Automatic fault detection method and system for intelligent electric kettle

Abstract

The invention belongs to the field of intelligent detection and feature quantification, and provides an automatic fault detection method and system for an intelligent electric kettle, and the method specifically comprises the steps: recognizing execution points from the intelligent electric kettle, enabling each execution point to form an execution current sequence, carrying out the Fourier transform feature extraction from the execution current sequence, and forming an execution feature group; and then calculating an abnormal pointing scalar by executing the feature group, and finally performing fault judgment according to the abnormal pointing scalar. The current signal data of the intelligent electric kettle in the working process are collected and analyzed in real time, under the condition that the intelligent electric kettle has multiple functions, the tedious setting process of monitoring and modulating regulation and control components of the intelligent electric kettle is avoided, the function program where a fault occurs can be automatically positioned, and the working efficiency of the intelligent electric kettle is improved. Therefore, the error code is displayed to realize fault judgment, fault error judgment caused by an asynchronous state among a plurality of monitoring means is avoided, and the specific function fault identification accuracy of the intelligent electric kettle is greatly improved.

Description

Technical Field

[0001] The invention belongs to the field of intelligent detection and feature quantification, and in particular relates to an automatic fault detection method and system for an intelligent electric kettle. Background Art

[0002] The versatile features of smart electric kettles make them widely used. The multifunctionality of smart electric kettles depends on the functional programs set by the manufacturer at the software level on the one hand, and on the diverse sensing and monitoring methods on the other hand. The combination of the two greatly enriches the application scenarios of electric kettles. However, the functional programs set by the manufacturer usually have unchangeable step requirements, and the target functions are realized in the joint action of sensing and control. Therefore, multifunctional electric kettles have quite high requirements for the monitoring sensitivity and control sensitivity of the control components. The control components include sensors and controllers. As the service life increases, these sensors and controllers will form different degrees of aging problems, and this aging problem often has the characteristics of slow change, resulting in electric kettle failure, which is also one of the main technical challenges in the design and production of smart electric kettles on the market. At present, the commonly used method in the industry is to monitor each sensor and controller. When the corresponding monitored device ages or fails, the corresponding functions of these aging devices are excluded, thereby preventing users from having functional deviation risks during use. Functional deviation risks refer to the problem that the effect of functional realization is inconsistent with the original set effect. However, this method has the problem that the monitoring behavior of components needs to be modulated separately for each functional program, and each preset functional program needs to measure and formulate relevant thresholds for each of its control components through experiments. Therefore, the setting process of this fault analysis for multi-functional electric kettles is inefficient and cumbersome. On the other hand, the integrity of the monitoring function will also be at risk of loss over time. This is because this method relies on multiple circuit monitoring components, which is easy to induce fault error judgment caused by asynchronous states between multiple monitoring means. Therefore, a more efficient and intelligent fault detection method and system is urgently needed. Summary of the invention

[0003] The purpose of the present invention is to provide an automatic fault detection method and system for an intelligent electric kettle to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0004] In order to achieve the above object, according to one aspect of the present invention, a method for automatic fault detection of an intelligent electric kettle is provided, the method comprising the following steps: Identify execution points from the smart electric kettle; form an execution current sequence at each execution point; perform Fourier transform feature extraction from the execution current sequence to form an execution feature group; calculate an abnormal pointing scalar through the execution feature group; and make a fault judgment based on the abnormal pointing scalar.

[0005] Furthermore, the method for identifying execution points from the smart electric kettle is: the smart electric kettle has several functional programs, and each execution of any functional program is recorded as an execution point of the functional program, and execution points in which work tasks are not fully executed and the duration is less than 120 seconds are excluded.

[0006] Furthermore, the method for forming an execution current sequence at each execution point is: for any execution point, the current signal of the control component is collected in real time by the current sensor of the smart electric kettle, and the current signal obtained in the time period from the start to the end of the execution point is constructed into a sequence in chronological order, which is recorded as the execution current sequence.

[0007] Furthermore, the method of performing Fourier transform feature extraction from the execution current sequence to form an execution feature group is: using fast Fourier transform to convert the execution current sequence into a frequency domain signal to obtain spectrum data, and extracting the main frequency and spectrum amplitude vector from the spectrum data as the execution feature group.

[0008] Furthermore, the method for calculating the abnormal pointing scalar by executing the feature group is: the average value of all components of the spectrum amplitude vector is recorded as ave, for any spectrum amplitude vector, the maximum value of its components is recorded as Mhx, the minimum value is recorded as Mhn, and the average value is recorded as ave, and the balanced difference divergence Vle is calculated: Vle = ave (Mhx-ave) / (ave-Mhn); if the balanced difference divergence of the execution point is greater than the component corresponding to the main frequency, it is recorded as the first scattered element point, otherwise it is a stable scattered execution point; the first stable scattered execution point of any first scattered element point in the reverse time direction is used as its reverse search execution point; Calculate the cosine similarity between the first scattered element point and its reverse search execution point. If the cosine similarity is greater than Then the first scattered element point is recorded as the second scattered element point, i is set as the serial number of the second scattered element point, and the total number of second scattered element points in the fault tolerance interval is recorded as Num; the spectrum amplitude vector of the i-th second scattered element point and its inverse search execution point is recorded as crt i and cht i , the main frequencies are denoted as crt i .mhz and cht i .mhz; remember crt i .ave and cht i The ratio of .ave is the inversion coefficient RA i , will cht i and crt i The cosine similarity is denoted as SE i ; Calculate the abnormal pointing scalar Nstg: ; where crt i .ax and crti .av are the variance and mean of each component in the i-th second scattered element point, and ln() is the logarithmic function with the natural logarithm e as the base.

[0009] The above-mentioned process of calculating the abnormal pointing scalar is carried out on the basis of the screening of the second scattered element point, so it can effectively quantify the risk of functional deviation induced by slow aging of individual components in the complex circuit design during use of the multifunctional smart electric kettle under the working procedure where the tasks of various components overlap. However, since this quantification method has a low comparison intensity of historical data, in the subsequent detection process, the longer the electric kettle is used, the more likely it is to lose adaptability to the low-order data of the abnormal pointing scalar value, resulting in erroneous judgment results of fault detection. In order to solve this problem, the present invention also proposes another more preferred solution.

[0010] Preferably, the method for calculating the abnormal pointing scalar by executing the feature group is: the mode of the main frequencies of all execution points is recorded as the reference main frequency, the spectrum amplitude sequence corresponding to any reference main frequency constitutes the frequency amplitude feature vector, and the standard deviation of all amplitude values ​​in the frequency amplitude feature vector is the frequency amplitude outlier rate; the weighted average of the frequency amplitude feature vectors of all reference main frequencies is recorded as the reference frequency amplitude feature vector; the cumulative value of the square of all amplitude values ​​in the reference frequency amplitude feature vector is recorded as the reference spectrum energy, if the cumulative value of the square of all amplitude values ​​in the spectrum amplitude sequence corresponding to any execution point is greater than the reference spectrum energy, then the execution point is recorded as a singular spectrum point, and all execution points between the singular spectrum point and the first singular spectrum point in the reverse execution time direction are set to form an execution point set, which is recorded as a sub-spectrum retrieval set; In the sub-spectrum search set, the number of all non-singular spectrum points is recorded as the frequency-amplitude lag order Lago. According to the frequency-amplitude lag order and the spectrum amplitude sequence, the frequency-amplitude correlation Framp is calculated: ; Where MNum is the number of amplitude values ​​contained in each spectrum amplitude sequence, FSmag and ENmag are the spectrum amplitude sequences corresponding to the first and last singular spectrum points in the sub-spectrum retrieval set, max() and hs() are the maximum value function and the harmonic mean function, respectively, and exp() is the exponential function with the natural constant e as the base. The calculation principle of frequency-amplitude correlation is that the spectrum complexity of other execution points can be determined by calculating the frequency-amplitude correlation of two specific execution points, without quantifying the spectrum amplitude sequence of the execution points one by one, thereby effectively optimizing the monitoring process and reducing the inefficient and cumbersome setting process in fault analysis; In the sub-spectrum retrieval set, the inverse number of all amplitude values ​​in the spectrum amplitude sequence corresponding to any execution point is recorded as the spectrum entropy value, and the product of the spectrum entropy value and the frequency-amplitude correlation of any execution point is recorded as the spectrum complexity Plety of the execution point; the execution point corresponding to the maximum main frequency in the sub-spectrum retrieval set is recorded as the high-frequency execution point, and the spectrum amplitude sequence corresponding to any non-high-frequency execution point constitutes a frequency-amplitude feature matrix Chama, and the frequency-amplitude feature matrix of the high-frequency execution point is recorded as Hchma, and the product of the transpose of the frequency-amplitude feature matrix of any execution point and the frequency-amplitude feature matrix of the high-frequency execution point is recorded as the heterogeneity matrix Cgrum, and the frequency-amplitude feature matrix of any execution point is subtracted from the frequency-amplitude feature matrices of other execution points to obtain all spectrum difference feature matrices of the execution point, and the variance of all elements in the spectrum difference feature matrix is ​​calculated and recorded as the spectrum deviation number; the mean of all spectrum deviation numbers of any execution point is recorded as the spectrum deviation coefficient, and the spectrum deviation coefficients of all execution points are arranged in ascending order, and the ratio of the serial number value corresponding to any execution point to the total number of execution points is recorded as the spectrum risk coefficient Trais; The abnormal direction scalar Anosc of the current execution point is calculated based on the anomaly concordance matrix and the spectrum risk coefficient: Anosc=ln(Plety)× tr[Cgrum]×Trais MF ∑ k2=1 MNum (APyu k2 ) 2 ; Among them, k2 is the cumulative variable, APyu k2 is the k2th amplitude value of the spectrum amplitude sequence corresponding to the execution point, tr[] is the diagonal accumulation function, which returns the cumulative sum of each diagonal element in the calling matrix. The calling matrix in the formula is a heterogeneous matrix; ln() is a logarithmic function with the natural constant e as the base.

[0011] Beneficial effects: Since the abnormal scalar quantity is comprehensively analyzed based on the set of current signal sequences in different periods, it can effectively quantify the risk of functional deviation caused by the slow aging of individual components in the complex circuit design during the use of the multi-functional smart electric kettle with overlapping tasks between various components, thereby identifying the probability of program functionality collapse in the current state, thereby ensuring the consistency of the function realization effect with the originally set effect to the greatest extent.

[0012] Furthermore, the method for fault judgment based on the abnormal pointing scalar is: for any functional program, preset an integer variable as the variation fault tolerance interval errgp, obtain the minimum value of the abnormal pointing scalars of the most recent errgp execution points and record it as the adjacent abnormal pointing scalar, obtain the average value of the abnormal pointing scalars of all execution points between the first execution point and the current moment and record it as the pointing scalar benchmark, when the adjacent abnormal pointing scalar is greater than the pointing scalar benchmark, it is determined that there is a fault in the functional program, and the next time the functional program is enabled, the fault judgment is performed by displaying the error code of the functional program on the display screen of the smart electric kettle.

[0013] Preferably, all undefined variables in the present invention, if not clearly defined, can be manually set thresholds.

[0014] The present invention also provides an intelligent electric kettle automatic fault detection system, the intelligent electric kettle automatic fault detection system comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor implementing the steps in the intelligent electric kettle automatic fault detection method when executing the computer program, the intelligent electric kettle automatic fault detection system can be run in computing devices such as desktop computers, notebook computers, PDAs, and cloud data centers, and the executable system may include, but is not limited to, a processor, a memory, and a server cluster, and the processor executes the computer program to run in the following system units: An execution point identification unit, used for identifying an execution point from the smart electric kettle; An execution current sequence acquisition unit is used to form an execution current sequence for each execution point; A feature group building unit, used for performing Fourier transform feature extraction from an execution current sequence to form an execution feature group; An abnormal direction scalar calculation unit, used for calculating the abnormal direction scalar by executing the feature group; The fault judgment unit is used to judge the fault according to the abnormal pointing scalar.

[0015] The beneficial effects of the present invention are as follows: the present invention provides an automatic fault detection method and system for an intelligent electric kettle, which effectively quantifies the risk of functional deviation caused by the slow aging of individual components in the complex circuit design during the use of the multifunctional intelligent electric kettle under the working procedure with overlapping tasks between various components, and the problem that the effect of the function realization is inconsistent with the original effect. The determination method of the present invention, while adapting to the multifunctional characteristics of the intelligent electric kettle, also avoids the cumbersome setting process of monitoring and modulating various control components of the intelligent electric kettle, thereby reducing the cumbersome measurement and testing of the component monitoring threshold in the process of product development, especially in the scenario where the monitoring fault occurs due to the aging of the control components of the intelligent electric kettle due to the passage of time, it can avoid the fault error judgment caused by the asynchronous state between multiple monitoring means. The accuracy of specific functional fault recognition of the intelligent electric kettle is greatly improved, and the hidden danger of functional loss of the intelligent electric kettle during use is significantly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings: Figure 1 Shown is a flow chart of an automatic fault detection method for an intelligent electric kettle; Figure 2 Shown is a structural diagram of an automatic fault detection system for an intelligent electric kettle. DETAILED DESCRIPTION

[0017] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0018] like Figure 1 The figure shows a flow chart of an automatic fault detection method for an intelligent electric kettle. Figure 1 To illustrate an automatic fault detection method for an intelligent electric kettle according to an embodiment of the present invention, the method comprises the following steps: Identify execution points from the smart electric kettle; form an execution current sequence at each execution point; perform Fourier transform feature extraction from the execution current sequence to form an execution feature group; calculate an abnormal pointing scalar through the execution feature group; and make a fault judgment based on the abnormal pointing scalar.

[0019] Furthermore, the method for identifying execution points from the smart electric kettle is: the smart electric kettle has several functional programs, and each execution of any functional program is recorded as an execution point of the functional program, and execution points in which work tasks are not fully executed and the duration is less than 120 seconds are excluded.

[0020] Smart electric kettle refers to a multifunctional electric kettle, which contains the function programs pre-set by the manufacturer. These function programs include heating with multi-stage water temperature control, making porridge, making soup, making desserts or making tea, etc. Each execution of any function program is recorded as an execution point of the function program, which means that each execution point corresponds to a working process of a function program in the electric kettle; Furthermore, the method for forming an execution current sequence at each execution point is: for any execution point, the current signal of the control component is collected in real time by the current sensor of the smart electric kettle, and the current signal obtained in the time period from the start to the end of the execution point is constructed into a sequence in chronological order, which is recorded as the execution current sequence.

[0021] The current signal is the current value obtained from the power cord of the electric kettle, thereby covering the current consumption information of all internal control components and actuators.

[0022] Furthermore, the method of performing Fourier transform feature extraction from the execution current sequence to form an execution feature group is: using fast Fourier transform to convert the execution current sequence into a frequency domain signal to obtain spectrum data, and extracting the main frequency and spectrum amplitude vector from the spectrum data as the execution feature group.

[0023] The spectrum data includes multiple frequency components and their corresponding amplitude and phase information; the spectrum amplitude vector is a sequence of amplitude values ​​arranged in ascending order of frequency components.

[0024] Furthermore, the method for calculating the abnormal pointing scalar by executing the feature group is: the average value of all components of the spectrum amplitude vector is recorded as ave, for any spectrum amplitude vector, the maximum value of its components is recorded as Mhx, the minimum value is recorded as Mhn, and the average value is recorded as ave, and the balanced difference divergence Vle is calculated: Vle = ave (Mhx-ave) / (ave-Mhn); if the balanced difference divergence of the execution point is greater than the component corresponding to the main frequency, it is recorded as the first scattered element point, otherwise it is a stable scattered execution point; the first stable scattered execution point of any first scattered element point in the reverse time direction is used as its reverse search execution point; Calculate the cosine similarity between the first scattered element point and its reverse search execution point. If the cosine similarity is greater than Then the first scattered element point is recorded as the second scattered element point, i is set as the serial number of the second scattered element point, and the total number of second scattered element points in the fault tolerance interval is recorded as Num; the spectrum amplitude vector of the i-th second scattered element point and its inverse search execution point is recorded as crt i and cht i , the main frequencies are denoted as crt i .mhz and cht i .mhz; remember crt i .ave and cht i The ratio of .ave is the inversion coefficient RA i , will cht i and crt i The cosine similarity is denoted as SE i ; Calculate the abnormal pointing scalar Nstg: ; where crt i .ax and crt i .av is the variance and mean of each component in the second scattered element point of the ith element, ln() is the logarithmic function with the natural logarithm e as the base, crt i .ave and cht i .ave represents the average value of all components of the spectrum amplitude vector of the i-th second scattered element point and its inverse search execution point.

[0025] Starting from the current execution point, 30-50 execution points in the reverse time direction constitute the fault tolerance interval; when the number of execution points in the fault tolerance interval is less than 30, subsequent operations cannot be performed.

[0026] Preferably, the method for calculating the abnormal pointing scalar by executing the feature group is as follows: any execution point corresponds to an execution current sequence feature group composed of a main frequency MFre and a spectrum amplitude sequence APyu, the mode of the main frequencies of all execution points is recorded as the reference main frequency, the spectrum amplitude sequence corresponding to any reference main frequency constitutes a frequency amplitude feature vector, and the standard deviation of all amplitude values ​​in the frequency amplitude feature vector is the frequency amplitude outlier rate; the weighted average of the frequency amplitude feature vectors of all reference main frequencies is recorded as the reference frequency amplitude feature vector, wherein the weight of each frequency amplitude feature vector is the inverse of the frequency amplitude outlier rate; the cumulative value of the square of all amplitude values ​​in the reference frequency amplitude feature vector is recorded as the reference spectrum energy, if the cumulative value of the square of all amplitude values ​​in the spectrum amplitude sequence corresponding to any execution point is greater than the reference spectrum energy, then the execution point is recorded as a singular spectrum point, and all execution points between the singular spectrum point and the first singular spectrum point in the reverse execution time direction are set to form an execution point set, recorded as a sub-spectrum retrieval set; In the sub-spectrum search set, the number of all non-singular spectrum points is recorded as the frequency-amplitude lag order Lago. According to the frequency-amplitude lag order and the spectrum amplitude sequence, the frequency-amplitude correlation Framp is calculated: ; Where MNum is the number of amplitude values ​​contained in each spectrum amplitude sequence, FSmag and ENmag are the spectrum amplitude sequences corresponding to the first and last singular spectrum points in the sub-spectrum retrieval set, max() and hs() are the maximum value function and the harmonic mean function, respectively, and exp() is the exponential function with the natural constant e as the base. In the sub-spectrum retrieval set, the inverse number of all amplitude values ​​in the spectrum amplitude sequence corresponding to any execution point is denoted as the spectrum entropy value, and the product of the spectrum entropy value and the frequency-amplitude correlation of any execution point is denoted as the spectrum complexity Plety of the execution point; the execution point corresponding to the maximum main frequency in the sub-spectrum retrieval set is denoted as the high-frequency execution point, and the spectrum amplitude sequence corresponding to any non-high-frequency execution point constitutes a frequency-amplitude feature matrix Chama, and the frequency-amplitude feature matrix of the high-frequency execution point is Hchma, where Hchma and Chama are matrices with one row and MNum columns, and their mathematical expressions are Chama=[MGti_1, MGti_2,…, MGti_MNum], Hchma=[HGti_1, HGti_2,…, HGti_MNum] respectively; the product of the transpose of the frequency-amplitude feature matrix of any execution point and the frequency-amplitude feature matrix of the high-frequency execution point is denoted as the heterogeneous concordance matrix Cgrum, that is, Cgrum=Chama T ×Hchma; subtract the frequency-amplitude feature matrix of any execution point from the frequency-amplitude feature matrix of other execution points to obtain all the spectrum difference feature matrices of the execution point, calculate the variance of all elements in the spectrum difference feature matrix, and record it as the spectrum deviation number; record the mean of all the spectrum deviation numbers of any execution point as the spectrum deviation coefficient, arrange the spectrum deviation coefficients of all execution points in ascending order, and record the ratio of the serial number value corresponding to any execution point to the total number of execution points as the spectrum risk coefficient Trais; The abnormal direction scalar Anosc of the current execution point is calculated based on the anomaly concordance matrix and the spectrum risk coefficient: Anosc=ln(Plety)× tr[Cgrum]×Trais MF ∑ k2=1 MNum (APyu k2 ) 2 ; Among them, k2 is the cumulative variable, APyu k2 is the k2th amplitude value of the spectrum amplitude sequence corresponding to the execution point, tr[] is the diagonal accumulation function, which returns the cumulative sum of each diagonal element in the calling matrix. The calling matrix in the formula is a heterogeneous matrix; ln() is a logarithmic function with the natural constant e as the base.

[0027] Furthermore, the method for fault judgment based on the abnormal pointing scalar is: for any functional program, an integer variable is preset as the variation fault tolerance interval errgp , whose value range is errgp∈[5,20] ; Get the minimum value of the abnormal pointing scalars of the most recent errgp execution points and record it as the adjacent abnormal pointing scalar; get the average value of the abnormal pointing scalars of all execution points between the first execution point and the current moment and record it as the pointing scalar benchmark; when the adjacent abnormal pointing scalar is greater than the pointing scalar benchmark, it is determined that there is a fault in the function program. When the function program is enabled next time, the fault judgment is made by displaying the error code of the function program on the display screen of the smart electric kettle.

[0028] Among them, the closest refers to the feature with the smallest time distance from the current moment.

[0029] An embodiment of the present invention provides an automatic fault detection system for an intelligent electric kettle, such as Figure 2 The figure shows a structure diagram of an automatic fault detection system for an intelligent electric kettle of the present invention. The automatic fault detection system for an intelligent electric kettle of this embodiment comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned automatic fault detection method embodiment of an intelligent electric kettle are implemented.

[0030] The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following units of the system: An execution point identification unit, used for identifying an execution point from the smart electric kettle; An execution current sequence acquisition unit is used to form an execution current sequence for each execution point; A feature group building unit, used for performing Fourier transform feature extraction from an execution current sequence to form an execution feature group; An abnormal direction scalar calculation unit, used for calculating the abnormal direction scalar by executing the feature group; The fault judgment unit is used to judge the fault according to the abnormal pointing scalar.

[0031] The intelligent electric kettle automatic fault detection system can be run in computing devices such as desktop computers, laptop computers, PDAs, and cloud servers. The intelligent electric kettle automatic fault detection system can run on systems including, but not limited to, processors and memories. Those skilled in the art can understand that the example is only an example of an intelligent electric kettle automatic fault detection system and does not constitute a limitation on an intelligent electric kettle automatic fault detection system. It can include more or fewer components than the example, or combine certain components, or different components. For example, the intelligent electric kettle automatic fault detection system can also include input and output devices, network access devices, buses, etc.

[0032] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the operation system of the automatic fault detection system for the smart electric kettle, and uses various interfaces and lines to connect the various parts of the entire operation system of the automatic fault detection system for the smart electric kettle.

[0033] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the automatic fault detection system of the intelligent electric kettle by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0034] Although the description of the present invention has been quite detailed and has been described in particular with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present invention. In addition, the present invention is described above with the embodiments foreseeable by the inventors, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that are not currently foreseen may still represent equivalent changes of the present invention.

Claims

1. A method for automatic fault detection of an intelligent electric kettle, characterized in that: The method comprises the following steps: identifying execution points from the smart electric kettle; forming an execution current sequence at each execution point; performing Fourier transform feature extraction from the execution current sequence to form an execution feature group; calculating an abnormal pointing scalar through the execution feature group; and making a fault judgment based on the abnormal pointing scalar; Among them, the execution feature group is constructed by the current sequence, including the main frequency and the spectrum amplitude vector. The method of calculating the abnormal direction scalar through the execution feature group is: calculate the balance difference divergence according to the spectrum amplitude vector, use the balance difference divergence to screen the execution point to obtain the second scattered element point, and calculate the abnormal direction scalar according to the main frequency and spectrum amplitude vector of the second scattered element point.

2. The method for automatic fault detection of an intelligent electric kettle according to claim 1, characterized in that: The method for identifying execution points from a smart electric kettle is: the smart electric kettle has several functional programs, and each execution of any functional program is recorded as an execution point of the functional program, and execution points in which work tasks are not fully executed and the duration is less than 120 seconds are excluded.

3. The method for automatic fault detection of an intelligent electric kettle according to claim 1, characterized in that: The method for forming an execution current sequence at each execution point is: for any execution point, the current signal of the control component is collected in real time by the current sensor of the smart electric kettle, and the current signal obtained in the time period from the start to the end of the execution point is constructed into a sequence in chronological order, which is recorded as the execution current sequence.

4. The method for automatic fault detection of an intelligent electric kettle according to claim 1, characterized in that: The method of extracting Fourier transform features from the execution current sequence to form an execution feature group is: using fast Fourier transform to convert the execution current sequence into a frequency domain signal to obtain spectrum data, and extracting the main frequency and spectrum amplitude vector from the spectrum data as the execution feature group.

5. The method for automatic fault detection of an intelligent electric kettle according to claim 1, characterized in that: The method of calculating the abnormal pointing scalar by executing the feature group is: record the average value of all components of the spectrum amplitude vector as ave, for any spectrum amplitude vector, record the maximum value of its components as Mhx, the minimum value as Mhn, and the average value as ave, and calculate the balanced difference divergence Vle: Vle = ave (Mhx-ave) / (ave-Mhn); if the balanced difference divergence of the execution point is greater than the component corresponding to the main frequency, it is recorded as the first scattered element point, otherwise it is a stable scattered execution point; the first stable scattered execution point of any first scattered element point in the reverse time direction is used as its reverse search execution point; Calculate the cosine similarity between the first scattered element point and its reverse search execution point. If the cosine similarity is greater than Then the first scattered element point is recorded as the second scattered element point, i is set as the serial number of the second scattered element point, and the total number of second scattered element points in the fault tolerance interval is recorded as Num; the spectrum amplitude vector of the i-th second scattered element point and its inverse search execution point is recorded as crt i and cht i , the main frequencies are denoted as crt i .mhz and cht i .mhz; remember crt i .ave and cht i The ratio of .ave is the inversion coefficient RA i , will cht i and crt i The cosine similarity of i ; Calculate the abnormal pointing scalar Nstg: ； where crt i .ax and crt i .av are the variance and mean of each component in the i-th second scattered element point.

6. The method for automatic fault detection of an intelligent electric kettle according to claim 1, characterized in that: The method of calculating the abnormal pointing scalar by executing the feature group can be replaced as follows: the mode of the main frequencies of all execution points is recorded as the benchmark main frequency, the spectrum amplitude sequence corresponding to any benchmark main frequency constitutes the frequency amplitude feature vector, and the standard deviation of all amplitude values ​​in the frequency amplitude feature vector is the frequency amplitude outlier rate; the weighted average of the frequency amplitude feature vectors of all benchmark main frequencies is recorded as the benchmark frequency amplitude feature vector, and the cumulative value of the square of all amplitude values ​​in the benchmark frequency amplitude feature vector is recorded as the benchmark spectrum energy. If the cumulative value of the square of all amplitude values ​​in the spectrum amplitude sequence corresponding to any execution point is greater than the benchmark spectrum energy, then the execution point is recorded as a singular spectrum point, and all execution points between the singular spectrum point and the first singular spectrum point in the reverse execution time direction are set to form an execution point set, which is recorded as a sub-spectrum retrieval set; in the sub-spectrum retrieval set, the number of all non-singular spectrum points is recorded as the frequency amplitude lag order, and the frequency amplitude correlation is calculated based on the frequency amplitude lag order and the spectrum amplitude sequence; In the sub-spectrum retrieval set, the inverse number of all amplitude values ​​in the spectrum amplitude sequence corresponding to any execution point is recorded as the spectrum entropy value, and the product of the spectrum entropy value and the frequency-amplitude correlation of any execution point is recorded as the spectrum complexity of the execution point; the execution point corresponding to the maximum main frequency in the sub-spectrum retrieval set is recorded as the high-frequency execution point, and the spectrum amplitude sequence corresponding to any non-high-frequency execution point constitutes a frequency-amplitude feature matrix. The frequency-amplitude feature matrix of the high-frequency execution point is recorded as, and the product of the transpose of the frequency-amplitude feature matrix of any execution point and the frequency-amplitude feature matrix of the high-frequency execution point is recorded as the heterogeneous matrix. The frequency-amplitude feature matrix of any execution point is subtracted from the frequency-amplitude feature matrices of other execution points to obtain all spectrum difference feature matrices of the execution point, and the variance of all elements in the spectrum difference feature matrix is ​​calculated and recorded as the spectrum deviation number; the mean of all spectrum deviation numbers of any execution point is recorded as the spectrum deviation coefficient, and the spectrum deviation coefficients of all execution points are arranged in ascending order. The ratio of the serial number value corresponding to any execution point to the total number of execution points is recorded as the spectrum risk coefficient. The abnormal pointing scalar of the current execution point is calculated according to the heterogeneous matrix and the spectrum risk coefficient.

7. The method for automatic fault detection of an intelligent electric kettle according to claim 1, characterized in that: The method for fault judgment based on the abnormal pointing scalar is: for any functional program, preset an integer variable as the variation fault tolerance interval errgp; obtain the minimum value of the abnormal pointing scalars of the most recent errgp execution points and record it as the adjacent abnormal pointing scalar; obtain the average value of the abnormal pointing scalars of all execution points between the first execution point and the current moment and record it as the pointing scalar benchmark; when the adjacent abnormal pointing scalar is greater than the pointing scalar benchmark, it is determined that the functional program has a fault; when the functional program is enabled next time, the fault judgment is performed by displaying the error code of the functional program on the display screen of the smart electric kettle.

8. An intelligent electric kettle automatic fault detection system, characterized in that: The intelligent electric kettle automatic fault detection system comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the intelligent electric kettle automatic fault detection method described in any one of claims 1 to 7 are implemented. The intelligent electric kettle automatic fault detection system runs on a desktop computer, a laptop computer, a PDA, and a computing device in a cloud data center.

Images