WO2023098372A1 - 自我诊断方法和无负压叠压供水设备 - Google Patents

自我诊断方法和无负压叠压供水设备 Download PDF

Info

Publication number
WO2023098372A1
WO2023098372A1 PCT/CN2022/128821 CN2022128821W WO2023098372A1 WO 2023098372 A1 WO2023098372 A1 WO 2023098372A1 CN 2022128821 W CN2022128821 W CN 2022128821W WO 2023098372 A1 WO2023098372 A1 WO 2023098372A1
Authority
WO
WIPO (PCT)
Prior art keywords
measurement data
preset
fault
input
water pump
Prior art date
Application number
PCT/CN2022/128821
Other languages
English (en)
French (fr)
Inventor
张秀芬
徐荣榕
周梦雪
Original Assignee
无锡汇田水务科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 无锡汇田水务科技有限公司 filed Critical 无锡汇田水务科技有限公司
Publication of WO2023098372A1 publication Critical patent/WO2023098372A1/zh

Links

Images

Classifications

    • E—FIXED CONSTRUCTIONS
    • E03—WATER SUPPLY; SEWERAGE
    • E03B—INSTALLATIONS OR METHODS FOR OBTAINING, COLLECTING, OR DISTRIBUTING WATER
    • E03B7/00—Water main or service pipe systems
    • E03B7/07—Arrangement of devices, e.g. filters, flow controls, measuring devices, siphons or valves, in the pipe systems
    • E03B7/078—Combined units with different devices; Arrangement of different devices with respect to each other
    • E—FIXED CONSTRUCTIONS
    • E03—WATER SUPPLY; SEWERAGE
    • E03B—INSTALLATIONS OR METHODS FOR OBTAINING, COLLECTING, OR DISTRIBUTING WATER
    • E03B11/00—Arrangements or adaptations of tanks for water supply
    • E—FIXED CONSTRUCTIONS
    • E03—WATER SUPPLY; SEWERAGE
    • E03B—INSTALLATIONS OR METHODS FOR OBTAINING, COLLECTING, OR DISTRIBUTING WATER
    • E03B7/00—Water main or service pipe systems
    • E03B7/09—Component parts or accessories
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model

Definitions

  • the application relates to the technical field of water supply equipment, in particular to a self-diagnosis method and non-negative pressure laminated water supply equipment.
  • the purpose of this application is to provide a self-diagnosis method and a non-negative pressure stacked water supply equipment, so that the non-negative pressure stacked water supply equipment can self-diagnose whether there is a fault, and reduce the probability of misjudgment.
  • the present application provides a self-diagnosis method for providing a self-diagnosis function for non-negative pressure laminated water supply equipment, the method comprising:
  • the multiple operating parameters include base vibration parameters, pipeline pressure parameters, bolt loosening parameters, soft joint use parameters, gasket use parameters, water pump At least two of temperature parameters, water pump vibration parameters, water pump speed parameters, motor temperature parameters, motor current parameters and motor voltage parameters;
  • the measurement data of multiple operating parameters are used as the first input of the fault detection model, and the fault detection model outputs the The predicted fault type and predicted similarity corresponding to the first input; wherein, the fault detection model is used to compare the first input with each fault data in the fault database to obtain the first input and each The similarity of the fault data, the highest similarity among the multiple similarities corresponding to the first input is used as the predicted similarity corresponding to the first input, and the fault data with the highest similarity to the first input is used The fault type is used as the predicted fault type corresponding to the first input, and the predicted fault type and the predicted similarity corresponding to the first input are output;
  • the beneficial effect of this technical solution is that: use two-stage detection process to judge whether there is a fault, when the first stage detects that a fault may occur, it is not directly judged as a fault, but enters the second stage of fault detection, When a possible failure is also detected in the second stage, it is determined that the non-negative pressure stacked water supply equipment is faulty. Therefore, the obtained fault detection results are highly reliable, avoiding frequent misjudgments and affecting the non-negative pressure stacked water supply normal use of the device.
  • multiple sensors are used to obtain measurement data of multiple operating parameters, and it is detected whether the measurement data of each operating parameter is within its corresponding preset range.
  • the measurement data of multiple operating parameters are input into the fault detection model, and the fault
  • the detection model determines the closest fault type of the non-negative pressure stacked water supply equipment in the current operation process as the predicted fault type, and the fault detection model also gives the similarity between the input data and the predicted fault type as the predicted similarity, by comparing The size of the predicted similarity and the preset similarity threshold is used to judge whether there is a fault. Obviously, the higher the similarity, the more likely the non-negative pressure superimposed water supply equipment has a fault corresponding to the predicted fault type.
  • the measurement data of multiple operating parameters is used as the input data of the fault detection model, taking into account the correlation between multiple operating parameters, and comprehensively judges the measurement data of multiple operating parameters to avoid the numerical fluctuation of a single operating parameter causing Misjudgment, but compare multiple operating parameters as a whole with multiple fault data stored in the fault database one by one, find out the fault data with the highest similarity, and use the fault type corresponding to the fault data as a prediction Fault types further improve the accuracy of fault detection results.
  • the acquisition process of the preset range corresponding to each of the operating parameters is as follows:
  • a preset range including the average value is obtained, and a ratio of a difference between a maximum value and a minimum value of the preset range to the average value is a preset constant corresponding to the operating parameter.
  • the beneficial effect of this technical solution is that: when the non-negative pressure laminated water supply equipment is in normal operation, the measurement data at multiple preset times are recorded and the average value is calculated, and the obtained average value can be used as the operating parameter in normal operation
  • the reference value in the process on this basis, set an appropriate fluctuation range to obtain a preset range including the average value, and the obtained preset range has a high reference value.
  • the values of different operating parameters vary greatly, and may not be an order of magnitude. Therefore, set the same or different preset constants for each operating parameter, and then set the ratio of the difference between the maximum value and the minimum value of the preset range to the average value. is the preset constant corresponding to the operating parameter, thereby limiting the fluctuation range of different operating parameters, and the obtained preset range is accurate and reasonable, and more in line with the needs of practical applications.
  • the training process of the fault detection model is as follows:
  • each training data in the training set includes sample data of multiple operating parameters and their corresponding labeling fault types and labeling similarities, and the sample data is obtained by actual measurement or generated by the generation network of the GAN model of;
  • the sample data of multiple operating parameters in the training data is used as the second input of the preset deep learning model, and the second input corresponding to the preset deep learning model is output.
  • the predicted fault type and predicted similarity wherein, the preset deep learning model is used to compare the second input with each fault data in the fault database to obtain the second input and The similarity of each fault data, the highest similarity among the multiple similarities corresponding to the second input is used as the predicted similarity corresponding to the second input, and the fault data with the highest similarity to the second input is used
  • the fault type is used as the predicted fault type corresponding to the second input, and the predicted fault type and predicted similarity corresponding to the second input are output;
  • the beneficial effect of this technical solution lies in: using the training set to train the preset deep learning model to obtain a fault detection model, the fault detection model can be obtained by training a large amount of training data, and can predict and obtain corresponding fault detection for various input data As a result, it has a wide range of applications and a high level of intelligence.
  • a preset deep learning model can be obtained.
  • Through the learning and tuning of the preset deep learning model Establish the functional relationship from input to output. Although the functional relationship between input and output cannot be found 100%, it can approach the actual correlation as much as possible.
  • the fault detection model trained from this can realize self-diagnosis of fault detection function, and the diagnostic results are highly reliable.
  • the method also includes:
  • a first self-diagnosis report is generated, and the first self-diagnostic report includes the predicted fault type corresponding to the first input;
  • the beneficial effect of this technical solution is: set filter conditions for the generation and sending of the report, if the similarity with the most similar fault data is still not very high, for example, the predicted similarity is only 20% or 35%, and the preset similarity is not reached Threshold (for example, 85%), it can be determined that there is no fault, so there is no need to generate and send a fault self-diagnosis report; only when the predicted similarity is greater than the preset similarity threshold, it is judged that there is a fault, and it needs to be generated Report and send. Only when the prediction similarity is high enough, the process of generating and sending the self-diagnosis report is involved, avoiding repeated use of computing resources when no fault occurs, saving energy and protecting the environment.
  • Threshold for example, 85%
  • multiple communication levels are set, corresponding to different user equipments (that is, the staff notified are different), for example, life and temperature-related faults correspond to lower communication levels, and the fault alarm information only needs to be sent
  • life and temperature-related faults correspond to lower communication levels
  • the fault alarm information only needs to be sent
  • the faults related to water pumps and motors correspond to a higher communication level
  • the fault alarm information needs to be sent to the maintenance personnel in this area and the person in charge of this area.
  • different staff can be notified according to the importance of the predicted fault type, and the differentiated push of fault alarm information can be realized.
  • the degree of intelligence is high, and it is more in line with the needs of practical applications.
  • the method also includes:
  • a second self-diagnosis report is generated, and the second self-diagnosis report includes the component names corresponding to the operating parameters that are not in its own preset range and preset question types;
  • the beneficial effect of this technical solution is that when it is detected in the first stage that some operating parameters are not within the preset range, although the final result of whether a fault has occurred has not yet been obtained through the second stage, the situation that some operating parameters are out of the normal range still means If there may be problems in the operation process, it can be regarded as a phenomenon worthy of vigilance, and the relevant staff should be reminded in time.
  • the names of parts that may have problems and the types of preset problems are given in the problem warning information. On the one hand, it assists the staff to make judgments.
  • the above-mentioned information is given in the problem warning information, which is convenient for the staff to carry the corresponding tools to deal with, avoiding the temporary discovery of tools that have been forgotten, and improving the efficiency of problem handling.
  • the method also includes:
  • a maintenance plan for the target component is generated, the target component is each of the soft joint and the gasket, and the maintenance plan for the target component includes the The useful life of the target component;
  • a maintenance task list for the target component is generated and sent to a preset user device.
  • the beneficial effect of this technical solution is: for the parts with service life, a maintenance plan is established from the beginning of operation, and when the service life of the parts reaches its own life, the maintenance task list is automatically generated and distributed to the relevant staff, In order to repair or replace corresponding parts in time, avoid major failures caused by aging parts, and scientifically and reasonably prevent potential safety hazards caused by aging parts.
  • the present application provides a non-negative pressure laminated water supply equipment, including:
  • a base the base is provided with a base vibration sensor, which is used to obtain the measurement data of the base vibration parameters of the non-negative pressure laminated water supply equipment;
  • a pipeline the pipeline is arranged on the base, the water inlet of the pipeline is connected to the water outlet of the water tank, the water outlet of the pipeline is connected to the water inlet of the steady flow tank, and the pipeline is provided with pipeline pressure sensor;
  • a bolt the bolt is arranged at the water inlet of the pipeline, and the bolt is provided with a bolt loosening sensor, which is used to detect whether the bolt is loose, and obtain the measurement data of the bolt loosening parameter;
  • a plurality of water pump units each of the water pump units includes a water pump and a motor, each of the water pumps is arranged on the base, each of the motors is arranged on a corresponding water pump, and each of the water pumps is provided with a water pump temperature sensor , water pump vibration sensor and water pump speed sensor, in order to obtain the measurement data of the water pump temperature parameter, water pump vibration parameter and water pump speed parameter of each described water pump, each described motor is provided with motor temperature sensor, motor current sensor and motor voltage a sensor, used to obtain the measurement data of the motor temperature parameter, the motor current parameter and the motor voltage parameter of each of the motors;
  • a controller the controller is connected with the base vibration sensor, the pipeline pressure sensor, the bolt looseness sensor, the multiple water pump temperature sensors, the multiple water pump vibration sensors, and the multiple water pump speed sensors respectively. Sensors, a plurality of the motor temperature sensors, a plurality of the motor current sensors and a plurality of the motor voltage sensors are electrically connected, the controller stores a fault detection model and a fault database, and the controller is configured to realize the above The steps described in any one of the methods.
  • the beneficial effect of the technical solution is to provide a non-negative pressure stacked pressure water supply equipment, the controller of which can perform two-stage fault detection, and the fault detection result has high accuracy.
  • the controller is also configured to:
  • the pipeline pressure sensor When receiving the base vibration sensor, the pipeline pressure sensor, the bolt loosening sensor, the plurality of the water pump temperature sensors, the plurality of the water pump vibration sensors, the plurality of the water pump speed sensors, the plurality of the When any one of the motor temperature sensor, the plurality of motor current sensors and the plurality of motor voltage sensors sends measurement data, the received measurement data is put into a queue to be sent;
  • the beneficial effects of this technical solution are: set conditions for data upload, use the queue to be sent to store the measurement data to be sent, and upload all the data when there is a sufficient amount of measurement data in the queue, that is, not every time the sensor receives When the measurement data is sent, the data is uploaded immediately, thereby greatly reducing the number of visits to the cloud server and greatly reducing the data processing pressure of the cloud server.
  • controller is further configured to upload data in the following manner:
  • the measurement data in the queue to be sent is complete means that the queue to be sent includes the base vibration sensor, the pipeline pressure sensor, the bolt loosening sensor, multiple water pump temperature sensors, multiple The measurement data sent by the water pump vibration sensor, the multiple water pump rotational speed sensors, the multiple motor temperature sensors, the multiple motor current sensors and the multiple motor voltage sensors.
  • the beneficial effect of this technical solution is: to set further conditions for data uploading. If the measurement data in the queue to be sent is to be uploaded to the cloud server, not only the quantity must be sufficient, but also the types must be complete.
  • the measurement data sent by the sensor can ensure that the data provided to the cloud server each time covers the measurement data of all operating parameters, which is convenient for subsequent data mining and analysis.
  • the controller is also configured to:
  • the beneficial effect of this technical solution is that in practical applications, there may be situations where some sensors themselves fail or the connection with the controller is interrupted. At this time, since the measurement data of these sensors has not entered the queue to be sent, the queue The measurement data in the system cannot always meet the complete conditions, and the cloud server will not be able to obtain the measurement data of the non-negative pressure laminated water supply equipment; by setting an appropriate preset time length, when the measurement data is incomplete, request data from the target sensor and start timing. If there is still no response after the timing expires, it means that the target sensor may no longer be able to provide data, so all measurement data can be uploaded directly without waiting for the corresponding measurement data of the target sensor. In this way, when some sensors cannot provide measurement data, the situation that the non-negative pressure superimposed water supply equipment cannot upload data to the cloud server is avoided.
  • Fig. 1 is a side view of a non-negative pressure laminated water supply equipment provided by the embodiment of the present application;
  • Fig. 2 is a top view of a non-negative pressure laminated water supply equipment provided by the embodiment of the present application;
  • FIG. 3 is a schematic diagram of a process framework of a self-diagnosis method provided in an embodiment of the present application
  • FIG. 4 is a schematic flow chart of a self-diagnosis method provided in an embodiment of the present application.
  • Fig. 5 is a schematic flowchart of an acquisition process of a preset range corresponding to an operating parameter provided in an embodiment of the present application
  • FIG. 6 is a schematic flowchart of a training process of a fault detection model provided in an embodiment of the present application.
  • Fig. 7 is a schematic flowchart of a part of a self-diagnosis method provided in the embodiment of the present application.
  • Fig. 8 is a partial flowchart of another self-diagnosis method provided by the embodiment of the present application.
  • Fig. 9 is a partial flowchart of another self-diagnosis method provided by the embodiment of the present application.
  • Fig. 10 is a partial flowchart of another self-diagnosis method provided by the embodiment of the present application.
  • Fig. 11 is a partial flowchart of another self-diagnosis method provided by the embodiment of the present application.
  • Fig. 12 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 13 is a schematic structural diagram of a program product for implementing a self-diagnosis method provided by an embodiment of the present application.
  • the present application provides a non-negative pressure laminated water supply equipment
  • the non-negative pressure laminated water supply equipment includes:
  • a base 10 the base 10 is provided with a base vibration sensor 11 for obtaining measurement data of base vibration parameters of the non-negative pressure laminated water supply equipment;
  • a pipeline 70 the pipeline 70 is arranged on the base 10, the water inlet of the pipeline 70 is connected with the water outlet of the water tank, and the water outlet of the pipeline 70 is connected with the water inlet of the steady flow tank, so
  • the pipeline 70 is provided with a pipeline pressure sensor 71;
  • a bolt 20, the bolt 20 is arranged at the water inlet of the pipeline 70, and the bolt 20 is provided with a bolt loosening sensor 21, which is used to detect whether the bolt 20 is loose, and obtain the measurement data of the bolt loosening parameter;
  • each of the water pump units includes a water pump 40 and a motor 30, each of the water pumps 40 is arranged on the base 10, each of the motors 30 is arranged on a corresponding water pump 40, each of the Water pump 40 is provided with water pump temperature sensor 41, water pump vibration sensor 42 and water pump speed sensor 43, in order to obtain the measurement data of water pump temperature parameter, water pump vibration parameter and water pump speed parameter of each described water pump 40, each described motor 30
  • a motor temperature sensor 31, a motor current sensor 32 and a motor voltage sensor 33 are provided to obtain the measurement data of the motor temperature parameters, motor current parameters and motor voltage parameters of each of the motors 30;
  • the controller is respectively connected with the base vibration sensor 11, the pipeline pressure sensor 71, the bolt looseness sensor 21, the multiple water pump temperature sensors, the multiple water pump vibration sensors, and the multiple water pump vibration sensors.
  • the water pump rotational speed sensor, a plurality of the motor temperature sensors, a plurality of the motor current sensors and a plurality of the motor voltage sensors are electrically connected, the controller stores a fault detection model and a fault database, and the controller is configured Complete the steps described in Implementing the Self-Diagnostic Method. Among them, the self-diagnosis method will be described below.
  • the non-negative pressure superimposed water supply equipment is equipped with multiple water pump units, each water pump unit includes a water pump and a motor, and each water pump and motor is respectively equipped with a plurality of sensors.
  • the above-mentioned “multiple water pump temperature sensors” means no load All the water pump temperature sensors corresponding to all the water pump units of the laminated water supply equipment, "a plurality of the water pump vibration sensors, a plurality of the water pump speed sensors, a plurality of the motor temperature sensors, a plurality of the motor current sensors and a plurality of the motor voltage sensor" and so on.
  • the non-negative pressure laminated water supply equipment may be provided with a plurality of bolts, and each bolt may be provided with a bolt loosening sensor.
  • the non-negative pressure superimposed water supply equipment is provided with 3 water pump units, and then the non-negative pressure superimposed water supply equipment is provided with 3 water pumps, 3 motors, and 3 water pumps. sensors, 3 water pump vibration sensors, 3 water pump speed sensors, 3 motor temperature sensors, 3 motor current sensors and 3 motor voltage sensors.
  • the controller may be a PLC controller.
  • a data communication circuit may be provided between the controller and each sensor.
  • the present application also provides a self-diagnosis method, which is used to provide self-diagnosis function for non-negative pressure laminated water supply equipment.
  • This method does not limit the non-negative pressure laminated water supply equipment.
  • the non-negative pressure laminated water supply equipment is, for example, the non-negative pressure laminated water supply equipment in Figure 1 and Figure 2, and it can also be applicable to this method. Other non-negative pressure stacked water supply equipment.
  • the methods include:
  • Step S101 Obtain measurement data of multiple operating parameters of the non-negative pressure laminated water supply equipment, the multiple operating parameters include base vibration parameters, pipeline pressure parameters, bolt loosening parameters, soft joint usage parameters, and gasket usage parameter, water pump temperature parameter, water pump vibration parameter, water pump speed parameter, motor temperature parameter, motor current parameter and motor voltage parameter;
  • Step S102 respectively detecting whether the measurement data of each of the operating parameters is within its corresponding preset range
  • Step S103 When it is detected that the measurement data of at least one operating parameter is not in its corresponding preset range, the measurement data of multiple operating parameters are used as the first input of the fault detection model, and the fault detection model is passed through the fault detection model Outputting the predicted fault type and predicted similarity corresponding to the first input;
  • the fault detection model is used to compare the first input with each fault data in the fault database, obtain the similarity between the first input and each fault data, and compare the first input
  • the highest similarity among the corresponding multiple similarities is used as the predicted similarity corresponding to the first input
  • the fault type of the fault data with the highest similarity to the first input is used as the predicted fault type corresponding to the first input , and output the predicted fault type and predicted similarity corresponding to the first input;
  • Step S104 When the predicted similarity corresponding to the first input is less than the preset similarity threshold, it is determined that no fault occurs; when the predicted similarity corresponding to the first input is not less than the preset similarity threshold, it is determined that there is a fault occur.
  • the usage parameter of the soft joint is, for example, the usage time of the soft joint
  • the usage parameter of the gasket is, for example, the usage time of the gasket
  • the present application does not limit "at least two" in step S101, which may be 2, 3, 5, 8, 10 or 11.
  • the plurality of operating parameters may include, for example, base vibration parameters, pipeline pressure parameters, bolt loosening parameters, soft joint usage parameters, gasket usage parameters, water pump temperature parameters, water pump vibration parameters, water pump speed parameters, Part of the motor temperature parameter, motor current parameter and motor voltage parameter.
  • the plurality of operating parameters may include, for example, base vibration parameters, pipeline pressure parameters, bolt loosening parameters, soft joint usage parameters, gasket usage parameters, water pump temperature parameters, water pump vibration parameters, and water pump speed parameters. , all of the motor temperature parameters, motor current parameters and motor voltage parameters.
  • the measurement data of the temperature parameters of the water pumps of the non-negative pressure superimposed water supply equipment may include the measurement data respectively collected by the water pump temperature sensors of each water pump. Vibration parameters, water pump speed parameters, motor temperature parameters, motor current parameters, and motor voltage parameters can be deduced by analogy, and will not be described here.
  • the measurement data of the water pump temperature parameters may include the measurement data collected by the water pump temperature sensor of the first water pump, the measurement data collected by the water pump temperature sensor of the second water pump, and the water pump temperature data of the third water pump. The measurement data collected by the temperature sensor.
  • each type of fault data has a corresponding fault type
  • the fault type can be identified by one or more of letters, numbers, Chinese characters and special symbols, for example, it can be expressed as "E4", "Water pump failure", "# ⁇ #” and so on.
  • the fault detection model compares the first input with 100 kinds of fault data respectively, and obtains 100 similarities, for example: 30%, 60%, ..., 98%, ..., 74%, 88%, among which the highest The similarity of 98% is used as the predicted similarity, and the fault type of the fault data corresponding to the 98% similarity is used as the predicted fault type.
  • the present application does not limit the selection of the preset similarity threshold.
  • the preset similarity threshold is, for example, 90%, 95% or 99%.
  • the above method uses a two-stage detection process to determine whether a fault has occurred.
  • a possible fault is detected in the first stage, it is not directly judged as a fault, but enters the second stage of fault detection.
  • the second stage also detects It is not determined that the non-negative pressure stacked water supply equipment fails until a possible failure occurs. Therefore, the obtained fault detection results are highly reliable, avoiding frequent misjudgments and affecting the normal use of the non-negative pressure stacked water supply equipment.
  • multiple sensors are used to obtain measurement data of multiple operating parameters, and it is detected whether the measurement data of each operating parameter is within its corresponding preset range.
  • the measurement data of multiple operating parameters are input into the fault detection model, and the fault
  • the detection model determines the closest fault type of the non-negative pressure stacked water supply equipment in the current operation process as the predicted fault type, and the fault detection model also gives the similarity between the input data and the predicted fault type as the predicted similarity, by comparing The size of the predicted similarity and the preset similarity threshold is used to judge whether there is a fault. Obviously, the higher the similarity, the more likely the non-negative pressure superimposed water supply equipment has a fault corresponding to the predicted fault type.
  • the measurement data of multiple operating parameters is used as the input data of the fault detection model, taking into account the correlation between multiple operating parameters, and comprehensively judges the measurement data of multiple operating parameters to avoid the numerical fluctuation of a single operating parameter causing Misjudgment, but compare multiple operating parameters as a whole with multiple fault data stored in the fault database one by one, find out the fault data with the highest similarity, and use the fault type corresponding to the fault data as a prediction Fault types further improve the accuracy of fault detection results.
  • the acquisition process of the preset range corresponding to each of the operating parameters is as follows:
  • Step S201 For each of the operating parameters, when the non-negative pressure laminated water supply equipment is in a normal operating state, respectively record the measurement data of the operating parameters at multiple preset times;
  • Step S202 Calculate the average value by using the measurement data of the operating parameters at multiple preset times
  • Step S203 Obtain a preset range including the average value, and the ratio of the difference between the maximum value and the minimum value of the preset range to the average value is a preset constant corresponding to the operating parameter.
  • the present application does not limit the selection of multiple preset times.
  • the multiple preset times are, for example, multiple preset times at intervals of 5 minutes.
  • the preset constants corresponding to each operating parameter may be the same or different.
  • base vibration parameters, pipeline pressure parameters, bolt loosening parameters, soft joint usage parameters, gasket usage parameters, water pump temperature parameters, water pump vibration parameters, water pump speed parameters, motor temperature parameters, motor current parameters and motor may all be 10%.
  • the non-negative pressure laminated water supply equipment when the non-negative pressure laminated water supply equipment is in normal operation state, record the measurement data at multiple preset times and calculate the average value, and the obtained average value can be used as the reference value of the operation parameter in the normal operation process , on this basis, an appropriate fluctuation range is set to obtain a preset range including the average value, and the obtained preset range has a high reference value.
  • the values of different operating parameters vary greatly, and may not be an order of magnitude. Therefore, set the same or different preset constants for each operating parameter, and then set the ratio of the difference between the maximum value and the minimum value of the preset range to the average value. is the preset constant corresponding to the operating parameter, thereby limiting the fluctuation range of different operating parameters, and the obtained preset range is accurate and reasonable, and more in line with the needs of practical applications.
  • the training process of the fault detection model is as follows:
  • Step S301 Obtain a training set.
  • Each training data in the training set includes sample data of multiple operating parameters and their corresponding labeled fault types and labeled similarities.
  • the sample data is obtained through actual measurement or using a GAN model. Generated by the network;
  • Step S302 For each of the training data, the sample data of a plurality of operating parameters in the training data is used as the second input of the preset deep learning model, and the preset deep learning model outputs the first The predicted fault type and predicted similarity corresponding to the two inputs; wherein, the preset deep learning model is used to compare the second input with each fault data in the fault database to obtain the first The similarity between two inputs and each fault data, the highest similarity among the multiple similarities corresponding to the second input is used as the predicted similarity corresponding to the second input, and the highest similarity with the second input The fault type of the fault data is used as the predicted fault type corresponding to the second input, and the predicted fault type and predicted similarity corresponding to the second input are output;
  • Step S303 Based on the predicted fault type and predicted similarity corresponding to the second input and the labeled fault type and labeled similarity corresponding to the second input, update the model parameters of the preset deep learning model;
  • Step S304 Detect whether the preset training end condition is met, if yes, stop training, and use the preset deep learning model obtained through training as the fault detection model, if not, use the next training The data continues to train the preset deep learning model.
  • the GAN model is the Generative Adversarial Network, which consists of a generation network and a discriminant network.
  • the generator network randomly samples from the latent space as input, and its output needs to imitate the real samples in the training set as much as possible.
  • the input of the discriminant network is the real sample or the output of the generation network, and its purpose is to distinguish the output of the generation network from the real sample as much as possible.
  • the generative network should deceive the discriminative network as much as possible.
  • the two networks fight against each other and constantly adjust the parameters. The ultimate goal is to make the discriminative network unable to judge whether the output of the generating network is true or not.
  • Using the GAN model can generate sample data of multiple operating parameters for the training process of the fault detection model, which can effectively reduce the amount of data collected from the original data and greatly reduce the cost of data collection and labeling.
  • the preset training end conditions can be set according to actual needs, and this application does not make any limitation thereto.
  • the preset training end condition may be reaching a preset number of training times.
  • the preset deep learning model is used to train the training set to obtain a fault detection model.
  • the fault detection model can be trained from a large amount of training data, and can predict and obtain corresponding fault detection results for various input data. It has a wide range of applications. , high level of intelligence.
  • a preset deep learning model can be obtained.
  • Through the learning and tuning of the preset deep learning model Establish the functional relationship from input to output. Although the functional relationship between input and output cannot be found 100%, it can approach the actual correlation as much as possible.
  • the fault detection model trained from this can realize self-diagnosis of fault detection function, and the diagnostic results are highly reliable.
  • the fault detection model is trained using a preset deep learning model.
  • the fault detection model may be obtained through training using a preset machine learning model.
  • the fault detection model may be obtained by optimizing a preset linear regression model.
  • the method may further include:
  • Step S105 When the predicted similarity corresponding to the first input is not less than the preset similarity threshold, generate a first self-diagnostic report, the first self-diagnostic report includes the predicted fault type corresponding to the first input ;
  • Step S1061 Based on the first self-diagnosis report, obtain a first solution strategy corresponding to the predicted fault type corresponding to the first input;
  • Step S1071 Generate fault alarm information including the first solution strategy, and send it to a preset user equipment.
  • the first self-diagnosis report is, for example, in txt format, doc format, xls format or csv format.
  • the preset user equipment is generally a staff's terminal equipment, and its equipment type may include, for example, one or more of a mobile phone, a tablet computer, a desktop computer, and a smart wearable device.
  • the method may further include:
  • Step S105 When the predicted similarity corresponding to the first input is not less than the preset similarity threshold, generate a first self-diagnostic report, the first self-diagnostic report includes the predicted fault type corresponding to the first input ;
  • Step S1062 Based on the first self-diagnosis report, obtain a first solution strategy and a first communication level corresponding to the predicted fault type corresponding to the first input, and each communication level corresponds to one or more preset user equipments ;
  • Step S1072 Generate fault alarm information including the first solution strategy, and send it to the user equipment corresponding to the first communication level.
  • filter conditions are set for the generation and sending of the report, if the similarity with the most similar fault data is still not very high, for example, the predicted similarity is only 20% or 35%, and the preset similarity threshold (for example, 85% is not reached) %), it can be determined that no fault has occurred, so there is no need to generate and send a fault self-diagnosis report; only when the predicted similarity is greater than the preset similarity threshold, it is determined that a fault has occurred, and a report needs to be generated and sent. Only when the prediction similarity is high enough, the process of generating and sending the self-diagnosis report is involved, avoiding repeated use of computing resources when no fault occurs, saving energy and protecting the environment.
  • the preset similarity threshold for example, 85% is not reached
  • multiple communication levels are set, corresponding to different user equipments (that is, the staff notified are different), for example, life and temperature-related faults correspond to lower communication levels, and the fault alarm information only needs to be sent
  • life and temperature-related faults correspond to lower communication levels
  • the fault alarm information only needs to be sent
  • the faults related to water pumps and motors correspond to a higher communication level
  • the fault alarm information needs to be sent to the maintenance personnel in this area and the person in charge of this area.
  • different staff can be notified according to the importance of the predicted fault type, and the differentiated push of fault alarm information can be realized.
  • the degree of intelligence is high, and it is more in line with the needs of practical applications.
  • the method may further include:
  • Step S108 When it is detected that the measurement data of at least one operating parameter is not within its corresponding preset range, generate a second self-diagnostic report, the second self-diagnostic report includes corresponding Component names and preset question types;
  • Step S109 Based on the second self-diagnosis report, generate problem warning information including the component name and the preset problem type, and send it to a preset user equipment, and use a display device to display the component name and the preset problem type.
  • problem warning information including the component name and the preset problem type
  • send it to a preset user equipment, and use a display device to display the component name and the preset problem type.
  • component names can be identified by one or more of letters, numbers, Chinese characters and special symbols, such as “A5", “water pump B”, “motor 01”, “bolt #306” and so on.
  • preset question types in the second self-diagnosis report, for reference by staff.
  • the preset problem type can be identified by one or more of letters, numbers, Chinese characters and special symbols, for example, it can be expressed as “A5", “water pump failure 01”, “pipe leaking”, “loose bolts” and so on.
  • the fact that some operating parameters are out of the normal range still means that during the operation process may If there is a problem, it can be regarded as a phenomenon worthy of vigilance, and the relevant staff should be reminded in time.
  • the names of parts that may have problems and the types of preset problems are given in the problem warning information. On the one hand, it assists the staff to make judgments.
  • the above-mentioned information is given in the problem warning information, which is convenient for the staff to carry the corresponding tools to deal with, avoiding the temporary discovery of tools that have been forgotten, and improving the efficiency of problem handling.
  • the method may further include:
  • Step S110 When the non-negative pressure laminated water supply equipment is put into operation, generate a maintenance plan for the target component, the target component is each of the soft joint and the gasket, and the maintenance plan for the target component is including the useful life of said target component;
  • Step S1111 Based on the maintenance plan of the target component, when it is detected that the service life of the target component has reached its own service life, a maintenance task list for the target component is generated and sent to a preset user device.
  • the service life of the soft joint is 30,000 hours.
  • a maintenance task list for the soft joint is generated and sent.
  • the method may further include:
  • Step S110 When the non-negative pressure laminated water supply equipment is put into operation, generate a maintenance plan for the target component, the target component is each of the soft joint and the gasket, and the maintenance plan for the target component is including the useful life of said target component;
  • Step S1112 Based on the maintenance plan of the target component, when it is detected that the difference between the service life of the target component itself and its service life is not greater than the preset duration threshold, generate a maintenance task list for the target component and send it to to the default user device.
  • the preset duration threshold is, for example, 100 hours.
  • a maintenance plan is established from the beginning of operation.
  • the service life of the parts reaches its own life, the maintenance task list is automatically generated and dispatched to the relevant staff for timely repair or replacement.
  • Corresponding components to avoid major failures caused by component aging, scientifically and reasonably prevent potential safety hazards caused by component aging.
  • the controller of the non-negative pressure laminated water supply equipment provided by the present application can perform two-stage fault detection, and the fault detection result has high accuracy.
  • the controller may also be configured to:
  • the pipeline pressure sensor When receiving the base vibration sensor, the pipeline pressure sensor, the bolt loosening sensor, the plurality of the water pump temperature sensors, the plurality of the water pump vibration sensors, the plurality of the water pump speed sensors, the plurality of the When any one of the motor temperature sensor, the plurality of motor current sensors and the plurality of motor voltage sensors sends measurement data, the received measurement data is put into a queue to be sent;
  • the preset quantity threshold is, for example, 11, 15, 20 and so on.
  • the non-negative pressure superimposed water supply equipment is provided with 3 water pump units, then the non-negative pressure superimposed water supply equipment is provided with a base vibration sensor, a pipeline pressure sensor, a bolt loosening sensor, 3 water pump temperature sensors, 3 water pump vibration sensors, 3 water pump speed sensors, 3 motor temperature sensors, 3 motor current sensors and 3 motor voltage sensors, that is, there are 21 sensors in total, and the preset number threshold can be set for 21.
  • controller may be further configured to upload data in the following manner:
  • the measurement data in the queue to be sent is complete means that the queue to be sent includes the base vibration sensor, the pipeline pressure sensor, the bolt loosening sensor, multiple water pump temperature sensors, multiple The measurement data sent by the water pump vibration sensor, the multiple water pump rotational speed sensors, the multiple motor temperature sensors, the multiple motor current sensors and the multiple motor voltage sensors.
  • the controller may also be configured to:
  • This application does not limit the preset duration, which may be 1 minute, 3 minutes or 5 minutes.
  • the preset number threshold is set to 21, when the measurement data sent by the motor voltage sensor of the third motor is received, the number of measurement data in the queue to be sent is detected It is 21, not less than the preset quantity threshold. It is still necessary to judge whether the measurement data in the queue to be sent is complete, because there may be multiple data sent by the same sensor in the queue to be sent. If it is complete, directly upload all the measurement data in all queues to be sent, and if it is found that the measurement data of some sensors is missing, first find out the sensors with missing measurement data. For example, if it is found that the measurement data sent by the water pump speed sensor of the second water pump is missing, a data acquisition request is sent to the water pump speed sensor of the second water pump.
  • the cloud server will not be able to obtain the measurement data of the non-negative pressure superimposed water supply equipment; by setting a suitable preset time length, when the measurement data is incomplete, the target sensor will be requested for data and start timing. If no response is received after the timing expires, It means that the target sensor may no longer be able to provide data, so all measurement data can be directly uploaded without waiting for the corresponding measurement data of the target sensor. In this way, when some sensors cannot provide measurement data, the situation that the non-negative pressure superimposed water supply equipment cannot upload data to the cloud server is avoided.
  • the embodiment of the present application also provides an electronic device 200, the electronic device 200 includes at least one memory 210, at least one processor 220 and a bus 230 connecting different platform systems.
  • Memory 210 may include readable media in the form of volatile memory, such as random access memory (RAM) 211 and/or cache memory 212 , and may further include read only memory (ROM) 213 .
  • RAM random access memory
  • ROM read only memory
  • the memory 210 also stores a computer program, and the computer program can be executed by the processor 220, so that the processor 220 executes the steps of the self-diagnosis method in the embodiment of the present application.
  • the implementation mode and the achieved technical effect are the same, and part of the content will not be repeated.
  • Memory 210 may also include utility 214 having at least one program module 215 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, examples of each or Implementations of network environments may be included in some combination.
  • program module 215 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, examples of each or Implementations of network environments may be included in some combination.
  • the processor 220 can execute the above-mentioned computer program, and can execute the utility tool 214 .
  • Bus 230 may represent one or more of several types of bus structures, including a memory bus or memory self-diagnostic method, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures .
  • the electronic device 200 can also communicate with one or more external devices 240 such as keyboards, pointing devices, Bluetooth devices, etc., and can also communicate with one or more devices capable of interacting with the electronic device 200, and/or communicate with the electronic device 200 200 is capable of communicating with any device (eg, router, modem, etc.) that communicates with one or more other computing devices. Such communication may occur through input-output interface 250 .
  • the electronic device 200 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and/or a public network such as the Internet) through the network adapter 260 .
  • the network adapter 260 can communicate with other modules of the electronic device 200 through the bus 230 . It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with electronic device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives And data backup storage platform, etc.
  • the embodiment of the present application also provides a computer-readable storage medium, which is used to store a computer program.
  • a computer program When the computer program is executed, the steps of the self-diagnosis method in the embodiment of the present application are realized.
  • the specific implementation method The implementation mode and the achieved technical effect are consistent with the above-mentioned self-diagnosis method described in the embodiment, and part of the content will not be repeated.
  • Fig. 13 shows the program product 300 for realizing the above-mentioned self-diagnosis method provided by this embodiment, which can adopt a portable compact disk read-only memory (CD-ROM) and include program codes, and can be installed on a terminal device such as a personal computer run on.
  • a readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, device or device.
  • Program product 300 may utilize any combination of one or more readable media.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read-only memory
  • optical storage devices magnetic storage devices, or any suitable combination of the foregoing.
  • a computer readable storage medium may include a data signal carrying readable program code in baseband or as part of a carrier wave traveling as part of a data signal. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a readable storage medium may also be any readable medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the program code contained on the readable storage medium can be transmitted by any appropriate medium, including but not limited to wireless, cable, optical cable, RF, etc., or any suitable combination of the above.
  • the program codes for performing the operations of the present invention can be written in any combination of one or more programming languages, and the programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages A programming language such as C or similar.
  • the program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute.
  • the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (for example, using an Internet service provider). business to connect via the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet service provider for example, using an Internet service provider

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Hydrology & Water Resources (AREA)
  • Structural Engineering (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Architecture (AREA)
  • Civil Engineering (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Artificial Intelligence (AREA)

Abstract

本申请提供了一种自我诊断方法和无负压叠压供水设备，所述方法包括：获取所述无负压叠压供水设备的多个运行参数的测量数据；当检测到至少一个所述运行参数的测量数据不处于自身对应的预设范围时，将多个所述运行参数的测量数据作为故障检测模型的第一输入，输出所述第一输入对应的预测故障类型和预测相似度；当所述第一输入对应的预测相似度小于预设相似度阈值时确定无故障发生，当所述第一输入对应的预测相似度不小于所述预设相似度阈值时确定有故障发生。使用两个阶段的检测过程来判断是否有故障发生，当第一阶段检测到可能发生故障时，并非直接判断为发生故障，而是进入第二阶段的故障检测，避免误判。

Description

自我诊断方法和无负压叠压供水设备 技术领域
本申请涉及供水设备的技术领域，尤其涉及自我诊断方法和无负压叠压供水设备。
背景技术
随着信息技术的发展，应用于供水领域的大数据分析已成为当今供水行业的发展趋势。传统的无负压叠压供水设备处于数据采集或者是数据“向后分析”阶段。二次供水的安全问题也逐渐成为市民关注的热点。因此，为提高二次供水安全系数，现提出一种具有自我诊断功能的无负压叠压供水设备，采取数据“向前分析”的方式，让设备故障具有预测性。
当前，有的无负压叠压供水设备已经具备数据采集功能和故障报警功能，但其采集到的数据，需要有相当经验的工程师才能判断故障类型。另外，现有技术的故障报警，其判断条件一般是某一运行参数的数值波动超出预设范围，但单一运行参数偶发性的数值波动可能是数据采集或者上传时发生错误造成的，此时直接进行故障报警，存在不小的误判概率。
发明内容
本申请的目的在于提供自我诊断方法和无负压叠压供水设备，以使无负压叠压供水设备能够自我诊断是否有故障发生，并减少误判概率。
本申请的目的采用以下技术方案实现：
第一方面，本申请提供了一种自我诊断方法，用于为无负压叠压供水设备提供自我诊断功能，所述方法包括：
获取所述无负压叠压供水设备的多个运行参数的测量数据，多个所述运行参数包括底座振动参数、管路压力参数、螺栓松动参数、软接头使用参数、密封垫使用参数、水泵温度参数、水泵振动参数、水泵转速参数、电机温度参数、电机电流参数和电机电压参数中的至少两个；
分别检测每个所述运行参数的测量数据是否处于自身对应的预设范围；
当检测到至少一个所述运行参数的测量数据不处于自身对应的预设范围时，将多个所述运行参数的测量数据作为故障检测模型的第一输入，通过所述故障检测模型输出所述第一输入对应的预测故障类型和预测相似度；其中，所述故障检测模型用于将所述第一输入分别与 故障数据库中的每个故障数据进行比对，得到所述第一输入与每个故障数据的相似度，将所述第一输入对应的多个相似度中最高的相似度作为所述第一输入对应的预测相似度，将与所述第一输入相似度最高的故障数据的故障类型作为所述第一输入对应的预测故障类型，并且输出所述第一输入对应的预测故障类型和预测相似度；
当所述第一输入对应的预测相似度小于预设相似度阈值时确定无故障发生，当所述第一输入对应的预测相似度不小于所述预设相似度阈值时确定有故障发生。
该技术方案的有益效果在于：使用两个阶段的检测过程来判断是否有故障发生，当第一阶段检测到可能发生故障时，并非直接判断为发生故障，而是进入第二阶段的故障检测，当第二阶段也检测到可能发生故障时，才确定无负压叠压供水设备发生故障，由此，所得到的故障检测结果可信度高，避免频繁误判，影响无负压叠压供水设备的正常使用。
具体而言，在第一阶段，使用多个传感器获取多个运行参数的测量数据，分别检测每个运行参数的测量数据是否处于自身对应的预设范围，当存在一个或多个运行参数的测量数据超出自身对应的预设范围时，表明无负压叠压供水设备有可能发生故障，这时候进入第二阶段；在第二阶段，将多个运行参数的测量数据输入故障检测模型，利用故障检测模型确定无负压叠压供水设备在当前运行过程中最接近的故障类型作为预测故障类型，故障检测模型还会同时给出输入数据与该预测故障类型的相似度作为预测相似度，通过比较预测相似度与预设相似度阈值的大小来判断是否有故障发生。显然，相似度越高，无负压叠压供水设备越有可能发生了该预测故障类型所对应的故障。
另外，以多个运行参数的测量数据作为故障检测模型的输入数据，考虑到了多个运行参数之间的关联性，针对多个运行参数的测量数据进行综合判定，避免单一运行参数的数值波动导致误判，而是将多个运行参数作为一个整体，与故障数据库中预先存储的多个故障数据逐一进行比对，找出相似度最高的故障数据，并将该故障数据对应的故障类型作为预测故障类型，进一步提高了故障检测结果的准确性。
在一些可选的实施例中，每个所述运行参数对应的预设范围的获取过程如下：
针对每个所述运行参数，当所述无负压叠压供水设备处于正常运行状态时，分别记录所述运行参数在多个预设时刻的测量数据；
利用所述运行参数在多个预设时刻的测量数据求取平均值；
获取包含所述平均值的预设范围，所述预设范围的最大值与最小值的差值与所述平均值之比是所述运行参数对应的预设常数。
该技术方案的有益效果在于：在无负压叠压供水设备处于正常运行状态时，记录多个预设时刻的测量数据并求取平均值，所得到的平均值能够作为该运行参数在正常运行过程中的参考数值，在此基础上，设置适当的波动幅度，得到包含该平均值的预设范围，所得到的预设范围具有较高的参考价值。不同的运行参数其数值相差很大，可能不是一个数量级，因此，为每个运行参数设置相同或不同的预设常数，再设置预设范围的最大值与最小值的差值与平均值之比是该运行参数对应的预设常数，由此来限定不同运行参数的波动幅度，所得到的预设范围准确、合理，更符合实际应用中的需求。
在一些可选的实施例中，所述故障检测模型的训练过程如下：
获取训练集，所述训练集中的每个训练数据包括多个运行参数的样本数据及其对应的标注故障类型和标注相似度，所述样本数据是实际测量得到的或者利用GAN模型的生成网络生成的；
针对每个所述训练数据，将所述训练数据中的多个运行参数的样本数据作为预设的深度学习模型的第二输入，通过所述预设的深度学习模型输出所述第二输入对应的预测故障类型和预测相似度；其中，所述预设的深度学习模型用于将所述第二输入分别与所述故障数据库中的每个故障数据进行比对，得到所述第二输入与每个故障数据的相似度，将所述第二输入对应的多个相似度中最高的相似度作为所述第二输入对应的预测相似度，将与所述第二输入相似度最高的故障数据的故障类型作为所述第二输入对应的预测故障类型，并且输出所述第二输入对应的预测故障类型和预测相似度；
基于所述第二输入对应的预测故障类型和预测相似度以及所述第二输入对应的标注故障类型和标注相似度，更新所述预设的深度学习模型的模型参数；
检测是否满足预设的训练结束条件，如果是，则停止训练，并将训练得到的所述预设的深度学习模型作为所述故障检测模型，如果否，则利用下一个所述训练数据继续训练所述预设的深度学习模型。
该技术方案的有益效果在于：利用训练集对预设的深度学习模型进行训练，得到故障检测模型，故障检测模型可以由大量的训练数据训练得到，能够针对多种输入数据预测得到相应的故障检测结果，适用范围广，智能化水平高。通过设计，建立适量的神经元计算节点和多层运算层次结构，选择合适的输入层和输出层，就可以得到预设的深度学习模型，通过该预设的深度学习模型的学习和调优，建立起从输入到输出的函数关系，虽然不能100％找到输入与输出的函数关系，但是可以尽可能地逼近现实的关联关系，由此训练得到的故障检测 模型，可以实现对故障检测的自我诊断功能，且诊断结果可靠性高。
在一些可选的实施例中，所述方法还包括：
当所述第一输入对应的预测相似度不小于所述预设相似度阈值时，生成第一自诊断报告，所述第一自诊断报告包括所述第一输入对应的预测故障类型；
基于所述第一自诊断报告，获取所述第一输入对应的预测故障类型所对应的第一解决策略和第一通信等级，每个通信等级对应预设的一个或多个用户设备；
生成包含所述第一解决策略的故障报警信息，并发送至所述第一通信等级对应的用户设备。
该技术方案的有益效果在于：为报告的生成和发送设置筛选条件，如果与最相似的故障数据的相似度仍然不是很高，例如预测相似度只有20％或者35％，没有达到预设相似度阈值(例如是85％)，则可判定没有故障发生，因此也不需要生成故障的自诊断报告并发送；只有当预测相似度大于预设相似度阈值时，判断有故障发生，才会需要生成报告并发送。只有当预测相似度足够高时，才涉及自诊断报告的生成和发送过程，避免无故障发生时重复调用计算资源，节能环保。另外，针对不同的预测故障类型，设置多个通信等级，分别对应不同的用户设备(即通知到的工作人员不同)，例如寿命、温度相关故障对应较低的通信等级，故障报警信息只需要发送给本片区维修人员，水泵、电机相关故障对应较高的通信等级，故障报警信息需要发送给本片区维修人员和本片区负责人。这样就可以根据预测故障类型的重要程度，通知不同的工作人员，实现故障报警信息的差异化推送，智能化程度高，更加符合实际应用中的需求。
在一些可选的实施例中，所述方法还包括：
当检测到至少一个所述运行参数的测量数据不处于自身对应的预设范围时，生成第二自诊断报告，所述第二自诊断报告包括不处于自身预设范围的运行参数对应的部件名称和预设问题类型；
基于所述第二自诊断报告，生成包含所述部件名称和所述预设问题类型的问题预警信息，并发送至预设的用户设备，以及利用显示设备显示所述部件名称和所述预设问题类型。
该技术方案的有益效果在于：在第一阶段检测到有运行参数不处于预设范围时，虽然尚未通过第二阶段得到是否发生故障的最终结果，但部分运行参数运行超出正常范围的情况依然意味着运行过程中可能存在问题，可以作为值得警惕的现象，及时提醒相关工作人员注意。另外，在问题预警信息中给出可能存在问题的部件名称和预设问题类型，一方面辅助工作人 员做出判断，另一方面，出问题的部件不同，所需要的检测、维修工具不同，在问题预警信息中给出上述信息，方便工作人员携带对应工具前去处理，避免临时发现有工具忘记带的情况，提高问题处理效率。
在一些可选的实施例中，所述方法还包括：
当所述无负压叠压供水设备开始投入运行时，生成目标部件的维修保养计划，所述目标部件分别是软接头和密封垫中的每一个，所述目标部件的维修保养计划包括所述目标部件的使用寿命；
基于所述目标部件的维修保养计划，当检测到所述目标部件的使用时长达到自身的使用寿命时，生成所述目标部件的维修保养任务单并发送至预设的用户设备。
该技术方案的有益效果在于：针对具有使用寿命的零部件，从开始运行起就建立维修保养计划，当零部件的使用时长达到自身寿命时，自动生成维修保养任务单并派发给相关工作人员，以便及时维修或者更换对应零部件，避免零部件老化造成重大故障发生，科学、合理地防范零部件老化带来的安全隐患。
第二方面，本申请提供了一种无负压叠压供水设备，包括：
底座，所述底座设置有底座振动传感器，用以获取所述无负压叠压供水设备的底座振动参数的测量数据；
管路，所述管路设置在所述底座上，所述管路的进水口与水箱的出水口连接，所述管路的出水口与稳流罐的进水口连接，所述管路设置有管路压力传感器；
螺栓，所述螺栓设置于所述管路的进水口，所述螺栓设置有螺栓松动传感器，用以检测所述螺栓是否发生松动，得到螺栓松动参数的测量数据；
多个水泵机组，每个所述水泵机组包括水泵和电机，每个所述水泵设置于所述底座上，每个所述电机设置于对应的水泵上，每个所述水泵设置有水泵温度传感器、水泵振动传感器和水泵转速传感器，用以获取每个所述水泵的水泵温度参数、水泵振动参数和水泵转速参数的测量数据，每个所述电机设置有电机温度传感器、电机电流传感器和电机电压传感器，用以获取每个所述电机的电机温度参数、电机电流参数和电机电压参数的测量数据；
控制器，所述控制器分别与所述底座振动传感器、所述管路压力传感器、所述螺栓松动传感器、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器电连接，所述控制器存储有故障检测模型和故障数据库，所述控制器被配置成实现上述任一项方法所述 的步骤。
该技术方案的有益效果在于：提供一种无负压叠压供水设备，其控制器能够执行两个阶段的故障检测，其故障检测结果准确度高。
在一些可选的实施例中，所述控制器还被配置成：
当接收到所述底座振动传感器、所述管路压力传感器、所述螺栓松动传感器、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器中的任意一个发送的测量数据时，将接收到的测量数据放入待发送队列；
检测所述待发送队列中的测量数据的数量是否不小于预设数量阈值；
当检测到所述待发送队列中的测量数据的数量不小于所述预设数量阈值时，将所述待发送队列中的所有测量数据上传至云服务器。
该技术方案的有益效果在于：为数据上传设置条件，采用待发送队列存储待发送的测量数据，当队列中存在足够数量的测量数据时再上传所有数据，也就是说，并非每次接收到传感器发送的测量数据时都立刻进行数据上传，由此大大减少访问云服务器的次数，极大降低了云服务器的数据处理压力。
在一些可选的实施例中，所述控制器被进一步配置成采用如下方式上传数据：
当检测到所述待发送队列中的测量数据的数量不小于预设数量阈值时，判断所述待发送队列中的测量数据是否齐全；
当所述待发送队列中的测量数据齐全时，将所述待发送队列中的所有测量数据上传至云服务器；
其中，所述待发送队列中的测量数据齐全是指所述待发送队列中包含所述底座振动传感器、所述管路压力传感器、所述螺栓松动传感器、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器发送的测量数据。
该技术方案的有益效果在于：为数据上传设置进一步条件，待发送队列中的测量数据要想上传到云服务器，不仅数量要足够多，并且类型要齐全，测量数据齐全是指队列中存储有所有传感器发送的测量数据，这样可以确保每次提供给云服务器的数据涵盖了所有运行参数的测量数据，便于后续的数据挖掘分析工作。
在一些可选的实施例中，所述控制器还被配置成：
当所述待发送队列中的测量数据不齐全时，确定缺失测量数据的目标传感器；
向所述目标传感器发送数据获取请求，并开始计时；
当预设时长内接收到所述目标传感器发送的测量数据时，停止计时，并在接收到所述目标传感器发送的测量数据的下一时刻，将所述待发送队列中的所有测量数据上传至云服务器；
当所述预设时长内未接收到所述目标传感器发送的测量数据时，在计时结束后，将所述待发送队列中的所有测量数据上传至云服务器。
该技术方案的有益效果在于：在实际应用中，可能存在部分传感器自身失效或者与控制器之间的连接中断的情况，此时，由于这部分传感器的测量数据始终没有进入待发送队列，则队列中的测量数据始终无法达到齐全的条件，云服务器将无法获取无负压叠压供水设备的测量数据；通过设置合适的预设时长，在测量数据不齐全时向目标传感器请求数据并开始计时，如果计时结束仍未得到响应，则意味着该目标传感器可能无法再提供数据，因此可以直接将所有测量数据上传，不必等待目标传感器对应的测量数据。由此，避免部分传感器无法提供测量数据时，无负压叠压供水设备无法上传数据至云服务器的情况。
附图说明
下面结合附图和实施例对本申请进一步说明。
图1是本申请实施例提供的一种无负压叠压供水设备的侧视图；
图2是本申请实施例提供的一种无负压叠压供水设备的俯视图；
图3是本申请实施例提供的一种自我诊断方法的流程框架示意图；
图4是本申请实施例提供的一种自我诊断方法的流程示意图；
图5是本申请实施例提供的一种运行参数对应的预设范围的获取过程的流程示意图；
图6是本申请实施例提供的一种故障检测模型的训练过程的流程示意图；
图7是本申请实施例提供的一种自我诊断方法的部分流程示意图；
图8是本申请实施例提供的另一种自我诊断方法的部分流程示意图；
图9是本申请实施例提供的又一种自我诊断方法的部分流程示意图；
图10是本申请实施例提供的又一种自我诊断方法的部分流程示意图；
图11是本申请实施例提供的又一种自我诊断方法的部分流程示意图；
图12是本申请实施例提供的一种电子设备的结构示意图；
图13是本申请实施例提供的一种用于实现自我诊断方法的程序产品的结构示意图。
图中：10、底座；20、螺栓；30、电机；40、水泵；50、软接头；60、密封垫；70、管 路；11、底座振动传感器；21、螺栓松动传感器；31、电机温度传感器；32、电机电流传感器；33、电机电压传感器；41、水泵温度传感器；42、水泵振动传感器；43、水泵转速传感器；71、管路压力传感器。
具体实施方式
下面，结合附图以及具体实施方式，对本申请做进一步描述，需要说明的是，在不相冲突的前提下，以下描述的各实施例之间或各技术特征之间可以任意组合形成新的实施例。
参见图1和图2，本申请提供了一种无负压叠压供水设备，所述无负压叠压供水设备包括：
底座10，所述底座10设置有底座振动传感器11，用以获取所述无负压叠压供水设备的底座振动参数的测量数据；
管路70，所述管路70设置在所述底座10上，所述管路70的进水口与水箱的出水口连接，所述管路70的出水口与稳流罐的进水口连接，所述管路70设置有管路压力传感器71；
螺栓20，所述螺栓20设置于所述管路70的进水口，所述螺栓20设置有螺栓松动传感器21，用以检测所述螺栓20是否发生松动，得到螺栓松动参数的测量数据；
多个水泵机组，每个所述水泵机组包括水泵40和电机30，每个所述水泵40设置于所述底座10上，每个所述电机30设置于对应的水泵40上，每个所述水泵40设置有水泵温度传感器41、水泵振动传感器42和水泵转速传感器43，用以获取每个所述水泵40的水泵温度参数、水泵振动参数和水泵转速参数的测量数据，每个所述电机30设置有电机温度传感器31、电机电流传感器32和电机电压传感器33，用以获取每个所述电机30的电机温度参数、电机电流参数和电机电压参数的测量数据；
控制器，所述控制器分别与所述底座振动传感器11、所述管路压力传感器71、所述螺栓松动传感器21、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器电连接，所述控制器存储有故障检测模型和故障数据库，所述控制器被配置成实现自我诊断方法所述的步骤。其中，自我诊断方法将在下文进行说明。
无负压叠压供水设备设置有多个水泵机组，每个水泵机组包括水泵和电机，每个水泵和电机又分别设置有多个传感器，上述“多个所述水泵温度传感器”是指无负压叠压供水设备的所有水泵机组对应的全部水泵温度传感器，“多个所述水泵振动传感器、多个所述水泵转 速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器”以此类推。
与之类似，无负压叠压供水设备可以设置有多个螺栓，每个螺栓可以设置有螺栓松动传感器。
本申请对“多个水泵机组”中“多个”对应的数量不做限定，其可以是3、4、5等。
在如图2所示的一个实施例中，无负压叠压供水设备设置有3个水泵机组，则该无负压叠压供水设备一共设置有3个水泵、3个电机、3个水泵温度传感器、3个水泵振动传感器、3个水泵转速传感器、3个电机温度传感器、3个电机电流传感器和3个电机电压传感器。
在一个实施例中，控制器可以是PLC控制器。
参见图3，在一个实施例中，控制器和每个传感器之间可以设置有数据通信电路。
参见图4，本申请还提供了一种自我诊断方法，用于为无负压叠压供水设备提供自我诊断功能。本方法对所述无负压叠压供水设备不做限定，所述无负压叠压供水设备例如是图1和图2中的无负压叠压供水设备，也可以是能够应用本方法的其他无负压叠压供水设备。
所述方法包括：
步骤S101：获取所述无负压叠压供水设备的多个运行参数的测量数据，多个所述运行参数包括底座振动参数、管路压力参数、螺栓松动参数、软接头使用参数、密封垫使用参数、水泵温度参数、水泵振动参数、水泵转速参数、电机温度参数、电机电流参数和电机电压参数中的至少两个；
步骤S102：分别检测每个所述运行参数的测量数据是否处于自身对应的预设范围；
步骤S103：当检测到至少一个所述运行参数的测量数据不处于自身对应的预设范围时，将多个所述运行参数的测量数据作为故障检测模型的第一输入，通过所述故障检测模型输出所述第一输入对应的预测故障类型和预测相似度；
其中，所述故障检测模型用于将所述第一输入分别与故障数据库中的每个故障数据进行比对，得到所述第一输入与每个故障数据的相似度，将所述第一输入对应的多个相似度中最高的相似度作为所述第一输入对应的预测相似度，将与所述第一输入相似度最高的故障数据的故障类型作为所述第一输入对应的预测故障类型，并且输出所述第一输入对应的预测故障类型和预测相似度；
步骤S104：当所述第一输入对应的预测相似度小于预设相似度阈值时确定无故障发生， 当所述第一输入对应的预测相似度不小于所述预设相似度阈值时确定有故障发生。
在一个实施例中，软接头使用参数例如是软接头使用时长，密封垫使用参数例如是密封垫使用时长。
本申请对步骤S101中的“至少两个”不做限定，其可以是2、3、5、8、10或者11。在一个实施例中，多个所述运行参数例如可以包括底座振动参数、管路压力参数、螺栓松动参数、软接头使用参数、密封垫使用参数、水泵温度参数、水泵振动参数、水泵转速参数、电机温度参数、电机电流参数和电机电压参数中的部分。在另一个实施例中，多个所述运行参数例如可以包括底座振动参数、管路压力参数、螺栓松动参数、软接头使用参数、密封垫使用参数、水泵温度参数、水泵振动参数、水泵转速参数、电机温度参数、电机电流参数和电机电压参数中的全部。
其中，当无负压叠压供水设备的水泵的数量大于1个时，无负压叠压供水设备的水泵温度参数的测量数据可以包括每个水泵的水泵温度传感器分别采集到的测量数据，水泵振动参数、水泵转速参数、电机温度参数、电机电流参数和电机电压参数以此类推，此处不做赘述。例如，当水泵的数量是3个时，水泵温度参数的测量数据可以包括第一水泵的水泵温度传感器采集到的测量数据、第二水泵的水泵温度传感器采集到的测量数据和第三水泵的水泵温度传感器采集到的测量数据。
在一个实施例中，故障数据库中有100种故障数据，每种故障数据具有对应的故障类型，故障类型可以用字母、数字、汉字和特殊符号中的一个或多个来标识，例如可以表示成“E4”、“水泵故障”、“#螺栓松动#”等。故障检测模型将第一输入分别与100种故障数据进行比对，得到100个相似度，例如是：30％、60％、……、98％、……、74％、88％，将其中最高的相似度98％作为预测相似度，将该98％相似度对应的故障数据的故障类型作为预测故障类型。
本申请对预设相似度阈值的选取不做限定，在一些实施例中，预设相似度阈值例如是90％、95％或者99％。
上述方法使用两个阶段的检测过程来判断是否有故障发生，当第一阶段检测到可能发生故障时，并非直接判断为发生故障，而是进入第二阶段的故障检测，当第二阶段也检测到可能发生故障时，才确定无负压叠压供水设备发生故障，由此，所得到的故障检测结果可信度高，避免频繁误判，影响无负压叠压供水设备的正常使用。
具体而言，在第一阶段，使用多个传感器获取多个运行参数的测量数据，分别检测每个 运行参数的测量数据是否处于自身对应的预设范围，当存在一个或多个运行参数的测量数据超出自身对应的预设范围时，表明无负压叠压供水设备有可能发生故障，这时候进入第二阶段；在第二阶段，将多个运行参数的测量数据输入故障检测模型，利用故障检测模型确定无负压叠压供水设备在当前运行过程中最接近的故障类型作为预测故障类型，故障检测模型还会同时给出输入数据与该预测故障类型的相似度作为预测相似度，通过比较预测相似度与预设相似度阈值的大小来判断是否有故障发生。显然，相似度越高，无负压叠压供水设备越有可能发生了该预测故障类型所对应的故障。
另外，以多个运行参数的测量数据作为故障检测模型的输入数据，考虑到了多个运行参数之间的关联性，针对多个运行参数的测量数据进行综合判定，避免单一运行参数的数值波动导致误判，而是将多个运行参数作为一个整体，与故障数据库中预先存储的多个故障数据逐一进行比对，找出相似度最高的故障数据，并将该故障数据对应的故障类型作为预测故障类型，进一步提高了故障检测结果的准确性。
下面针对多个运行参数之间的关联性进行举例说明。在维持恒定流量的前提下，管路压力参数、水泵转速参数之间的关系是正相关的，即，水泵转速参数的测量数据越大，管路压力参数的测量数据越大。
1)当无负压叠压供水设备的一个水泵的水泵转速参数的测量数据超出自身对应的预设范围(超出是指测量数据大于预设范围的最大值)，并且管路压力参数的测量数据超出自身对应的预设范围时，有可能是水泵发生故障；
2)当无负压叠压供水设备的多个水泵的水泵转速参数的测量数据均处于自身对应的预设范围，而管路压力参数的测量数据大大超出自身对应的预设范围时，有可能是管路压力传感器自身发生故障，导致采集到的测量数据失真；
3)当无负压叠压供水设备的多个水泵的水泵转速参数的测量数据均大大超出自身对应的预设范围，而管路压力参数的测量数据却仍处于自身对应的预设范围时，有可能是管路发生故障，例如发生了管道泄露的情况。
由此可见，即使管路压力参数超出预设范围，也不一定对应唯一的故障类型，综合考虑多个运行参数，才能准确判断故障类型。
参见图5，在一些可选的实施例中，每个所述运行参数对应的预设范围的获取过程如下：
步骤S201：针对每个所述运行参数，当所述无负压叠压供水设备处于正常运行状态时，分别记录所述运行参数在多个预设时刻的测量数据；
步骤S202：利用所述运行参数在多个预设时刻的测量数据求取平均值；
步骤S203：获取包含所述平均值的预设范围，所述预设范围的最大值与最小值的差值与所述平均值之比是所述运行参数对应的预设常数。
本申请对多个预设时刻的选取不做限定，在一个实施例中，多个预设时刻例如是间隔5分钟的多个预设时刻。
每个运行参数对应的预设常数可以是相同的，也可以是不同的。在一个实施例中，底座振动参数、管路压力参数、螺栓松动参数、软接头使用参数、密封垫使用参数、水泵温度参数、水泵振动参数、水泵转速参数、电机温度参数、电机电流参数和电机电压参数对应的预设常数可以都是10％。
由此，在无负压叠压供水设备处于正常运行状态时，记录多个预设时刻的测量数据并求取平均值，所得到的平均值能够作为该运行参数在正常运行过程中的参考数值，在此基础上，设置适当的波动幅度，得到包含该平均值的预设范围，所得到的预设范围具有较高的参考价值。不同的运行参数其数值相差很大，可能不是一个数量级，因此，为每个运行参数设置相同或不同的预设常数，再设置预设范围的最大值与最小值的差值与平均值之比是该运行参数对应的预设常数，由此来限定不同运行参数的波动幅度，所得到的预设范围准确、合理，更符合实际应用中的需求。
参见图6，在一些可选的实施例中，所述故障检测模型的训练过程如下：
步骤S301：获取训练集，所述训练集中的每个训练数据包括多个运行参数的样本数据及其对应的标注故障类型和标注相似度，所述样本数据是实际测量得到的或者利用GAN模型的生成网络生成的；
步骤S302：针对每个所述训练数据，将所述训练数据中的多个运行参数的样本数据作为预设的深度学习模型的第二输入，通过所述预设的深度学习模型输出所述第二输入对应的预测故障类型和预测相似度；其中，所述预设的深度学习模型用于将所述第二输入分别与所述故障数据库中的每个故障数据进行比对，得到所述第二输入与每个故障数据的相似度，将所述第二输入对应的多个相似度中最高的相似度作为所述第二输入对应的预测相似度，将与所述第二输入相似度最高的故障数据的故障类型作为所述第二输入对应的预测故障类型，并且输出所述第二输入对应的预测故障类型和预测相似度；
步骤S303：基于所述第二输入对应的预测故障类型和预测相似度以及所述第二输入对应的标注故障类型和标注相似度，更新所述预设的深度学习模型的模型参数；
步骤S304：检测是否满足预设的训练结束条件，如果是，则停止训练，并将训练得到的所述预设的深度学习模型作为所述故障检测模型，如果否，则利用下一个所述训练数据继续训练所述预设的深度学习模型。
其中，GAN模型即生成对抗网络(Generative Adversarial Network)，由一个生成网络与一个判别网络组成。生成网络从潜在空间(latent space)中随机采样作为输入，其输出结果需要尽量模仿训练集中的真实样本。判别网络的输入则为真实样本或生成网络的输出，其目的是将生成网络的输出从真实样本中尽可能分辨出来。而生成网络则要尽可能地欺骗判别网络。两个网络相互对抗、不断调整参数，最终目的是使判别网络无法判断生成网络的输出结果是否真实。使用GAN模型可以生成多个运行参数的样本数据，用于故障检测模型的训练过程，能有效降低原始数据采集的数据量，大大降低数据采集和标注的成本。
预设的训练结束条件可以根据实际需求设定，本申请在此不对其做任何限定。在一个实施例中，预设的训练结束条件可以是达到预设的训练次数。
由此，利用训练集对预设的深度学习模型进行训练，得到故障检测模型，故障检测模型可以由大量的训练数据训练得到，能够针对多种输入数据预测得到相应的故障检测结果，适用范围广，智能化水平高。通过设计，建立适量的神经元计算节点和多层运算层次结构，选择合适的输入层和输出层，就可以得到预设的深度学习模型，通过该预设的深度学习模型的学习和调优，建立起从输入到输出的函数关系，虽然不能100％找到输入与输出的函数关系，但是可以尽可能地逼近现实的关联关系，由此训练得到的故障检测模型，可以实现对故障检测的自我诊断功能，且诊断结果可靠性高。
在一个实施例中，故障检测模型是利用预设的深度学习模型训练得到的。在另一实施例中，故障检测模型可以是利用预设的机器学习模型训练得到的。在又一实施例中，故障检测模型可以是利用预设的线性回归模型优化得到的。
参见图7，在一些可选的实施例中，所述方法除了步骤S101～S104之外，还可以包括：
步骤S105：当所述第一输入对应的预测相似度不小于所述预设相似度阈值时，生成第一自诊断报告，所述第一自诊断报告包括所述第一输入对应的预测故障类型；
步骤S1061：基于所述第一自诊断报告，获取所述第一输入对应的预测故障类型所对应的第一解决策略；
步骤S1071：生成包含所述第一解决策略的故障报警信息，并发送至预设的用户设备。
其中，第一自诊断报告例如是txt格式、doc格式、xls格式或者csv格式。
预设的用户设备一般是工作人员的终端设备，其设备类型例如可以包括手机、平板电脑、台式机和智能穿戴设备中的一个或多个。
参见图8，在另一些可选的实施例中，所述方法除了步骤S101～S104之外，还可以包括：
步骤S105：当所述第一输入对应的预测相似度不小于所述预设相似度阈值时，生成第一自诊断报告，所述第一自诊断报告包括所述第一输入对应的预测故障类型；
步骤S1062：基于所述第一自诊断报告，获取所述第一输入对应的预测故障类型所对应的第一解决策略和第一通信等级，每个通信等级对应预设的一个或多个用户设备；
步骤S1072：生成包含所述第一解决策略的故障报警信息，并发送至所述第一通信等级对应的用户设备。
由此，为报告的生成和发送设置筛选条件，如果与最相似的故障数据的相似度仍然不是很高，例如预测相似度只有20％或者35％，没有达到预设相似度阈值(例如是85％)，则可判定没有故障发生，因此也不需要生成故障的自诊断报告并发送；只有当预测相似度大于预设相似度阈值时，判断有故障发生，才会需要生成报告并发送。只有当预测相似度足够高时，才涉及自诊断报告的生成和发送过程，避免无故障发生时重复调用计算资源，节能环保。另外，针对不同的预测故障类型，设置多个通信等级，分别对应不同的用户设备(即通知到的工作人员不同)，例如寿命、温度相关故障对应较低的通信等级，故障报警信息只需要发送给本片区维修人员，水泵、电机相关故障对应较高的通信等级，故障报警信息需要发送给本片区维修人员和本片区负责人。这样就可以根据预测故障类型的重要程度，通知不同的工作人员，实现故障报警信息的差异化推送，智能化程度高，更加符合实际应用中的需求。
参见图9，在一些可选的实施例中，所述方法除了步骤S101～S104之外，还可以包括：
步骤S108：当检测到至少一个所述运行参数的测量数据不处于自身对应的预设范围时，生成第二自诊断报告，所述第二自诊断报告包括不处于自身预设范围的运行参数对应的部件名称和预设问题类型；
步骤S109：基于所述第二自诊断报告，生成包含所述部件名称和所述预设问题类型的问题预警信息，并发送至预设的用户设备，以及利用显示设备显示所述部件名称和所述预设问题类型。
其中，部件名称可以用字母、数字、汉字和特殊符号中的一个或多个来标识，例如可以表示成“A5”、“水泵B”、“电机01”、“螺栓#306”等。第二自诊断报告中的预设问题类型可以是一个或多个，以供工作人员参考。预设问题类型可以用字母、数字、汉字和特 殊符号中的一个或多个来标识，例如可以表示成“A5”、“水泵故障01”、“管道漏水”、“螺栓松动”等。
由此，在第一阶段检测到有运行参数不处于预设范围时，虽然尚未通过第二阶段得到是否发生故障的最终结果，但部分运行参数运行超出正常范围的情况依然意味着运行过程中可能存在问题，可以作为值得警惕的现象，及时提醒相关工作人员注意。另外，在问题预警信息中给出可能存在问题的部件名称和预设问题类型，一方面辅助工作人员做出判断，另一方面，出问题的部件不同，所需要的检测、维修工具不同，在问题预警信息中给出上述信息，方便工作人员携带对应工具前去处理，避免临时发现有工具忘记带的情况，提高问题处理效率。
参见图10，在一些可选的实施例中，所述方法除了步骤S101～S104之外，还可以包括：
步骤S110：当所述无负压叠压供水设备开始投入运行时，生成目标部件的维修保养计划，所述目标部件分别是软接头和密封垫中的每一个，所述目标部件的维修保养计划包括所述目标部件的使用寿命；
步骤S1111：基于所述目标部件的维修保养计划，当检测到所述目标部件的使用时长达到自身的使用寿命时，生成所述目标部件的维修保养任务单并发送至预设的用户设备。
例如软接头的使用寿命是30000小时，当检测到软接头的使用时长达到30000小时时，生成软接头的维修保养任务单并发送。
参见图11，在另一些可选的实施例中，所述方法除了步骤S101～S104之外，还可以包括：
步骤S110：当所述无负压叠压供水设备开始投入运行时，生成目标部件的维修保养计划，所述目标部件分别是软接头和密封垫中的每一个，所述目标部件的维修保养计划包括所述目标部件的使用寿命；
步骤S1112：基于所述目标部件的维修保养计划，当检测到所述目标部件自身的使用寿命与其使用时长的差值不大于预设时长阈值时，生成所述目标部件的维修保养任务单并发送至预设的用户设备。
其中，预设时长阈值例如是100小时。
由此，针对具有使用寿命的零部件，从开始运行起就建立维修保养计划，当零部件的使用时长达到自身寿命时，自动生成维修保养任务单并派发给相关工作人员，以便及时维修或者更换对应零部件，避免零部件老化造成重大故障发生，科学、合理地防范零部件老化带来 的安全隐患。
参见上述方法实施例中的表述，本申请提供的一种无负压叠压供水设备，其控制器能够执行两个阶段的故障检测，其故障检测结果准确度高。
在一些可选的实施例中，所述控制器还可以被配置成：
当接收到所述底座振动传感器、所述管路压力传感器、所述螺栓松动传感器、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器中的任意一个发送的测量数据时，将接收到的测量数据放入待发送队列；
检测所述待发送队列中的测量数据的数量是否不小于预设数量阈值；
当检测到所述待发送队列中的测量数据的数量不小于所述预设数量阈值时，将所述待发送队列中的所有测量数据上传至云服务器。
其中，预设数量阈值例如是11、15、20等。在一个实施例中，无负压叠压供水设备设置有3个水泵机组，则该无负压叠压供水设备设置有1个底座振动传感器、1个管路压力传感器、1个螺栓松动传感器、3个水泵温度传感器、3个水泵振动传感器、3个水泵转速传感器、3个电机温度传感器、3个电机电流传感器和3个电机电压传感器，即共设置有21个传感器，预设数量阈值可以设置为21。
由此，为数据上传设置条件，采用待发送队列存储待发送的测量数据，当队列中存在足够数量的测量数据时再上传所有数据，也就是说，并非每次接收到传感器发送的测量数据时都立刻进行数据上传，由此大大减少访问云服务器的次数，极大降低了云服务器的数据处理压力。
在一些可选的实施例中，所述控制器可以被进一步配置成采用如下方式上传数据：
当检测到所述待发送队列中的测量数据的数量不小于预设数量阈值时，判断所述待发送队列中的测量数据是否齐全；
当所述待发送队列中的测量数据齐全时，将所述待发送队列中的所有测量数据上传至云服务器；
其中，所述待发送队列中的测量数据齐全是指所述待发送队列中包含所述底座振动传感器、所述管路压力传感器、所述螺栓松动传感器、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感 器和多个所述电机电压传感器发送的测量数据。
由此，为数据上传设置进一步条件，待发送队列中的测量数据要想上传到云服务器，不仅数量要足够多，并且类型要齐全，测量数据齐全是指队列中存储有所有传感器发送的测量数据，这样可以确保每次提供给云服务器的数据涵盖了所有运行参数的测量数据，便于后续的数据挖掘分析工作。
在一些可选的实施例中，所述控制器还可以被配置成：
当所述待发送队列中的测量数据不齐全时，确定缺失测量数据的目标传感器；
向所述目标传感器发送数据获取请求，并开始计时；
当预设时长内接收到所述目标传感器发送的测量数据时，停止计时，并在接收到所述目标传感器发送的测量数据的下一时刻，将所述待发送队列中的所有测量数据上传至云服务器；
当所述预设时长内未接收到所述目标传感器发送的测量数据时，在计时结束后，将所述待发送队列中的所有测量数据上传至云服务器。
本申请对预设时长不做限定，其可以是1分钟、3分钟或者5分钟。
在上述设置有3个水泵机组的实施例中，预设数量阈值设置为21，当接收到第三电机的电机电压传感器发送的测量数据时，检测到所述待发送队列中的测量数据的数量是21，不小于预设数量阈值，仍需判断待发送队列中的测量数据是否齐全，因为待发送队列中可能存在同一传感器发送的多个数据。如果齐全则直接上传所有待发送队列中的所有测量数据，如果发现缺失了部分传感器的测量数据，则首先找出缺失测量数据的传感器。例如发现缺失了第二水泵的水泵转速传感器发送的测量数据，则向第二水泵的水泵转速传感器发送数据获取请求。
在实际应用中，可能存在部分传感器自身失效或者与控制器之间的连接中断的情况，此时，由于这部分传感器的测量数据始终没有进入待发送队列，则队列中的测量数据始终无法达到齐全的条件，云服务器将无法获取无负压叠压供水设备的测量数据；通过设置合适的预设时长，在测量数据不齐全时向目标传感器请求数据并开始计时，如果计时结束仍未得到响应，则意味着该目标传感器可能无法再提供数据，因此可以直接将所有测量数据上传，不必等待目标传感器对应的测量数据。由此，避免部分传感器无法提供测量数据时，无负压叠压供水设备无法上传数据至云服务器的情况。
参见图12，本申请实施例还提供了一种电子设备200，电子设备200包括至少一个存储 器210、至少一个处理器220以及连接不同平台系统的总线230。
存储器210可以包括易失性存储器形式的可读介质，例如随机存取存储器(RAM)211和/或高速缓存存储器212，还可以进一步包括只读存储器(ROM)213。
其中，存储器210还存储有计算机程序，计算机程序可以被处理器220执行，使得处理器220执行本申请实施例中自我诊断方法的步骤，其具体实现方式与上述自我诊断方法的实施例中记载的实施方式、所达到的技术效果一致，部分内容不再赘述。
存储器210还可以包括具有至少一个程序模块215的实用工具214，这样的程序模块215包括但不限于：操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。
相应的，处理器220可以执行上述计算机程序，以及可以执行实用工具214。
总线230可以为表示几类总线结构中的一种或多种，包括存储器总线或者存储器自我诊断方法、外围总线、图形加速端口、处理器或者使用多种总线结构中的任意总线结构的局域总线。
电子设备200也可以与一个或多个外部设备240例如键盘、指向设备、蓝牙设备等通信，还可与一个或者多个能够与该电子设备200交互的设备通信，和/或与使得该电子设备200能与一个或多个其它计算设备进行通信的任何设备(例如路由器、调制解调器等)通信。这种通信可以通过输入输出接口250进行。并且，电子设备200还可以通过网络适配器260与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络，例如因特网)通信。网络适配器260可以通过总线230与电子设备200的其它模块通信。应当明白，尽管图中未示出，可以结合电子设备200使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理器、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储平台等。
本申请实施例还提供了一种计算机可读存储介质，该计算机可读存储介质用于存储计算机程序，所述计算机程序被执行时实现本申请实施例中自我诊断方法的步骤，其具体实现方式与上述自我诊断方法的实施例中记载的实施方式、所达到的技术效果一致，部分内容不再赘述。
图13示出了本实施例提供的用于实现上述自我诊断方法的程序产品300，其可以采用便携式紧凑盘只读存储器(CD-ROM)并包括程序代码，并可以在终端设备，例如个人电脑上运行。然而，本发明的程序产品300不限于此，在本申请中，可读存储介质可以是任何包含 或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。程序产品300可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以为但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
计算机可读存储介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。可读存储介质还可以是任何可读介质，该可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。可读存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、有线、光缆、RF等，或者上述的任意合适的组合。可以以一种或多种程序设计语言的任意组合来编写用于执行本发明操作的程序代码，程序设计语言包括面向对象的程序设计语言诸如Java、C++等，还包括常规的过程式程序设计语言诸如C语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中，远程计算设备可以通过任意种类的网络，包括局域网(LAN)或广域网(WAN)，连接到用户计算设备，或者，可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”、“第五”、“第六”、“第七”、“第八”、“第九”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“对应于”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
本申请从使用目的上，效能上，进步及新颖性等观点进行阐述，已符合专利法所强调的 功能增进及使用要件，本申请以上的说明书及说明书附图，仅为本申请的较佳实施例而已，并非以此局限本申请，因此，凡一切与本申请构造，装置，特征等近似、雷同的，即凡依本申请专利申请范围所作的等同替换或修饰等，皆应属本申请的专利申请保护的范围之内。

Claims (10)

  1. 一种用于为无负压叠压供水设备提供自我诊断功能的自我诊断方法，其特征在于，用于为无负压叠压供水设备提供自我诊断功能，所述方法包括：
    获取所述无负压叠压供水设备的多个运行参数的测量数据，多个所述运行参数包括底座振动参数、管路压力参数、螺栓松动参数、软接头使用参数、密封垫使用参数、水泵温度参数、水泵振动参数、水泵转速参数、电机温度参数、电机电流参数和电机电压参数中的至少两个；
    分别检测每个所述运行参数的测量数据是否处于自身对应的预设范围；
    当检测到至少一个所述运行参数的测量数据不处于自身对应的预设范围时，将多个所述运行参数的测量数据作为故障检测模型的第一输入，通过所述故障检测模型输出所述第一输入对应的预测故障类型和预测相似度；其中，所述故障检测模型用于将所述第一输入分别与故障数据库中的每个故障数据进行比对，得到所述第一输入与每个故障数据的相似度，将所述第一输入对应的多个相似度中最高的相似度作为所述第一输入对应的预测相似度，将与所述第一输入相似度最高的故障数据的故障类型作为所述第一输入对应的预测故障类型，并且输出所述第一输入对应的预测故障类型和预测相似度；
    当所述第一输入对应的预测相似度小于预设相似度阈值时确定无故障发生，当所述第一输入对应的预测相似度不小于所述预设相似度阈值时确定有故障发生。
  2. 根据权利要求1所述的用于为无负压叠压供水设备提供自我诊断功能的自我诊断方法，其特征在于，每个所述运行参数对应的预设范围的获取过程如下：
    针对每个所述运行参数，当所述无负压叠压供水设备处于正常运行状态时，分别记录所述运行参数在多个预设时刻的测量数据；
    利用所述运行参数在多个预设时刻的测量数据求取平均值；
    获取包含所述平均值的预设范围，所述预设范围的最大值与最小值的差值与所述平均值之比是所述运行参数对应的预设常数。
  3. 根据权利要求1所述的用于为无负压叠压供水设备提供自我诊断功能的自我诊断方法，其特征在于，所述故障检测模型的训练过程如下：
    获取训练集，所述训练集中的每个训练数据包括多个运行参数的样本数据及其对应的标注故障类型和标注相似度，所述样本数据是实际测量得到的或者利用GAN模型的生成网络生成的；
    针对每个所述训练数据，将所述训练数据中的多个运行参数的样本数据作为预设的深度 学习模型的第二输入，通过所述预设的深度学习模型输出所述第二输入对应的预测故障类型和预测相似度；其中，所述预设的深度学习模型用于将所述第二输入分别与所述故障数据库中的每个故障数据进行比对，得到所述第二输入与每个故障数据的相似度，将所述第二输入对应的多个相似度中最高的相似度作为所述第二输入对应的预测相似度，将与所述第二输入相似度最高的故障数据的故障类型作为所述第二输入对应的预测故障类型，并且输出所述第二输入对应的预测故障类型和预测相似度；
    基于所述第二输入对应的预测故障类型和预测相似度以及所述第二输入对应的标注故障类型和标注相似度，更新所述预设的深度学习模型的模型参数；
    检测是否满足预设的训练结束条件，如果是，则停止训练，并将训练得到的所述预设的深度学习模型作为所述故障检测模型，如果否，则利用下一个所述训练数据继续训练所述预设的深度学习模型；
    其中，预设的训练结束条件是达到预设的训练次数。
  4. 根据权利要求1所述的用于为无负压叠压供水设备提供自我诊断功能的自我诊断方法，其特征在于，所述方法还包括：
    当所述第一输入对应的预测相似度不小于所述预设相似度阈值时，生成第一自诊断报告，所述第一自诊断报告包括所述第一输入对应的预测故障类型；
    基于所述第一自诊断报告，获取所述第一输入对应的预测故障类型所对应的第一解决策略和第一通信等级，每个通信等级对应预设的一个或多个用户设备；
    生成包含所述第一解决策略的故障报警信息，并发送至所述第一通信等级对应的用户设备。
  5. 根据权利要求1所述的用于为无负压叠压供水设备提供自我诊断功能的自我诊断方法，其特征在于，所述方法还包括：
    当检测到至少一个所述运行参数的测量数据不处于自身对应的预设范围时，生成第二自诊断报告，所述第二自诊断报告包括不处于自身预设范围的运行参数对应的部件名称和预设问题类型；
    基于所述第二自诊断报告，生成包含所述部件名称和所述预设问题类型的问题预警信息，并发送至预设的用户设备，以及利用显示设备显示所述部件名称和所述预设问题类型。
  6. 根据权利要求1所述的用于为无负压叠压供水设备提供自我诊断功能的自我诊断方法，其特征在于，所述方法还包括：
    当所述无负压叠压供水设备开始投入运行时，生成目标部件的维修保养计划，所述目标部件分别是软接头和密封垫中的每一个，所述目标部件的维修保养计划包括所述目标部件的使用寿命；
    基于所述目标部件的维修保养计划，当检测到所述目标部件的使用时长达到自身的使用寿命时，生成所述目标部件的维修保养任务单并发送至预设的用户设备。
  7. 一种无负压叠压供水设备，其特征在于，包括：
    底座，所述底座设置有底座振动传感器，用以获取所述无负压叠压供水设备的底座振动参数的测量数据；
    管路，所述管路设置在所述底座上，所述管路的进水口与水箱的出水口连接，所述管路的出水口与稳流罐的进水口连接，所述管路设置有管路压力传感器；
    螺栓，所述螺栓设置于所述管路的进水口，所述螺栓设置有螺栓松动传感器，用以检测所述螺栓是否发生松动，得到螺栓松动参数的测量数据；
    多个水泵机组，每个所述水泵机组包括水泵和电机，每个所述水泵设置于所述底座上，每个所述电机设置于对应的水泵上，每个所述水泵设置有水泵温度传感器、水泵振动传感器和水泵转速传感器，用以获取每个所述水泵的水泵温度参数、水泵振动参数和水泵转速参数的测量数据，每个所述电机设置有电机温度传感器、电机电流传感器和电机电压传感器，用以获取每个所述电机的电机温度参数、电机电流参数和电机电压参数的测量数据；
    控制器，所述控制器分别与所述底座振动传感器、所述管路压力传感器、所述螺栓松动传感器、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器电连接，所述控制器存储有故障检测模型和故障数据库，所述控制器被配置成实现权利要求1-6任一项方法所述的步骤。
  8. 根据权利要求7所述的无负压叠压供水设备，其特征在于，所述控制器还被配置成：
    当接收到所述底座振动传感器、所述管路压力传感器、所述螺栓松动传感器、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器中的任意一个发送的测量数据时，将接收到的测量数据放入待发送队列；
    检测所述待发送队列中的测量数据的数量是否不小于预设数量阈值；
    当检测到所述待发送队列中的测量数据的数量不小于所述预设数量阈值时，将所述待发 送队列中的所有测量数据上传至云服务器。
  9. 根据权利要求8所述的无负压叠压供水设备，其特征在于，所述控制器被进一步配置成采用如下方式上传数据：
    当检测到所述待发送队列中的测量数据的数量不小于预设数量阈值时，判断所述待发送队列中的测量数据是否齐全；
    当所述待发送队列中的测量数据齐全时，将所述待发送队列中的所有测量数据上传至云服务器；
    其中，所述待发送队列中的测量数据齐全是指所述待发送队列中包含所述底座振动传感器、所述管路压力传感器、所述螺栓松动传感器、多个所述水泵温度传感器、多个所述水泵振动传感器、多个所述水泵转速传感器、多个所述电机温度传感器、多个所述电机电流传感器和多个所述电机电压传感器发送的测量数据。
  10. 根据权利要求9所述的无负压叠压供水设备，其特征在于，所述控制器还被配置成：
    当所述待发送队列中的测量数据不齐全时，确定缺失测量数据的目标传感器；
    向所述目标传感器发送数据获取请求，并开始计时；
    当预设时长内接收到所述目标传感器发送的测量数据时，停止计时，并在接收到所述目标传感器发送的测量数据的下一时刻，将所述待发送队列中的所有测量数据上传至云服务器；
    当所述预设时长内未接收到所述目标传感器发送的测量数据时，在计时结束后，将所述待发送队列中的所有测量数据上传至云服务器。
PCT/CN2022/128821 2021-11-30 2022-10-31 自我诊断方法和无负压叠压供水设备 WO2023098372A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111440578.5 2021-11-30
CN202111440578.5A CN113931258B (zh) 2021-11-30 2021-11-30 自我诊断方法和无负压叠压供水设备

Publications (1)

Publication Number Publication Date
WO2023098372A1 true WO2023098372A1 (zh) 2023-06-08

Family

ID=79288686

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/128821 WO2023098372A1 (zh) 2021-11-30 2022-10-31 自我诊断方法和无负压叠压供水设备

Country Status (2)

Country Link
CN (1) CN113931258B (zh)
WO (1) WO2023098372A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116634037A (zh) * 2023-07-25 2023-08-22 水利部机电研究所 一种用于水泵智能诊断的数据传输方法及系统

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113931258B (zh) * 2021-11-30 2022-06-24 无锡汇田水务科技有限公司 自我诊断方法和无负压叠压供水设备
CN114353854B (zh) * 2022-03-21 2022-05-24 蘑菇物联技术（深圳）有限公司 用于在线定位异常传感器的方法、设备和介质
CN115022151B (zh) * 2022-07-04 2023-06-23 青岛佳世特尔智创科技有限公司 一种泵机组状态监测分析方法及系统
CN115199518A (zh) * 2022-07-22 2022-10-18 无锡汇田水务科技有限公司 排污泵的控制方法、装置、电子设备及存储介质
CN116328244B (zh) * 2023-03-21 2023-09-01 江苏智慧工场技术研究院有限公司 一种消防巡检方法、系统及存储介质

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105354755A (zh) * 2015-09-30 2016-02-24 冯小林 基于物联网的供水设备的管理方法
CN107862375A (zh) * 2017-10-30 2018-03-30 北京计算机技术及应用研究所 一种两阶段的设备故障诊断方法
CN107885189A (zh) * 2017-11-14 2018-04-06 北京煜邦电力技术股份有限公司 供水设备监控方法及装置
CN107957277A (zh) * 2017-12-21 2018-04-24 重庆金鑫科技产业发展有限公司 一种无负压二次供水设备的检测系统
CN209556031U (zh) * 2018-12-14 2019-10-29 浙江正同水务设备有限公司 带故障检测功能的无负压供水设备
CN110469495A (zh) * 2018-05-11 2019-11-19 上海威派格智慧水务股份有限公司 一种多水泵供水系统的故障诊断方法
CN110765619A (zh) * 2019-10-28 2020-02-07 中国人民解放军63921部队 基于多状态参数的无失效屏蔽泵故障短期多步预测方法
KR102147610B1 (ko) * 2019-12-23 2020-08-25 (주) 그린텍아이엔씨 자가진단 및 자가복구 기능을 갖는 스마트형 상하수도 원방 감시장치
CN113931258A (zh) * 2021-11-30 2022-01-14 无锡汇田水务科技有限公司 自我诊断方法和无负压叠压供水设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0896039A (ja) * 1994-09-29 1996-04-12 Akira Hayashi 水道管路情報管理装置
DE102019124985A1 (de) * 2019-09-17 2021-03-18 Livisi Gmbh Hausautomationssystem

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105354755A (zh) * 2015-09-30 2016-02-24 冯小林 基于物联网的供水设备的管理方法
CN107862375A (zh) * 2017-10-30 2018-03-30 北京计算机技术及应用研究所 一种两阶段的设备故障诊断方法
CN107885189A (zh) * 2017-11-14 2018-04-06 北京煜邦电力技术股份有限公司 供水设备监控方法及装置
CN107957277A (zh) * 2017-12-21 2018-04-24 重庆金鑫科技产业发展有限公司 一种无负压二次供水设备的检测系统
CN110469495A (zh) * 2018-05-11 2019-11-19 上海威派格智慧水务股份有限公司 一种多水泵供水系统的故障诊断方法
CN209556031U (zh) * 2018-12-14 2019-10-29 浙江正同水务设备有限公司 带故障检测功能的无负压供水设备
CN110765619A (zh) * 2019-10-28 2020-02-07 中国人民解放军63921部队 基于多状态参数的无失效屏蔽泵故障短期多步预测方法
KR102147610B1 (ko) * 2019-12-23 2020-08-25 (주) 그린텍아이엔씨 자가진단 및 자가복구 기능을 갖는 스마트형 상하수도 원방 감시장치
CN113931258A (zh) * 2021-11-30 2022-01-14 无锡汇田水务科技有限公司 自我诊断方法和无负压叠压供水设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116634037A (zh) * 2023-07-25 2023-08-22 水利部机电研究所 一种用于水泵智能诊断的数据传输方法及系统
CN116634037B (zh) * 2023-07-25 2023-09-29 水利部机电研究所 一种用于水泵智能诊断的数据传输方法及系统

Also Published As

Publication number Publication date
CN113931258A (zh) 2022-01-14
CN113931258B (zh) 2022-06-24

Similar Documents

Publication Publication Date Title
WO2023098372A1 (zh) 自我诊断方法和无负压叠压供水设备
EP3902992B1 (en) Scalable system and engine for forecasting wind turbine failure
US12019436B2 (en) System and method for proactive handling of multiple faults and failure modes in an electrical network of energy assets
CN110991666B (zh) 故障检测方法、模型的训练方法、装置、设备及存储介质
CN112727965B (zh) 采煤机制动器的故障监测方法及装置
CN111045894B (zh) 数据库异常检测方法、装置、计算机设备和存储介质
US20130060524A1 (en) Machine Anomaly Detection and Diagnosis Incorporating Operational Data
CN112136161B (zh) 用于智能报警分组的系统和方法
CN109976975B (zh) 一种磁盘容量预测方法、装置、电子设备及存储介质
CN109088775B (zh) 异常监控方法、装置以及服务器
JP2012242159A (ja) システムの高い可用性のためにセンサデータを補間する方法、コンピュータプログラム、システム。
CN109948937B (zh) 人工智能自学习的安全隐患检测方法、系统、设备及介质
CN117041029A (zh) 网络设备故障处理方法、装置、电子设备及存储介质
CN114398354A (zh) 数据监测方法、装置、电子设备及存储介质
CN114819225A (zh) 一种海上能源机组智能化运维方法及系统
CN117235664A (zh) 配电通信设备的故障诊断方法、系统和计算机设备
CN115599077A (zh) 车辆故障定界方法、装置、电子设备及存储介质
CN113487086B (zh) 设备剩余使用寿命预测方法、装置、计算机设备和介质
CN115951170B (zh) 输电线路故障监测方法、装置、计算机设备和存储介质
CN116541728A (zh) 一种基于密度聚类的故障诊断方法及装置
CN104076795A (zh) 工艺塔运行效率的实时评价方法、装置和工艺塔
CN115098326A (zh) 一种系统异常检测方法及装置、存储介质及电子设备
CN116338113B (zh) 环境智慧感知模拟系统、方法、服务器和存储介质
CN113985202B (zh) 一种电容故障预警方法、装置、电子设备及存储介质
JP7281394B2 (ja) 異常診断装置およびプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22900177

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE