CN117234166B - Fault perception operation and maintenance method and system for equipment - Google Patents
Fault perception operation and maintenance method and system for equipment Download PDFInfo
- Publication number
- CN117234166B CN117234166B CN202311490007.1A CN202311490007A CN117234166B CN 117234166 B CN117234166 B CN 117234166B CN 202311490007 A CN202311490007 A CN 202311490007A CN 117234166 B CN117234166 B CN 117234166B
- Authority
- CN
- China
- Prior art keywords
- equipment
- result
- response parameter
- fault
- data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012423 maintenance Methods 0.000 title claims abstract description 20
- 230000008447 perception Effects 0.000 title abstract description 3
- 230000004044 response Effects 0.000 claims abstract description 139
- 238000004140 cleaning Methods 0.000 claims abstract description 32
- 230000007613 environmental effect Effects 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims description 69
- 230000005856 abnormality Effects 0.000 claims description 68
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 238000010276 construction Methods 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 7
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 239000007788 liquid Substances 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000012530 fluid Substances 0.000 description 4
- 238000012546 transfer Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
Abstract
The disclosure provides a fault perception operation and maintenance method and system of equipment, and relates to an intelligent control technology, wherein the method comprises the following steps: constructing a device feature set, including device size features and device flow features; determining an equipment working mode; constructing a response parameter set, wherein the response parameter set is constructed through a response parameter database extracted by big data and a cleaning influence factor; extracting the characteristics of a supply pipeline of the equipment to generate calibrated heat loss data; constructing a device supervision feature set, including a supply pressure feature, a straight pipeline flow velocity feature and a heat exchange result feature; compensating the calibrated heat loss data through the environmental characteristic factors, and carrying out fault collaborative identification on the equipment supervision characteristic set according to the compensation result and the response parameter set; and carrying out response control on the equipment according to the fault collaborative identification result. The technical problem that equipment fault sensing accuracy is low due to the interference of various factors can be solved, and the accuracy of equipment fault sensing can be improved, so that the accuracy of equipment control is improved.
Description
Technical Field
The present disclosure relates to intelligent control technology, and more particularly, to a fault-aware operation and maintenance method and system for a device.
Background
In modern industrial production, equipment failure and downtime are very challenging and costly problems for the enterprise, and predictive maintenance has emerged as an advanced maintenance strategy to address this problem.
The predictive maintenance is to analyze the equipment operation data, sense and predict the possible faults of the equipment according to the data analysis result, and in the existing equipment fault sensing process, the accuracy and the accuracy of analyzing a plurality of interference factors such as the outside and the inside are lower, so that the equipment fault sensing accuracy is lower, and the accuracy of equipment control is affected.
The existing equipment fault sensing method has the following defects: the fault sensing accuracy of the equipment is low due to interference of various factors.
Disclosure of Invention
Therefore, in order to solve the above technical problems, the technical solution adopted in the embodiments of the present disclosure is as follows:
a fault-aware operation and maintenance method of a device, comprising the steps of: constructing a device feature set of the device, wherein the device feature set is constructed according to basic data of the device and comprises device size features and device flow features; determining an equipment working mode of the equipment, wherein the equipment working mode is obtained by reading control parameters of the equipment after communication connection with the equipment is established; constructing a response parameter set, wherein the response parameter set is constructed through a response parameter database extracted from big data and a cleaning influence factor, and the response parameter data is obtained by taking the equipment working mode and the equipment characteristic set as basic data in a matching way; extracting supply pipeline characteristics of the equipment according to the equipment characteristic set, and generating calibration heat loss data according to the supply pipeline characteristics and the equipment working mode; constructing an equipment supervision feature set, wherein the equipment supervision feature set comprises a supply pressure feature, a straight pipeline flow velocity feature and a heat exchange result feature; collecting and generating an environmental characteristic factor, compensating the calibrated heat loss data through the environmental characteristic factor, and carrying out fault collaborative identification on the equipment supervision characteristic set according to a compensation result and the response parameter set; and carrying out response control on the equipment according to the fault collaborative identification result.
A fault-aware operation and maintenance system for a device, comprising: the device feature set construction module is used for constructing a device feature set of the device, the device feature set is constructed according to basic data of the device, and the device feature set comprises device size features and device flow features; the device working mode determining module is used for determining a device working mode of the device, wherein the device working mode is obtained by reading control parameters of the device after communication connection with the device is established; the response parameter set construction module is used for constructing a response parameter set, the response parameter set is constructed through a response parameter database extracted by big data and a cleaning influence factor, and the response parameter data is obtained by taking the equipment working mode and the equipment characteristic set as basic data in a matching way; the calibration heat loss data generation module is used for extracting the characteristics of a supply pipeline of the equipment according to the equipment characteristic set and generating calibration heat loss data according to the characteristics of the supply pipeline and the equipment working mode; the device monitoring feature set construction module is used for constructing a device monitoring feature set, and the device monitoring feature set comprises a supply pressure feature, a straight pipeline flow speed feature and a heat exchange result feature; the fault collaborative recognition module is used for collecting and generating an environmental characteristic factor, compensating the calibrated heat loss data through the environmental characteristic factor, and carrying out fault collaborative recognition on the equipment supervision characteristic set according to a compensation result and the response parameter set; and the equipment response control module is used for carrying out response control on the equipment according to the fault collaborative identification result.
By adopting the technical method, compared with the prior art, the technical progress of the present disclosure has the following points:
the technical problem that the equipment fault sensing accuracy is low due to the interference of various factors in the existing equipment fault sensing method can be solved, the interference of the cleaning influence factors on response parameters can be eliminated by combining the response parameter database and the cleaning influence factors to construct a response parameter set, and the accuracy of the construction of the response parameter set is improved; the generated environmental characteristic factors compensate the calibration heat loss data, so that the interference of the environment on the calibration heat loss data can be eliminated, and the accuracy of the calibration heat loss data is improved; and finally, performing fault sensing on the equipment according to the calibrated heat loss data and the response parameter set after compensation, so that the interference of various factors can be eliminated, the accuracy of equipment fault sensing is improved, and the accuracy of equipment control is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are used in the description of the embodiments will be briefly described below.
Fig. 1 is a schematic flow chart of a fault-aware operation and maintenance method of a device;
Fig. 2 is a schematic flow chart of constructing a response parameter set in a fault-aware operation and maintenance method of a device according to the present application;
fig. 3 is a schematic structural diagram of a fault-aware operation and maintenance system of a device according to the present application.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
Based on the above description, as shown in fig. 1, the present disclosure provides a fault-aware operation and maintenance method of a device, including:
constructing a device feature set of the device, wherein the device feature set is constructed according to basic data of the device and comprises device size features and device flow features;
the method provided by the application is used for improving the accuracy of equipment fault sensing so as to further improve the accuracy of equipment control, wherein the equipment mainly refers to equipment such as a heat exchanger, but the application range of the method is not limited to the heat exchanger, and in order to enable a person skilled in the art to conveniently understand the equipment, in the following embodiment, the equipment fault sensing operation and maintenance system mainly comprises the heat exchanger for illustration.
The heat exchanger is an energy-saving device for realizing heat transfer between two or more fluids with different temperatures, and is used for transferring heat from a fluid with a higher temperature to a fluid with a lower temperature, so that the temperature of the fluid reaches the index specified by a flow.
Firstly, acquiring basic data of equipment, wherein the basic data of the equipment comprise data such as equipment brands, equipment types, equipment models, equipment sizes, equipment operation control parameters and the like, and extracting equipment characteristic data in the basic data of the equipment, wherein the equipment characteristic data comprise equipment size characteristics and equipment flow characteristics, the equipment size characteristics comprise structures of all parts of the equipment and sizes of all parts, and the heat exchanger is exemplified by straight pipes, spiral pipes, flow path plates and the like; wherein the flow characteristics of the device refer to the flow rate, heat loss, heat exchange effect and other characteristics of the device, such as: flow rate of liquid in the pipeline in the heat exchanger, heat transfer efficiency and the like. And obtaining the equipment size characteristics and the equipment flow characteristics, and constructing an equipment characteristic set according to the equipment size characteristics and the equipment flow characteristics. By constructing the device feature set, data support is provided for the next step of device operation data analysis, and the response parameter set is constructed.
Determining an equipment working mode of the equipment, wherein the equipment working mode is obtained by reading control parameters of the equipment after communication connection with the equipment is established;
the equipment and the fault sensing operation and maintenance system of the equipment realize data interaction in a signal transmission mode, firstly, communication connection between the system and the equipment is established, after connection establishment is completed, control parameters of the equipment are obtained, wherein the control parameters refer to operation control parameters of the current equipment, a heat exchanger is taken as an example, the operation control parameters comprise parameters such as liquid flow rate, heat exchange quantity and the like in a pipeline, and then the working mode of the equipment is determined according to the control parameters of the equipment. By obtaining the device operating mode, support is provided for obtaining response parameter data in the next step.
Constructing a response parameter set, wherein the response parameter set is constructed through a response parameter database extracted from big data and a cleaning influence factor, and the response parameter data is obtained by taking the equipment working mode and the equipment characteristic set as basic data in a matching way;
as shown in fig. 2, in one embodiment, the method further comprises:
calling a device ID according to the device feature set;
Taking the equipment ID as a backtracking feature, executing the backtracking of the equipment in the same batch of equipment, and obtaining a batch test data set of equipment backtracking, wherein the batch test data set is provided with a sample size identifier;
invoking a homotype test data set of the same type, wherein the homotype test data set is equipment test data of equipment of the same type as the equipment, and the invoking amount of the homotype test data set is determined by the sample amount;
configuring initial trust values of equipment in the same batch and equipment in the same model, and performing trust adjustment on the initial trust values according to the sample size proportion;
and extracting test characteristics of the batch test data set and the isotype test data set according to trust adjustment results to construct the response parameter set.
Based on big data technology, relevant data inquiry is carried out according to the equipment characteristic set, and a response parameter database is constructed according to the data inquiry result.
First, a device ID is obtained from the device feature set, wherein the device ID refers to a serial number for characterizing the device identity, and each device has a unique device ID. And then taking the equipment ID as a backtracking feature, wherein the backtracking feature is an information searching feature, carrying out data searching based on a big data technology to obtain a plurality of same-batch equipment of the equipment, wherein the same-batch equipment is equipment which has the same production batch and the same model as the equipment, and obtaining batch test data sets of the plurality of same-batch equipment according to the plurality of same-batch equipment, wherein the batch test data sets are provided with sample quantity identifiers, and the sample quantity is the sample quantity of the batch test data sets. The batch test data set refers to equipment test data of the same batch of equipment in operation, wherein the equipment test data comprises data such as flow rate, pressure supply, heat exchange effect and the like of the equipment in operation.
And then calling the equipment test data of the equipment with the same model according to the equipment ID, wherein the equipment with the same model refers to equipment with the same model and different batches of equipment, the calling quantity of the equipment with the same model test data set is determined through the sample quantity, when the sample quantity is larger, the calling quantity of the equipment with the same model test data set is properly reduced, and when the sample quantity is smaller, the calling quantity of the equipment with the same model test data set is properly increased.
And carrying out initial trust value configuration on the same batch of equipment and the same type of equipment, wherein the initial trust value of the same batch of equipment is larger than the initial trust value of the same type of equipment, namely the reliability of the same batch of equipment is higher, and the specific value of the initial trust value can be set by oneself according to actual conditions. And performing trust adjustment on the initial trust value according to a sample size ratio, wherein the sample size ratio refers to the ratio of the sample size to the call volume, the larger the sample size is, the larger the number of the equipment in the same batch is represented, the initial trust value of the equipment in the same batch is increased, the smaller the sample size is, the larger the number of the equipment in the same type is represented, and the initial trust value of the equipment in the same type is increased. And obtaining trust adjustment results of the equipment in the same batch and the equipment in the same model.
And then extracting the test characteristics of the batch test data set and the test data set with the same type according to the trust adjustment result, and constructing a response parameter set according to the test characteristic extraction result.
By adjusting the initial trust values of the equipment in the same batch and the equipment in the same type according to the sample size proportion, the accuracy of the test characteristics in the test data set can be improved, and the accuracy of the construction of the response parameter database is improved.
In one embodiment, the method further comprises:
establishing a sample mean standard line according to the batch test data set;
taking the sample mean standard line as an evaluation reference, and performing individual discrete evaluation on the homotypic test data set and the batch test data set;
and carrying out individual deviation calculation according to the individual discrete evaluation result and the trust adjustment result, and carrying out sample elimination according to the individual deviation calculation result so as to construct the response parameter set.
And carrying out average processing on the flow velocity, the pressure supply and the heat exchange effect in the batch test data set to obtain a flow velocity average value, a pressure supply average value and a heat exchange effect average value of the batch test data, and then establishing a sample average value standard line according to the flow velocity average value, the pressure supply average value and the heat exchange effect average value.
Taking the sample mean value standard line as an evaluation standard, and performing individual discrete evaluation on the homotype test data set and the batch test data set according to the sample mean value standard line, wherein the individual discrete evaluation refers to judging the discrete degree of the test data according to the difference value between the test data in the homotype test data set and the batch test data set and the sample mean value standard line, wherein the larger the difference value between the test data and the sample mean value standard line is, the higher the individual discrete degree is; the smaller the difference, the lower the degree of individual discreteness. The individual discrete degree can be represented by setting an individual discrete coefficient, the larger the individual discrete degree is, the larger the individual discrete coefficient is, the smaller the individual discrete degree is, and the individual discrete coefficient can be assigned by a person skilled in the art according to actual conditions.
And then, carrying out individual deviation calculation according to an individual discrete evaluation result and the trust adjustment result, firstly, setting an individual discrete weight value according to the trust adjustment result, wherein the larger the trust value of an individual is, the more reliable the test data of the individual are represented, the smaller the weight value is, the smaller the trust value of the individual is, the larger the weight value is, the weight value can be set according to the trust adjustment result through the existing variation coefficient method, and the variation coefficient method is a commonly used weighting method for a person skilled in the art, and is not described in an unfolding way, so that the individual discrete weight value is obtained.
And then carrying out weighted calculation on the individual discrete evaluation results according to the individual discrete weight values, namely multiplying the individual discrete weight values by corresponding individual discrete coefficients to obtain individual deviation calculation results. An individual deviation threshold is set, wherein the individual deviation threshold can be set according to the actual conditions of the test data and the sample size. Judging an individual deviation calculation result according to an individual deviation threshold, eliminating a sample corresponding to the individual deviation calculation result when the individual deviation calculation result is larger than the individual deviation threshold, and constructing a response parameter database according to the rest of the individuals, namely the rest of test data.
By inquiring and extracting test data of the same-batch and same-type equipment based on big data and screening the data reliability of the extracted test data and constructing a response parameter database according to the screened reliable data, the construction accuracy of the response parameter database can be improved, and the acquisition accuracy of a response parameter set can be improved.
Acquiring a cleaning influence factor of the equipment, wherein the cleaning influence factor is used for representing the influence degree of a cleaning state in a pipeline of the equipment on response parameters, wherein the smaller the influence degree is, the smaller the cleaning influence factor is, and the larger the influence degree is, the larger the cleaning influence factor is; for example: in the use process of the heat exchanger, corresponding dirt, scale and other impurities can be generated according to the use time, and the pipeline cleaning is required to be carried out regularly to ensure the use efficiency of the heat exchanger. The cleaning influence factor can be set according to a device cleaning time interval which is the most recent time, wherein the shorter the time interval is, the higher the cleaning degree of the device is, the smaller the cleaning influence factor is, and the longer the time interval is, the lower the cleaning degree of the device is, and the larger the cleaning influence factor is.
And then inputting the equipment working mode and the equipment characteristic set into the response parameter database to perform response parameter matching to obtain a response parameter set, and adjusting the response parameter set according to a cleaning influence factor, for example: taking the heat exchanger as an example, when the dirt in the pipeline of the heat exchanger is more, when the pressure supply is unchanged, the liquid flow rate in the pipeline can be increased, and at the moment, the liquid flow rate in the pipeline is adjusted according to the size of the cleaning influence factor, so that the influence of the dirt in the pipeline on the liquid flow rate can be eliminated, and the liquid flow rate is more fit with the actual situation. A set of response parameters for the cleaning impact factor adjustment is obtained.
By obtaining the response parameter set, support is provided for the next step of equipment fault sensing, and the accuracy of obtaining the response parameter set can be improved, and meanwhile, the accuracy of equipment fault sensing can be improved due to the fact that the influence of the pipeline cleaning degree on the response parameter set is considered when the response parameter set is constructed.
Extracting supply pipeline characteristics of the equipment according to the equipment characteristic set, and generating calibration heat loss data according to the supply pipeline characteristics and the equipment working mode;
Extracting the characteristics of a supply pipeline of the equipment according to the characteristic set of the equipment, wherein the supply pipeline refers to a supply and delivery pipeline of liquid in the equipment, the characteristics of the supply pipeline comprise pipeline materials, pipeline dimensions, pipeline thickness and the like, and then calculating heat loss data according to the characteristics of the supply pipeline and the working mode of the equipment, wherein the heat loss refers to the heat loss proportion in the working process of a heat exchanger, and calibrated heat loss data refers to the standard heat loss proportion under the condition that other factors are not considered. And by obtaining the calibrated heat loss data, a judgment basis is provided for the next step of equipment operation state identification.
Constructing an equipment supervision feature set, wherein the equipment supervision feature set comprises a supply pressure feature, a straight pipeline flow velocity feature and a heat exchange result feature;
and acquiring an equipment supervision index, wherein the equipment supervision index comprises pressure, straight pipeline flow rate and heat exchange results, and the heat exchange results refer to the heat transfer efficiency of the heat exchanger. And monitoring the equipment according to the equipment supervision index to obtain a real-time supervision characteristic set of the equipment, namely an equipment supervision characteristic set, wherein the equipment supervision characteristic set comprises a supply pressure characteristic, a straight pipeline flow speed characteristic and a heat exchange result characteristic. By obtaining the equipment supervision feature set, data support is provided for the next step of equipment fault identification.
Collecting and generating an environmental characteristic factor, compensating the calibrated heat loss data through the environmental characteristic factor, and carrying out fault collaborative identification on the equipment supervision characteristic set according to a compensation result and the response parameter set;
the temperature sensor is used for collecting the ambient temperature of the equipment to obtain ambient temperature data, generating an ambient characteristic factor according to the ambient temperature data, and then optimizing and adjusting the calibrated heat loss data according to the ambient characteristic factor, for example: when the temperature is too high and is higher than the standard operating temperature, the difficulty of machine cooling is increased, the heat loss data is higher than the calibrated heat loss data, the value of the calibrated heat loss data is required to be increased, and when the temperature is lower than the standard operating temperature, the value of the calibrated heat loss data is properly reduced. And obtaining a calibration heat loss data compensation result. And then carrying out fault collaborative identification on the equipment supervision feature set according to the calibration heat loss data compensation result and the response parameter set.
In one embodiment, the method further comprises:
generating a pressure supply abnormality identification result, wherein the pressure supply abnormality identification result is obtained by performing pressure identification on the supply pressure characteristics by the response parameter set, and the pressure supply abnormality identification result comprises a steady state value abnormality result and a stability abnormality result;
In one embodiment, the method further comprises:
constructing a driving parameter set, wherein the driving parameter set is obtained by monitoring an input voltage signal of the equipment;
using a standard voltage signal as a reference signal to map the supply pressure influence of the driving parameter set;
and performing recognition compensation of the pressure supply abnormality recognition result according to the mapping result.
And carrying out pressure recognition on the supply pressure characteristic according to the response parameter set, marking the supply pressure characteristic as pressure supply abnormality when the supply pressure characteristic does not meet the supply pressure in the response parameter set, obtaining a pressure supply abnormality recognition result, and then carrying out optimization adjustment on the pressure supply abnormality recognition result according to the equipment voltage.
Firstly, monitoring input voltage in the running process of the equipment to obtain an input voltage signal set in the running process of the equipment, and constructing a driving parameter set according to the input voltage signal set.
And acquiring a standard voltage signal in the running process of the equipment, wherein the standard voltage signal refers to a voltage value of the equipment in a normal working state. And then taking the standard voltage signal as a reference signal, and carrying out supply pressure influence mapping on the driving parameter set, wherein the supply pressure influence mapping is that a mapping relation between voltage and supply pressure is established, and the larger the voltage is, the larger the supply pressure is, and the smaller the voltage is, and the smaller the supply pressure is.
And then performing recognition compensation on the pressure supply abnormality recognition result according to the mapping result, for example: assuming that the supply pressure is 10 in the case of the standard voltage, when the device input voltage is too small, and the supply pressure according to the voltage map at this time is 9.8, the supply pressure 9.8 is a normal value, and there is no case that the device pressure supply is abnormal. And judging a pressure supply abnormality identification result subjected to identification compensation according to the supply pressure in the response parameter set, and generating a pressure supply abnormality identification result, wherein the pressure supply abnormality identification result comprises a steady state value abnormality result and a stability abnormality result, the steady state value abnormality result refers to the amplitude difference value between the supply pressure characteristic and the standard supply pressure characteristic, and the stability abnormality result refers to the fluctuation frequency of the supply pressure characteristic.
By constructing the mapping relation of the input voltage and the supply pressure to identify and compensate the pressure supply abnormality identification result, the accuracy of the pressure supply abnormality identification result can be improved.
Taking the pressure supply abnormality identification result as first cooperative data, and performing cooperative abnormality identification of the flow rate on the straight pipeline flow rate characteristics through the response parameter set to generate a flow rate abnormality identification result;
And obtaining the fault collaborative recognition result according to the pressure supply abnormality recognition result and the flow speed abnormality recognition result.
And taking the pressure supply abnormality identification result as first cooperative data, then carrying out cooperative abnormality identification on the flow velocity of the straight pipeline flow velocity characteristic according to the response parameter set, and marking the straight pipeline flow velocity characteristic as flow velocity abnormality when the straight pipeline flow velocity characteristic does not meet the flow velocity in the response parameter set, so as to obtain a flow velocity abnormality identification result. And then obtaining a fault collaborative recognition result according to the pressure supply abnormality recognition result and the flow speed abnormality recognition result.
In one embodiment, the method further comprises:
taking the abnormal flow rate identification result as second cooperative data, and carrying out result correction on the compensation result through the second cooperative data;
performing heat loss compensation on the heat exchange response of the response parameter set according to the correction result to generate heat loss compensation data;
performing heat exchange efficiency compensation on the heat exchange response of the response parameter set through the first cooperative data to generate efficiency conversion compensation data;
adjusting the heat exchange response through the heat loss compensation data and the efficiency conversion compensation data, and carrying out abnormal recognition on the heat exchange result characteristics according to the adjustment result to generate a heat exchange control abnormal recognition result;
And obtaining the fault collaborative recognition result according to the pressure supply abnormality recognition result, the flow speed abnormality recognition result and the heat exchange control abnormality recognition result.
And taking the abnormal flow rate identification result as second cooperative data, and carrying out result correction on the calibration heat loss data compensation result according to the second cooperative data, wherein the relationship between the calibration heat loss data and the flow rate is not considered when the calibration heat loss data is compensated according to the environmental characteristic factors, and the result correction is used for eliminating the influence of the abnormal flow rate identification result on the calibration heat loss data compensation result, for example: when the flow speed abnormality identification result is lower than the standard flow speed in the response parameter set, the consumed energy is higher and the calibrated heat loss data is increased when the flow speed is slower; and when the flow speed abnormality identification result is larger than the standard flow speed in the response parameter set, reducing the calibrated heat loss data. And obtaining a correction result of the calibration heat loss data compensation result. And then carrying out heat loss compensation on the heat exchange response of the response parameter set according to the correction result, namely adjusting the standard heat loss data of the heat exchange response according to the correction result to generate heat loss compensation data.
And performing heat exchange efficiency compensation on the heat exchange response of the response parameter set through the first cooperative data, wherein the heat exchange efficiency compensation refers to performing optimization adjustment on the heat exchange efficiency according to the pressure supply abnormality identification result, for example: when the pressure supply identification result is smaller than the supply pressure characteristic in the response parameter set or the fluctuation range of the pressure supply identification result is larger, the heat exchange efficiency needs to be properly reduced, and efficiency conversion compensation data is generated.
The heat exchange response is then adjusted based on the heat loss compensation data and the efficiency-conversion compensation data, for example: when the heat loss compensation becomes larger and the efficiency conversion becomes smaller, the heat exchange response needs to be properly reduced, and the heat exchange response after adjustment is completed is obtained. And according to the abnormal identification of the heat exchange result characteristic of the heat exchange response after the adjustment is completed, when the heat exchange result characteristic meets the heat exchange response of the heat exchange response after the adjustment is completed, the heat exchange result characteristic is marked abnormally, and a heat exchange control abnormal identification result is obtained.
And finally, constructing a fault collaborative recognition result according to the pressure supply abnormality recognition result, the flow speed abnormality recognition result and the heat exchange control abnormality recognition result, and obtaining the fault collaborative recognition result. By obtaining the fault collaborative recognition result, support is provided for the next step of accurate control of the equipment.
And carrying out response control on the equipment according to the fault collaborative identification result.
In one embodiment, the method further comprises:
collecting the fault co-identification results to construct a device fault feature set of the device;
constructing a sensitive correlation factor according to the equipment fault feature set;
and executing subsequent fault identification through the sensitive correlation factor.
Judging according to the fault collaborative recognition result, when one or more of the pressure supply abnormality recognition result, the flow speed abnormality recognition result and the heat exchange control abnormality recognition result in the fault collaborative recognition result have abnormality marks, indicating that the equipment has fault characteristics at the moment, generating an abnormal operation early warning signal, and performing response control on the equipment according to the abnormal operation early warning signal, for example: and stopping for maintenance, etc.
Recording a fault collaborative recognition result when the fault characteristics exist in the equipment, and extracting the equipment fault characteristics in the fault collaborative recognition result, for example: supply pressure instability, excessive heat loss, etc., to construct a set of plant fault characteristics. And then constructing a sensitive correlation factor according to the equipment fault feature set, wherein the sensitive correlation factor refers to key reasons causing equipment fault features, such as: when the device has unstable supply pressure, the input voltage is a sensitive correlation factor. And finally, executing subsequent fault identification according to the sensitive correlation factor, so that the efficiency of equipment fault identification can be improved.
The method solves the technical problem that the existing equipment fault sensing method has lower equipment fault sensing accuracy due to the interference of various factors, and can improve the accuracy of equipment fault sensing, thereby improving the accuracy of equipment control.
In one embodiment, as shown in FIG. 3, there is provided a fault-aware operation-and-maintenance system for a device, comprising:
the device feature set construction module is used for constructing a device feature set of the device, the device feature set is constructed according to basic data of the device, and the device feature set comprises device size features and device flow features;
the device working mode determining module is used for determining a device working mode of the device, wherein the device working mode is obtained by reading control parameters of the device after communication connection with the device is established;
the response parameter set construction module is used for constructing a response parameter set, the response parameter set is constructed through a response parameter database extracted by big data and a cleaning influence factor, and the response parameter data is obtained by taking the equipment working mode and the equipment characteristic set as basic data in a matching way;
The calibration heat loss data generation module is used for extracting the characteristics of a supply pipeline of the equipment according to the equipment characteristic set and generating calibration heat loss data according to the characteristics of the supply pipeline and the equipment working mode;
the device monitoring feature set construction module is used for constructing a device monitoring feature set, and the device monitoring feature set comprises a supply pressure feature, a straight pipeline flow speed feature and a heat exchange result feature;
the fault collaborative recognition module is used for collecting and generating an environmental characteristic factor, compensating the calibrated heat loss data through the environmental characteristic factor, and carrying out fault collaborative recognition on the equipment supervision characteristic set according to a compensation result and the response parameter set;
and the equipment response control module is used for carrying out response control on the equipment according to the fault collaborative identification result.
In one embodiment, the system further comprises:
the pressure supply abnormality identification result generation module is used for generating a pressure supply abnormality identification result, the pressure supply abnormality identification result is obtained by performing pressure identification on the supply pressure characteristic by the response parameter set, and the pressure supply abnormality identification result comprises a steady state value abnormality result and a stability abnormality result;
The flow speed abnormality identification result generation module is used for carrying out flow speed collaborative abnormality identification on the straight pipeline flow speed characteristics through the response parameter set by taking the pressure supply abnormality identification result as first collaborative data to generate a flow speed abnormality identification result;
the failure cooperative identification result obtaining module is used for obtaining the failure cooperative identification result according to the pressure supply abnormal identification result and the flow speed abnormal identification result.
In one embodiment, the system further comprises:
the compensation result correction module is used for taking the abnormal flow rate identification result as second cooperative data and carrying out result correction on the compensation result through the second cooperative data;
the heat loss compensation data generation module is used for performing heat loss compensation on the heat exchange response of the response parameter set according to the correction result to generate heat loss compensation data;
the heat exchange efficiency compensation module is used for carrying out heat exchange efficiency compensation on the heat exchange response of the response parameter set through the first cooperative data to generate efficiency conversion compensation data;
The heat exchange control abnormal recognition result generation module is used for adjusting the heat exchange response through the heat loss compensation data and the efficiency conversion compensation data, carrying out abnormal recognition of the heat exchange result characteristics according to the adjustment result and generating a heat exchange control abnormal recognition result;
the fault collaborative identification result obtaining module is used for obtaining the fault collaborative identification result according to the pressure supply abnormal identification result, the flow speed abnormal identification result and the heat exchange control abnormal identification result.
In one embodiment, the system further comprises:
the device ID calling module is used for calling the device ID according to the device feature set;
the same batch equipment backtracking execution module is used for executing the same batch equipment backtracking of the equipment by taking the equipment ID as a backtracking characteristic and obtaining a batch test data set of equipment backtracking, wherein the batch test data set is provided with a sample size identifier;
the same-type test data set calling module is used for calling the same-type test data set, wherein the same-type test data set is equipment test data of equipment with the same type as the equipment, and the calling quantity of the same-type test data set is determined through the sample quantity;
The trust adjustment module is used for configuring initial trust values of the equipment in the same batch and the equipment in the same model, and performing trust adjustment on the initial trust values according to the sample size proportion;
and the response parameter set construction module is used for extracting the test characteristics of the batch test data set and the homotype test data set according to the trust adjustment result so as to construct the response parameter set.
In one embodiment, the system further comprises:
the sample mean value standard line establishing module is used for establishing a sample mean value standard line according to the batch test data set;
the individual discrete evaluation module is used for carrying out individual discrete evaluation on the homotypic test data set and the batch test data set by taking the sample mean standard line as an evaluation reference;
and the sample elimination module is used for carrying out individual deviation calculation according to the individual discrete evaluation result and the trust adjustment result, and carrying out sample elimination according to the individual deviation calculation result so as to construct the response parameter set.
In one embodiment, the system further comprises:
The driving parameter set construction module is used for constructing a driving parameter set, and the driving parameter set is obtained by monitoring an input voltage signal of the equipment;
the supply pressure influence mapping module is used for carrying out supply pressure influence mapping on the driving parameter set by taking a standard voltage signal as a reference signal;
and the identification compensation module is used for executing the identification compensation of the pressure supply abnormality identification result according to the mapping result.
In one embodiment, the system further comprises:
the equipment fault feature set construction module is used for collecting the fault collaborative identification result to construct an equipment fault feature set of the equipment;
the sensitive association factor construction module is used for constructing sensitive association factors according to the equipment fault feature set;
and the subsequent fault identification module is used for executing subsequent fault identification through the sensitive correlation factor.
In summary, compared with the prior art, the embodiments of the present disclosure have the following technical effects:
(1) And performing fault sensing on the equipment according to the calibrated heat loss data and the response parameter set after compensation, so that the interference of various factors can be eliminated, the accuracy of equipment fault sensing is improved, and the accuracy of equipment control is improved.
(2) By inquiring and extracting test data of the same-batch and same-type equipment based on big data and screening the data reliability of the extracted test data and constructing a response parameter database according to the screened reliable data, the construction accuracy of the response parameter database can be improved, and the acquisition accuracy of a response parameter set can be improved.
(3) By obtaining the response parameter set, support is provided for the next step of equipment fault sensing, and the accuracy of obtaining the response parameter set can be improved, and meanwhile, the accuracy of equipment fault sensing can be improved due to the fact that the influence of the pipeline cleaning degree on the response parameter set is considered when the response parameter set is constructed.
The above examples merely represent a few embodiments of the present disclosure and are not to be construed as limiting the scope of the invention. Accordingly, various alterations, modifications and variations may be made by those having ordinary skill in the art without departing from the scope of the disclosed concept as defined by the following claims and all such alterations, modifications and variations are intended to be included within the scope of the present disclosure.
Claims (5)
1. A method of fault-aware operation and maintenance of a device, the method comprising:
constructing a device feature set of the device, wherein the device feature set is constructed according to basic data of the device and comprises device size features and device flow features;
determining an equipment working mode of the equipment, wherein the equipment working mode is obtained by reading control parameters of the equipment after communication connection with the equipment is established;
constructing a response parameter set, wherein the response parameter set is constructed through a response parameter database extracted by big data and a cleaning influence factor, the response parameter data is obtained by inputting the equipment working mode and the equipment characteristic set into the response parameter database for response parameter matching, and the response parameter set is adjusted according to the cleaning influence factor, and the cleaning influence factor is used for representing the influence degree of the cleaning state in the equipment pipeline on the response parameter;
extracting supply pipeline characteristics of the equipment according to the equipment characteristic set, and generating calibration heat loss data according to the supply pipeline characteristics and the equipment working mode;
constructing an equipment supervision feature set, wherein the equipment supervision feature set comprises a supply pressure feature, a straight pipeline flow velocity feature and a heat exchange result feature;
Collecting and generating an environmental characteristic factor, compensating the calibrated heat loss data through the environmental characteristic factor, and carrying out fault collaborative identification on the equipment supervision characteristic set according to a compensation result and the response parameter set;
performing response control on the equipment according to the fault collaborative recognition result;
wherein said constructing a set of response parameters comprises:
calling a device ID according to the device feature set;
taking the equipment ID as a backtracking feature, executing the backtracking of the equipment in the same batch of equipment, and obtaining a batch test data set of equipment backtracking, wherein the batch test data set is provided with a sample size identifier;
invoking a homotype test data set of the same type, wherein the homotype test data set is equipment test data of equipment of the same type as the equipment, and the invoking amount of the homotype test data set is determined by the sample amount;
configuring initial trust values of equipment in the same batch and equipment in the same model, and performing trust adjustment on the initial trust values according to the sample size proportion;
extracting test characteristics of the batch test data set and the homotype test data set according to trust adjustment results to construct the response parameter set;
The fault collaborative identification of the equipment supervision feature set according to the compensation result and the response parameter set comprises the following steps:
generating a pressure supply abnormality identification result, wherein the pressure supply abnormality identification result is obtained by performing pressure identification on the supply pressure characteristics by the response parameter set, and the pressure supply abnormality identification result comprises a steady state value abnormality result and a stability abnormality result;
taking the pressure supply abnormality identification result as first cooperative data, and performing cooperative abnormality identification of the flow rate on the straight pipeline flow rate characteristics through the response parameter set to generate a flow rate abnormality identification result;
obtaining the fault collaborative recognition result according to the pressure supply abnormality recognition result and the flow speed abnormality recognition result;
taking the abnormal flow rate identification result as second cooperative data, and carrying out result correction on the compensation result through the second cooperative data;
performing heat loss compensation on the heat exchange response of the response parameter set according to the correction result to generate heat loss compensation data;
performing heat exchange efficiency compensation on the heat exchange response of the response parameter set through the first cooperative data to generate efficiency conversion compensation data;
Adjusting the heat exchange response through the heat loss compensation data and the efficiency conversion compensation data, and carrying out abnormal recognition on the heat exchange result characteristics according to the adjustment result to generate a heat exchange control abnormal recognition result;
and obtaining the fault collaborative recognition result according to the pressure supply abnormality recognition result, the flow speed abnormality recognition result and the heat exchange control abnormality recognition result.
2. The method of claim 1, wherein the method further comprises:
establishing a sample mean standard line according to the batch test data set;
taking the sample mean standard line as an evaluation reference, and performing individual discrete evaluation on the homotypic test data set and the batch test data set;
and carrying out individual deviation calculation according to the individual discrete evaluation result and the trust adjustment result, and carrying out sample elimination according to the individual deviation calculation result so as to construct the response parameter set.
3. The method of claim 1, wherein the method further comprises:
constructing a driving parameter set, wherein the driving parameter set is obtained by monitoring an input voltage signal of the equipment;
using a standard voltage signal as a reference signal to map the supply pressure influence of the driving parameter set;
And performing recognition compensation of the pressure supply abnormality recognition result according to the mapping result.
4. The method of claim 1, wherein the method further comprises:
collecting the fault co-identification results to construct a device fault feature set of the device;
constructing a sensitive correlation factor according to the equipment fault feature set;
and executing subsequent fault identification through the sensitive correlation factor.
5. A fault-aware operation and maintenance system for a device, characterized by the steps for performing any one of the fault-aware operation and maintenance methods of a device as claimed in claims 1-4, said system comprising:
the device feature set construction module is used for constructing a device feature set of the device, the device feature set is constructed according to basic data of the device, and the device feature set comprises device size features and device flow features;
the device working mode determining module is used for determining a device working mode of the device, wherein the device working mode is obtained by reading control parameters of the device after communication connection with the device is established;
the response parameter set construction module is used for constructing a response parameter set, the response parameter set is constructed through a response parameter database extracted by big data and a cleaning influence factor, the response parameter data is obtained by inputting the equipment working mode and the equipment characteristic set into the response parameter database for response parameter matching, the response parameter set is adjusted according to the cleaning influence factor, and the cleaning influence factor is used for representing the influence degree of the cleaning state in the equipment pipeline on the response parameter;
The calibration heat loss data generation module is used for extracting the characteristics of a supply pipeline of the equipment according to the equipment characteristic set and generating calibration heat loss data according to the characteristics of the supply pipeline and the equipment working mode;
the device monitoring feature set construction module is used for constructing a device monitoring feature set, and the device monitoring feature set comprises a supply pressure feature, a straight pipeline flow speed feature and a heat exchange result feature;
the fault collaborative recognition module is used for collecting and generating an environmental characteristic factor, compensating the calibrated heat loss data through the environmental characteristic factor, and carrying out fault collaborative recognition on the equipment supervision characteristic set according to a compensation result and the response parameter set;
and the equipment response control module is used for carrying out response control on the equipment according to the fault collaborative identification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311490007.1A CN117234166B (en) | 2023-11-10 | 2023-11-10 | Fault perception operation and maintenance method and system for equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311490007.1A CN117234166B (en) | 2023-11-10 | 2023-11-10 | Fault perception operation and maintenance method and system for equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117234166A CN117234166A (en) | 2023-12-15 |
| CN117234166B true CN117234166B (en) | 2024-03-08 |
Family
ID=89098456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311490007.1A Active CN117234166B (en) | 2023-11-10 | 2023-11-10 | Fault perception operation and maintenance method and system for equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117234166B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201116914D0 (en) * | 2011-09-30 | 2011-11-16 | Thermal Integration Ltd | Water heating system |
| JP5839528B1 (en) * | 2015-04-27 | 2016-01-06 | 俊一 田原 | Temperature drop compensation type geothermal exchanger and temperature drop compensation type geothermal power generator |
| CN208536132U (en) * | 2018-05-18 | 2019-02-22 | 南京优能空调系统有限公司 | A kind of dual temperature state unit heat exchange station |
| CN112985790A (en) * | 2021-02-07 | 2021-06-18 | 中国石油大学(北京) | Heat exchanger operation monitoring and fault diagnosis method and system |
| CN114935374A (en) * | 2022-07-26 | 2022-08-23 | 克拉玛依市富城天然气有限责任公司 | Control method and system for oil well natural gas flow metering process |
| CN115771497A (en) * | 2022-11-30 | 2023-03-10 | 华南理工大学 | Brake heat fading compensation control method based on brake pressure control |
| CN116804406A (en) * | 2023-06-16 | 2023-09-26 | 无锡俐莱科技有限公司 | Micro compressor abnormality detection system for new energy automobile |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012532306A (en) * | 2009-07-07 | 2012-12-13 | アー − ヒート アライド ヒート イクスチェンジ テクノロジー アクチェンゲゼルシャフト | Heat exchange system and method of operating a heat exchange system |
| JP6064613B2 (en) * | 2013-01-18 | 2017-01-25 | 株式会社ノーリツ | Water heater |
| US10760996B2 (en) * | 2017-07-11 | 2020-09-01 | Caterpillar Inc. | Machine commissioning system and method |
| US11358437B2 (en) * | 2019-10-04 | 2022-06-14 | Ford Global Technologies, Llc | Heat pump system and method for operating said system |
-
2023
- 2023-11-10 CN CN202311490007.1A patent/CN117234166B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201116914D0 (en) * | 2011-09-30 | 2011-11-16 | Thermal Integration Ltd | Water heating system |
| JP5839528B1 (en) * | 2015-04-27 | 2016-01-06 | 俊一 田原 | Temperature drop compensation type geothermal exchanger and temperature drop compensation type geothermal power generator |
| CN208536132U (en) * | 2018-05-18 | 2019-02-22 | 南京优能空调系统有限公司 | A kind of dual temperature state unit heat exchange station |
| CN112985790A (en) * | 2021-02-07 | 2021-06-18 | 中国石油大学(北京) | Heat exchanger operation monitoring and fault diagnosis method and system |
| CN114935374A (en) * | 2022-07-26 | 2022-08-23 | 克拉玛依市富城天然气有限责任公司 | Control method and system for oil well natural gas flow metering process |
| CN115771497A (en) * | 2022-11-30 | 2023-03-10 | 华南理工大学 | Brake heat fading compensation control method based on brake pressure control |
| CN116804406A (en) * | 2023-06-16 | 2023-09-26 | 无锡俐莱科技有限公司 | Micro compressor abnormality detection system for new energy automobile |
Non-Patent Citations (2)
| Title |
|---|
| Active fault diagnosis for hybrid systems based on sensitivity analysis and EKF;Mehdi Gholami等;《2011 American Control Conference》;全文 * |
| 不同条件下环路热管蒸发器补偿器传热传质特性实验研究;刘超;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117234166A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8452441B2 (en) | Process quality predicting system and method thereof | |
| CN108981796B (en) | Five-in-one hydraulic mechanical fault diagnosis method | |
| CN111352408B (en) | Multi-working-condition process industrial process fault detection method based on evidence K nearest neighbor | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| TW200307972A (en) | Correlation of end-of-line data mining with process tool data mining | |
| CN103103570B (en) | Based on the aluminium cell condition diagnostic method of pivot similarity measure | |
| WO2020181759A1 (en) | Intelligent prediction system for predicting device failure and potential defective product on miniature transformer production line | |
| CN113219910A (en) | Full-flow production self-diagnosis and optimization system | |
| CN107679715A (en) | A kind of electric energy meter comprehensive error process merit rating method and evaluation system based on SPC | |
| CN109409425A (en) | A kind of fault type recognition method based on neighbour's constituent analysis | |
| CN110986407A (en) | Fault diagnosis method for centrifugal water chilling unit | |
| CN103105849A (en) | Industrial regulating valve non-linear operating characteristic diagnosis method | |
| CN114935374A (en) | Control method and system for oil well natural gas flow metering process | |
| CN117234166B (en) | Fault perception operation and maintenance method and system for equipment | |
| CN111338310B (en) | Industrial process steady-state working condition identification and classification method | |
| CN117270514A (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
| CN102289718A (en) | Method for softly measuring height of mud layer in settlement process of red mud | |
| CN105278333B (en) | The Data Modeling Method and system of extra-supercritical unit coordinated control system | |
| CN109213057A (en) | Intelligent diagnostics device and method | |
| CN105699043B (en) | A kind of wind tunnel sensors that improve measure stability and the method for precision | |
| CN115186754A (en) | Unit energy efficiency monitoring and diagnosing method based on information entropy and auto-associative regression model | |
| CN114608741A (en) | Pressure sensor acquisition system based on big data | |
| CN115879355A (en) | Temperature compensation method of piezoelectric sensor | |
| CN114722888A (en) | Early fault detection method based on Wasserstein distance | |
| CN113467434B (en) | CCA fermentation process KPI related fault monitoring method based on double-layer k nearest neighbor standardization |
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 |