CN111414999A - Method and device for monitoring running state of equipment - Google Patents
Method and device for monitoring running state of equipment Download PDFInfo
- Publication number
- CN111414999A CN111414999A CN202010341683.2A CN202010341683A CN111414999A CN 111414999 A CN111414999 A CN 111414999A CN 202010341683 A CN202010341683 A CN 202010341683A CN 111414999 A CN111414999 A CN 111414999A
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- point data
- measuring point
- predicted value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 238000011156 evaluation Methods 0.000 claims abstract description 40
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000007781 pre-processing Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 abstract description 13
- 230000009286 beneficial effect Effects 0.000 description 5
- 239000007789 gas Substances 0.000 description 4
- 230000010354 integration Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000002945 steepest descent method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Images
Classifications
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The invention is suitable for the technical field of energy, and provides a method and a device for monitoring the running state of equipment, wherein the method comprises the following steps: acquiring measuring point data of the equipment according to historical data of the equipment; processing the measuring point data by adopting a time sequence model to obtain a predicted value of the equipment at a preset moment; processing the measured point data and the predicted value by adopting a reverse error neural network to obtain a residual predicted value; obtaining an evaluation reference value according to the predicted value and the residual predicted value; determining a confidence interval of the equipment at a preset moment according to the measured point data and the evaluation reference value of the equipment; and determining the running state of the equipment according to the running data of the equipment at the preset moment and the confidence interval. The method monitors the actual running state of the equipment in real time based on the time series model and the inverse error neural network algorithm, determines the running state of the equipment by combining the confidence interval range, and ensures the accuracy, convenience and rapidness of prediction.
Description
Technical Field
The invention relates to the technical field of energy, in particular to a method and a device for monitoring the running state of equipment.
Background
The equipment in the energy station can show different operation states during operation due to different use time, use modes and use places. At present, whether the equipment is in a normal operation state is discovered mainly by monitoring the distance between certain measuring points of the equipment and a standard threshold value or some specified limit values.
However, most of the operation thresholds or limit values of the equipment are mainly derived from the rated parameters of the equipment manufacturer or provided by professional technicians according to experience, and since the thresholds or limit values are usually fixed values and cannot be adjusted in real time according to the operation state of the equipment, the actual operation state of the equipment cannot be accurately monitored, and thus the normal operation of the equipment cannot be ensured.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for monitoring an operating state of a device, a terminal device, and a computer-readable storage medium, so as to solve the technical problem that the actual operating state of the device cannot be accurately monitored in the prior art, so that normal operation of the device cannot be guaranteed.
In a first aspect, the present invention provides a method for monitoring an operating state of a device, including:
acquiring measuring point data of the equipment according to historical data of the equipment;
processing the measuring point data by adopting a time sequence model to obtain a predicted value of the equipment at a preset moment;
processing the measuring point data and the predicted value by adopting a reverse error neural network to obtain a residual predicted value;
obtaining an evaluation reference value according to the predicted value and the residual predicted value;
determining a confidence interval of the equipment at the preset moment according to the measuring point data of the equipment and the evaluation reference value;
and determining the running state of the equipment according to the running data of the equipment at the preset moment and the confidence interval.
Preferably, the acquiring of the station data of the equipment according to the historical data of the equipment comprises:
preprocessing acquired historical data of the equipment to acquire preprocessed time series data, wherein the preprocessing comprises removing repeated data and/or abnormal data in the historical data;
and grouping the time sequence data according to a preset step length, and calculating the average value of each group of data to obtain the measuring point data of the equipment.
Preferably, the time series model comprises a differential integrated moving average autoregressive model.
The processing the measuring point data and the predicted value by adopting a reverse error neural network to obtain a residual predicted value comprises the following steps:
acquiring an initial residual value according to the measuring point data and the predicted value;
and the inverse error neural network processes the initial residual value to obtain a residual prediction value.
Preferably, the obtaining an initial residual value according to the measured point data and the predicted value includes:
acquiring the operation data of the equipment at the preset moment according to the measuring point data;
and subtracting the predicted value from the operation data to obtain the initial residual value.
Preferably, in the step of obtaining an evaluation reference value according to the predicted value and the residual predicted value, the evaluation reference value is a sum of the predicted value and the residual predicted value.
Preferably, the determining a confidence interval of the equipment at the preset time according to the measured point data of the equipment and the evaluation reference value includes:
acquiring an average value of the measuring point data according to the measuring point data of the equipment;
acquiring the standard deviation of the measuring point data according to the average value of the measuring point data;
and determining a confidence interval of the equipment at the preset moment according to the evaluation reference value and the standard deviation of the measuring point data.
In a second aspect, the present invention provides a device for monitoring an operation state of equipment, including:
the measuring point data acquisition module is used for acquiring measuring point data of the equipment according to historical data of the equipment;
the predicted value acquisition module is used for processing the measuring point data by adopting a time sequence model to acquire a predicted value of the equipment at a preset moment;
the residual predicted value obtaining module is used for processing the measuring point data and the predicted value by adopting a reverse error neural network to obtain a residual predicted value;
the evaluation reference value obtaining module is used for obtaining an evaluation reference value according to the predicted value and the residual predicted value;
the confidence interval determining module is used for determining the confidence interval of the equipment at the preset moment according to the measuring point data of the equipment and the evaluation reference value;
and the operation state determining module is used for determining the operation state of the equipment according to the operation data of the equipment at the preset moment and the confidence interval.
In a third aspect, the present invention provides a readable medium, which includes an execution instruction, and when a processor of an electronic device executes the execution instruction, the electronic device executes the method for monitoring the device operation state according to any one of the first aspect.
In a fourth aspect, the present invention provides an electronic device, including a processor and a memory storing execution instructions, where when the processor executes the execution instructions stored in the memory, the processor executes the method for monitoring the device operating status according to any one of the first aspect.
The method for monitoring the running state of the equipment provided by the embodiment of the invention has the beneficial effects that at least: the method is combined with a big data technology, based on the combined use of a time series model and a reverse error neural network algorithm, can monitor and obtain the actual running state of the target equipment in real time under the remote condition, and then is combined with the reasonable confidence interval range of the equipment running, thereby effectively overcoming the defect of inaccurate prediction of the actual running state of the equipment in the prior art, and simultaneously, the accurate prediction result is beneficial to the scheduling optimization of the subsequent work. The monitoring method provided by the embodiment is simple in overall operation, guarantees accuracy, convenience and rapidness of prediction, improves overall processing speed, and saves processing resources.
Further effects of the above-mentioned unconventional preferred modes will be described below in conjunction with specific embodiments.
Drawings
In order to more clearly illustrate the embodiments or the prior art solutions of the present invention, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a schematic flow chart of a method for monitoring an operating state of a device according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of another method for monitoring an operating state of a device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for monitoring an operating state of an apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention. Unless otherwise specified, the technical means used in the examples are conventional means well known to those skilled in the art.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
The idea of remotely detecting the running state of equipment is more and more accepted by the development of big data and internet of things technology, the running state of the equipment is monitored in real time by using data, and when the running data deviates from the running standard (threshold or limit), the running data sometimes results from abnormal running of the equipment, but sometimes results from the change of the running standard due to the continuous change of the running condition of the equipment.
The equipment operation standard generally complies with some fixed threshold values or limit values set by an equipment manufacturer, but for some operation parameter standards, a relative evaluation standard or a dynamic evaluation standard can be introduced, wherein the standard is the same monitoring quantity of the same equipment under the same operation environment (geography, position and working condition), and the evaluation standard mainly comprises two parts, namely an evaluation reference value and a confidence interval determination.
The invention provides a method for monitoring the running state of equipment by combining a big data technology and based on a time sequence and a neural network algorithm.
Referring to fig. 1, a specific embodiment of the method for monitoring the operating state of the equipment according to the present invention is shown. In this embodiment, the method specifically includes the following steps:
step 101: and acquiring measuring point data of the equipment according to historical data of the equipment.
The device can be any device in the energy station, and collects and summarizes all or needed historical data information of the determined target device.
The measuring point data related in the embodiment can be realized by using a measuring point data acquisition module. The measuring point data acquisition module is mainly used for acquiring measuring point data of the equipment according to historical data of the equipment. The measuring point data acquisition module can comprise a preprocessing unit and a measuring point data acquisition unit, and the preprocessing unit and the measuring point data acquisition unit can be connected in series.
Specifically, repeated data and/or abnormal data which may appear in the time sequence data can be removed through the preprocessing unit, and then the time sequence data is grouped by the preset step length through the measuring point data acquiring unit. Thereby obtaining station data for the device.
Step 102: and processing the measuring point data by adopting a time sequence model to obtain a predicted value of the equipment at a preset moment.
The time series algorithm is a relatively mature algorithm which can realize prediction aiming at time series data, and the data information adopted by the embodiment is ordered according to time and is suitable for prediction by adopting a time series method. The time series model may include an Autoregressive model (AR), an Autoregressive moving average model (ARMA), a differentially integrated moving average Autoregressive model (ARIMA), and the like. In this embodiment, a differential integrated moving average Autoregressive (ARIMA) model may be preferably used to predict the predetermined time of the target device. The measuring point data involved in the step can be realized by a predicted value acquisition module.
It should be understood that the difference integration moving average autoregressive model is one of the preferred models in the present embodiment, but may be other time series models or algorithms, and is not limited herein.
Step 103: and processing the measuring point data and the predicted value by adopting a reverse error neural network to obtain a residual predicted value.
The BP (back propagation) neural network is a multi-layer feedback neural network, is one of the most widely used neural networks, has strong nonlinear mapping capability and self-learning and self-adapting capability, and can comprise a multi-layer feedforward neural network and an inverse error neural network.
The residual prediction value related in this embodiment may be implemented by using a residual prediction value obtaining module. The residual prediction value obtaining module is configured to perform operation processing on a difference value between the prediction value and the operation data, that is, the initial residual value, to obtain a residual prediction value. The residual prediction value obtaining module may include an initial residual value obtaining unit and a residual prediction value obtaining unit.
Specifically, the initial residual value obtaining unit may obtain, according to the measurement point data, operation data of the device at the preset time, so as to obtain an initial residual value; and the residual prediction value obtaining unit is used for processing the initial residual value by a reverse error neural network to obtain a residual prediction value.
Step 104: and obtaining an evaluation reference value according to the predicted value and the residual predicted value.
And the residual prediction value is a real number (including a rational number and an irrational number) and is signed, so that the evaluation reference value can be obtained by adding the prediction value and the residual prediction value.
The measuring point data related in the step can be realized by an evaluation reference value acquisition module.
Step 105: and determining a confidence interval of the equipment at the preset moment according to the measuring point data of the equipment and the evaluation reference value.
The evaluation reference value of the equipment operation is only a reference value, the reasonable operation of the equipment is theoretically an interval, the operation data in the interval are all reasonable ranges, and otherwise, the operation is abnormal.
The measured point data involved in this step can be implemented using a confidence interval determination module. The confidence interval determination module is mainly used for calculating and processing the measured point data of the equipment and the evaluation reference value, obtaining the average value and the standard deviation of the measured point data and further determining the confidence interval. The confidence interval determination module may include an average value acquisition unit, a standard deviation acquisition unit, and a confidence interval acquisition unit.
Specifically, the average value obtaining unit may obtain an average value based on the measured point data, the standard deviation obtaining unit may obtain a standard deviation based on the average value, and the confidence interval obtaining unit may obtain a confidence interval based on the standard deviation and the evaluation reference value.
Step 106: and determining the running state of the equipment according to the running data of the equipment at the preset moment and the confidence interval.
The real-time operation state of the equipment can be judged and determined based on the operation data (or referred to as actual value) and the confidence interval of the equipment at the preset moment.
The measuring point data involved in the step can be realized by using an operation state determining module.
According to the technical scheme, the beneficial effects of the embodiment are as follows: the method is combined with a big data technology, based on the combined use of a time series model and a reverse error neural network algorithm, the actual running state of the target equipment can be monitored and obtained in real time under the remote condition, and then the reasonable confidence interval range of the equipment running is combined, so that the defect of inaccurate prediction of the actual running state of the equipment in the prior art is effectively overcome, and meanwhile, the accurate prediction result is beneficial to scheduling optimization of subsequent work. The monitoring method provided by the embodiment is simple in overall operation, guarantees accuracy, convenience and rapidness of prediction, improves overall processing speed, and saves processing resources.
Fig. 1 shows only a basic embodiment of the method of the present invention, and based on this, certain optimization and expansion can be performed, and other preferred embodiments of the method can also be obtained.
Fig. 2 shows another embodiment of the method for monitoring the operation state of the device according to the present invention. The present embodiment is further described with reference to specific application scenarios on the basis of the foregoing embodiments. The method specifically comprises the following steps:
step 201: preprocessing acquired historical data of the equipment to acquire preprocessed time series data, wherein the preprocessing comprises removing repeated data and/or abnormal data in the historical data.
When the historical data is sorted, as much data as possible can be collected, so that the accuracy of prediction can be ensured.
The preprocessing involved in the step can be realized by a preprocessing unit of the measuring point data acquisition module.
Step 202: and grouping the time sequence data according to a preset step length, and calculating the average value of each group of data to obtain the measuring point data of the equipment.
The historical data set refers to historical standard data of equipment operation, and according to a statistical theory, the mean value of the sample can be regarded as a theoretical mean value, namely a theoretical standard value of the equipment operation. The measured point data adopted in this embodiment is sorted according to time, for example, the preset step length can be understood as that every 10 pieces of data are used as a group of data sequence, and the average value is calculated as new measured point data. It should be understood that 5 pieces of data, 20 pieces of data, and 99 pieces of data may be provided as a set of data sequences, and are not limited herein.
The selection of the data measuring points in the historical data set is related to the property of the equipment to be monitored, and if the boiler exhaust gas temperature is observed to be normal or not, the boiler exhaust gas temperature data needs to be input. This can also be understood as follows: the measuring point data is data of certain attribute of the target equipment. It should be understood that the data of the data measuring point about the equipment attribute may be various attribute data information of the equipment, such as the boiler exhaust gas temperature, the exhaust gas waste heat, and the like, and is not limited herein.
The measuring point data involved in the step can be realized by using a measuring point data acquisition unit of the measuring point data acquisition module.
Step 203: and processing the measured point data by adopting a difference integration moving average autoregressive model to obtain a predicted value of the equipment at a preset moment.
In this embodiment, it may be preferable that the difference-integrated moving average autoregressive model predicts the predetermined time of the target device. It should be understood that the difference integration moving average autoregressive model is one of the preferred models in the present embodiment, but may be other time series models or algorithms, and is not limited herein.
Step 204: and acquiring an initial residual value according to the measuring point data and the predicted value.
The initial residual value involved in the step can be realized by an initial residual value acquisition unit of a residual prediction value acquisition module.
Specifically, according to the measuring point data, the operation data of the equipment at the preset moment is obtained; and subtracting the predicted value from the operation data to obtain the initial residual value.
Step 205: and the inverse error neural network processes the initial residual value to obtain a residual prediction value.
The learning rule of the inverse error neural network is to use the steepest descent method to continuously adjust the weight and the threshold value of the network through back propagation so as to minimize the error square sum of the network.
In order to further improve the prediction accuracy, a reverse error neural network algorithm is adopted to predict the nonlinear residual errors of the measured point data (actual value) in the historical data and the predicted value of the time sequence, so that the predicted value of the time sequence is corrected, and finally the final prediction result is output. It should be understood that the inverse error neural network algorithm is one of the preferred algorithms in this embodiment, and other neural network algorithms are certainly possible, which is not limited herein.
And the difference is made between the predicted value and the operation data and is used as the input data of the inverse error neural network so as to realize the feedback of a difference integration moving average autoregressive model algorithm and ensure that the prediction result is more accurate.
The residual predicted value involved in the step can be realized by using a residual predicted value acquisition unit of the residual predicted value acquisition module.
Step 206: and in the step of obtaining an evaluation reference value according to the predicted value and the residual predicted value, the evaluation reference value is the sum of the predicted value and the residual predicted value.
Step 207: and acquiring an average value of the measuring point data according to the measuring point data of the equipment.
The average value of the measuring point data can be as follows: in time order, every 10 pieces of data are used as a group of data sequence, and the average value is calculated
It should be understood that 5 pieces of data, 20 pieces of data, and 99 pieces of data may be provided as a set of data sequences, and are not limited herein.
The average values involved in this step may be implemented using the average value obtaining unit of the confidence interval determination module.
Step 208: and acquiring the standard deviation of the measuring point data according to the average value of the measuring point data.
Based on the average value and the measured point data, the standard deviation σ of the measured point data can be obtained.
The standard deviation referred to in this step may be implemented using a standard deviation obtaining unit of the confidence interval determination module.
Step 209: and determining a confidence interval of the equipment at the preset moment according to the evaluation reference value and the standard deviation of the measuring point data.
In this embodiment, a 3 σ manner is adopted to determine a confidence interval, where the confidence interval is:
wherein ,
and sigma is the standard deviation of the measuring point data, and is the evaluation reference value.
The confidence interval involved in this step may be implemented by a confidence interval acquisition unit of the confidence interval determination module.
Step 210: and determining the running state of the equipment according to the running data of the equipment at the preset moment and the confidence interval.
The operation state referred to in this step can be realized by the operation state determination module.
According to the above technical solutions, on the basis of the embodiment shown in fig. 1, the present embodiment further has the following beneficial effects: by carrying out data preprocessing on the time series data, removing repeated data and/or abnormal data to enable the basic data to be more tidy and clean; grouping the time series data to enable the processed data to be closer to standard data, laying a foundation for further processing of data in subsequent steps, and improving prediction accuracy; meanwhile, according to the calculation result, the real-time running state of the equipment can be simply and quickly calculated, and whether the running state of the equipment is abnormal or not can be judged within a reasonable running range.
Fig. 3 shows an embodiment of the apparatus for monitoring the operation status of the device according to the present invention. The apparatus of this embodiment is a physical apparatus for performing the method described in fig. 1-2. The technical solution is essentially the same as that in the above embodiment, and the corresponding description in the above embodiment is also applicable to this embodiment. The device in this embodiment includes:
a measuring point data obtaining module 301, configured to obtain measuring point data of a device according to historical data of the device;
a predicted value obtaining module 302, configured to process the measurement point data by using a time series model, and obtain a predicted value of the device at a preset time;
a residual prediction value obtaining module 303, configured to process the measurement point data and the prediction value by using a reverse error neural network, so as to obtain a residual prediction value;
an evaluation reference value obtaining module 304, configured to obtain an evaluation reference value according to the predicted value and the residual predicted value;
a confidence interval determining module 305, configured to determine a confidence interval of the device at the preset time according to the measured point data of the device and the evaluation reference value;
and an operation state determining module 306, configured to determine an operation state of the device according to the operation data of the device at the preset time and the confidence interval.
In addition, on the basis of the embodiment shown in fig. 3, preferably, the station data acquiring module 301 may include:
the preprocessing unit is used for preprocessing the acquired historical data of the equipment to acquire preprocessed time series data, and the preprocessing comprises removing repeated data and/or abnormal data in the historical data.
And the measuring point data acquisition unit is used for grouping the time series data according to a preset step length and calculating the average value of each group of data so as to acquire the measuring point data of the equipment.
Preferably, the residual prediction value obtaining module 303 may include:
and the initial residual value obtaining unit is used for obtaining an initial residual value according to the measuring point data and the predicted value.
Specifically, according to the measuring point data, the operation data of the equipment at the preset moment is obtained; and subtracting the predicted value from the operation data to obtain the initial residual value.
And the residual prediction value obtaining unit is used for processing the initial residual value by the reverse error neural network to obtain a residual prediction value.
Preferably, the confidence interval determination module 305 may include:
and the average value acquisition unit is used for acquiring the average value of the measuring point data according to the measuring point data of the equipment.
And the standard deviation acquisition unit is used for acquiring the standard deviation of the measuring point data according to the average value of the measuring point data.
And the confidence interval acquisition unit is used for determining the confidence interval of the equipment at the preset time according to the evaluation reference value and the standard deviation of the measuring point data.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. On the hardware level, the electronic device comprises a processor and optionally an internal bus, a network interface and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (peripheral component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.
And the memory is used for storing the execution instruction. In particular, a computer program that can be executed by executing instructions. The memory may include both memory and non-volatile storage and provides execution instructions and data to the processor.
In a possible implementation manner, the processor reads the corresponding execution instruction from the nonvolatile memory to the memory and then executes the execution instruction, and may also obtain the corresponding execution instruction from other devices, so as to form the monitoring device of the device operation state on a logic level. The processor executes the execution instructions stored in the memory to implement the method for operating the device provided by any embodiment of the invention through the executed execution instructions.
The method executed by the device for monitoring the operating status of the equipment according to the embodiment of the invention shown in fig. 3 can be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
An embodiment of the present invention further provides a readable storage medium, where the readable storage medium stores an execution instruction, and when the stored execution instruction is executed by a processor of an electronic device, the electronic device can be caused to perform the method for monitoring the device operating state provided in any embodiment of the present invention, and is specifically configured to perform the methods shown in fig. 1 to fig. 2.
The electronic device described in the foregoing embodiments may be a computer.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, 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, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A method for monitoring the running state of equipment is characterized by comprising the following steps:
acquiring measuring point data of the equipment according to historical data of the equipment;
processing the measuring point data by adopting a time sequence model to obtain a predicted value of the equipment at a preset moment;
processing the measuring point data and the predicted value by adopting a reverse error neural network to obtain a residual predicted value;
obtaining an evaluation reference value according to the predicted value and the residual predicted value;
determining a confidence interval of the equipment at the preset moment according to the measuring point data of the equipment and the evaluation reference value;
and determining the running state of the equipment according to the running data of the equipment at the preset moment and the confidence interval.
2. The method for monitoring the running state of the equipment according to claim 1, wherein the step of acquiring the measuring point data of the equipment according to the historical data of the equipment comprises the following steps:
preprocessing acquired historical data of the equipment to acquire preprocessed time series data, wherein the preprocessing comprises removing repeated data and/or abnormal data in the historical data;
and grouping the time sequence data according to a preset step length, and calculating the average value of each group of data to obtain the measuring point data of the equipment.
3. The method of monitoring the operational status of a plant according to claim 1, wherein the time series model comprises a differential integrated moving average autoregressive model.
4. The method for monitoring the operating condition of the equipment according to claim 1, wherein the processing the measured point data and the predicted value by using an inverse error neural network to obtain a residual predicted value comprises:
acquiring an initial residual value according to the measuring point data and the predicted value;
and the inverse error neural network processes the initial residual value to obtain a residual prediction value.
5. The method for monitoring the running state of the equipment according to claim 4, wherein the step of obtaining the initial residual value according to the measured point data and the predicted value comprises the following steps:
acquiring the operation data of the equipment at the preset moment according to the measuring point data;
and subtracting the predicted value from the operation data to obtain the initial residual value.
6. The method for monitoring an operating status of an apparatus according to claim 1, wherein in the step of obtaining an evaluation reference value according to the predicted value and the residual predicted value, the evaluation reference value is a sum of the predicted value and the residual predicted value.
7. The method for monitoring the running state of the equipment according to claim 1, wherein the step of determining the confidence interval of the equipment at the preset moment according to the measured point data of the equipment and the evaluation reference value comprises the following steps:
acquiring an average value of the measuring point data according to the measuring point data of the equipment;
acquiring the standard deviation of the measuring point data according to the average value of the measuring point data;
determining a confidence interval of the equipment at the preset time according to the evaluation reference value and the standard deviation of the measuring point data, wherein the confidence interval is as follows:
wherein ,
and sigma is the standard deviation of the measuring point data, and is the evaluation reference value.
8. An apparatus for monitoring an operating condition of a device, comprising:
the measuring point data acquisition module is used for acquiring measuring point data of the equipment according to historical data of the equipment;
the predicted value acquisition module is used for processing the measuring point data by adopting a time sequence model to acquire a predicted value of the equipment at a preset moment;
the residual predicted value obtaining module is used for processing the measuring point data and the predicted value by adopting a reverse error neural network to obtain a residual predicted value;
the evaluation reference value obtaining module is used for obtaining an evaluation reference value according to the predicted value and the residual predicted value;
the confidence interval determining module is used for determining the confidence interval of the equipment at the preset moment according to the measuring point data of the equipment and the evaluation reference value;
and the operation state determining module is used for determining the operation state of the equipment according to the operation data of the equipment at the preset moment and the confidence interval.
9. A readable medium comprising executable instructions which, when executed by a processor of an electronic device, cause the electronic device to perform a method of monitoring the operational status of a device as claimed in any one of claims 1 to 7.
10. An electronic device comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method for monitoring the operation status of the device according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010341683.2A CN111414999B (en) | 2020-04-27 | 2020-04-27 | Method and device for monitoring running state of equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010341683.2A CN111414999B (en) | 2020-04-27 | 2020-04-27 | Method and device for monitoring running state of equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111414999A true CN111414999A (en) | 2020-07-14 |
| CN111414999B CN111414999B (en) | 2023-08-22 |
Family
ID=71492065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010341683.2A Active CN111414999B (en) | 2020-04-27 | 2020-04-27 | Method and device for monitoring running state of equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111414999B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115418A (en) * | 2020-08-13 | 2020-12-22 | 深圳市智物联网络有限公司 | Method, device and equipment for acquiring bias estimation information |
| CN112422376A (en) * | 2020-10-15 | 2021-02-26 | 招商华软信息有限公司 | Method for automatically accessing non-standardized equipment to cloud platform, electronic equipment and storage medium |
| CN112668887A (en) * | 2020-12-29 | 2021-04-16 | 新奥数能科技有限公司 | Service data acquisition method and device, readable storage medium and electronic equipment |
| CN113190429A (en) * | 2021-06-03 | 2021-07-30 | 河北师范大学 | Server performance prediction method and device and terminal equipment |
| CN113300371A (en) * | 2021-05-31 | 2021-08-24 | 广东电网有限责任公司 | Method and device for determining real-time voltage of power distribution room |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040102937A1 (en) * | 2002-11-21 | 2004-05-27 | Honeywell International Inc. | Energy forecasting using model parameter estimation |
| CN101771758A (en) * | 2008-12-31 | 2010-07-07 | 北京亿阳信通软件研究院有限公司 | Dynamic determine method for normal fluctuation range of performance index value and device thereof |
| US20120303408A1 (en) * | 2000-10-17 | 2012-11-29 | Jeff Scott Eder | Automated risk transfer system |
| CN104380739A (en) * | 2013-04-05 | 2015-02-25 | 索尼公司 | Image processing device and image processing method |
| CN106529145A (en) * | 2016-10-27 | 2017-03-22 | 浙江工业大学 | ARIMA-BP neutral network-based bridge monitoring data prediction method |
| CN106599271A (en) * | 2016-12-22 | 2017-04-26 | 江苏方天电力技术有限公司 | Emission monitoring time series data abnormal value detection method for coal-fired unit |
| CN107092582A (en) * | 2017-03-31 | 2017-08-25 | 江苏方天电力技术有限公司 | One kind is based on the posterior exceptional value on-line checking of residual error and method for evaluating confidence |
| CN107194034A (en) * | 2017-04-21 | 2017-09-22 | 广州明珞汽车装备有限公司 | A kind of equipment damage detection method and system based on GPR |
| CN107633331A (en) * | 2017-09-26 | 2018-01-26 | 北京福布罗科技有限公司 | Time series models method for building up and device |
| CN109948714A (en) * | 2019-03-22 | 2019-06-28 | 华南理工大学 | Chinese scene text row recognition methods based on residual error convolution sum recurrent neural network |
| CN110297712A (en) * | 2019-05-20 | 2019-10-01 | 贵州联科卫信科技有限公司 | A kind of ARIMA combination forecasting method towards block chain node load estimation |
| CN110400010A (en) * | 2019-07-11 | 2019-11-01 | 新华三大数据技术有限公司 | Prediction technique, device, electronic equipment and computer readable storage medium |
-
2020
- 2020-04-27 CN CN202010341683.2A patent/CN111414999B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120303408A1 (en) * | 2000-10-17 | 2012-11-29 | Jeff Scott Eder | Automated risk transfer system |
| US20040102937A1 (en) * | 2002-11-21 | 2004-05-27 | Honeywell International Inc. | Energy forecasting using model parameter estimation |
| CN101771758A (en) * | 2008-12-31 | 2010-07-07 | 北京亿阳信通软件研究院有限公司 | Dynamic determine method for normal fluctuation range of performance index value and device thereof |
| CN104380739A (en) * | 2013-04-05 | 2015-02-25 | 索尼公司 | Image processing device and image processing method |
| CN106529145A (en) * | 2016-10-27 | 2017-03-22 | 浙江工业大学 | ARIMA-BP neutral network-based bridge monitoring data prediction method |
| CN106599271A (en) * | 2016-12-22 | 2017-04-26 | 江苏方天电力技术有限公司 | Emission monitoring time series data abnormal value detection method for coal-fired unit |
| CN107092582A (en) * | 2017-03-31 | 2017-08-25 | 江苏方天电力技术有限公司 | One kind is based on the posterior exceptional value on-line checking of residual error and method for evaluating confidence |
| CN107194034A (en) * | 2017-04-21 | 2017-09-22 | 广州明珞汽车装备有限公司 | A kind of equipment damage detection method and system based on GPR |
| CN107633331A (en) * | 2017-09-26 | 2018-01-26 | 北京福布罗科技有限公司 | Time series models method for building up and device |
| CN109948714A (en) * | 2019-03-22 | 2019-06-28 | 华南理工大学 | Chinese scene text row recognition methods based on residual error convolution sum recurrent neural network |
| CN110297712A (en) * | 2019-05-20 | 2019-10-01 | 贵州联科卫信科技有限公司 | A kind of ARIMA combination forecasting method towards block chain node load estimation |
| CN110400010A (en) * | 2019-07-11 | 2019-11-01 | 新华三大数据技术有限公司 | Prediction technique, device, electronic equipment and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| SUNOK KIM，等: "Unified Confidence Estimation Networks for Robust Stereo Matching" * |
| 潘轶彪，等: "基于多层感知器的异常数据实时检测方法" * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115418A (en) * | 2020-08-13 | 2020-12-22 | 深圳市智物联网络有限公司 | Method, device and equipment for acquiring bias estimation information |
| CN112115418B (en) * | 2020-08-13 | 2024-03-26 | 深圳市智物联网络有限公司 | Method, device and equipment for acquiring bias estimation information |
| CN112422376A (en) * | 2020-10-15 | 2021-02-26 | 招商华软信息有限公司 | Method for automatically accessing non-standardized equipment to cloud platform, electronic equipment and storage medium |
| CN112668887A (en) * | 2020-12-29 | 2021-04-16 | 新奥数能科技有限公司 | Service data acquisition method and device, readable storage medium and electronic equipment |
| CN113300371A (en) * | 2021-05-31 | 2021-08-24 | 广东电网有限责任公司 | Method and device for determining real-time voltage of power distribution room |
| CN113300371B (en) * | 2021-05-31 | 2022-07-12 | 广东电网有限责任公司 | Method and device for determining real-time voltage of power distribution room |
| CN113190429A (en) * | 2021-06-03 | 2021-07-30 | 河北师范大学 | Server performance prediction method and device and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111414999B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111414999B (en) | Method and device for monitoring running state of equipment | |
| CN112311611B (en) | Data anomaly monitoring method and device and electronic equipment | |
| CN109143094B (en) | Abnormal data detection method and device for power battery | |
| CN111832827A (en) | Distribution network fault early warning method and device, readable medium and electronic equipment | |
| US11620539B2 (en) | Method and device for monitoring a process of generating metric data for predicting anomalies | |
| CN110688617B (en) | Fan vibration abnormity detection method and device | |
| CN114723082B (en) | Abnormality early warning method and system for intelligent low-voltage complete equipment | |
| CN110838075A (en) | Training and predicting method and device for prediction model of transient stability of power grid system | |
| CN111401795A (en) | Method and device for evaluating health state of equipment, readable medium and electronic equipment | |
| CN111523205B (en) | Specific enthalpy determining method and device for superheated steam | |
| CN114648245A (en) | Equipment inspection priority evaluation method and system based on artificial intelligence | |
| CN111445105B (en) | Power plant online performance diagnosis method and system based on target value analysis | |
| KR101998972B1 (en) | Method of analyzing and visualizing the cause of process failure by deriving the defect occurrence index by variable sections | |
| CN114444827A (en) | Cluster performance evaluation method and device | |
| CN112330063B (en) | Equipment fault prediction method, equipment fault prediction device and computer readable storage medium | |
| CN110866682A (en) | Underground cable early warning method and device based on historical data | |
| CN110718231A (en) | Monitoring method, device, terminal and storage medium based on acoustic network | |
| CN111259338B (en) | Component failure rate correction method and device, computer equipment and storage medium | |
| CN110646229B (en) | Air preheater fault diagnosis method and device, electronic equipment and storage medium | |
| CN116432527A (en) | Cavitation prediction method and device, storage medium and electronic equipment | |
| JPH10187226A (en) | Plant state predicting device | |
| CN110553678A (en) | Multi-sensor system detection method and device, computer equipment and storage medium | |
| CN112802313B (en) | Alarm method and device of equipment | |
| CN112700043B (en) | Load prediction method, load prediction device, computer readable storage medium and electronic equipment | |
| CN111274687B (en) | Component failure rate prediction method and device, computer equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230724 Address after: 065001 China (Hebei) Pilot Free Trade Zone Daxing Airport Area Langfang Airport Economic Zone Hangyidao Free Trade Zone Science and Technology Innovation Base 2101, Langfang City, Hebei Province Applicant after: Xinao Xinzhi Technology Co.,Ltd. Address before: 100102 10th floor, 1 Wangjing East Road, Chaoyang District, Beijing Applicant before: ENNEW DIGITAL TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |