A quality detection method and intelligent analysis and detection system in feed production process

Abstract

The present application relates to a quality detection method and intelligent analysis and detection system in a feed production process, which belongs to the field of quality control and aims to solve the problem of interference of sample thickness on the detection results. The method includes obtaining a first detection spectrum and the test subject thickness corresponding to the first detection spectrum; removing interference in the first detection spectrum and correcting the first detection spectrum to obtain a second detection spectrum; calculating the baseline of the second detection spectrum and calculating the movement of the baseline of the second detection spectrum, using the movement to correct the test subject thickness to obtain a standard test subject; calculating the component content of the standard test subject according to the difference between the detection spectrum and the reference spectrum. The quality detection method and intelligent analysis and detection system in the feed production process disclosed in the present application can correct the sample thickness according to the detection results, and then analyze the components in the sample. At the same time, interference factors can be removed during the analysis to obtain more accurate detection results.

Description

Technical Field

[0001] The present application relates to the technical field of quality control, and in particular to a quality detection method and an intelligent analysis and detection system in a feed production process. Background Art

[0002] One of the mid- and late-stage processes in feed production is to mix various raw materials to obtain a mixture, which is used to make feed pellets or finished feed. The content of each component in the finished feed has clear requirements. The current commonly used detection method is to test the raw materials or the mixture, and then make adjustments based on the test results. For example, if the crude protein content in the feed is insufficient, additional additions are required.

[0003] The specific testing process is sampling-sending samples-analysis-giving results-adjustment. The testing time of this method is 2-3 hours and has a certain lag, which means that if adjustments are required, the production line needs to wait for the test results.

[0004] To solve this problem, new detection methods have begun to be added to the detection, such as near-infrared detection. When a sample with a high content of compounds containing chemical bonds (OH, NH and CH, etc.) is provided with near-infrared light, the sample will absorb some energy at these specific wavelengths, so the intensity of the reflected light in these areas is lower. By analyzing the reflected spectrum, the content of the components in the feed can be obtained.

[0005] The emitted near-infrared light has surface reflection, internal reflection and absorption. When using automated detection methods, the sample thickness will directly affect the absorption of near-infrared light, causing deviations in the test results. Summary of the invention

[0006] The present application provides a quality inspection method and an intelligent analysis and inspection system in a feed production process, which can correct the sample thickness according to the inspection results, and then analyze the components in the sample. During the analysis process, interference factors can also be removed to obtain more accurate inspection results.

[0007] The above-mentioned purpose of the present application is achieved through the following technical solutions:

[0008] In a first aspect, the present application provides a method for quality detection in a feed production process, comprising:

[0009] Obtaining a first detection spectrum and a test subject thickness corresponding to the first detection spectrum;

[0010] removing interference in the first detection spectrum and correcting the first detection spectrum to obtain a second detection spectrum;

[0011] Calculating a baseline of the second detection spectrum and moving the second detection spectrum according to the baseline of the second detection spectrum so that the baseline of the second detection spectrum coincides with the baseline of the reference spectrum;

[0012] Obtaining the movement amount of the baseline of the second detection spectrum and correcting the test subject thickness according to the movement amount to obtain a standard test subject;

[0013] Obtain the detection spectrum of the standard subject and calculate the baseline of the detection spectrum;

[0014] Moving the detection spectrum so that the baseline of the detection spectrum coincides with the baseline of the reference spectrum;

[0015] The component content of the standard test object is calculated based on the difference between the detection spectrum and the reference spectrum.

[0016] In a possible implementation manner of the first aspect, removing interference in the first detection spectrum and correcting the first detection spectrum to obtain the second detection spectrum includes:

[0017] Generate a selection waveform, the selection waveform has a frequency and an attenuation value, the number of the selection waveforms is multiple, and the frequencies and / or attenuation values ​​of any two selection waveforms are different;

[0018] Using the selected waveform to screen the first detection spectrum to obtain a first detection sub-spectrum;

[0019] Grouping the first detection sub-spectra according to the peaks and troughs, each group including a plurality of first detection sub-spectra;

[0020] The first detection sub-spectra belonging to the same group are combined to obtain a second detection sub-spectra, and the first detection sub-spectra in the same group are all located in the absorption region of the second detection sub-spectra;

[0021] The second detection sub-spectra are combined to obtain a second detection spectrum.

[0022] In a possible implementation manner of the first aspect, determining the frequency of the selected waveform includes:

[0023] Determine the absorption frequency range of the component pointed by the selected waveform;

[0024] Assigning frequency values ​​in the absorption frequency range to the selection waveform, one selection waveform is assigned one frequency value, and one frequency value corresponds to multiple selection waveforms;

[0025] Among them, for multiple selected waveforms corresponding to one frequency value, the frequency values ​​of the selected waveforms are all the same, and the attenuation values ​​of any two of the selected waveforms are different.

[0026] In a possible implementation manner of the first aspect, determining the attenuation value of the selected waveform includes:

[0027] After assigning a frequency to the selected waveform, a random attenuation value is then assigned to the selected waveform;

[0028] The first detection spectrum is screened using a selection waveform having a frequency and an attenuation value to obtain a first detection sub-spectrum;

[0029] Calculating the amplitude change of the first detection sub-spectrum;

[0030] When the amplitude variation of the first detection sub-spectrum is greater than the allowed threshold, a direction of an attenuation value is randomly selected and the process of calculating the amplitude variation of the first detection sub-spectrum is repeated to determine the correct direction of the attenuation value;

[0031] When an attenuation value is randomly assigned to the selected waveform, the attenuation value range is divided into a plurality of sub-attenuation value ranges and an attenuation value is randomly selected from the sub-attenuation value ranges and assigned to the selected waveform.

[0032] In a possible implementation manner of the first aspect, after obtaining the second detection spectrum, the method further includes:

[0033] Determine the main peak area and the sub-peak area;

[0034] Calculate the multiple relationship between the frequency of the sub-peak area and the frequency of the main peak area;

[0035] When the obtained multiple is an integer, the sub-peak area is added to the corresponding main peak area;

[0036] Among them, after the sub-peak area is added to the corresponding main peak area, the height and area of ​​the main peak area are increased.

[0037] In a possible implementation manner of the first aspect, calculating the baseline of the second detection spectrum includes:

[0038] Processing the second detection spectrum in sections to obtain absorption sections and non-absorption sections;

[0039] Obtaining a baseline of a non-absorption segment, wherein the number of the baseline of the non-absorption segment is multiple;

[0040] The baselines of the plurality of non-absorption segments are fused to obtain the baseline of the second detection spectrum.

[0041] In a possible implementation manner of the first aspect, obtaining a baseline of the non-absorption segment includes:

[0042] Draw a horizontal reference line and move the horizontal reference line to coincide with the non-absorption segment, wherein the coincidence includes at least one point;

[0043] Calculate the area of ​​the non-absorption segment on both sides of the horizontal reference line and adjust the height of the horizontal reference line according to the difference between the two areas;

[0044] When the difference between the areas of the two regions is zero, the horizontal reference line at this time is used as the reference line of the non-absorption segment.

[0045] In a second aspect, the present application provides a quality detection device in a feed production process, comprising:

[0046] A first data acquisition unit, used for acquiring a first detection spectrum and a test subject thickness corresponding to the first detection spectrum;

[0047] A data correction unit, used to remove interference in the first detection spectrum and correct the first detection spectrum to obtain a second detection spectrum;

[0048] A first calculation unit, used for calculating a baseline of a second detection spectrum and moving the second detection spectrum according to the baseline of the second detection spectrum, so that the baseline of the second detection spectrum coincides with the baseline of the reference spectrum;

[0049] A second calculation unit is used to obtain the movement amount of the baseline of the second detection spectrum and correct the test subject thickness according to the movement amount to obtain a standard test subject;

[0050] A second data acquisition unit is used to acquire a detection spectrum of a standard subject and calculate a baseline of the detection spectrum;

[0051] A mobile processing unit is used to move the detection spectrum so that the baseline of the detection spectrum coincides with the baseline of the reference spectrum;

[0052] The third calculation unit is used to calculate the component content of the standard test subject according to the difference between the detection spectrum and the reference spectrum.

[0053] In a third aspect, the present application provides an intelligent analysis and detection system in a feed production process, the system comprising:

[0054] one or more memories for storing instructions;

[0055] One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0056] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0057] Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0058] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0059] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0060] The chip system may be composed of chips, or may include chips and other discrete devices.

[0061] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic flowchart of the steps of a quality detection method provided in this application.

[0063] Figure 2 It is a schematic diagram of the principle of a detection process provided by this application.

[0064] Figure 3 This is a schematic diagram of reflection of near-infrared light at a sample provided in the present application.

[0065] Figure 4 It is a schematic diagram of a first detection spectrum provided in this application.

[0066] Figure 5 It is a schematic diagram of a second detection spectrum provided in this application.

[0067] Figure 6 It is a schematic diagram of the relative positions of a reference spectrum and a second detection spectrum provided in the present application.

[0068] Figure 7 This is a schematic diagram of the principle of using a waveform selection method to screen a first detection spectrum provided by the present application.

[0069] Figure 8 It is a schematic diagram of a process of merging first detection sub-spectra belonging to the same group provided by the present application.

[0070] Fig. 9 It is a schematic diagram of the merging of a sub-peak region and a corresponding main peak region provided by the present application.

[0071] Fig.10 This is a schematic diagram of segmented processing of the second detection spectrum provided by the present application.

[0072] Fig.11 It is a schematic diagram of a baseline for obtaining a non-absorption segment provided in the present application. DETAILED DESCRIPTION

[0073] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.

[0074] This application discloses a method for quality detection in a feed production process. In some examples, see Figure 1 The quality detection method in the feed production process disclosed in the present application comprises the following steps:

[0075] S101, obtaining a first detection spectrum and a test thickness corresponding to the first detection spectrum;

[0076] S102, removing interference in the first detection spectrum and correcting the first detection spectrum to obtain a second detection spectrum;

[0077] S103, calculating a baseline of the second detection spectrum and moving the second detection spectrum according to the baseline of the second detection spectrum, so that the baseline of the second detection spectrum coincides with the baseline of the reference spectrum;

[0078] S104, obtaining the movement amount of the baseline of the second detection spectrum and correcting the test subject thickness according to the movement amount to obtain a standard test subject;

[0079] S105, obtaining a detection spectrum of a standard subject and calculating a baseline of the detection spectrum;

[0080] S106, moving the detection spectrum so that the baseline of the detection spectrum coincides with the baseline of the reference spectrum;

[0081] S107, calculating the component content of the standard test subject according to the difference between the detection spectrum and the reference spectrum.

[0082] In general, the quality detection method in the feed production process disclosed in the present application needs to be implemented with the help of automatic sampling equipment and near-infrared analysis equipment. The automatic sampling equipment includes a sampling probe and a conveyor belt installed on a pipeline. The sample obtained by the sampling probe is placed on the conveyor belt and transported to the near-infrared analysis equipment for analysis after being formed. Figure 2 As shown in the figure, the arrows represent the flow path of the sample, and the dotted line represents the propagation path of the near-infrared light.

[0083] At this time, the components are affected by factors such as ratio accuracy, batches and different manufacturers, which may cause deviations in the test results. Figure 3As mentioned above, near-infrared light will experience surface reflection, internal reflection and absorption at the sample. Surface reflection refers to the reflection of near-infrared light at the sample surface, internal reflection refers to the reflection of near-infrared light inside the sample, and absorption refers to the absorption of near-infrared light by the sample.

[0084] For a sample, the proportion of near-infrared light absorbed by it in the total amount of near-infrared light should be fixed or fluctuate within a small range, so that the test results can be more accurate. If the absorption is insufficient (the sample thickness is less than the allowable value) or the absorption is too large (the sample thickness is greater than the allowable value), the proportion of internal reflection will be insufficient, which will affect the accuracy of the test results.

[0085] The technical solution in the present application, in step S101, first obtains a first detection spectrum and a test subject thickness corresponding to the first detection spectrum. Here, the first detection spectrum is generated based on a test subject, and the test subject thickness corresponding to the first detection spectrum is obtained by laser ranging.

[0086] In step S102, refer to Figure 4 and Figure 5 , the interference in the first detection spectrum will be removed and corrected to obtain the second detection spectrum. The interference here is divided into spectral interference and non-spectral interference. Non-spectral interference includes ionization interference, physical interference, chemical interference and matrix effect interference. Figure 4 In the figure, the arrow points to the position where the interference occurs. After correction, Figure 5 The interference is removed at the corresponding position of .

[0087] The purpose of removing interference is to make the second detection spectrum based on the subject and obtain accurate detection results.

[0088] In step S103, refer to Figure 6 The horizontal dotted line in the figure is the reference spectrum. The reference line of the second detection spectrum is calculated and the second detection spectrum is moved according to the reference line of the second detection spectrum so that the reference line of the second detection spectrum coincides with the reference line of the reference spectrum. Then, in step S104, the movement amount of the reference line of the second detection spectrum is obtained and the test thickness is corrected according to the movement amount to obtain a standard test.

[0089] It should be noted here that near-infrared analysis equipment can also analyze the composition of the conveyor belt. Therefore, when selecting the conveyor belt, the peak of the spectrum corresponding to the conveyor belt should be outside the detection range of the sample, even Figure 6 As shown, the spectrum corresponding to the transport band is not shown in the reference spectrum.

[0090] It should also be noted here that the test subject (feed) is made of multiple components, each of which has different batches and manufacturers. Even when the preparation process parameters of the test subject change, the test results will change.

[0091] For example, when the density of the test object increases, the proportion of internal reflection will decrease. A further explanation is that the increase in density will cause the amount of voids inside the test object to decrease, thereby reducing the probability of diffuse reflection. At this time, the thickness of the test object needs to be appropriately increased.

[0092] By correcting the thickness of the test object, the test result can be made more accurate, because the same test reference or test model will be used at this time, and the required input amount can also be stabilized. In step S104, multiple corrections of the test object thickness may be involved, and because the present application uses a conveyor belt to transport the test object, the test objects of different thicknesses can be continuously generated and transported to the near-infrared analysis device by the conveyor belt.

[0093] In step S105, the detection spectrum of the standard subject is obtained and the baseline of the detection spectrum is calculated, and then the detection spectrum is moved so that the baseline of the detection spectrum coincides with the baseline of the reference spectrum, which is the content of step S106.

[0094] Finally, in step S107, the component content of the standard test object is calculated according to the difference between the detection spectrum and the reference spectrum. The specific calculation methods are as follows:

[0095] The first method: calculate the amplitude of the peak and convert it according to the amplitude;

[0096] The second method: calculate the area of ​​the curve segment where the peak is located and convert it based on the area.

[0097] For some examples, see Figure 7 , the specific method of removing interference in the first detection spectrum and correcting the first detection spectrum to obtain the second detection spectrum is:

[0098] S201, generating a selection waveform, the selection waveform having a frequency and an attenuation value, the number of the selection waveforms is multiple, and the frequencies and / or attenuation values ​​of any two selection waveforms are different;

[0099] S202, screening the first detection spectrum using the selection waveform to obtain a first detection sub-spectrum;

[0100] S203, grouping the first detection sub-spectra according to the peaks and troughs, each group including a plurality of first detection sub-spectra;

[0101] S204, merging the first detection sub-spectra belonging to the same group to obtain a second detection sub-spectra, wherein the first detection sub-spectra in the same group are all located in the absorption region of the second detection sub-spectra;

[0102] S205, combining the second detection sub-spectra to obtain a second detection spectrum.

[0103] In step S201 to step S205, the first detection spectrum is screened using the selection waveform. The screening process of the selection waveform is described as follows:

[0104] The first detection spectrum is considered to be composed of multiple waves. If it is converted to the frequency domain for processing using only Fourier transform, the time domain characteristics will be lost. The function of selecting a waveform (wavelet) is to display it in both the time domain and the frequency domain.

[0105] The selected waveform has two characteristics, namely, frequency and attenuation value. At this time, the amplitude of the selected waveform is a fixed value.

[0106] The specific way to determine the frequency of the selected waveform is:

[0107] S301, determining the absorption frequency range of the component pointed by the selected waveform;

[0108] S302, assigning a frequency value in the absorption frequency range to a selection waveform, wherein one selection waveform is assigned one frequency value, and one frequency value corresponds to multiple selection waveforms;

[0109] Among them, for multiple selected waveforms corresponding to one frequency value, the frequency values ​​of the selected waveforms are all the same, and the attenuation values ​​of any two of the selected waveforms are different.

[0110] In step S301 and step S302, it is necessary to first determine the absorption frequency range of the component pointed to by the selection waveform. The absorption frequency range of each component is fixed. Then, the frequency value in the absorption frequency range is assigned to the selection waveform. One selection waveform is assigned one frequency value, and one frequency value corresponds to multiple selection waveforms.

[0111] The specific method for determining the attenuation value of the selected waveform is:

[0112] S401, after assigning a frequency to the selected waveform, randomly assign an attenuation value to the selected waveform;

[0113] S402, screening the first detection spectrum using a selection waveform having a frequency and an attenuation value to obtain a first detection sub-spectrum;

[0114] S403, calculating the amplitude variation of the first detection sub-spectrum;

[0115] S404, when the amplitude variation of the first detection sub-spectrum is greater than the allowable threshold, randomly select a direction of an attenuation value and repeat the process of calculating the amplitude variation of the first detection sub-spectrum to determine the correct direction of the attenuation value;

[0116] When an attenuation value is randomly assigned to the selected waveform, the attenuation value range is divided into a plurality of sub-attenuation value ranges and an attenuation value is randomly selected from the sub-attenuation value ranges and assigned to the selected waveform.

[0117] In step S401 to step S404, an attenuation value is first randomly assigned to the selected waveform, and then the first detection spectrum is screened using the selected waveform to obtain a first detection sub-spectrum, and then the amplitude change of the first detection sub-spectrum is calculated.

[0118] The amplitude change here is the similarity between the selected waveform and a certain section of the first detection spectrum. The higher the similarity, the greater the amplitude change. At this time, there may be two situations: no amplitude change and amplitude change. When there is an amplitude change, the amplitude change and the allowable threshold are calculated.

[0119] When the amplitude change of the first detection sub-spectrum is greater than the allowed threshold, a direction of an attenuation value is randomly selected and the process of calculating the amplitude change of the first detection sub-spectrum is repeated to determine the correct direction of the attenuation value. The directions of the attenuation value can be increasing or decreasing. Determining the correct direction of the attenuation value is to determine whether the attenuation value needs to be increased or decreased.

[0120] When there is no amplitude change, an attenuation value is assigned again and the above process is repeated.

[0121] As for the attenuation value, its range is also calibrated through preliminary experiments, which will not be repeated here.

[0122] After the frequency and attenuation values ​​are determined, the amplitude of the selected waveform is adjusted. There are two adjustment methods: increase and decrease. During the adjustment process, the changing trend of the amplitude change is examined. When the amplitude change is the largest, the amplitude at this time is used as the amplitude of the selected waveform.

[0123] Returning to step S201 to step S205, in step S204, the first detection sub-spectra belonging to the same group are merged to obtain a second detection sub-spectra. Figure 8 In this process, the first detection sub-spectra in the same group are all located in the absorption region of the second detection sub-spectra, with the purpose of collecting all the first detection sub-spectra that meet the requirements.

[0124] Finally, in step S205, the second detection sub-spectra are combined to obtain a second detection spectrum. After the combination process, the connection part needs to be smoothed.

[0125] See also Fig. 9 After obtaining the second detection spectrum, the following processing is required:

[0126] Determine the main peak area and the sub-peak area;

[0127] Calculate the multiple relationship between the frequency of the sub-peak area and the frequency of the main peak area;

[0128] When the obtained multiple is an integer, the sub-peak area is added to the corresponding main peak area;

[0129] Among them, after the sub-peak area is added to the corresponding main peak area, the height and area of ​​the main peak area are increased.

[0130] This processing method takes into account the frequency doubling phenomenon. From the perspective of energy conservation, the sub-peak area caused by the frequency doubling phenomenon can be regarded as an overflow of the main peak area that reflects the proportion of a certain component in the test subject. Here, the sub-peak area needs to be added to the corresponding main peak area.

[0131] After the sub-peak region is added to the corresponding main peak region, the height and area of ​​the main peak region are increased. The specific method is to place the sub-peak region directly on the main peak region and then smooth the connection.

[0132] In some examples, calculating a baseline of the second detected spectrum includes:

[0133] S501, segmenting the second detection spectrum to obtain absorption segments and non-absorption segments;

[0134] S502, obtaining a baseline of a non-absorption segment, wherein the number of the baseline of the non-absorption segment is multiple;

[0135] S503, merging the baselines of the plurality of non-absorption segments to obtain a baseline of the second detection spectrum.

[0136] In step S501 to step S503, the second detection spectrum is firstly processed into segments, see Fig.10 , an absorption segment (thin solid line segment) and a non-absorption segment (thick solid line segment) are obtained. The non-absorption segment participates in calculating the baseline of the second detection spectrum. The specific processing method is to fuse the baselines of multiple non-absorption segments to obtain the baseline of the second detection spectrum.

[0137] See also Fig.11 , the specific method to obtain the baseline of the non-absorption segment is:

[0138] Draw a horizontal reference line and move the horizontal reference line to coincide with the non-absorption segment, wherein the coincidence includes at least one point;

[0139] Calculate the area of ​​the non-absorption segment on both sides of the horizontal reference line and adjust the height of the horizontal reference line according to the difference between the two areas;

[0140] When the difference between the areas of the two regions is zero, the horizontal reference line at this time is used as the reference line of the non-absorption segment.

[0141] The method of fusing the baselines of multiple non-absorbing segments is:

[0142] Create a reference baseline and calculate the distance from the baseline of the non-absorbent segment to the reference baseline;

[0143] The obtained distances are accumulated to obtain the total distance value;

[0144] Move the reference baseline to minimize the total distance;

[0145] The reference baseline corresponding to the minimum total distance value is used as the baseline of the second detection spectrum.

[0146] The present application also provides a quality detection device in a feed production process, comprising:

[0147] A first data acquisition unit, used for acquiring a first detection spectrum and a test subject thickness corresponding to the first detection spectrum;

[0148] A data correction unit, used to remove interference in the first detection spectrum and correct the first detection spectrum to obtain a second detection spectrum;

[0149] A first calculation unit, used for calculating a baseline of a second detection spectrum and moving the second detection spectrum according to the baseline of the second detection spectrum, so that the baseline of the second detection spectrum coincides with the baseline of the reference spectrum;

[0150] A second calculation unit is used to obtain the movement amount of the baseline of the second detection spectrum and correct the test subject thickness according to the movement amount to obtain a standard test subject;

[0151] A second data acquisition unit is used to acquire a detection spectrum of a standard subject and calculate a baseline of the detection spectrum;

[0152] A mobile processing unit is used to move the detection spectrum so that the baseline of the detection spectrum coincides with the baseline of the reference spectrum;

[0153] The third calculation unit is used to calculate the component content of the standard test subject according to the difference between the detection spectrum and the reference spectrum.

[0154] Furthermore, it also includes:

[0155] A generating unit, used for generating a selection waveform, the selection waveform having a frequency and an attenuation value, the number of the selection waveforms is multiple, and the frequencies and / or attenuation values ​​of any two selection waveforms are different;

[0156] A first screening unit, configured to screen the first detection spectrum using a selection waveform to obtain a first detection sub-spectrum;

[0157] A grouping unit, used for grouping the first detection sub-spectra according to the peaks and troughs, each group including a plurality of first detection sub-spectra;

[0158] A first merging unit is used to merge the first detection sub-spectra belonging to the same group to obtain a second detection sub-spectra, wherein the first detection sub-spectra in the same group are all located in the absorption region of the second detection sub-spectra;

[0159] The second merging unit is used to merge the second detection sub-spectra to obtain a second detection spectrum.

[0160] Furthermore, it also includes:

[0161] A first determination unit, used to determine the absorption frequency range of the component pointed by the selected waveform;

[0162] A first assigning unit is used to assign a frequency value in the absorption frequency range to the selection waveform, one selection waveform is assigned one frequency value, and one frequency value corresponds to multiple selection waveforms;

[0163] Among them, for multiple selected waveforms corresponding to one frequency value, the frequency values ​​of the selected waveforms are all the same, and the attenuation values ​​of any two of the selected waveforms are different.

[0164] Furthermore, it also includes:

[0165] A second assigning unit is used to assign a frequency to the selected waveform and then randomly assign an attenuation value to the selected waveform;

[0166] A second screening unit, configured to screen the first detection spectrum using a selection waveform having a frequency and an attenuation value to obtain a first detection sub-spectrum;

[0167] A fourth calculation unit, used for calculating the amplitude change of the first detection sub-spectrum;

[0168] A third screening unit is used to randomly select a direction of an attenuation value and repeat the process of calculating the amplitude change of the first detection sub-spectrum when the amplitude change of the first detection sub-spectrum is greater than an allowable threshold, so as to determine a correct direction of the attenuation value;

[0169] When an attenuation value is randomly assigned to the selected waveform, the attenuation value range is divided into a plurality of sub-attenuation value ranges and an attenuation value is randomly selected from the sub-attenuation value ranges and assigned to the selected waveform.

[0170] Furthermore, it also includes:

[0171] A second determining unit, used to determine the main peak area and the sub-peak area;

[0172] a fifth calculation unit, used for calculating the multiple relationship between the frequency of the sub-peak region and the frequency of the main peak region;

[0173] A merging unit, used to add the sub-peak area to the corresponding main peak area when the obtained multiple is an integer;

[0174] Among them, after the sub-peak area is added to the corresponding main peak area, the height and area of ​​the main peak area are increased.

[0175] Furthermore, it also includes:

[0176] A segmentation processing unit, used for segmenting the second detection spectrum to obtain absorption segments and non-absorption segments;

[0177] A first processing unit is used to obtain a baseline of a non-absorption segment, wherein the number of the baselines of the non-absorption segment is multiple;

[0178] The second processing unit is used to fuse the baselines of the multiple non-absorption segments to obtain the baseline of the second detection spectrum.

[0179] Furthermore, it also includes:

[0180] A drawing unit, used for drawing a horizontal reference line and moving the horizontal reference line to overlap with the non-absorption segment, wherein the overlap includes at least one point;

[0181] A sixth calculation unit, used for calculating the area of ​​the non-absorption segment located on both sides of the horizontal reference line and adjusting the height of the horizontal reference line according to the difference between the two areas;

[0182] The third determining unit is used to use the horizontal reference line as the reference line of the non-absorption segment when the difference between the areas of the two regions is zero.

[0183] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0184] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0185] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0186] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0187] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0188] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0190] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.

[0191] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0192] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0193] The present application also provides an intelligent analysis and detection system in a feed production process, the system comprising:

[0194] one or more memories for storing instructions;

[0195] One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0196] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0197] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0198] The chip system may be composed of chips, or may include chips and other discrete devices.

[0199] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0200] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0201] Optionally, the computer instructions are stored in a memory.

[0202] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0203] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0204] The non-volatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0205] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0206] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A quality detection method in a feed production process, characterized in that: include: Obtaining a first detection spectrum and a test subject thickness corresponding to the first detection spectrum; removing interference in the first detection spectrum and correcting the first detection spectrum to obtain a second detection spectrum; Calculating a baseline of the second detection spectrum and moving the second detection spectrum according to the baseline of the second detection spectrum so that the baseline of the second detection spectrum coincides with the baseline of the reference spectrum; Obtaining the movement amount of the baseline of the second detection spectrum and correcting the test subject thickness according to the movement amount to obtain a standard test subject; Obtain the detection spectrum of the standard subject and calculate the baseline of the detection spectrum; Moving the detection spectrum so that the baseline of the detection spectrum coincides with the baseline of the reference spectrum; The component content of the standard test object is calculated based on the difference between the detection spectrum and the reference spectrum; Calculating the baseline of the second detection spectrum includes: Processing the second detection spectrum in sections to obtain absorption sections and non-absorption sections; Obtaining a baseline of a non-absorption segment, wherein the number of the baseline of the non-absorption segment is multiple; The baselines of the plurality of non-absorption segments are fused to obtain a baseline of a second detection spectrum; The baseline for obtaining the non-absorbent segment includes: Draw a horizontal reference line and move the horizontal reference line to coincide with the non-absorption segment, wherein the coincidence includes at least one point; Calculate the area of ​​the non-absorption segment on both sides of the horizontal reference line and adjust the height of the horizontal reference line according to the difference between the two areas; When the difference between the areas of the two regions is zero, the horizontal reference line at this time is used as the reference line of the non-absorption segment.

2. The quality detection method in the feed production process according to claim 1, characterized in that: Removing interference from the first detection spectrum and correcting the first detection spectrum to obtain the second detection spectrum includes: Generate a selection waveform, the selection waveform has a frequency and an attenuation value, the number of the selection waveforms is multiple, and the frequencies and / or attenuation values ​​of any two selection waveforms are different; Using the selected waveform to screen the first detection spectrum to obtain a first detection sub-spectrum; Grouping the first detection sub-spectra according to the peaks and troughs, each group including a plurality of first detection sub-spectra; The first detection sub-spectra belonging to the same group are combined to obtain a second detection sub-spectra, and the first detection sub-spectra in the same group are all located in the absorption region of the second detection sub-spectra; The second detection sub-spectra are combined to obtain a second detection spectrum.

3. The quality detection method in the feed production process according to claim 2, characterized in that: Determining the frequency of the selected waveform includes: Determine the absorption frequency range of the component pointed by the selected waveform; Assigning frequency values ​​in the absorption frequency range to the selection waveform, one selection waveform is assigned one frequency value, and one frequency value corresponds to multiple selection waveforms; Among them, for multiple selected waveforms corresponding to one frequency value, the frequency values ​​of the selected waveforms are all the same, and the attenuation values ​​of any two of the selected waveforms are different.

4. The quality detection method in the feed production process according to claim 3, characterized in that: Determining the attenuation value of the selected waveform includes: After assigning a frequency to the selected waveform, a random attenuation value is then assigned to the selected waveform; The first detection spectrum is screened using a selection waveform having a frequency and an attenuation value to obtain a first detection sub-spectrum; Calculating the amplitude change of the first detection sub-spectrum; When the amplitude variation of the first detection sub-spectrum is greater than the allowed threshold, a direction of an attenuation value is randomly selected and the process of calculating the amplitude variation of the first detection sub-spectrum is repeated to determine the correct direction of the attenuation value; When an attenuation value is randomly assigned to the selected waveform, the attenuation value range is divided into a plurality of sub-attenuation value ranges and an attenuation value is randomly selected from the sub-attenuation value ranges and assigned to the selected waveform.

5. The quality detection method in the feed production process according to any one of claims 1 to 4, characterized in that: After obtaining the second detection spectrum, the method further includes: Determine the main peak area and the sub-peak area; Calculate the multiple relationship between the frequency of the sub-peak area and the frequency of the main peak area; When the obtained multiple is an integer, the sub-peak area is added to the corresponding main peak area; Among them, after the sub-peak area is added to the corresponding main peak area, the height and area of ​​the main peak area are increased.

6. A quality detection device in a feed production process, characterized in that: include: A first data acquisition unit, used for acquiring a first detection spectrum and a test subject thickness corresponding to the first detection spectrum; A data correction unit, used to remove interference in the first detection spectrum and correct the first detection spectrum to obtain a second detection spectrum; A first calculation unit, used for calculating a baseline of the second detection spectrum and moving the second detection spectrum according to the baseline of the second detection spectrum, so that the baseline of the second detection spectrum coincides with the baseline of the reference spectrum; A second calculation unit is used to obtain the movement amount of the baseline of the second detection spectrum and correct the test subject thickness according to the movement amount to obtain a standard test subject; A second data acquisition unit is used to acquire a detection spectrum of a standard subject and calculate a baseline of the detection spectrum; A mobile processing unit is used to move the detection spectrum so that the baseline of the detection spectrum coincides with the baseline of the reference spectrum; A third calculation unit is used to calculate the component content of the standard test subject according to the difference between the detection spectrum and the reference spectrum; A segmentation processing unit, used for segmenting the second detection spectrum to obtain absorption segments and non-absorption segments; A first processing unit is used to obtain a baseline of a non-absorption segment, wherein the number of the baselines of the non-absorption segment is multiple; A second processing unit is used to fuse the baselines of the plurality of non-absorption segments to obtain a baseline of a second detection spectrum; A drawing unit, used for drawing a horizontal reference line and moving the horizontal reference line to overlap with the non-absorption segment, wherein the overlap includes at least one point; A sixth calculation unit, used for calculating the area of ​​the non-absorption segment located on both sides of the horizontal reference line and adjusting the height of the horizontal reference line according to the difference between the two areas; The third determining unit is used to use the horizontal reference line as the reference line of the non-absorption segment when the difference between the areas of the two regions is zero.

7. An intelligent analysis and detection system in the feed production process, characterized in that: The system comprises: one or more memories for storing instructions; One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 5 is executed.

Images