A non-intrusive identification method and device for industrial and commercial oil fume purifiers

Through multi-dimensional feature change detection based on CUSUM algorithm, non-intervention identification of industrial and commercial oil fume purifiers is realized, and the problems of high monitoring costs and difficult in the existing technology are solved, monitoring accuracy and ease of implementation are improved, and environmental law enforcement is provided. Important support.

CN114595727BActive Publication Date: 2024-11-08STATE GRID JIANGSU ELECTRIC POWER CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202210257032.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-16
Publication Date
2024-11-08
Estimated Expiration
2042-03-16

AI Technical Summary

Technical Problem

In the prior art, monitoring of industrial and commercial oil fume purifiers usually requires the installation of detection devices in each device, which leads to high cost and difficult management, and the inability to effectively monitor the sewage discharge situation in the catering industry.

Method used

Using the CUSUM-based transient event detection algorithm, transient change events are extracted from the effective value sequence of active power, reactive power, second harmonic current and third harmonic current, and the opening of the oil fume purifier is judged through the multi-dimensional feature change. Time, realize non-interventional identification.

Benefits of technology

It reduces the number and cost of equipment, improves the accuracy and ease of implementation of monitoring, provides an important basis for industrial and commercial environmental protection law enforcement, and can effectively detect the opening status of the oil fume purifier.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114595727B_ABST
    Figure CN114595727B_ABST
Patent Text Reader

Abstract

The present invention discloses a non-intrusive identification method and device for industrial and commercial oil fume purifiers. The method comprises: obtaining pre-collected active power, reactive power, 2nd harmonic current and 3rd harmonic current effective value sequences of a set sampling frequency at a general meter of a shop to be detected; using a transient event detection algorithm based on CUSUM to extract transient change events from the effective value sequence of active power, and obtaining multi-dimensional characteristic changes of reactive power, 2nd harmonic current and 3rd harmonic current through transient change event tracking; judging whether the multi-dimensional characteristic changes conform to the industrial and commercial oil fume purifier model and obtaining the final start time. The present invention only collects data at the user's general meter to achieve the monitoring effect of the exhaust fan, uses a small number of equipment, has low cost and is easy to implement, and provides an important basis for industrial and commercial environmental protection law enforcement.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a non-intrusive identification method and device for industrial and commercial oil fume purifiers, belonging to the technical field of electric power research. Background Art

[0002] In recent years, with the rapid economic development, people's consumption level has gradually increased. Whether it is a small shop or restaurant along the street, or a barbecue restaurant or hot pot restaurant in a large shopping mall, it is often crowded. This type of catering industry often produces sewage, exhaust gas and noise during operation. At the same time, the catering industry is also the main exhaust gas emission industry. If the corresponding exhaust pollution control equipment is not turned on during business hours and pollutants are allowed to be discharged, it will have a greater impact on the environment. Therefore, it is necessary to monitor the industrial and commercial sewage treatment equipment. However, the usual method is to install a detection device in each device to be monitored. This method has high investment costs and is difficult to manage and implement. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a non-intrusive identification method and device for industrial and commercial oil fume purifiers to solve the above-mentioned problems.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a non-intrusive identification method for industrial and commercial oil fume purifiers, comprising:

[0006] Obtain the effective value sequence of active power, reactive power, second harmonic current and third harmonic current collected in advance at the total meter of the shop to be tested, and set the sampling frequency;

[0007] A transient event detection algorithm based on CUSUM is used to extract transient change events from the effective value sequence of active power, and multi-dimensional characteristic changes of reactive power, second harmonic current and third harmonic current are obtained through the transient change event tracking;

[0008] It is determined whether the multi-dimensional feature change conforms to the industrial and commercial oil fume purifier model and the final start time is obtained.

[0009] Furthermore, the method further includes: after obtaining the effective value sequence, selecting a filter window, performing median filtering processing on the effective value sequence in the filter window by using a median filtering algorithm, and obtaining a filtered effective value sequence.

[0010] Furthermore, the selecting of the filtering window and performing median filtering on the effective value sequence in the filtering window by using a median filtering algorithm to obtain the effective value sequence after filtering include:

[0011] Select filter window n w, for a filter center with index k, when n w When n is an odd number, the filtering interval is [k-(n-1) / 2, k+(n-1) / 2]; when n w When it is an even number, the filtering interval is [kn / 2, k+n / 2+1];

[0012] In each filtering interval, the median value is taken according to the size to replace the original sampling value with the subscript k, so as to obtain the effective value sequence after filtering.

[0013] Furthermore, the transient event detection algorithm based on CUSUM is used to extract transient change events from the effective value sequence of active power, and the multi-dimensional characteristic changes of reactive power, second harmonic current and third harmonic current are obtained by tracking the transient change events, including:

[0014] The transient event detection algorithm of the CUSUM is defined as:

[0015] Consider a random time series x = {x(k)}, k = 1, 2, ... Assume that a change point occurs at time p, and define the statistical function in the non-parametric bilateral CUSUM algorithm Its meaning is:

[0016]

[0017]

[0018] In the formula The positive and negative offsets of the current detection point with index k after removing the noise;

[0019]

[0020] Where μ0 is the mean of the sequence before the change point, β is the noise value, and the sequence x k Changes smaller than β are ignored;

[0021] Let the delay time be d, and consider or When or When , it is considered that a change point occurs, where H is the event threshold, otherwise d = d + 1, update and Let’s continue the comparison;

[0022] The active power event change point and event change time are obtained and recorded as ΔP1, ΔP2, and Δt. The change values ​​of other reactive power, secondary current, and tertiary current characteristics are simultaneously extracted and recorded as ΔQ1, ΔQ2, ΔI31, and ΔI32.

[0023] Furthermore, the determination of whether the multi-dimensional feature change conforms to the industrial and commercial oil fume purifier model is defined as follows:

[0024]

[0025] If it meets the requirements, record the start time; if it does not meet the requirements, continue monitoring.

[0026] In a second aspect, the present invention provides a non-intrusive identification device for industrial and commercial oil fume purifiers, comprising:

[0027] An effective value sequence acquisition unit is used to acquire the effective value sequence of active power, reactive power, second harmonic current and third harmonic current of the pre-collected total meter of the shop to be detected, with a set sampling frequency;

[0028] A multi-dimensional characteristic change acquisition unit, used to extract transient change events from the effective value sequence of active power using a transient event detection algorithm based on CUSUM, and obtain multi-dimensional characteristic changes of reactive power, second harmonic current and third harmonic current through the transient change event tracking;

[0029] The judgment unit is used to judge whether the multi-dimensional characteristic change conforms to the industrial and commercial oil fume purifier model and obtain the final opening time.

[0030] Furthermore, it also includes: a median filtering unit, which is used to select a filtering window after obtaining the effective value sequence, and perform median filtering processing on the effective value sequence in the filtering window using a median filtering algorithm to obtain a filtered effective value sequence.

[0031] In a third aspect, the present invention provides a non-intrusive identification device for a commercial oil fume purifier, including a processor and a storage medium;

[0032] The storage medium is used to store instructions;

[0033] The processor is configured to operate according to the instructions to execute the steps of any of the aforementioned methods.

[0034] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the aforementioned methods.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] 1. The non-intrusive identification method and device of industrial and commercial oil fume purifiers of the present invention use event detection algorithms to extract active, reactive and harmonic features, and construct an identification model for industrial and commercial oil fume purifiers, which can be directly used to detect whether each industrial and commercial oil fume purifier is turned on;

[0037] 2. Currently, the detection of industrial and commercial pollution control equipment is still at the stage of using interventional equipment, that is, each pollution control equipment is separately installed with a monitoring device, which is costly and difficult to implement. The present invention is a non-intrusive method, which only collects data at the user's total meter to achieve the monitoring effect of the exhaust fan, uses a small number of equipment, is low in cost, and is easy to implement, providing an important basis for industrial and commercial environmental protection law enforcement;

[0038] 3. The active power of the oil fume purifier varies little, most of which are within 1000w, and a few are greater than 1000w. It is easy to be annihilated in complex situations. The present invention uses a multi-dimensional method to identify, which reduces the probability of being annihilated in single feature identification and improves accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of a non-intrusive identification method for industrial and commercial oil fume purifiers provided by an embodiment of the present invention;

[0040] Figure 2 It is a schematic diagram of a model provided by an embodiment of the present invention; DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0042] Example 1

[0043] This embodiment introduces a non-intrusive identification method for industrial and commercial oil fume purifiers, including:

[0044] Obtain the effective value sequence of active power, reactive power, second harmonic current and third harmonic current collected in advance at the total meter of the shop to be tested, and set the sampling frequency;

[0045] A transient event detection algorithm based on CUSUM is used to extract transient change events from the effective value sequence of active power, and multi-dimensional characteristic changes of reactive power, second harmonic current and third harmonic current are obtained through the transient change event tracking;

[0046] It is determined whether the multi-dimensional feature change conforms to the industrial and commercial oil fume purifier model and the final start time is obtained.

[0047] The application process of the non-intrusive identification method for industrial and commercial oil fume purifiers provided in this embodiment specifically involves the following steps:

[0048] Step 1: Install the data collection equipment at the main meter of the shop to be tested to obtain the effective value sequence of active power, reactive power, second harmonic current and third harmonic current at one point in 0.1s.

[0049] Step 2: Preprocess the collected data and use the median filter algorithm to remove noise interference. In Example 1, the window n is selected. w =10 for median filtering.

[0050] Step 2.1: According to the median filtering algorithm described in step 2, first select the filtering window n w , for a filter center with index k, when n w When n is an odd number, the filtering interval is [k-(n-1) / 2, k+(n-1) / 2]; when n w When it is an even number, the filtering interval is [kn / 2, k+n / 2+1];

[0051] Step 2.2: Based on step 2.1, each filter interval takes the median value according to the size to replace the original sample value with the subscript k;

[0052] Step 3: Use the transient event detection algorithm based on CUSUM to extract transient change events and obtain multi-dimensional feature changes before and after the event occurs, which specifically includes the following steps:

[0053] Step 3.1: According to step 3, the CUSUM algorithm is defined as:

[0054] Consider a random time series x = {x(k)}, k = 1, 2, ... Assume that a change point occurs at time p, and define the statistical function in the non-parametric bilateral CUSUM algorithm Its meaning is:

[0055]

[0056]

[0057] In the formula The positive and negative offsets of the current detection point with index k after removing the noise

[0058]

[0059] Where μ0 is the mean of the sequence before the change point, β is the noise value, and the sequence x k Changes smaller than β are ignored;

[0060] Let the delay time be d, and consider or When or When , it is considered that a change point occurs, where H is the event threshold, otherwise d = d + 1, update and Let’s continue the comparison;

[0061] In step 3 of this method, only active power p is used for event extraction, where H∈(100, +∞), d=10, and the β value will become smaller after filtering;

[0062] Step 3.2: After obtaining the active power event change point and event change time in step 3.1, record them as ΔP1, ΔP2, Δt, and simultaneously extract the change values ​​of other reactive power, secondary current and tertiary current characteristics, record them as ΔQ1, ΔQ2, ΔI31, ΔI32.

[0063] Step 4: Determine whether the characteristic change conforms to the oil fume purifier model, which is defined as follows: Example 1: Figure 2 Said:

[0064]

[0065] If it meets the requirements, record the start time; if it does not meet the requirements, continue monitoring.

[0066] Example 2

[0067] This embodiment provides a non-intrusive identification device for industrial and commercial oil fume purifiers, including:

[0068] An effective value sequence acquisition unit is used to acquire the effective value sequence of active power, reactive power, second harmonic current and third harmonic current of the pre-collected total meter of the shop to be detected, with a set sampling frequency;

[0069] A multi-dimensional characteristic change acquisition unit, used to extract transient change events from the effective value sequence of active power using a transient event detection algorithm based on CUSUM, and obtain multi-dimensional characteristic changes of reactive power, second harmonic current and third harmonic current through the transient change event tracking;

[0070] The judgment unit is used to judge whether the multi-dimensional characteristic change conforms to the industrial and commercial oil fume purifier model and obtain the final opening time.

[0071] Furthermore, it also includes: a median filtering unit, which is used to select a filtering window after obtaining the effective value sequence, and perform median filtering processing on the effective value sequence in the filtering window using a median filtering algorithm to obtain a filtered effective value sequence.

[0072] Example 3

[0073] This embodiment provides a non-intrusive identification device for a commercial oil fume purifier, including a processor and a storage medium;

[0074] The storage medium is used to store instructions;

[0075] The processor is used to operate according to the instructions to execute the steps of the method according to any one of Embodiment 1.

[0076] Example 4

[0077] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any method described in Embodiment 1 are implemented.

[0078] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A non-intrusive identification method for industrial and commercial oil fume purifiers, characterized in that: include: Obtain the effective value sequence of active power, reactive power, second harmonic current and third harmonic current collected in advance at the total meter of the shop to be tested, and set the sampling frequency; A transient event detection algorithm based on CUSUM is used to extract transient change events from the effective value sequence of active power, and multi-dimensional characteristic changes of reactive power, second harmonic current and third harmonic current are obtained through the transient change event tracking; Determine whether the multi-dimensional feature change conforms to the industrial and commercial oil fume purifier model and obtain the final start time; The determination of whether the multi-dimensional feature change conforms to the industrial and commercial oil fume purifier model is defined as follows: ; In the formula, , is the active power event change point, is the event change time, is other reactive power, is the change value of the secondary current and tertiary current characteristics; If it meets the requirements, record the start time; if it does not meet the requirements, continue monitoring.

2. The non-intrusive identification method for industrial and commercial oil fume purifiers according to claim 1 is characterized in that: Also includes: After obtaining the effective value sequence, a filtering window is selected, and a median filtering algorithm is used to perform median filtering on the effective value sequence in the filtering window to obtain a filtered effective value sequence.

3. The non-intrusive identification method for industrial and commercial oil fume purifiers according to claim 2 is characterized in that: The selecting of the filtering window, performing median filtering processing on the effective value sequence in the filtering window by using a median filtering algorithm, and obtaining the effective value sequence after filtering, comprises: Select filter window , for a subscript The filter center is When is an odd number, the filtering interval is ;when When is an even number, the filtering interval is ; Each filter interval is replaced by the median value according to the size. The original sampling value is obtained to obtain the effective value sequence after filtering.

4. The non-intrusive identification method for industrial and commercial oil fume purifiers according to claim 1 is characterized in that: The transient event detection algorithm based on CUSUM is used to extract transient change events from the effective value sequence of active power, and the multi-dimensional characteristic changes of reactive power, second harmonic current and third harmonic current are obtained through the transient change event tracking, including: The transient event detection algorithm of the CUSUM is defined as: Examining random time series . ; Assumption Generate a change point at the moment and define the statistical function in the non-parametric bilateral CUSUM algorithm , which means: ; ; In the formula The current subscript is The positive and negative offsets of the detection point after removing the noise; ; In the formula is the mean of the series before the change point, is the noise value, the sequence Less than Changes in will be ignored; The delay time is ,think >0 or >0, it is considered that a change point may occur. >H or >H, a change point is considered to occur, where H is the event threshold, otherwise d=d+1, renew and Let’s continue the comparison; Obtain the active power event change point and event change time and record them as , , , and simultaneously extract the change values ​​of other reactive power, secondary current and tertiary current characteristics, recorded as .

5. A non-intrusive identification device for industrial and commercial oil fume purifiers, characterized in that: include: An effective value sequence acquisition unit is used to acquire the effective value sequence of active power, reactive power, second harmonic current and third harmonic current of the pre-collected total meter of the shop to be detected, with a set sampling frequency; A multi-dimensional characteristic change acquisition unit, used to extract transient change events from the effective value sequence of active power using a transient event detection algorithm based on CUSUM, and obtain multi-dimensional characteristic changes of reactive power, second harmonic current and third harmonic current through the transient change event tracking; A judgment unit is used to judge whether the multi-dimensional feature change conforms to the industrial and commercial oil fume purifier model and obtain the final opening time; the judgment of whether the multi-dimensional feature change conforms to the industrial and commercial oil fume purifier model is defined as follows: ; In the formula, , is the active power event change point, is the event change time, is other reactive power, is the change value of the secondary current and tertiary current characteristics; If it meets the requirements, record the start time; if it does not meet the requirements, continue monitoring.

6. The non-intrusive identification device for industrial and commercial oil fume purifiers according to claim 5, characterized in that: Also includes: The median filtering unit is used to select a filtering window after obtaining the effective value sequence, and perform median filtering processing on the effective value sequence in the filtering window using a median filtering algorithm to obtain a filtered effective value sequence.

7. A non-intrusive identification device for commercial oil fume purifiers, characterized in that: including processor and storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Citation Information

Patent Citations

  • Intelligent power grid load testing and recognition method based on steady state and transient state characteristic joint matching

    CN103105556A

  • A non-intrusive load detection and decomposition method based on a state matrix decision tree

    CN109387712A

  • Non-invasive load identification method based on MLCDTL

    CN110555369A

  • Multi-class typical load feature analysis and extraction method

    CN113408481A