

3. A wireless sensor dynamic voltage regulation method based on load current prediction as claimed in claim 1, wherein, According to the load current prediction sequence output by the load current prediction model and the response characteristics of the output voltage of the DC-DC converter in the wireless sensor to the load current under different working conditions, determining the feedforward compensation amount of the power supply voltage of the wireless sensor under different working conditions specifically comprises: Obtaining the response characteristics of the output voltage of the DC-DC converter in the wireless sensor to the load current under different working conditions, wherein the response characteristics represent the delay time and voltage deviation amplitude of the change of the output voltage with the load current; According to the response characteristics of the output voltage to the load current under different working conditions, the voltage change rate of the output voltage with the load current under different working conditions is determined; According to the response characteristics of the output voltage to the load current under different working conditions, the load current change trend value under different working conditions is extracted from the load current prediction sequence output by the load current prediction model; According to the load current change trend value under different working conditions and the voltage change rate of the output voltage with the load current under different working conditions, the power supply voltage of the wireless sensor under different working conditions is feedforward compensated to obtain the feedforward compensation amount of the power supply voltage of the wireless sensor under different working conditions.

4. A wireless sensor dynamic voltage regulation method based on load current prediction as claimed in claim 1, wherein, According to the load disturbance information, the output voltage ripple of the DC-DC converter is suppressed to obtain the disturbance suppression degree of the output voltage ripple of the DC-DC converter, specifically comprising: Collecting load disturbance information of the wireless sensor when the load current suddenly changes; Extracting features from the load disturbance information to obtain disturbance mutation features and disturbance time features; Through the disturbance mutation features and the disturbance time features, the output voltage ripple of the DC-DC converter is feedback suppressed to obtain the feedback suppression index of the output voltage ripple of the DC-DC converter; The disturbance suppression index is used to determine the disturbance suppression degree of the output voltage ripple of the DC-DC converter.

5. A wireless sensor dynamic voltage regulation method based on load current prediction as claimed in claim 1, wherein, The disturbance suppression degree and all the feedforward compensation amounts are used to close-loop regulate the supply voltage of the wireless sensor, and a closed-loop gain coefficient of the supply voltage is obtained. The response sensitivity of the closed-loop regulation is adjusted according to the disturbance suppression degree. The supply voltage deviation of the wireless sensor is determined. The supply voltage of the wireless sensor is closed-loop checked by all the feedforward compensation amounts, and a closed-loop checking sequence of the supply voltage is obtained. A closed-loop gain coefficient of the supply voltage is determined according to the response sensitivity, the supply voltage deviation and the closed-loop checking sequence.

6. A wireless sensor dynamic voltage regulation method based on load current prediction as claimed in claim 1, wherein, The voltage regulation instruction of the wireless sensor is generated according to the closed-loop gain coefficient. A control gain parameter of the supply voltage of the wireless sensor is determined according to the closed-loop gain coefficient. The voltage regulation instruction of the wireless sensor is generated by the control gain parameter.

7. A wireless sensor dynamic voltage regulation method based on load current prediction as claimed in claim 1, wherein, The feedforward compensation amount represents a compensation voltage that is applied in advance to offset the output voltage fluctuation caused by the change of the load current.

8. A wireless sensor dynamic voltage regulation method based on load current prediction as claimed in claim 1, wherein, The disturbance suppression degree represents the reduction ratio of the output voltage ripple of the DC-DC converter compared with the steady-state ripple before the disturbance.

9. A wireless sensor dynamic voltage regulation method based on load current prediction as claimed in claim 1, wherein, The closed-loop gain coefficient represents the gain coefficient of the response intensity to the supply voltage deviation in the closed-loop regulation process.

10. A wireless sensor dynamic voltage regulation system based on load current prediction for performing a wireless sensor dynamic voltage regulation method based on load current prediction according to any one of claims 1 to 9, characterized in that, The wireless sensor dynamic voltage regulation system comprises: a model construction module configured to acquire historical load current data of the wireless sensor under different working conditions, and to construct a load current prediction model; a feedforward compensation module configured to determine feedforward compensation amounts of the supply voltage of the wireless sensor under different working conditions according to a load current prediction sequence output by the load current prediction model and response characteristics of output voltages of a DC-DC converter in the wireless sensor to load currents under different working conditions; a disturbance suppression module configured to acquire load disturbance information of the wireless sensor when the load current is suddenly changed, to suppress the output voltage ripple of the DC-DC converter according to the load disturbance information, and to obtain a disturbance suppression degree of the output voltage ripple of the DC-DC converter; a closed-loop regulation module configured to close-loop regulate the supply voltage of the wireless sensor by the disturbance suppression degree and all the feedforward compensation amounts, to obtain a closed-loop gain coefficient of the supply voltage, and to generate a voltage regulation instruction of the wireless sensor according to the closed-loop gain coefficient.

Images