Filter element fault diagnosis and classification method, water purifier and filter element fault diagnosis and classification device

Abstract

The invention discloses a filter element fault diagnosis and classification method, a water purifier and a filter element fault diagnosis and classification device, and relates to the technical field of water purification equipment, the filter element fault diagnosis and classification method is applied to a multi-stage filter element system, and the multi-stage filter element system comprises multi-stage filter elements and a driving module, the driving module is used for providing power for liquid conveyed to the multi-stage filter element and comprises a motor; the filter element fault diagnosis and classification method comprises the following steps that a driving module is controlled to operate according to a set operation mode, and current characteristics of a motor in the set operation mode are obtained; and according to the current characteristics in the operation mode, determining the specific positions of the fault filter elements in the multi-stage filter elements. The technical problem of how to timely and reliably determine the position of a specific filter element with a fault in the multi-stage filter element on the premise of not additionally arranging a detection device is solved.

Description

Technical Field

[0001] The present application relates to the technical field of water purification equipment, and in particular to a filter element fault diagnosis and classification method, a water purifier, and a filter element fault diagnosis and classification device. Background Art

[0002] Water purifiers and other devices are equipped with multi-stage filter elements. Different filter elements have different filtering functions. During use, the aging and clogging degrees of different filter elements are also different. This leads to the inability to determine which level of filter element has failed when the filter element fails.

[0003] At present, relevant technologies for fault detection of multi-stage filter elements generally require the installation of sensors for each of the multi-stage filter elements to perform status detection. This solution requires the installation of additional sensors and other detection devices, which not only increases costs and equipment complexity, but also cannot timely and reliably determine the specific location of the filter element where the fault occurs in the multi-stage filter element because the status detection needs to be performed separately for the multi-stage filter elements. Summary of the Invention

[0004] The main purpose of this application is to provide a filter element fault diagnosis and classification method, a water purifier and a filter element fault diagnosis and classification device, aiming to solve the technical problem of how to timely and reliably determine the specific filter element location where a fault occurs in a multi-stage filter element without setting up an additional detection device.

[0005] In one aspect, a filter element fault diagnosis and classification method is provided, which is applied to a multi-stage filter element system. The multi-stage filter element system includes a multi-stage filter element and a drive module. The drive module is used to provide power for liquid delivered to the multi-stage filter element. The drive module includes a motor. The filter element fault diagnosis and classification method includes the following steps: Control the drive module to operate according to the set operating mode and obtain the current characteristics of the motor in the set operating mode; The specific location of the filter element where the fault occurs in the multi-stage filter element is determined based on the current characteristics under the operating mode.

[0006] In one embodiment, determining the specific location of a faulty filter element in a multi-stage filter element based on the current characteristics in the operating mode specifically includes the following steps: Combining the phase current data of the motor in the operating mode into a multi-mode feature vector; The multi-mode feature vector is classified to determine the specific filter element location where the fault occurs in the multi-stage filter element according to the classification result.

[0007] In one embodiment, the classification of the multi-mode feature vectors to determine the specific location of the faulty filter element in the multi-stage filter element according to the classification results specifically includes the following steps: Using a first classifier to classify the multi-mode feature vector to analyze and determine the candidate filter element locations that may have faults in the multi-stage filter element, and obtain a first classification result; Calculating and determining the confidence level of the candidate filter element position in the first classification result; When the confidence level is not less than a preset threshold, the candidate filter element position is determined as the specific filter element position where the fault occurs; When the confidence level is less than a preset threshold, the first classification result is analyzed by the second classifier to obtain a second classification result. The first classification result and the second classification result are combined to calculate the probability of failure in each candidate filter element position. The specific filter element position where the failure occurs in each candidate filter element position is determined based on the probability of failure in each candidate filter element position.

[0008] In one embodiment, the first classifier is a random forest classifier, and the second classifier is a neural network classifier.

[0009] In one embodiment, the control driving module operates according to a set operating mode and obtains the current characteristics of the motor in the set operating mode, specifically including the following steps: Obtain the current phase current data of the motor, control the drive module to run at the operating speed of the set operating mode based on the current phase current data of the motor, obtain the operating status of the filter element, and obtain the phase current data of the motor in each operating mode.

[0010] In one embodiment, the multi-stage filter element includes at least a first-stage filter element, a second-stage filter element, and a third-stage filter element connected in series. Obtaining the operating status of the filter element and obtaining the phase current data of the motor in each operating mode specifically include the following steps: When the control driving module is operated at the first operating speed, at least the operating state of the first-stage filter element is obtained, and phase current data of the motor in the first operating mode is obtained; When the control driving module is operated at the second operating speed, at least the operating state of the second-stage filter element and the phase current data of the motor in the second operating mode are obtained; When the control driving module is operated at the third operating speed, at least the operating state of the third-stage filter element and the phase current data of the motor in the third operating mode are obtained; When the control driving module is operated at the fourth operating speed, the operating state of each filter element is obtained, and the phase current data of the motor in the fourth operating mode is obtained; Among them, the first operating speed is less than the second operating speed and less than the third operating speed and less than the fourth operating speed, and the fourth operating speed is determined according to the current phase current data of the motor.

[0011] In one embodiment, the operating status of the filter element is obtained by: Obtain the corresponding relationship between the motor phase current data and the filter element operating status, as well as the current phase current data of the motor, and obtain the operating status of the filter element based on the current phase current data of the motor, the corresponding relationship between the motor phase current data and the filter element operating status; And / or, obtaining detection data of the sensor module, and determining the operating status of the filter element based on the detection data, wherein the sensor module includes at least one of a water quality sensor, a flow sensor, a temperature sensor, and a sound sensor, or a combination of multiple thereof.

[0012] In one embodiment, before executing the step of controlling the driving module to operate according to the set operating mode and obtaining the current characteristics of the motor in the set operating mode, the filter element fault diagnosis and classification method further includes the following steps: In response to the operation instruction, obtaining current phase current data of the motor, and processing the current phase current data of the motor; Obtain the mapping relationship between motor phase current data and filter element faults; When a multi-stage filter element failure is determined based on processed current phase current data of the motor and a mapping relationship between the motor phase current data and filter element failure, a difference test is initiated.

[0013] In one embodiment, the processing of the current phase current data of the motor specifically includes the following steps: Preprocessing the current phase current data of the motor; Calculate time domain features based on pre-processed current phase current data of the motor; Performing Fourier transform on the preprocessed current phase current data of the motor to obtain a frequency spectrum, and obtaining frequency domain features calculated based on the frequency spectrum; Performing wavelet transform on the preprocessed current phase current data of the motor to obtain a time-frequency distribution, and obtaining a time-frequency domain feature calculated based on the time-frequency distribution; Combining the time domain features, frequency domain features, and time-frequency domain features to form a pending feature vector, performing data processing on the pending feature vector, and obtaining a target feature vector; When it is determined that a multi-stage filter element has failed based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element failure, starting the difference test specifically includes the following steps: When a multi-stage filter element fails, a difference test is initiated according to a mapping relationship between the target feature vector, the motor phase current data, and the filter element failure.

[0014] In one embodiment, when a multi-stage filter element failure is determined based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element failure, a difference test is initiated, which specifically includes the following steps: Obtain samples of normal operating conditions and various types of filter element fault conditions, label the various fault types, determine the mapping relationship between motor phase current data and filter element faults, and build a third classifier containing a classification model; When the third classifier determines that the multi-stage filter element is faulty based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element fault, a differential test is initiated; Wherein, the third classifier adopts SVM classifier.

[0015] In one embodiment, the filter element fault diagnosis and classification method further includes the following steps: Establish communication between the multi-stage filter system and the cloud platform; In response to the algorithm optimization instruction, the mapping relationship between the motor phase current data of different user terminals and the filter element faults is obtained and summarized through the cloud platform, and the classification model is optimized and updated based on the obtained mapping relationship between the motor phase current data of different user terminals and the filter element faults.

[0016] In one embodiment, after performing the step of determining the specific location of the faulty filter element in the multi-stage filter element based on the current characteristics in the operating mode, the following steps are further included: Calculate the probability of filter element failure at the specific filter element location where the failure occurs and the remaining life of the filter element at the specific filter element location where the failure occurs, and generate a diagnostic report based on the calculation results; The control display interface displays the diagnostic report and maintenance information for the faulty filter element.

[0017] In one embodiment, the filter element fault diagnosis and classification method further includes the following steps: Responding to a system initialization instruction, obtaining a classification model and configuration information; After determining the specific location of the faulty filter element in the multi-stage filter element, the method further includes the following steps: Output a replacement reminder for the filter element at the specific location where the fault occurs; In response to a user filter cartridge replacement confirmation instruction, the configuration information is updated.

[0018] In another aspect, a water purifier is provided, comprising a multi-stage filter cartridge system, the multi-stage filter cartridge system comprising: A multi-stage filter element is used to filter liquid, and the multi-stage filter element includes at least a first-stage filter element, a second-stage filter element, and a third-stage filter element connected in series; A drive module includes a variable frequency pump, a motor, and a motor drive circuit. The variable frequency pump is connected to the first-stage filter element and is used to provide power for the liquid transmitted to the multi-stage filter element. The motor is connected to the variable frequency pump drive and is used to provide power for the variable frequency pump. The motor drive circuit is connected to the motor drive and is used to drive the motor to work. A current sampling circuit, used for collecting phase current data of the motor; The controller stores and executes the filter element fault diagnosis classification program, and when executing the program, implements the steps of the filter element fault diagnosis classification method described in the above embodiment.

[0019] In one embodiment, the multi-stage filter element system also includes a user interface, which is used to display a diagnostic report and filter element maintenance information. The diagnostic report includes at least the filter element failure probability of the specific filter element position where the fault occurs and the remaining life of the filter element at the specific filter element position where the fault occurs.

[0020] On the other hand, a filter element fault diagnosis and classification device is provided, which includes: a memory, a processor, and a filter element fault diagnosis and classification program stored on the memory and executable on the processor, wherein the filter element fault diagnosis and classification program is configured to implement the steps of the filter element fault diagnosis and classification method described in the above embodiment.

[0021] One or more technical solutions proposed in this application have at least the following technical effects: The control drive module operates in accordance with a set operating mode and obtains the current characteristics of the motor in the set operating mode; based on the current characteristics in the operating mode, the specific location of the faulty filter element in the multi-stage filter element is determined; no additional detection device is installed, but the specific location of the faulty filter element in the multi-stage filter element is determined based on the current characteristics of the motor in the set mode. This effectively solves the technical problem of being unable to promptly and reliably determine the specific location of the faulty filter element in the multi-stage filter element, and by reducing the use of additional detection devices, not only reduces costs, reduces equipment complexity and failure rate, but also improves system reliability. Because the current signal can be collected and processed in real time, the specific location of the faulty filter element in the multi-stage filter element can be directly determined by obtaining the current characteristics of the motor in the set operating mode, effectively reducing errors, improving the accuracy of fault diagnosis, and achieving accurate diagnosis of the specific location of the faulty filter element in the multi-stage filter element, and further solving the problem of replacing the filter element too early or too late. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 A flow chart illustrating an embodiment of a filter element fault diagnosis and classification method of the present application is provided; Figure 2 A partial flow chart of an embodiment of the filter element fault diagnosis and classification method of the present application is provided; Figure 3 One of the partial flow diagrams provided for one embodiment of the filter element fault diagnosis and classification method of the present application; Figure 4 A flowchart of an embodiment of step S200 of the present application is provided; Figure 5 A flowchart of an embodiment of step S110 of the present application is provided; Figure 6 A second partial flow chart of an embodiment of the filter element fault diagnosis and classification method provided in the present application; Figure 7 A partial flow chart of another embodiment of the filter element fault diagnosis and classification method of the present application is provided; Figure 8 A flowchart of an embodiment of step S310 of the present application is provided; Figure 9 A third partial flow chart of an embodiment of the filter element fault diagnosis and classification method provided in the present application; Figure 10 A flowchart of an embodiment of step S330 of the present application is provided; Figure 11 This is the current waveform diagram under normal working conditions; Figure 12 This is the current waveform of the PP cotton filter element when it is blocked; Figure 13 This is the current waveform diagram of the activated carbon filter element being blocked; Figure 14 This is the current waveform diagram of the RO reverse osmosis membrane blockage failure; Figure 15 A flowchart of an embodiment of step S220 of the present application is provided; Figure 16 A fourth partial flow chart of an embodiment of the filter element fault diagnosis and classification method provided in the present application; Figure 17A fifth partial flow chart of an embodiment of the filter element fault diagnosis and classification method provided in the present application; Figure 18 A partial flow chart of another embodiment of the filter element fault diagnosis and classification method of the present application is provided; Figure 19 A partial flow chart of another embodiment of the filter element fault diagnosis and classification method provided in the present application; Figure 20 A sixth partial flow chart of an embodiment of the filter element fault diagnosis and classification method provided in the present application; Figure 21 A partial flow chart of another embodiment of the filter element fault diagnosis and classification method provided in the present application; Figure 22 A schematic diagram of a module provided for an embodiment of a water purifier according to an embodiment of the present application; Figure 23 A schematic diagram of an embodiment of a multi-stage filter element according to an embodiment of the present application; Figure 24 FIG. 1 is a schematic diagram of an embodiment of a current sampling module according to an embodiment of the present application.

[0024] Description of Figure Numbers: 100, multi-stage filter element; 110, PP cotton filter element; 120, activated carbon filter element; 130, RO reverse osmosis membrane; 140, mineralized filter element; 210, variable frequency pump; 220, motor; 230, motor drive circuit; 240, analog-to-digital conversion module; 300, current sampling circuit; 410, signal processing module; 420, feature extraction module; 430, fault classification module; 440, control module; 500. User interface.

[0025] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0027] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0028] Water purifiers and other devices are equipped with multi-stage filter cartridges. Different filter cartridges have different filtration functions. Multi-stage filter cartridges can achieve multi-stage progressive purification, with higher filtration efficiency and wider application range than single filter cartridges. During use, multi-stage filter cartridges age and clog to varying degrees, making it difficult to determine which stage of the filter is faulty when a filter cartridge fails.

[0029] Currently, related technologies use a unified replacement reminder strategy for fault detection of multi-stage filter elements, replacing all filter elements at the same time regardless of their status. Alternatively, sensors need to be installed separately for each of the multi-stage filter elements to detect their status. The installation of additional sensors and other detection devices not only increases product cost and complexity, but also increases the number of failure points due to improper installation. It is also impossible to reliably and timely determine the specific location of the faulty filter element in the multi-stage filter element, affecting user experience and maintenance efficiency. When a filter element failure occurs, it is impossible to determine the specific location of the faulty filter element in the multi-stage filter element, which can lead to some filter elements being replaced too early or too late.

[0030] Some embodiments of the present application propose a filter element fault diagnosis and classification method, a water purifier, and a filter element fault diagnosis and classification device, which are used to promptly and reliably determine the specific filter element location where a fault occurs in a multi-stage filter element without additional detection devices such as sensors.

[0031] In this application, the filter cartridge fault diagnosis and classification method is primarily applied to water purifiers, water purification systems, and other equipment and systems with water purification functions, with the controller as the primary execution entity. The controller can be located in the water purifier, a control device connected to the water purifier, or independently located within the various components of the water purifier. It can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) or programs loaded from a storage device into random access memory (RAM). RAM also stores various programs and data required for water purification. The controller and storage modules such as ROM and RAM are connected to each other via a bus; storage modules can also include storage devices such as magnetic tape and hard drives. Input / output (I / O) interfaces are also connected to the bus. Typically, the following systems can be connected to the I / O interface: input devices such as touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, and gyroscopes; output devices such as liquid crystal displays (LCDs), speakers, and vibrators; and communication devices. The communication device can allow the water purifier to communicate with other devices wirelessly or by wire to exchange data.

[0032] For ease of presentation, this application primarily describes controllers and other control devices with control functions as the primary execution entities. The filter element fault diagnosis classification method is applied to a multi-stage filter element system. The multi-stage filter element system includes a multi-stage filter element and a drive module, which absorbs or filters impurities from the liquid through the multi-stage filter element. The drive module is used to provide power for the liquid delivered to the multi-stage filter element and includes a motor.

[0033] like Figure 1 As shown, the filter element fault diagnosis classification method includes the following steps: Step S100: Control the driving module to operate according to the set operating mode, and obtain the current characteristics of the motor in the set operating mode.

[0034] The current characteristics of the motor are key parameters reflecting its operating status and can be used to determine the motor load, speed, torque, etc. The drive module of the multi-stage filter element system is used to provide power for the liquid transported to the multi-stage filter element. When the motor is working, the current characteristics of the motor can indirectly reflect the blockage, damage and other conditions of the filter element, and then be used to further determine the specific filter element location where the fault occurs in the multi-stage filter element.

[0035] For example, current signals can be collected using current detection components such as Hall effect sensors, current sensors, or shunt resistors. For a three-phase motor, for example, the current detection component covers the motor's three-phase circuit to enable current collection. Based on the acquired motor phase current data and other current signals, time domain analysis is performed by calculating the current mean and peak values. The current signal is converted into a spectrum using a fast Fourier transform (FFT). Harmonic components are analyzed to identify abnormal frequency characteristics, thereby obtaining the current characteristics of the motor under the set operating mode.

[0036] Different filter elements exhibit varying current characteristics when the driver module operates in different operating modes. By controlling the driver module's motor to operate in various preset modes, the system's operating conditions can be altered, thereby stimulating the characteristics of different filter elements under different operating conditions. These different operating modes can more clearly demonstrate the characteristics of faulty filter elements, facilitating subsequent feature extraction and analysis.

[0037] The current characteristics can reflect the working state of the filter element under specific operating conditions, such as the magnitude and fluctuation of the current. For example, the set operating mode can be one or more. When there are multiple operating modes, it is necessary to obtain the current characteristics of the motor under multiple set operating modes. The current characteristics of the motor vary under different operating modes (such as different motor operating speeds, different water consumption, etc.), and the current characteristics of the filter elements in the same filter element position under the same operating mode may be similar, but the filter elements in different filter element positions will show significant differences under different operating modes. Setting and obtaining the current characteristics of the motor under multiple set operating modes can eliminate interference factors in a single operating mode, and can be used to distinguish filter element faults at different filter element positions, thereby improving fault location accuracy. Under different operating modes, the current characteristics of a faulty filter element will be different from those of a normal filter element. In each operating mode, the phase current data of the filter element is detected and recorded in real time. By recording and obtaining these characteristics, a basis can be provided for subsequent fault diagnosis.

[0038] Step S200: Determine the specific location of the faulty filter element in the multi-stage filter element based on the current characteristics in the operating mode.

[0039] Filter element failures include, but are not limited to, blockage, damage (such as aging or damage from external impact), misaligned installation, and filter failure. For example, when a motor becomes clogged, this can cause changes in water flow resistance, which in turn affects the motor load. The motor's phase current data can reflect this load change, which is closely related to the degree of filter element blockage. When the filter element is not clogged, water flow resistance is low, requiring less power to drive the liquid through the filter element, and the motor drive current is also low. As the filter element becomes increasingly clogged, water flow resistance increases. To maintain a constant flow rate or pressure, the motor needs to output greater torque, resulting in a significant increase in current. The rate of change of current reflects the rate of filter element blockage. For example, a rapid increase in current indicates increasing filter element blockage, while a slow change indicates a slow rate of blockage. The current rate of change can be used to determine the current level of filter element blockage. Taking sudden blockage, breakage and other faults as an example, possible abnormal conditions can be identified based on the acquired current change rate; for example: when the phase current of the motor rises sharply in a short period of time and exceeds the preset current threshold, it can be determined that the filter element may be suddenly blocked; because when the filter element is damaged, the fluid resistance drops sharply, causing the motor load to fluctuate, the motor current may oscillate irregularly, and at the same time, the energy of the low-frequency component in the frequency domain may increase abnormally. Therefore, when the motor current fluctuates irregularly and the frequency characteristics are abnormal, it can be determined that the filter element may be damaged.

[0040] In a multi-stage filter system, because each filter element has different effects on water flow resistance when a blockage or other failure occurs, the impact on current varies depending on the specific location of the filter element within the multi-stage filter element. Multi-stage filter elements can include pre-filter elements (such as PP cotton) and post-filter elements (such as RO membranes). For example, the pre-filter element, located at the front end and having a greater impact on overall flow, will show a significant upward trend in current data, including motor phase current. For example, post-filter elements, with their relatively small pore size and relatively high resistance, will experience a sharp increase in motor current within a short period of time when a failure occurs.

[0041] As an example, the current characteristics (such as time domain and frequency domain parameters) of each filter element under normal conditions in different operating modes (such as different motor operating speeds, different water consumption, etc.) can be obtained to determine the current range of each filter element under normal conditions; the current characteristics of each filter element under different operating modes can also be obtained when a fault occurs. The current characteristics are further obtained by obtaining current signals such as the phase current of the motor in real time. When an abnormal current condition is determined based on the obtained current signal, such as the current exceeding the current range under normal conditions or the current characteristics being different from the current characteristics under normal conditions, a fault is determined. The obtained current characteristics can be compared with the current characteristics of each filter element when a fault occurs to determine the specific location of the filter element where the fault occurs. Alternatively, the correspondence between the filter element fault and the current characteristics can be determined. Based on the correspondence between the fault and the current characteristics (such as the mapping relationship between the motor phase current data and the filter element fault), the specific location of the fault filter element can be determined from the obtained current characteristics.

[0042] As another example, the current characteristics of each level of filter element when a fault occurs under different operating modes can be obtained to determine the correspondence between the fault and the current characteristics (such as the mapping relationship between motor phase current data and filter element fault). Based on the correspondence between the fault and the current characteristics, the specific filter element location where the fault occurs can be determined by the obtained current characteristics.

[0043] As another example, the degree of influence of filter element failure at different filter element positions in a multi-stage filter element on the current characteristics can be established. After obtaining the current characteristics of filter element failures at each stage under different operating modes, the specific filter element position where the failure occurs can be determined based on the degree of influence of filter element failure at different filter element positions in the multi-stage filter element on the current characteristics.

[0044] Compared to the solution of separately installing multiple pressure sensors, flowmeters, and other detection devices for each multi-stage filter element, which has high costs and complexity, increases the number of fault points due to improper installation, and cannot accurately determine the specific filter element location of the multi-stage filter element where the fault occurs, the embodiments of the present application do not install additional detection devices such as pressure sensors or flowmeters. Instead, they utilize the water purifier's own driver module and current sampling circuit to determine the current characteristics of the motor in the set mode by real-time acquisition of the motor current. The specific filter element location of the fault in the multi-stage filter element is further determined based on the current characteristics in the operating mode. This effectively solves the technical problem of being unable to timely and reliably determine the specific filter element location of the fault in the multi-stage filter element, and by reducing the need for additional detection devices, it not only reduces costs, equipment complexity and failure rate, but also improves system reliability. Because the current signal has the characteristics of real-time acquisition and processing, the specific filter element location of the fault in the multi-stage filter element can be directly determined by acquiring the current characteristics of the motor in the set operating mode, effectively reducing errors and improving the accuracy of fault diagnosis. In some scenarios, the fault diagnosis accuracy can even reach over 90%. In this way, the specific location of the filter element where the fault occurs can be accurately diagnosed, and the problem of replacing the filter element too early or too late can be further solved.

[0045] like Figure 2 、 Figure 3 As shown, in one embodiment, step S100, controlling the driving module to operate according to a set operating mode and obtaining the current characteristics of the motor in the set operating mode, specifically includes the following steps: Step S110, obtain the current phase current data of the motor, control the drive module to run at the operating speed of the set operating mode according to the current phase current data of the motor, obtain the operating status of the filter element, and obtain the phase current data of the motor in each operating mode.

[0046] A motor's current signature is directly related to its operating speed. For example, when a filter clog increases water flow resistance, the motor's speed may decrease due to the increased load. Without speed control, current fluctuations reflect both speed fluctuations and load variations, making it difficult to accurately attribute a filter failure. By monitoring and acquiring motor phase current data in real time and controlling the driver module to operate according to a set operating mode, current signature deviations caused by speed fluctuations can be avoided. Furthermore, the motor's current signature is related to its own operating speed. By controlling the driver module to operate according to a set operating mode based on the current motor phase current data, current signature deviations caused by speed fluctuations can be mitigated to a certain extent, reducing errors in determining the specific location of the faulty filter. For example, when a filter clog increases water flow resistance, the motor's speed may decrease due to the increased load. Current fluctuations at this time reflect both speed fluctuations and load variations. Without speed control, current fluctuations reflect both speed fluctuations and load variations (such as filter clogs and water quality), making it difficult to distinguish between progressive filter blockage caused by a filter failure and temporary resistance fluctuations due to water quality issues.

[0047] The filter element's operating status includes current flow, pressure, blockage status, usage duration, and accumulated water usage. For example, when a filter element becomes clogged due to the filter element itself, there's a temporal correspondence between changes in the filter element's resistance and changes in the motor's current characteristics. By determining whether a filter element failure has occurred, the relationship between the failure and the current characteristics (such as the mapping between motor phase current data and filter element failure) can be determined. This can be used to eliminate non-structural failure factors, such as increased resistance due to normal filter element aging and transient blockage caused by temporary large particles in the water.

[0048] Exemplarily, the motor is a three-phase motor with controllable operating speed, operating at different speeds in different operating modes. Based on the motor's current phase current data, the driver module is controlled to operate according to the set operating mode, and the operating status of the filter element and the motor's phase current data in each operating mode are obtained. This can further determine the specific location of a faulty filter element in a multi-stage filter element, thereby reducing errors, improving the accuracy of fault diagnosis, and achieving precise diagnosis of the specific location of the faulty filter element.

[0049] In some other implementations, the specific filter element location where the fault occurs can be comprehensively judged in combination with the operating status of the filter element, and further determination can be made whether to output fault reminders, filter element replacement alarm reminders and other prompt information; the specific settings can be based on actual conditions and are not limited.

[0050] like Figure 4As shown, in one embodiment, step S200, based on the current characteristics in the operating mode, determines the specific location of the filter element where the fault occurs in the multi-stage filter element, specifically comprising the following steps: Step S210: combining the phase current data of the motor in the operating mode into a multi-mode feature vector.

[0051] The multi-mode feature vector is used to form a high-dimensional vector by dimensional splicing the current characteristics of the motor in different operating modes (such as time domain parameters, frequency domain parameters, time-frequency domain characteristics, etc.).

[0052] Step S220: classify the multi-mode feature vector to determine the specific location of the faulty filter element in the multi-stage filter element according to the classification result.

[0053] Exemplarily, the set operating mode may be one or more. When there are multiple operating modes, it is necessary to obtain current characteristics of the motor in the multiple set operating modes.

[0054] For example, the post-filter has a smaller pore size than the pre-filter. In low-speed mode, the motor drives the water at a relatively low speed. Initially, when the pre-filter becomes clogged, water resistance slowly increases. To maintain a constant flow rate, the motor torque increases slightly, resulting in a gradual, small current increase. This characteristic shows a steady increase in the time domain, with no significant abnormalities in the frequency domain harmonic components. In high-speed mode, the motor drives a large flow rate. A clogged pre-filter causes a sudden increase in resistance. To maintain speed, the motor frequently adjusts its output torque, causing sharp current fluctuations. This characteristic shows irregular pulses in the time domain, and a surge in high-order harmonic components may occur in the frequency domain. The change in resistance of the post-filter is more pronounced at high speeds. Therefore, a slight current increase at low speed could indicate a clogged pre-filter, a clogged post-filter, or water quality. Further analysis, combined with motor phase current data from high-speed operation, is necessary. If a sharp current fluctuation is observed, water quality can be ruled out and the pre-filter is considered clogged. If a concentrated current increase with abnormal high-frequency spectrum waves is observed, the post-filter is considered faulty.

[0055] By obtaining the current characteristics of the motor under multiple set operating modes and combining them into multi-mode feature vectors, and by classifying the multi-mode feature vectors, it is possible to eliminate interference factors in a single operating mode, distinguish filter element faults in different filter element positions, and improve fault location accuracy.

[0056] In one embodiment, the multi-stage filter element includes at least a first-stage filter element, a second-stage filter element, and a third-stage filter element connected in series.

[0057] The multi-stage filter element may include a pre-filter element for achieving primary filtration, a middle filter element for deep water purification, and a post-filter element for absorbing residual odors. The number of pre-filter elements, middle filter elements, and post-filter elements may be one or more. When the multi-stage filter element includes a first-stage filter element, a second-stage filter element, and a third-stage filter element, in series order, the first-stage filter element may be a pre-filter element, the second-stage filter element may be a middle filter element, and the third-stage filter element may be a post-filter element; when the multi-stage filter element includes a fourth-stage filter element or at least one other filter element in addition to the first-stage filter element, the second-stage filter element, and the third-stage filter element, in series order, the first-stage filter element may be a pre-filter element, the second-stage filter element, the third-stage filter element, etc. may be a middle filter element, and the last-stage filter element may be a post-filter element; the specific configuration may be based on actual conditions and is not limited here.

[0058] like Figure 5 、 Figure 6 As shown, the step S110 of obtaining the operating status of the filter element and obtaining the phase current data of the motor in each operating mode specifically includes the following steps: Step S111: when controlling the driving module to operate at a first operating speed, obtaining at least an operating state of the first-stage filter element and phase current data of the motor in the first operating mode; Step S112: when the driving module is controlled to operate at the second operating speed, at least the operating state of the second-stage filter element and the phase current data of the motor in the second operating mode are obtained; Step S113: when the driving module is controlled to operate at the third operating speed, at least the operating state of the third-stage filter element and the phase current data of the motor in the third operating mode are obtained; Step S114: when the control driving module is operated at the fourth operating speed, obtaining the operating status of each filter element and obtaining the phase current data of the motor in the fourth operating mode; Among them, the first operating speed is less than the second operating speed and less than the third operating speed and less than the fourth operating speed, and the fourth operating speed is determined according to the current phase current data of the motor.

[0059] For example, the motor can be operated in corresponding operating modes by controlling the drive module to operate at different operating speeds. When the motor operates in different operating modes, the current characteristics of different faults such as blockage faults in different filter elements at different levels in different operating modes are different. First operating speed < second operating speed < third operating speed < fourth operating speed: When the control drive module operates at the first operating speed, the operating status of the first filter element can be obtained, and the operating status of at least one filter element at other levels other than the first filter element can also be obtained; when the control drive module operates at the second operating speed, the operating status of the second filter element can be obtained, and the operating status of at least one filter element at other levels other than the second filter element can also be obtained; when the control drive module operates at the third operating speed, the operating status of the third filter element can also be obtained, and the operating status of at least one filter element at other levels other than the third filter element can also be obtained; because the fourth operating speed is determined based on the current phase current data of the motor and can be dynamically and flexibly adjusted, when the control drive module operates at the fourth operating speed, the operating status of the first filter element can be obtained, and the operating status of the filter elements at all levels can also be obtained. By controlling the drive module to run at different operating speeds, the motor works in the corresponding operating mode, and by collecting the phase current data of the motor working in different operating modes, differentiated testing is achieved, which is used to accurately locate the faulty filter element based on the obtained filter element operating status and phase current data.

[0060] The aforementioned steps S111 to S113 may be performed in sequence from low to high operating speed, or may be performed in sequence from high to low operating speed, or one or more of them may be executed according to actual selection.

[0061] Taking the example of obtaining the operating status of at least the first-stage filter element and the phase current data of the motor in the first operating mode when the control drive module is operating at the first operating speed, since the pre-filter element is responsible for intercepting large particles of impurities and is prone to clogging due to impurity accumulation, when the control drive module is operating at a lower operating speed such as the first operating speed, the water flow rate is slow, and when the pre-filter element is blocked, it will directly lead to a decrease in the water inlet flow rate. Therefore, when the control drive module is operating at the first operating speed, the operating status of the first-stage filter element can be obtained, and the operating status of at least one other level of filter element besides the first-stage filter element can also be obtained. When the motor is running at a low speed, if the pre-filter element fails, the motor current will change significantly. The blockage status of the pre-filter element can be identified through the current fluctuation, avoiding excessive loads on the middle filter element and the rear filter element due to pre-filter blockage.

[0062] Taking the example of obtaining the operating status of at least the third-stage filter element and the phase current data of the motor in the third operating mode when the control drive module is operating at the third operating speed, since the filter elements in the later stages are mainly used for deep filtration, they may become clogged due to the accumulation of fine impurities. Therefore, when the control drive module is operating at a higher operating speed such as the third operating speed, the water flow rate is faster. If the middle filter element or the rear filter element in the later stages becomes clogged, the water flow rate will become unstable. Therefore, when the control drive module is operating at the third operating speed, the operating status of the third-stage filter element can be obtained, and the operating status of at least one other filter element in the later stages can also be obtained. When the motor is operating at a higher operating speed, if the filter element in the later stages fails, the current will fluctuate or increase abnormally. Therefore, when the current characteristics such as high-frequency fluctuations are identified, the clogged state of the filter element in the later stages can be reflected.

[0063] Taking the example of obtaining the operating status of each stage of filter element and the phase current data of the motor in the fourth operating mode when the control drive module operates at the fourth operating speed, because the fourth operating speed is determined based on the current phase current data of the motor and is mainly used to change the water flow rate, it is necessary to detect the status of the filter elements at each level to further achieve the precise positioning of the specific filter element where the fault occurs.

[0064] In addition, the aforementioned fourth operating speed is determined based on the current phase current data of the motor. In addition to being able to be set to be greater than the third operating speed, it can also be achieved by controlling the operation of the drive module in a manner of switching the operating speed from low speed to high speed, and flexibly adjusting the operating status of the filter elements at different filter element positions obtained when switching the operating speed of the drive module; or, controlling the operation of the drive module by switching the operating set time according to different operating speeds, and flexibly adjusting the operating status of the filter elements at different filter element positions obtained when switching the operating speed of the drive module.

[0065] The operating status of the filter element is obtained in the following ways: In one embodiment, the correspondence between the motor phase current data and the filter element operating status is obtained, and the current phase current data of the motor is obtained, and the operating status of the filter element is obtained based on the current phase current data of the motor, the correspondence between the motor phase current data and the filter element operating status.

[0066] The operating status of the filter element includes normal operating status, blockage fault, damage fault, etc. When a blockage fault occurs during motor operation, the blockage fault will cause changes in water flow resistance, which in turn affects the motor load, and the motor phase current data can reflect this load change of the motor. Based on the correspondence between the motor phase current data and the operating status of the filter element, the operating status of the filter element can be directly determined by obtaining the current phase current data of the motor. Because the current signal has the characteristics of real-time collection and processing, by obtaining the current characteristics of the motor under the set operating mode, the current operating status of the filter element can be determined in a timely and reliable manner. By reducing the use of additional detection devices, it not only reduces costs, reduces equipment complexity and failure rate, but also improves system reliability.

[0067] In another embodiment, detection data of a sensor module is acquired, and the operating status of the filter element is determined based on the detection data, wherein the sensor module includes at least one of a water quality sensor, a flow sensor, a temperature sensor, and a sound sensor, or a combination of multiple thereof.

[0068] The water quality sensor can be combined with indicators such as the changes in the TDS values ​​of the inlet and outlet water to assist in determining the operating status of filter elements such as RO membranes; the flow sensor can be combined with flow changes to assist in determining the blockage of the filter element; the water temperature factor will affect the performance of the motor, and detecting the temperature through the temperature sensor can improve the accuracy of determining the correspondence between the motor phase current data and the operating status of the filter element; the sound sensor can be used to analyze the operating sound characteristics of the pump body such as the variable frequency pump of the drive module to assist in identifying the type of fault.

[0069] In some other embodiments, the operating status of the filter element can be obtained based on the current phase current data of the motor, the correspondence between the motor phase current data and the operating status of the filter element, and the operating status of the filter element can be further determined in combination with the detection data of the sensor module, so as to further improve the accuracy of determining the status of the filter element.

[0070] In some other embodiments, in addition to identifying faulty filter elements, the fault type and severity can be further subdivided based on the test results. For example, the fault type can be classified into different fault types such as physical blockage of the filter element, microbial contamination, and material aging; the filter element status can be divided into four levels: normal, mild abnormality, moderate fault, and severe fault based on the severity of the blockage fault; combined fault diagnosis can be performed on the filter elements to identify complex fault conditions where multiple filter elements have problems at the same time; non-filter element fault identification can also be performed to distinguish filter element faults from other system problems such as pump failures and pipe blockages. The specific configuration can be based on actual settings and is not limited here.

[0071] like Figure 7As shown, in one embodiment, before executing step S100, controlling the drive module to operate according to the set operating mode, and obtaining the current characteristics of the motor in the set operating mode, the filter element fault diagnosis and classification method further includes the following steps: Step S310 : In response to the operation instruction, obtain the current phase current data of the motor and process the current phase current data of the motor.

[0072] A run command is a command that triggers a driver module to begin operation. It's used to automatically trigger the operation of devices with multi-stage filter systems, such as water purifiers, thereby driving water and other liquids through the filter elements. This run command can be a hardware signal automatically triggered by the circuit after detecting the multi-stage filter element has started operating; it can also be a software command triggered by a software timer; it can also be triggered by a local device such as a touch screen or button during human-computer interaction, or it can be manually selected and triggered by a remote device such as a user interface or terminal device app. This system detects and acquires the current motor phase current data in real time and processes it.

[0073] Step S320: Acquire a mapping relationship between motor phase current data and filter element faults.

[0074] For example, the mapping relationship between the motor phase current data and the filter element failure can be determined based on the motor phase current data when the filter elements at different levels fail, as determined by experiments or from a historical database.

[0075] Step S330: When it is determined that a multi-stage filter element fails based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element failure, a difference test is started.

[0076] Differentiation testing involves controlling the speed of the driver module to ensure the motor operates according to a set operating mode after a fault is identified in a multi-stage filter element. This allows for targeted testing of the filter elements at different levels to accurately locate the faulty filter element. If a fault is initially determined (e.g., an abnormal current waveform) based on real-time current data from the motor phase, differentiation testing is automatically initiated.

[0077] By dynamically detecting and acquiring motor phase current data, the system determines whether a multi-stage filter element is currently faulty based on this data. This data is then used to initiate differential testing only when a fault is confirmed. This differential testing then further identifies the specific location of the faulty filter element within the multi-stage filter element based on the current characteristics under operating mode. This effectively eliminates non-filter element faults, improves the accuracy of fault diagnosis, and enhances the reliability of the diagnostic results for the specific location of the faulty filter element within the multi-stage filter element.

[0078] like Figure 8As shown, in one embodiment, the processing of the current phase current data of the motor in step S310 specifically includes the following steps: Step S311: pre-process the current phase current data of the motor.

[0079] The preprocessing is used to preprocess the current phase current data of the motor and remove noise through a filtering algorithm to obtain the preprocessed current phase current data of the motor.

[0080] Step S312: Calculate the time domain characteristics based on the preprocessed current phase current data of the motor.

[0081] Time-domain features can be extracted from the time series of the motor's current phase current data to reflect its temporal variation. These features include peak current (lpeak), mean current (lmean), mean current (Irms), current waveform factor (CF), and current rise rate (Irise). Peak current represents the maximum value of the current waveform; mean current represents the average value of the current waveform; mean current represents the root mean square (RMS) value of the current waveform; waveform factor represents the ratio of peak current to RMS value; and rise rate represents the rate at which the current increases from zero to peak current.

[0082] Step S313: Perform Fourier transform on the pre-processed current phase current data of the motor to obtain a spectrum, and obtain frequency domain features calculated based on the spectrum.

[0083] Frequency domain features can be used to convert current signals from the time domain to the frequency domain through Fourier transform, analyzing the energy distribution of different frequency components. Frequency domain features include fundamental amplitude (A1), harmonic component amplitudes (A2, ...An), total harmonic distortion (THD), harmonic characteristic ratio (HCR), and spectral center of gravity (FC). Fundamental amplitude is used to measure the amplitude of components other than the fundamental current; harmonic component amplitude represents the amplitude of each harmonic component; total harmonic distortion represents the ratio of a harmonic component to the fundamental component; harmonic characteristic ratio represents the ratio of a specific harmonic to the fundamental; and spectral center of gravity represents the weighted center frequency of the spectral energy distribution.

[0084] Step S312 and step S313 may be executed sequentially or simultaneously, which is not limited here.

[0085] Step S314: performing wavelet transform on the pre-processed current phase current data of the motor to obtain a time-frequency distribution, and obtaining a time-frequency domain feature calculated based on the time-frequency distribution.

[0086] Time-frequency domain features can be used to analyze the distribution characteristics of signals in the two-dimensional time-frequency plane. These features include wavelet energy distribution (WE), wavelet entropy (WEnt), and empirical mode decomposition (EMD). Wavelet energy distribution represents the energy distribution of the current waveform in different frequency bands; wavelet entropy represents an indicator of the complexity of the current waveform; and empirical mode decomposition represents the intrinsic mode function characteristics of the current signal.

[0087] Step S315: Combine the time domain features, frequency domain features, and time-frequency domain features to form a pending feature vector, perform data processing on the pending feature vector, and obtain a target feature vector.

[0088] Exemplarily, the eigenvectors to be determined are normalized, for example, by converting the eigenvalues ​​to a standard normal distribution with a mean of 0 and a standard deviation of 1, or by scaling the eigenvectors to a uniform interval using min-max normalization. Normalization of the eigenvectors to be determined is used to scale different features (such as current mean, harmonic amplitude, time-frequency entropy, etc.) with different ranges to a uniform interval (such as [0, 1] or [-1, 1]), giving different types of features (such as time domain, frequency domain, and time-frequency domain features) the same weight, thereby preventing features with excessively large values ​​from directly affecting the analysis results.

[0089] After normalizing the eigenvectors, we can use principal component analysis (PCA) to reduce the dimensionality and obtain the target eigenvectors. This can reduce data storage space and computational complexity, improving the efficiency of subsequent analysis and processing.

[0090] The aforementioned step S330, when determining that a multi-stage filter element has failed based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element failure, initiates the difference test, specifically including the following steps: When a multi-stage filter element fails, a difference test is initiated based on the mapping relationship between the target feature vector, the motor phase current data, and the filter element failure.

[0091] In this way, the accuracy of filter element fault detection can be significantly improved, and the detection accuracy of whether a multi-stage filter element has a fault can be improved, so that differentiated testing will only be started when a multi-stage filter element has a fault, reducing the consumption of meaningless detection resources and improving the accuracy of fault diagnosis results.

[0092] like Figure 9 、 Figure 10 As shown, in one embodiment, step S330, when it is determined that a multi-stage filter element has failed based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element failure, a difference test is started, which specifically includes the following steps: Step S331: obtain normal operating condition samples and various filter element fault operating condition samples, mark various fault types, determine the mapping relationship between motor phase current data and filter element faults, and construct a third classifier including a classification model.

[0093] Normal operating condition samples can be obtained by controlling the multi-stage filter system to operate in different operating modes, or by controlling the multi-stage filter system to operate under normal operating conditions such as rated voltage, flow rate, and water temperature, and obtaining phase current data of the motor during stable operation. Samples of various filter element failure conditions can be obtained through experiments such as simulating filter element blockage and filter element damage; they can also be obtained through phase current data recorded during long-term operation of equipment such as water purifiers when failures occur, or from historical databases that store historical usage records.

[0094] For example, Figure 11 As shown in the figure, under normal working conditions, the fundamental current wave is obvious, the harmonic components are small, and the waveform is stable. The pre-filter element includes PP cotton filter element, pre-activated carbon filter element, metal filter, etc. Figure 12 As shown, taking PP cotton filter element as an example, the dotted line is the current waveform under normal working conditions; the solid line is the current waveform when a blockage fault occurs; when a blockage fault occurs, its current characteristics are as follows: the current waveform shows an increase in high-frequency fluctuations, and the fundamental amplitude increases slightly; the middle filter element includes activated carbon filter element, RO reverse osmosis membrane, nanofiltration membrane, etc. Figure 13 As shown in the figure, taking the activated carbon filter as an example, the dotted line is the current waveform under normal working conditions; the solid line is the current waveform when a blockage fault occurs; when a blockage occurs, the current characteristics appear as follows: the third harmonic in the current harmonic component increases significantly, and the waveform distortion increases; Figure 14 As shown in the figure, taking an RO reverse osmosis membrane as an example, the dashed line represents the current waveform under normal operating conditions; the solid line represents the current waveform during a blockage fault. During a blockage fault, the current characteristics are characterized by a significant increase in the mean current value, a decrease in the wave form factor, and an increase in low-frequency components. Post-filter elements include post-activated carbon filters, mineralized filters, and weak alkaline filters. For example, when a mineralized filter element is blocked, the current characteristics are characterized by a significant phase shift in the current waveform and a change in the proportion of harmonic characteristics.

[0095] Step S332: When the third classifier determines that a multi-stage filter element fails based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element failure, a differentiation test is started; wherein the third classifier adopts an SVM classifier.

[0096] Normal operating condition samples and various filter element failure condition samples are obtained to construct a training set, and the SVM classifier M1 is trained. The SVM classifier M1 learns the difference between the normal and faulty filter element feature vectors, so that the new feature vectors obtained based on the current phase current data of the motor can be classified to determine whether there is a filter element failure and quickly screen out possible faults. When the SVM classifier determines that the filter element at the specific filter element position corresponding to the feature vector is faulty, it means that the characteristics of the filter element are significantly different from those of a normal filter element, but at this time it is not yet certain which specific filter element has failed. The purpose of the differentiation test procedure is to further obtain more information about the fault in order to more accurately locate the specific filter element position where the fault occurs.

[0097] Because the mapping relationship between motor phase current data and filter element faults can be nonlinear and complex, the third classifier can be trained to learn complex mapping rules for real-time analysis of current characteristics and quickly output the fault type corresponding to the current characteristics, thereby improving detection efficiency and accuracy. Current anomalies may be caused by non-filter element factors such as motor failure, voltage fluctuations, and water quality. First, the mapping relationship is used to preliminarily screen out multi-stage filter element failures, and then differential testing is initiated. Differentiation testing is only initiated when multi-stage filter element failures occur, reducing the consumption of meaningless detection resources and improving the accuracy of fault diagnosis. Differentiation testing can distinguish between single-stage faults and multi-stage faults, and it can also avoid the need for complete filter element replacement, reducing maintenance costs.

[0098] like Figure 15 As shown, in one embodiment, step S220, classifying the multi-mode feature vector to determine the specific filter element location where the fault occurs in the multi-stage filter element according to the classification result, specifically includes the following steps: Step S221: using a first classifier to classify the multi-mode feature vector to analyze and determine the location of a candidate filter element that may have a fault in the multi-stage filter element, and obtain a first classification result; Step S222: Calculate and determine the confidence level of the candidate filter element position in the first classification result.

[0099] The confidence level corresponds to a set of filter element locations where failures may occur. By determining the confidence level of a candidate filter element location, its corresponding failure probability can be calculated. Confidence level screening can narrow the scope of fault location, reduce misjudgments, and further improve the accuracy of locating the specific filter element location where a failure occurs in a multi-stage filter element.

[0100] Step S223: When the confidence level is not less than the preset threshold, the candidate filter element position is determined as the specific filter element position where the fault occurs; Step S224: When the confidence level is less than a preset threshold, the first classification result is analyzed by the second classifier to obtain a second classification result. The first classification result and the second classification result are combined to calculate the probability of failure at each candidate filter element position. The specific filter element position where the failure occurs in each candidate filter element position is determined based on the probability of failure at each candidate filter element position.

[0101] As you can understand, the current signatures recorded and acquired under each operating mode are combined into a multi-mode signature vector. This signature vector contains comprehensive information about the filter element under different operating conditions, providing a more comprehensive picture of its operating status. Compared to signatures from a single operating mode, multi-mode signature vectors contain more information, helping to improve the accuracy of fault diagnosis.

[0102] like Figure 16 、 Figure 17 As shown, in one embodiment, the first classifier adopts a random forest classifier, and the second classifier adopts a neural network classifier.

[0103] Random forest is an integrated learning algorithm that consists of multiple decision trees. Each decision tree classifies the input feature vector and then uses it to determine the final first classification result. The first classifier uses a random forest classifier to exclude filter elements with correct operating status from multi-stage filter elements and narrow the screening range to the locations of filter elements that may have faults, so as to improve the positioning accuracy of the faulty filter elements. A training set is constructed using known faulty filter element samples and corresponding multimodal feature vectors to train the random forest classifier M2. The random forest classifier M2 learns the mapping relationship between different faulty filter element types and multimodal feature vectors, so that it can classify new feature vectors and determine the type of faulty filter element. A preliminary type judgment of the faulty filter element based on the multimodal feature vector can provide a basis for subsequent further analysis.

[0104] The confidence level P reflects the credibility of the classification result. In the random forest classifier, the confidence level of the candidate filter element position in the first classification result is calculated and determined. When the confidence level is lower than the preset threshold, it indicates that the candidate filter element position in the first classification result determined by the random forest classifier M2 is not reliable enough and may be misjudged. At this point, the neural network classifier M3 is activated for further analysis. Neural networks have powerful nonlinear fitting and adaptive learning capabilities, and can handle complex nonlinear relationships. By learning from a large amount of sample data, they can discover potential patterns and characteristics in the data, thereby improving the accuracy of fault diagnosis.

[0105] By comprehensively considering the classification results of the random forest classifier M2 and the neural network classifier M3, methods such as weighted averaging can be used to determine the specific filter element location where the fault occurred among the candidate filter element locations. This is used to integrate the advantages of multiple classifiers to output more accurate and reliable fault filter element types and failure probabilities, providing a decision basis for subsequent repair and maintenance.

[0106] like Figure 18 As shown, in one embodiment, the filter element fault diagnosis and classification method further includes the following steps: Step S410: establishing communication between the multi-stage filter system and the cloud platform; Step S420, in response to the algorithm optimization instruction, obtain and summarize the mapping relationship between the motor phase current data of different user terminals and the filter element faults through the cloud platform, and optimize and update the classification model based on the obtained mapping relationship between the motor phase current data of different user terminals and the filter element faults.

[0107] The cloud platform is a service platform based on cloud computing technology, providing data storage, computing, analysis, and application service interfaces. This enables remote management and interaction of device data, storing the mapping relationship between motor phase current data and filter element faults for each user end, and providing computing resources for algorithm optimization and model updates. By optimizing the classification model based on the mapping relationship between motor phase current data and filter element faults for different user ends, obtained through communication with the cloud platform, the accuracy of filter element status judgment can be continuously improved, allowing accurate determination of multi-stage filter element faults and the specific location of the faulty filter element within the multi-stage filter element.

[0108] like Figure 19 、 Figure 20 As shown, in one embodiment, after executing step S200, determining the specific location of the faulty filter element in the multi-stage filter element according to the current characteristics in the operating mode, the following steps are also included: Step S510: Calculate the probability of filter element failure at the specific filter element position where the failure occurs and the remaining life of the filter element at the specific filter element position where the failure occurs, and generate a diagnostic report based on the calculation results; Step S520: Control the display interface to display the diagnostic report and maintenance information for the faulty filter element.

[0109] A diagnostic report is generated based on the probability of filter element failure and the remaining life of the filter element at the specific location of the faulty filter element. The generated diagnostic report and maintenance information for the faulty filter element are pushed to the user interface for display. This allows users to quickly and intuitively understand the filter element status, whether a fault has occurred, the remaining life of the faulty filter element, and filter element maintenance information.

[0110] In addition to being displayed through the user interface, users can also view diagnostic reports and maintenance information through mobile phone apps, laptops, tablets or other mobile terminals, or fixed terminals such as desktop computers.

[0111] In one embodiment, the filter element fault diagnosis and classification method further includes the following steps: Responding to a system initialization instruction, obtaining a classification model and configuration information; The initialization command is a signal that triggers the reset or clearing of system parameters. It can be a hardware signal automatically triggered by the circuit after detecting a filter replacement, a software command triggered by a software timer, or a user-triggered interactive signal triggered by a local device such as a touch screen or keypad during human-computer interaction, or manually selected and triggered by a remote device such as a user interface or terminal app. A classification model can be constructed and updated based on the mapping between motor phase current data and filter faults. Configuration information includes the configuration parameters, operating status, and replacement time of multi-stage filters.

[0112] like Figure 21 As shown, after determining the specific location of the faulty filter element in the multi-stage filter element in step S200, the following steps are also included: Step S610: Outputting a reminder to replace the filter element at the specific filter element location where the fault occurs; Step S620: In response to the user's filter element replacement confirmation instruction, update the configuration information.

[0113] In this way, users can be reminded to replace faulty filter elements in a timely manner, and update configuration information in a timely manner after replacing the filter elements, thereby reducing fault diagnosis misjudgments caused by inadequate configuration information updates.

[0114] like Figure 22 As shown, some embodiments of the present application further provide a water purifier, which includes a multi-stage filter element 100 system, and the multi-stage filter element 100 system includes a multi-stage filter element 100, a drive module, a current sampling circuit 300 and a controller.

[0115] The multi-stage filter element 100 is used for filtering liquid, and the multi-stage filter element 100 comprises at least a first-stage filter element, a second-stage filter element, and a third-stage filter element connected in series.

[0116] The multi-stage filter element 100 may include a pre-filter element for achieving primary filtration, a middle filter element for deep water purification, and a post-filter element for absorbing residual odors. The number of the pre-filter element, middle filter element, and post-filter element may be one or more. When the multi-stage filter element 100 includes a first-stage filter element, a second-stage filter element, and a third-stage filter element, in series order, the first-stage filter element may be a pre-filter element, the second-stage filter element may be a middle filter element, and the third-stage filter element may be a post-filter element; when the multi-stage filter element 100 includes a fourth-stage filter element or at least one other filter element in addition to the first-stage filter element, the second-stage filter element, and the third-stage filter element, in series order, the first-stage filter element may be a pre-filter element, the second-stage filter element, the third-stage filter element, etc. may be a middle filter element, and the last-stage filter element may be a post-filter element; the specific configuration may be based on actual conditions and is not limited here.

[0117] like Figure 23 As shown, the pre-filter element includes a PP cotton filter element 110, a pre-activated carbon filter element 120, and a metal filter. Taking the PP cotton filter element 110 as an example, when a blockage occurs, its current characteristics are: the current waveform shows an increase in high-frequency fluctuations and a slight increase in the fundamental amplitude. The mid-filter element includes an activated carbon filter element 120, an RO reverse osmosis membrane 130, and a nanofiltration membrane. Taking the activated carbon filter element 120 as an example, when a blockage occurs, its current characteristics are: a significant increase in the third harmonic in the current harmonic components and increased waveform distortion. Taking the RO reverse osmosis membrane 130 as an example, when a blockage occurs, its current characteristics are: a significant increase in the current mean, a decrease in the crest factor, and an increase in the low-frequency component. The post-filter element includes a post-activated carbon filter element 120, a mineralized filter element 140, and a weak alkaline filter element. Taking the mineralized filter element 140 as an example, when a blockage occurs, its current characteristics are: a significant change in the current waveform phase and a change in the harmonic characteristic ratio.

[0118] The drive module is used to provide power for the liquid delivered to the filter element, thereby allowing the filter element to absorb or filter impurities in the liquid. The drive module includes a variable frequency pump 210, a motor 220, and a motor drive circuit 230. The variable frequency pump 210 is connected to the first-stage filter element and is used to provide power for the liquid delivered to the multi-stage filter element 100; the motor 220 is connected to the variable frequency pump 210 and is used to provide power for the variable frequency pump 210; and the motor drive circuit 230 is connected to the motor 220 and is used to drive the motor 220. In addition to the variable frequency pump 210, any pump body, such as a centrifugal pump or a gear pump, can also be used, without limitation here. The motor 220 is connected to the variable frequency diaphragm pump and is used to provide power for the variable frequency diaphragm pump; the motor drive circuit 230 is connected to the motor 220 and is used to drive the motor 220. The motor drive circuit 230 is used to provide drive current to the variable frequency motor 220, which is used to control the speed and torque of the motor 220 and can also be used to detect the status of the motor 220. The controller drives the motor 220 through the motor drive circuit 230 and controls the speed of the motor 220 so that the drive module operates according to the set operating mode.

[0119] The current sampling circuit 300 is used to collect phase current data from the motor 220. Using a dual-resistance sampling method, the current sampling circuit 300 detects the three-phase current of the motor 220 in real time, obtaining current signals such as the motor 220's phase current data. The current sampling circuit 300 is connected to a controller and is used to feed back the real-time detected phase current data and other current signals to the controller. The controller includes a signal processing module 410, a feature extraction module 420, a fault classification module 430, and a control module 440. The signal processing module 410 processes the received motor 220 phase current data, classification model, and other data. The feature extraction module 420 is used to extract current features. The fault classification module 430 is used to determine whether a fault has occurred and the specific filter element location within the multi-stage filter element 100 where the fault has occurred. The control module 440 controls the operation of the drive module, enabling the drive module to automatically provide power for the liquid delivered to the filter element.

[0120] like Figure 24As shown, exemplarily, the current sampling module includes a motor phase line, a sampling resistor, a differential amplifier, and an analog-to-digital conversion module 240, wherein the motor phase line is used to transmit the electric energy required for driving; the sampling resistor is connected to the motor phase line, and the FOC (Field-Oriented Control) dual-resistance sampling algorithm can be used to detect the phase current and other current data of the motor 220 in real time; the differential amplifier is connected to the sampling resistor and is used to amplify and process the current data; the analog-to-digital conversion module 240 is connected to the differential amplifier and the signal processing unit respectively, and is used to convert the analog voltage signal output by the differential amplifier into a digital signal. The signal processing unit performs digital filtering (such as sliding window filtering) and fast Fourier transform (FFT) on the received digital signal to extract the phase current effective value, current peak value, change rate (ΔI / Δt) and abnormal fluctuation characteristics of the motor 220, providing data support for the motor 220 control algorithm and filter element fault diagnosis. The current sampling module is used to detect the phase current data of the motor 220 and other operating parameters of the motor 220 in real time. The controller controls the operation of the driving module so that the driving module can automatically provide power for the liquid delivered to the filter element.

[0121] The controller stores and executes the filter element fault diagnosis and classification program, and when executing the program, implements the steps of the filter element fault diagnosis and classification method of the above embodiment.

[0122] Compared with the solution of separately setting up multiple pressure sensors, flow meters and other detection devices for the corresponding multi-stage filter element 100, which has high cost and complexity, increases fault points due to improper installation, and cannot accurately determine the specific filter element position where the fault occurs in the multi-stage filter element 100, the embodiment of the present application does not install additional detection devices such as pressure sensors or flow meters, but uses the water purifier's own drive module and current sampling circuit 300 to determine the current characteristics of the motor 220 in the set mode by real-time collection of the motor 220 current, and further determine the specific filter element position where the fault occurs in the multi-stage filter element 100 based on the current characteristics in the operating mode; effectively solves the technical problem of being unable to timely and reliably determine the specific filter element position where the fault occurs in the multi-stage filter element 100, and by reducing the use of additional detection devices, not only reduces costs, reduces equipment complexity and failure rate, but also improves system reliability. Because current signals can be collected and processed in real time, the current characteristics of motor 220 under a set operating mode can be directly used to determine the specific location of a faulty filter element in multi-stage filter element 100. This effectively reduces errors and improves the accuracy of fault diagnosis. In some scenarios, the accuracy of fault diagnosis can even reach over 90%. This allows for precise diagnosis of the specific location of a faulty filter element and further addresses the issue of premature or delayed filter element replacement.

[0123] In one embodiment, the multi-stage filter element 100 system also includes a user interface 500, which is used to display diagnostic reports and filter element maintenance information. The diagnostic report includes at least the filter element failure probability of the specific filter element position where the fault occurs and the remaining life of the filter element at the specific filter element position where the fault occurs.

[0124] In this way, users can timely and intuitively understand the status of the filter element, whether there is a fault, the remaining life of the faulty filter element, filter element maintenance information, etc.

[0125] The water purifier provided in this application, utilizing the filter element fault diagnosis and classification method described in the aforementioned embodiment, can resolve the technical problem of promptly and reliably determining the specific location of a faulty filter element in a multi-stage filter element without the need for additional detection devices. Compared to the prior art, the beneficial effects of the water purifier provided in this application are the same as those of the filter element fault diagnosis and classification method described in the aforementioned embodiment, and the other technical features of the water purifier are the same as those disclosed in the aforementioned embodiment, and are not further elaborated here.

[0126] On the other hand, the present application provides a filter element fault diagnosis and classification device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a filter element fault diagnosis and classification program that can be executed by the at least one processor, and the filter element fault diagnosis and classification program is configured to implement the steps of the filter element fault diagnosis and classification method as described in the above embodiment.

[0127] The filter element fault diagnosis and classification device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. The specific configuration can be tailored to actual needs and is not intended to limit the functionality and scope of use of the embodiments of the present application.

[0128] The filter element fault diagnosis and classification device may include a processing device that can perform various appropriate actions and processes based on programs stored in read-only memory or programs loaded from a storage device into random access memory. The random access memory also stores various programs and data required for the operation of the filter element fault diagnosis and classification device. The processing device, read-only memory, and random access memory are interconnected via a bus. An input / output interface is also connected to the bus. Typically, the following systems may be connected to the input / output interface: input devices such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices such as magnetic tape and hard disk; and communication devices. The communication devices may enable the filter element fault diagnosis and classification device to communicate with other devices wirelessly or wired to exchange data. While the figures illustrate a filter element fault diagnosis and classification device with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0129] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a filter element fault diagnosis classification program product, which includes a filter element fault diagnosis classification program carried on a computer-readable medium, and the filter element fault diagnosis classification program contains program code for executing the method shown in the flowchart. In such an embodiment, the filter element fault diagnosis classification program can be downloaded and installed from the network through a communication device, or installed from a storage device, or installed from a read-only memory. When the filter element fault diagnosis classification program is executed by the processing device, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0130] The filter element fault diagnosis and classification device provided in this application, which utilizes the filter element fault diagnosis and classification method described in the aforementioned embodiment, can solve the technical problem of promptly and reliably determining the specific location of a faulty filter element in a multi-stage filter element without the need for additional detection devices. Compared to the prior art, the filter element fault diagnosis and classification device provided in this application achieves the same beneficial effects as the filter element fault diagnosis and classification method described in the aforementioned embodiment. The other technical features of this filter element fault diagnosis and classification device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0131] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0132] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0133] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A filter element fault diagnosis and classification method, characterized in that: Applied to a multi-stage filter element system, the multi-stage filter element system includes a multi-stage filter element and a drive module, the drive module is used to provide power for the liquid transported to the multi-stage filter element, and the drive module includes a motor; the filter element fault diagnosis and classification method includes the following steps: Control the drive module to operate according to the set operating mode and obtain the current characteristics of the motor in the set operating mode; The specific location of the filter element where the fault occurs in the multi-stage filter element is determined based on the current characteristics under the operating mode.

2. The filter element fault diagnosis and classification method according to claim 1, characterized in that: Determining the specific location of the faulty filter element in the multi-stage filter element according to the current characteristics in the operating mode specifically includes the following steps: Combining the phase current data of the motor in the operating mode into a multi-mode feature vector; The multi-mode feature vector is classified to determine the specific filter element location where the fault occurs in the multi-stage filter element according to the classification result.

3. The filter element fault diagnosis and classification method according to claim 2, characterized in that: The multi-mode feature vector is classified to determine the specific location of the faulty filter element in the multi-stage filter element according to the classification result, specifically comprising the following steps: Using a first classifier to classify the multi-mode feature vector to analyze and determine the candidate filter element locations that may have faults in the multi-stage filter element, and obtain a first classification result; Calculating and determining the confidence level of the candidate filter element position in the first classification result; When the confidence level is not less than a preset threshold, the candidate filter element position is determined as the specific filter element position where the fault occurs; When the confidence level is less than a preset threshold, the first classification result is analyzed by the second classifier to obtain a second classification result. The first classification result and the second classification result are combined to calculate the probability of failure in each candidate filter element position. The specific filter element position where the failure occurs in each candidate filter element position is determined based on the probability of failure in each candidate filter element position.

4. The filter element fault diagnosis and classification method according to claim 3, characterized in that: The first classifier adopts a random forest classifier, and the second classifier adopts a neural network classifier.

5. The filter element fault diagnosis and classification method according to claim 1, characterized in that: The control driving module operates according to the set operating mode and obtains the current characteristics of the motor in the set operating mode, specifically including the following steps: Obtain the current phase current data of the motor, control the drive module to run at the operating speed of the set operating mode based on the current phase current data of the motor, obtain the operating status of the filter element, and obtain the phase current data of the motor in each operating mode.

6. The filter element fault diagnosis and classification method according to claim 5, characterized in that: The multi-stage filter element includes at least a first-stage filter element, a second-stage filter element, and a third-stage filter element connected in series. The method of obtaining the operating status of the filter element and obtaining the phase current data of the motor in each operating mode specifically includes the following steps: When the control driving module is operated at the first operating speed, at least the operating state of the first-stage filter element and the phase current data of the motor in the first operating mode are obtained; When the control driving module is operated at the second operating speed, at least the operating state of the second-stage filter element and the phase current data of the motor in the second operating mode are obtained; When the driving module is controlled to operate at the third operating speed, at least the operating state of the third-stage filter element and the phase current data of the motor in the third operating mode are obtained; When the control driving module is operated at the fourth operating speed, the operating state of each filter element is obtained, and the phase current data of the motor in the fourth operating mode is obtained; Among them, the first operating speed is less than the second operating speed and less than the third operating speed and less than the fourth operating speed, and the fourth operating speed is determined according to the current phase current data of the motor.

7. The filter element fault diagnosis and classification method according to claim 5, characterized in that: The operating status of the filter element is obtained in the following ways: Obtain the corresponding relationship between the motor phase current data and the filter element operating status, as well as the current phase current data of the motor, and obtain the operating status of the filter element based on the current phase current data of the motor, the corresponding relationship between the motor phase current data and the filter element operating status; And / or, obtaining detection data of the sensor module, and determining the operating status of the filter element based on the detection data, wherein the sensor module includes at least one of a water quality sensor, a flow sensor, a temperature sensor, and a sound sensor, or a combination of multiple thereof.

8. The filter element fault diagnosis and classification method according to claim 1, characterized in that: Before executing the step of controlling the drive module to operate according to the set operating mode and obtaining the current characteristics of the motor in the set operating mode, the filter element fault diagnosis and classification method further includes the following steps: In response to the operation instruction, obtaining current phase current data of the motor, and processing the current phase current data of the motor; Obtain the mapping relationship between motor phase current data and filter element faults; When a multi-stage filter element failure is determined based on the processed current phase current data of the motor and a mapping relationship between the motor phase current data and the filter element failure, a difference test is initiated.

9. The filter element fault diagnosis and classification method according to claim 8, characterized in that: The processing of the current phase current data of the motor specifically includes the following steps: Preprocessing the current phase current data of the motor; Calculate time domain features based on pre-processed current phase current data of the motor; Performing Fourier transform on the preprocessed current phase current data of the motor to obtain a frequency spectrum, and obtaining frequency domain features calculated based on the frequency spectrum; Performing wavelet transform on the preprocessed current phase current data of the motor to obtain a time-frequency distribution, and obtaining a time-frequency domain feature calculated based on the time-frequency distribution; Combining the time domain features, frequency domain features, and time-frequency domain features to form a pending feature vector, performing data processing on the pending feature vector, and obtaining a target feature vector; When it is determined that a multi-stage filter element has failed based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element failure, starting the difference test specifically includes the following steps: When a multi-stage filter element fails, a difference test is initiated according to a mapping relationship between the target feature vector, the motor phase current data, and the filter element failure.

10. The filter element fault diagnosis and classification method according to claim 8, characterized in that: When it is determined that a multi-stage filter element has failed based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element failure, starting the difference test specifically includes the following steps: Obtain samples of normal operating conditions and various types of filter element fault conditions, label the various fault types, determine the mapping relationship between motor phase current data and filter element faults, and build a third classifier containing a classification model; When the third classifier determines that the multi-stage filter element is faulty based on the processed current phase current data of the motor and the mapping relationship between the motor phase current data and the filter element fault, a differential test is initiated; Wherein, the third classifier adopts SVM classifier.

11. The filter element fault diagnosis and classification method according to claim 10, wherein: The filter element fault diagnosis and classification method further comprises the following steps: Establish communication between the multi-stage filter system and the cloud platform; In response to the algorithm optimization instruction, the mapping relationship between the motor phase current data of different user terminals and the filter element faults is obtained and summarized through the cloud platform, and the classification model is optimized and updated based on the obtained mapping relationship between the motor phase current data of different user terminals and the filter element faults.

12. The filter element fault diagnosis and classification method according to any one of claims 1 to 11, characterized in that: After executing the step of determining the specific location of the faulty filter element in the multi-stage filter element based on the current characteristics in the operating mode, the method further includes the following steps: Calculate the probability of filter element failure at the specific filter element location where the failure occurs and the remaining life of the filter element at the specific filter element location where the failure occurs, and generate a diagnostic report based on the calculation results; The control display interface displays the diagnostic report and maintenance information for the faulty filter element.

13. The filter element fault diagnosis and classification method according to any one of claims 1 to 11, characterized in that: The filter element fault diagnosis and classification method further comprises the following steps: Responding to a system initialization instruction, obtaining a classification model and configuration information; After determining the specific location of the faulty filter element in the multi-stage filter element, the method further includes the following steps: Output a replacement reminder for the filter element at the specific location where the fault occurs; In response to a user filter cartridge replacement confirmation instruction, the configuration information is updated.

14. A water purifier, characterized in that: A multi-stage filter element system is provided, wherein the multi-stage filter element system comprises: A multi-stage filter element is used to filter liquid, and the multi-stage filter element includes at least a first-stage filter element, a second-stage filter element, and a third-stage filter element connected in series; A drive module includes a variable frequency pump, a motor, and a motor drive circuit. The variable frequency pump is connected to the first-stage filter element and is used to provide power for the liquid transmitted to the multi-stage filter element. The motor is connected to the variable frequency pump drive and is used to provide power for the variable frequency pump. The motor drive circuit is connected to the motor drive and is used to drive the motor to work. A current sampling circuit, used for collecting phase current data of the motor; The controller stores and executes a filter element fault diagnosis and classification program, and implements the steps of the filter element fault diagnosis and classification method as described in any one of claims 1 to 13 when executing the program.

15. The water purifier according to claim 14, characterized in that: The multi-stage filter element system also includes a user interface, which is used to display a diagnostic report and filter element maintenance information. The diagnostic report at least includes the filter element failure probability and the remaining life of the filter element at the specific filter element position where the fault occurs.

16. A filter element fault diagnosis and classification device, characterized in that: include: A memory, a processor, and a filter element fault diagnosis and classification program stored in the memory and executable on the processor, wherein the filter element fault diagnosis and classification program is configured to implement the steps of the filter element fault diagnosis and classification method according to any one of claims 1 to 13.

Images