CN107607342B - Healthy energy efficiency detection method for air conditioner room equipment group - Google Patents
Healthy energy efficiency detection method for air conditioner room equipment group Download PDFInfo
- Publication number
- CN107607342B CN107607342B CN201710866822.1A CN201710866822A CN107607342B CN 107607342 B CN107607342 B CN 107607342B CN 201710866822 A CN201710866822 A CN 201710866822A CN 107607342 B CN107607342 B CN 107607342B
- Authority
- CN
- China
- Prior art keywords
- vibration
- signal
- equipment
- separation
- energy efficiency
- 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
Images
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a method for detecting the health energy efficiency of an air conditioner room equipment group, which comprises the steps of firstly installing a vibration sensor in a room, transmitting a received vibration signal to a data acquisition system, and acquiring the vibration signal of equipment; then, a separation model W is calculated through a high-order accumulation blind source separation algorithm of mutual information under a natural gradient1、W2. Blind source separation is carried out on the multi-source mixed signal by utilizing the calculated separation model, so that the time-frequency characteristics of the equipment fault signal are extracted; then, signal characteristic recognition is carried out according to the characteristic parameters and the position of the sensor, the fault type and the working state of the equipment are judged, and corresponding processing is timely carried out according to the analyzed state information, so that the purposes of equipment health detection and equipment operation efficiency improvement are achieved. The invention can extract the vibration signal characteristics when a single device runs under the condition that a plurality of devices run together, thereby correctly judging the health state of the device and improving the running efficiency.
Description
Technical Field
The invention belongs to the technical field of equipment fault diagnosis, and particularly relates to a healthy energy efficiency detection method for an air conditioner room equipment group.
Background
Under the trend of complicated and large-scale equipment, in order to save space resources and facilitate maintenance and management of the air conditioner room, different types of units are often installed in the same space in a centralized manner. At present, the average value of the energy efficiency ratio of the domestic air conditioning system is about 2.5, the lowest value is only 1.7, and the energy efficiency ratio is far lower than the efficiency value of a single air conditioning unit. Compared with the foreign countries, China is always at a disadvantage in the aspect of equipment energy efficiency utilization, the foreign equipment energy efficiency utilization rate can reach over 75%, but the domestic utilization rate is only about 30%. The main reasons for this situation are that various devices in the machine room vibrate and transmit, secondary vibration caused by noise reduces the operation efficiency of the devices, mechanical faults occur frequently, and therefore the energy efficiency of the unit is reduced. Therefore, the vibration monitoring is carried out on the equipment group in the air conditioning unit room, the early failure of the single equipment is found in time, and the powerful guarantee for ensuring the healthy and efficient operation of the air conditioning unit is provided.
The equipment state monitoring system obtains the running state of the equipment by analyzing various state characteristic information, reduces the damage of the equipment as much as possible, and avoids unnecessary energy efficiency waste and financial loss. Therefore, the efficient and accurate equipment health and energy efficiency monitoring system can not only ensure the normal operation of the air conditioner room, but also improve the equipment operation efficiency and reduce the shutdown maintenance cost. However, the state monitoring method of the sensor can only monitor a single device, and the influence of factors such as mutual interference of various devices and change of unit operation efficiency cannot be diagnosed accurately and in real time. Therefore, under the condition that signals of multiple vibration sources are unknown and the output power of the air conditioning unit dynamically changes, the fact that the signal characteristics of the fault source of the single unit can be extracted becomes a key technical problem.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a novel healthy energy efficiency detection method for an air conditioner room equipment group of a multi-source mixed signal fault identification technology aiming at the problem that the mixed signals of a plurality of vibration sources are difficult to quickly and accurately identify the running state of the equipment, so that the method is sensitive to weak early fault signals and can identify various fault characteristics; the invention can extract the vibration signal characteristics when a single device runs under the condition that a plurality of devices run together, thereby correctly judging the health state of the device and improving the running efficiency. The method provided by the invention improves the performance of a blind separation algorithm, improves the separation precision of the vibration signal, and enables the separation performance to be more stable, reliable, accurate and efficient in practical application, so that the health and energy efficiency states of the unit can be accurately, effectively and timely judged, and the purposes of early discovery of equipment faults and accurate identification of fault types and energy efficiency levels are achieved.
In order to achieve the purpose, the invention adopts the following technical scheme.
The invention discloses a method for detecting health energy efficiency of an air conditioner room equipment group, which is characterized by comprising the following steps of:
step 1: firstly, arranging vibration measuring points at key parts such as a compressor, a coupler and the like of an air conditioning unit in a machine room, measuring axial, vertical and horizontal vibration frequency spectrums of all parts of the unit by using a vibration spectrum analyzer, and finally transmitting signals to a data acquisition system;
step 2: then, the collected and stored vibration signal is used as an input signal X (t) and a third-order accumulation quantity is used
And fourth order accumulation
Indicating the output signal y (t), the edge entropy H (y)i) And integrating the third order
And fourth order accumulation
Edge entropy H (y) is obtained by expanding the Edgeworth seriesi) Respectively using the natural gradient method to the W in the mutual information expression1、W2Derivation whereby a separation matrix W is calculated1And W2Finally, on the basis of a nonlinear multi-source signal blind separation model, separating a vibration source signal y (t) by using the solved separation matrix;
and step 3: and finally, performing characteristic analysis on the separated source signal, thereby determining a main fault source of the machine room, identifying the running state according to the separated vibration source signal characteristic, and feeding back the running state information of the equipment to the health energy efficiency monitoring system in time, thereby achieving the purpose of monitoring the health and energy efficiency states in real time.
In a preferred embodiment of the present invention, the vibration measuring point arranged in the equipment room in step 1 is a vibration sensor.
As another preferred embodiment of the present invention, the separation matrix W is calculated in the step 21、W2Comprises the following steps:
(1) determining the optimal installation position of the vibration sensor according to the key parts of the air conditioning unit, collecting vibration data of the air conditioning unit by using a data collecting system, and collecting air by using the vibration sensors arranged at the key parts of a compressor, a coupling and the like on the air conditioning unitVibration signal X of regulating unitj(t), j is 1, 2, n, wherein j is the number of channels, and n is a positive integer;
(2) the blind source separation algorithm according to the invention is used for collecting vibration signals X of the air conditioning unitj(t) performing blind source separation to obtain an original vibration signal source sj(t) approximate signal source yj(t), wherein j is 1, 2.
(3) Will yiIs calculated by a third-order accumulation amount
And fourth order accumulation
Representing and expanding the graph by using an Edgeworth series:
wherein
Are each yiThird and fourth order accumulation amounts of (a);
(4) the output y is expressed as mutual information by using separation parameters according to the definition of mutual information in the information theory:
(5) defining a vector function f (y) as a nonlinear excitation function, and calculating the vector function according to the sigmoid function:
(6) using gradient descent algorithm with minimum mutual information, separately for W in formula (b)1And W2Derivation:
wherein D (u) ═ diag [ P'y1(y1)，…，P′yn(yn)]，diag[·]Vectorization is carried out to form a diagonal matrix, diagonal elements are corresponding components of the vector, and η is learning step length;
(7) finally, substituting the formula (c) into the formulas (d) and (e), solving the separation matrix W1And W2：
W1(k+1)＝W1(k)+η(I－f(y)yT)W1(k) (f)，
W2(k+1)＝W2(k)+η(I－f(y)yT－W1(k)Tf(y)yT)W2(k) (g)，
Wherein η is the adaptive learning step size;
(8) separating the collected signal X (t) by using a separation matrix to solve a source signal y (t);
(9) drawing;
(10) performing a feature analysis on the isolated source signal y (t);
(11) and ending.
As another preferred embodiment of the present invention, the CSI2310 vibration spectrum analyzer is used as the vibration spectrum analyzer in step 1.
The invention selects an air conditioner room of an underground layer, wherein the air conditioner room comprises two heat pump units, three circulating water pumps and various pipelines as calculation examples. The multi-source vibration separation method has good time-frequency aggregation and anti-interference performance, so that multi-source mixed signals can be separated to the maximum extent, and the type of a fault can be judged according to the energy distribution, the frequency composition and the pulse time interval of the separated signals, thereby determining the running state of equipment in a machine room.
When the invention is applied to engineering, an equipment vibration acquisition system is generally arranged in an air conditioner room to detect the running state of equipment for a long time, and the working state of the equipment can be judged by separating the time-frequency characteristics of fault signals according to vibration signals acquired actually through the signal processing method of the invention, so that the aim of monitoring the health and energy efficiency of the equipment is fulfilled.
According to the invention, the vibration sensor is arranged on the equipment and is transmitted to the data acquisition system, and the signal blind source separation processing is carried out on the acquired multi-source mixed signal based on a high-order accumulation mutual information blind source separation algorithm of a natural gradient. The signal processing method can accurately reflect the time-frequency characteristics of the equipment fault signal, and provides an effective means for monitoring the working state of the equipment and early warning the equipment fault.
The method of high-order cumulant is adopted, the influence of estimation error on the separation result can be reduced, the performance of a blind separation algorithm is improved, the calculation precision is improved, the fault type and the equipment working state can be judged through the time-frequency characteristic parameters of the processed signals, and the problem that the conventional fault diagnosis method is difficult to accurately separate the multi-source signals is avoided, so that the method has strong operability, quick diagnosis and high precision.
Compared with the prior art, the invention has the beneficial effects that: at present, mechanical equipment is continuously large-sized, diversified and clustered, domestic enterprises do not have mature products for equipment group detection systems, import is mainly relied on, and domestic partial software has a larger gap compared with foreign software; in addition, the whole set of overseas equipment health monitoring system is expensive in selling price and is not consistent with the running state of domestic equipment, so that the whole set of overseas equipment health monitoring system cannot play a good role. Meanwhile, the design environment of foreign products is different from the working environment of domestic equipment, so that the operation reliability of the equipment in severe environment cannot be improved. The invention can quickly and accurately analyze the working state of the equipment, ensure the safety and the high efficiency of the equipment, improve the early warning effect of the unhealthy state of the equipment and reduce the maintenance cost. Meanwhile, the invention is also effective in fault detection in complex space environments such as machine rooms, equipment groups and the like, is particularly suitable for fault detection of equipment such as water source heat pumps, water pump machine rooms, air conditioning boxes, wind turbines, blowers and the like, can greatly reduce the detection and maintenance cost of various equipment, improves the equipment maintenance mode, and improves the safety reliability and high efficiency of equipment operation, thereby bringing remarkable economic benefit.
Drawings
In order to make the technical problems, technical solutions and advantageous effects solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and the detailed description. It should be understood that the detailed description and specific examples, while indicating the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a schematic diagram of multi-source signal blind separation of a health energy efficiency detection method for an air conditioner room equipment group according to the present invention.
FIG. 2 is a diagram of the radial vibration mixed signal of the measuring point No. 3 of the invention.
FIG. 3 is a diagram of the axial vibration mixed signal of the No. 3 measuring point of the invention.
FIG. 4 is a separation diagram of the radial vibration mixed signal of the measuring point No. 3 of the invention.
FIG. 5 is a diagram of the separation of the axial vibration mixed signal of the No. 3 measuring point of the invention.
Fig. 6 is a signal processing program calculation block diagram of a health energy efficiency detection method for an air conditioner room equipment group according to the present invention.
Fig. 7 is a device health monitoring technology route diagram of a method for detecting health energy efficiency of an air conditioner room device group according to the present invention.
Detailed Description
The invention relates to a method for detecting the health energy efficiency of an air conditioner room equipment group, which comprises the steps of firstly installing a vibration sensor in a room, transmitting a received vibration signal to a data acquisition system, and acquiring the vibration signal of equipment; then, a separation model W is calculated through a high-order accumulation blind source separation algorithm of mutual information under a natural gradient1、W2. Blind source separation is carried out on the multi-source mixed signal by utilizing the calculated separation model, so that the time-frequency characteristics of the equipment fault signal are extracted; then, signal characteristic recognition is carried out according to the characteristic parameters and the position of the sensor, the fault type and the working state of the equipment are judged, and corresponding processing is timely carried out according to the analyzed state information, so that the purposes of equipment health detection and equipment operation efficiency improvement are achieved.
The method comprises the following specific steps:
1) blind source separation of multi-source mixed signals
Due to the complexity of the working environment of the equipment and the large number and variety of the equipment, the classical signal blind source separation is not suitable for the complex and severe working environment. The objective of blind source separation is to find a suitable non-linear function g (x) by observing the signal x (t) so that the source signal s (t) is recovered by it, i.e.:
s(t)＝[y1(t),y2(t),…ym(t)]＝g[(x(t))](1)
in the formula, y (t) is referred to as an estimated vector of s (t).
In the invention, the interference of the multi-source mixed signal on the fault signal characteristic identification is considered, and the model of the adopted separation system is as follows:
y(t)＝W1g(W2X(t))＝s(t) (2)
where g (u) acts as a scalar function on each component of vector u, i.e. g (u) { g (u) }1),g(u2),…,g(un)}T；W1、W2Are discrete matrices, i.e., are all reversible.
Formula (2) shows that under the condition of mixed signals, blind separation can directly utilize the received unknown mixed signals, and source signals are recovered from observation data under the condition of no prior knowledge, and the blind separation method is often used as a signal-noise separation method; as shown in fig. 1, x (t) is a signal vector collected by the sensor, s (t) is a source signal vector, a is an unknown mixing matrix, and the output y (t) is an estimated vector of s (t).
2) Device vibration signal acquisition
The method comprises the following steps that an underground equipment room comprises two heat pump units, three circulating water pumps and various pipelines, and strong vibration of the units is transmitted to the upstairs through a building; in the machine room, a CSI2310 vibration spectrum analyzer is adopted to measure the axial, vertical and horizontal vibration spectrum of each component of the No. 1 heat pump unit; the data acquisition system consists of a vibration sensor, a data acquisition card, a digital signal simulator and a computer, wherein after the vibration signal is converted by the data acquisition card, the data acquisition card transmits a signal output by the sensor to the display and stores the signal.
3) Minimum mutual information method in non-linear blind separation algorithm
The nonlinear blind signal separation method mainly comprises a maximum entropy method and a minimum mutual information method, wherein when the mixed model is linear, the maximum entropy method and the minimum mutual information are equivalent; when the mixture model is non-linear, the two algorithms have large difference in performance; the blind separation algorithm based on the minimum mutual information can separate a plurality of signal sources by using fewer sensors, and is suitable for the actual situation that a plurality of devices are provided and the number of faults is unknown; according to the definition of mutual information in the information theory, the mutual information expressed by the separation parameter of the output y can be obtained as follows:
wherein G ═ WA is the global matrix, and h (y) ═ -E [ log (P)y(y))]To separate the edge entropy of the system output signal, equation (3) can therefore be written as:
with the increase of the number of the sources, the calculation amount of the algorithm is too large, and the defects of difficult convergence and poor stability exist; finding an efficient estimation method is therefore very important to improve the performance of the algorithm.
4) Separation matrix calculation method
In order to sequentially extract the most significant characteristic values according to the independence measure relation between the information sources under the condition that the number of fault sources is unknown and is possibly more than the number of sensors, the method improves the algorithm by utilizing the random characteristics of the source signals on the basis of the minimum mutual information natural gradient algorithm.
The probability density expression of the output signal y (t) and the observation signal x (t) of the separation system is:
wherein P isy(Y) is the probability density function of Y, sinceThe probability density function of the output signal is an unknown quantity, so the edge entropy H (y) needs to be calculated firsti) Otherwise, an explicit expression of the mutual information amount cannot be obtained.
Therefore, y in the formula (b)iBy a third-order accumulation amount for the edge entropy term
And fourth order accumulation
Representing and expanding the graph by using an Edgeworth series:
wherein
Are each yiThird and fourth order accumulation amounts.
Then respectively aligning W in the formula (b) under natural gradient1And W2Taking the derivative to obtain:
in the formula (e), the vector function f (y) is a nonlinear excitation function, and the vector function is calculated according to the sigmoid function:
wherein D (u) ═ diag (P'y1(y1)，…，P′yn(yn))，diag[·]Vectorization is carried out to form a diagonal matrix, diagonal elements are corresponding components of the vector, and η is the self-adaptive learning step size.
And finally, substituting the nonlinear excitation function in the formula (c) into the formula (e) to obtain a high-order accumulation blind separation algorithm based on mutual information of natural gradient:
W1(k+1)＝W1(k)+η(I－f(y)yT)W1(k) (f)，
W2(k+1)＝W2(k)+η(I－f(y)yT－W1(k)Tf(y)yT)W2(k) (g)，
where η is the adaptive learning step size.
A block diagram of a signal processing program for calculating edge entropy in mutual information by using a high-order accumulation amount and finally calculating a separation model by a natural gradient method is shown in fig. 6, and the signal processing program comprises the following steps:
①, using the vibration signal of a certain measuring point on the machine set as an observation signal X (t);
②, according to the formula (b), the output y is expressed in a mutual information form by separation parameters;
③ calculation of output y from the third and fourth order accumulations according to equation (a)iThe edge entropy is expanded by using an Edgeworth series;
④ Natural gradient Algorithm with minimum mutual information for W according to equations (d) and (e), respectively1、W2Derivation is carried out;
⑤ solving vector function f (y) according to sigmoid function
⑥ calculation of separation model W by taking equation (c) into equation (e)1，W2；
⑦ separating the matrix W1、W2Substituting the formula (2) to solve the source signal;
⑧ drawing
⑨, and finishing.
5) Analysis of the separation signal characteristics
And recalculating the separation model by using the optimized high-order accumulation amount, eliminating the interference in fault signal identification by using a new separation model on the basis of a blind separation theory, excavating characteristic parameters of the fault signal, and finally identifying the fault type and the equipment working state according to the separated fault signal, wherein the fault type and the equipment working state are respectively shown in fig. 4 and fig. 5. As shown in fig. 4, from the whole frequency spectrum, the vibration value appears at 4 times of frequency (200Hz) at most, while the vibration speed of other frequency components is almost negligible, and since the number of male rotors is 4, one rotation period will be rubbed 4 times, which is equivalent to 1 time of frequency, which indicates that the rotor mesh is poor due to the gear processing, manufacturing and assembling; as shown in FIG. 5, harmonic occurs in the frequency band of 150-250Hz, and the maximum peak value is at the frequency multiplication of 4, and the symmetrical amplitudes at both sides decrease progressively, and tests show that the natural frequency of the unit at shutdown is 203Hz, and the frequency spectrum has a peak value at the frequency multiplication of 4 during operation, which shows that the unit operation frequency is close to the natural frequency, so that resonance occurs. The resonance of the equipment can cause the deformation and the uneven stress of the internal structure, especially the rotor part with higher requirements on dynamic balance, and the forced vibration can affect the health level of the unit, thereby causing the reduction of the working efficiency of the unit.
6) Monitoring of health status of the device and improving efficiency of operation of the device
After detailed analysis is performed on the plant signal separated by the signal separation system, the plant operation state signal to be analyzed is transmitted to the plant operation state evaluation area, as shown in fig. 7. According to the state information in the evaluation area, on one hand, corresponding state tracking and maintenance suggestions can be made, so that the working personnel can find the unhealthy state of the equipment in time and take reasonable maintenance measures according to the system suggestions. On the other hand, maintenance reminding and maintenance guidance can be made, the effects of equipment health prediction and management are achieved, and equipment maintenance is regularly and reasonably carried out according to the maintenance guidance. In addition, the analyzed equipment operation data, the analyzed fault information data and the analyzed algorithm data are timely stored in a corresponding database, so that the operation state of the equipment can be quickly and conveniently reflected in time. According to the method, the running state of the equipment can be adjusted to the optimal state at any time, and the sub-health state of the equipment is reduced, so that the running energy efficiency of the equipment is improved.
It should be understood that the detailed description of the present invention is only for illustrating the present invention and is not limited by the technical solutions described in the embodiments of the present invention, and those skilled in the art should understand that the present invention can be modified or substituted equally to achieve the same technical effects; as long as the use requirements are met, the method is within the protection scope of the invention.
Claims (3)
1. The method for detecting the health energy efficiency of the air conditioner room equipment group is characterized by comprising the following steps of:
step 1: firstly, arranging vibration measuring points at key parts of a compressor and a coupling of an air conditioning unit in a machine room, measuring axial, vertical and horizontal vibration frequency spectrums of each part of the unit by using a vibration spectrum analyzer, and finally transmitting signals to a data acquisition system;
step 2: then, the collected and stored vibration signal is used as an input signal X (t) and a third-order accumulation quantity is used
And fourth order accumulation
Indicating the output signal y (t), the edge entropy H (y)i) And integrating the third order
And fourth order accumulation
Edge entropy H (y) is obtained by expanding the Edgeworth seriesi) Respectively using the natural gradient method to the W in the mutual information expression1、W2Derivation whereby a separation matrix W is calculated1And W2Finally, on the basis of a nonlinear multi-source signal blind separation model, separating a vibration source signal y (t) by using the solved separation matrix;
and step 3: finally, performing characteristic analysis on the separated source signal so as to determine a main fault source of the machine room, identifying an operation state according to the separated vibration source signal characteristic, and feeding back equipment operation state information to a health energy efficiency monitoring system in time so as to achieve the purpose of monitoring health and energy efficiency states in real time;
calculating the moment of separation in said step 2Array W1、W2Comprises the following steps:
(1) determining the optimal installation position of the vibration sensor according to the key position of the air conditioning unit, collecting vibration data of the air conditioning unit by using a data collection system, and collecting vibration signals X of the air conditioning unit by using the vibration sensors arranged at the key positions of a compressor and a coupling on the air conditioning unitj(t), j is 1, 2, n, wherein j is the number of channels, and n is a positive integer;
(2) according to the blind source separation algorithm, collecting vibration signals X of the air conditioning unitj(t) performing blind source separation to obtain an original vibration signal source sj(t) approximate signal source yj(t), wherein j is 1, 2.
(3) Will yiIs calculated by a third-order accumulation amount
And fourth order accumulation
Representing and expanding the graph by using an Edgeworth series:
wherein
Are each yiThird and fourth order accumulation amounts of (a);
(4) according to the definition of mutual information in the information theory, the output y is expressed as mutual information by using a separation parameter:
(5) defining a vector function f (y) as a nonlinear excitation function, and calculating the vector function according to the sigmoid function:
(6) using gradient descent algorithm with minimum mutual information, separately for W in formula (b)1And W2Derivation:
wherein D (u) ═ diag [ P'y1(y1)，…，P′yn(yn)]，diag[·]Vectorization is carried out to form a diagonal matrix, diagonal elements are corresponding components of the vector, and η is learning step length;
(7) finally, substituting the formula (c) into the formulas (d) and (e), solving the separation matrix W1And W2：
W1(k+1)＝W1(k)+η(I－f(y)yT)W1(k) (f)，
W2(k+1)＝W2(k)+η(I－f(y)yT－W1(k)Tf(y)yT)W2(k) (g)，
Wherein η is the adaptive learning step size;
(8) separating the collected signal X (t) by using a separation matrix to solve a source signal y (t);
(9) drawing;
(10) performing a feature analysis on the isolated source signal y (t);
(11) and ending.
2. The method for detecting the health energy efficiency of the equipment group in the air conditioner room as claimed in claim 1, wherein the vibration measuring points arranged in the equipment room in the step 1 are vibration sensors.
3. The method for detecting health energy efficiency of the air conditioner room equipment group according to claim 1, wherein the method comprises the following steps: and the vibration spectrum analyzer in the step 1 adopts a CSI2310 vibration spectrum analyzer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710866822.1A CN107607342B (en) | 2017-09-22 | 2017-09-22 | Healthy energy efficiency detection method for air conditioner room equipment group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710866822.1A CN107607342B (en) | 2017-09-22 | 2017-09-22 | Healthy energy efficiency detection method for air conditioner room equipment group |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107607342A CN107607342A (en) | 2018-01-19 |
| CN107607342B true CN107607342B (en) | 2020-05-26 |
Family
ID=61061807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710866822.1A Active CN107607342B (en) | 2017-09-22 | 2017-09-22 | Healthy energy efficiency detection method for air conditioner room equipment group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107607342B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110146317B (en) * | 2019-04-29 | 2021-11-12 | 北京和欣运达科技有限公司 | Method and device for diagnosing health state of building electromechanical equipment |
| CN112432317A (en) * | 2020-11-16 | 2021-03-02 | 东南大学 | Sensor optimal arrangement method for classroom and ventilation monitoring system thereof |
| CN113884236B (en) * | 2021-08-24 | 2022-06-21 | 西安电子科技大学 | Multi-sensor fusion dynamic balance analysis method, system, equipment and medium |
| CN116400627A (en) * | 2023-04-13 | 2023-07-07 | 深圳市丰源升科技有限公司 | Industrial remote control system and method based on 5G |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003078423A (en) * | 2001-09-03 | 2003-03-14 | Clarion Co Ltd | Processor for separating blind signal |
| CN1914683A (en) * | 2004-02-26 | 2007-02-14 | 南承铉 | Methods and apparatus for blind separation of multichannel convolutive mixtures in the frequency domain |
| CN104155134A (en) * | 2014-08-06 | 2014-11-19 | 北京信息科技大学 | Judgment method of applicability of high-order cumulant feature extraction method |
| CN104390780A (en) * | 2014-11-25 | 2015-03-04 | 沈阳化工大学 | Gear case fault diagnosis method based on blind source separation |
-
2017
- 2017-09-22 CN CN201710866822.1A patent/CN107607342B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003078423A (en) * | 2001-09-03 | 2003-03-14 | Clarion Co Ltd | Processor for separating blind signal |
| CN1914683A (en) * | 2004-02-26 | 2007-02-14 | 南承铉 | Methods and apparatus for blind separation of multichannel convolutive mixtures in the frequency domain |
| CN104155134A (en) * | 2014-08-06 | 2014-11-19 | 北京信息科技大学 | Judgment method of applicability of high-order cumulant feature extraction method |
| CN104390780A (en) * | 2014-11-25 | 2015-03-04 | 沈阳化工大学 | Gear case fault diagnosis method based on blind source separation |
Non-Patent Citations (1)
| Title |
|---|
| 基于盲分离的空调机组故障振声诊断研究;周勃;《中国博士学位论文全文数据库 工程科技Ⅱ辑（月刊）》;20090215(第02期);2.4 非线性混合的盲分离、第六章 大空间设备群的振声综合诊断 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107607342A (en) | 2018-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107607342B (en) | Healthy energy efficiency detection method for air conditioner room equipment group | |
| CN103645052B (en) | A kind of gearbox of wind turbine remote online status monitoring and lifetime estimation method | |
| CN108446529B (en) | Organic Rankine cycle system fault detection method based on generalized mutual entropy-DPCA algorithm | |
| CN104122086B (en) | Fault Diagnosis of Gearbox for Wind Turbine method based on Kriging model | |
| CN201311360Y (en) | Vibrating online monitoring failure diagnostic device | |
| CN109255333B (en) | Fault hybrid diagnosis method for rolling bearing of large wind turbine generator | |
| CN103195727A (en) | Device for on-line monitoring and evaluating state of air blower | |
| CN113253705B (en) | Fault diagnosis method and device for air blower | |
| CN112001511A (en) | Equipment reliability and dynamic risk evaluation method, system and equipment based on data mining | |
| CN106441843B (en) | A kind of rotating machinery fault method for waveform identification | |
| CN103236019A (en) | Method and system for automatically generating energy-saving diagnosis and modification strategy for typical energy-consuming system | |
| CN111273125A (en) | RST-CNN-based power cable channel fault diagnosis method | |
| CN104343709A (en) | Draught fan failure detection apparatus and method | |
| CN117375246B (en) | Power equipment management method, system and equipment | |
| CN116086814A (en) | Fault analysis and intelligent diagnosis system for heavy-duty gas turbine | |
| CN103529337B (en) | The recognition methods of nonlinear correlation relation between equipment failure and electric quantity information | |
| CN109613372B (en) | Power grid fault diagnosis method based on multi-element power grid database | |
| CN117536872B (en) | Roots blower state monitoring system and fault prediction method | |
| CN106126949A (en) | A kind of steam turbine generator running status appraisal procedure | |
| CN113390641A (en) | Intelligent early warning and online diagnosis method and system for equipment faults of wind and smoke system | |
| CN111898794B (en) | Abnormal monitoring method for thermal efficiency of large coal-fired boiler | |
| CN104569814A (en) | Approximate entropy-based direct-current traction motor health condition real-time analysis method | |
| CN102778632A (en) | Double normalization recognition method for directly forecasting and recognizing transformer winding fault type | |
| CN203394815U (en) | Draught fan set energy efficiency real time test device based on wireless data transmission | |
| CN115906437A (en) | Fan state determination method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |