CN112924652B - FPGA (field programmable Gate array) acceleration-based portable low-power-consumption multi-feature illegal cooking oil detector - Google Patents
FPGA (field programmable Gate array) acceleration-based portable low-power-consumption multi-feature illegal cooking oil detector Download PDFInfo
- Publication number
- CN112924652B CN112924652B CN202110140478.4A CN202110140478A CN112924652B CN 112924652 B CN112924652 B CN 112924652B CN 202110140478 A CN202110140478 A CN 202110140478A CN 112924652 B CN112924652 B CN 112924652B
- Authority
- CN
- China
- Prior art keywords
- fpga
- oil
- illegal cooking
- temperature resistant
- resistant container
- 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
- 239000008162 cooking oil Substances 0.000 title claims abstract description 24
- 230000001133 acceleration Effects 0.000 title claims abstract description 8
- 239000003921 oil Substances 0.000 claims abstract description 55
- 150000002978 peroxides Chemical class 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 239000003153 chemical reaction reagent Substances 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000010438 heat treatment Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000009529 body temperature measurement Methods 0.000 abstract description 2
- 239000004278 EU approved seasoning Substances 0.000 description 4
- 235000011194 food seasoning agent Nutrition 0.000 description 4
- 235000013305 food Nutrition 0.000 description 3
- 241000287828 Gallus gallus Species 0.000 description 2
- 238000010411 cooking Methods 0.000 description 2
- LPUQAYUQRXPFSQ-DFWYDOINSA-M monosodium L-glutamate Chemical compound [Na+].[O-]C(=O)[C@@H](N)CCC(O)=O LPUQAYUQRXPFSQ-DFWYDOINSA-M 0.000 description 2
- 235000013923 monosodium glutamate Nutrition 0.000 description 2
- 239000004223 monosodium glutamate Substances 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000008157 edible vegetable oil Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/26—Oils; Viscous liquids; Paints; Inks
- G01N33/28—Oils, i.e. hydrocarbon liquids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/955—Hardware or software architectures specially adapted for image or video understanding using specific electronic processors
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Chemical & Material Sciences (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Software Systems (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Edible Oils And Fats (AREA)
Abstract
The invention discloses a low-power-consumption portable multi-feature illegal cooking oil detector based on FPGA acceleration, which comprises an oil sample acquisition device and a data processing module, wherein the data processing module adopts an FPGA as an operation main body, the FPGA comprises a ROM module, an RAM module and a calculation module, and the FPGA carries out operation analysis on acquired data through a kNN algorithm; the oil sample collection device comprises a high-temperature resistant container, a reaction reagent reaction tube is arranged inside the high-temperature resistant container, a temperature measurement sensor and a heating tube are arranged in the high-temperature resistant container, and a conductivity/peroxide value sensor is arranged in the reaction reagent reaction tube. The invention accelerates the operation of the kNN algorithm by using the FPGA with the approximate multiplier, and judges whether the oil sample is the illegal cooking oil or not by performing operation analysis on the four-dimensional data acquired by the oil sample to be detected by using the kNN algorithm, thereby obviously improving the detection precision and having the advantages of high speed and low power consumption.
Description
Technical Field
The invention relates to the technical field of illegal cooking oil detection, in particular to a low-power-consumption portable multi-feature illegal cooking oil detector based on FPGA acceleration.
Background
Food cooked by eating the illegal cooking oil brings great harm to the health, and food safety supervision departments can sample and detect cooking oil of catering merchants to realize safety oil supervision. Conventional laboratory detection methods are very accurate but consume a significant amount of time. Most of the existing field detection methods are used for measuring a threshold value aiming at a certain single property of the illegal cooking oil, and the method can cause error and result error due to other impurities in the oil sample to be detected.
Disclosure of Invention
The invention aims to provide a low-power-consumption portable multi-feature illegal cooking oil detector based on FPGA acceleration so as to solve the problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme: a low-power-consumption portable multi-feature illegal cooking oil detector based on FPGA acceleration comprises an oil sample acquisition device and a data processing module, wherein the data processing module adopts FPGA as an operation main body, the FPGA comprises a ROM module, an RAM module and a calculation module, and the FPGA carries out operation analysis on acquired data through a kNN algorithm; the oil sample collection device comprises a high-temperature resistant container, a reaction reagent reaction tube is arranged inside the high-temperature resistant container, a temperature measurement sensor and a heating tube are arranged in the high-temperature resistant container, and a conductivity/peroxide value sensor is arranged in the reaction reagent reaction tube.
As a further improvement of the technical scheme of the invention, the target value of the oil sample data to be measured acquired by the oil sample acquisition device is as follows: a conductivity value at 60 ℃, a difference between conductivities at 60 ℃ and 25 ℃, a peroxide value at 25 ℃, and a peroxide value difference between 60 ℃ and 25 ℃.
As a further improvement of the technical scheme of the present invention, the target value of the oil sample to be measured is calculated by using the kNN algorithm of the approximate multiplier in the FPGA and all the training samples in the ROM as euclidean distances, specifically:
in the formula, xiI-th characteristic data, y, representing the sample to be testedn，iThe ith characteristic data represents the nth training sample; FPGA minimum k dnD is equal to knAnd (4) counting the corresponding categories, and outputting the category with the highest occupation ratio as a detection result, so that whether the oil product to be detected is the illegal cooking oil can be judged.
As a further improvement of the technical scheme of the invention, the oil sample collecting device also comprises a stepping motor, and the stepping motor shakes the oil to be detected through a rotating disk and a transmission rod.
Compared with the prior art, the invention has the following beneficial effects:
1. the method judges whether the oil product belongs to the illegal cooking oil or not by detecting the characteristic data of four dimensions, namely the 60 ℃ conductivity value, the 60 ℃ and 25 ℃ conductivity difference value, the 25 ℃ peroxide value and the 60 ℃ and 25 ℃ peroxide value difference value of the oil sample to be detected.
2. The invention accelerates the operation of the kNN algorithm by using the FPGA with the approximate multiplier, and performs operation analysis on the acquired data through the kNN algorithm, thereby outputting a result and judging whether the sample to be detected belongs to the illegal cooking oil, and the invention has the advantages of high speed and low power consumption.
Drawings
Fig. 1 is a schematic view of the overall structure of the present invention.
FIG. 2 is a flow chart of the present invention for detecting an oil sample to be detected.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
With reference to fig. 1-2, a low-power-consumption portable multi-feature illegal cooking oil detector based on FPGA acceleration comprises an oil sample collection device and a data processing module, wherein the data processing module adopts an FPGA as an operation main body, the FPGA comprises a ROM module, a RAM module and a calculation module, and the FPGA performs operation analysis on collected data through a kNN algorithm; in addition oil appearance collection system includes high temperature resistant container, and the inside reaction reagent reaction tube that is provided with of high temperature resistant container, be provided with temperature sensor and heating pipe in the high temperature resistant container, be provided with conductivity peroxide value sensor in the reaction reagent reaction tube, further still include step motor, and step motor rocks the oil that awaits measuring through rotary disk and transfer line. It should be particularly noted that the target value of the oil sample data to be measured acquired by the oil sample acquisition device of the present invention is: conductivity value at 60 ℃, difference between conductivity values at 60 ℃ and 25 ℃, peroxide value at 25 ℃, and peroxide value difference between 60 ℃ and 25 ℃; and then, calculating Euclidean distances of target values acquired by the oil sample to be detected and all training samples in the ROM through a kNN algorithm using an approximate multiplier in the FPGA, wherein the Euclidean distances are specifically as follows:
in the formula, xiI-th characteristic data, y, representing the sample to be testedn，iThe ith characteristic data represents the nth training sample; FPGA minimum k dnD is equal to knAnd (4) counting the corresponding categories, and outputting the category with the highest occupation ratio as a detection result, so that whether the oil product to be detected is the illegal cooking oil can be judged.
In order to further illustrate the above embodiments, so that those skilled in the art can clearly understand the contents of the present invention, the following experimental description is provided.
6 different kinds of oil are selected, each kind of oil has different brands, and 15 kinds of original oil samples are used in total. In addition, edible oil and illegal cooking oil are mixed in order to meet the traditional detection index of part of illegal merchants; on the other hand, the oil sample to be measured may have participated in cooking, and various seasonings required for cooking appear inside. Therefore, for the practical situation, the number of the oil samples to be measured is increased on the basis of 15 original oil samples by the following method:
firstly, mixing 15 original oil samples pairwise according to the proportion of 8:2 to obtain 210 new oil samples and adding labels. All combinations (54 types) of the illegal cooking oil are specially explained, the labels are illegal cooking oil no matter the proportion of the illegal cooking oil, and other oil sample labels are used as labels according to 80 percent of oil samples;
respectively adding common Chinese meal seasonings such as salt, monosodium glutamate and chicken essence into the 15 original oil samples according to the same amount to obtain 225 new oil samples, and marking all the labels according to the labels of the oil samples before the seasonings are added;
and thirdly, adding common seasonings of Chinese food such as salt, chicken essence, monosodium glutamate and the like into the 210 oil samples according to the same amount to obtain 3150 new oil samples, wherein the label adding mode of the new oil samples is the same as that of 1.
Finally, 3600 oil samples are used as the data of the test under 6 different oil sample categories, and the quantity of all types of oil samples is shown in the table 1:
TABLE 1 number of individual oil samples in data set
The FPGA of the Intel Cyclone 10LP 10CL006ZU256I8G is selected, and the oil sample acquisition device and the data processing module are constructed according to the description in the embodiment, wherein the multiplier is an approximate multiplier realized by the user, and an IP core or a DSP module is not directly called. The resource occupation situation of realizing the kNN algorithm for illegal cooking oil detection by using an approximate multiplier in the FPGA is shown in a table 2:
TABLE 2 resource occupancy in FPGA
| Resource&Performance | Consumption |
| LUTs | 1,049 |
| Registers | 374 |
| Memory(Kb) | 19.20 |
| DSP(Embedded Multiplier) | 0 |
| Max Freq(MHz) | 200 |
| Latency(μs) | 4.775 |
| Power(mW) | 65.62 |
Simultaneously, a plurality of common embedded development platforms are selected: the results obtained by comparing the platform with the FPGA data processing module are as follows:
through the analysis of the time consumption, the power consumption and other indexes during the processing of the plurality of platform data, the operation of the kNN algorithm is accelerated by adopting the FPGA, and the oil sample data is analyzed and judged whether to be the illegal cooking oil or not through the kNN algorithm, so that the method has the advantages of high speed and low power consumption.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (2)
1. The utility model provides a portable multi-feature trench oil detector of low-power consumption based on FPGA accelerates, includes oil appearance collection system and data processing module, its characterized in that: the data processing module adopts an FPGA as an operation main body, the FPGA comprises a ROM module, an RAM module and a calculation module, and the interior of the FPGA carries out operation analysis on the acquired data through a kNN algorithm; the oil appearance collection system includes high temperature resistant container, and the inside reaction reagent reaction tube that is provided with of high temperature resistant container, be provided with temperature sensor and heating pipe in the high temperature resistant container, be provided with conductivity/peroxide value sensor in the reaction reagent reaction tube, the target value that oil appearance collection system gathered the oil appearance data that awaits measuring is: conductivity value at 60 ℃, difference between conductivity values at 60 ℃ and 25 ℃, peroxide value at 25 ℃, and peroxide value difference between 60 ℃ and 25 ℃; the method comprises the following steps that the target value acquired by the oil sample to be detected is subjected to Euclidean distance calculation by using a kNN algorithm of an approximate multiplier in an FPGA and all training samples in a ROM, and specifically comprises the following steps:
in the formula, xiI-th characteristic data, y, representing the sample to be testedn，iThe ith characteristic data represents the nth training sample; FPGA minimum k dnD is equal to knAnd (4) counting the corresponding categories, and outputting the category with the highest occupation ratio as a detection result, so that whether the oil product to be detected is the illegal cooking oil can be judged.
2. The FPGA acceleration-based low-power-consumption portable multi-feature illegal cooking oil detector as claimed in claim 1, characterized in that: the oil sample collection device further comprises a stepping motor, and the stepping motor shakes the oil to be detected through the rotating disk and the transmission rod.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110140478.4A CN112924652B (en) | 2021-02-02 | 2021-02-02 | FPGA (field programmable Gate array) acceleration-based portable low-power-consumption multi-feature illegal cooking oil detector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110140478.4A CN112924652B (en) | 2021-02-02 | 2021-02-02 | FPGA (field programmable Gate array) acceleration-based portable low-power-consumption multi-feature illegal cooking oil detector |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112924652A CN112924652A (en) | 2021-06-08 |
| CN112924652B true CN112924652B (en) | 2022-04-15 |
Family
ID=76169431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110140478.4A Active CN112924652B (en) | 2021-02-02 | 2021-02-02 | FPGA (field programmable Gate array) acceleration-based portable low-power-consumption multi-feature illegal cooking oil detector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112924652B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204405639U (en) * | 2014-12-22 | 2015-06-17 | 华东交通大学 | A kind of doping of the edible oil based on FPGA swill-cooked dirty oil detecting system |
| CN109871887A (en) * | 2019-01-29 | 2019-06-11 | 淮阴工学院 | A kind of novel trench oil detection method and detection device based on SVM |
| CN109884282A (en) * | 2019-01-29 | 2019-06-14 | 淮阴工学院 | Novel trench oil detection method and its detection system based on GRNN neural network |
-
2021
- 2021-02-02 CN CN202110140478.4A patent/CN112924652B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204405639U (en) * | 2014-12-22 | 2015-06-17 | 华东交通大学 | A kind of doping of the edible oil based on FPGA swill-cooked dirty oil detecting system |
| CN109871887A (en) * | 2019-01-29 | 2019-06-11 | 淮阴工学院 | A kind of novel trench oil detection method and detection device based on SVM |
| CN109884282A (en) * | 2019-01-29 | 2019-06-14 | 淮阴工学院 | Novel trench oil detection method and its detection system based on GRNN neural network |
Non-Patent Citations (4)
| Title |
|---|
| KNN算法在动物油鉴别区分中的应用研究;赵杨沄等;《计算机与应用化学》;20140728;第31卷(第7期);第859-864页 * |
| Stochastic modeling of the transient regime of an electronic nose for waste cooking oil classification;A.F.Siqueira等;《Journal of Food Engineering》;20171011;第221卷;第114-123页 * |
| 地沟油多指标快速筛选模式的研究;高卫东等;《中国食品工业》;20151130;第11卷;摘要 * |
| 基于多标记学习的食用植物油分类识别与掺伪检测研究;周海琴;《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅰ辑》;20180315(第3期);第16页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112924652A (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103518130B (en) | Organism gas-detecting device and organism gas detection method | |
| CN101936895B (en) | Near infrared spectroscopy analysis rapid detection method of rice freshness | |
| CN103235095B (en) | Water-injected meat detection method and device | |
| CN101452075B (en) | At-sea small target detecting method based on average period | |
| CN101493431A (en) | Method for detecting fresh degree of chicken meat by electronic nose | |
| CN104132896A (en) | Method for rapidly identifying adulterated meat | |
| CN202057355U (en) | Temperature/humidity sensor apparatus | |
| CN203745367U (en) | Intelligent pork freshness detector | |
| CN103792198A (en) | Intermediate infrared-near infrared correlation spectrum discriminating method for melamine-doped milk | |
| Li et al. | Quantitative analysis of fish meal freshness using an electronic nose combined with chemometric methods | |
| CN1804582A (en) | Method for identifying reductive milk in fresh milk and commodity milk by using near infrared spectrum | |
| CN105547915A (en) | Shell food freshness determination system based on density model and method of system | |
| CN102393376A (en) | Support vector regression-based near infrared spectroscopy for detecting content of multiple components of fish ball | |
| CN112098357B (en) | Strawberry sensory quality grade evaluation method based on near infrared spectrum | |
| CN112924652B (en) | FPGA (field programmable Gate array) acceleration-based portable low-power-consumption multi-feature illegal cooking oil detector | |
| CN110596080A (en) | Mineral element-based golden pomfret origin identification method | |
| CN103487398B (en) | A kind of analytical method of lysine fermentation liquor | |
| Zhang et al. | Rapid recognition of marine fish surimi by one-step discriminant analysis based on near-infrared diffuse reflectance spectroscopy | |
| CN109030755A (en) | The detection device and method of grain moisture content, mass of 1000 kernel and bulk density based on image processing techniques | |
| CN104849350A (en) | Method for identifying and classifying wood defects based on multiple features | |
| CN103529026A (en) | Detection method and kit of illegal cooking oil as well as production method of detection color comparison card | |
| CN107300535A (en) | The method of near-infrared quick detection organic fertilizer active constituent content | |
| CN103927438B (en) | Near-infrared wavelength Variable Selection based on successive projection algorithm | |
| CN106770861A (en) | The evaluation method of oil-filled transformer on-line monitoring availability of data | |
| CN105136881A (en) | Method for quickly detecting sausages adulterated with rotten pork |
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 |