Remote fault maintenance method for coffee machine

Abstract

The invention provides a remote fault maintenance method for a coffee machine, and relates to the technical field of coffee machine maintenance. The remote fault maintenance method for the coffee machine comprises the following steps: S1, module division and fault signal determination; s2, collecting test data, and carrying out fault analysis training by utilizing machine self-learning; s3, enabling a remote diagnosis function by the user; s4, fault signal detection is carried out on the fault model; s5, the user carries out self-recovery according to the diagnosis report; and S6, processing when the repair scheme is invalid. According to the invention, when the coffee machine of the user has a fault, the user can actively apply for a remote diagnosis service, the coffee machine can automatically upload historical whole machine operation data and a fault signal to the server, and the server rapidly analyzes the data through machine learning, generates a fault diagnosis report and provides a detailed fault reason and a repair scheme.

Description

Technical Field

[0001] The invention relates to the technical field of coffee machine maintenance, and in particular to a remote fault maintenance method for a coffee machine. Background Art

[0002] Commercial coffee machines are primarily designed to be used in coffee shops, restaurants, hotels, and other places. Although both commercial and home coffee machines are designed to make coffee, there are still big differences between them. Commercial coffee machines need to be used frequently, so they are usually of higher quality and durability, and can withstand higher frequency of use and more rigorous environments. Commercial coffee machines usually have a larger capacity than home coffee machines. Because commercial coffee machines need to be able to make a large amount of coffee, they usually have a larger water and bean storage capacity. Commercial coffee machines need to be able to make a large amount of coffee in a short period of time.

[0003] With the widespread use of coffee machines in business and homes, the requirements for their reliability and timely troubleshooting are becoming higher and higher. Traditional coffee machine fault diagnosis often relies on manual experience, and there are problems such as inaccurate diagnosis and untimely treatment. At the same time, the lack of effective prediction of faults and remote assistance functions brings many inconveniences to users. Therefore, an intelligent coffee machine fault diagnosis and processing system is needed to solve these problems. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a remote fault maintenance method for a coffee machine, which solves the defects and deficiencies in the prior art.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for remote fault maintenance of a coffee machine, the method comprising the following steps:

[0008] S1. Module division and fault signal determination;

[0009] S2. Collect test data and use machine self-learning to conduct fault analysis training;

[0010] S3, the user turns on the remote diagnosis function;

[0011] S4, fault model performs fault signal detection;

[0012] S5. The user performs self-recovery according to the diagnostic report;

[0013] S6. What to do when the repair plan is invalid.

[0014] Preferably, in step 1, the coffee machine is divided into modules: coffee boiler, steam boiler, extraction BLDC motor, milk pump BLDC motor, BLDC Hall sensor reading, pill feeding, grinding motor, grinding AC motor, left grinding BLDC motor, right grinding BLDC motor, communication interface, box bin detection control and milk circuit.

[0015] Preferably, step 1 also includes fault state judgment: each module contains stateful elements and stateless elements. The stateful elements directly judge whether the element return signal is normal through the returned response signal; the stateless elements need to be judged whether they are normal through logical analysis; for example, the CBL heating wire in the coffee boiler is a stateless element, which only responds to the heating command, and the drive control cannot perceive its current state. If the CBL heating wire is abnormal, it is necessary to perceive the current temperature through the CBL left boiler temperature sensor. Through temperature logic analysis, after heating for a certain period of time, the reading of the CBL left boiler temperature sensor should be within a certain value range, and then it is judged that the CBL heating wire is abnormal; and the CBL left boiler temperature sensor is a stateful element. When it is damaged, it will be unable to read data; if an abnormality occurs, the reading is wrong, and then it is judged that the CBL left boiler temperature sensor is abnormal, and the fault logic is determined through module division, and the corresponding repair manual is compiled.

[0016] Preferably, in step 2, the specific contents are as follows:

[0017] 1) Through a large number of functional tests during the testing phase, a wide range of data including various parameters during machine operation (such as temperature, pressure, current, voltage, etc.), operation records (such as startup time, operation mode, operation frequency, etc.), real-time data and historical data when a fault occurs, etc. are collected, and the collected data is cleaned to remove noise data and abnormal values; for example, if there are occasional erroneous readings from sensors, they need to be identified and processed;

[0018] 2) In the fault analysis of the coffee machine, a machine self-learning method based on deep learning was adopted. First, a large amount of operating data of the coffee machine in normal operation and various fault states was collected, including but not limited to temperature data (such as coffee furnace temperature, milk circuit temperature, etc.), motor operation data (such as extraction motor, grinding motor speed, current, etc.), operation time data (such as the time interval between each coffee making, the duration of different operation steps), etc.;

[0019] 3) These data are divided into training sets and test sets. A deep neural network (DNN) is selected as the machine learning algorithm. The network structure includes an input layer, multiple hidden layers, and an output layer. The input layer receives the above-collected coffee machine operation data, and performs feature extraction and nonlinear transformation through the hidden layer. The output layer classifies the fault type.

[0020] 4) In the training phase, the training set data is input into the DNN, and the weights and biases of the network are continuously adjusted through the back-propagation algorithm, so that the network can accurately predict the fault type based on the input operation data. For example, when the temperature of the coffee furnace continues to rise abnormally and the motor current is unstable, the trained DNN can accurately determine that the heating module of the coffee furnace is faulty;

[0021] 5) After training and verification, the model is applied to actual coffee machine fault analysis. During the operation of the coffee machine, the real-time collected data is input into the trained DNN model. The model can quickly evaluate the current status of the machine. When it is determined that there may be a fault, it will issue an alarm in time and provide possible causes of the fault and maintenance suggestions.

[0022] Preferably, in step 3, the specific contents are as follows:

[0023] 1) After the user turns on the remote diagnosis function of the coffee machine, the system automatically obtains the current status data and fault signals of the coffee machine. These data include the operating data of each component mentioned above and the fault-related data. The obtained data is first saved locally in the application to ensure the integrity and accessibility of the data;

[0024] 2) The application establishes a connection with the server through 4G / WiFi / Ethernet. During the connection establishment process, the system will perform a network check to ensure the stability and security of data transmission. After completing the network check, the locally stored fault data and historical operation data will be uploaded to the server.

[0025] Preferably, in step 4, the trained machine learning model is deployed to the actual machine system, machine data is collected in real time and input into the model for fault analysis, a fault diagnosis report is generated based on the uploaded whole machine status data and fault signals, and a remote fault repair plan and maintenance guidance are provided.

[0026] Preferably, in step 5, after receiving the diagnostic result on the application returned by the server, the user performs troubleshooting operations on his own according to the provided troubleshooting suggestions. For example, if the diagnostic report indicates that an abnormal operation function of the coffee machine is due to a software setting problem caused by improper user operation, the user can follow the operating instructions in the report and reset the relevant parameters through the operation interface of the coffee machine to restore the normal operation of the coffee machine. This user self-recovery function improves the timeliness of fault handling and reduces dependence on professional maintenance personnel.

[0027] Preferably, in step 6, the specific contents are as follows:

[0028] 1) After the user or the system executes the fault repair plan, the system will monitor and evaluate the repair effect. If the coffee machine fault still exists after a certain period of time or a certain number of operations, the repair plan is judged to be invalid;

[0029] 2) If the repair plan is ineffective, the system will provide maintenance personnel with a maintenance preparation plan based on the fault prediction report. The plan takes into account the previous fault diagnosis results and possible causes of the fault, and lists the maintenance materials that may be needed when the maintenance personnel perform on-site maintenance, such as specific models of motors, sensors, circuit boards and other parts, as well as various maintenance tools. The maintenance personnel will check the plan in advance and prepare the required materials before performing on-site maintenance, thus avoiding maintenance delays due to incomplete maintenance materials and improving maintenance efficiency.

[0030] (III) Beneficial effects

[0031] The present invention provides a method for remote fault maintenance of a coffee machine, which has the following beneficial effects:

[0032] 1. In the present invention, when a user's coffee machine encounters a fault, the user can actively apply for remote diagnosis service. The coffee machine can automatically upload historical whole machine operation data and fault signals to the server. The server quickly analyzes the data through machine learning and generates a fault diagnosis report, providing detailed fault causes and repair plans.

[0033] 2. The present invention automatically pushes maintenance suggestions, including required spare parts and operating instructions, to help users or maintenance personnel deal with problems efficiently, and realizes intelligent diagnosis, prediction, processing and maintenance support for coffee machine failures, greatly improving the reliability and maintainability of the coffee machine, and reducing the user's usage cost and maintenance difficulty. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] Example:

[0037] like Figure 1 As shown, an embodiment of the present invention provides a method for remote fault maintenance of a coffee machine, the method comprising the following steps:

[0038] S1. Module division and fault signal determination;

[0039] 1) Divide the coffee machine into modules: coffee boiler, steam boiler, extraction BLDC motor, milk pump BLDC motor, BLDC Hall sensor reading, pill feeding, grinding motor, grinding AC motor, left grinding BLDC motor, right grinding BLDC motor, communication interface, box bin detection control and milk circuit;

[0040] 2) It also includes fault status judgment: each module contains stateful components and stateless components. The stateful components directly judge whether the component return signal is normal through the returned response signal; the stateless components need to be judged through logical analysis whether they are normal; for example, the CBL heating wire in the coffee boiler is a stateless component, which only responds to the heating command, and the drive control cannot perceive its current state. If the CBL heating wire is abnormal, it is necessary to sense the current temperature through the CBL left boiler temperature sensor. Through temperature logic analysis, after heating for a certain period of time, the reading of the CBL left boiler temperature sensor should be within a certain value range, and then it is judged that the CBL heating wire is abnormal; and the CBL left boiler temperature sensor is a stateful component. When it is damaged, it will not be able to read data; if an abnormality occurs, the reading is wrong, and then it is judged that the CBL left boiler temperature sensor is abnormal. The fault logic is determined through module division, and the corresponding repair manual is sorted out;

[0041] S2. Collect test data and use machine self-learning to conduct fault analysis training;

[0042] The specific contents are as follows:

[0043] 1) Through a large number of functional tests during the testing phase, a wide range of data including various parameters during machine operation (such as temperature, pressure, current, voltage, etc.), operation records (such as startup time, operation mode, operation frequency, etc.), real-time data and historical data when a fault occurs, etc. are collected, and the collected data is cleaned to remove noise data and abnormal values; for example, if there are occasional erroneous readings from sensors, they need to be identified and processed;

[0044] 2) In the fault analysis of the coffee machine, a machine self-learning method based on deep learning was adopted. First, a large amount of operating data of the coffee machine in normal operation and various fault states was collected, including but not limited to temperature data (such as coffee furnace temperature, milk circuit temperature, etc.), motor operation data (such as extraction motor, grinding motor speed, current, etc.), operation time data (such as the time interval between each coffee making, the duration of different operation steps), etc.;

[0045] 3) These data are divided into training sets and test sets. A deep neural network (DNN) is selected as the machine learning algorithm. The network structure includes an input layer, multiple hidden layers, and an output layer. The input layer receives the above-collected coffee machine operation data, and performs feature extraction and nonlinear transformation through the hidden layer. The output layer classifies the fault type.

[0046] 4) In the training phase, the training set data is input into the DNN, and the weights and biases of the network are continuously adjusted through the back-propagation algorithm, so that the network can accurately predict the fault type based on the input operation data. For example, when the temperature of the coffee furnace continues to rise abnormally and the motor current is unstable, the trained DNN can accurately determine that the heating module of the coffee furnace is faulty;

[0047] 5) After training and verification, the model is applied to actual coffee machine fault analysis. During the operation of the coffee machine, the real-time collected data is input into the trained DNN model. The model can quickly evaluate the current state of the machine. When it is determined that there may be a fault, it will issue an alarm in time and provide possible fault causes and repair suggestions;

[0048] S3, the user turns on the remote diagnosis function;

[0049] The specific contents are as follows:

[0050] 1) After the user turns on the remote diagnosis function of the coffee machine, the system automatically obtains the current status data and fault signals of the coffee machine. These data include the operating data of each component mentioned above and the fault-related data. The obtained data is first saved locally in the application to ensure the integrity and accessibility of the data;

[0051] 2) The application establishes a connection with the server through 4G / WiFi / Ethernet. During the connection establishment process, the system will perform network verification to ensure the stability and security of data transmission. After the network verification is completed, the locally stored fault data and historical operation data will be uploaded to the server;

[0052] S4. The fault model detects fault signals, deploys the trained machine learning model to the actual machine system, collects machine data in real time and inputs it into the model for fault analysis, generates fault diagnosis reports based on the uploaded machine status data and fault signals, and provides remote fault repair solutions and maintenance guidance;

[0053] S5. The user performs self-recovery according to the diagnostic report. After receiving the diagnostic results on the application returned by the server, the user performs troubleshooting operations according to the provided troubleshooting suggestions. For example, if the diagnostic report indicates that an abnormal operation function of the coffee machine is due to a software setting problem caused by improper user operation, the user can follow the operation guide in the report and reset the relevant parameters through the operation interface of the coffee machine to restore the normal operation of the coffee machine. This user self-recovery function improves the timeliness of fault handling and reduces the dependence on professional maintenance personnel;

[0054] S6. What to do when the repair plan is invalid. The details are as follows:

[0055] 1) After the user or the system executes the fault repair plan, the system will monitor and evaluate the repair effect. If the coffee machine fault still exists after a certain period of time or a certain number of operations, the repair plan is judged to be invalid;

[0056] 2) If the repair plan is ineffective, the system will provide maintenance personnel with a maintenance preparation plan based on the fault prediction report. The plan takes into account the previous fault diagnosis results and possible causes of the fault, and lists the maintenance materials that may be needed when the maintenance personnel perform on-site maintenance, such as specific models of motors, sensors, circuit boards and other parts, as well as various maintenance tools. The maintenance personnel will check the plan in advance and prepare the required materials before performing on-site maintenance, thus avoiding maintenance delays due to incomplete maintenance materials and improving maintenance efficiency.

[0057] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprising a reference structure" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0058] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A coffee machine remote fault maintenance method, characterized in that: The method comprises the following steps: S1. Module division and fault signal determination; S2. Collect test data and use machine self-learning to perform fault analysis training; S3, the user turns on the remote diagnosis function; S4, fault model performs fault signal detection; S5. The user performs self-recovery according to the diagnostic report; S6. What to do when the repair plan is invalid.

2. A coffee machine remote fault maintenance method according to claim 1, characterized in that: In the step 1, the coffee machine is divided into modules: coffee boiler, steam boiler, extraction BLDC motor, milk pump BLDC motor, BLDC Hall sensor reading, pill feeding, grinding motor, grinding AC motor, left grinding BLDC motor, right grinding BLDC motor, communication interface, box bin detection control and milk circuit.

3. A coffee machine remote fault maintenance method according to claim 2, characterized in that: The step 1 also includes fault status judgment: each module contains stateful components and stateless components. The stateful components directly judge whether the component return signal is normal through the returned response signal; the stateless components need to be judged whether they are normal through logical analysis; for example, the CBL heating wire in the coffee boiler is a stateless component, which only responds to the heating command, and the drive control cannot sense its current state. If the CBL heating wire is abnormal, it is necessary to sense the current temperature through the CBL left boiler temperature sensor. Through temperature logic analysis, after heating for a certain period of time, the reading of the CBL left boiler temperature sensor should be within a certain value range, and then it is judged that the CBL heating wire is abnormal; The CBL left boiler temperature sensor is a stateful component, and when it is damaged, the data cannot be read; If an abnormality occurs, the reading is wrong, and it is judged that there is an abnormality in the CBL left boiler temperature sensor. The fault logic is determined through module division, and the corresponding repair manual is compiled.

4. A coffee machine remote fault maintenance method according to claim 1, characterized in that: In step 2, the specific contents are as follows: 1) Through a large number of functional tests during the testing phase, a wide range of parameters, operation records, real-time data when faults occur, and historical data are collected, and the collected data is cleaned to remove noise data and abnormal values; for example, if there are occasional erroneous readings from sensors, they need to be identified and processed; 2) In the fault analysis of the coffee machine, a machine self-learning method based on deep learning was adopted. First, a large amount of operating data of the coffee machine in normal operation and various fault states was collected, including but not limited to temperature data, motor operation data, and operation time data; 3) These data are divided into training sets and test sets. A deep neural network is selected as the machine learning algorithm. The network structure includes an input layer, multiple hidden layers and an output layer. The input layer receives the above-collected coffee machine operation data, and the hidden layer performs feature extraction and nonlinear transformation. The output layer classifies the fault type. 4) In the training phase, the training set data is input into the DNN, and the weights and biases of the network are continuously adjusted through the back-propagation algorithm, so that the network can accurately predict the fault type based on the input operation data. For example, when the temperature of the coffee furnace continues to rise abnormally and the motor current is unstable, the trained DNN can accurately determine that the heating module of the coffee furnace is faulty; 5) After training and verification, the model is applied to actual coffee machine fault analysis. During the operation of the coffee machine, the real-time collected data is input into the trained DNN model. The model can quickly evaluate the current status of the machine. When it is determined that there may be a fault, it will issue an alarm in time and provide possible causes of the fault and maintenance suggestions.

5. The method for remote fault maintenance of a coffee machine according to claim 1, characterized in that: In step 3, the specific contents are as follows: 1) After the user turns on the remote diagnosis function of the coffee machine, the system automatically obtains the current status data and fault signals of the coffee machine. These data include the operating data of each component mentioned above and the fault-related data. The obtained data is first saved locally in the application to ensure the integrity and accessibility of the data; 2) The application establishes a connection with the server through 4G / WiFi / Ethernet. During the connection establishment process, the system will perform a network check to ensure the stability and security of data transmission. After completing the network check, the locally stored fault data and historical operation data will be uploaded to the server.

6. A coffee machine remote fault maintenance method according to claim 1, characterized in that: In step 4, the trained machine learning model is deployed to the actual machine system, machine data is collected in real time and input into the model for fault analysis, a fault diagnosis report is generated based on the uploaded machine status data and fault signals, and a remote fault repair plan and maintenance guidance are provided.

7. The method for remote fault maintenance of a coffee machine according to claim 1, characterized in that: In step 5, after receiving the diagnostic result on the application returned by the server, the user can perform troubleshooting operations on his own according to the troubleshooting suggestions provided. For example, if the diagnostic report indicates that an abnormal operation function of the coffee machine is due to a software setting problem caused by improper user operation, the user can follow the operating instructions in the report and reset the relevant parameters through the operation interface of the coffee machine to restore the normal operation of the coffee machine. This user self-recovery function improves the timeliness of fault handling and reduces dependence on professional maintenance personnel.

8. The method for remote fault maintenance of a coffee machine according to claim 1, characterized in that: In step 6, the specific contents are as follows: 1) After the user or the system executes the fault repair plan, the system will monitor and evaluate the repair effect. If the coffee machine fault still exists after a certain period of time or a certain number of operations, the repair plan is judged to be invalid; 2) If the repair plan is ineffective, the system will provide maintenance personnel with a maintenance preparation plan based on the fault prediction report. The plan takes into account the previous fault diagnosis results and possible causes of the fault, and lists the maintenance materials that may be needed when the maintenance personnel perform on-site maintenance, such as specific models of motors, sensors, circuit boards and other parts, as well as various maintenance tools. The maintenance personnel will check the plan in advance and prepare the required materials before performing on-site maintenance.

Images