CN116519054A - Health state monitoring system and method for heat station equipment - Google Patents
Health state monitoring system and method for heat station equipment Download PDFInfo
- Publication number
- CN116519054A CN116519054A CN202310460219.9A CN202310460219A CN116519054A CN 116519054 A CN116519054 A CN 116519054A CN 202310460219 A CN202310460219 A CN 202310460219A CN 116519054 A CN116519054 A CN 116519054A
- Authority
- CN
- China
- Prior art keywords
- early warning
- parameters
- sensor
- motor
- early
- 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.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 47
- 238000010801 machine learning Methods 0.000 claims description 35
- 238000010438 heat treatment Methods 0.000 claims description 21
- 230000001502 supplementing effect Effects 0.000 claims description 11
- 230000000903 blocking effect Effects 0.000 claims description 10
- 230000003862 health status Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 150000001875 compounds Chemical class 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 abstract description 36
- 230000002159 abnormal effect Effects 0.000 abstract description 11
- 238000007689 inspection Methods 0.000 abstract description 9
- 230000008569 process Effects 0.000 abstract description 5
- 238000003745 diagnosis Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000004927 fusion Effects 0.000 abstract description 3
- 238000005299 abrasion Methods 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 4
- 239000007788 liquid Substances 0.000 description 4
- 208000024891 symptom Diseases 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000004880 explosion Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005202 decontamination Methods 0.000 description 2
- 230000003588 decontaminative effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000035784 germination Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
Abstract
The invention discloses a health state monitoring system and method of heat station equipment, which adopts a multi-sensor information fusion technology, brings the problems of blockage of a plate heat exchanger, abrasion of a motor bearing, burst of a pipeline and the like into a real-time state supervision system, establishes a temperature, vibration fault diagnosis expert analysis and a temperature field analysis model in a mode of adding vibration and a temperature sensor, combines real-time data such as pressure flow and the like of the original PLC to form a comprehensive equipment fault early warning system, judges abnormal conditions of equipment in real time, collects, processes and analyzes fault information, and provides important inspection basis for on-site inspection. Through the collection of equipment state data, the intelligent analysis is calculated in combination with the edge, the current operation health state of the equipment is effectively evaluated, early warning information is timely provided, equipment fault early warning grades are sent out in advance, and the equipment reliability is guaranteed for the quick inspection of maintenance personnel.
Description
Technical Field
The invention relates to the technical field of heat station equipment, in particular to a heat station equipment health state monitoring system and method.
Background
The heating station is a transfer station for connecting a heating network with a user, and the heat medium conveyed by the heating network is changed into distributable heat energy after being directionally regulated, so that the requirement of domestic heating is met. The standard heating station equipment is provided with a heat exchanger, a circulating pump, a secondary net dirt remover, a water supplementing pump, a water supplementing tank, a metering instrument, a control valve and the like. The number of the devices and the size of the devices are different according to the scale of the heating power station. The distribution of the heat stations is randomly set up according to urban planning, the points are multiple and dispersed, and a plurality of heat stations are governed by a common medium and small urban heat supply network management company, so that the equipment is huge in maintenance quantity, and great pressure is brought to overhaul and maintenance work.
At present, maintenance work is carried out according to a planned maintenance mode and a sudden fault maintenance mode, wherein the planned maintenance mode is to carry out inspection maintenance on all heating power equipment in a heat supply stopping stage and maintain fault points, the mode is time-consuming and labor-consuming, and hidden fault points cannot be effectively cleared; the emergency fault maintenance is to maintain the heating equipment after emergency faults occur during the heating period, the heating of the area can be influenced in the maintenance stage, and maintenance staff are busy in handling the emergency faults of the equipment every day, so that the workload of workers is greatly increased.
The existing heat station equipment management mode method is based on a PLC logic control method to realize closed-loop operation of heat exchange station equipment, the control mode belongs to operation automation, only has simple fault alarm and overload protection functions aiming at equipment faults, can not effectively early warn the equipment faults, and can ensure normal operation of the equipment only by matching with manual inspection.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a health state monitoring system and a health state monitoring method for a heating power station device, which can effectively detect the operation state of the heating power device, output early warning signals of the heating power device according to the operation state, discharge faults as early as possible, lighten maintenance pressure and reduce the operation cost of the heating power device,
the invention is realized by the following technical scheme:
a health state monitoring system of heat station equipment comprises a heat exchanger blockage early warning unit, a pipeline explosion-leakage early warning unit, a motor early warning unit and a control unit;
the heat exchanger blockage early warning unit is used for acquiring pressure, temperature and flow parameters of a heat exchanger medium in the thermodynamic system and sending the acquired pressure, temperature and flow to the machine head for display;
the pipeline explosion-leakage early warning unit is used for acquiring pressure and flow parameters of each water supply pipeline in the thermodynamic system and sending the acquired pressure and flow parameters to the machine head for display;
the motor early warning unit is used for acquiring vibration parameters, temperature parameters, voltage and current parameters of each motor in the thermodynamic system by a user and sending the acquired vibration parameters, temperature parameters, voltage and current parameters to the machine head for display;
the control unit is used for analyzing the received parameters and outputting early warning signals.
Preferably, the heat exchanger blockage early warning unit comprises pressure sensors, temperature sensors and flow sensors which are arranged on pipelines of a water inlet and a water outlet of the heat exchanger.
Preferably, the motor early warning unit comprises a vibration sensor, a temperature sensor and a current-voltage sensor which are arranged on the circulating pump and the water supplementing pump.
Preferably, the pipeline explosion-leakage early warning unit comprises a flow sensor and a pressure sensor; the medium flow pipeline of the thermodynamic system is provided with a flow sensor and a pressure sensor at intervals.
Preferably, the control unit comprises a data acquisition module, an early warning analysis module and a display module, wherein the data acquisition module is connected with each sensor in a wireless mode, and the acquisition module and the display module are connected with the early warning analysis module.
An early warning method of a health state monitoring system of heat station equipment, wherein the early warning method of a heat exchanger blockage early warning unit comprises the following steps:
the method comprises the steps of obtaining pressure, flow and temperature parameters of a water inlet and a water outlet of water supply and return of the heat exchanger, inputting the obtained parameters as sample data into a constructed blocking machine learning model, training the blocking machine learning model, obtaining a normal running state and an alarm threshold value of the current heat exchanger by the trained blocking machine learning model, and outputting an early warning signal when the running parameters of the heat exchanger do not accord with the normal running state.
Preferably, the motor early warning unit early warning method comprises the following steps:
obtaining a vibration parameter jump curve, a temperature jump curve, a three-phase voltage balance curve and a current load curve of a vibration sensor, a temperature sensor and a voltage and current sensor in a normal state in a historical time period, inputting the vibration parameter jump curve, the temperature jump curve, the three-phase voltage balance curve and the current load curve as sample data into a constructed motor early-warning machine learning model, training the motor early-warning machine learning model, and obtaining operation parameters of the normal state of the motor by the trained motor early-warning machine learning model;
and inputting the real-time operation parameters of the motor into a trained motor early warning machine learning model, judging the real-time operation state of the motor, and outputting an early warning signal according to a judging result.
Preferably, the early warning method of the pipeline explosion leakage early warning unit comprises the following steps:
obtaining the K values of all the sensors, inputting the K values of all the sensors as sample data into a constructed pipeline early-warning machine learning model, training the pipeline early-warning machine learning model, and carrying out compound operation on the K values of all the sensors by the trained pipeline early-warning machine learning model to obtain the standard health state L of all the heating power pipelines;
the real-time K values of the sensors are input into a trained pipeline early warning machine learning model, the real-time health state L1 of the current pipeline is output, the standard health state L is compared with the real-time health state L1, and an early warning signal is output.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention provides a health state monitoring system of heat station equipment, which adopts a multi-sensor information fusion technology, brings the problems of blockage of a plate heat exchanger, abrasion of a motor bearing, burst of a pipeline and the like into a real-time state supervision system, establishes a temperature, vibration fault diagnosis expert analysis and a temperature field analysis model by adding vibration and temperature sensors, combines real-time data such as pressure flow and the like of the original PLC to form a comprehensive equipment fault early warning system, judges abnormal conditions of equipment in real time, collects, processes and analyzes fault information, and provides important inspection basis for on-site inspection. Through the collection of equipment state data, the intelligent analysis is calculated in combination with the edge, the current operation health state of the equipment is effectively evaluated, early warning information is timely provided, equipment fault early warning grades are sent out in advance, and the equipment reliability is guaranteed for the quick inspection of maintenance personnel.
Drawings
FIG. 1 is a block diagram of a system for monitoring the health status of a heat station device according to the present invention;
fig. 2 is a block diagram of a system for monitoring the health status of a heat station device according to the present invention.
Detailed Description
The invention will now be described in further detail with reference to the accompanying drawings, which illustrate but do not limit the invention.
A health state monitoring system of heat station equipment comprises a heat exchanger blockage early warning unit, a pipeline explosion-leakage early warning unit, a motor early warning unit and a control unit;
the heat exchanger blockage early warning unit is used for acquiring pressure, temperature and flow parameters of a heat exchanger medium in the thermodynamic system and sending the acquired pressure, temperature and flow to the machine head for display.
The pipeline explosion-leakage early warning unit is used for acquiring pressure and flow parameters of each water supply pipeline in the thermodynamic system and sending the acquired pressure and flow parameters to the machine head for display.
And the motor early warning unit is used for acquiring vibration parameters, temperature parameters, voltage and current parameters of each motor in the thermodynamic system by a user and sending the acquired vibration parameters, temperature parameters, voltage and current parameters to the machine head for display.
And the control unit is used for analyzing the received parameters and outputting early warning signals.
The heat exchanger blockage early warning unit comprises a pressure sensor, a temperature sensor and a flow sensor, wherein the pressure sensor, the temperature sensor and the flow sensor are arranged on pipelines of a water inlet and a water outlet of the heat exchanger, and further the pressure, the flow and the temperature of the water inlet and the water outlet of the heat exchanger are obtained.
The method comprises the steps of acquiring pressure, flow and temperature parameters of a water inlet and a water outlet of water supply and return of the heat exchanger through a sensor, inputting the acquired parameters as sample data into a constructed blocking machine learning model, training the blocking machine learning model, analyzing working condition parameters of the heat exchanger in a historical time period and corresponding to the current time, obtaining the normal running state of the current heat exchanger by the blocking machine learning model, obtaining an accurate alarm threshold value in the current time period, and finally obtaining a reasonable and effective working condition interval of the heat exchanger. The fault monitoring of the plate heat exchangers of different brands is met through self-learning setting parameters of a single device, the alarm threshold value can be adjusted at any time according to the process requirements, and the fixed-point accurate monitoring of the heat exchanger is truly realized.
The blocking machine learning model is a deep learning network model or a convolutional neural network model.
The motor early warning unit comprises a vibration sensor, a temperature sensor and a current and voltage sensor, wherein the vibration sensor is used for acquiring acceleration and displacement data of the motor, the temperature sensor is used for measuring the shaft end temperature of the motor, and the current and voltage sensor is used for measuring the current and voltage values of the motor.
And a vibration sensor, a temperature sensor, a voltage and current sensor are arranged on the motor and are used for acquiring triaxial acceleration, speed, displacement, front and rear axle temperatures, three-phase voltage and current data of the motor. And inputting the acquired parameters as sample data into a constructed motor early-warning machine learning model, training the motor early-warning machine learning model, obtaining the operating parameters of the motor in a normal state by the trained motor early-warning machine learning model, calibrating alarm thresholds according to a plurality of parameter levels, and finally realizing a motor health state assessment system.
And inputting the real-time operation parameters of the motor into a trained motor early warning machine learning model, judging the real-time operation state of the motor, and outputting an early warning signal according to a judging result. Intelligent analysis among vibration, temperature rise and three-phase balance is realized through data modeling, abnormal states of the motor are output,
according to rated parameters of a motor nameplate, abnormal states of the motor can be analyzed, overhaul and maintenance can be reminded when early symptoms are caused, alarm thresholds are calibrated according to multiple parameter levels, and early detection and early prevention of equipment faults are achieved. The accident hidden trouble is killed in the cradle stage, and the device has predictive analysis and alarm means, so that the effective supervision force of the device is improved, and the accident non-stop and fault expansion and other afterfactors are reduced.
According to the motor early-warning machine learning model, a fault early-warning system of the motor is established, each motor in the thermodynamic system is numbered and input into the fault early-warning system, and when the motor output by any model is in an abnormal state, the fault early-warning system outputs an early-warning model to instruct maintenance personnel to overhaul and maintain the numbered motor. The fault early warning system of the motor judges the abnormal condition of the equipment in real time and provides important checking basis for spot inspection. And the current running health state of the equipment is effectively evaluated, early warning information is timely provided, the equipment fault early warning level is sent out in advance, and a data foundation is laid for state maintenance.
The pipeline explosion-leakage early warning unit comprises a flow sensor and a pressure sensor, wherein the flow sensor and the pressure sensor are arranged on a medium flow pipeline of the thermodynamic system at a certain distance, the flow sensor and the pressure sensor send measured parameters to the control unit in real time, the control unit analyzes the flow and pressure parameters and outputs early warning signals of the thermodynamic system, and the analysis process is as follows:
and carrying out statistical calculation on data in each sensor history time period to obtain the K value of each sensor, and calculating a plurality of K values, namely K1, K2, K3. and Kn by a plurality of sensors. The method comprises the steps that K values of all sensors are obtained and are used as sample data to be input into a constructed pipeline early-warning machine learning model, the pipeline early-warning machine learning model is trained, and the trained pipeline early-warning machine learning model carries out compound operation on the K values of all the sensors to obtain a standard health state L of each heating power pipeline; the real-time K values of the sensors are input into a trained pipeline early warning machine learning model, the real-time health state L1 of the current pipeline is output, the standard health state L is compared with the real-time health state L1, and an early warning signal is output. And (3) carrying out compound operation on the K values of all the sensors to obtain the health state L of each heating power pipeline, wherein the K value of a single sensor can also carry out the health state of the single sensor, so that closed loop detection is realized. For example, the current pipeline can be judged to be blocked, unsmooth or have leakage points through K values of the temperature, the pressure and the flow of the inlet and the outlet.
The temperature sensor mainly collects temperature information of two ends of a water inlet and a water outlet of the plate heat exchanger, the shaft ends of the water pump and the surface of the pipeline, and the temperature sensor collects temperature by adopting mature PT100, and the temperature collection range is-5-200 ℃. The temperature sensor converts the temperature data into a digital signal and uploads the digital signal to the control unit in a wired or wireless mode. The vibration sensor mainly collects triaxial acceleration and displacement data of the motor and the water pump X, Y, Z. The vibration sensor converts acceleration and displacement data into digital signals, and the digital signals are uploaded to the control unit in a wired or wireless mode.
The temperature sensor and the vibration sensor are powered by batteries, data are operated in a wireless transmission mode, and all measuring chips use digital chips, so that analog data jump caused by air temperature, humidity and radiation is reduced to the greatest extent. The temperature acquisition used in this embodiment is constant current source drive. Vibration uses RMS algorithm effective values, the algorithm structure is as follows:
the voltage and current sensor adopts an intelligent ammeter to measure the electricity consumption parameters of the motor and comprises A, B, C three-phase voltage and current data, and the intelligent ammeter converts voltage and current signals into digital signals and uploads the digital signals to the control unit in a wired and wireless or wireless mode.
The pressure, flow, liquid level and the like of the heating power pipeline are provided with corresponding sensors, and the brand and the model of the sensors are selected according to the design requirements of the heating power station, so that the types are numerous. The signals of pressure, flow, liquid level and the like are all connected into the original control loop in series by adopting a 4-20 mA data acquisition module, and the original measurement mode is not changed. The 4-20 mA data acquisition module converts the information into a digital signal and uploads the digital signal to the control unit in a wired or wireless mode.
The control unit comprises a data acquisition module, an early warning analysis module and a display module, wherein the data acquisition module is connected with each sensor in a wireless mode, the wireless mode is accessed by adopting low-power wireless protocols such as ZigBee, loRa and the like, the wired mode is accessed by adopting RS485, RJ45 and CAN bus protocols, the protocols all belong to mature and stable communication protocols, the acquisition module and the display module are connected with the early warning analysis module, and the display module is used for displaying temperature, vibration, current voltage, flow and liquid level data of each thermal device.
All communications including wireless message reporting uses, but is not limited to, CRC redundancy check for data checking, with a CRC check prototype of x++16x12x51 (0 x 1021).
Example 1
The heat station equipment health state monitoring system provided by the invention is described below by taking a heat exchange system as an example.
Referring to fig. 2, FT represents a flow sensor, PT represents a pressure sensor, TE represents a temperature sensor, 3V represents a 3-phase voltmeter, 3I represents a 3-phase ammeter, and VS represents a vibration sensor.
The inlet of the rotary decontamination pump of the primary water supply pipeline is provided with a first flow sensor, a pipeline between the inlet of the rotary decontamination pump and the hot side inlet of the plate heat exchanger is provided with a first pressure sensor and a first temperature sensor, the pipeline of the hot side inlet of the plate heat exchanger is provided with a second pressure sensor and a second temperature sensor, and the joint of the primary water supply pipeline and the secondary water supply pipeline is provided with a second flow sensor.
The primary water return pipeline of the cold side outlet of the plate heat exchanger is provided with a third pressure sensor, a third temperature sensor and a third flow sensor, and the cold side inlet of the plate heat exchanger is provided with a fourth pressure sensor and a fourth temperature sensor.
The cold side inlet of the plate heat exchanger is connected with a first circulating pump and a second circulating pump which are connected in parallel through pipelines, a three-phase ammeter, a three-phase voltmeter, a temperature sensor and a vibration sensor are respectively arranged on the first circulating pump and the second circulating pump, and a pressure sensor is arranged at the outlet of the circulating pump. The inlets of the first circulating pump and the second circulating pump are respectively connected with the first water supplementing pump, the second water supplementing pump and the dirt remover, the dirt remover is connected with the secondary water return pipeline, and the inlets of the first water supplementing pump and the second water supplementing pump are connected with the water supplementing tank through the water outlet pipeline. The secondary return water pipeline is provided with a flow sensor, the water supplementing pump is provided with a three-phase ammeter, a three-phase voltmeter, a temperature sensor and a vibration sensor, and the outlet of the water supplementing pump is provided with a pressure sensor.
Pressure and temperature sensors are added on two sides of the plate heat exchanger, pressure and temperature data on two sides are collected for a long time, so that a historical normal ratio floating range is derived, and a central value is taken to set the ratio as a reference value. The damage ratio is set by manually calibrating the damaged plate heat exchanger data. And acquiring detailed normal operation interval and abnormal damage interval values by collecting temperature and pressure data of a plurality of brands and different power plate heat exchangers. Through the temperature and pressure data after the calibration, unmanned supervision can be realized for the plate heat exchanger, and multi-stage alarming is performed according to the operation parameter time, such as prompting cleaning, acid adding, fastening, replacement and the like. Realize unmanned automatic control and health status evaluation of plate heat exchanger.
By additionally arranging the motor vibration sensor and the temperature sensor, the voltage and current sensor synchronously compares the data jump curve, the three-phase balance curve and the load curve. The intelligent analysis between vibration, temperature rise and three-phase balance is realized through data modeling, the abnormal state of the motor can be analyzed according to rated parameters of a motor nameplate, the maintenance can be reminded when early symptoms are caused, the alarm threshold is calibrated aiming at a plurality of parameter levels, the early detection and early prevention of equipment faults are realized. The accident hidden trouble is killed in the cradle stage, and the device has predictive analysis and alarm means, so that the effective supervision force of the device is improved, and the accident non-stop and fault expansion and other afterfactors are reduced.
The flow sensor and the pressure sensor are additionally arranged for primary water supply, primary water return, secondary water supply and secondary water return. Can monitor and discover the abnormal conditions such as leakage, pipe explosion and the like in advance and solve the abnormal conditions in advance. By adding a plurality of flow and pressure sensors along the pipeline, the approximate region positions of leakage and pipe explosion can be positioned, and reliable data support is provided for advanced accident handling and hidden danger elimination.
Each sensor is connected with a data acquisition module of the control unit through wireless communication, health state monitoring systems of a plurality of thermodynamic systems can be connected through a background monitoring center, the control units of the thermodynamic stations synchronously upload data to the background monitoring center through optical fibers, 4G, 5G, NB-IoT and other protocols, all thermodynamic station equipment in an area is monitored and early warned through the background monitoring center, and each scattered thermodynamic station is connected to a network in an Internet of things mode to realize synchronous management.
The monitoring center continuously collects the real-time parameters through the database, and stores the parameters according to the process requirements in different categories to establish a large data center database. And establishing a digital model according to the technological parameter requirements, and importing relevant data, time and other parameters according to the functionality. And synchronously realizing data dependency relationship and processing method, and evaluating the basis of alarm threshold calibration and the like aiming at normal data value and abnormal data value of equipment. And (5) equipment fault diagnosis and equipment hidden danger early warning are realized according to a threshold method and an analysis method. The early fault symptoms are reflected to a human-computer interaction interface, and the equipment health state evaluation is provided through the data indexes, so that unmanned equipment supervision is achieved, the degree of transition from a planned maintenance method to preventive state maintenance is changed, and the workload of operation and maintenance staff is greatly reduced. The remedial measures in the prior art are evolved to the extent of prevention in advance and extinction in the germination period. Through the system, equipment fault visualization and foreseeability are realized, so that operation and maintenance personnel can comprehensively grasp the health state of the equipment and the future overhaul and maintenance time node.
Compared with the prior art, the system has the following beneficial effects:
1. the system adopts a multi-sensor information fusion technology, has the functions of real-time data monitoring and acquisition and data transmission, and is compatible with sensors required by monitoring states of all devices by arranging a set of health state monitoring system of the heat station device on each heat station. The sensor may upload data in a wired or wireless manner. Distributed management and rapid deployment and installation can be realized.
2. The system is independent of the existing control system, and the system installation and deployment does not change the integrity and normal running state of the original equipment and control mode. The method can make up the supervision blind area in the original control system, and has a supplementary and deep supervision level for the fine management of the equipment.
3. The fault early warning judgment can be conveniently carried out, and the post-event diagnosis is changed into the pre-event analysis. The early symptoms of the equipment abnormality are conveniently captured, the range is locked, the prior analysis is carried out, the equipment reliability is improved, the hidden trouble of the equipment, emergency repair and non-stop are reduced, and the stop time is reduced;
4. the health state monitoring system of the heat station equipment has strong compatibility and expansibility. Meanwhile, the supervision of conventional heat station equipment such as plate heat exchangers, motor water pumps, pipelines and the like with different brands and different models is met. Therefore, the system can be compatible with almost all heat station equipment, has the functions of subsequent capacity expansion, expansion and upgrading, has comprehensive consideration on quick deployment of the existing heat station, compatible upgrading of a newly built heat station in the future and the like, is a set of upgradeable state maintenance system which truly solves the current actual pain point problem, meets the sustainable development in the future, and provides decision-making basis for the rise of the supervision level of the heat station equipment.
The equipment health maintenance system comprises measuring methods of temperature, vibration, voltage and current, pressure and flow, liquid level and the like. Modeling by background data, pouring data dependency relationship, and realizing functions of fault monitoring, fault germination period early warning, equipment monitoring state evaluation, maintenance period suggestion and the like by big data analysis. The transition from the scheduled maintenance mode to the state maintenance mode is realized. The equipment health state maintenance system is positioned in the comprehensive management of the heat station equipment: the method aims to improve the supervision capability and the fault early warning level of equipment, enable faults to be found in the sprouting period, eliminate the faults as early as possible, prevent the faults in advance instead of post-repair measures, reduce maintenance pressure, reduce operation cost and monitor the health state of the heat station equipment in real time and comprehensively.
The equipment health state maintenance system changes a planned maintenance mode and a post-emergency maintenance mode into a state maintenance mode, and selects maintenance, lubrication or fastening screws and the like according to the actual health state of the equipment. The supervision degree and supervision level of the background on equipment are greatly improved, the manpower and material resource expenditure of maintenance personnel is reduced, the probability of sudden faults is reduced, and a series of peripheral influences caused by the sudden faults are reduced; the invention utilizes the thinking of the Internet of things to divide a whole set of system into software and hardware according to functions, and is compatible with different heating stations by building blocks. Meanwhile, the practical objective conditions such as future expansion and capacity expansion are considered, and the system is a precisely positioned and practical maintenance system for the thermal station.
The above is only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited by this, and any modification made on the basis of the technical scheme according to the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (8)
1. The health state monitoring system of the heat station equipment is characterized by comprising a heat exchanger blockage early warning unit, a pipeline explosion-leakage early warning unit, a motor early warning unit and a control unit;
the heat exchanger blockage early warning unit is used for acquiring pressure, temperature and flow parameters of a heat exchanger medium in the thermodynamic system and sending the acquired pressure, temperature and flow to the machine head for display;
the pipeline explosion-leakage early warning unit is used for acquiring pressure and flow parameters of each water supply pipeline in the thermodynamic system and sending the acquired pressure and flow parameters to the machine head for display;
the motor early warning unit is used for acquiring vibration parameters, temperature parameters, voltage and current parameters of each motor in the thermodynamic system by a user and sending the acquired vibration parameters, temperature parameters, voltage and current parameters to the machine head for display;
the control unit is used for analyzing the received parameters and outputting early warning signals.
2. The system for monitoring the health state of heat station equipment according to claim 1, wherein the heat exchanger blockage pre-warning unit comprises pressure sensors, temperature sensors and flow sensors which are arranged on pipelines of a water inlet and a water outlet of the heat exchanger.
3. A system for monitoring the health status of a heat station device according to claim 1, wherein the motor pre-warning unit comprises a vibration sensor, a temperature sensor and a current-voltage sensor arranged on a circulating pump and a water supplementing pump.
4. The system for monitoring the health state of heat station equipment according to claim 1, wherein the pipeline explosion-leakage early warning unit comprises a flow sensor and a pressure sensor; the medium flow pipeline of the thermodynamic system is provided with a flow sensor and a pressure sensor at intervals.
5. The system for monitoring the health status of a heat station device according to claim 1, wherein the control unit comprises a data acquisition module, an early warning analysis module and a display module, the data acquisition module is connected with each sensor in a wireless mode, and the acquisition module and the display module are connected with the early warning analysis module.
6. A method for pre-warning a health status monitoring system of a heat station device according to any one of claims 1-5, wherein the pre-warning method for a heat exchanger blockage pre-warning unit comprises the following steps:
the method comprises the steps of obtaining pressure, flow and temperature parameters of a water inlet and a water outlet of water supply and return of the heat exchanger, inputting the obtained parameters as sample data into a constructed blocking machine learning model, training the blocking machine learning model, obtaining a normal running state and an alarm threshold value of the current heat exchanger by the trained blocking machine learning model, and outputting an early warning signal when the running parameters of the heat exchanger do not accord with the normal running state.
7. A method for early warning of a health status monitoring system of a heat station device according to claim 3, wherein the method for early warning of the motor early warning unit comprises the following steps:
obtaining a vibration parameter jump curve, a temperature jump curve, a three-phase voltage balance curve and a current load curve of a vibration sensor, a temperature sensor and a voltage and current sensor in a normal state in a historical time period, inputting the vibration parameter jump curve, the temperature jump curve, the three-phase voltage balance curve and the current load curve as sample data into a constructed motor early-warning machine learning model, training the motor early-warning machine learning model, and obtaining operation parameters of the normal state of the motor by the trained motor early-warning machine learning model;
and inputting the real-time operation parameters of the motor into a trained motor early warning machine learning model, judging the real-time operation state of the motor, and outputting an early warning signal according to a judging result.
8. The method for early warning of a health status monitoring system of a heat station device according to claim 4, wherein the method for early warning of the pipe explosion-missing early warning unit is as follows:
obtaining the K values of all the sensors, inputting the K values of all the sensors as sample data into a constructed pipeline early-warning machine learning model, training the pipeline early-warning machine learning model, and carrying out compound operation on the K values of all the sensors by the trained pipeline early-warning machine learning model to obtain the standard health state L of all the heating power pipelines;
the real-time K values of the sensors are input into a trained pipeline early warning machine learning model, the real-time health state L1 of the current pipeline is output, the standard health state L is compared with the real-time health state L1, and an early warning signal is output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310460219.9A CN116519054A (en) | 2023-04-21 | 2023-04-21 | Health state monitoring system and method for heat station equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310460219.9A CN116519054A (en) | 2023-04-21 | 2023-04-21 | Health state monitoring system and method for heat station equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116519054A true CN116519054A (en) | 2023-08-01 |
Family
ID=87396994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310460219.9A Pending CN116519054A (en) | 2023-04-21 | 2023-04-21 | Health state monitoring system and method for heat station equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116519054A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117170312A (en) * | 2023-11-03 | 2023-12-05 | 南通钜盛数控机床有限公司 | Quantitative evaluation method for health degree of numerical control machine tool spindle |
| CN117572295A (en) * | 2024-01-12 | 2024-02-20 | 山东和兑智能科技有限公司 | Multi-mode on-line monitoring and early warning method for high-voltage sleeve |
| CN117170312B (en) * | 2023-11-03 | 2024-04-12 | 南通钜盛数控机床有限公司 | Quantitative evaluation method for health degree of numerical control machine tool spindle |
-
2023
- 2023-04-21 CN CN202310460219.9A patent/CN116519054A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117170312A (en) * | 2023-11-03 | 2023-12-05 | 南通钜盛数控机床有限公司 | Quantitative evaluation method for health degree of numerical control machine tool spindle |
| CN117170312B (en) * | 2023-11-03 | 2024-04-12 | 南通钜盛数控机床有限公司 | Quantitative evaluation method for health degree of numerical control machine tool spindle |
| CN117572295A (en) * | 2024-01-12 | 2024-02-20 | 山东和兑智能科技有限公司 | Multi-mode on-line monitoring and early warning method for high-voltage sleeve |
| CN117572295B (en) * | 2024-01-12 | 2024-04-12 | 山东和兑智能科技有限公司 | Multi-mode on-line monitoring and early warning method for high-voltage sleeve |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
| CN114640173B (en) | Early warning model of transformer and generator based on many characteristic quantities | |
| CN103403463B (en) | Fault detection and diagnosis algorithm | |
| CN104796082A (en) | System and method for diagnosing faults of photovoltaic power generation systems in online manner | |
| KR20140130540A (en) | Method and system for real-time performance recovery advisory for centrifugal compressors | |
| CN103942735A (en) | Method for evaluating relay protection states | |
| CN110991692B (en) | Heat exchanger group operation condition monitoring, cleaning and early warning method based on dynamic envelope curve method | |
| CN112177661B (en) | Accurate monitoring and abnormity early warning system and method for local ventilation parameters of coal mine | |
| CN110926809A (en) | Big data analysis-based wind turbine generator transmission chain fault early warning method | |
| CN105022373A (en) | Port equipment maintenance system based on zigbee technology | |
| CN106997513A (en) | The distribution net equipment state evaluation system analyzed based on big data | |
| CN105841980B (en) | HXD type locomotive cooling duct monitoring of working condition and fault pre-diagnosing method and system | |
| CN112836941B (en) | Online health condition assessment method for high-pressure system of steam turbine of coal motor unit | |
| CN105320123A (en) | Measurement and control equipment health state evaluating system and method based on online monitored data | |
| CN113902288A (en) | Management system and method for water resource regulation and control and operation | |
| CN113177646B (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN112000654B (en) | High-speed railway strong wind monitoring data quality control method and device | |
| CN113669628A (en) | Operation monitoring and online fault diagnosis system for steam heating network | |
| CN108093210A (en) | A kind of transformer oil level warning system and its alarm method | |
| CN214173430U (en) | A monitoring system that is used for efficiency ann healthy integration of ventilation blower or water pump | |
| CN108416386A (en) | A kind of method and system judged extremely for Hydropower Unit bearing temperature | |
| RU2541937C2 (en) | Oil production data support and control method in real time and automated system for its implementation | |
| CN219828579U (en) | Urban water supply network flow monitoring and early warning system | |
| CN112611413A (en) | Energy efficiency and health integrated monitoring method and device for ventilator or water pump | |
| CN106325258A (en) | Relay protection device state assessment method based on online monitoring information |
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 |