CN111047732A - Equipment abnormity diagnosis method and device based on energy consumption model and data interaction - Google Patents
Equipment abnormity diagnosis method and device based on energy consumption model and data interaction Download PDFInfo
- Publication number
- CN111047732A CN111047732A CN201911293016.5A CN201911293016A CN111047732A CN 111047732 A CN111047732 A CN 111047732A CN 201911293016 A CN201911293016 A CN 201911293016A CN 111047732 A CN111047732 A CN 111047732A
- Authority
- CN
- China
- Prior art keywords
- equipment
- steady
- energy consumption
- working condition
- neural network
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
Abstract
The application relates to the technical field of computer data processing, in particular to a method and a device for diagnosing equipment abnormity based on an energy consumption model and data interaction. The application provides an equipment abnormity diagnosis method based on an energy consumption model and data interaction, which comprises the following steps: acquiring time history data of a selected variable for one or more components of equipment to be diagnosed according to an appointed operation parameter variable, then acquiring a time period set under a steady state condition by using a probability statistics method in a sliding window, further calculating to obtain a steady state condition statistics set, and screening an achievable value of a performance coefficient based on the steady state condition statistics set to construct a performance coefficient dynamic alarm curve of the equipment to be diagnosed through a neural network model; and inputting the real-time collected operation parameter variables into a neural network model, and if the output value of the neural network model exceeds the performance coefficient dynamic alarm curve, judging the suspected fault of the equipment to be diagnosed and sending an alarm signal.
Description
Technical Field
The application relates to the technical field of computer data processing, in particular to a method and a device for diagnosing equipment abnormity based on an energy consumption model and data interaction.
Background
Equipment anomalies, which are material damage and unscheduled outages caused by equipment unexpected stoppages, efficiency drops, or malfunctions of robots and other electromechanical equipment during automated operation or manufacturing, are common problems that are often the end of equipment operation or equipment manufacturing, adding considerable cost to the user.
In the implementation of some equipment abnormality diagnosis methods, for example, the method relates to the field of building energy consumption diagnosis, and comprises refrigeration unit equipment, water pump equipment, cooling tower equipment, water system equipment, air conditioner end equipment, boiler equipment and an equipment supply end indoor environment, wherein temperature sensors are arranged at corresponding positions of the equipment, positioning chips are arranged on the temperature sensors, the temperature sensors are in signal connection with a remote computer system in a wireless signal transmission mode, and received data are further compared with a preset variable threshold value to judge the abnormal state of the equipment.
However, in the actual operation process of the method, when the equipment is aged or the equipment is in a failure critical state, although the sensor values at each position are kept normal, the performance coefficient of the whole equipment often fluctuates greatly, that is, the method cannot make advance judgment before the equipment failure occurs, and cannot make real-time detection and advance judgment on the performance of the whole equipment.
Disclosure of Invention
The application provides an equipment abnormity diagnosis method and device based on an energy consumption model and data interaction.
The embodiment of the application is realized as follows:
a first aspect of an embodiment of the present application provides an apparatus anomaly diagnosis method based on an energy consumption model and data interaction, including:
acquiring time history data of the selected variable for one or more components of the equipment to be diagnosed according to the specified operation parameter variable;
acquiring a time period set under a steady-state working condition by using a probability statistic method in a sliding window based on the time history data;
calculating to obtain a steady-state working condition statistical set based on the time period set under the steady-state working condition, wherein the steady-state working condition statistical set is composed of different steady-state working condition statistical variables containing performance coefficients;
screening an reachable value of the performance coefficient based on the steady-state working condition statistic set, and constructing a performance coefficient dynamic alarm curve of the equipment to be diagnosed through a neural network model;
and inputting the real-time collected operation parameter variables into a neural network model, and if the output value of the neural network model exceeds the performance coefficient dynamic alarm curve, judging the suspected fault of the equipment to be diagnosed and sending an alarm signal.
A second aspect of the embodiments of the present application provides an apparatus for diagnosing an abnormality of a device based on an energy consumption model and data interaction, including:
the energy consumption monitoring component is used for acquiring time history data of one or more components of specified operation parameter variables of the equipment to be diagnosed;
the server is connected with the energy consumption monitoring component and the alarm platform through a network to transmit information, and based on the time history data, a time period set under a steady-state working condition is obtained by using a probability statistics method in a sliding window; calculating to obtain a steady-state working condition statistical set based on the time period set under the steady-state working condition, wherein the steady-state working condition statistical set is composed of different steady-state working condition statistical variables containing performance coefficients; screening the reachable values of the performance coefficients based on the steady-state working condition statistic set to construct a performance coefficient dynamic alarm curve of the equipment to be diagnosed; inputting the real-time collected operation parameter variables into a neural network model, and if the output value of the neural network model exceeds the performance coefficient dynamic alarm curve, judging the suspected fault of the equipment to be diagnosed and sending an alarm signal;
and the alarm platform is connected with the energy consumption monitoring component and the server through a network to transmit information, and is used for displaying the real-time operation parameter variable of the equipment to be diagnosed and displaying alarm information sent by the server.
The technical scheme provided by the application comprises the following beneficial technical effects: acquiring time history data of one or more component operating parameters of equipment to be diagnosed by monitoring to obtain an identified steady-state working condition set; further, data processing is carried out in a sliding window by using a statistical method, so that all steady-state working condition time period sets of the equipment can be obtained; the performance coefficients are further screened and calculated through the improved neural network model, the reachable values of the performance coefficients under all steady-state working conditions can be obtained, the dynamic alarm curve of the performance coefficients of the equipment is further generated, the performance curve values generated through the operation parameters of the equipment can be compared with the dynamic alarm curve in real time, the obtained results are accurate, and the obtained results can be used as pre-judged equipment abnormity diagnosis results.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a schematic diagram of a system 100 for diagnosing equipment abnormality based on energy consumption model and data interaction according to an embodiment of the present application;
FIG. 2 illustrates a schematic diagram of a computing device 200 in an embodiment of the present application;
FIG. 3 is a flowchart illustrating a method for diagnosing equipment abnormality based on energy consumption model and data interaction according to an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a sliding window of a device anomaly diagnosis method based on an energy consumption model and data interaction according to an embodiment of the present application;
FIG. 5 shows an equipment anomaly diagnosis method χ based on energy consumption model and data interaction in an embodiment of the present application2-a schematic density curve of the distribution;
fig. 6 shows a schematic diagram of an apparatus abnormality diagnosis device 600 based on an energy consumption model and data interaction according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Reference throughout this specification to "embodiments," "some embodiments," "one embodiment," or "an embodiment," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases "in various embodiments," "in some embodiments," "in at least one other embodiment," or "in an embodiment" or the like throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Thus, the particular features, structures, or characteristics shown or described in connection with one embodiment may be combined, in whole or in part, with the features, structures, or characteristics of one or more other embodiments, without limitation. Such modifications and variations are intended to be included within the scope of the present application.
Fig. 1 shows a schematic diagram of a device abnormality diagnosis system 100 based on an energy consumption model and data interaction according to an embodiment of the present application. The system 100 for diagnosing abnormality of equipment based on energy consumption model and data interaction is a system capable of automatically diagnosing abnormality of equipment.
The system 100 for diagnosing device abnormalities based on energy consumption models and data interactions may include a server 110, at least one storage device 120, at least one network 130, and one or more detection apparatuses 150-1, 150-2. The server 110 may include a processing engine 112.
In some embodiments, the server 110 may be a single server or a group of servers. The server farm can be centralized or distributed (e.g., server 110 can be a distributed system). In some embodiments, the server 110 may be local or remote. For example, server 110 may access data stored in storage device 120 via network 130. Server 110 may be directly connected to storage device 120 to access the stored data. In some embodiments, the server 110 may be implemented on a cloud platform. The cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, multiple clouds, the like, or any combination of the above.
In some embodiments, server 110 and the alert platform may be implemented on a computing device as illustrated in FIG. 2 herein, including one or more components of computing device 200.
In some embodiments, the server 110 may include a processing engine 112. Processing engine 112 may process information and/or data related to the service request to perform one or more of the functions described herein. For example, the processing engine 112 may be based on information collected by the acquisition detection device 150 and sent to the storage device 120 via the network 130 for updating data stored therein. In some embodiments, processing engine 112 may include one or more processors. The processing engine 112 may include one or more hardware processors, such as a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an application specific instruction set processor (ASIP), an image processor (GPU), a physical arithmetic processor (PPU), a Digital Signal Processor (DSP), a field-programmable gate array (FPGA), a Programmable Logic Device (PLD), a controller, a micro-controller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination of the above.
In some embodiments, storage device 120 may be connected to network 130 to enable communication with one or more components in device anomaly diagnosis system 100 based on energy consumption models and data interactions. One or more components of the device anomaly diagnostic system 100 based on the energy consumption model and data interaction may access data or instructions stored in the storage device 120 via the network 130. In some embodiments, the storage device 120 may be directly connected or in communication with one or more components of the device anomaly diagnostic system 100 based on the energy consumption model and data interaction. In some embodiments, storage device 120 may be part of server 110.
The network 130 may facilitate the exchange of information and/or data. In some embodiments, one or more components of the energy consumption model and data interaction based equipment anomaly diagnostic system 100 may send information and/or data to other components of the energy consumption model and data interaction based equipment anomaly diagnostic system 100 via the network 130. For example, the server 110 may obtain/obtain the request from the detection device 150 via the network 130. In some embodiments, the network 130 may be any one of a wired network or a wireless network, or a combination thereof. In some embodiments, the network 130 may include one or more network access points. For example, the network 130 may include wired or wireless network access points, such as base stations and/or Internet switching points 130-1, 130-2, and so forth. Through the access point, one or more components of the device anomaly diagnostic system 100 based on the energy consumption model and data interaction may be connected to the network 130 to exchange data and/or information.
The detection device 150 may include an image sensor, a temperature sensor, a flow sensor, a speed sensor, a pressure sensor, a sound sensor, a mobile communication device, and the like. In some embodiments, the detection device 150 may be used to take a picture and/or photograph of the surrounding environment at the location. In some embodiments, the detection apparatus 150 may transmit the collected various data information to one or more devices in the device abnormality diagnosis system 100 based on the energy consumption model and data interaction. For example, the detection device 150 may send the temperature or flow rate at the chilled water valve of the device to be tested, such as a central air conditioning chiller, to the server 110 for processing or storage in the storage device 120.
FIG. 2 is a schematic diagram of an exemplary computing device 200 shown in accordance with some embodiments of the present application.
For ease of understanding, only one processor is exemplarily depicted in fig. 2. However, it should be noted that the computing device 200 in the present application may include multiple processors, and thus the operations and/or methods described in the present application that are implemented by one processor may also be implemented by multiple processors, collectively or independently. For example, if in the present application a processor of computing device 200 performs steps 1 and 2, it should be understood that steps 1 and 2 may also be performed by two different processors of computing device 200, either collectively or independently.
Fig. 3 shows a flowchart of a device anomaly diagnosis method based on an energy consumption model and data interaction according to an embodiment of the present application.
In step 301, time history data for selected variables is obtained for one or more components of the device to be diagnosed based on specified operating parameter variables.
In this embodiment, in order to facilitate the explanation of the method for diagnosing the abnormality of the equipment based on the energy consumption model and the data interaction, a central air-conditioning water chiller is taken as an example for explanation. Although the present embodiment describes the abnormality diagnosis of the air conditioner with specific structural features and/or method actions, it is to be understood that the abnormality diagnosis method of the appended claims or description is not limited to the air conditioner.
Before the diagnosis of an air conditioning chiller is explained in detail, a brief description of the basic concept of an air conditioning chiller will be given, which generally preferably includes chilled water and cooling water.
The chilled water is chilled water which is sent to a fan coil to cool an indoor space after being cooled by an evaporator of a main unit of the central air conditioner, and a chilled water system is generally in closed circulation and is common tap water, and the temperature of the chilled water is generally between 7 and 12 ℃.
The cooling water is circulating water for cooling a refrigerant in a condenser of a main machine of the central air conditioner, the cooling water is heated in the condenser of the main machine and then flows into a cooling tower for cooling, the cooled cooling water flows into the condenser again and then is circulated continuously, the cooling water is generally treated tap water, and the temperature of the cooling water is generally between 20 and 40 ℃.
In this embodiment, detection devices, specifically, sensors are disposed at the inlet and outlet positions of the water path of the central air conditioning chiller, the power supply node, and the periphery of the equipment to collect the operation parameter variables of the chilled water and the cooling water, the power operation parameter variables, the ambient temperature, and the like.
The term "sensor" as used in this embodiment refers to a measuring, detecting or sensing device mounted on the device to be tested or any component thereof. A non-exhaustive list of the parts of the sensor that are or can be mounted on the device to be monitored: a camera; a chemical sensor; antennas, capacitive or other electric field sensors, electromagnetic wave sensors; a pressure sensor; a weight sensor; a magnetic field sensor; an air traffic meter; a humidity sensor; a clock; a temperature sensor; a flow sensor; a slip detection system, etc.
In some embodiments, it is generally desirable to extract as much information as possible from sources already present in the tool, i.e., from those used by the device, with respect to the type of data collected by the sensor to achieve the desired functionality.
The signal content measurable by existing sensors typically includes the following signals, which are present in the plant operation or plant manufacturing automation process and can be used for condition monitoring and fault diagnosis:
motor PWM duty (duty): the PWM duty of the motor is the percentage of the input voltage supplied to each motor phase at any given time. The duty cycle of each motor phase may be used in a health monitoring and fault diagnosis system.
Motor current: the motor current represents the current flowing through each of the three phases of each motor. The motor current may be obtained as an absolute value or as a percentage of the maximum current. If obtained as an absolute value, the unit of this current is amperes. The motor current value, in turn, may be used to calculate motor torque using a motor torque-current relationship.
Actual position, velocity and acceleration: these are the position, velocity and acceleration of each motor shaft. The units of position, velocity and acceleration values are degrees, degrees/second and degrees/second squared, respectively, for the axis of rotation. For the translation axis, the units of position, velocity and acceleration values are millimeters, millimeters/second and millimeters/second squared, respectively.
Desired position, velocity and acceleration: these are the position, velocity and acceleration values that the controller commands the motor to have. These properties have similar units to the actual position, velocity and acceleration described above.
Position and velocity tracking error: these are the differences between the respective desired values and the actual values. These properties have similar units to the actual position, velocity and acceleration described above.
The stabilizing time is as follows: this is the time it takes for the position and velocity tracking error to settle within a specified window at the end of the move.
Encoder simulation and absolute position output: the motor position is determined by an encoder, which outputs two types of signals: analog signals and absolute position signals. The analog signals are sine and cosine signals in millivolts. The absolute position signal is a non-volatile integer value indicating the number of simulated sinusoidal cycles that have passed or an integer multiple of the simulated sinusoidal cycles. Typically, the digital output is read at power up and the shaft position is thereafter determined from the analogue signal only.
The clamp state: this is the state of the gripper: open or close. In the case where the vacuum-energized edge contacts the gripper, it is the blocked/unblocked state of the one or more sensors.
Pressure of the vacuum system: this is the vacuum level measured by the vacuum sensor. This is an analog sensor whose output is digitized by an analog-to-digital converter. In the case of a suction gripper, the vacuum level indicates whether the wafer has been grasped.
Substrate presence sensor state: in a passive clamp end effector, the wafer presence sensor output is a binary output. In a vacuum-energized edge source contact clamp end effector, the presence of a wafer is determined by the output states of two or more sensors, each of which is binary.
Mapper sensor state: this is the state of the mapper sensor is blocked or non-blocked in any given instance.
Mapper/aligner detector light intensity: this is a measure of the intensity of light detected by the light detector. This signal is typically available as an integer value (which may, for example, have a range of 0-1024).
Mapper sensor position capture data: this is an array of robot axis position values at which the mapper sensor changes state.
Vacuum valve state: this is the commanded state of the vacuum valve. Which specifies whether the solenoid that operates the vacuum valve should be energized.
Voltage at the fuse output: the voltage at the output of each fuse in the motor control circuit is monitored. The blown fuse results in a low output voltage.
Substrate alignment data: these are the substrate eccentricity vectors and angular orientations of the alignment references of the substrate reported by the aligner.
Position data at the time of conversion of the external substrate sensor: in some cases, the atmospheric and vacuum portions of the tool may be equipped with optical sensors that detect the leading and trailing edges of a substrate carried by the robot. Robot position data corresponding to these events is used to quickly (on-the-fly) identify eccentricity of a substrate on the robot end effector.
Substrate cycle time: this is the time required for a single substrate to be processed by the tool, usually measured under steady flow conditions.
Microenvironment pressure: this is the pressure measured by the pressure sensor in the atmospheric part of the tool.
Direct measurement of motor torque: the motor torque may be measured directly rather than estimated from the motor current. This is done by using a dynamometer or a torque meter to measure the external force/torque required to keep the powered motor stationary.
The temperature of the motor is as follows: this refers to the temperature of the motor and is read by a temperature sensor mounted on the motor. The temperature may be obtained in degrees C.
An over travel sensor: these are sensors, such as limit switches, that indicate whether the motor shaft associated with the sensor exceeds its allowable range of travel.
Acoustic and vibration sensor data: this represents the electrical signals obtained from microphones and accelerometers placed at various points on or near the robot.
Infrared sensor data: this represents temperature readings taken from infrared sensors placed at various points in the tool to monitor temperature changes.
Power consumption: the values of motor current, speed and duty cycle may be used to calculate the electrical power consumed by each motor at any given moment.
Deflection: this represents the electrical signals obtained from strain gauges placed at various points on the robot to measure deflection.
Belt tension: the output of the force sensing device attached to the belt tensioner is used as a measure of belt tension. In newtons.
Duration of cooling fan operation: the cooling fan may be operated continuously or controlled by a thermostat. A useful indicator of heat dissipation from the robot is the duration of cooling fan operation controlled by the thermostat.
Electrostatic charge of substrates in other approaches, the substrate charge level may be determined by controlled discharge of radicals.
Position data at external sensor transition: additional external sensors may be used to detect edges of the moving substrate and robotic components to allow the controller to capture corresponding robot position data and use the resulting information, for example, for robot and substrate repeatability inspections.
Video image: these represent video images obtained from a video camera fixedly mounted at a specific position that the robot periodically reaches or a camera carried by the robot. In the latter case, the camera may be pointed at the end effector or at a fixed marker.
Ventilation pressure (plenum pressure): this is the pressure measured by the pressure sensor on the input side of the filter in the fan filter unit.
Component failures can be broadly divided into two distinct types: progressive "chronic" failure and immediate "acute" failure. The first type of faults can be detected by the condition monitoring system at their early stages of development. Early detection and repair helps to avoid undesirable failures during operation. On the other hand, the second type of failure is not suitable for early detection. However, when faults occur, the fault diagnosis system may help diagnose the faults and thus shorten the time to return the machine to operation.
In this embodiment, by collecting the operation parameter variables of the central air-conditioning cold water unit in the normal operation state, the operation parameter variables at least include the following contents: chilled water inlet temperature, chilled water outlet temperature, chilled water flow, cooling water inlet temperature, cooling water outlet temperature, cooling water flow, all equipment power, ambient temperature, and the like.
The operation parameter variable X of the central air-conditioning water chilling unit is represented by a matrix as follows:
wherein x is11，x12，x1nThe values of the 1 st variable at the 1 st sampling moment, the 2 nd sampling moment and the nth sampling moment are respectively represented; for the same reason xm1，xm2，xmnMeans that the m-th variable is at the n-th variableThe value of the sampling instant; any parameter in the matrix X may be denoted as XijI.e. the value of the ith variable at the jth sampling instant; in matrix X, the sampling interval is T.
In step 302, based on the time history data, a set of time periods under steady state conditions is obtained by using probability statistics in a sliding window.
FIG. 4 shows a sliding window schematic diagram of a device anomaly diagnosis method based on an energy consumption model and data interaction according to an embodiment of the application.
As shown in the figure, the length of the sliding window is n, that is, n sampling time points of each operation parameter variable in the process of the central air-conditioning water chilling unit in the normal operation state are represented. When data analysis enters the next window, it can be found that the initial sampling time point in the sliding window, that is, the 1 st sampling time point, moves down by one sampling interval, and the corresponding terminal sampling time point of the sliding window, that is, the nth sampling time point, also moves down by one sampling interval, thereby forming the sliding effect of the window.
In this embodiment, the steady-state operating condition refers to a state of the central air conditioning chiller unit when the central air conditioning chiller unit normally operates, and whether the operating parameter variable is in the steady-state operating condition is determined by using a standard deviation method in a manner that the time history data is a sliding window for eyes.
The standard deviation, which is the arithmetic square root of the variance, is expressed as a, and reflects the degree of dispersion of a data set. It should be noted that, in probability statistics, the method of using the standard deviation is most commonly used as a measure of the degree of statistical distribution, and the standard deviation is not necessarily the same for two groups of data with the same average.
In this embodiment, a time period set under a steady-state working condition is obtained by a specific method using a standard deviation in a sliding window, and the standard deviation can represent the stability of the collected central air conditioning chiller operation parameter variables in this embodiment.
The standard deviation s of all collected operating parameter variables within the window is calculated as follows:
s＝(s1，s2，sm)，
wherein s ismRepresenting the standard deviation of the mth variable within the sliding window.
And setting the length of the sliding window as n, namely representing n sampling time points of each parameter variable in the normal operation state of the central air-conditioning water chilling unit, or called as sampling points.
Standard deviation s of load data in the sliding windowiIs expressed as:
wherein N is the number of load data in the sliding window; x is the number ofijThe value of the jth sampling moment of the ith parameter variable in the sliding window is obtained;
is the arithmetic mean of the N load data of the ith variable in the sliding window.
FIG. 5 shows an equipment anomaly diagnosis method χ based on energy consumption model and data interaction in an embodiment of the present application2A schematic of the density curve of the distribution.
When the central air-conditioning water chilling unit is in a steady-state working condition, the distribution of the measured values of the operation parameter variables of the central air-conditioning water chilling unit follows normal distribution N (mu, sigma)2) Where μ represents the mean of the population and σ represents the standard deviation. Namely, under the steady-state working condition, the operation parameter variables of the central air-conditioning water chilling unit should conform to normal distribution on the whole.
The length of the sliding window is n, and the standard deviation of the load data in the sliding window is s, then
Obeying x with degree of freedom (n-1)2Normal distribution, which is expressed as follows:
in this embodiment, the threshold θ of the unsteady state condition may be according to χ2-a density curve of a normal distribution.
Based on the numerical distribution principle of the 3 σ criterion, the present embodiment will be described in detail below for the non-steady-state condition. If the probability that the standard deviation s < θ corresponding to the steady-state operating condition is 0.995, the threshold θ of the non-steady-state operating condition of the operating parameter variable can be represented as:
after the unsteady state working condition threshold value of the operation parameter variable is based on, processing the time history data of the central air-conditioning water chilling unit by a sliding window method to obtain the standard deviation of each operation parameter variable in the sliding window:
s＝(s1，s2，sm)，
and when the standard deviation of each operation parameter variable is smaller than the corresponding unsteady state working condition threshold value, the central air-conditioning water chilling unit is in a normal operation state under the steady state working condition.
According to the data record of the energy consumption monitoring system in this embodiment, the sampling time point t1 when the central air-conditioning water chiller enters the steady-state working condition and the sampling time point t2 when the central air-conditioning water chiller exits the steady-state working condition can be obtained, the time period from t1 to t2 is the time period of the central air-conditioning water chiller which is continuously in the steady-state working condition, and a time period set of all the time periods in the steady-state working condition in the time history data of the central air-conditioning water chiller is obtained by a sliding window method.
In step 303, a steady-state condition statistical set is calculated based on the time period set under the steady-state condition, where the steady-state condition statistical set is composed of different steady-state condition statistical variables including performance coefficients.
The performance coefficient refers to the ratio of the refrigerating capacity to the refrigerating power consumption when the air conditioner operates in a refrigerating mode under a steady-state working condition and a specified condition. And calculating the performance coefficient of the equipment to be diagnosed under the steady-state working condition in each time period in the time period set under the steady-state working condition. For example, calculating the performance coefficient of the central air conditioning water chilling unit under the steady-state working condition in the time period from t1 to t 2. Extracting the operation parameter variables of the central air-conditioning water chilling unit in the time period from t1 to t2, namely all time history data in the time period, and showing the operation parameter variables as follows:
firstly, calculating the refrigerating capacity of the central air-conditioning water chilling unit in a time period from t1 to t2, and showing the refrigerating capacity as follows:
wherein Q islds，iThe unit of the instantaneous flow of the chilled water at the moment i is kg/s; t is tldsin，iThe unit of the return water temperature of the chilled water at the time i is shown as follows; t is tldsout，iThe unit of the temperature of the outlet water of the frozen water at the time point i is expressed as the temperature of the outlet water; t, representing a sensor sampling period of the central air-conditioning water chilling unit, wherein the unit of the sensor sampling period is s; c represents the specific heat capacity of the chilled water and has a unit of kJ/(kg. DEG C.).
Secondly, calculating the power consumption of the central air-conditioning water chilling unit in a time period from t1 to t 2:
wherein, p represents the instantaneous power of all equipment of the central air-conditioning water chilling unit, and the unit of p is kW; and T represents a sensor sampling period of the central air-conditioning water chilling unit, and the unit of the sensor sampling period is s.
And finally, calculating the average performance coefficient of the central air-conditioning water chilling unit in the time period from t1 to t2 according to the power consumption and the refrigerating capacity of the central air-conditioning water chilling unit in the time period from t1 to t2, wherein the average performance coefficient is represented as follows:
cop＝Q/P
in this embodiment, a steady-state condition statistical variable y is constructed, where the steady-state condition statistical variable y represents a set of various operation parameter variables and other parameters of the central air-conditioning water chiller unit under a steady-state condition of a certain time period.
The steady-state condition statistical variable y represents contents including: refrigeration capacity, ambient temperature, coefficient of performance, operating parameter variables, expressed as:
wherein Q represents the refrigerating capacity of the central air-conditioning water chilling unit, thjThe temperature of the environment of the central air is represented, cop represents the coefficient of performance of the central air-conditioning water chilling unit,
and representing the operation parameter variable of the central air-conditioning water chilling unit.
Through the method of the sliding window, the steady-state working condition statistical variable Y in different time periods is counted to form a steady-state working condition statistical set Y, which is expressed as follows:
Y＝(y1，y2，，yK)
and K represents the number of the statistical variables of the statistical steady-state working condition.
In step 304, a performance coefficient dynamic alarm curve of the device to be diagnosed is constructed through a neural network model based on the reachable values of the performance coefficients screened by the steady-state working condition statistic set.
And calculating the reachable values of the performance coefficients under the steady-state working conditions in different time periods, and calculating and counting the performance coefficients of the central air-conditioning water chilling unit under the steady-state working conditions in the steps to obtain a steady-state working condition statistical set Y of the central air-conditioning water chilling unit in the normal running state.
It should be noted that, due to different operating modes of the central air conditioner and differences of various environmental variables, differences of the performance coefficients under the steady-state operating conditions may be greatly different, and in order to obtain the achievable performance coefficients of the central air conditioner water chilling unit under different steady-state operating conditions, in this embodiment, the achievable values of the performance coefficients in all the steady-state operating condition statistical sets, or also referred to as boundary values, are extracted.
It should be noted that, although the coefficient of performance of the central air-conditioning water chiller unit reaches a certain larger value under a certain steady-state operating condition, if the frequency of occurrence of the coefficient of performance is too small, it indicates that the coefficient of performance under the steady-state operating condition may have a larger contingency, and the coefficient of performance of the central air-conditioning water chiller unit under most of the steady-state operating conditions cannot be represented. In another case, although the central air-conditioning water chiller is in a steady-state working condition, the performance coefficient is lower than the minimum required performance coefficient of the central air-conditioning water chiller due to the close fault of equipment or the aging of the equipment, and the performance coefficient under the steady-state working condition can be considered to be not in accordance with the normal operation state of the equipment.
Therefore, in this embodiment, the performance coefficients cop in the steady-state condition statistical set Y are statistically screened, the larger values of the performance coefficients are retained, and those performance coefficients with larger values that are accidental can be screened and removed, so that the accidental introduction of the solution result into the model is avoided.
Fig. 5 shows a schematic diagram of a performance coefficient screening process in an embodiment of the present application.
Firstly, based on the minimum rated performance coefficient cop of the central air-conditioning water chilling unit0And setting the Y performance coefficient of the steady-state working condition statistic set to be smaller than cop0And removing the steady-state working condition statistical variables to obtain a steady-state working condition statistical set with performance coefficients meeting the requirements.
Secondly, counting the frequency of the performance coefficient in each steady-state working condition statistical variable based on the steady-state working condition statistical set with the performance coefficient meeting the requirement;
then, calculating and screening the threshold N with contingency of the performance coefficient by using a 3 sigma criterion based on the frequency of the performance coefficient0The frequency of the performance coefficient is lower than the threshold value N0And removing the steady-state working condition statistical variables to obtain a final steady-state working condition statistical set.
Referring to the 3 δ principle, in normal distribution analysis, σ represents the standard deviation, μ represents the mean, and x ═ μ is the symmetry axis of the image, the 3 σ principle can be described by the following numerical distribution:
the probability of the numerical distribution in (μ - σ, μ + σ) is 0.6827;
the probability of the numerical distribution in (μ -2 σ, μ +2 σ) is 0.9545;
the probability of the numerical distribution in (μ -3 σ, μ +3 σ) is 0.9973;
from the above-mentioned characteristics of the numerical distribution, it is considered that the values of Y are almost entirely concentrated in the (μ -3 σ, μ +3 σ) range, and the possibility of exceeding this range is only less than 0.3%.
And finally, constructing a dynamic alarm curve of the performance coefficient by using an L2-GA-BP neural network model based on the final steady-state public statistic set.
The L2-GA-BP neural network model is a hybrid neural network model formed by combining an L2 regularized BP neural network model and a genetic algorithm GA.
The learning and training process of the BP neural network model is a process of solving a global optimal solution through a nonlinear function, and the network may be trapped in a local optimal value due to the defect of overall optimization of the neural network model. Regular terms are added in the BP neural network model, so that the problem of overlarge data weight matrix can be avoided.
The genetic algorithm GA has the advantage of strong capability of optimizing the overall search of data, and has the defect of poor capability of local search.
In this embodiment, a hybrid network model combining genetic algorithm GA with the L2-BP neural network model is used, and the advantages of both can be combined into a new global search algorithm.
The construction of the L2-GA-BP neural network model in this example will be explained below.
Firstly, performing L2 regularization on the BP neural network model to obtain an L2-BP neural network model.
The L2 is regular, so that the solution of the neural network model is biased to be smaller in norm, and the limitation on the model space is realized by limiting the size of the norm, so that overfitting is avoided to a certain extent. However, the regression function does not have the ability to generate sparse solutions, and the resulting coefficients still require all the features in the data to compute the prediction.
In order to avoid overfitting of the neural network and improve the generalization capability of the model, the method of this embodiment performs L2 regularization on the BP neural network model, and plays a role of penalty weight in the process of reverse derivation, which can be expressed as follows:
wherein J is a loss function, and m is the number of data in the input batch data; lambda is a hyper-parameter, and the value range of lambda is [0, 1 ].
Omega is a weight matrix of each layer in the training process of the neural network model, and the operation is to perform 2-norm operation of the matrix on each weight matrix, namely to square each element and then to sum the square.
After the loss function is modified, the derivative of the back propagation is also changed, and the derivative of the weight matrix ω is expressed as follows:
then updated by ω of the corresponding layer, as follows:
further expressed as:
the method realizes the additional punishment on the weight matrix omega, avoids the overfitting of the neural network model to a certain extent, and can improve the generalization capability of the neural network model.
And secondly, performing GA genetic algorithm optimization on the L2-BP neural network model to obtain an L2-GA-BP neural network model.
The BP algorithm has the characteristic of accurate optimization, and the GA genetic algorithm has strong macro search capability and good global optimization performance. Therefore, the GA genetic algorithm and the BP network are combined, the genetic algorithm is used for optimizing, the search range is narrowed, then the BP network is used for carrying out accurate solving, the purposes of global optimizing, rapidness and high efficiency can be achieved, and on the basis of data learning training, the neural network model can carry out continuous self-improvement on the accuracy of data learning in the process of continuously accumulating data.
In step 305, the real-time collected operation parameter variables are input into the neural network model, and if the output value exceeds the performance coefficient dynamic alarm curve, the suspected fault of the device to be diagnosed is determined and an alarm signal is sent out.
When the input end of the neural network model continuously inputs the operation parameter variables and other parameter variables of the central air-conditioning water chiller unit, such as the environmental temperature and the like, the neural network model outputs the performance coefficient value, and the performance coefficient forms an instant output performance coefficient curve along with the continuously input operation parameter variables, the output instant performance coefficient curve is compared with the performance coefficient dynamic alarm curve obtained in the step 304, if the performance coefficient value exceeds the performance coefficient dynamic alarm curve, the performance coefficient of the steady-state working condition is considered to belong to an abnormal state, the equipment to be diagnosed possibly has a fault or a fault in the future, and an alarm signal is sent to operation and maintenance personnel to perform manual diagnosis and intervention on the equipment in time.
In the practical application of the method, the neural network model can calculate the reasonable operation range of the energy consumption under the current operation condition by combining the operation parameter variable under the current condition of the central air-conditioning water chilling unit, the practical operation characteristics and the operation rules of each device can be accurately analyzed based on practical operation data, and when the practical energy consumption exceeds the reasonable range, an alarm is given.
The embodiment of the application also provides an equipment abnormity diagnosis device based on the energy consumption model and data interaction, which comprises an energy consumption monitoring part, a server and an alarm platform.
Fig. 6 shows a schematic diagram of an apparatus abnormality diagnosis device 600 based on an energy consumption model and data interaction according to an embodiment of the present application.
The energy consumption monitoring component 601 is configured to collect time history data of one or more components of the specified operating parameter variable of the device to be diagnosed.
The server 602 establishes connection with the energy consumption monitoring component 601 and the alarm platform 603 through a network to transmit information, and obtains a time period set under a steady-state working condition by using a probability statistics method in a sliding window based on the time history data; calculating to obtain a steady-state working condition statistical set based on the time period set under the steady-state working condition, wherein the steady-state working condition statistical set is composed of different steady-state working condition statistical variables containing performance coefficients; screening the reachable values of the performance coefficients based on the steady-state working condition statistic set to construct a performance coefficient dynamic alarm curve of the equipment to be diagnosed; and inputting the real-time collected operation parameter variables into a neural network model, and if the output value of the neural network model exceeds the performance coefficient dynamic alarm curve, judging the suspected fault of the equipment to be diagnosed and sending an alarm signal.
And the alarm platform 603 is connected with the energy consumption monitoring component 601 and the server 602 through a network for information transmission, and is used for displaying the real-time operation parameter variable of the equipment to be diagnosed and displaying the alarm information sent by the server.
In some embodiments, the alarm platform may further provide an energy use exception diagnosis record table of the device, the record table supports viewing exception records in the form of a line graph, and the automatic refresh system automatically refreshes when a page is loaded. The system sets a normal interval of the optimization model, the curve beyond the normal range is displayed in red, and the staff can respond in time according to the alarm.
It should be noted that, in the embodiment of the present application, a method for diagnosing an equipment abnormality is described by taking a central air conditioner as an example, but the present application does not limit equipment to be diagnosed, and the diagnosis method described in the present application can be applied to different equipment by using different sensors to perform data acquisition, analysis and processing.
According to the method, the prediction and the real-time feedback are combined, the energy consumption abnormity diagnosis is carried out on the equipment through the optimized neural network model, the equipment can be effectively monitored, the abnormal condition is monitored and effectively alarmed, the energy management level of the building is improved, the energy consumption waste of the building is effectively reduced, and the operation cost is reduced. For the actual engineering problem, the theory of a data learning method is fully utilized to be combined with the actual engineering problem, and a large amount of historical data are combined to train the optimized neural network model, so that the intelligent algorithm can obtain the internal coupling relation between the air conditioner load and the influence factors, and the change rule of the actual air conditioner load and the influence factors is found in a more targeted manner.
The method has the advantages that the set steady-state working condition set can be obtained by monitoring and acquiring the time history data of the operating parameters of one or more components of the equipment to be diagnosed; further, data processing is carried out in a sliding window by using a statistical method, so that all steady-state working condition time period sets of the equipment can be obtained; the performance coefficients are further screened and calculated through the improved neural network model, the reachable values of the performance coefficients under all steady-state working conditions can be obtained, the dynamic alarm curve of the performance coefficients of the equipment is further generated, the performance curve values generated through the operation parameters of the equipment can be compared with the dynamic alarm curve in real time, the obtained results are accurate, and the obtained results can be used as pre-judged equipment abnormity diagnosis results.
Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data blocks," modules, "" engines, "" units, "" components, "or" systems. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
It is to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that an article or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the use of the phrase "comprising a. -. said" to define an element does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
It is to be understood that the present application is not limited to what has been described above, and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (9)
1. An equipment abnormity diagnosis method based on energy consumption model and data interaction is characterized by comprising the following steps:
acquiring time history data of the selected variable for one or more components of the equipment to be diagnosed according to the specified operation parameter variable;
acquiring a time period set under a steady-state working condition by using a probability statistic method in a sliding window based on the time history data;
calculating to obtain a steady-state working condition statistical set based on the time period set under the steady-state working condition, wherein the steady-state working condition statistical set is composed of different steady-state working condition statistical variables containing performance coefficients;
screening an reachable value of the performance coefficient based on the steady-state working condition statistic set, and constructing a performance coefficient dynamic alarm curve of the equipment to be diagnosed through a neural network model;
and inputting the real-time collected operation parameter variables into a neural network model, and if the output value of the neural network model exceeds the performance coefficient dynamic alarm curve, judging the suspected fault of the equipment to be diagnosed and sending an alarm signal.
2. The method of claim 1, wherein the operating parameter variables comprise: chilled water inlet temperature, chilled water outlet temperature, chilled water flow, cooling water inlet temperature, cooling water outlet temperature, cooling water flow, all equipment power, ambient temperature.
3. The method for diagnosing the abnormality of the equipment based on the energy consumption model and the data interaction as claimed in claim 1, wherein the standard deviation of the internal load data of the sliding window characterizes the stability degree of the operation parameter variable of the equipment to be diagnosed, and is represented as:
wherein N is the number of load data in the sliding window; x is the number ofijThe value of the jth sampling moment of the ith parameter variable in the sliding window is obtained;
is the arithmetic mean of the N load data of the ith variable in the sliding window.
4. The equipment abnormality diagnosis method based on the energy consumption model and the data interaction as claimed in claim 1, wherein the equipment abnormality diagnosis method based on the energy consumption model and the data interaction is applied to a central air-conditioning water chiller, and the performance coefficient represents a ratio of cooling capacity to power consumption in a time period, and is represented as follows:
cop＝Q/P
and Q represents the refrigerating capacity of the central air-conditioning water chilling unit in the time period, and P represents the power consumption of the central air-conditioning water chilling unit in the time period.
5. The method for diagnosing equipment abnormality based on energy consumption model and data interaction of claim 1, wherein the steady-state condition statistical variable representation comprises: refrigeration capacity, ambient temperature, coefficient of performance, operating parameter variables, expressed as:
wherein Q represents the refrigerating capacity of the central air-conditioning water chilling unit, thjThe temperature of the environment of the central air is represented, cop represents the coefficient of performance of the central air-conditioning water chilling unit,
and representing the operation parameter variable of the central air-conditioning water chilling unit.
6. The method of claim 1, wherein the neural network model is an L2-GA-BP neural network model, that is, a hybrid neural network model formed by combining an L2 regularized BP neural network model with a genetic algorithm GA.
7. An apparatus abnormality diagnosis device based on energy consumption model and data interaction is characterized by comprising:
the energy consumption monitoring component is used for acquiring time history data of one or more components of specified operation parameter variables of the equipment to be diagnosed;
the server is connected with the energy consumption monitoring component and the alarm platform through a network to transmit information, and based on the time history data, a time period set under a steady-state working condition is obtained by using a probability statistics method in a sliding window; calculating to obtain a steady-state working condition statistical set based on the time period set under the steady-state working condition, wherein the steady-state working condition statistical set is composed of different steady-state working condition statistical variables containing performance coefficients; screening the reachable values of the performance coefficients based on the steady-state working condition statistic set to construct a performance coefficient dynamic alarm curve of the equipment to be diagnosed; inputting the real-time collected operation parameter variables into a neural network model, and if the output value of the neural network model exceeds the performance coefficient dynamic alarm curve, judging the suspected fault of the equipment to be diagnosed and sending an alarm signal;
and the alarm platform is connected with the energy consumption monitoring component and the server through a network to transmit information, and is used for displaying the real-time operation parameter variable of the equipment to be diagnosed and displaying alarm information sent by the server.
8. The device abnormality diagnosis apparatus based on the energy consumption model and the data interaction as claimed in claim 1, wherein the alarm platform provides an energy consumption abnormality diagnosis record table of the device to be diagnosed, and the energy consumption abnormality diagnosis record table supports the view in the form of a line graph.
9. The apparatus abnormality diagnosis device according to claim 1, wherein the operation parameter variables collected by the energy consumption monitoring unit include: chilled water inlet temperature, chilled water outlet temperature, chilled water flow, cooling water inlet temperature, cooling water outlet temperature, cooling water flow, all equipment power, ambient temperature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911293016.5A CN111047732B (en) | 2019-12-16 | 2019-12-16 | Equipment abnormity diagnosis method and device based on energy consumption model and data interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911293016.5A CN111047732B (en) | 2019-12-16 | 2019-12-16 | Equipment abnormity diagnosis method and device based on energy consumption model and data interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111047732A true CN111047732A (en) | 2020-04-21 |
| CN111047732B CN111047732B (en) | 2022-04-12 |
Family
ID=70236667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911293016.5A Active CN111047732B (en) | 2019-12-16 | 2019-12-16 | Equipment abnormity diagnosis method and device based on energy consumption model and data interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111047732B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111857024A (en) * | 2020-07-31 | 2020-10-30 | 博崖(上海)自动化科技有限公司 | Diagnosis method for remote early warning of central air conditioner |
| CN112036077A (en) * | 2020-08-14 | 2020-12-04 | 天地（常州）自动化股份有限公司 | Overheating protection method for mining explosion-proof water-cooled frequency converter without flow sensor |
| CN112067334A (en) * | 2020-08-31 | 2020-12-11 | 电子科技大学 | Fault identification method for air conditioner external unit |
| CN112085062A (en) * | 2020-08-10 | 2020-12-15 | 广东工业大学 | Wavelet neural network-based abnormal energy consumption positioning method |
| CN112885047A (en) * | 2021-01-15 | 2021-06-01 | 湖南五凌电力科技有限公司 | Intelligent early warning method for state monitoring of unit, transformer and auxiliary machine |
| CN112991331A (en) * | 2021-04-19 | 2021-06-18 | 广州大一互联网络科技有限公司 | Operation and maintenance method and device of data center using insulating cooling liquid |
| CN113091309A (en) * | 2021-03-08 | 2021-07-09 | 浙江大学 | Heat conduction oil circulation fault diagnosis system |
| CN113110387A (en) * | 2021-04-20 | 2021-07-13 | 上海市环境科学研究院 | Environment-friendly intelligent diagnosis system, method and storage medium |
| CN113587387A (en) * | 2021-07-19 | 2021-11-02 | 上海佐竹冷热控制技术有限公司 | Air conditioning equipment early warning method and system |
| CN114838968A (en) * | 2022-04-28 | 2022-08-02 | 江苏一万节能科技股份有限公司 | Air conditioner fault detection method and system based on cold water cooling test |
| CN114927205A (en) * | 2022-05-06 | 2022-08-19 | 透彻影像(北京)科技有限公司 | Deployment monitoring system based on artificial intelligence pathology auxiliary diagnosis system |
| CN116203298A (en) * | 2023-01-31 | 2023-06-02 | 赛福凯尔(绍兴)医疗科技有限公司 | Power protection method and system based on magnetic coupling digital isolator |
| CN116416768A (en) * | 2023-06-12 | 2023-07-11 | 山东特发光源光通信有限公司 | Early warning system for central processing unit of optical cable cutting machine |
Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1629556A (en) * | 2003-12-19 | 2005-06-22 | 珠海福士得冷气工程有限公司 | Energy-saving central air conditioning system |
| CN101520412A (en) * | 2009-03-23 | 2009-09-02 | 中国计量学院 | Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network |
| FR2939928A1 (en) * | 2008-12-15 | 2010-06-18 | Snecma | STANDARDIZATION OF DATA USED FOR MONITORING AN AIRCRAFT ENGINE |
| CN102063078A (en) * | 2009-11-13 | 2011-05-18 | 深圳达实智能股份有限公司 | System for remotely monitoring energy consumption of central air-conditioning |
| CN102324887A (en) * | 2011-09-08 | 2012-01-18 | 天津理工大学 | Wind driven generator stability control method based on hybrid neural network |
| US20130246858A1 (en) * | 2012-03-15 | 2013-09-19 | Kenneth Paul Ceglia | Methods and apparatus for monitoring operation of a system asset |
| CN103699111A (en) * | 2013-09-26 | 2014-04-02 | 青岛海信网络科技股份有限公司 | Failure detection method and device for distributed monitoring system |
| WO2014117245A1 (en) * | 2013-01-31 | 2014-08-07 | Spielo International Canada Ulc | Faults and performance issue prediction |
| CN104729024A (en) * | 2015-04-08 | 2015-06-24 | 南京优助智能科技有限公司 | Air conditioning load prediction method based on indoor average temperature |
| CN204631962U (en) * | 2015-05-08 | 2015-09-09 | 南京中医药大学 | Instrument and equipment service condition pen recorder |
| CN105389648A (en) * | 2015-10-21 | 2016-03-09 | 南京富岛信息工程有限公司 | Distinguishing method for steady-state operating condition of atmospheric and vacuum distillation device |
| CN106297027A (en) * | 2016-07-28 | 2017-01-04 | 珠海小可乐科技有限公司 | Charging pile collecting method and system thereof |
| CN106600047A (en) * | 2016-12-09 | 2017-04-26 | 上海铁路局 | Method for fault identification and early warning of air conditioners in passenger compartments of motor train unit based on BP neural network |
| CN106652527A (en) * | 2017-02-10 | 2017-05-10 | 青岛海信网络科技股份有限公司 | Fault diagnosis method and system of traffic signal controller |
| CN106801980A (en) * | 2017-01-25 | 2017-06-06 | 青岛海尔空调器有限总公司 | Air-conditioning fire prevention control method and control system |
| CN107314504A (en) * | 2017-06-15 | 2017-11-03 | 美的集团武汉制冷设备有限公司 | Air-conditioning system, air conditioner and the method for carrying out Studies of Human Body Heat image abnormal alarm |
| CN107644474A (en) * | 2017-09-20 | 2018-01-30 | 深圳市鑫汇达机械设计有限公司 | A kind of Power Line Inspection System for intelligent grid |
| CN107797006A (en) * | 2017-10-19 | 2018-03-13 | 国家电网公司 | Transformer load Forecasting Methodology and device |
| CN107796609A (en) * | 2017-10-17 | 2018-03-13 | 西安建筑科技大学 | A kind of handpiece Water Chilling Units method for diagnosing faults based on DBN model |
| CN107844799A (en) * | 2017-10-17 | 2018-03-27 | 西安建筑科技大学 | A kind of handpiece Water Chilling Units method for diagnosing faults of integrated SVM mechanism |
| CN207635545U (en) * | 2017-12-14 | 2018-07-20 | 天津博迈科海洋工程有限公司 | Module intelligent air condition temperature-adjusting device between a kind of large electric |
| CN108507117A (en) * | 2017-10-13 | 2018-09-07 | 上海智容睿盛智能科技有限公司 | A kind of Air-conditioning system sensor method for diagnosing faults based on wavelet neural network |
| CN109061341A (en) * | 2018-07-10 | 2018-12-21 | 杭州安脉盛智能技术有限公司 | Kalman filtering transformer fault prediction technique and system neural network based |
| US20190108603A1 (en) * | 2017-08-09 | 2019-04-11 | Skylight Tools, Inc. | Property enhancement services |
| US20190146482A1 (en) * | 2016-05-09 | 2019-05-16 | Strong Force Iot Portfolio 2016, Llc | Method and system for adjusting an operating parameter for a power station |
| CN109781399A (en) * | 2019-02-27 | 2019-05-21 | 天津大学 | A kind of air cooling refrigeration unit sensor fault diagnosis method neural network based |
| CN109858140A (en) * | 2019-01-28 | 2019-06-07 | 西安建筑科技大学 | One kind being based on comentropy discrete type Bayesian network water cooler method for diagnosing faults |
| CN109902826A (en) * | 2019-03-11 | 2019-06-18 | 珠海格力电器股份有限公司 | Household electrical appliances energy saving model construction method based on genetic algorithm, control method, household electrical appliances |
-
2019
- 2019-12-16 CN CN201911293016.5A patent/CN111047732B/en active Active
Patent Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1629556A (en) * | 2003-12-19 | 2005-06-22 | 珠海福士得冷气工程有限公司 | Energy-saving central air conditioning system |
| FR2939928A1 (en) * | 2008-12-15 | 2010-06-18 | Snecma | STANDARDIZATION OF DATA USED FOR MONITORING AN AIRCRAFT ENGINE |
| CN101520412A (en) * | 2009-03-23 | 2009-09-02 | 中国计量学院 | Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network |
| CN102063078A (en) * | 2009-11-13 | 2011-05-18 | 深圳达实智能股份有限公司 | System for remotely monitoring energy consumption of central air-conditioning |
| CN102324887A (en) * | 2011-09-08 | 2012-01-18 | 天津理工大学 | Wind driven generator stability control method based on hybrid neural network |
| US20130246858A1 (en) * | 2012-03-15 | 2013-09-19 | Kenneth Paul Ceglia | Methods and apparatus for monitoring operation of a system asset |
| WO2014117245A1 (en) * | 2013-01-31 | 2014-08-07 | Spielo International Canada Ulc | Faults and performance issue prediction |
| CN103699111A (en) * | 2013-09-26 | 2014-04-02 | 青岛海信网络科技股份有限公司 | Failure detection method and device for distributed monitoring system |
| CN104729024A (en) * | 2015-04-08 | 2015-06-24 | 南京优助智能科技有限公司 | Air conditioning load prediction method based on indoor average temperature |
| CN204631962U (en) * | 2015-05-08 | 2015-09-09 | 南京中医药大学 | Instrument and equipment service condition pen recorder |
| CN105389648A (en) * | 2015-10-21 | 2016-03-09 | 南京富岛信息工程有限公司 | Distinguishing method for steady-state operating condition of atmospheric and vacuum distillation device |
| US20190146482A1 (en) * | 2016-05-09 | 2019-05-16 | Strong Force Iot Portfolio 2016, Llc | Method and system for adjusting an operating parameter for a power station |
| CN106297027A (en) * | 2016-07-28 | 2017-01-04 | 珠海小可乐科技有限公司 | Charging pile collecting method and system thereof |
| CN106600047A (en) * | 2016-12-09 | 2017-04-26 | 上海铁路局 | Method for fault identification and early warning of air conditioners in passenger compartments of motor train unit based on BP neural network |
| CN106801980A (en) * | 2017-01-25 | 2017-06-06 | 青岛海尔空调器有限总公司 | Air-conditioning fire prevention control method and control system |
| CN106652527A (en) * | 2017-02-10 | 2017-05-10 | 青岛海信网络科技股份有限公司 | Fault diagnosis method and system of traffic signal controller |
| CN107314504A (en) * | 2017-06-15 | 2017-11-03 | 美的集团武汉制冷设备有限公司 | Air-conditioning system, air conditioner and the method for carrying out Studies of Human Body Heat image abnormal alarm |
| US20190108603A1 (en) * | 2017-08-09 | 2019-04-11 | Skylight Tools, Inc. | Property enhancement services |
| CN107644474A (en) * | 2017-09-20 | 2018-01-30 | 深圳市鑫汇达机械设计有限公司 | A kind of Power Line Inspection System for intelligent grid |
| CN108507117A (en) * | 2017-10-13 | 2018-09-07 | 上海智容睿盛智能科技有限公司 | A kind of Air-conditioning system sensor method for diagnosing faults based on wavelet neural network |
| CN107844799A (en) * | 2017-10-17 | 2018-03-27 | 西安建筑科技大学 | A kind of handpiece Water Chilling Units method for diagnosing faults of integrated SVM mechanism |
| CN107796609A (en) * | 2017-10-17 | 2018-03-13 | 西安建筑科技大学 | A kind of handpiece Water Chilling Units method for diagnosing faults based on DBN model |
| CN107797006A (en) * | 2017-10-19 | 2018-03-13 | 国家电网公司 | Transformer load Forecasting Methodology and device |
| CN207635545U (en) * | 2017-12-14 | 2018-07-20 | 天津博迈科海洋工程有限公司 | Module intelligent air condition temperature-adjusting device between a kind of large electric |
| CN109061341A (en) * | 2018-07-10 | 2018-12-21 | 杭州安脉盛智能技术有限公司 | Kalman filtering transformer fault prediction technique and system neural network based |
| CN109858140A (en) * | 2019-01-28 | 2019-06-07 | 西安建筑科技大学 | One kind being based on comentropy discrete type Bayesian network water cooler method for diagnosing faults |
| CN109781399A (en) * | 2019-02-27 | 2019-05-21 | 天津大学 | A kind of air cooling refrigeration unit sensor fault diagnosis method neural network based |
| CN109902826A (en) * | 2019-03-11 | 2019-06-18 | 珠海格力电器股份有限公司 | Household electrical appliances energy saving model construction method based on genetic algorithm, control method, household electrical appliances |
Non-Patent Citations (2)
| Title |
|---|
| 万文妮等: "空气处理机组中传感器故障检测和诊断", 《制冷与空调》 * |
| 王占伟等: "基于融合的贝叶斯网络的冷水机组故障诊断", 《化工学报》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111857024A (en) * | 2020-07-31 | 2020-10-30 | 博崖(上海)自动化科技有限公司 | Diagnosis method for remote early warning of central air conditioner |
| CN111857024B (en) * | 2020-07-31 | 2023-11-24 | 博崖(上海)自动化科技有限公司 | Diagnosis method for remote early warning of central air conditioner |
| CN112085062A (en) * | 2020-08-10 | 2020-12-15 | 广东工业大学 | Wavelet neural network-based abnormal energy consumption positioning method |
| CN112036077A (en) * | 2020-08-14 | 2020-12-04 | 天地（常州）自动化股份有限公司 | Overheating protection method for mining explosion-proof water-cooled frequency converter without flow sensor |
| CN112036077B (en) * | 2020-08-14 | 2023-10-24 | 天地（常州）自动化股份有限公司 | Overheat protection method for mining flameproof water-cooled frequency converter without flow sensor |
| CN112067334A (en) * | 2020-08-31 | 2020-12-11 | 电子科技大学 | Fault identification method for air conditioner external unit |
| CN112067334B (en) * | 2020-08-31 | 2022-03-15 | 电子科技大学 | Fault identification method for air conditioner external unit |
| CN112885047A (en) * | 2021-01-15 | 2021-06-01 | 湖南五凌电力科技有限公司 | Intelligent early warning method for state monitoring of unit, transformer and auxiliary machine |
| CN113091309B (en) * | 2021-03-08 | 2022-02-22 | 浙江大学 | Heat conduction oil circulation fault diagnosis system |
| CN113091309A (en) * | 2021-03-08 | 2021-07-09 | 浙江大学 | Heat conduction oil circulation fault diagnosis system |
| CN112991331A (en) * | 2021-04-19 | 2021-06-18 | 广州大一互联网络科技有限公司 | Operation and maintenance method and device of data center using insulating cooling liquid |
| CN112991331B (en) * | 2021-04-19 | 2021-10-26 | 广州大一互联网络科技有限公司 | Operation and maintenance method and device of data center using insulating cooling liquid |
| CN113110387A (en) * | 2021-04-20 | 2021-07-13 | 上海市环境科学研究院 | Environment-friendly intelligent diagnosis system, method and storage medium |
| CN113587387A (en) * | 2021-07-19 | 2021-11-02 | 上海佐竹冷热控制技术有限公司 | Air conditioning equipment early warning method and system |
| CN114838968A (en) * | 2022-04-28 | 2022-08-02 | 江苏一万节能科技股份有限公司 | Air conditioner fault detection method and system based on cold water cooling test |
| CN114838968B (en) * | 2022-04-28 | 2023-10-20 | 江苏一万节能科技股份有限公司 | Air conditioner fault detection method and system based on cold water cooling test |
| CN114927205A (en) * | 2022-05-06 | 2022-08-19 | 透彻影像(北京)科技有限公司 | Deployment monitoring system based on artificial intelligence pathology auxiliary diagnosis system |
| CN114927205B (en) * | 2022-05-06 | 2023-01-13 | 北京透彻未来科技有限公司 | Deployment monitoring system based on artificial intelligence pathology auxiliary diagnosis system |
| CN116203298A (en) * | 2023-01-31 | 2023-06-02 | 赛福凯尔(绍兴)医疗科技有限公司 | Power protection method and system based on magnetic coupling digital isolator |
| CN116203298B (en) * | 2023-01-31 | 2024-04-02 | 赛福凯尔(绍兴)医疗科技有限公司 | Power protection method and system based on magnetic coupling digital isolator |
| CN116416768A (en) * | 2023-06-12 | 2023-07-11 | 山东特发光源光通信有限公司 | Early warning system for central processing unit of optical cable cutting machine |
| CN116416768B (en) * | 2023-06-12 | 2023-08-29 | 山东特发光源光通信有限公司 | Early warning system for central processing unit of optical cable cutting machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111047732B (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047732B (en) | Equipment abnormity diagnosis method and device based on energy consumption model and data interaction | |
| Shakya | A self monitoring and analyzing system for solar power station using IoT and data mining algorithms | |
| US7031880B1 (en) | Method and apparatus for assessing performance of an environmental control system | |
| US7496472B2 (en) | Method and system for assessing performance of control systems | |
| US11145914B2 (en) | Model based monitoring of battery system | |
| CN113763667B (en) | Fire disaster early warning and state monitoring device and method based on 5G edge calculation | |
| WO2018112352A1 (en) | Techniques of automated fault detection and related systems and methods | |
| JPWO2018220760A1 (en) | Air conditioner failure diagnosis device | |
| CN106771801B (en) | Online monitoring device for capacitor bank and application method of online monitoring device | |
| JP2005301582A (en) | Process management device | |
| JP2018207650A (en) | Feature quantity evaluation system for rotary electric machine and feature quantity evaluation method for rotary electric machine | |
| CN115840480A (en) | Method, device and system for controlling environmental parameters of clean room | |
| Lutska et al. | Forecasting the efficiency of the control system of the technological object on the basis of neural networks | |
| US10648735B2 (en) | Machine learning based predictive maintenance of a dryer | |
| JP3161844B2 (en) | Plant abnormality detection method and apparatus | |
| JP4434905B2 (en) | Process management device | |
| CN115640860A (en) | Electromechanical equipment remote maintenance method and system for industrial cloud service | |
| CN114970101A (en) | Management method and system of dehumidification device, electronic equipment and computer storage medium | |
| KR100340967B1 (en) | Method and apparatus for detecting fault using General Regression Neural Network | |
| CN117413273A (en) | Method, apparatus and computer storage medium for monitoring an enclosure environment | |
| Yoshida et al. | RARX algorithm based model development and application to real time data for on-line fault detection in VAV AHU units | |
| CN116192038A (en) | Photovoltaic system fault diagnosis method and device and computer equipment | |
| CN110701727B (en) | Method and system for detecting faults in an HVAC system and memory | |
| Stul et al. | Development of a SVM prediction model to optimize the energy consumption of industrial installations by detecting and classifying errors at an early stage | |
| EP2921918A1 (en) | Smart field device for use in automation and control systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |