Intelligent operation and maintenance management method and platform for self-service water adding machine

Abstract

The invention discloses an intelligent operation and maintenance management method and platform for a self-service water adding machine, and relates to the related field of intelligent operation and maintenance. The method comprises the following steps: determining a sensor module and a plurality of execution modules; associating the plurality of sensors for performing anomaly detection on the execution modules and the sensor module, and performing anomaly detection analysis to generate a plurality of associated sensor sets and a plurality of anomaly detection models; collecting a real-time sensing data set, and performing division according to the plurality of associated sensor sets to generate a plurality of associated sensing data sets; inputting a plurality of anomaly detection models to carry out anomaly analysis on the plurality of execution modules, positioning an abnormal execution module, carrying out operation and maintenance mode decision, and generating an abnormal operation and maintenance mode; and performing operation and maintenance management according to the exception execution module and the exception operation and maintenance mode. The technical problem of low operation and maintenance management efficiency caused by lack of intelligent means in operation and maintenance management of the existing self-service water adding machine is solved, and the technical effect of intelligent and efficient operation and maintenance management of the self-service water adding machine is achieved.

Description

Technical Field

[0001] The present application relates to fields related to intelligent operation and maintenance, and in particular to an intelligent operation and maintenance management method and platform for a self-service water filling machine. Background Art

[0002] A self-service water dispenser is a self-service device that is usually installed in public places or specific facilities for users to use. In the existing self-service water dispenser operation and maintenance management method, it is usually necessary to manually check the operating status of the equipment regularly, record and analyze various parameters of the equipment, and determine whether the equipment has faults or potential risks. This method is not only inefficient, but also difficult to detect and handle equipment failures in a timely manner, resulting in high operation and maintenance costs and insufficient equipment reliability.

[0003] In the current relevant technologies, the operation and maintenance management of self-service water filling machines lacks intelligent means, which leads to the technical problem of low efficiency of operation and maintenance management. Summary of the invention

[0004] The present application provides a method and platform for intelligent operation and maintenance management of self-service water-filling machines. By determining a sensor module and multiple execution modules in a target self-service water-filling machine, an abnormality detection association between the sensor and the execution module is established, and multiple associated sensor sets and anomaly detection models are generated. The sensor module is used to collect real-time sensor data sets, and the data sets are divided according to the associated sensor sets to generate multiple associated sensor data sets. The associated sensor data sets are input into the anomaly detection model for anomaly analysis, the abnormal execution module is located, and an operation and maintenance mode decision is made. The corresponding abnormal operation and maintenance mode is generated, and operation and maintenance management is performed according to the abnormal execution module and the abnormal operation and maintenance mode. Technical means such as the above achieve the technical effect of realizing intelligent and efficient operation and maintenance management of self-service water-filling machines.

[0005] The present application provides an intelligent operation and maintenance management method for a self-service water filling machine, including:

[0006] Determine the sensor module and multiple execution modules in the target self-service water filling machine; associate the multiple execution modules with the sensors for abnormality detection of the sensor module and perform abnormality detection analysis to generate multiple associated sensor sets and multiple abnormality detection models; collect real-time sensor data sets through the sensor module in the target self-service water filling machine, and divide them according to the multiple associated sensor sets to generate multiple associated sensor data sets; input the multiple associated sensor data sets into the multiple abnormality detection models to perform abnormality analysis on the multiple execution modules, locate the abnormal execution modules, and make operation and maintenance mode decisions to generate corresponding abnormal operation and maintenance modes; perform operation and maintenance management according to the abnormal execution modules and the abnormal operation and maintenance modes.

[0007] In a possible implementation, the multiple execution modules are associated with sensors for abnormality detection of the sensor module and abnormality detection analysis is performed to generate multiple associated sensor sets and multiple abnormality detection models, and the following processing is performed:

[0008] Acquire a water flow circulation network in the target self-service water filling machine; determine the execution relationship between the water flow circulation network and the multiple execution modules, and establish an execution path, wherein the nodes of the execution path are the multiple execution modules; acquire the multi-source sensor type in the sensor module, determine the associated sensor type of the multiple execution modules according to the execution path, and generate the multiple associated sensor sets; calibrate the sensor data mapping of the multiple associated sensor sets according to the execution path, and train and construct the multiple anomaly detection models.

[0009] In a possible implementation, the execution relationship between the water flow network and the multiple execution modules is determined, and an execution path is established, wherein the nodes of the execution path are the multiple execution modules, and the following processing is performed:

[0010] Arrange the multiple execution modules in an execution order according to the execution relationship to generate an execution sequence, wherein each sequence node in the execution sequence carries an execution operation identifier; obtain the initialization water source state of the water flow circulation network; analyze the change of the water source state based on the initialization water source state and the execution operation identifier, generate the post-execution water source state corresponding to each sequence node, and establish a water source state sequence; generate the execution path based on the water source state sequence.

[0011] In a possible implementation, the sensor data mapping of the plurality of associated sensor sets is calibrated according to the execution path, and the plurality of anomaly detection models are trained and constructed, and the following processing is performed:

[0012] Determine the sensing accuracy of each sensor in the sensor module; combine the water source state sequence with the multiple associated sensor sets to constrain the sensing range and generate multiple calibrated sensor data sets; use the multiple calibrated sensor data sets as calibrated sensor data in a non-fault mode to train the multiple anomaly detection models.

[0013] In a possible implementation, the multiple associated sensor data sets are input into the multiple anomaly detection models to perform anomaly analysis on the multiple execution modules, locate the abnormal execution modules, make an operation and maintenance mode decision, generate a corresponding abnormal operation and maintenance mode, and perform the following processing:

[0014] The execution modules with abnormalities are identified through the multiple abnormality detection models, the abnormal execution modules are generated, and the corresponding abnormal indicators are obtained; the operation and maintenance mode decision is made in combination with the abnormal execution modules and the abnormal indicators, and the abnormal operation and maintenance mode is generated, wherein the operation and maintenance mode includes a first operation and maintenance mode and a second operation and maintenance mode, the first operation and maintenance mode is an operation and maintenance mode in an emergency shutdown state, and the second operation and maintenance mode is an operation and maintenance mode in a device operating state, wherein the operation and maintenance priority of the first operation and maintenance mode is greater than that of the second operation and maintenance mode.

[0015] In a possible implementation, the abnormal execution module and the abnormal indicator are combined to make an operation and maintenance mode decision, generate the abnormal operation and maintenance mode, and perform the following processing:

[0016] For the multiple execution modules, multiple historical operation and maintenance record data sets are collected; based on the multiple historical operation and maintenance record data sets, an operation and maintenance decision maker is trained with operation and maintenance decision features, wherein the operation and maintenance decision features include fault type and fault severity; the abnormal execution module and the abnormal indicator are input into the operation and maintenance decision maker to perform operation and maintenance mode analysis to generate the abnormal operation and maintenance mode.

[0017] In a possible implementation, operation and maintenance management is performed according to the abnormal execution module and the abnormal operation and maintenance mode, and the following processing is performed:

[0018] If the abnormal operation and maintenance mode is the first operation and maintenance mode, an emergency control instruction is generated to shut down the target self-service water filling machine, and an emergency reminder message is generated and pushed to the operation and maintenance management terminal together with the abnormal execution module; if the abnormal operation and maintenance mode is the second operation and maintenance mode, the self-decision optimization database is called to optimize the control parameters of the abnormal execution module, and an operation and maintenance reminder message is generated and pushed to the operation and maintenance management terminal together with the abnormal execution module; wherein the self-decision optimization database contains the objective function for reducing the degree of fault impact corresponding to the multiple execution modules under the second operation and maintenance mode, the function value of the objective function is the degree of fault impact, and the independent variable is the control parameter.

[0019] In a possible implementation, the following processing is performed:

[0020] Connect to the cloud database to collect the historical operation record data set of the target self-service water dispenser; analyze the operation rules of the water dispenser with the historical operation record data set to generate a water adding strategy; and perform water adding scheduling with the water adding strategy.

[0021] The present application also provides a self-service water filling machine intelligent operation and maintenance management platform, including:

[0022] A module determination unit, the module determination unit is used to determine the sensor module and multiple execution modules in the target self-service water filling machine; a sensor association unit, the sensor association unit is used to associate the multiple execution modules with the sensors for abnormality detection of the sensor module and perform abnormality detection analysis to generate multiple associated sensor sets and multiple abnormality detection models; a real-time sensor data acquisition unit, the real-time sensor data acquisition unit is used to collect real-time sensor data sets through the sensor modules in the target self-service water filling machine, and divide them according to the multiple associated sensor sets to generate multiple associated sensor data sets; an abnormality analysis unit, the abnormality analysis unit is used to input the multiple associated sensor data sets into the multiple abnormality detection models to perform abnormality analysis on the multiple execution modules, locate the abnormal execution modules, and make operation and maintenance mode decisions to generate corresponding abnormal operation and maintenance modes; an operation and maintenance management unit, the operation and maintenance management unit is used to perform operation and maintenance management according to the abnormal execution modules and the abnormal operation and maintenance modes.

[0023] The present application proposes an intelligent operation and maintenance management method and platform for self-service water-filling machines. First, the sensor module and multiple execution modules in the target self-service water-filling machine are determined. Then, the sensors for abnormal detection of the multiple execution modules and the sensor modules are associated and anomaly detection analysis is performed to generate multiple associated sensor sets and multiple anomaly detection models. Then, real-time sensor data sets are collected through the sensor module in the target self-service water-filling machine, and divided according to multiple associated sensor sets to generate multiple associated sensor data sets. The multiple associated sensor data sets are then input into multiple anomaly detection models to perform anomaly analysis on multiple execution modules, locate abnormal execution modules, make operation and maintenance mode decisions, generate corresponding abnormal operation and maintenance modes, and finally perform operation and maintenance management according to the abnormal execution modules and abnormal operation and maintenance modes, thereby achieving the technical effect of realizing intelligent and efficient operation and maintenance management of self-service water-filling machines. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention are briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0025] Figure 1 A flowchart of an intelligent operation and maintenance management method for a self-service water filling machine provided in an embodiment of the present application.

[0026] Figure 2 A structural schematic diagram of an intelligent operation and maintenance management platform for a self-service water filling machine provided in an embodiment of the present application.

[0027] Explanation of the reference numerals: module determination unit 10 , sensor association unit 20 , real-time sensor data acquisition unit 30 , abnormality analysis unit 40 , operation and maintenance management unit 50 . DETAILED DESCRIPTION

[0028] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0030] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0031] The present application embodiment provides a method for intelligent operation and maintenance management of a self-service water filling machine, such as Figure 1 As shown, the method includes:

[0032] Step S100, determine the sensor module and multiple execution modules in the target self-service water filling machine. Specifically, conduct a comprehensive inspection and identification of the target self-service water filling machine, and record all built-in sensor modules and execution modules. Among them, the sensor module is a device or device that can sense the specified measured value and convert it into a usable signal according to a certain rule, including water level sensors, flow sensors, pressure sensors, etc., which are used to monitor various state parameters inside the water filling machine in real time. The execution module is a device that receives control signals and works according to its control requirements, including water pumps, solenoid valves, etc., which are responsible for performing corresponding operations according to sensor data, such as adding water, heating, cooling, etc. Finally, create a detailed list of the names, models, locations and functions of all sensor modules and execution modules.

[0033] Step S200, associate the multiple execution modules with the sensors for abnormality detection of the sensor module and perform abnormality detection analysis to generate multiple associated sensor sets and multiple abnormality detection models. Specifically, based on the established list, analyze which sensor modules each execution module is directly or indirectly associated with. For example, the working state of a water pump is closely related to the data of a water level sensor and a flow sensor. Using machine learning methods, an abnormality detection model is constructed for each execution module. These models can learn normal working modes based on historical data and identify abnormal situations that deviate from normal modes. According to the results of the association analysis, the related sensor modules are combined into associated sensor sets, each set corresponding to a specific execution module, and are used together to monitor the working state of the execution module.

[0034] In a possible implementation, the multiple execution modules are associated with the sensors for abnormal detection of the sensor module and abnormal detection analysis is performed to generate multiple associated sensor sets and multiple abnormal detection models. Step S200 further includes step S210, obtaining the water flow circulation network in the target self-service water filling machine. Specifically, the technician conducts a detailed survey of the target self-service water filling machine to understand its internal water flow circulation structure, including the layout and connection method of components such as water tanks, water pipes, and water pumps. Based on the survey results, a water flow circulation network diagram in the target self-service water filling machine is drawn, and this network diagram shows the connection relationship between each component and the flow direction of the water flow. While drawing the network diagram, the key parameters of each component are recorded, such as the capacity of the water tank, the power of the water pump, the diameter of the water pipe, etc. Step S220, determining the execution relationship between the water flow circulation network and the multiple execution modules, and establishing an execution path, wherein the nodes of the execution path are the multiple execution modules. Specifically, according to the design document or survey results of the target self-service water filling machine, the functions and effects of each execution module (such as a water pump, a solenoid valve, etc.) are determined. According to the water flow network diagram, determine the execution relationship between the various execution modules, that is, how they work together to complete the water adding task. Based on the execution relationship, draw an execution path diagram. This diagram uses the execution modules as nodes and the execution relationships between them as edges to show the execution process of the water adding task.

[0035] Step S230, obtaining the multi-source sensor types in the sensor module, determining the associated sensor types of the multiple execution modules according to the execution path, and generating the multiple associated sensor sets. Specifically, the types and positions of all sensor modules in the target self-service water filling machine are listed, such as water level sensors, flow sensors, etc. According to the execution path diagram, determine what types of sensor data each execution module needs to monitor its working status. Combine the sensor types required by each execution module to form an associated sensor set, which is used for subsequent data collection and abnormality analysis. Step S240, calibrate the sensor data mapping of the multiple associated sensor sets according to the execution path, and train and construct the multiple abnormality detection models. Specifically, according to the execution path diagram, calibrate and map the sensor data in each associated sensor set, that is, convert the sensor data into parameter values ​​or indicators related to the working status of the execution module. Collect relevant sensor data from the historical operation records of the target self-service water filling machine as sample data for training the abnormality detection model, use machine learning methods to learn the training data of each associated sensor set, and construct an abnormality detection model. These models can identify abnormal data that deviates from the normal mode, thereby locating the abnormal execution module. The trained anomaly detection model is verified and tuned using the validation data set to ensure its accuracy and reliability. This implementation method obtains the water flow network in the target self-service water dispenser, determines the execution relationship between the execution modules, and establishes the execution path. By associating sensors with the execution modules, a set of associated sensors is generated, ensuring that the working status of each execution module can be effectively monitored and analyzed, thereby improving the efficiency and accuracy of operation and maintenance.

[0036] In a possible implementation, the execution relationship between the water flow circulation network and the multiple execution modules is determined, and an execution path is established, wherein the nodes of the execution path are the multiple execution modules, and step S220 further includes step S221, arranging the multiple execution modules in the execution order according to the execution relationship to generate an execution sequence, wherein each sequence node in the execution sequence carries an execution operation identifier. Specifically, based on the execution relationship, combined with the water flow direction and the role of each module in controlling the water flow, the order of each execution module in executing the water adding task is determined. The determined execution order is expressed in the form of a sequence, each sequence node corresponds to an execution module, and carries the execution operation identifier of the module, including the name, number and brief description of the execution action of the module. Step S222, obtaining the initialization water source state of the water flow circulation network. Specifically, before the water adding task starts, the initialization water source state of the water flow circulation network is determined by measuring and recording the initial water level, flow rate and other parameters of components such as water tanks and water pipes. Step S223, analyze the change of the water source state with the initialization water source state and the execution operation identifier, generate the water source state after execution corresponding to each sequence node, and establish a water source state sequence. Specifically, based on the initialization water source state and the execution sequence, simulate the execution process of the water adding task. Predict and calculate the water source state after each execution module executes the operation. For each sequence node, calculate the water source state after execution (the state of the water level, flow rate and other parameters of each component in the water flow network after the execution module executes the operation) according to its corresponding execution module and execution operation identifier, and update it to the water source state sequence. Step S224, generate the execution path with the water source state sequence. Specifically, based on the water source state sequence, construct a complete execution path, which is represented in the form of sequence nodes, and each node corresponds to an execution module and its water source state after execution. This implementation method generates an execution path that reflects the execution process of the water-adding task and the role of each execution module by analyzing the execution relationship between each execution module inside the target self-service water-adding machine and the initialization water source status of the water flow network. Based on the execution path, the sensor module and the execution module can be more accurately associated to generate an associated sensor set and anomaly detection model, which improves the accuracy and timeliness of anomaly detection and reduces the risk of equipment failure.

[0037] In a possible implementation, the multiple associated sensor sets are calibrated for sensor data mapping according to the execution path, and the multiple anomaly detection models are trained and constructed. Step S240 further includes step S241, determining the sensing accuracy of each sensor in the sensor module. Specifically, the specifications and performance parameters of all sensors in the target self-service water dispenser are collected, including sensing accuracy, measurement range, response time, etc. The sensing accuracy of each sensor is evaluated according to the collected specification parameters. Sensing accuracy refers to the degree of deviation between the sensor measurement value and the true value, expressed as a percentage or error range. Step S242, combining the water source state sequence with the multiple associated sensor sets to constrain the sensing range, and generate multiple calibrated sensor data sets. Specifically, based on the generated water source state sequence and the determined associated sensor set, combined with the sensor measurement range and measurement accuracy, the sensing range of each sensor during the execution of the water adding task is determined. According to the determined sensing range, the data collected by the sensor is constrained, including eliminating data beyond the measurement range, correcting or marking abnormal data, etc. The sensor data that has been constrained is sorted according to the water source state sequence and the associated sensor set to generate multiple calibrated sensor data sets. Each data set corresponds to a specific execution module or execution path node, and contains all valid data collected by the sensor of the node during the execution of the task. Step S243, the multiple calibrated sensor data sets are used as calibrated sensor data in non-fault mode to train the multiple anomaly detection models. Specifically, the multiple calibrated sensor data sets generated in step S242 are used as input and trained using a neural network model algorithm. During the training process, the model learns the sensor data features under normal conditions and constructs a model structure for identifying abnormal conditions. After the training is completed, the anomaly detection performance and accuracy of the model are evaluated by testing using a part of the calibrated sensor data sets that are not involved in the training. According to the verification results, the model is adjusted and optimized to improve its anomaly detection capability and generalization performance. This implementation method ensures that the data input into the anomaly detection model is accurate and reliable by determining the sensing accuracy and performing sensing range constraints, thereby improving the accuracy of anomaly detection.

[0038] Step S300, collects real-time sensor data sets through the sensor modules in the target self-service water dispenser, and divides them according to the multiple associated sensor sets to generate multiple associated sensor data sets. Specifically, all sensor modules in the target self-service water dispenser are started to collect various state parameter data in real time. According to the associated sensor sets, the collected real-time sensor data sets are divided to form multiple associated sensor data sets, each of which corresponds to an execution module.

[0039] Step S400, input the multiple associated sensor data sets into the multiple anomaly detection models to perform anomaly analysis on the multiple execution modules, locate the abnormal execution modules, make operation and maintenance mode decisions, and generate corresponding abnormal operation and maintenance modes. Specifically, each associated sensor data set is input into the corresponding anomaly detection model to perform real-time anomaly analysis, and the model outputs one or more abnormal indicators to determine whether there is an abnormality in the execution module. According to the results of the abnormal analysis, the execution module with the abnormality is located, and the corresponding abnormal operation and maintenance mode is formulated for the abnormal execution module, including strategies such as immediate shutdown for maintenance, reduction of workload, and adjustment of working parameters to ensure the safe operation of the self-service water filling machine.

[0040] In a possible implementation, the multiple associated sensor data sets are input into the multiple anomaly detection models to perform anomaly analysis on the multiple execution modules, locate the abnormal execution modules, make operation and maintenance mode decisions, and generate corresponding abnormal operation and maintenance modes. Step S400 further includes step S410, identifying the execution modules with abnormalities through the multiple anomaly detection models, generating the abnormal execution modules, and obtaining corresponding abnormal indicators. Specifically, multiple associated sensor data sets (such as pressure, flow and other sensor data) are input into a pre-trained anomaly detection model, and the anomaly detection model performs pattern recognition on the input data to determine which data deviates from the normal range or historical trend, outputs the recognition results, and indicates which execution modules (such as water pumps, solenoid valves, etc.) are abnormal. For the identified abnormal execution modules, specific abnormal indicators are extracted, such as abnormal water pressure values, water flow speeds, etc. Step S420, combining the abnormal execution module and the abnormal index to make an operation and maintenance mode decision, and generate the abnormal operation and maintenance mode, wherein the operation and maintenance mode includes a first operation and maintenance mode and a second operation and maintenance mode, wherein the first operation and maintenance mode is an operation and maintenance mode in an emergency shutdown state, and the second operation and maintenance mode is an operation and maintenance mode in an equipment running state, wherein the operation and maintenance priority of the first operation and maintenance mode is greater than that of the second operation and maintenance mode. Specifically, according to the type of the abnormal execution module and the severity of the abnormal index, the impact of the abnormality on the overall operation of the equipment is evaluated. If the abnormality is serious and may cause equipment damage or safety hazards (such as water pollution caused by filter element failure), the first operation and maintenance mode (operation and maintenance mode in an emergency shutdown state) is selected, and the equipment operation is stopped immediately and professional maintenance is waited for. If the abnormality is minor and does not affect the basic operation of the equipment (such as slight water pressure fluctuations), the second operation and maintenance mode (operation and maintenance mode in an equipment running state) is selected to allow the equipment to continue to operate and perform maintenance without interrupting the service. According to the evaluation results, specific operation and maintenance instructions and modes are generated, including the scheduling of operation and maintenance personnel, required spare parts, and estimated repair time. This implementation method selects different operation and maintenance modes according to the severity of the abnormality, which not only ensures the safe shutdown of the equipment in an emergency, but also allows maintenance without affecting basic services, reducing losses caused by equipment downtime.

[0041] In a possible implementation, the operation and maintenance mode decision is made in combination with the abnormal execution module and the abnormal indicator to generate the abnormal operation and maintenance mode. Step S420 further includes step S421, collecting multiple historical operation and maintenance record data sets for the multiple execution modules. Specifically, data is collected from the historical operation and maintenance records of the target self-service water filling machine. These data sets contain various operation and maintenance events that have occurred in the past, including but not limited to the fault type, fault occurrence time, fault handling process, fault severity assessment, and measures taken to finally resolve the fault, etc. These data provide practical experience about equipment failure modes and operation and maintenance strategies. Step S422, based on the multiple historical operation and maintenance record data sets, the operation and maintenance decision maker is trained with operation and maintenance decision features, wherein the operation and maintenance decision features include fault type and fault severity. Specifically, the operation and maintenance decision maker is trained using the collected historical operation and maintenance record data sets. The operation and maintenance decision maker is a machine learning model that learns how to make effective operation and maintenance decisions by analyzing the operation and maintenance decision features in historical operation and maintenance data. In this process, the model will identify the association between different fault types (such as water pump failure, solenoid valve failure, etc.) and severity (such as minor, medium, and severe), as well as the correspondence between these faults and specific operation and maintenance measures. Step S423, the abnormal execution module and the abnormal index are input into the operation and maintenance decision maker for operation and maintenance mode analysis to generate the abnormal operation and maintenance mode. Specifically, after the abnormal execution module is detected and the corresponding abnormal index is obtained, this information is input into the trained operation and maintenance decision maker. The operation and maintenance decision maker automatically analyzes and determines the operation and maintenance mode to be adopted based on the input abnormal features and the historical operation and maintenance mode it has learned, including emergency shutdown of the equipment to avoid further damage (first operation and maintenance mode), or remote monitoring or dispatching maintenance personnel to handle on-site when the equipment can still operate safely (second operation and maintenance mode). This implementation method trains the operation and maintenance decision maker based on historical operation and maintenance data, and can automatically generate abnormal operation and maintenance modes according to fault types and severity, which speeds up fault response and improves operation and maintenance efficiency.

[0042] Step S500, perform operation and maintenance management according to the abnormal execution module and the abnormal operation and maintenance mode. Specifically, according to the abnormal operation and maintenance mode, issue corresponding operation and maintenance instructions to the target self-service water filling machine, including starting backup equipment, adjusting working parameters, triggering alarm signals, etc. During the execution of the operation and maintenance instructions, continuously monitor the operating status of the target self-service water filling machine and collect feedback data. Record the key information in the operation and maintenance process, including abnormal location, operation and maintenance mode, operation and maintenance effect, etc., and generate a detailed operation and maintenance report for subsequent analysis and improvement. The embodiment of the present application determines the sensor module and multiple execution modules in the target self-service water filling machine, establishes anomaly detection associations between the sensors and the execution modules, and generates multiple associated sensor sets and anomaly detection models. The sensor module is used to collect real-time sensor data sets, and the data sets are divided according to the associated sensor sets to generate multiple associated sensor data sets. The associated sensor data sets are input into the anomaly detection model for anomaly analysis, the abnormal execution module is located, and an operation and maintenance mode decision is made to generate a corresponding abnormal operation and maintenance mode. Operation and maintenance management is performed according to the abnormal execution module and the abnormal operation and maintenance mode, and other technical means are used to achieve the technical effect of realizing intelligent and efficient operation and maintenance management of the self-service water filling machine.

[0043] In a possible implementation, operation and maintenance management is performed according to the abnormal execution module and the abnormal operation and maintenance mode, and step S500 further includes step S510. If the abnormal operation and maintenance mode is the first operation and maintenance mode, an emergency control instruction is generated to close the target self-service water filling machine, and an emergency reminder message is generated and pushed to the operation and maintenance management terminal together with the abnormal execution module. Specifically, when it is judged that the abnormal operation and maintenance mode is the first operation and maintenance mode, it means that there is a serious fault or safety hazard in the self-service water filling machine, and immediate measures need to be taken to prevent the fault from expanding or causing more serious consequences. At this time, an emergency control instruction is generated, which is used to immediately close or isolate the faulty execution module and shut down the entire self-service water filling machine to ensure safety. At the same time, an emergency reminder message is generated, which contains key information such as a specific description of the fault, the location of the abnormal execution module, and the content of the emergency control instruction. This information is pushed to the operation and maintenance management terminal in real time together with the identification of the target self-service water filling machine (such as equipment number, location information, etc.) and the information of the abnormal execution module. The operation and maintenance management terminal is a mobile device, computer or dedicated operation and maintenance management system of the operation and maintenance personnel, which is used to ensure that the operation and maintenance personnel can quickly receive information and take corresponding actions. Step S520, if the abnormal operation and maintenance mode is the second operation and maintenance mode, the self-decision optimization database is called to optimize the control parameters of the abnormal execution module, and the operation and maintenance reminder information is generated and pushed to the operation and maintenance management terminal together with the abnormal execution module, wherein the self-decision optimization database contains the objective function corresponding to the plurality of execution modules in the second operation and maintenance mode for reducing the degree of influence of the fault, the function value of the objective function is the degree of influence of the fault, and the independent variable is the control parameter. Specifically, when it is judged that the abnormal operation and maintenance mode is the second operation and maintenance mode, it means that although the fault in the self-service water filling machine exists, it has not reached the level of emergency shutdown, and can still be repaired or optimized in the running state of the equipment. At this time, the self-decision optimization database is called, which contains the objective functions and control parameters of the plurality of execution modules in the second operation and maintenance mode. Among them, the objective function is used to quantify the degree of influence of the fault, such as the reduction of production efficiency and the increase of energy consumption caused by the fault, and the control parameter is a parameter that can be adjusted to optimize the performance of the equipment or reduce the impact of the fault. Based on the current fault situation, the control parameters are automatically adjusted to minimize the value of the objective function, that is, to reduce the impact of the fault. While the control parameters are optimized, an operation and maintenance reminder message is generated, which contains key information such as the specific description of the fault, the optimized control parameters, and the recommended operation and maintenance measures. This information will also be pushed to the operation and maintenance management terminal together with the identification of the target self-service water dispenser and the information of the abnormal execution module.This implementation method, in the first operation and maintenance mode, quickly responds to serious faults by generating emergency control instructions and pushing emergency reminder information, preventing the fault from expanding or causing more serious consequences, and ensuring the safety of equipment and personnel; in the second operation and maintenance mode, it automatically adjusts control parameters and optimizes equipment performance to solve problems while the equipment is running, avoiding unnecessary downtime and improving operation and maintenance efficiency. By using a self-decision-making optimization database and objective function, the accuracy and efficiency of operation and maintenance operations are improved.

[0044] In a possible implementation, the method further includes step S600, connecting to a cloud database to collect a historical operation record data set of the target self-service water filling machine. Specifically, the target self-service water filling machine establishes a connection with the cloud database through a secure and stable network connection method (such as Wi-Fi, 4G / 5G, etc.). Once the connection is established, the target self-service water filling machine collects its historical operation record data set, including the running time, water addition amount, energy consumption, fault records, sensor readings and other information of the water filling machine, and these data are stored in the form of time series. The collected data is transmitted to the cloud database in an encrypted manner. The cloud database is a platform for centralized storage and management of large amounts of data, located on the Internet, and can be accessed through the network. Step S700, using the historical operation record data set to analyze the operating rules of the water filling machine and generate a water addition strategy. Specifically, the collected historical operation record data set is preprocessed, including data cleaning, missing value processing, outlier detection, etc., to ensure the accuracy and consistency of the data. Using data mining technology, the historical operation record data set is deeply analyzed to reveal the operation law of the water adding machine, including the change trend and correlation of parameters such as water addition amount and energy consumption of the water adding machine in different time periods and different environmental conditions. Based on the analyzed operation law, a set of optimized water adding strategies is generated, including adjusting the water addition amount in different time periods, optimizing energy consumption, predicting and preventing potential faults, etc., to improve the operation efficiency of the water adding machine, reduce energy consumption and failure rate. Step S800, water adding scheduling is performed with the water adding strategy. Specifically, the generated water adding strategy is applied to the actual operation of the target self-service water adding machine, and the parameters such as water addition amount and operation time of the water adding machine are adjusted and controlled in real time. While implementing the water adding strategy, the operation status and parameter changes of the target self-service water adding machine are monitored in real time through the sensor module, and any abnormal situation is discovered and handled in time to ensure the stable operation of the water adding machine. This implementation method can reasonably arrange the operation time and water addition amount of the water adding machine, as well as control the energy consumption of the water adding machine by analyzing the operation law of the water adding machine and generating an optimized water adding strategy, thereby improving the operation efficiency of the water adding machine and reducing energy consumption.

[0045] In the above, refer to Figure 1 A self-service water filling machine intelligent operation and maintenance management method according to an embodiment of the present invention is described in detail. Figure 2An intelligent operation and maintenance management platform for a self-service water filling machine according to an embodiment of the present invention is described.

[0046] According to an embodiment of the present invention, an intelligent operation and maintenance management platform for a self-service water dispenser is used to solve the technical problem that the existing operation and maintenance management of self-service water dispensers lacks intelligent means, resulting in low efficiency of operation and maintenance management, so as to achieve the technical effect of realizing intelligent and efficient operation and maintenance management of self-service water dispensers. An intelligent operation and maintenance management platform for a self-service water dispenser includes: a module determination unit 10, a sensor association unit 20, a real-time sensor data acquisition unit 30, an abnormality analysis unit 40, and an operation and maintenance management unit 50.

[0047] The module determination unit 10 is used to determine the sensor module and multiple execution modules in the target self-service water filling machine; the sensor association unit 20 is used to associate the multiple execution modules with the sensors for abnormality detection of the sensor modules and perform abnormality detection analysis to generate multiple associated sensor sets and multiple abnormality detection models; the real-time sensor data acquisition unit 30 is used to collect real-time sensor data sets through the sensor modules in the target self-service water filling machine, and divide them according to the multiple associated sensor sets to generate multiple associated sensor data sets; the abnormality analysis unit 40 is used to input the multiple associated sensor data sets into the multiple abnormality detection models to perform abnormality analysis on the multiple execution modules, locate the abnormal execution modules, and make operation and maintenance mode decisions to generate corresponding abnormal operation and maintenance modes; the operation and maintenance management unit 50 is used to perform operation and maintenance management according to the abnormal execution modules and the abnormal operation and maintenance modes.

[0048] The specific configuration of the sensor association unit 20 will be described in detail below. As described above, the multiple execution modules are associated with the sensors for abnormality detection of the sensor module and abnormality detection analysis is performed to generate multiple associated sensor sets and multiple abnormality detection models. The sensor association unit 20 may further include: a water flow network acquisition unit for acquiring the water flow network in the target self-service water dispenser; an execution path establishment unit for determining the execution relationship between the water flow network and the multiple execution modules, and establishing an execution path, wherein the nodes of the execution path are the multiple execution modules; an associated sensor type determination unit for acquiring the multi-source sensor type in the sensor module, determining the associated sensor type of the multiple execution modules according to the execution path, and generating the multiple associated sensor sets; a calibration sensor data mapping unit for calibrating sensor data mapping of the multiple associated sensor sets according to the execution path, and training and constructing the multiple abnormality detection models.

[0049] Among them, the execution relationship between the water flow circulation network and the multiple execution modules is determined, and an execution path is established, wherein the nodes of the execution path are the multiple execution modules, and the execution path establishment unit may further include: an execution sequence generation unit is used to arrange the multiple execution modules in an execution order according to the execution relationship, and generate an execution sequence, wherein each sequence node in the execution sequence carries an execution operation identifier; an initialization water source state acquisition unit is used to obtain the initialization water source state of the water flow circulation network; a water source state sequence establishment unit is used to analyze the change of the water source state with the initialization water source state and the execution operation identifier, generate the post-execution water source state corresponding to each sequence node, and establish a water source state sequence; an execution path generation unit is used to generate the execution path with the water source state sequence.

[0050] Among them, according to the execution path, the calibration sensor data mapping is performed on the multiple associated sensor sets, and the multiple anomaly detection models are trained and constructed. The calibration sensor data mapping unit may further include: a sensing accuracy determination unit for determining the sensing accuracy of each sensor in the sensor module; a sensing range constraint unit for combining the water source state sequence with the multiple associated sensor sets to perform sensing range constraints and generate multiple calibrated sensor data sets; an anomaly detection model training unit for training the multiple anomaly detection models using the multiple calibrated sensor data sets as calibrated sensor data under non-fault mode.

[0051] The specific configuration of the abnormality analysis unit 40 will be described in detail below. As described above, the multiple associated sensor data sets are input into the multiple abnormality detection models to perform abnormality analysis on the multiple execution modules, locate the abnormal execution modules, and make operation and maintenance mode decisions to generate corresponding abnormal operation and maintenance modes. The abnormality analysis unit 40 may further include: an execution module abnormality identification unit for identifying abnormal execution modules through the multiple abnormality detection models, generating the abnormal execution modules, and obtaining corresponding abnormal indicators; an operation and maintenance mode decision unit for making operation and maintenance mode decisions in combination with the abnormal execution modules and the abnormal indicators to generate the abnormal operation and maintenance mode, wherein the operation and maintenance mode includes a first operation and maintenance mode and a second operation and maintenance mode, wherein the first operation and maintenance mode is an operation and maintenance mode in an emergency shutdown state, and the second operation and maintenance mode is an operation and maintenance mode in an equipment operation state, wherein the operation and maintenance priority of the first operation and maintenance mode is greater than that of the second operation and maintenance mode.

[0052] Among them, an operation and maintenance mode decision is made in combination with the abnormal execution module and the abnormal indicator to generate the abnormal operation and maintenance mode. The operation and maintenance mode decision unit may further include: a historical operation and maintenance record data set acquisition unit is used to collect multiple historical operation and maintenance record data sets for the multiple execution modules; an operation and maintenance decision maker training unit is used to train an operation and maintenance decision maker with operation and maintenance decision features based on the multiple historical operation and maintenance record data sets, wherein the operation and maintenance decision features include fault type and fault severity; an operation and maintenance mode analysis unit is used to input the abnormal execution module and the abnormal indicator into the operation and maintenance decision maker to perform operation and maintenance mode analysis to generate the abnormal operation and maintenance mode.

[0053] The specific configuration of the operation and maintenance management unit 50 will be described in detail below. As described above, the operation and maintenance management is performed according to the abnormal execution module and the abnormal operation and maintenance mode, and the operation and maintenance management unit 50 may further include: a first operation and maintenance management unit is used to generate an emergency control instruction to shut down the target self-service water filling machine if the abnormal operation and maintenance mode is the first operation and maintenance mode, and generate an emergency reminder message and push it to the operation and maintenance management terminal together with the abnormal execution module; a second operation and maintenance management unit is used to call the self-decision optimization database to optimize the control parameters of the abnormal execution module if the abnormal operation and maintenance mode is the second operation and maintenance mode, and generate an operation and maintenance reminder message and push it to the operation and maintenance management terminal together with the abnormal execution module, wherein the self-decision optimization database contains the objective function for reducing the degree of fault impact corresponding to the multiple execution modules in the second operation and maintenance mode, the function value of the objective function is the degree of fault impact, and the independent variable is the control parameter.

[0054] Among them, the platform may further include: a historical operation record data set collection unit used to connect to a cloud database to collect the historical operation record data set of the target self-service water filling machine; an operation rule analysis unit used to analyze the operation rules of the water filling machine using the historical operation record data set to generate a water adding strategy; and a water adding scheduling unit used to perform water adding scheduling using the water adding strategy.

[0055] An intelligent operation and maintenance management platform for a self-service water filling machine provided in an embodiment of the present invention can execute an intelligent operation and maintenance management method for a self-service water filling machine provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0056] Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0057] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A self-service water filling machine intelligent operation and maintenance management method, characterized in that: include: Determine the sensor module and multiple execution modules in the target self-service water dispenser; Associating the multiple execution modules with the sensors of the sensor module for abnormality detection and performing abnormality detection analysis to generate multiple associated sensor sets and multiple abnormality detection models; A real-time sensor data set is collected through a sensor module in the target self-service water dispenser, and divided according to the plurality of associated sensor sets to generate a plurality of associated sensor data sets; Input the multiple associated sensor data sets into the multiple anomaly detection models to perform anomaly analysis on the multiple execution modules, locate the abnormal execution modules, make operation and maintenance mode decisions, and generate corresponding abnormal operation and maintenance modes; Operation and maintenance management is performed according to the abnormal execution module and the abnormal operation and maintenance mode.

2. The intelligent operation and maintenance management method of a self-service water filling machine according to claim 1, characterized in that: Associating the multiple execution modules with the sensors of the sensor module for abnormality detection and performing abnormality detection analysis to generate multiple associated sensor sets and multiple abnormality detection models, including: Obtaining a water flow network in the target self-service water dispenser; Determine the execution relationship between the water flow network and the multiple execution modules, and establish an execution path, wherein the nodes of the execution path are the multiple execution modules; Acquire the multi-source sensor types in the sensor module, determine the associated sensor types of the multiple execution modules according to the execution path, and generate the multiple associated sensor sets; Calibrate sensor data mapping for the multiple associated sensor sets according to the execution path, and train and construct the multiple anomaly detection models.

3. The intelligent operation and maintenance management method of a self-service water filling machine according to claim 2, characterized in that: Determine the execution relationship between the water flow network and the multiple execution modules, and establish an execution path, wherein the nodes of the execution path are the multiple execution modules, including: Arranging the multiple execution modules in an execution order according to the execution relationship to generate an execution sequence, wherein each sequence node in the execution sequence carries an execution operation identifier; Obtaining the initialization water source state of the water flow circulation network; Performing a change analysis of the water source state based on the initialization water source state and the execution operation identifier, generating a post-execution water source state corresponding to each sequence node, and establishing a water source state sequence; The execution path is generated according to the water source state sequence.

4. A self-service water filling machine intelligent operation and maintenance management method as claimed in claim 3, characterized in that: Calibrate sensor data mapping for the plurality of associated sensor sets according to the execution path, and train and construct the plurality of anomaly detection models, including: Determining the sensing accuracy of each sensor in the sensor module; Combining the water source state sequence with the plurality of associated sensor sets to constrain sensing ranges, generating a plurality of calibrated sensing data sets; The multiple anomaly detection models are trained using the multiple calibration sensor data sets as calibration sensor data in a non-fault mode.

5. The intelligent operation and maintenance management method of a self-service water filling machine according to claim 1, characterized in that: Inputting the multiple associated sensor data sets into the multiple anomaly detection models to perform anomaly analysis on the multiple execution modules, locate the abnormal execution modules, and make an operation and maintenance mode decision to generate a corresponding abnormal operation and maintenance mode, including: Identify the execution modules with abnormalities through the multiple abnormality detection models, generate the abnormal execution modules, and obtain corresponding abnormal indicators; An operation and maintenance mode decision is made in combination with the abnormal execution module and the abnormal indicator to generate the abnormal operation and maintenance mode, wherein the operation and maintenance mode includes a first operation and maintenance mode and a second operation and maintenance mode, wherein the first operation and maintenance mode is an operation and maintenance mode in an emergency shutdown state, and the second operation and maintenance mode is an operation and maintenance mode in an equipment operation state, wherein the operation and maintenance priority of the first operation and maintenance mode is greater than that of the second operation and maintenance mode.

6. A self-service water filling machine intelligent operation and maintenance management method as claimed in claim 5, characterized in that: Combining the abnormal execution module and the abnormal indicator to make an operation and maintenance mode decision and generate the abnormal operation and maintenance mode includes: For the multiple execution modules, collecting multiple historical operation and maintenance record data sets; Based on the multiple historical operation and maintenance record data sets, training an operation and maintenance decision maker with operation and maintenance decision features, wherein the operation and maintenance decision features include fault type and fault severity; The abnormal execution module and the abnormal index are input into the operation and maintenance decision maker to perform operation and maintenance mode analysis to generate the abnormal operation and maintenance mode.

7. A self-service water filling machine intelligent operation and maintenance management method as claimed in claim 6, characterized in that: Performing operation and maintenance management according to the abnormal execution module and the abnormal operation and maintenance mode includes: If the abnormal operation and maintenance mode is the first operation and maintenance mode, an emergency control instruction is generated to shut down the target self-service water dispenser, and an emergency reminder message is generated and pushed to the operation and maintenance management terminal together with the abnormal execution module; If the abnormal operation and maintenance mode is the second operation and maintenance mode, the self-decision optimization database is called to optimize the control parameters of the abnormal execution module, and the operation and maintenance reminder information is generated and pushed to the operation and maintenance management terminal together with the abnormal execution module; The self-decision optimization database includes the objective function for reducing the impact of faults corresponding to the multiple execution modules in the second operation and maintenance mode, the function value of the objective function is the impact of faults, and the independent variable is the control parameter.

8. The intelligent operation and maintenance management method of a self-service water filling machine according to claim 1, characterized in that: Also includes: Connect to the cloud database to collect the historical operation record data set of the target self-service water filling machine; Analyze the operation rules of the water adding machine using the historical operation record data set to generate a water adding strategy; Water addition scheduling is performed according to the water addition strategy.

9. A self-service water filling machine intelligent operation and maintenance management platform, characterized in that: The platform is used to implement the intelligent operation and maintenance management method of a self-service water filling machine according to any one of claims 1 to 8, and the platform includes: A module determination unit, the module determination unit is used to determine a sensor module and a plurality of execution modules in a target self-service water dispenser; A sensor association unit, the sensor association unit is used to associate the multiple execution modules with the sensors of the sensor module for abnormality detection and perform abnormality detection analysis to generate multiple associated sensor sets and multiple abnormality detection models; A real-time sensor data acquisition unit, the real-time sensor data acquisition unit is used to collect a real-time sensor data set through a sensor module in a target self-service water dispenser, and divide the data into multiple associated sensor sets to generate multiple associated sensor data sets; An abnormality analysis unit, the abnormality analysis unit is used to input the multiple associated sensor data sets into the multiple abnormality detection models to perform abnormality analysis on the multiple execution modules, locate the abnormal execution modules, and make an operation and maintenance mode decision to generate a corresponding abnormal operation and maintenance mode; An operation and maintenance management unit, wherein the operation and maintenance management unit is used to perform operation and maintenance management according to the abnormal execution module and the abnormal operation and maintenance mode.

Images