Self-service car washing machine automatic detection and fault early warning system and method thereof

Abstract

The application relates to an automatic detection and fault early warning system and method for a self-service car washer, which comprises a data acquisition module, a diagnosis circuit module, a water quality feature acquisition module, a correlation analysis module and an alarm module. The application can comprehensively understand the operation state of the equipment and the water quality condition by collecting multiple parameters in real time, can accurately identify potential problems and give early warning through correlation analysis and a dynamic early warning mechanism, can reduce the false alarm and missed alarm conditions, can improve the accuracy of early warning, and can adapt to the dynamic changes of the operation state of the equipment and the water quality condition through the correlation analysis and the dynamic early warning mechanism, can predict and intervene in advance potential problems, and has the effects of improving the comprehensiveness of self-service car washer fault monitoring, enhancing the accuracy of early warning, and improving the adaptability and reliability of the system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault early warning, in particular to an automatic detection and fault early warning system for a self-service car washer and a method thereof. BACKGROUND

[0002] With the increasing number of cars, self-service car washers, as a convenient and efficient way of washing cars, have been favored by more and more car owners. However, in the long-term operation of self-service car washers, due to the influence of various factors such as complex working environment, equipment aging, and water quality changes, various faults often occur in each execution device (such as water pump, motor, nozzle, etc.) in the working system and the water treatment system, resulting in a decline in car washing effect, and even may cause equipment damage or safety accidents.

[0003] In the prior art, the fault detection and early warning of self-service car washers mainly rely on manual inspection and simple sensor monitoring. Although manual inspection can intuitively find some problems, it has the defects of low efficiency and difficulty in real-time monitoring. Simple sensor monitoring can only monitor a single parameter and cannot fully reflect the running state of the equipment and the water quality, and cannot give early warning of faults.

[0004] Especially, in the operation of self-service car washers, there is a complex correlation between operating parameters (such as motor speed, water pump pressure, nozzle spray angle, etc.) and water quality. These correlation not only affects the car washing effect, but also is an important precursor of faults. However, the existing technology often ignores the analysis and use of these correlation, resulting in a big discount in the accuracy and timeliness of fault early warning. SUMMARY

[0005] In order to solve the above-mentioned defects, the present application provides an automatic detection and fault early warning system for a self-service car washer and a method thereof.

[0006] The above-mentioned invention purpose of the present application is realized by the following technical scheme:

[0007] An automatic detection and fault early warning system for a self-service car washer, comprising:

[0008] A data acquisition module for acquiring operating parameters of each execution device in the working system of the self-service car washer and water quality parameters in the water treatment system in real time;

[0009] A diagnostic circuit module for analyzing the operating parameters to diagnose the state of each execution device, and outputting operating parameter features or issuing an alarm signal based on the state analysis result;

[0010] A water quality feature acquisition module for feature extraction and analysis of the collected water quality parameters to obtain water quality features;

[0011] the correlation analysis module is configured to perform correlation analysis on the operation parameter features and the water quality features to obtain trend features and correlation features, extract abnormal features based on the trend features and the correlation features, and output an abnormal signal;

[0012] the alarm module is configured to issue a fault prompt message when receiving the alarm signal or the abnormal signal.

[0013] By adopting the above technical solutions, the data acquisition module is responsible for collecting operation parameters (such as rotation speed, pressure, temperature, etc.) of each execution device in the self-service car washing machine working system and water quality parameters (such as pH value, turbidity, residual chlorine amount, etc.) in the water treatment system in real time; the diagnosis circuit module analyzes the collected operation parameters to determine whether the working state of each execution device is normal and outputs operation parameter features, and directly triggers an alarm signal when an abnormality is detected; the water quality feature acquisition module focuses on the processing and analysis of water quality parameters, extracts key water quality features from raw data through feature extraction, and provides an important basis for correlation analysis; the correlation analysis module performs in-depth correlation analysis on the operation parameter features and the water quality features to reveal the potential relationship and trend between the two and identify abnormal features, and outputs an abnormal signal to provide support for fault early warning; the alarm module will immediately issue a fault prompt message when receiving the alarm signal or the abnormal signal, so that timely measures can be taken to prevent the fault from further deteriorating; the present application comprehensively understands the running state of the equipment and the water quality condition by collecting a plurality of parameters in real time, accurately identifies potential problems and issues an alarm in advance through correlation analysis and a dynamic early warning mechanism, reduces the situation of false positives and false negatives, improves the accuracy of early warning, and through the correlation analysis and the dynamic early warning mechanism, adapts to the dynamic changes of the equipment running state and the water quality condition, predicts and intervenes in advance potential problems, has the effects of improving the comprehensiveness of self-service car washing machine fault monitoring, enhancing the accuracy of early warning, and improving the adaptability and reliability of the system.

[0014] In a preferred example, the present application can be further configured as follows:

[0015] the physical sensor unit includes a temperature sensor, a pressure sensor, and a flow sensor;

[0016] the chemical sensor unit includes a pH sensor, a conductivity sensor, a dissolved oxygen sensor, and an ammonia nitrogen sensor;

[0017] the self-calibration unit is configured to periodically calibrate the physical sensor unit and the chemical sensor unit.

[0018] By adopting the technical scheme, the physical sensor unit includes a temperature sensor, a pressure sensor and a flow sensor, which are respectively used for monitoring the running temperature and its change of each executing device of the self-service car washing machine in the car washing process, the working pressure of the executing devices such as the water pump and the spray head in the car washing process and the flow of the water flow in the car washing process; the chemical sensor includes a pH sensor, a conductivity sensor, a dissolved oxygen sensor and an ammonia nitrogen sensor, wherein the pH sensor is used for measuring the acidity and alkalinity of water quality, ensuring that the water for car washing is in a suitable pH range, so as to protect the vehicle surface and the car washing equipment, the conductivity sensor reflects the conductivity of water, which is helpful to evaluate the purity of water quality, the dissolved oxygen sensor monitors the dissolved oxygen content in water, which is crucial for maintaining the normal operation of the biological treatment system (such as the activated sludge method), and the ammonia nitrogen sensor is used for detecting the ammonia nitrogen content in water, and the ammonia nitrogen content is one of the important indicators for evaluating the degree of water pollution; the self-calibration unit is used for periodically calibrating the physical sensor unit and the chemical sensor unit, so as to ensure the accuracy and reliability of the sensor data and eliminate the measurement error caused by the aging of the sensor, the change of the environment and other factors.

[0019] In a preferred example, the application can be further configured to: the diagnostic circuit module comprises:

[0020] a predictive maintenance unit for predicting the future running state of the equipment based on historical data and the running parameters input in real time by the data acquisition module, and outputting the running parameter characteristics;

[0021] a fault tree analysis unit for fault analysis on the running parameter characteristics and matching the corresponding fault path based on the analysis result;

[0022] a microprocessor for receiving the running parameters input in real time by the data acquisition module and storing the historical data, and sending an alarm signal when receiving the fault path information and outputting the running parameter characteristics when receiving the running parameter characteristics.

[0023] By adopting the technical scheme, the predictive maintenance unit utilizes historical data and real-time input operation parameters of the data acquisition module to construct a prediction model, to mine potential rules in the data, predict future operation state of the equipment and output operation parameter features; the fault tree analysis unit analyzes the operation parameter features output by the predictive maintenance unit: analyzes possible causes and paths of the fault through construction of a fault tree model, and matches corresponding fault paths based on the analysis result; the microprocessor is responsible for receiving real-time input operation parameters of the data acquisition module, and storing historical data for use by the predictive maintenance unit, at the same time, when receiving fault path information output by the fault tree analysis unit, the microprocessor will immediately issue an alarm signal, and when receiving operation parameter features output by the predictive maintenance unit, the microprocessor will output the operation parameter features; through the above design, the application realizes comprehensive monitoring and accurate early warning of the self-service car washing machine working system, the use of the predictive maintenance unit enables the system to discover potential faults in advance, avoids equipment downtime and service interruption caused by faults, improves the availability of the equipment and customer satisfaction, the introduction of the fault tree analysis unit simplifies the fault troubleshooting process, reduces the maintenance difficulty and cost, and the efficient processing capacity and information transmission mechanism of the microprocessor ensure the collaborative work of each part of the system, and improve the overall efficiency.

[0024] In a preferred example, the water quality feature acquisition module can be further configured to include:

[0025] The feature extraction unit is configured to perform feature extraction on the collected water quality parameters, thereby obtaining a plurality of types of preliminary features.

[0026] The data analysis unit is configured to pre-process and deeply analyze the preliminary features, thereby obtaining fluctuation range features.

[0027] The water quality state evaluation unit is configured to analyze the water quality state based on the fluctuation range features, and output water quality features based on the analysis result.

[0028] By adopting the technical scheme, the feature extraction unit performs preliminary processing on the water quality parameters (such as temperature, pH value, conductivity, dissolved oxygen, ammonia nitrogen, etc.) acquired by the data acquisition module, that is, extracts several types of preliminary features representing water quality characteristics from the original data, including statistical quantities such as mean value, standard deviation, maximum value, minimum value, or specific patterns identified by a specific algorithm; the data analysis unit further preprocesses and deeply analyzes the preliminary features output by the feature extraction unit, the preprocessing includes data cleaning (removing outliers, filling missing values, etc.), normalization or standardization processing, to ensure the accuracy and comparability of the data, and the deep analysis involves complex statistical methods, machine learning algorithms or data mining techniques, to reveal the fluctuation range characteristics of the water quality parameters, that is, the change range and stability of the water quality parameters under certain time or conditions; the water quality state evaluation unit evaluates the water quality state based on the fluctuation range characteristics output by the data analysis unit, and outputs the evaluation result in the form of water quality characteristics; the application realizes efficient and accurate monitoring and evaluation of the water quality of the self-service car wash machine by combining feature extraction, data analysis and water quality state evaluation, and has multiple effects of improving water quality management efficiency, reducing water treatment cost, ensuring car washing effect and equipment safety, etc.

[0029] In a preferred example, the application can be further configured as follows:

[0030] The feature fusion unit is configured to fuse the operation parameter features and the water quality features to generate comprehensive features.

[0031] The trend prediction unit is configured to perform trend prediction on the comprehensive features based on a pre-set time series analysis technique to obtain trend features.

[0032] The correlation mining unit is configured to perform correlation mining on the comprehensive features based on a pre-defined data mining algorithm to obtain correlation features between the operation parameters and the water quality features.

[0033] The anomaly detection unit is configured to dynamically set an anomaly threshold according to the correlation features and the trend features, and perform anomaly detection on the real-time input comprehensive features, and output an anomaly signal when an anomaly feature is detected.

[0034] By adopting the above technical solution, the feature fusion unit integrates the operating parameter features and water quality features provided by the data acquisition module and the water quality feature acquisition module respectively, integrating the two types of features in a unified space or framework to generate comprehensive features that can fully reflect the working status and water quality of the self-service car wash machine; the trend prediction unit uses pre-set time series analysis technology to predict the trend of the fused comprehensive features; the correlation mining unit performs correlation mining on the comprehensive features based on predefined data mining algorithms to reveal the correlation between operating parameter features and water quality features, such as how changes in certain operating parameters affect water quality features, or how changes in certain water quality features reflect changes in operating status; the anomaly detection unit dynamically sets anomaly threshold based on correlation features and trend features, and performs anomaly detection on the real-time input comprehensive features. When an anomaly feature is detected, the anomaly detection unit will immediately output an anomaly signal, which helps to promptly discover and handle abnormal situations in the system and ensure the stable operation of the system; this application, through the combination of feature fusion, trend prediction, correlation mining, and anomaly detection, realizes comprehensive and in-depth analysis and intelligent early warning of the water treatment and monitoring system for self-service car wash machines, which has multiple effects such as improving system operating efficiency, reducing failure rate, and optimizing water quality management.

[0035] In a preferred embodiment, this application can be further configured such that: when generating comprehensive features, the feature fusion unit constructs time series data for the comprehensive features, and the trend prediction unit is used for:

[0036] Based on a pre-set time series clustering algorithm, cluster analysis is performed on the time series data in the comprehensive features, and several different operating modes are identified.

[0037] The algorithm uses a pre-set dynamic time warping algorithm to extract similar patterns from time series data and perform trend prediction to obtain trend characteristics.

[0038] The association mining unit is used for:

[0039] Based on the results of cluster analysis, the correlation between operating parameter characteristics and water quality characteristics under different operating modes is explored to extract correlation features;

[0040] By combining pre-set data mining algorithms with the extracted association features, association rules are mined to identify the association rules corresponding to the association features.

[0041] By adopting the technical scheme, when the feature fusion unit generates the comprehensive feature, not only the operation parameter feature and the water quality feature are fused, but also time series data is constructed for the comprehensive feature, so that each comprehensive feature contains information in the time dimension; the trend prediction unit uses a pre-set time series clustering algorithm to perform clustering analysis on the time series data in the comprehensive feature, so as to classify features with similar change patterns into one category, thereby identifying several different operation modes, and through a pre-set dynamic time warping algorithm, similar patterns are extracted from the time series data and trend prediction is performed, the dynamic time warping algorithm can handle the non-linear change and time shift problem in the time series data, so that the future trend of the feature is more accurately predicted; the association mining unit mines the association between the operation parameter feature and the water quality feature under different operation modes based on the result of the clustering analysis, and in combination with a pre-set data mining algorithm, the extracted associated features are mined for association rules, and through mining the potential rules between the associated features, the causal relationship or the correlation relationship between the operation parameter and the water quality feature is identified; through the combination of the technologies of feature fusion, time series construction, clustering analysis, dynamic time warping algorithm and association rule mining, the application realizes comprehensive and in-depth analysis and intelligent early warning of the self-service car washing machine water treatment and monitoring system, not only improves the system operation efficiency and water quality management level, but also reduces the failure rate and maintenance cost.

[0042] The second application object of the application is achieved by the following technical scheme:

[0043] An automatic detection and fault early warning method for a self-service car washing machine, comprising:

[0044] Real-time acquisition of operation parameters of each execution device in the working system of the self-service car washing machine and water quality parameters in the water treatment system; analysis of the operation parameters to diagnose the state of each execution device, and output of an operation parameter feature or issuance of an alarm signal based on the state analysis result; feature extraction and analysis of the acquired water quality parameters to obtain a water quality feature; correlation analysis of the operation parameter feature and the water quality feature to obtain a trend feature and an associated feature, extraction of an abnormal feature based on the trend feature and the associated feature, and output of an abnormal signal; issuance of a fault prompt information when the alarm signal or the abnormal signal is received.

[0045] By adopting the technical scheme, the operation parameters of each executing device in the working system of the self-service car washing machine and the water quality parameters in the water treatment system are collected in real time; the operation parameters are analyzed to diagnose the state of each executing device, and operation parameter features are output or an alarm signal is sent based on the state analysis result; the water quality features are obtained by performing feature extraction and analysis on the collected water quality parameters; the trend features and the correlation features are obtained by performing correlation analysis on the operation parameter features and the water quality features, the abnormal features are extracted based on the trend features and the correlation features, and an abnormal signal is output; when the alarm signal or the abnormal signal is received, a fault prompt information is sent.

[0046] In a preferred example, the application can be further configured as follows: the operation parameters are analyzed to diagnose the state of each executing device, and operation parameter features are output or an alarm signal is sent based on the state analysis result, including:

[0047] Based on the historical data and the operation parameters input in real time by the data collection module, the future operation state of the device is predicted, and operation parameter features are output; the operation parameter features are analyzed for faults, and corresponding fault paths are matched based on the analysis result; the operation parameters input in real time by the data collection module and the historical data are received, and an alarm signal is sent when the fault path information is received, and operation parameter features are output when the operation parameter features are received.

[0048] By adopting the technical scheme, the operation parameters are analyzed to diagnose the state of each executing device, and operation parameter features are output or an alarm signal is sent based on the state analysis result, including: based on the historical data and the operation parameters input in real time by the data collection module, the future operation state of the device is predicted, and operation parameter features are output; the operation parameter features are analyzed for faults, and corresponding fault paths are matched based on the analysis result; the operation parameters input in real time by the data collection module and the historical data are received, and an alarm signal is sent when the fault path information is received, and operation parameter features are output when the operation parameter features are received.

[0049] In a preferred example, the application can be further configured as follows: the water quality features are obtained by performing feature extraction and analysis on the collected water quality parameters, including:

[0050] The water quality parameters collected are subjected to feature extraction, thereby obtaining a plurality of types of preliminary features; the preliminary features are preprocessed and deeply analyzed, thereby obtaining fluctuation range features; the water quality state is analyzed based on the fluctuation range features, and water quality features are output based on the analysis result.

[0051] By adopting the technical scheme, the water quality parameters collected are subjected to feature extraction and analysis to obtain water quality features, including feature extraction on the collected water quality parameters to obtain preliminary features of several types; the preliminary features are subjected to pretreatment and in-depth analysis to obtain fluctuation range features; the water quality state is analyzed based on the fluctuation range features, and the water quality features are output based on the analysis result.

[0052] In summary, the present application includes at least one of the following beneficial technical effects:

[0053] 1. The present application comprehensively understands the running state of the equipment and the water quality condition by collecting multiple parameters in real time, accurately identifies potential problems and issues an early warning, reduces false positives and false negatives, improves the accuracy of the warning, and through the correlation analysis and dynamic early warning mechanism, adapts to the dynamic changes of the equipment running state and the water quality condition, predicts and intervenes in advance, has the effect of improving the comprehensiveness of the self-service car washing machine fault monitoring, enhancing the accuracy of the warning, and improving the adaptability and reliability of the system. BRIEF DESCRIPTION OF DRAWINGS

[0054] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description of embodiments of the present application taken in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of embodiments of the present application and constitute a part of the specification, together with the description, to explain the present application and do not limit the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0055] Figure 1 is a block diagram of an automatic detection and fault warning system for a self-service car washing machine according to the present application;

[0056] Figure 2 is a block diagram of a data acquisition module in an embodiment of an automatic detection and fault warning system for a self-service car washing machine according to the present application;

[0057] Figure 3 is a block diagram of a diagnostic circuit module in an embodiment of an automatic detection and fault warning system for a self-service car washing machine according to the present application;

[0058] Figure 4 is a block diagram of a water quality feature acquisition module in an embodiment of an automatic detection and fault warning system for a self-service car washing machine according to the present application;

[0059] Figure 5 is a block diagram of a correlation analysis module in an embodiment of an automatic detection and fault warning system for a self-service car washing machine according to the present application. DETAILED DESCRIPTION

[0060] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description of embodiments of the present application taken in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of embodiments of the present application and constitute a part of the specification, together with the description, to explain the present application and do not limit the present application. In the drawings, the same reference numerals generally represent the same components or steps. Figures 1-5Further details of the present application are described below.

[0061] In one embodiment, as shown in Figure 1 The present application discloses an automatic detection and fault warning system 100 for a self-service car washing machine, which specifically comprises:

[0062] A data acquisition module 110 is configured to acquire, in real time, running parameters of each execution device in a working system of the self-service car washing machine and water quality parameters in a water treatment system;

[0063] A diagnostic circuit module 120 is configured to analyze the running parameters to diagnose a state of each execution device and output a running parameter feature or send an alarm signal based on a result of the state analysis;

[0064] A water quality feature acquisition module 130 is configured to extract and analyze features of the acquired water quality parameters to acquire water quality features;

[0065] An association analysis module 140 is configured to perform association analysis on the running parameter features and the water quality features to acquire trend features and association features, extract abnormal features based on the trend features and the association features, and output an abnormal signal;

[0066] An alarm module 150 is configured to send a fault prompt information when receiving the alarm signal or the abnormal signal;

[0067] In the present embodiment, the operating parameter refers to the specific value or state of each executing device (such as motor speed, water pump pressure, nozzle spray angle, etc.) in the self-service car washing machine working system during the working process, which reflects the running state and working performance of the device; the water quality parameter refers to the physical and chemical properties of water in the water treatment system, such as pH value (acidity), turbidity (water clarity), conductivity (water conductivity), etc., which directly reflects the quality of water; the state analysis is to judge whether the executing device is in normal working state or whether there is a potential fault through the analysis of the operating parameter, which involves threshold judgment, trend analysis, pattern recognition, etc. of the parameter; the operating parameter feature is the feature extracted from the operating parameter which can represent the running state of the device, such as average speed, pressure fluctuation range, etc.; the alarm signal is the signal sent by the diagnosis circuit module when detecting device failure or abnormal state, which is used to trigger the alarm module to send fault prompt information; the feature extraction is to extract the feature from the water quality parameter which can represent the water quality condition, such as the stability of pH value, the change trend of turbidity, etc.; the water quality feature is the feature representation of the water quality parameter after feature extraction, which is used for subsequent water quality analysis and correlation analysis; the correlation analysis is a data analysis method used to reveal the relationship between two or more variables, which is used to reveal the internal relationship between the operating parameter feature and the water quality feature in the self-service car washing machine system; the trend feature is the change trend of the operating parameter feature or the water quality feature over time obtained by time series analysis, such as gradual rise, fall or fluctuation, etc.; the correlation feature is the feature representing the correlation between the operating parameter feature and the water quality feature, such as the positive or negative correlation between the change of a certain operating parameter and a certain feature of water quality; the abnormal feature is the feature that has significant difference compared with the normal running state or water quality condition, which may indicate device failure, water quality deterioration or other abnormal conditions; the fault prompt information is the prompt information sent by the alarm module when the system detects device failure or water quality abnormality, which is used to inform the user or maintenance personnel to take corresponding processing measures, which can be presented through sound, light, text or icon on the display screen, etc.

[0068] Specifically, the data collection module is responsible for collecting the operating parameters (such as rotation speed, pressure, temperature, etc.) of each execution device in the self-service car washing machine working system and the water quality parameters (such as pH value, turbidity, residual chlorine content, etc.) in the water treatment system in real time; the diagnostic circuit module analyzes the collected operating parameters to determine whether the working state of each execution device is normal and outputs the operating parameter characteristics, and directly triggers an alarm signal when an anomaly is detected; the water quality feature acquisition module focuses on the processing and analysis of water quality parameters, and extracts key water quality features from raw data through feature extraction to provide an important basis for correlation analysis; the correlation analysis module performs in-depth correlation analysis on the operating parameter characteristics and the water quality characteristics to reveal the potential relationship and trend between the two and identify abnormal features, and outputs an abnormal signal to provide support for fault early warning; the alarm module will immediately issue a fault prompt information when receiving an alarm signal or an abnormal signal, so as to take timely measures to prevent the fault from further deteriorating.

[0069] In an embodiment, as shown in FIG. 1, the data collection module 110 includes: Figure 2

[0070] a physical sensor unit 111 including a temperature sensor, a pressure sensor, and a flow sensor;

[0071] a chemical sensor unit 112 including a pH sensor, a conductivity sensor, a dissolved oxygen sensor, and an ammonia nitrogen sensor;

[0072] a self-calibration unit 113 for periodically calibrating the physical sensor unit and the chemical sensor unit;

[0073] In this embodiment, the temperature sensor is used to measure the temperature of the water in the self-service car washing machine working system and the water treatment system; the pressure sensor is used to detect the working pressure of devices such as water pumps and nozzles; the flow sensor is used to measure the flow of water, i.e., the volume of water passing through the pipeline or device per unit time; the pH sensor is used to measure the pH value of the water; the conductivity sensor is used to measure the conductivity of the water, i.e., the water's ability to conduct electricity; the dissolved oxygen sensor is used to measure the dissolved oxygen content in the water; the ammonia nitrogen sensor is used to detect the ammonia nitrogen content in the water; calibration is a process of correcting the measured values of the sensors to ensure that their accuracy is consistent with the standard value or reference value. Since the sensors may be affected by factors such as environment, temperature, and humidity during use and thus deviate, they need to be calibrated periodically;

[0074] ​Specifically, the physical sensor unit includes temperature sensors, pressure sensors, and flow sensors, respectively used to monitor the operating temperature of each execution device of the self-service car washing machine and its changes, the working pressure of the execution devices such as water pumps and spray heads during the car washing process, and the flow of water flow during the car washing process; the chemical sensor includes a pH sensor, a conductivity sensor, a dissolved oxygen sensor, and an ammonia nitrogen sensor, wherein the pH sensor is used to measure the acidity and alkalinity of water quality, to ensure that the water for washing cars is within the appropriate pH range, to protect the vehicle surface and the car washing equipment, the conductivity sensor reflects the water conductivity, which helps to evaluate the purity of water quality, the dissolved oxygen sensor monitors the dissolved oxygen content in water, which is crucial for maintaining the normal operation of biological treatment systems (such as activated sludge method), and the ammonia nitrogen sensor is used to detect the ammonia nitrogen content in water, which is one of the important indicators for evaluating the degree of water pollution; the self-calibration unit is used to calibrate the physical sensor unit and the chemical sensor unit periodically to ensure the accuracy and reliability of the sensor data, and to eliminate the measurement errors caused by sensor aging, environmental changes and other factors.

[0075] In an embodiment, as shown in FIG. 1, the diagnostic circuit module 120 includes: Figure 3

[0076] a predictive maintenance unit 121 for predicting the future operating state of the equipment based on historical data and real-time input operating parameters of the data acquisition module, and outputting operating parameter characteristics;

[0077] a fault tree analysis unit 122 for fault analysis on the operating parameter characteristics and matching the corresponding fault path based on the analysis result;

[0078] a microprocessor 123 for receiving real-time input operating parameters of the data acquisition module and storing historical data, and sending an alarm signal when receiving the fault path information and outputting the operating parameter characteristics when receiving the operating parameter characteristics;

[0079] ​In the embodiment, the predictive maintenance is a process of using historical data and real-time data to analyze the running state of the equipment, predicting the possible future failure or performance degradation of the equipment, and formulating a maintenance plan accordingly; the historical data are the recorded data of the equipment running in the past period of time, including running parameters, failure records, maintenance records, etc.; the running parameter features are features that can represent the running state of the equipment extracted by the predictive maintenance unit by analyzing the historical data and the real-time input running parameters, including the average value, the standard deviation, the trend of change, etc., which are used to predict the future running state of the equipment; the fault tree analysis is a logical analysis method for identifying and analyzing various possible causes of equipment failure, which builds a fault tree, takes the fault as the top event, and then decomposes the intermediate events and basic events that cause the fault layer by layer, so as to find out the root cause of the fault; the fault path is the path from the top event (fault) to the basic event (fault cause) in the fault tree analysis, and each fault path represents a possible cause combination that may lead to the occurrence of the fault; the fault analysis is a process in which the fault tree analysis unit deeply analyzes the running parameter features, identifies possible fault modes, and matches the corresponding fault paths based on the analysis results; the alarm signal is a signal sent by the microprocessor when the fault tree analysis unit matches the fault path, and the alarm signal can trigger the alarm module to send a fault prompt information so that the user or the maintenance personnel can take timely measures; the output running parameter features are a process in which the microprocessor outputs the running parameter features output by the predictive maintenance unit to the correlation analysis module or other modules that need these data when receiving the running parameter features;

[0080] Specifically, the predictive maintenance unit uses the historical data and the real-time input running parameters of the data acquisition module to build a prediction model to mine the potential rules in the data, predict the future running state of the equipment and output the running parameter features; the fault tree analysis unit analyzes the running parameter features output by the predictive maintenance unit: analyzes the possible causes and paths of the fault by building a fault tree model, and matches the corresponding fault paths based on the analysis results; the microprocessor is responsible for receiving the real-time input running parameters of the data acquisition module and storing the historical data for use by the predictive maintenance unit, at the same time, when receiving the fault path information output by the fault tree analysis unit, the microprocessor will immediately send an alarm signal, and when receiving the running parameter features output by the predictive maintenance unit, the microprocessor will output the running parameter features.

[0081] In an embodiment, as shown in FIG. 1, Figure 4 The water quality feature acquisition module 130 includes:

[0082] The feature extraction unit 131 is configured to extract features from the collected water quality parameters, thereby obtaining a plurality of types of preliminary features.

[0083] The data analysis unit 132 is configured to preprocess and deeply analyze the preliminary features to obtain fluctuation range features.

[0084] The water quality state evaluation unit 133 is configured to analyze the water quality state based on the fluctuation range features and output water quality features based on the analysis result.

[0085] In this embodiment, the feature extraction is a process of extracting key information or indicators that can represent the characteristics of data from raw data. In water quality monitoring, the feature extraction unit 131 is used to extract preliminary features from collected water quality parameters such as pH value, conductivity, dissolved oxygen, etc. The preliminary features are basic features that can reflect certain aspects of the characteristics of water quality parameters after being processed by the feature extraction unit, including statistical quantities such as mean value, maximum value, minimum value, standard deviation, or feature values calculated by specific algorithms. The preprocessing is a pre-processing step of the data analysis unit 132 on the preliminary features before deep analysis, including data cleaning (removing outliers, filling missing values, etc.), data normalization (converting different dimensional data to the same dimension), etc. Deep analysis is a process of deeper analysis of preliminary features by the data analysis unit based on preprocessing, such as trend analysis, correlation analysis, clustering analysis, etc., to reveal the internal rules and abnormal changes of water quality parameters. Fluctuation range features are features obtained by deep analysis, which can reflect the fluctuation of water quality parameters, including fluctuation amplitude, fluctuation frequency, fluctuation trend, etc. Water quality state analysis is a process of analyzing the water quality state by the water quality state evaluation unit 133 based on the fluctuation range features to determine whether the water quality is in a normal state, whether there is an abnormality or potential risk. Water quality features are features obtained by the water quality state evaluation unit 133, which can comprehensively reflect the water quality status, including water quality grade, pollutant type and concentration, water quality stability, etc. The output result is a process of outputting water quality features by the water quality state evaluation unit 133 according to the analysis result, which can be presented to users or related systems in the form of reports, charts, alerts, etc. to take appropriate measures to ensure water quality safety in a timely manner.

[0086] Specifically, the feature extraction unit performs preliminary processing on the water quality parameters (such as temperature, pH value, conductivity, dissolved oxygen, ammonia nitrogen, etc.) acquired by the data acquisition module, that is, extracts several types of preliminary features representing water quality characteristics from the original data, including statistical quantities such as mean, standard deviation, maximum value, minimum value, or specific patterns identified by specific algorithms; the data analysis unit further preprocesses and deeply analyzes the preliminary features output by the feature extraction unit, the preprocessing includes data cleaning (removing outliers, filling missing values, etc.), normalization or standardization processing to ensure the accuracy and comparability of the data, and the deep analysis involves complex statistical methods, machine learning algorithms or data mining techniques to reveal the fluctuation range characteristics of the water quality parameters, that is, the change range and stability of the water quality parameters under certain conditions; the water quality state evaluation unit evaluates the water quality state based on the fluctuation range characteristics output by the data analysis unit, and outputs the evaluation results in the form of water quality characteristics.

[0087] In an embodiment, as shown in FIG. 1, the correlation analysis module 140 includes: Figure 5

[0088] a feature fusion unit 141 for fusing the operation parameter features and the water quality features to generate comprehensive features;

[0089] a trend prediction unit 142 for predicting the trends of the comprehensive features based on a pre-set time series analysis technique to obtain trend features;

[0090] a correlation mining unit 143 for mining the correlations between the operation parameter features and the water quality features based on a pre-defined data mining algorithm to obtain correlation features;

[0091] an anomaly detection unit 144 for dynamically setting an anomaly threshold according to the correlation features and the trend features, and detecting anomalies in the real-time input comprehensive features, and outputting an anomaly signal when an anomaly feature is detected;

[0092] ​In the present embodiment, feature fusion refers to the combination of features from different sources or types (in this case, operational parameter features and water quality features) into a unified comprehensive feature; comprehensive feature refers to a single representation of operational parameter features and water quality features obtained through feature fusion; time series analysis technique refers to a statistical technique for analyzing the trend of data over time, in the correlation analysis module 140, the trend prediction unit 142 uses the time series analysis technique to predict the future change of the comprehensive feature; trend feature refers to the trend information about the change of the comprehensive feature over time obtained through time series analysis; data mining algorithm refers to an algorithm for extracting useful information and patterns from a large amount of data, in the correlation analysis module 140, the correlation mining unit 143 uses a predefined data mining algorithm to mine the correlation between operational parameter features and water quality features; correlation feature refers to a feature about the relationship between operational parameter features and water quality features obtained through correlation mining, which reveals the interaction and influence between different features; abnormal threshold refers to a limit value dynamically set according to the correlation feature and the trend feature, used to judge whether the comprehensive feature is abnormal; anomaly detection refers to the process of comparing the real-time input comprehensive feature with the abnormal threshold to identify any feature deviating from the normal pattern; abnormal feature refers to the comprehensive feature identified as abnormal by the anomaly detection unit 144, which may indicate that the system has a fault, water quality deterioration or other abnormal conditions; abnormal signal refers to the signal output by the anomaly detection unit 144 when an abnormal feature is detected, which can trigger an alarm module or other response mechanism to take timely measures to handle abnormal conditions;

[0093] Specifically, the feature fusion unit fuses the operational parameter features and water quality features provided by the data acquisition module and the water quality feature acquisition module respectively, integrates the two types of features in a unified space or framework, and generates a comprehensive feature that can fully reflect the working state and water quality of the self-service car wash machine; the trend prediction unit uses a pre-set time series analysis technique to predict the trend of the fused comprehensive feature; the correlation mining unit mines the correlation between the comprehensive features based on a predefined data mining algorithm, to reveal the correlation between the operational parameter features and the water quality features, such as how the changes of certain operational parameters affect the water quality features, or how certain changes of the water quality features reflect the changes of the operational state; the anomaly detection unit dynamically sets an abnormal threshold according to the correlation feature and the trend feature, and performs anomaly detection on the real-time input comprehensive feature, and when an abnormal feature is detected, the anomaly detection unit will immediately output an abnormal signal, which helps to discover and handle abnormal conditions in the system in a timely manner and ensure stable operation of the system.

[0094] In an embodiment, the feature fusion unit 141 constructs time series data for the comprehensive feature when generating the comprehensive feature, and the trend prediction unit 142 is configured to:

[0095] The time series data in the comprehensive features are clustered and analyzed based on a preset time series clustering algorithm, and several different operation modes are identified;

[0096] Similar patterns are extracted from the time series data by a preset dynamic time warping algorithm, and trend prediction is performed to obtain trend features;

[0097] The association mining unit 143 is configured to:

[0098] Based on the results of the clustering analysis, the association between the operation parameter features and the water quality features in different operation modes is mined to extract association features;

[0099] The extracted association features are subjected to association rule mining in combination with a preset data mining algorithm, so as to identify the association rules corresponding to the association features;

[0100] In this embodiment, the time series data is a sequence of observation values arranged in time sequence, which is constructed by the feature fusion unit 141 for the comprehensive features in the feature fusion process, and records the values of a variable or a group of variables at different time points. In this embodiment, the time series data contains the changes of the operation parameter features and the water quality features over time. The time series clustering algorithm is an algorithm for grouping or clustering time series data. The trend prediction unit 142 performs clustering analysis on the time series data in the comprehensive features by using the time series clustering algorithm, so as to identify several different operation modes, which may represent the working states of the system under different conditions or the water quality change modes. The dynamic time warping algorithm is an algorithm for measuring the similarity between two time series. The trend prediction unit 142 extracts similar patterns from the time series data by using the DTW algorithm, and performs trend prediction based on the similar patterns to obtain trend features. The DTW algorithm can handle the non-linear alignment problem of time series on the time axis, and is therefore suitable for identifying similar patterns with time delay or speed change. Association rule mining is to discover the relationships or patterns between items in a data set. The association rule is a rule about the relationship between association features obtained by association rule mining. In this embodiment, the association rule describes the causal relationship or co-occurrence relationship between certain operation parameter features and water quality features under different operation modes.

[0101] Specifically, the feature fusion unit not only fuses the operation parameter features and the water quality features when generating the comprehensive features, but also constructs time series data for the comprehensive features, so that each comprehensive feature contains information in the time dimension; the trend prediction unit uses a pre-set time series clustering algorithm to perform clustering analysis on the time series data in the comprehensive features, so as to classify features with similar change patterns into a category, thereby identifying several different operation modes, and through a pre-set dynamic time warping algorithm, similar patterns are extracted from the time series data and trend prediction is performed, the dynamic time warping algorithm can handle the nonlinear change and time shift problem in the time series data, thereby more accurately predicting the future trend of the features; the association mining unit mines the association between the operation parameter features and the water quality features under different operation modes based on the results of the clustering analysis, and combines a pre-set data mining algorithm to perform association rule mining on the extracted association features, and by mining the potential rules between the association features, the causal relationship or the correlation relationship between the operation parameters and the water quality features is identified.

[0102] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0103] In an embodiment, an automatic detection and fault warning method for a self-service car washing machine is provided, which corresponds to the automatic detection and fault warning system for a self-service car washing machine in the above embodiment. The automatic detection and fault warning method for a self-service car washing machine comprises:

[0104] Real-time acquisition of operation parameters of each execution device in the working system of the self-service car washing machine and water quality parameters in the water treatment system; analysis of the operation parameters to diagnose the state of each execution device, and output of operation parameter features or issuance of an alarm signal based on the state analysis result; feature extraction and analysis of the acquired water quality parameters to obtain water quality features; correlation analysis of the operation parameter features and the water quality features to obtain trend features and association features, extraction of abnormal features based on the trend features and the association features, and output of an abnormal signal; issuance of a fault prompt information when the alarm signal or the abnormal signal is received;

[0105] Optionally, the analysis of the operation parameters to diagnose the state of each execution device, and the output of operation parameter features or the issuance of an alarm signal based on the state analysis result, comprises:

[0106] Based on historical data and the running parameters input by the data acquisition module in real time, the future running state of the equipment is predicted and the running parameter features are output; the running parameter features are analyzed for faults and the corresponding fault paths are matched based on the analysis results; the running parameters input by the data acquisition module in real time and the historical data are received, and when the fault path information is received, an alarm signal is sent out, and when the running parameter features are received, the running parameter features are output;

[0107] Optionally, the collected water quality parameters are subjected to feature extraction and analysis to obtain water quality features, including:

[0108] The collected water quality parameters are subjected to feature extraction to obtain preliminary features of several types; the preliminary features are preprocessed and subjected to in-depth analysis to obtain fluctuation range features; the water quality state is analyzed based on the fluctuation range features, and the water quality features are output based on the analysis results;

[0109] For specific limitations of the automatic detection and fault early warning method for the self-service car washer, reference can be made to the limitations of the automatic detection and fault early warning system for the self-service car washer in the foregoing, which will not be repeated here. Each module in the automatic detection and fault early warning system for the self-service car washer can be realized by software, hardware, or a combination thereof, in whole or in part. Each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0110] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An automatic detection and fault early warning system for a self-service car wash machine, characterized in that: include: The data acquisition module is used to collect the operating parameters of each device in the self-service car wash system and the water quality parameters in the water treatment system in real time. The diagnostic circuit module is used to analyze operating parameters to diagnose the status of each actuator, and output operating parameter characteristics or issue alarm signals based on the status analysis results; The water quality feature acquisition module is used to extract and analyze the features of the collected water quality parameters to obtain water quality features; The correlation analysis module is used to perform correlation analysis on operating parameter characteristics and water quality characteristics to obtain trend characteristics and correlation characteristics, extract abnormal characteristics based on trend characteristics and correlation characteristics, and output abnormal signals. The alarm module is used to issue fault prompt information when an alarm signal or abnormal signal is received; The diagnostic circuit module includes: The predictive maintenance unit is used to predict the future operating status of the equipment and output operating parameter characteristics based on historical data and the operating parameters input in real time by the data acquisition module. The fault tree analysis unit is used to perform fault analysis on the characteristics of operating parameters and match the corresponding fault paths based on the analysis results. The microprocessor is used to receive real-time input operating parameters from the data acquisition module and store historical data, and to issue an alarm signal when receiving fault path information and to output operating parameter characteristics when receiving operating parameter characteristics. The correlation analysis module includes: The feature fusion unit is used to fuse operating parameter features and water quality features to generate comprehensive features; The trend prediction unit is used to predict trends in comprehensive features based on pre-set time series analysis techniques in order to obtain trend characteristics. The correlation mining unit is used to perform correlation mining on comprehensive features based on predefined data mining algorithms to obtain correlation features between operating parameters and water quality characteristics. The anomaly detection unit is used to dynamically set the anomaly threshold based on correlation features and trend features, and to perform anomaly detection on the comprehensive features input in real time. When an anomaly feature is detected, an anomaly signal is output. The system is specifically designed for self-service car wash machines. Its operating parameters include water pump pressure, nozzle spray angle, and motor speed. Water quality parameters include pH value, conductivity, dissolved oxygen, and ammonia nitrogen content. The water quality characteristic acquisition module includes: The feature extraction unit is used to extract features from the collected water quality parameters to obtain several types of preliminary features; The data analysis unit is used to preprocess the initial features and perform in-depth analysis to obtain the fluctuation range characteristics; The water quality status assessment unit is used to analyze the water quality status based on the fluctuation range characteristics and output water quality characteristics based on the analysis results.

2. The automatic detection and fault early warning system for a self-service car wash machine according to claim 1, characterized in that: The data acquisition module includes: A physical sensor unit, comprising a temperature sensor, a pressure sensor, and a flow sensor; A chemical sensor unit, wherein the chemical sensors include a pH sensor, a conductivity sensor, a dissolved oxygen sensor, and an ammonia nitrogen sensor; A self-calibration unit is used to periodically calibrate the physical sensor unit and the chemical sensor unit.

3. The automatic detection and fault early warning system for a self-service car wash machine according to claim 1, characterized in that: When generating comprehensive features, the feature fusion unit constructs time-series data for the comprehensive features. The trend prediction unit is used for: Based on a pre-set time series clustering algorithm, cluster analysis is performed on the time series data in the comprehensive features, and several different operating modes are identified. The algorithm uses a pre-set dynamic time warping algorithm to extract similar patterns from time series data and perform trend prediction to obtain trend characteristics. The association mining unit is used for: Based on the results of cluster analysis, the correlation between operating parameter characteristics and water quality characteristics under different operating modes is explored to extract correlation features; By combining pre-set data mining algorithms with the extracted association features, association rules are mined to identify the association rules corresponding to the association features.

4. An automatic detection and fault warning method for a self-service car wash machine, used in the automatic detection and fault warning system for a self-service car wash machine as described in any one of claims 1-3, characterized in that: include: Real-time collection of operating parameters of various executing devices in the self-service car wash system and water quality parameters in the water treatment system; Analyze operating parameters to diagnose the status of each actuator, and output operating parameter characteristics or issue alarm signals based on the status analysis results; extract and analyze features of collected water quality parameters to obtain water quality characteristics; The system performs correlation analysis on operating parameter characteristics and water quality characteristics to obtain trend characteristics and correlation characteristics. Based on the trend characteristics and correlation characteristics, it extracts abnormal characteristics and outputs abnormal signals. When an alarm signal or abnormal signal is received, it issues a fault prompt message. The analysis of operating parameters to diagnose the status of each execution device, and the output of operating parameter characteristics or the issuance of alarm signals based on the status analysis results, include: Based on historical data and real-time operating parameters input by the data acquisition module, the system predicts the future operating status of the equipment and outputs operating parameter characteristics; it performs fault analysis on the operating parameter characteristics and matches the corresponding fault path based on the analysis results; it receives real-time operating parameters input by the data acquisition module and stores historical data, and issues an alarm signal when fault path information is received and outputs operating parameter characteristics when operating parameter characteristics are received. The process of extracting and analyzing features from the collected water quality parameters to obtain water quality characteristics includes: Feature extraction is performed on the collected water quality parameters to obtain several types of preliminary features; the preliminary features are preprocessed and analyzed in depth to obtain fluctuation range features; the water quality status is analyzed based on the fluctuation range features, and water quality features are output based on the analysis results.

Images