WO2021057230A1 - 基于颜色识别的水质检测方法、装置、设备及存储介质 - Google Patents

基于颜色识别的水质检测方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2021057230A1
WO2021057230A1 PCT/CN2020/104563 CN2020104563W WO2021057230A1 WO 2021057230 A1 WO2021057230 A1 WO 2021057230A1 CN 2020104563 W CN2020104563 W CN 2020104563W WO 2021057230 A1 WO2021057230 A1 WO 2021057230A1
Authority
WO
WIPO (PCT)
Prior art keywords
water quality
rgb
color
quality detection
parameter
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.)
Ceased
Application number
PCT/CN2020/104563
Other languages
English (en)
French (fr)
Inventor
张京玲
聂湛然
吴英健
王天雷
欧涛
石霖
黄锦涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuyi University Fujian
Original Assignee
Wuyi University Fujian
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuyi University Fujian filed Critical Wuyi University Fujian
Publication of WO2021057230A1 publication Critical patent/WO2021057230A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

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
    • G01N33/18—Water
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/75—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated
    • G01N21/77—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator
    • G01N21/78—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator producing a change of colour
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/75—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated
    • G01N21/77—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator
    • G01N21/78—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator producing a change of colour
    • G01N21/80—Indicating pH value
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2201/00—Features of devices classified in G01N21/00
    • G01N2201/12—Circuits of general importance; Signal processing
    • G01N2201/129—Using chemometrical methods
    • G01N2201/1296—Using chemometrical methods using neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Definitions

  • the present invention relates to the technical field of water quality detection, in particular to a water quality detection method, device, equipment and storage medium based on color recognition.
  • the first is to manually use reagents to detect water quality
  • the second is to use electronic sensors to detect water quality.
  • the test results are obtained by manually taking water samples, adding reagents, and comparing the human eye with the standard colorimetric card.
  • the human eye vision is easily affected by other factors, it is very The color perception may be different, there may be errors in the judgment of the color, and multiple inspections are required every day, which is time-consuming and laborious.
  • the use of reagents to manually detect water quality needs to be compared with the colorimetric card, and the equipped colorimetric card has only a fixed color corresponding to a fixed water quality parameter value, and the water quality parameter level spans a large range, generally across a water quality parameter level. Unable to accurately read the water quality parameters.
  • the water quality is detected by an electronic sensor.
  • the sensor is expensive, has high detection accuracy, complicated operation, and high maintenance cost.
  • farmers need multiple sensors, and the overall cost is too high.
  • the present invention aims to solve at least one of the technical problems existing in the prior art.
  • the present invention proposes a water quality detection method, device, equipment and storage medium based on color recognition, which can fit a non-linear curve through the RBF neural network, and use the non-linear curve to establish a lightweight database of RGB-water quality parameters for color recognition. Ways to measure the water quality parameters, the measurement is more accurate.
  • a water quality detection method based on color recognition includes the following steps:
  • the color RGB value is compared with the lightweight database to obtain the water quality detection parameters of the water sample to be detected.
  • a water quality detection method based on color recognition has at least the following beneficial effects: this embodiment uses color recognition technology instead of human eyes to obtain color information with water quality parameter information; and uses reagent detection instead of current electronics.
  • the disadvantage of the sensor is expensive; the use of RBF neural network to fit the non-linear curve composed of RGB-water quality parameters, such as fitting the non-linear curve composed of RGB-PH value, breaks through the reading limit of the colorimetric card, and achieves accurate measurement of water quality parameters .
  • the method further includes the following steps:
  • the minimum absolute value method is used for the comparison.
  • the non-linear curve of RGB-water quality parameters is used to establish a lightweight database of RGB-water quality parameters, and the least absolute value method is used for data comparison to realize the offline and instant RGB-water quality parameter identification of single-chip microcomputer.
  • the collection unit is used to collect water quality parameter samples and RGB color parameter samples
  • a normalization unit configured to perform normalization processing on the water quality parameter sample and the RGB color parameter sample
  • Fitting curve unit used to use RBF neural network model to fit a nonlinear curve composed of RGB-water quality parameters
  • the database establishment unit is used to establish a lightweight database of RGB-water quality parameters using the non-linear curve of RGB-water quality parameters;
  • the acquiring unit is used to acquire the color RGB value of the water sample to be tested after reacting with the reagent;
  • the comparison unit is used to compare the color RGB value with the database to obtain the water quality detection parameters of the water sample to be tested.
  • the second aspect of the present invention further includes the following units:
  • the alarm unit is used to send an alarm message when the water quality detection parameter exceeds a preset water quality threshold.
  • the comparison unit is further configured to compare the color RGB value with the lightweight database by using the least absolute value method.
  • a water quality detection device based on color recognition includes at least one control processor and a memory for communicative connection with the at least one control processor; An instruction executed by the at least one control processor, the instruction being executed by the at least one control processor, so that the at least one control processor can execute the water quality detection method based on color recognition according to the first aspect described above.
  • a computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute the above-mentioned first aspect based on Water quality detection method for color recognition.
  • a computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer At the time, the computer is made to execute the water quality detection method based on color recognition as in the first aspect described above.
  • FIG. 1 is a schematic diagram of a water quality detection method based on color recognition according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a water quality detection device based on color recognition according to an embodiment of the present invention
  • Fig. 3 is a schematic diagram of a water quality detection device based on color recognition according to an embodiment of the present invention.
  • the water quality detection device 200 The water quality detection device 200, the control processor 210, and the memory 220 based on color recognition.
  • orientation description involved such as up, down, front, back, left, right, etc. indicates the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, but In order to facilitate the description of the present invention and simplify the description, it does not indicate or imply that the device or element referred to must have a specific orientation, be configured and operate in a specific orientation, and therefore cannot be understood as a limitation to the present invention.
  • a water quality detection method based on color recognition includes the following steps:
  • S1 Collect water quality parameter samples and RGB color parameter samples.
  • the water quality parameters that need to be tested include: PH value, turbidity, nitrite, ammonia nitrogen and dissolved oxygen.
  • PH value the traditional method of acid-base neutralization titration is used to configure the test solution with different pH values into the water quality detection device.
  • the pH value is in the range of 0-14, and 28 levels are selected at intervals of 0.5 pH value.
  • the configured PH test solution water quality detection device is used to obtain the corresponding RGB color parameters using the water quality detection device.
  • 10 groups were recorded with the same operation, and a total of 280 RGB-PH value samples were obtained.
  • RBF neural network model to fit a nonlinear curve composed of RGB-water quality parameters.
  • the trial and error method is used to continuously modify each parameter, and finally the corresponding relationship between the red, green, and blue channels of the RGB color parameter and the water quality parameter PH value is obtained, and the RGB- The PH value neural model fits the nonlinear curve composed of RGB-PH value. And use the same method to fit the nonlinear curve of different RGB-water quality parameters.
  • S4 Use the non-linear curve of RGB-water quality parameters to build a lightweight database of RGB-water quality parameters. Discrete the nonlinear curve with a ph precision of 0.01 to obtain a data table of a set of rgb corresponding to a ph value, and build a lightweight database of RGB-PH values. And use the same method to obtain different RGB-water quality parameter lightweight databases.
  • S5 Write the lightweight database into the Flash of the single-chip microcomputer; it is convenient to perform off-line and instant RGB-water quality parameter identification.
  • a water quality detection method based on color recognition has at least the following beneficial effects: this embodiment uses color recognition technology instead of human eyes to obtain color information with water quality parameter information; and uses reagent detection instead of current electronics.
  • the disadvantage of the sensor is expensive; the use of RBF neural network to fit the non-linear curve composed of RGB-water quality parameters, such as fitting the non-linear curve composed of RGB-PH value, breaks through the reading limit of the colorimetric card, and achieves accurate measurement of water quality parameters .
  • the non-linear curve of RGB-water quality parameters is used to establish a lightweight database of RGB-water quality parameters, and the least absolute value method is used for data comparison to realize the offline and instant RGB-water quality parameter identification of single-chip microcomputer.
  • the method further includes the following steps:
  • a water quality detection device 100 based on color recognition includes the following units:
  • the collection unit 110 is used to collect water quality parameter samples and RGB color parameter samples
  • the normalization unit 120 is configured to perform normalization processing on the water quality parameter samples and the RGB color parameter samples;
  • the curve fitting unit 130 is configured to use the RBF neural network model to fit a nonlinear curve composed of RGB-water quality parameters;
  • the database establishing unit 140 is used to establish a lightweight database of RGB-water quality parameters by using the non-linear curve of RGB-water quality parameters;
  • the obtaining unit 150 is configured to obtain the color RGB value of the water sample to be detected after the reaction with the reagent;
  • the comparison unit 160 is configured to compare the color RGB value with the lightweight database to obtain the water quality detection parameters of the water sample to be detected.
  • the second aspect of the present invention further includes the following units:
  • the alarm unit 170 is configured to send an alarm message when the water quality detection parameter exceeds a preset water quality threshold.
  • the comparison unit 160 is further configured to compare the color RGB value with the lightweight database by using the least absolute value method.
  • a water quality detection device 200 based on color recognition can be any type of smart terminal, such as a mobile phone, a tablet computer, or a personal computer. Wait.
  • the water quality detection device 200 based on color recognition includes: one or more control processors 210 and a memory 220.
  • one control processor 210 is taken as an example.
  • control processor 210 and the memory 220 may be connected through a bus or in other ways.
  • connection through a bus is taken as an example.
  • the memory 220 can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as those corresponding to the water quality detection method based on color recognition in the embodiment of the present invention
  • Program instructions/modules for example, units 110-170 shown in Figure 2.
  • the control processor 210 executes various functional applications and data processing of the water quality detection device 100 based on color recognition by running the non-transitory software programs, instructions, and modules stored in the memory 220, that is, to implement the color-based Recognized water quality testing methods.
  • the memory 220 may include a storage program area and a storage data area.
  • the storage program area may store an operating system and an application program required by at least one function; the storage data area may store information created based on the use of the water quality detection device 100 based on color recognition. Data etc.
  • the memory 220 may include a high-speed random access memory 220, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid state storage devices.
  • the storage 220 may optionally include a storage 220 remotely provided with respect to the control processor 210, and these remote storages 220 may be connected to the water quality detection device 200 based on color recognition through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the one or more modules are stored in the memory 220, and when executed by the one or more control processors 210, the water quality detection method based on color recognition in the above method embodiment is executed, for example, the above description is executed
  • the method steps S1 to S8 in FIG. 1 realize the functions of the units 110-170 in FIG. 2.
  • a computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more control processors 210, for example, Executed by one control processor 210 in FIG. 3, the above-mentioned one or more control processors 210 may execute the water quality detection method based on color recognition in the above-mentioned method embodiment, for example, execute the above-described method steps in FIG. 1 S1 to S8 realize the functions of units 110-170 in FIG. 2.
  • the device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • each implementation manner can be implemented by means of software plus a general hardware platform.
  • All or part of the processes in the methods of the above embodiments can be implemented by computer programs instructing relevant hardware.
  • the programs can be stored in a computer readable storage medium. At this time, it may include the flow of the embodiment of the above-mentioned method.
  • the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.
  • a computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer At the time, the computer is made to execute the water quality detection method based on color recognition as in the first aspect described above.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biochemistry (AREA)
  • Analytical Chemistry (AREA)
  • Theoretical Computer Science (AREA)
  • Plasma & Fusion (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

本发明公开了基于颜色识别的水质检测方法、装置、设备及存储介质，包括：采集水质参数样本和RGB颜色参数样本；对水质参数样本和RGB颜色参数样本归一化处理；使用RBF神经网络模型拟合RGB-PH值构成非线性曲线；使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库；获取待检测水样与试剂反应后颜色RGB值；将颜色RGB值与数据库进行比对，获得待检测水样的水质检测参数。采用颜色识别技术来代替人眼获取带有水质参数信息的颜色信息；使用试剂检测代替当前电子传感器的价格昂贵的缺点；使用RBF神经网络拟合RGB-水质参数构成非线性曲线，突破比色卡读数限制，精确测量水质参数；使用最小绝对值法进行数据比对，实现单片机脱机离线式和即时性RGB-水质参数识别。

Description

基于颜色识别的水质检测方法、装置、设备及存储介质 技术领域
本发明涉及水质检测技术领域，特别涉及一种基于颜色识别的水质检测方法、装置、设备及存储介质。
背景技术
目前，淡水养殖业每天都要对水质进行定时检测，一般需要对PH值、浊度、亚硝酸盐、氨氮和溶解氧等参数进行检测，根据检测结果来调节水质，从而保证养殖物的正常生长。
目前主要用于淡水养殖水质检测的方法有两种：第一种是人工使用试剂来检测水质，第二种是使用电子传感器来检测水质。
对于上述第一种方式，通过人工取水样，滴加试剂，再通过人眼与标准比色卡对比得出检测结果，但由于人眼视觉易受其它因素影响，对在不同环境下的同一颜色感觉可能不同，对颜色的判断可能会有误差，且每天都需要进行多次检测，费时又费力。另外，使用试剂来人工检测水质需要和比色卡进行比对，而配带的比色卡只有固定的颜色对应固定的水质参数值，且水质参数等级跨越较大，一般跨越一个水质参数等级，无法做到精确读取水质参数。
对于上述第二种方式，通过电子传感器检测水质，传感器的价格昂贵，检测精度高，操作较复杂，维护成本也很高，且养殖户需要多种传感器，总体一套下来成本过于高昂。
发明内容
本发明旨在至少解决现有技术中存在的技术问题之一。为此，本发明提出一种基于颜色识别的水质检测方法、装置、设备及存储介质，能够通过RBF神经网络拟合非线性曲线，使用非线性曲线建立RGB-水质参数轻量数据库进行颜色识别的方式来测量到水质参数，测量更加精确。
根据本发明的第一方面实施例的一种基于颜色识别的水质检测方法，包括以 下步骤：
采集水质参数样本和RGB颜色参数样本；
对所述水质参数样本和所述RGB颜色参数样本进行归一化处理；
使用RBF神经网络模型拟合RGB-水质参数构成的非线性曲线；
使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库；
获取待检测水样与试剂反应后的颜色RGB值；
将所述颜色RGB值与所述轻量数据库进行比对，获得待检测水样的水质检测参数。
根据本发明实施例的一种基于颜色识别的水质检测方法，至少具有如下有益效果：本实施例采用颜色识别技术来代替人眼进行获取带有水质参数信息的颜色信息；使用试剂检测代替当前电子传感器的价格昂贵的缺点；使用RBF神经网络拟合RGB-水质参数构成的非线性曲线，例如拟合RGB-PH值构成的非线性曲线，突破比色卡的读数限制，做到精确测量水质参数。
根据本发明的第一方面的一些实施例，还包括以下步骤：
当所述水质检测参数超过预设的水质阈值，则发出警报信息。
根据本发明的第一方面的一些实施例，所述将所述颜色RGB值与所述轻量数据库进行比对时，采用最小绝对值法进行比对。使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库，使用最小绝对值法进行数据比对，实现单片机脱机离线式和即时性RGB-水质参数识别。
根据本发明的第二方面实施例的一种基于颜色识别的水质检测装置，包括以下单元：
采集单元，用于采集水质参数样本和RGB颜色参数样本；
归一化单元，用于对所述水质参数样本和所述RGB颜色参数样本进行归一化处理；
拟合曲线单元，用于使用RBF神经网络模型拟合RGB-水质参数构成的非线性曲线；
数据库建立单元，用于使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库；
获取单元，用于获取待检测水样与试剂反应后的颜色RGB值；
比对单元，用于将所述颜色RGB值与所述数据库进行比对，获得待检测水样的水质检测参数。
根据本发明的第二方面的一些实施例，还包括以下单元：
警报单元，用于当所述水质检测参数超过预设的水质阈值，则发出警报信息。
根据本发明的第二方面的一些实施例，所述比对单元，还用于采用最小绝对值法将所述颜色RGB值与所述轻量数据库进行比对。
根据本发明的第三方面实施例的一种基于颜色识别的水质检测设备，包括至少一个控制处理器和用于与所述至少一个控制处理器通信连接的存储器；所述存储器存储有可被所述至少一个控制处理器执行的指令，所述指令被所述至少一个控制处理器执行，以使所述至少一个控制处理器能够执行如上述第一方面的基于颜色识别的水质检测方法。
根据本发明的第四方面实施例的一种计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使计算机执行如上述第一方面的基于颜色识别的水质检测方法。
根据本发明的第五方面实施例的一种计算机程序产品，所述计算机程序产品包括存储在计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使计算机执行如上述第一方面的基于颜色识别的水质检测方法。
本发明的附加方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。
附图说明
本发明的上述和/或附加的方面和优点从结合下面附图对实施例的描述中将变得明显和容易理解，其中：
图1为本发明实施例的一种基于颜色识别的水质检测方法的示意图；
图2为本发明实施例的一种基于颜色识别的水质检测装置的示意图；
图3为本发明实施例的一种基于颜色识别的水质检测设备的示意图。
附图标记：
基于颜色识别的水质检测装置100、采集单元110、归一化单元120、拟合曲线单元130、数据库建立单元140、获取单元150、比对单元160、警报单元170；
基于颜色识别的水质检测设备200、控制处理器210、存储器220。
具体实施方式
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本实用新型，而不能理解为对本实用新型的限制。
在本发明的描述中，需要理解的是，涉及到方位描述，例如上、下、前、后、左、右等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。
在本发明的描述中，若干的含义是一个或者多个，多个的含义是两个以上，大于、小于、超过等理解为不包括本数，以上、以下、以内等理解为包括本数。如果有描述到第一、第二只是用于区分技术特征为目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量或者隐含指明所指示的技术特征的先后关系。
本发明的描述中，除非另有明确的限定，设置、安装、连接等词语应做广义理解，所属技术领域技术人员可以结合技术方案的具体内容合理确定上述词语在本发明中的具体含义。
参照图1，根据本发明的第一方面实施例的一种基于颜色识别的水质检测方 法，包括以下步骤：
S1：采集水质参数样本和RGB颜色参数样本。需要检测的水质参数包括：PH值、浊度、亚硝酸盐、氨氮和溶解氧等。以PH值为例子，使用传统的酸碱中和滴定的方法配置不同PH值的试液放入水质检测装置，PH值的范围为0-14，以0.5个PH值为间隔选取28个等级的PH值，把配置好的PH试液水质检测装置，使用水质检测装置得到相应RGB颜色参数。为了减少实验的误差和偶然性，以同样的操作记录10组，共得到280个RGB-PH值样本。
S2：对所述水质参数样本和所述RGB颜色参数样本进行归一化处理。对于RGB颜色参数样本值，通过除以255获得0～1之间标准化颜色值；对于水质参数PH样本值，通过除以14获得0～1之间标准化颜色值。
S3：使用RBF神经网络模型拟合RGB-水质参数构成的非线性曲线。选定输入节点为3个，分别对应RGB颜色参数的三个通道；中间隐藏层选取12个隐藏节点；输出节点为1个，对应水质参数PH值。利用RBF神经网络，通过对损失函数进行梯度下降，使用试凑法不断修正每个参数，最终获得RGB颜色参数的红、绿、蓝的三个通道与水质参数PH值的对应关系，得到RGB-PH值神经模型，拟合出RGB-PH值构成的非线性曲线。并用同样的方法分别拟合不同的RGB-水质参数的非线性曲线。
S4：使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库。把非线性曲线按0.01的ph值精度进行离散处理，得到一组rgb对应一个ph值的数据表，建立RGB-PH值轻量数据库。并用同样的方法分别获得不同的RGB-水质参数轻量数据库。
S5：把所述轻量数据库写入单片机的Flash；方便进行脱机离线式和即时性RGB-水质参数识别。
S6：获取待检测水样与试剂反应后的颜色RGB值。
S7：将所述颜色RGB值与所述轻量数据库使用最小绝对值法进行比对，获得待检测水样的水质检测参数。
根据本发明实施例的一种基于颜色识别的水质检测方法，至少具有如下有益效果：本实施例采用颜色识别技术来代替人眼进行获取带有水质参数信息的颜色信息；使用试剂检测代替当前电子传感器的价格昂贵的缺点；使用RBF神经网络拟合RGB-水质参数构成的非线性曲线，例如拟合RGB-PH值构成的非线性曲线，突破比色卡的读数限制，做到精确测量水质参数。使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库，使用最小绝对值法进行数据比对，实现单片机脱机离线式和即时性RGB-水质参数识别。
根据本发明的第一方面的一些实施例，还包括以下步骤：
S8：当所述水质检测参数超过预设的水质阈值，则发出警报信息。
参照图2，根据本发明的第二方面实施例的一种基于颜色识别的水质检测装置100，包括以下单元：
采集单元110，用于采集水质参数样本和RGB颜色参数样本；
归一化单元120，用于对所述水质参数样本和所述RGB颜色参数样本进行归一化处理；
拟合曲线单元130，用于使用RBF神经网络模型拟合RGB-水质参数构成的非线性曲线；
数据库建立单元140，用于使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库；
获取单元150，用于获取待检测水样与试剂反应后的颜色RGB值；
比对单元160，用于将所述颜色RGB值与所述轻量数据库进行比对，获得待检测水样的水质检测参数。
需要说明的是，由于本实施例中的基于颜色识别的水质检测装置100与上述的基于颜色识别的水质检测方法基于相同的发明构思，因此，方法实施例中的相应内容同样适用于本装置实施例，此处不再详述。
根据本发明的第二方面的一些实施例，还包括以下单元：
警报单元170，用于当所述水质检测参数超过预设的水质阈值，则发出警报 信息。
根据本发明的第二方面的一些实施例，所述比对单元160，还用于采用最小绝对值法将所述颜色RGB值与所述轻量数据库进行比对。
参照图3，根据本发明的第三方面实施例的一种基于颜色识别的水质检测设备200，该基于颜色识别的水质检测设备200可以是任意类型的智能终端，例如手机、平板电脑、个人计算机等。
具体地，该基于颜色识别的水质检测设备200包括：一个或多个控制处理器210和存储器220，图3中以一个控制处理器210为例。
控制处理器210和存储器220可以通过总线或者其他方式连接，图3中以通过总线连接为例。
存储器220作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序、非暂态性计算机可执行程序以及模块，如本发明实施例中的基于颜色识别的水质检测方法对应的程序指令/模块，例如，图2中所示的单元110-170。控制处理器210通过运行存储在存储器220中的非暂态软件程序、指令以及模块，从而执行基于颜色识别的水质检测装置100的各种功能应用以及数据处理，即实现上述方法实施例的基于颜色识别的水质检测方法。
存储器220可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据基于颜色识别的水质检测装置100的使用所创建的数据等。此外，存储器220可以包括高速随机存取存储器220，还可以包括非暂态存储器，例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施方式中，存储器220可选包括相对于控制处理器210远程设置的存储器220，这些远程存储器220可以通过网络连接至该基于颜色识别的水质检测设备200。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述一个或者多个模块存储在所述存储器220中，当被所述一个或者多个控制处理器210执行时，执行上述方法实施例中的基于颜色识别的水质检测方法， 例如，执行以上描述的图1中的方法步骤S1至S8，实现图2中的单元110-170的功能。
根据本发明的第四方面实施例的一种计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个控制处理器210执行，例如，被图3中的一个控制处理器210执行，可使得上述一个或多个控制处理器210执行上述方法实施例中的基于颜色识别的水质检测方法，例如，执行以上描述的图1中的方法步骤S1至S8，实现图2中的单元110-170的功能。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施方式的描述，本领域技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现。本领域技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(ReadOnly Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
根据本发明的第五方面实施例的一种计算机程序产品，所述计算机程序产品包括存储在计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使计算机执行如上述第一方面的基于颜色识别的水质检测方法。
上面结合附图对本发明实施例作了详细说明，但是本发明不限于上述实施例，在所述技术领域普通技术人员所具备的知识范围内，还可以在不脱离本发明宗旨的前提下作出各种变化。

Claims (9)

  1. 一种基于颜色识别的水质检测方法，其特征在于，包括以下步骤：
    采集水质参数样本和RGB颜色参数样本；
    对所述水质参数样本和所述RGB颜色参数样本进行归一化处理；
    使用RBF神经网络模型拟合RGB-水质参数构成的非线性曲线；
    使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库；
    获取待检测水样与试剂反应后的颜色RGB值；
    将所述颜色RGB值与所述轻量数据库进行比对，获得待检测水样的水质检测参数。
  2. 根据权利要求1所述的基于颜色识别的水质检测方法，其特征在于，还包括以下步骤：
    当所述水质检测参数超过预设的水质阈值，则发出警报信息。
  3. 根据权利要求1所述的基于颜色识别的水质检测方法，其特征在于：所述将所述颜色RGB值与所述轻量数据库进行比对时，采用最小绝对值法进行比对。
  4. 一种基于颜色识别的水质检测装置，其特征在于，包括以下单元：
    采集单元，用于采集水质参数样本和RGB颜色参数样本；
    归一化单元，用于对所述水质参数样本和所述RGB颜色参数样本进行归一化处理；
    拟合曲线单元，用于使用RBF神经网络模型拟合RGB-水质参数构成的非线性曲线；
    数据库建立单元，用于使用RGB-水质参数的非线性曲线建立RGB-水质参数轻量数据库；
    获取单元，用于获取待检测水样与试剂反应后的颜色RGB值；
    比对单元，用于将所述颜色RGB值与所述轻量数据库进行比对，获得待检测水样的水质检测参数。
  5. 根据权利要求4所述的基于颜色识别的水质检测装置，其特征在于，还包括以下单元：
    警报单元，用于当所述水质检测参数超过预设的水质阈值，则发出警报信息。
  6. 根据权利要求4所述的基于颜色识别的水质检测装置，其特征在于：
    所述比对单元，还用于采用最小绝对值法将所述颜色RGB值与所述轻量数据库进行比对。
  7. 一种基于颜色识别的水质检测设备，其特征在于：包括至少一个控制处理器和用于与所述至少一个控制处理器通信连接的存储器；所述存储器存储有可被所述至少一个控制处理器执行的指令，所述指令被所述至少一个控制处理器执行，以使所述至少一个控制处理器能够执行如权利要求1至3任一项所述的基于颜色识别的水质检测方法。
  8. 一种计算机可读存储介质，其特征在于：所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使计算机执行如权利要求1至3任一项所述的基于颜色识别的水质检测方法。
  9. 一种计算机程序产品，其特征在于：所述计算机程序产品包括存储在计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使计算机执行如权利要求1至3任一项所述的基于颜色识别的水质检测方法。
PCT/CN2020/104563 2019-09-26 2020-07-24 基于颜色识别的水质检测方法、装置、设备及存储介质 Ceased WO2021057230A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910916788.3A CN110579471A (zh) 2019-09-26 2019-09-26 基于颜色识别的水质检测方法、装置、设备及存储介质
CN201910916788.3 2019-09-26

Publications (1)

Publication Number Publication Date
WO2021057230A1 true WO2021057230A1 (zh) 2021-04-01

Family

ID=68813731

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/104563 Ceased WO2021057230A1 (zh) 2019-09-26 2020-07-24 基于颜色识别的水质检测方法、装置、设备及存储介质

Country Status (3)

Country Link
US (1) US20210096121A1 (zh)
CN (1) CN110579471A (zh)
WO (1) WO2021057230A1 (zh)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110579471A (zh) * 2019-09-26 2019-12-17 五邑大学 基于颜色识别的水质检测方法、装置、设备及存储介质
CN111539477B (zh) * 2020-04-26 2023-06-27 中海云科(北京)科技有限公司 水质监测管理方法、装置、服务器及可读存储介质
CN112595678B (zh) * 2020-11-26 2023-06-13 中国科学院苏州生物医学工程技术研究所 基于rgb的图像比色的浓度测定方法、系统、存储介质
CN112858278B (zh) * 2021-02-03 2021-11-05 杭州环析检测科技有限公司 一种全自动水质POPs检测装置
CN115508276A (zh) * 2021-06-23 2022-12-23 中国石油化工股份有限公司 水质检测方法、检测装置及检测系统
US20240288414A1 (en) * 2021-06-23 2024-08-29 China Petroleum & Chemical Corporation Water quality testing method and water quality testing apparatus
CN113820305A (zh) * 2021-09-30 2021-12-21 盈奇科技（深圳）有限公司 一种总磷检测设备及方法
CN113915532B (zh) * 2021-10-26 2023-11-03 浙江华章科技有限公司 一种集装模块化流量检测设备
CN114002217B (zh) * 2021-11-02 2024-05-14 苏州国科医工科技发展(集团)有限公司 一种通过ph试纸图像读取ph值的方法
CN113901965B (zh) * 2021-12-07 2022-05-24 广东省科学院智能制造研究所 分液中的液体状态识别方法及分液系统
CN115684516B (zh) * 2022-08-29 2024-03-26 邯郸市亿润工程咨询有限公司 一种水利工程污水处理检测方法、装置、电子设备及介质
CN115661081B (zh) * 2022-10-28 2023-11-14 江苏中农物联网科技有限公司 基于图像处理的水产养殖自动控制换水方法
CN115598124B (zh) * 2022-11-03 2023-07-18 淮北师范大学 颜色去卷积水质检测方法
CN115656417B (zh) * 2022-11-04 2025-10-28 湖南洪康新材料科技有限公司 滴定颜色判定的方法及颜色滴定装置
CN116008197B (zh) * 2023-03-28 2023-06-02 矿冶科技集团有限公司 镍、钴离子浓度在线分析仪器及其分析方法
CN116298167A (zh) * 2023-05-15 2023-06-23 胜利星科检测技术(山东)有限公司 一种油田在线水质检测系统
CN116642879A (zh) * 2023-07-12 2023-08-25 马然 一种水质硬度自动检测装置及检测方法
CN117269444B (zh) * 2023-09-18 2025-10-31 贵州大学 水质检测方法、装置和设备
CN118817616B (zh) * 2024-06-25 2025-02-07 马鞍山市桓泰环保设备有限公司 一种基于数据分析的污水在线监测系统
CN121170610B (zh) * 2025-11-20 2026-02-13 中国铁塔股份有限公司四川省分公司 一种基于时空因果和流形学习的水体颜色识别回归方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20020087802A (ko) * 2001-05-16 2002-11-23 김민기 수질과 대기질의 모니터링 및 분석시스템
CN1688880A (zh) * 2002-09-19 2005-10-26 易斯提克株式会社 使用图像的水质测定设备和方法
CN102680469A (zh) * 2012-06-07 2012-09-19 江南大学 家庭饮用水水质多参数快速检测方法及检测设备
CN202693478U (zh) * 2012-06-07 2013-01-23 江南大学 家庭饮用水水质多参数快速检测设备
CN104700153A (zh) * 2014-12-05 2015-06-10 江南大学 基于模拟退火优化BP神经网络的pH值预测方法
CN107609581A (zh) * 2017-08-31 2018-01-19 山东师范大学 一种无接触pH试纸读值装置及其方法
CN109377490A (zh) * 2018-10-31 2019-02-22 深圳市长隆科技有限公司 水质检测方法、装置及计算机终端
CN110579471A (zh) * 2019-09-26 2019-12-17 五邑大学 基于颜色识别的水质检测方法、装置、设备及存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102841060B (zh) * 2012-09-29 2015-01-07 安徽工业大学 一种在线水质快速检测系统
CN105115911B (zh) * 2015-09-18 2018-02-09 清华大学 一种水质检测方法及其专用微流控芯片
KR101923815B1 (ko) * 2017-03-22 2018-11-29 국방과학연구소 색도 측정을 이용한 미생물 농도 측정 방법
CN110222698B (zh) * 2019-05-24 2020-12-29 广东沁华智能环境技术股份有限公司 一种基于色彩信息处理进行水质分析的方法及系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20020087802A (ko) * 2001-05-16 2002-11-23 김민기 수질과 대기질의 모니터링 및 분석시스템
CN1688880A (zh) * 2002-09-19 2005-10-26 易斯提克株式会社 使用图像的水质测定设备和方法
CN102680469A (zh) * 2012-06-07 2012-09-19 江南大学 家庭饮用水水质多参数快速检测方法及检测设备
CN202693478U (zh) * 2012-06-07 2013-01-23 江南大学 家庭饮用水水质多参数快速检测设备
CN104700153A (zh) * 2014-12-05 2015-06-10 江南大学 基于模拟退火优化BP神经网络的pH值预测方法
CN107609581A (zh) * 2017-08-31 2018-01-19 山东师范大学 一种无接触pH试纸读值装置及其方法
CN109377490A (zh) * 2018-10-31 2019-02-22 深圳市长隆科技有限公司 水质检测方法、装置及计算机终端
CN110579471A (zh) * 2019-09-26 2019-12-17 五邑大学 基于颜色识别的水质检测方法、装置、设备及存储介质

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
BAO XIN-YUE, LIU SHENG, SONG WAN-GAN, GAO HONG-WEN: "Using a PC camera to determine the concentration of nitrite, ammonia nitrogen, sulfide, phosphate, and copper in water", ANALYTICAL METHODS, ROYAL SOCIETY OF CHEMISTRY, GBR, vol. 10, no. 18, 1 January 2018 (2018-01-01), GBR, pages 2096 - 2101, XP055793826, ISSN: 1759-9660, DOI: 10.1039/C8AY00312B *
LIHUA YOU, JINGJING WU, YAO WANG, SHUJUAN SONG: "Optimized BP Neural Network Based on Simulated Annealing Algorithm for pH Value Prediction", CHINESE JOURNAL OF SENSORS AND ACTUATORS, vol. 27, no. 12, 1 December 2014 (2014-12-01), pages 1643 - 1648, XP055793819, DOI: 10.3969 /j.issn.1004-1699.2014.12.011 *
YONGCHENG LIN, CHAOYANG LIN, ZHIFENG LIANG, YONGSHENG LUO, JINGLING ZHANG: "Freshwater Aquaculture Monitoring System based on the Technology of the Internet of Things", ELECTRICAL ENGINEERING, 1 January 2015 (2015-01-01), pages 59 - 62, XP055793825, ISSN: 1673-3800 *
ZHANG BO: "PH Value and Chloirde Ion Detection System Research Based on Color Sensing", CHINESE MASTER'S THESES FULL-TEXT DATABASE, SHAANXI NORMAL UNIVERSITY, CN, 1 June 2013 (2013-06-01), CN, XP055793823, ISSN: 1674-0246 *

Also Published As

Publication number Publication date
US20210096121A1 (en) 2021-04-01
CN110579471A (zh) 2019-12-17

Similar Documents

Publication Publication Date Title
WO2021057230A1 (zh) 基于颜色识别的水质检测方法、装置、设备及存储介质
CN103090899B (zh) 传感器检测装置及检测方法
US20100063762A1 (en) Method for operating a measuring point
CN107589391B (zh) 一种检测电能计量装置整体误差的方法、装置和系统
CN109443553A (zh) 红外测温方法、装置、系统及计算机可读存储介质
CN105223196A (zh) 一种基于智能终端的尿液分析方法
CN107478382A (zh) 一种压力仪表自动检测装置及其检测方法
CN109784390B (zh) 一种人工智能嗅觉动态响应图谱气体检测识别方法
CN103487210A (zh) 一种智能压力仪表全自动检定调试方法及仪器
CN208239436U (zh) 一种水质氨氮检测系统
CN111998918A (zh) 一种误差校正方法、误差校正装置及流量传感系统
CN106557652A (zh) 判断样品检测数据可疑值的方法
CN105675171A (zh) 基于云服务器的恒温箱现场校准装置及方法
CN115792444A (zh) 干式电抗器状态评估方法、装置、系统和计算机设备
CN103529185A (zh) 一种智能型多参数在线水质分析仪
CN114689159A (zh) 用于计量设备数据管理的系统、方法、电子设备及介质
CN114627307A (zh) 一种燃气表智能识别检测方法、系统和可读存储介质
CN109682858A (zh) 一种利用气体传感器实时检测气体浓度的方法
CN111561968A (zh) 基于传感器的环境参数检测方法、装置及数据处理设备
CN104596578A (zh) 一种基于移动终端的外接件巡检方法、系统及移动终端
CN210664551U (zh) 一种防止改仪器标定值作弊的装置
US20240426880A1 (en) Method for monitoring the power consumption of a measuring point, as well as measuring point and process control system
CN106950480A (zh) 电力设备局部放电在线定性检测方法、系统、及设备
CN205982554U (zh) 一种dsp芯片批量检测装置
CN113869403A (zh) 基于便携式测温装置的温度检测方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20867115

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20867115

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20867115

Country of ref document: EP

Kind code of ref document: A1