CN110286103A - A kind of surrounding medium method for sensing and device - Google Patents

A kind of surrounding medium method for sensing and device Download PDF

Info

Publication number
CN110286103A
CN110286103A CN201910381052.0A CN201910381052A CN110286103A CN 110286103 A CN110286103 A CN 110286103A CN 201910381052 A CN201910381052 A CN 201910381052A CN 110286103 A CN110286103 A CN 110286103A
Authority
CN
China
Prior art keywords
signal
blue light
light signals
medium
infrared
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.)
Granted
Application number
CN201910381052.0A
Other languages
Chinese (zh)
Other versions
CN110286103B (en
Inventor
宋佳城
万跃敏
靳东风
张男
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.)
TANDA TECHNOLOGY Co Ltd
Original Assignee
TANDA TECHNOLOGY Co Ltd
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 TANDA TECHNOLOGY Co Ltd filed Critical TANDA TECHNOLOGY Co Ltd
Priority to CN201910381052.0A priority Critical patent/CN110286103B/en
Publication of CN110286103A publication Critical patent/CN110286103A/en
Application granted granted Critical
Publication of CN110286103B publication Critical patent/CN110286103B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • 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
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/47—Scattering, i.e. diffuse reflection
    • G01N21/49—Scattering, i.e. diffuse reflection within a body or fluid
    • G01N21/53—Scattering, i.e. diffuse reflection within a body or fluid within a flowing fluid, e.g. smoke

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The application is suitable for fire-fighting domain, provides surrounding medium method for sensing and device, comprising: by the infrared signal and blue light signals that receive the predeterminated frequency across current environment medium；The infrared signal received and the blue light signals are converted into the analog signal of predetermined amplitude；Signal sampling and quantization are carried out to the analog signal, obtain quantized data；The quantized data is inputted preparatory trained disaggregated model to identify, obtains the media type of the current environment medium.The present embodiment is according to the optical scattering principle of particle, in two dimensions of dimensional orientation and lambda1-wavelength, the surrounding medium detection method based on two-way double spectrum is devised, efficient algorithm for pattern recognition is cooperated, can effectively and precisely identify the surrounding medium in current environment.

Description

A kind of surrounding medium method for sensing and device
Technical field
The application belongs to fire-fighting domain more particularly to a kind of surrounding medium method for sensing and device.
Background technique
Existing surrounding medium sensing mode is generally basede on infrared light scattering principle, composition mainly include optical dark room, Circuit board, infrared transmitting tube and reception pipe etc..This surrounding medium sensing mode is easy the interference by interference sources such as vapor, It is insensitive to the response of many organic combustibles, therefore surrounding medium is caused to sense blunt problem.
Summary of the invention
In view of this, the embodiment of the present application provides surrounding medium method for sensing and device, with solve in the prior art this Kind surrounding medium sensing mode is easy the source interference that is interfered, and insensitive to the response of many organic combustibles, therefore causes Surrounding medium senses blunt problem.
The first aspect of the embodiment of the present application provides a kind of surrounding medium method for sensing, comprising:
Receive the infrared signal and blue light signals of the predeterminated frequency across current environment medium；
The infrared signal received and the blue light signals are converted into the analog signal of predetermined amplitude；The simulation Signal includes the corresponding analog signal of the infrared signal, the corresponding analog signal of the blue light signals；
Signal sampling and quantization are carried out to the analog signal, obtain quantized data；The quantized data includes described red The corresponding quantized data of external signal, the corresponding quantized data of the blue light signals；
The quantized data is inputted preparatory trained disaggregated model to identify, obtains the current environment medium Media type.
The second aspect of the embodiment of the present application provides a kind of surrounding medium sensing device, comprising:
Receiving unit, for receiving the infrared signal and blue light signals of the predeterminated frequency across current environment medium；
Converting unit, for the infrared signal received and the blue light signals to be converted into the simulation of predetermined amplitude Signal；The analog signal includes the corresponding analog signal of the infrared signal, the corresponding analog signal of the blue light signals；
Quantifying unit obtains quantized data for carrying out signal sampling and quantization to the analog signal；The quantization number According to including the corresponding quantized data of the infrared signal, the corresponding quantized data of the blue light signals；
Recognition unit is identified for the quantized data to be inputted trained disaggregated model in advance, is obtained described The media type of current environment medium.
The third aspect of the embodiment of the present application provides a kind of surrounding medium sensing device, comprising: processor, input are set Standby, output equipment and memory, the processor, input equipment, output equipment and memory are connected with each other, wherein described to deposit Reservoir is used to store the computer program for supporting device to execute the above method, and the computer program includes program instruction, described Processor is configured for calling described program instruction, the method for executing above-mentioned first aspect.
The fourth aspect of the embodiment of the present application provides a kind of computer readable storage medium, the computer storage medium It is stored with computer program, the computer program includes program instruction, and described program instruction makes institute when being executed by a processor State the method that processor executes above-mentioned first aspect.
Existing beneficial effect is the embodiment of the present application compared with prior art: by receiving across current environment medium The infrared signal and blue light signals of predeterminated frequency；The infrared signal received and the blue light signals are converted into default width The analog signal of degree；Signal sampling and quantization are carried out to the analog signal, obtain quantized data；The quantized data is inputted Preparatory trained disaggregated model is identified, the media type of the current environment medium is obtained.The present embodiment is according to particle Optical scattering principle devise environment based on two-way double spectrum in two dimensions of dimensional orientation and lambda1-wavelength and be situated between Quality detection method cooperates efficient algorithm for pattern recognition, can effectively and precisely identify the surrounding medium in current environment.
Detailed description of the invention
It in order to more clearly explain the technical solutions in the embodiments of the present application, below will be to embodiment or description of the prior art Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only some of the application Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these Attached drawing obtains other attached drawings.
Fig. 1 is the flow chart for the surrounding medium method for sensing that the embodiment of the present application one provides；
Fig. 2 is the flow chart for the surrounding medium method for sensing that the embodiment of the present application two provides；
Fig. 3 is the schematic diagram for the surrounding medium sensing device that the embodiment of the present application three provides；
Fig. 4 is the schematic diagram for the surrounding medium sensing device that the embodiment of the present application four provides；
Fig. 5 is the schematic diagram for the surrounding medium sensing device that the embodiment of the present application five provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed Body details, so as to provide a thorough understanding of the present application embodiment.However, it will be clear to one skilled in the art that there is no these specific The application also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity The detailed description of road and method, so as not to obscure the description of the present application with unnecessary details.
In order to illustrate technical solution described herein, the following is a description of specific embodiments.
It is a kind of flow chart for surrounding medium method for sensing that the embodiment of the present application one provides referring to Fig. 1, Fig. 1.This implementation The executing subject of environment media sensing method is the device with surrounding medium sensing function in example, is including but not limited to calculated The devices such as machine, server, tablet computer or terminal.Surrounding medium method for sensing as shown in the figure may comprise steps of:
S101: the infrared signal and blue light signals of the predeterminated frequency across current environment medium are received.
Smoke detector involved in the present embodiment, according to the optical scattering principle of particle, in dimensional orientation and incident light In two dimensions of wavelength, the position of infrared transmitting tube and blue emission pipe relative to reception pipe is devised, so that two kinds of spectrum pair The transmitting light source answered can emit optical signal from different directions.Cooperate efficient algorithm for pattern recognition software again, it can be effective Ground identifies fire information databases and the vapor, kitchen such as cotton cord hidden combustion fire, normal heptane open fire required in standard GB/T 4715 The interference sources such as cooking fume.
The executing subject of the present embodiment is the device with surrounding medium sensing function, can be a kind of two-way double spectral lights Inductance smoke detector includes Optical Dark Solitary Pulse chamber cap on hardware configuration, optical dark room main body, transmit-receive tube bracket, circuit board, red The double spectrum acquisition pipes of outer transmitting tube, blue emission pipe and red blue light, abbreviation reception pipe.Wherein, infrared transmitting tube, blue emission pipe It is fixed on bracket with reception pipe, bracket is inserted on circuit board, darkroom main body and bracket snapping, darkroom lid and darkroom main body set It connects.
Further, in order to maximize the difference of different medium feature vector in the present embodiment, we are provided with Two-way transmitting and the mode for receiving two kinds of spectrum.Specifically, we spatially adjust the position of infrared transmitting tube and reception pipe Relationship makes the two in Forward receiving state；The positional relationship for adjusting blue emission pipe and reception pipe both makes after being in receiving shape State.Space angle is preset angle between forward direction infrared transmitting tube and reception pipe, for example, can for 130 degree or 120~ Between 130 degree, space angle is also preset angle between backward blue emission pipe and reception pipe, such as can be 73 degree, or Between 68~78 degree of person.Meanwhile by the way that the signal of infrared and two kinds of spectrum of blue light is carried out time-division processing, prevent the two from emitting With spectral aliasing occurs in receive process.
Infrared signal and blue light signals in the present embodiment are that have to be issued by detector, and the detector in the present embodiment can be with The component being mounted in surrounding medium sensing device is also possible to the equipment separated with surrounding medium sensing device, herein not It limits.Infrared signal and blue light signals in the present embodiment are issued by detector, and the frequency of two kinds of signals is identical, and And all have passed through current surrounding medium.
It should be noted that the surrounding medium in the present embodiment includes various types of air dielectrics, for example, cotton cord glows Situations such as interference sources such as the smog or vapor, culinary cuisine oil smoke of the fire information databases such as fire, normal heptane open fire, herein not It limits.
Illustratively, the predeterminated frequency in the present embodiment can be 1Hz, we are by control detector to be more than or equal to The frequency of 1Hz makes infrared transmitting tube and the outside irradiating infrared light of blue emission pipe and blue spectrum signal, infrared emission and blue light Emit at predetermined intervals between transmitting, to prevent infrared and blue light signals aliasing, illustratively, time interval here It can be 1ms or more.We are when receiving infrared signal and blue light signals, and receive both signals respectively, to prevent Aliasing only occurs between unlike signal, influences the detection to surrounding medium.
S102: the infrared signal received and the blue light signals are converted into the analog signal of predetermined amplitude；Institute Stating analog signal includes the corresponding analog signal of the infrared signal and the corresponding analog signal of the blue light signals.
It is receiving after the infrared signal of current environment and blue light signals, it will by the conditioned circuit of both signals Optical signal is converted to the analog signal of predetermined amplitude.It should be noted that two kinds of different medium will be being passed through in the present embodiment When signal carries out amplitude conversion, carries out respectively, be also to prevent that aliasing occurs between different types of signal, most After obtain the corresponding analog signal of infrared signal and the corresponding analog signal of blue light signals.
Specifically, when infrared signal and blue light signals to be converted into the analog signal of predetermined amplitude, using infraluminescence Diode issues the infrared waves through ovennodulation；Infrared receiving circuit is by infrared receiving diode, triode or silicon photocell Composition, the infrared light that infrared transmitter emits is converted to corresponding electric signal by them, then send post amplifier.Transmitter is general It is made of several parts such as instruction key or operating stick, instruction coding system, modulation circuit, driving circuit, transmit circuit.Refer to when pressing When enabling key or pushing operating stick, instruction encoding circuit generates required instruction encoding signal, and instruction encoding signal carries out carrier wave Modulation, then by launching outward modulated fixed instruction encoding signal by transmit circuit after driving circuit progress power amplification.It receives Circuit is generally by a few part groups such as reception circuit, amplifying circuit, modulation circuit, instruction decoding circuit, driving circuit, execution circuit At.It can be completed by optocoupler, optocoupler exports 0V, 3.3V or 5V, so that it may directly obtain the signal by digital circuit. If the power of light becomes electric signal, the photosensitive elements such as photo resistance can be used, all from very weak light to very strong light The power or size of current signal can be converted to by photodiode, then can be flowed through fixed resistance below, can be obtained The analog signal of voltage signal form.
S103: signal sampling and quantization are carried out to the analog signal, obtain quantized data.
In the corresponding analog signal of infrared signal for obtaining predetermined amplitude, after the corresponding analog signal of blue light signals, I Signal sampling and quantization are carried out to analog signal, obtain quantized data.Signal sampling and quantization to analog signal can lead to Analog-digital converter realization is crossed, the analog-digital converter in the present embodiment, which refers to, is converted to continuously varying analog signal discrete number The device of word signal.
Specifically, analog signal is continuous in the time domain, therefore can convert it to continuous in time a series of Digital signal.This requires that defining a parameter to indicate new digital signal samples from analog signal rate.This rate The referred to as sample frequency of converter.The signal of consecutive variations, Bandwidth-Constrained can be acquired, i.e., measured every the time and stores one A signal value may then pass through interpolation for the discrete signal after conversion and be reduced to original signal.The accuracy of this process by The limitation of quantization error.However, being likely to reach to original letter in the case where only also high than twice of signal frequency when sample rate Number loyal reduction, this rule embodied in sampling thheorem.Since the analog-digital converter of actual use not can be carried out Conversion in real time completely, so carrying out to be allowed to keep by some outer adding methods during once converting to input signal It is constant.There are commonly sample-hold circuits, in most of situation, can store input by using a capacitor Analog voltage, and the connection of this capacitor and input signal is closed, disconnected by switching OR circuit.Many simulation numerals turn It changes integrated circuit and has just contained such sample-hold subsystem in inside.
Optionally, the speed of analog-digital converter has biggish difference according to its type.Wilkinson simulation numeral turns Parallel operation is limited by its clock rate.Frequency is more than 300 megahertzs and has become possibility.Time needed for conversion is directly and channel Quantity it is proportional.For a successive approximation analog-digital converter, conversion time is proportional to the logarithm of number of channels. In this way, a large amount of channels can make Approach by inchmeal converter faster than Wilkinson converter.However, Louis Wilkins converter trumpet Time is digital, and Approach by inchmeal converter is simulation.Due to simulation itself is just slower than number, work as number of channels Increase, the required time also increases.In this way, it has the process vied each other at work.Flash analog-digital converter is The most fast one kind in these three the insides, conversion is substantially with an independent parallel process.For 8 bit locations, conversion can be with It is completed within the time of more than ten of nanosecond.
S104: the quantized data is inputted into preparatory trained disaggregated model and is identified, the current environment is obtained The media type of medium.
By acquisition history infrared signal and history blue light signals in the present embodiment, collected historical signal is instructed Practice, obtains disaggregated model, collected live signal is detected and be identified by disaggregated model, determine current environment In media type.Specifically, we when carrying out model training, acquisition history infrared signal and history blue light first is believed Number, further according to history infrared signal, history blue light signals and preset algorithm for pattern recognition, obtain history feature data；It goes through History characteristic includes that the infrared signal characteristic slope range of history infrared signal, the blue light signals feature of history blue light signals are oblique Rate range.Wherein, signal characteristic slope range is for indicating infrared and blue light signals characteristic slope bound, characteristic slope ratio Range is for indicating infrared and blue light characteristic slope ratio bound, and feature alarm threshold value range is for indicating infrared and blue light Feature alarm threshold value range bound.Every kind of test fire or interference source all correspond to one group of characteristic, this group of data are known as should The feature vector of smog or interference source is planted, for identification smog or interference source category.
After obtaining the corresponding quantized data of infrared signal, the corresponding quantized data of blue light signals, we will quantify number It is identified according to inputting in trained disaggregated model in advance, data is filtered, calculate, classify, predict and are sentenced by algorithm It certainly handles, obtains the media type of current environment medium.The characteristic for the varying environment medium that will acquire respectively with it is infrared Signal characteristic slope range, blue light signals characteristic slope range are combined, and obtain different light sources by varying environment medium When corresponding characteristic.If be consistent with the feature vector comparison of a certain smog or interference or close, judgement is this kind Smog or interference source.
Above scheme, by the infrared signal and blue light signals that receive the predeterminated frequency across current environment medium；It will connect The infrared signal and the blue light signals that receive are converted into the analog signal of predetermined amplitude；The analog signal includes described The corresponding analog signal of infrared signal, the corresponding analog signal of the blue light signals；Signal sampling is carried out to the analog signal And quantization, obtain quantized data；The quantized data includes the corresponding quantized data of the infrared signal, the blue light signals pair The quantized data answered；The quantized data is inputted preparatory trained disaggregated model to identify, obtains the current environment The media type of medium.The present embodiment is according to the optical scattering principle of particle, in two dimensions of dimensional orientation and lambda1-wavelength On, the surrounding medium detection method based on two-way double spectrum is devised, efficient algorithm for pattern recognition is cooperated, it can effective, essence Really identify the surrounding medium in current environment.
Referring to fig. 2, Fig. 2 is a kind of flow chart for surrounding medium method for sensing that the embodiment of the present application two provides.This implementation The executing subject of environment media sensing method is the device with surrounding medium sensing function in example, is including but not limited to calculated The devices such as machine, server, tablet computer or terminal.Surrounding medium method for sensing as shown in the figure may comprise steps of:
S201: the infrared signal and blue light signals of the predeterminated frequency across current environment medium are received.
The implementation of S101 is identical in S201 embodiment corresponding with Fig. 1 in the present embodiment, specifically refers to The associated description of S101 in the corresponding embodiment of Fig. 1, details are not described herein.
S202: the infrared signal received and the blue light signals are converted into the analog signal of predetermined amplitude；Institute Stating analog signal includes the corresponding analog signal of the infrared signal, the corresponding analog signal of the blue light signals.
The implementation of S101 is identical in S202 embodiment corresponding with Fig. 1 in the present embodiment, specifically refers to The associated description of S101 in the corresponding embodiment of Fig. 1, details are not described herein.
S203: signal sampling and quantization are carried out to the analog signal, obtain quantized data.
After obtaining the corresponding analog signal of infrared signal, the corresponding analog signal of blue light signals, we believe simulation It number is sampled and is quantified, obtain quantized data.Sampling in the present embodiment, which refers to, converts the continuous quantity of time-domain or spatial domain At the process of discrete magnitude, the sample number of each second is sample frequency.Sampling is above, in amplitude all continuously to simulate the time Signal, in the effect of sampling pulse, it is upper discrete to be converted into the time, has on the time still continuous discrete in fixed intervals but amplitude Analog signal.Quantization for indicating the continuous value of signal, or largely possible discrete value be approximately it is limited it is multiple from Dissipate the process of value.
Further, step S203 can specifically include step S2031~S2032:
S2031: signal sampling and quantization are carried out to the analog signal, obtain digital signal.
The process for analog signal being changed into digital signal is referred to as sampling, and used capital equipment is analog/digital Converter (Analog to Digital Converter, DAC).The process of sampling is actually to believe common analog signal Number electric signal be converted into binary code 0 and 1, these 0 and 1 just constitute digital signal file, and the frequency of sampling the big then right The quality of data is more guaranteed, just can guarantee and does not generate low-frequency distortion.
Optionally, sampling is exactly that continuous signal is become to the process of pulse train by the effect of sampling switch.In addition to week Phase sampling, is extracted except data by certain time interval, can not also be limited herein by some other sample modes It is fixed.Such as: periods synchronized sampling is waited, the periods such as multiple sampling switch are opened and closed simultaneously；Equal periods asynchronous-sampling, multiple sampling switch It waits the periods but is not opened and closed simultaneously；Periodically nonuniform sampling, each sampling switch are opened and closed with the different periods；Stochastical sampling, switch motion is random, Without periodically.
In digital processing field, quantization refers to the continuous value of signal, or a large amount of possible discrete values, approximate For the process of limited multiple or less discrete values.Quantization is mainly used in the conversion from continuous signal to digital signal.Even Continuous signal becomes discrete signal by sampling, and discrete signal becomes digital signal by quantization.Pay attention to the usual feelings of discrete signal The process by quantization is not needed under condition, but may be not discrete in codomain, it is desired nonetheless to by the process of quantization.Signal Sampling and quantization usually be all to be realized by analog-to-digital conversion.
Optionally, the quantization in the present embodiment may include uniform quantization and non-uniform quantizing, herein without limitation.Its In, uniform quantization is for indicating that the input dynamic range of digital-to-analogue conversion is evenly divided into 2^n parts.Non-uniform quantizing is used for table Show that the division of the input dynamic range of digital-to-analogue conversion is uneven, the general curve with similar index is quantified.
S2032: according to preset filtering principle, shaping is filtered to the digital signal, obtains the quantized data.
After obtaining digital signal, we are filtered shaping according to preset filtering principle, to data-signal, obtain Quantized data.The data transmission system to work under bandwidth-constrained environment, the also width for needing to consider to limit signal necessarily will increase The bit error rate of receiver end.The system of Bandwidth-Constrained usually uses pulse-shaping technique, which can solve Bandwidth-Constrained Problem, while the bit error rate is reduced to the maximum extent.Filter shape in the present embodiment is to filter out specific band frequency in signal Operation, to inhibit and prevent in environment interference source to the interference in signals transmission.
Specifically, most basic information unit is rectangular pulse in Digital Transmission.It is with determining amplitude A and really Fixed duration T.Fig. 1 shows such a pulse, wherein amplitude A=1, cycle T=To, and the central point of pulse is the time Coordinate origin, t=0.It is, in general, that a series of this pulses (each delaying T seconds relative to previous) constitute information Transmission.In this case, information is encoded by the amplitude of pulse.Simplest situation is that Binary Zero is encoded as not having Pulse (A=0), and binary one is then encoded to that there are pulse (A=constants).Because the lasting span of each pulse is the period T, then maximum pulsation rate is that 1/T pulse is per second, this corresponds to the message transmission rate of 1/Tbit/s.In more complicated data In transmission plan, the amplitude of pulse can take positive value and negative value, but also can take multiple discrete amplitudes, they can be used to It is encoded for the information more than 1.For example, 4 level can be used to encode two information, wherein each level point Not Dui Ying 4 kinds coding one of.In some cases, can be with the multiple pulses of simultaneous transmission, it thus can be to more bits It is encoded.
Optionally, the frequency filtering property that we can use circuit realizes the selection to signal intermediate frequency rate ingredient.According to It is signal to be regarded as the analog signal as made of different frequency sine-wave superimposed when frequency filtering, by selecting different frequencies Rate ingredient come realize signal filter.High-pass filter, low-pass filter, bandpass filter or band can be passed through in the present embodiment The modes such as filter are hindered to realize the filtering integer of digital signal, obtain quantized data herein without limitation.Wherein, we according to Different quantized data demands determines the filter of corresponding function, illustratively, when the ingredient for allowing upper frequency in signal When passing through filter, then high-pass filter is used；When allowing the ingredient of lower frequency in signal to pass through filter, then using low Bandpass filter.If the cutoff frequency of low-frequency range is fp1, the cutoff frequency of high band is fp2, when frequency is between fp1 and fp2 What signal can be attenuated by the signal of other frequencies, then use bandpass filter；Conversely, frequency fp1 to fp2 range it Between be attenuated, external enwergy pass through, then use bandstop filter.
S204: the quantized data is inputted into the disaggregated model and carries out curve differential calculation, obtains indicating the quantization The signal characteristic slope of data situation；The signal characteristic slope includes signal characteristic slope and the institute of the infrared signal State the signal characteristic slope of blue light signals.
After obtaining quantized data, quantized data is inputted progress curve difference gauge in preset disaggregated model by us It calculates, obtains the signal characteristic slope of infrared quantized data and blue light quantization data situation, the signal characteristic in the present embodiment Slope includes the signal characteristic slope of infrared signal and the signal characteristic slope of blue light signals.
Specifically, we can be calculated when calculating received IR signal characteristic slope by following formula:Calculate blue light receive signal characteristic slope when can by following formula come It calculates:Wherein, KIRFor indicating received IR signal characteristic slope； KBLUEFor indicating that blue light receives signal characteristic slope；I is for indicating that i-th samples；N is for indicating total sampling number；T is used for Indicate the sampling time；t0For indicating sampling time for the first time, tiFor indicating the sampling time of i-th；SIR t0For indicating t0When Carve collected infrared signal quantized value；SIR tiFor indicating tiMoment collected infrared signal quantized value；SBLUE t0For table Show t0Moment collected infrared signal quantized value；SBLUE tiFor indicating tiMoment collected infrared signal quantized value.
S205: it according to the signal characteristic slope of the signal characteristic slope of the infrared signal and the blue light signals, calculates Characteristic slope ratio between the infrared signal and the blue light signals.
We pass through after the signal characteristic slope of signal characteristic slope and blue light signals that infrared signal is calculated The signal characteristic slope of infrared signal and the signal characteristic slope of blue light signals calculate the spy between infrared signal and blue light signals Levy slope ratio.Specific calculation, which can be, is divided by two data directly to obtain characteristic slope ratio.
Further, can also include step S2061~S2063 before step S206:
S2061: history infrared signal and history blue light signals are obtained.
It is that the corresponding characteristic of varying environment medium is obtained by training in advance in the present embodiment, according to these features Data determine the type of surrounding medium representated by current collected optical signal.
The first step of training history feature data in the present embodiment is exactly first to obtain history infrared signal and history blue light letter Number.It should be noted that the historical data obtained in step S2061 was obtained under the case where knowing current environment media type It takes, to determine the corresponding characteristic of current environment medium according to current surrounding medium and collected optical signal data.
S2062: it according to the history infrared signal, the history blue light signals and preset algorithm for pattern recognition, obtains To history feature data；The history feature data include the infrared signal characteristic slope range of the history infrared signal, institute State the blue light signals characteristic slope range of history blue light signals.
After obtaining history infrared signal, history blue light signals, we are according to preset algorithm for pattern recognition to these Signal data is trained, and obtains history feature data.Specific training process is as follows:
The first step is filtered shaping to infrared and blue light original quantisation data respectively first, filters out interference components, only stay The principal component of lower energy reaction signal trend；It wherein, may include referring to the received simulation electricity of the infrared and blue light of acquisition in principal component Press signal, the digital quantity S after analog-to-digital conversionIR、SBLUE；
Second step calculates separately infrared and blue light signals principal component data and curves time differential, can reflect Infrared and blue light signals variation tendency characteristic slope；
Third step, constantly more infrared and blue light signals principal component data and curves characteristic slopes, obtains to reflect red Outer and blue light signals relative different characteristic slope ratio；
4th step is carried out training mode recognizer using a large amount of fire information databases and interference source data, is obtained optimal red External signal characteristic slope range, blue light signals characteristic slope range, infrared, blue light signals characteristic slope are alarmed than range and feature Threshold range collects the corresponding surrounding medium of optical signal for accurately measuring by these threshold ranges.Wherein, signal is special Sign slope range is for indicating infrared and blue light signals characteristic slope bound；Characteristic slope than range for indicate it is infrared and The bound of blue light characteristic slope ratio；Feature alarm threshold value range is for indicating infrared and blue light feature alarm threshold value range Lower limit；Every kind of test fire or interference source all correspond to one group of characteristic, this group of data are known as to the spy of this kind of smog or interference source Vector is levied, for identification smog or interference source category.
Illustratively, our standards according to specified in standard GB/T 4715 or smoke alarm new edition standard UL217 Open fire or smoldering fire (paper, cotton, timber, polyurethane, normal heptane) and interference source (vapor, culinary art interference etc.) are tested to biography Sensor carries out simulated fire test；Often carry out a test fire or interference source test, sensor will calculate it is collected it is infrared and Blue light receives data, obtains and records infrared and blue light characteristic slope, characteristic slope ratio, feature alarm threshold value；Repeat Interference source test is tested, is often carried out a test, sensor just can acquire and be calculated one group of characteristic, largely be tested Afterwards, sensor just can filter out the characteristic slope model of the infrared and blue light signals under different smog or interference source by queuing algorithm It encloses, characteristic slope is than range and feature alarm threshold value range.
It should be noted that the disaggregated model in the present embodiment obtains media type for handling quantized data.This implementation Preparatory trained algorithm for pattern recognition in example remittance, for obtaining judging the data area of medium according to given data, the two is not Conflict.
S2063: the history feature data are combined from the data of different surrounding mediums respectively, are not shared the same light Source corresponding characteristic when passing through varying environment medium.
Obtain in the previous step optimal infrared signal characteristic slope range, blue light signals characteristic slope range, it is infrared, After blue light signals characteristic slope is than range and feature alarm threshold value range, we will come from same in these characteristics The data of kind smog or interference source are combined, and one group of feature vector that can reflect its feature is formed.The rest may be inferred, can be obtained The feature vector of a variety of difference smog or interference source.
S206: the corresponding characteristic of varying environment medium obtained according to preparatory training, described in currently collected Infrared signal and the corresponding characteristic of the blue light signals, determine the media type of the current environment medium；It is described Characteristic includes the signal characteristic slope of the infrared signal, the signal characteristic slope of the blue light signals, the infrared letter Characteristic slope ratio number between the blue light signals.
It is being calculated, the signal characteristic slope, described infrared of the signal characteristic slope of infrared signal, the blue light signals After characteristic slope ratio between signal and the blue light signals, we will train the history feature data come and acquisition in real time The characteristic being calculated compares, and determines the media type of current environment medium.Exactly sensor is acquired and calculated Characteristic vector data out and each feature vectors obtained after largely training are compared, and if a certain smog or The feature vector comparison of interference is consistent or close, then judgement is this kind of smog or interference source.
S207: if detection obtains the media type phase of the media type and preset alarm medium of the current environment medium Together, and it is more than the alarm threshold set, then triggers alarm；The alarm medium includes poisonous medium, inflammable and explosive medium.
It is preset with alarm threshold in the present embodiment, the threshold value of the medium parameter of alarm will be triggered for indicating.It is true in detection After the media type for having determined current environment medium, if detection obtains the media type of current environment medium and preset alarm is situated between The media type of matter is identical, and the parameter of currently detected surrounding medium is more than the alarm threshold of setting, then triggers alarm.Root According to the alarm regulation in practical application, the alarm medium in the present embodiment may include poisonous medium, inflammable and explosive medium Deng herein without limitation.
Optionally, feature report can be calculated by the infrared signal and blue light signals that get in real time in the present embodiment Alert value, by by this feature alarming value with train in advance come feature alarm threshold value compare, it is determined whether need to set out Alarm, to notify the people or administrative staff in current environment.
Above scheme, by the infrared signal and blue light signals that receive the predeterminated frequency across current environment medium；It will connect The infrared signal and the blue light signals that receive are converted into the analog signal of predetermined amplitude；The analog signal includes described The corresponding analog signal of infrared signal, the corresponding analog signal of the blue light signals；Signal sampling is carried out to the analog signal And quantization, obtain quantized data；The quantized data includes the corresponding quantized data of the infrared signal, the blue light signals pair The quantized data answered；The quantized data is inputted into the disaggregated model and carries out curve differential calculation, obtains indicating the quantization The signal characteristic slope of data situation；The signal characteristic slope includes the signal characteristic slope of the infrared signal, institute State the signal characteristic slope of blue light signals；Signal according to the signal characteristic slope of the infrared signal, the blue light signals is special Slope is levied, the characteristic slope ratio between the infrared signal and the blue light signals is calculated；The difference obtained according to preparatory training The corresponding characteristic of surrounding medium, with the current collected infrared signal and the corresponding feature of the blue light signals Data determine the media type of the current environment medium；The characteristic includes that the signal characteristic of the infrared signal is oblique Characteristic slope ratio between rate, the signal characteristic slope of the blue light signals, the infrared signal and the blue light signals.This reality Example is applied according to the optical scattering principle of particle, in two dimensions of dimensional orientation and lambda1-wavelength, is devised based on two-way double The surrounding medium detection method of spectrum, cooperates efficient algorithm for pattern recognition, can effectively and precisely identify in current environment Surrounding medium.
It is a kind of schematic diagram for surrounding medium sensing device that the embodiment of the present application three provides referring to Fig. 3, Fig. 3.Environment is situated between Matter sensing device 300 can be the mobile terminals such as smart phone, tablet computer.The surrounding medium sensing device 300 of the present embodiment Including each unit be used to execute each step in the corresponding embodiment of Fig. 1, referring specifically to the corresponding embodiment of Fig. 1 and Fig. 1 In associated description, do not repeat herein.The surrounding medium sensing device 300 of the present embodiment includes:
Receiving unit 301, for receiving the infrared signal and blue light signals of the predeterminated frequency across current environment medium；
Converting unit 302, for the infrared signal received and the blue light signals to be converted into predetermined amplitude Analog signal；The analog signal includes the corresponding analog signal of the infrared signal, the corresponding simulation letter of the blue light signals Number；
Quantifying unit 303 obtains quantized data for carrying out signal sampling and quantization to the analog signal；The amount Changing data includes the corresponding quantized data of the infrared signal, the corresponding quantized data of the blue light signals；
Recognition unit 304 identifies for the quantized data to be inputted preparatory trained disaggregated model, obtains institute State the media type of current environment medium.
Further, the recognition unit 304 may include:
Differentiation element carries out curve differential calculation for the quantized data to be inputted the disaggregated model, is indicated The signal characteristic slope of the quantized data situation of change；The signal characteristic slope includes the signal characteristic of the infrared signal The signal characteristic slope of slope, the blue light signals；
Slope unit, for oblique according to signal characteristic slope, the signal characteristic of the blue light signals of the infrared signal Rate calculates the characteristic slope ratio between the infrared signal and the blue light signals；
Determination unit, for being acquired with current according to the corresponding characteristic of varying environment medium that training obtains in advance The infrared signal and the corresponding characteristic of the blue light signals arrived, determines the medium class of the current environment medium Type；The characteristic includes the signal characteristic slope, described of the signal characteristic slope of the infrared signal, the blue light signals Characteristic slope ratio between infrared signal and the blue light signals.
Further, the surrounding medium sensing device further include:
Data capture unit, for obtaining history infrared signal and history blue light signals；
Historical data unit, for according to the history infrared signal, the history blue light signals and preset mode Recognizer obtains history feature data；The history feature data include the infrared signal feature of the history infrared signal Slope range, the blue light signals characteristic slope range of the history blue light signals；
Assembled unit, the characteristic of the varying environment medium for will acquire are oblique with the infrared signal feature respectively Rate range, the blue light signals characteristic slope range are combined, and it is corresponding when through varying environment medium to obtain different light sources Characteristic.
Further, the quantifying unit 303 may include:
Sample quantization unit obtains digital signal for carrying out signal sampling and quantization to the analog signal；
Integer unit is filtered, for shaping being filtered to the digital signal, obtaining institute according to preset filtering principle State quantized data.
Further, the surrounding medium sensing device further include:
Alarm unit, if Jie for detecting the media type Yu preset alarm medium that obtain the current environment medium Matter type is identical, and is more than the alarm threshold of setting, then triggers alarm；The alarm medium include preset poisonous medium, easily Fire explosive medium.
Above scheme, by the infrared signal and blue light signals that receive the predeterminated frequency across current environment medium；It will connect The infrared signal and the blue light signals that receive are converted into the analog signal of predetermined amplitude；The analog signal includes described The corresponding analog signal of infrared signal, the corresponding analog signal of the blue light signals；Signal sampling is carried out to the analog signal And quantization, obtain quantized data；The quantized data includes the corresponding quantized data of the infrared signal, the blue light signals pair The quantized data answered；The quantized data is inputted preparatory trained disaggregated model to identify, obtains the current environment The media type of medium.The present embodiment is according to the optical scattering principle of particle, in two dimensions of dimensional orientation and lambda1-wavelength On, the surrounding medium detection method based on two-way double spectrum is devised, efficient algorithm for pattern recognition is cooperated, it can effective, essence Really identify the surrounding medium in current environment.
Referring to fig. 4, Fig. 4 is a kind of schematic diagram for surrounding medium sensing device that the embodiment of the present application four provides.Fig. 4 and figure It is in place of 3 difference, Fig. 4 after S303 includes step S404-S407 in step corresponding to Fig. 3.The ring of the present embodiment The each unit that border media sensing device 400 includes is used to execute each step in the corresponding embodiment of Fig. 2, referring specifically to Fig. 2 And the associated description in the corresponding embodiment of Fig. 2, it does not repeat herein.The surrounding medium sensing device 400 of the present embodiment includes:
Receiving unit 401, for receiving the infrared signal and blue light signals of the predeterminated frequency across current environment medium；
Converting unit 402, for the infrared signal received and the blue light signals to be converted into predetermined amplitude Analog signal；The analog signal includes the corresponding analog signal of the infrared signal, the corresponding simulation letter of the blue light signals Number；
Quantifying unit 403 obtains quantized data for carrying out signal sampling and quantization to the analog signal；The amount Changing data includes the corresponding quantized data of the infrared signal, the corresponding quantized data of the blue light signals；
Differentiation element 404 carries out curve differential calculation for the quantized data to be inputted the disaggregated model, obtains table Show the signal characteristic slope of the quantized data situation of change；The signal characteristic slope includes that the signal of the infrared signal is special Levy the signal characteristic slope of slope, the blue light signals；
Slope unit 405, for the signal characteristic according to the signal characteristic slope of the infrared signal, the blue light signals Slope calculates the characteristic slope ratio between the infrared signal and the blue light signals；
Determination unit 406 and is currently adopted for according to the obtained corresponding characteristic of varying environment medium of training in advance The infrared signal and the corresponding characteristic of the blue light signals collected, determines the medium of the current environment medium Type；The characteristic includes the signal characteristic slope of the infrared signal, the signal characteristic slope of the blue light signals, institute State the characteristic slope ratio between infrared signal and the blue light signals.
Alarm unit 407, if obtaining the media type and preset alarm medium of the current environment medium for detecting Media type it is identical, and be more than setting alarm threshold, then trigger alarm；The alarm medium includes preset toxic Jie Matter, inflammable and explosive medium.
Further, the surrounding medium sensing device further include:
Data capture unit, for obtaining history infrared signal and history blue light signals；
Historical data unit, for according to the history infrared signal, the history blue light signals and preset mode Recognizer obtains history feature data；The history feature data include the infrared signal feature of the history infrared signal Slope range, the blue light signals characteristic slope range of the history blue light signals；
Assembled unit, the characteristic of the varying environment medium for will acquire are oblique with the infrared signal feature respectively Rate range, the blue light signals characteristic slope range are combined, and it is corresponding when through varying environment medium to obtain different light sources Characteristic.
Further, the quantifying unit 403 may include:
Sample quantization unit obtains digital signal for carrying out signal sampling and quantization to the analog signal；
Integer unit is filtered, for shaping being filtered to the digital signal, obtaining institute according to preset filtering principle State quantized data.
Above scheme, by the infrared signal and blue light signals that receive the predeterminated frequency across current environment medium；It will connect The infrared signal and the blue light signals that receive are converted into the analog signal of predetermined amplitude；The analog signal includes described The corresponding analog signal of infrared signal, the corresponding analog signal of the blue light signals；Signal sampling is carried out to the analog signal And quantization, obtain quantized data；The quantized data includes the corresponding quantized data of the infrared signal, the blue light signals pair The quantized data answered；The quantized data is inputted preparatory trained disaggregated model to identify, obtains the current environment The media type of medium.The present embodiment is according to the optical scattering principle of particle, in two dimensions of dimensional orientation and lambda1-wavelength On, the surrounding medium detection method based on two-way double spectrum is devised, efficient algorithm for pattern recognition is cooperated, it can effective, essence Really identify the surrounding medium in current environment.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present application constitutes any limit It is fixed.
It is a kind of schematic diagram for surrounding medium sensing device that the embodiment of the present application five provides referring to Fig. 5, Fig. 5.Such as Fig. 5 institute Surrounding medium sensing device 500 in the present embodiment shown may include: processor 501, memory 502 and be stored in storage In device 502 and the computer program 503 that can be run on processor 501.Processor 501 is realized when executing computer program 503 Step in above-mentioned each surrounding medium method for sensing embodiment.Memory 502 is for storing computer program, the computer Program includes program instruction.Processor 501 is used to execute the program instruction of the storage of memory 502.Wherein, processor 501 is matched It sets for calling described program instruction execution or less to operate:
Processor 501 is used for:
Receive the infrared signal and blue light signals of the predeterminated frequency across current environment medium；
The infrared signal received and the blue light signals are converted into the analog signal of predetermined amplitude；The simulation Signal includes the corresponding analog signal of the infrared signal, the corresponding analog signal of the blue light signals；
Signal sampling and quantization are carried out to the analog signal, obtain quantized data；The quantized data includes described red The corresponding quantized data of external signal, the corresponding quantized data of the blue light signals；
The quantized data is inputted preparatory trained disaggregated model to identify, obtains the current environment medium Media type.
Further, processor 501 is specifically used for:
The quantized data is inputted into the disaggregated model and carries out curve differential calculation, obtains indicating that the quantized data becomes Change the signal characteristic slope of situation；The signal characteristic slope includes the signal characteristic slope of the infrared signal, the blue light The signal characteristic slope of signal；
According to the signal characteristic slope of the infrared signal, the signal characteristic slope of the blue light signals, calculate described red Characteristic slope ratio between external signal and the blue light signals；
According to the corresponding characteristic of varying environment medium that preparatory training obtains, with the current collected infrared letter Number and the corresponding characteristic of the blue light signals, determine the media type of the current environment medium；The characteristic According to including the signal characteristic slope of the infrared signal, the signal characteristic slope of the blue light signals, the infrared signal and institute State the characteristic slope ratio between blue light signals.
Further, processor 501 is specifically used for:
Obtain history infrared signal and history blue light signals；
According to the history infrared signal, the history blue light signals and preset algorithm for pattern recognition, history is obtained Characteristic；The history feature data include infrared signal characteristic slope range, the history of the history infrared signal The blue light signals characteristic slope range of blue light signals；
The characteristic for the varying environment medium that will acquire respectively with the infrared signal characteristic slope range, the indigo plant Optical signal characteristic slope range is combined, and obtains different light sources corresponding characteristic when through varying environment medium.
Further, processor 501 is specifically used for:
Signal sampling and quantization are carried out to the analog signal, obtain digital signal；
According to preset filtering principle, shaping is filtered to the digital signal, obtains the quantized data.
Further, processor 501 is specifically used for:
If the media type that detection obtains the current environment medium is identical as the media type of preset alarm medium, and More than the alarm threshold of setting, then alarm is triggered；The alarm medium includes preset poisonous medium, inflammable and explosive medium.
Above scheme, by the infrared signal and blue light signals that receive the predeterminated frequency across current environment medium；It will connect The infrared signal and the blue light signals that receive are converted into the analog signal of predetermined amplitude；The analog signal includes described The corresponding analog signal of infrared signal, the corresponding analog signal of the blue light signals；Signal sampling is carried out to the analog signal And quantization, obtain quantized data；The quantized data includes the corresponding quantized data of the infrared signal, the blue light signals pair The quantized data answered；The quantized data is inputted preparatory trained disaggregated model to identify, obtains the current environment The media type of medium.The present embodiment is according to the optical scattering principle of particle, in two dimensions of dimensional orientation and lambda1-wavelength On, the surrounding medium detection method based on two-way double spectrum is devised, efficient algorithm for pattern recognition is cooperated, it can effective, essence Really identify the surrounding medium in current environment.
It should be appreciated that in the embodiment of the present application, alleged processor 501 can be central processing unit (Central Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at Reason device is also possible to any conventional processor etc..
The memory 502 may include read-only memory and random access memory, and to processor 501 provide instruction and Data.The a part of of memory 502 can also include nonvolatile RAM.For example, memory 502 can also be deposited Store up the information of device type.
In the specific implementation, processor 501, memory 502 described in the embodiment of the present application, computer program 503 can Execute realization described in the first embodiment and second embodiment of surrounding medium method for sensing provided by the embodiments of the present application The implementation of terminal described in the embodiment of the present application also can be performed in mode, and details are not described herein.
A kind of computer readable storage medium, the computer-readable storage medium are provided in another embodiment of the application Matter is stored with computer program, and the computer program includes program instruction, and described program instructs realization when being executed by processor:
Receive the infrared signal and blue light signals of the predeterminated frequency across current environment medium；
The infrared signal received and the blue light signals are converted into the analog signal of predetermined amplitude；The simulation Signal includes the corresponding analog signal of the infrared signal, the corresponding analog signal of the blue light signals；
Signal sampling and quantization are carried out to the analog signal, obtain quantized data；The quantized data includes described red The corresponding quantized data of external signal, the corresponding quantized data of the blue light signals；
The quantized data is inputted preparatory trained disaggregated model to identify, obtains the current environment medium Media type.
Further, it is also realized when the computer program is executed by processor:
The quantized data is inputted into the disaggregated model and carries out curve differential calculation, obtains indicating that the quantized data becomes Change the signal characteristic slope of situation；The signal characteristic slope includes the signal characteristic slope of the infrared signal, the blue light The signal characteristic slope of signal；
According to the signal characteristic slope of the infrared signal, the signal characteristic slope of the blue light signals, calculate described red Characteristic slope ratio between external signal and the blue light signals；
According to the corresponding characteristic of varying environment medium that preparatory training obtains, with the current collected infrared letter Number and the corresponding characteristic of the blue light signals, determine the media type of the current environment medium；The characteristic According to including the signal characteristic slope of the infrared signal, the signal characteristic slope of the blue light signals, the infrared signal and institute State the characteristic slope ratio between blue light signals.
Further, it is also realized when the computer program is executed by processor:
Obtain history infrared signal and history blue light signals；
According to the history infrared signal, the history blue light signals and preset algorithm for pattern recognition, history is obtained Characteristic；The history feature data include infrared signal characteristic slope range, the history of the history infrared signal The blue light signals characteristic slope range of blue light signals；
The characteristic for the varying environment medium that will acquire respectively with the infrared signal characteristic slope range, the indigo plant Optical signal characteristic slope range is combined, and obtains different light sources corresponding characteristic when through varying environment medium.
Further, it is also realized when the computer program is executed by processor:
Signal sampling and quantization are carried out to the analog signal, obtain digital signal；
According to preset filtering principle, shaping is filtered to the digital signal, obtains the quantized data.
Further, it is also realized when the computer program is executed by processor:
If the media type that detection obtains the current environment medium is identical as the media type of preset alarm medium, and More than the alarm threshold of setting, then alarm is triggered；The alarm medium includes preset poisonous medium, inflammable and explosive medium.
Above scheme, by the infrared signal and blue light signals that receive the predeterminated frequency across current environment medium；It will connect The infrared signal and the blue light signals that receive are converted into the analog signal of predetermined amplitude；The analog signal includes described The corresponding analog signal of infrared signal, the corresponding analog signal of the blue light signals；Signal sampling is carried out to the analog signal And quantization, obtain quantized data；The quantized data includes the corresponding quantized data of the infrared signal, the blue light signals pair The quantized data answered；The quantized data is inputted preparatory trained disaggregated model to identify, obtains the current environment The media type of medium.The present embodiment is according to the optical scattering principle of particle, in two dimensions of dimensional orientation and lambda1-wavelength On, the surrounding medium detection method based on two-way double spectrum is devised, efficient algorithm for pattern recognition is cooperated, it can effective, essence Really identify the surrounding medium in current environment.
The computer readable storage medium can be the internal storage unit of terminal described in aforementioned any embodiment, example Such as the hard disk or memory of terminal.The computer readable storage medium is also possible to the External memory equipment of the terminal, such as The plug-in type hard disk being equipped in the terminal, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card) etc..Further, the computer readable storage medium can also be wrapped both The internal storage unit for including the terminal also includes External memory equipment.The computer readable storage medium is described for storing Other programs and data needed for computer program and the terminal.The computer readable storage medium can be also used for temporarily Ground stores the data that has exported or will export.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not It is considered as beyond scope of the present application.
It is apparent to those skilled in the art that for convenience of description and succinctly, the end of foregoing description The specific work process at end and unit, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed terminal and method can pass through it Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied Another system is closed or is desirably integrated into, or some features can be ignored or not executed.In addition, shown or discussed phase Mutually between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication of device or unit Connection is also possible to electricity, mechanical or other form connections.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.Some or all of unit therein can be selected to realize the embodiment of the present application scheme according to the actual needs Purpose.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words It embodies, which is stored in a storage medium, including some instructions are used so that a computer Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the application Portion or part steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. are various can store program The medium of code.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any Those familiar with the art within the technical scope of the present application, can readily occur in various equivalent modifications or replace It changes, these modifications or substitutions should all cover within the scope of protection of this application.Therefore, the protection scope of the application should be with right It is required that protection scope subject to.

Claims (10)

1. a kind of surrounding medium method for sensing characterized by comprising
Receive the infrared signal and blue light signals of the predeterminated frequency across current environment medium；
The infrared signal received and the blue light signals are converted into the analog signal of predetermined amplitude；The analog signal Including the corresponding analog signal of the infrared signal, the corresponding analog signal of the blue light signals；
Signal sampling and quantization are carried out to the analog signal, obtain quantized data；The quantized data includes the infrared letter Number corresponding quantized data, the corresponding quantized data of the blue light signals；
The quantized data is inputted preparatory trained disaggregated model to identify, obtains the medium of the current environment medium Type.
2. surrounding medium method for sensing as described in claim 1, which is characterized in that described to input the quantized data in advance Trained disaggregated model is identified, the media type of the current environment medium is obtained, comprising:
The quantized data is inputted into the disaggregated model and carries out curve differential calculation, obtains indicating the quantized data variation feelings The signal characteristic slope of condition；The signal characteristic slope includes the signal characteristic slope of the infrared signal, the blue light signals Signal characteristic slope；
According to the signal characteristic slope of the infrared signal, the signal characteristic slope of the blue light signals, the infrared letter is calculated Characteristic slope ratio number between the blue light signals；
According to the corresponding characteristic of varying environment medium that preparatory training obtains, with the current collected infrared signal and The corresponding characteristic of blue light signals, determines the media type of the current environment medium；The characteristic packet Include the signal characteristic slope of the infrared signal, the signal characteristic slope of the blue light signals, the infrared signal and the indigo plant Characteristic slope ratio between optical signal.
3. surrounding medium method for sensing as claimed in claim 2, which is characterized in that the basis difference that training obtains in advance The corresponding characteristic of surrounding medium, before the media type for determining the current environment medium, further includes:
Obtain history infrared signal and history blue light signals；
According to the history infrared signal, the history blue light signals and preset algorithm for pattern recognition, history feature is obtained Data；The history feature data include the infrared signal characteristic slope range of the history infrared signal, the history blue light The blue light signals characteristic slope range of signal；
The characteristic for the varying environment medium that will acquire is believed with the infrared signal characteristic slope range, the blue light respectively Number characteristic slope range is combined, and obtains different light sources corresponding characteristic when through varying environment medium.
4. surrounding medium method for sensing as described in claim 1, which is characterized in that described to carry out signal to the analog signal Sampling and quantization, obtain quantized data, comprising:
Signal sampling and quantization are carried out to the analog signal, obtain digital signal；
According to preset filtering principle, shaping is filtered to the digital signal, obtains the quantized data.
5. surrounding medium method for sensing according to any one of claims 1-4, which is characterized in that described by the quantized data It inputs trained disaggregated model in advance to be identified, after obtaining the media type of the current environment medium, further includes:
If the media type that detection obtains the current environment medium is identical as the media type of preset alarm medium, and is more than The alarm threshold of setting, and be more than the alarm threshold of setting, then trigger alarm；The alarm medium includes preset toxic Jie Matter, inflammable and explosive medium.
6. surrounding medium method for sensing as described in claim 1, which is characterized in that the infrared signal is by preset infrared hair Pipe sending is penetrated, the blue light signals are issued by preset blue emission pipe, the infrared transmitting tube and the blue emission pipe point Not at default angle between reception pipe；The reception pipe is used to receive the infrared signal that the infrared transmitting tube issues and described The blue light signals that blue emission pipe issues.
7. a kind of surrounding medium sensing device characterized by comprising
Receiving unit, for receiving the infrared signal and blue light signals of the predeterminated frequency across current environment medium；
Converting unit, the simulation for the infrared signal received and the blue light signals to be converted into predetermined amplitude are believed Number；The analog signal includes the corresponding analog signal of the infrared signal, the corresponding analog signal of the blue light signals；
Quantifying unit obtains quantized data for carrying out signal sampling and quantization to the analog signal；The quantized data packet Include the corresponding quantized data of the infrared signal, the corresponding quantized data of the blue light signals；
Recognition unit is identified for the quantized data to be inputted trained disaggregated model in advance, is obtained described current The media type of surrounding medium.
8. surrounding medium sensing device as claimed in claim 7, which is characterized in that the recognition unit may include:
Differentiation element carries out curve differential calculation for the quantized data to be inputted the disaggregated model, obtains described in expression The signal characteristic slope of quantized data situation of change；The signal characteristic slope includes that the signal characteristic of the infrared signal is oblique The signal characteristic slope of rate, the blue light signals；
Slope unit, for the signal characteristic slope according to the signal characteristic slope of the infrared signal, the blue light signals, meter Calculate the characteristic slope ratio between the infrared signal and the blue light signals；
Determination unit, it is and current collected for according to the obtained corresponding characteristic of varying environment medium of training in advance The infrared signal and the corresponding characteristic of the blue light signals, determine the media type of the current environment medium； The characteristic includes the signal characteristic slope, described red of the signal characteristic slope of the infrared signal, the blue light signals Characteristic slope ratio between external signal and the blue light signals.
9. a kind of surrounding medium sensing device, including memory, processor and storage are in the memory and can be described The computer program run on processor, which is characterized in that the processor realizes such as right when executing the computer program It is required that the step of any one of 1 to 6 the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists In when the computer program is executed by processor the step of any one of such as claim 1 to 6 of realization the method.
CN201910381052.0A 2019-05-08 2019-05-08 Environmental medium sensing method and device Active CN110286103B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910381052.0A CN110286103B (en) 2019-05-08 2019-05-08 Environmental medium sensing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910381052.0A CN110286103B (en) 2019-05-08 2019-05-08 Environmental medium sensing method and device

Publications (2)

Publication Number Publication Date
CN110286103A true CN110286103A (en) 2019-09-27
CN110286103B CN110286103B (en) 2022-02-08

Family

ID=68002195

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910381052.0A Active CN110286103B (en) 2019-05-08 2019-05-08 Environmental medium sensing method and device

Country Status (1)

Country Link
CN (1) CN110286103B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115015072A (en) * 2022-07-19 2022-09-06 煤炭科学技术研究院有限公司 Fire smoke detection method and device and electronic equipment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104483271A (en) * 2014-12-19 2015-04-01 武汉大学 Forest biomass amount retrieval method based on collaboration of optical reflection model and microwave scattering model
CN109581372A (en) * 2018-12-10 2019-04-05 北京航天泰坦科技股份有限公司 A kind of Remote Sensing Monitoring of Ecological Environment method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104483271A (en) * 2014-12-19 2015-04-01 武汉大学 Forest biomass amount retrieval method based on collaboration of optical reflection model and microwave scattering model
CN109581372A (en) * 2018-12-10 2019-04-05 北京航天泰坦科技股份有限公司 A kind of Remote Sensing Monitoring of Ecological Environment method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
A. M. SAYER等: "MODIS Collection 6 aerosol products: Comparison between Aqua’s e-Deep Blue, Dark Target, and "merged" data sets,and usage recommendations", 《JOURNAL OF GEOPHYSICAL RESEARCH：ATMOSPHERES》 *
孙峻岭: "双向散射及双波段光电感烟火灾探测器特性研究与设计", 《中国优秀硕士学位论文全文数据库》 *
王殊等: "双波长气溶胶粒径传感方法及其火灾烟雾探测器", 《火灾科学》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115015072A (en) * 2022-07-19 2022-09-06 煤炭科学技术研究院有限公司 Fire smoke detection method and device and electronic equipment

Also Published As

Publication number Publication date
CN110286103B (en) 2022-02-08

Similar Documents

Publication Publication Date Title
US20050007877A1 (en) Acoustic system for communication in pipelines
CN101614566B (en) Low-power and two-wire vortex shedding flowmeter based on fast Fourier transform
US20180252611A1 (en) Methods and apparatus to analyze recordings in leak detection
CN104901702B (en) data storage device
CN101669307B (en) Sensor network calibration
Krishna et al. Zigbee based voice control system for smart home
CN110286103A (en) A kind of surrounding medium method for sensing and device
US20230098237A1 (en) Analog and digital frequency domain data sensing circuit
CN109962742A (en) Portable remote monitoring data monitoring platform and monitoring method
Abbasi‐Kesbi et al. Denoising MEMS accelerometer sensors based on L2‐norm total variation algorithm
CN104720788A (en) Evaluation system and method for vital sign monitoring device
Chen et al. A new transient feature extraction method of power signatures for Nonintrusive Load Monitoring Systems
Vafeas et al. Energy-efficient, noninvasive water flow sensor
CN104282347A (en) Wireless sound detection apparatus for nuclear-power-station valve leakage and compression transmission method
CN115981507B (en) Touch sensing system
US10375493B2 (en) Audio test mode
CN204831538U (en) Vibration control protection appearance
CN104382596A (en) Myoelectrical collection equipment and device and method for self-check of myoelectrical collection equipment
US9559789B2 (en) Control device update
CN204886926U (en) A circuit for inciting somebody to action voltage signal converts frequency signal into
WO2022241539A1 (en) Systems and methods for asynchronous data communication in noisy environments
RU105550U1 (en) DATA TRANSFER INTERFERENCE SYSTEM
CN109168109A (en) A kind of wireless loudspeaker based on mobile terminal
CN109544479B (en) Time-frequency image enhancement method and related equipment
TWI740411B (en) Data processing system disposed on sensor and method thereof and de-identified device

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
CB02 Change of applicant information

Address after: 518000 East and fourth floors, building A1, xinjianxing science and Technology Industrial Park, Fengxin Road, Loucun, Gongming street, Guangming District, Shenzhen City, Guangdong Province

Applicant after: TANDA Technology Co., Ltd.

Address before: 518000 Guangdong province Shenzhen Guangming New District Gongming Street Village Feng Xin Lu Xinjian Xing Technology Industrial Park A1 Building 1 floor, 3 floor, 4 East Building, 5 floor

Applicant before: TANDA Technology Co., Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant