CN117285382B - Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network - Google Patents
Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network Download PDFInfo
- Publication number
- CN117285382B CN117285382B CN202311563528.5A CN202311563528A CN117285382B CN 117285382 B CN117285382 B CN 117285382B CN 202311563528 A CN202311563528 A CN 202311563528A CN 117285382 B CN117285382 B CN 117285382B
- Authority
- CN
- China
- Prior art keywords
- odor
- fermentation
- low
- fish
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000855 fermentation Methods 0.000 title claims abstract description 128
- 230000004151 fermentation Effects 0.000 title claims abstract description 127
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 87
- 239000002699 waste material Substances 0.000 title claims abstract description 70
- 239000003337 fertilizer Substances 0.000 title claims abstract description 56
- 210000003608 fece Anatomy 0.000 title claims abstract description 44
- 239000010871 livestock manure Substances 0.000 title claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims description 49
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 61
- 239000003895 organic fertilizer Substances 0.000 claims abstract description 31
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 30
- 240000006439 Aspergillus oryzae Species 0.000 claims description 41
- 235000002247 Aspergillus oryzae Nutrition 0.000 claims description 41
- 230000004044 response Effects 0.000 claims description 41
- 244000063299 Bacillus subtilis Species 0.000 claims description 37
- 235000014469 Bacillus subtilis Nutrition 0.000 claims description 37
- 230000000694 effects Effects 0.000 claims description 33
- 241000186361 Actinobacteria <class> Species 0.000 claims description 31
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 21
- 240000004808 Saccharomyces cerevisiae Species 0.000 claims description 20
- 241000235342 Saccharomycetes Species 0.000 claims description 17
- 238000005259 measurement Methods 0.000 claims description 17
- 230000001953 sensory effect Effects 0.000 claims description 13
- 238000013401 experimental design Methods 0.000 claims description 11
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 9
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 9
- 238000011081 inoculation Methods 0.000 claims description 9
- 229910052698 phosphorus Inorganic materials 0.000 claims description 9
- 239000011574 phosphorus Substances 0.000 claims description 9
- 239000011591 potassium Substances 0.000 claims description 9
- 229910052700 potassium Inorganic materials 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000010298 pulverizing process Methods 0.000 claims description 7
- 241000894006 Bacteria Species 0.000 claims description 5
- 230000003203 everyday effect Effects 0.000 claims description 5
- 238000009423 ventilation Methods 0.000 claims description 5
- 239000002245 particle Substances 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000003756 stirring Methods 0.000 claims description 3
- 238000002156 mixing Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 239000000126 substance Substances 0.000 abstract description 18
- 238000011161 development Methods 0.000 abstract description 6
- 239000002131 composite material Substances 0.000 abstract description 5
- 235000015097 nutrients Nutrition 0.000 abstract description 5
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 239000013543 active substance Substances 0.000 abstract description 3
- 239000007788 liquid Substances 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 150000001413 amino acids Chemical class 0.000 abstract description 2
- 239000003814 drug Substances 0.000 abstract description 2
- 229910001385 heavy metal Inorganic materials 0.000 abstract description 2
- 230000006872 improvement Effects 0.000 abstract description 2
- 150000003839 salts Chemical class 0.000 abstract description 2
- 238000001179 sorption measurement Methods 0.000 abstract description 2
- 235000013343 vitamin Nutrition 0.000 abstract description 2
- 239000011782 vitamin Substances 0.000 abstract description 2
- 229940088594 vitamin Drugs 0.000 abstract description 2
- 229930003231 vitamin Natural products 0.000 abstract description 2
- 230000000813 microbial effect Effects 0.000 abstract 1
- 150000007523 nucleic acids Chemical class 0.000 abstract 1
- 102000039446 nucleic acids Human genes 0.000 abstract 1
- 108020004707 nucleic acids Proteins 0.000 abstract 1
- 230000004936 stimulating effect Effects 0.000 abstract 1
- 235000019645 odor Nutrition 0.000 description 42
- 235000014680 Saccharomyces cerevisiae Nutrition 0.000 description 18
- 239000000047 product Substances 0.000 description 18
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 14
- 239000002054 inoculum Substances 0.000 description 12
- 238000011160 research Methods 0.000 description 12
- 238000002474 experimental method Methods 0.000 description 11
- 230000035558 fertility Effects 0.000 description 10
- 238000005457 optimization Methods 0.000 description 10
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 9
- 230000004913 activation Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 8
- 229910000037 hydrogen sulfide Inorganic materials 0.000 description 8
- 230000002195 synergetic effect Effects 0.000 description 8
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 7
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000003912 environmental pollution Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 239000002994 raw material Substances 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- QTBSBXVTEAMEQO-UHFFFAOYSA-N Acetic acid Chemical compound CC(O)=O QTBSBXVTEAMEQO-UHFFFAOYSA-N 0.000 description 6
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 6
- 229910052799 carbon Inorganic materials 0.000 description 6
- 235000014113 dietary fatty acids Nutrition 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 229930195729 fatty acid Natural products 0.000 description 6
- 239000000194 fatty acid Substances 0.000 description 6
- 150000004665 fatty acids Chemical class 0.000 description 6
- 244000005700 microbiome Species 0.000 description 6
- 239000002689 soil Substances 0.000 description 6
- 239000012855 volatile organic compound Substances 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 210000001835 viscera Anatomy 0.000 description 5
- 239000001569 carbon dioxide Substances 0.000 description 4
- 229910002092 carbon dioxide Inorganic materials 0.000 description 4
- 239000002361 compost Substances 0.000 description 4
- 238000009264 composting Methods 0.000 description 4
- 210000002816 gill Anatomy 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 239000000843 powder Substances 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 241000196324 Embryophyta Species 0.000 description 3
- 102000004190 Enzymes Human genes 0.000 description 3
- 108090000790 Enzymes Proteins 0.000 description 3
- 108091005804 Peptidases Proteins 0.000 description 3
- 230000004103 aerobic respiration Effects 0.000 description 3
- 229910021529 ammonia Inorganic materials 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 3
- 244000052616 bacterial pathogen Species 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000001035 drying Methods 0.000 description 3
- 229940088598 enzyme Drugs 0.000 description 3
- 239000004744 fabric Substances 0.000 description 3
- 239000000796 flavoring agent Substances 0.000 description 3
- 230000003301 hydrolyzing effect Effects 0.000 description 3
- 230000004060 metabolic process Effects 0.000 description 3
- 229910052760 oxygen Inorganic materials 0.000 description 3
- 239000001301 oxygen Substances 0.000 description 3
- 239000010802 sludge Substances 0.000 description 3
- IKHGUXGNUITLKF-UHFFFAOYSA-N Acetaldehyde Chemical compound CC=O IKHGUXGNUITLKF-UHFFFAOYSA-N 0.000 description 2
- DLFVBJFMPXGRIB-UHFFFAOYSA-N Acetamide Chemical compound CC(N)=O DLFVBJFMPXGRIB-UHFFFAOYSA-N 0.000 description 2
- 102000013142 Amylases Human genes 0.000 description 2
- 108010065511 Amylases Proteins 0.000 description 2
- 241000193830 Bacillus <bacterium> Species 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 2
- 235000017491 Bambusa tulda Nutrition 0.000 description 2
- FERIUCNNQQJTOY-UHFFFAOYSA-N Butyric acid Chemical compound CCCC(O)=O FERIUCNNQQJTOY-UHFFFAOYSA-N 0.000 description 2
- 102000035195 Peptidases Human genes 0.000 description 2
- 244000082204 Phyllostachys viridis Species 0.000 description 2
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 2
- ONIBWKKTOPOVIA-UHFFFAOYSA-N Proline Chemical compound OC(=O)C1CCCN1 ONIBWKKTOPOVIA-UHFFFAOYSA-N 0.000 description 2
- 239000004365 Protease Substances 0.000 description 2
- 241000187180 Streptomyces sp. Species 0.000 description 2
- 101100343203 Vigna unguiculata LBII gene Proteins 0.000 description 2
- 235000019418 amylase Nutrition 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000011425 bamboo Substances 0.000 description 2
- VHRGRCVQAFMJIZ-UHFFFAOYSA-N cadaverine Chemical compound NCCCCCN VHRGRCVQAFMJIZ-UHFFFAOYSA-N 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003153 chemical reaction reagent Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 230000029087 digestion Effects 0.000 description 2
- XBDQKXXYIPTUBI-UHFFFAOYSA-N dimethylselenoniopropionate Natural products CCC(O)=O XBDQKXXYIPTUBI-UHFFFAOYSA-N 0.000 description 2
- 235000019634 flavors Nutrition 0.000 description 2
- FUZZWVXGSFPDMH-UHFFFAOYSA-N hexanoic acid Chemical compound CCCCCC(O)=O FUZZWVXGSFPDMH-UHFFFAOYSA-N 0.000 description 2
- 230000002401 inhibitory effect Effects 0.000 description 2
- 230000007794 irritation Effects 0.000 description 2
- KQNPFQTWMSNSAP-UHFFFAOYSA-N isobutyric acid Chemical compound CC(C)C(O)=O KQNPFQTWMSNSAP-UHFFFAOYSA-N 0.000 description 2
- JVTAAEKCZFNVCJ-UHFFFAOYSA-N lactic acid Chemical compound CC(O)C(O)=O JVTAAEKCZFNVCJ-UHFFFAOYSA-N 0.000 description 2
- 244000144972 livestock Species 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 239000002207 metabolite Substances 0.000 description 2
- 150000007524 organic acids Chemical class 0.000 description 2
- 244000144977 poultry Species 0.000 description 2
- KIDHWZJUCRJVML-UHFFFAOYSA-N putrescine Chemical compound NCCCCN KIDHWZJUCRJVML-UHFFFAOYSA-N 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- ZFRKQXVRDFCRJG-UHFFFAOYSA-N skatole Chemical compound C1=CC=C2C(C)=CNC2=C1 ZFRKQXVRDFCRJG-UHFFFAOYSA-N 0.000 description 2
- 238000002798 spectrophotometry method Methods 0.000 description 2
- 239000010902 straw Substances 0.000 description 2
- GETQZCLCWQTVFV-UHFFFAOYSA-N trimethylamine Chemical compound CN(C)C GETQZCLCWQTVFV-UHFFFAOYSA-N 0.000 description 2
- NQPDZGIKBAWPEJ-UHFFFAOYSA-N valeric acid Chemical compound CCCCC(O)=O NQPDZGIKBAWPEJ-UHFFFAOYSA-N 0.000 description 2
- 238000012418 validation experiment Methods 0.000 description 2
- 241000186046 Actinomyces Species 0.000 description 1
- 239000004382 Amylase Substances 0.000 description 1
- 108010059892 Cellulase Proteins 0.000 description 1
- 108010084185 Cellulases Proteins 0.000 description 1
- 102000005575 Cellulases Human genes 0.000 description 1
- 229920000742 Cotton Polymers 0.000 description 1
- 241000287828 Gallus gallus Species 0.000 description 1
- 239000004367 Lipase Substances 0.000 description 1
- 102000004882 Lipase Human genes 0.000 description 1
- 108090001060 Lipase Proteins 0.000 description 1
- 240000003183 Manihot esculenta Species 0.000 description 1
- 235000016735 Manihot esculenta subsp esculenta Nutrition 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000283973 Oryctolagus cuniculus Species 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 239000005700 Putrescine Substances 0.000 description 1
- 102100037486 Reverse transcriptase/ribonuclease H Human genes 0.000 description 1
- 241000235070 Saccharomyces Species 0.000 description 1
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 239000002154 agricultural waste Substances 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 150000001412 amines Chemical class 0.000 description 1
- 229940025131 amylases Drugs 0.000 description 1
- 230000004099 anaerobic respiration Effects 0.000 description 1
- 239000003242 anti bacterial agent Substances 0.000 description 1
- 230000000844 anti-bacterial effect Effects 0.000 description 1
- 229940088710 antibiotic agent Drugs 0.000 description 1
- 235000019658 bitter taste Nutrition 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 229940106157 cellulase Drugs 0.000 description 1
- 238000013329 compounding Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001877 deodorizing effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000007865 diluting Methods 0.000 description 1
- HNPSIPDUKPIQMN-UHFFFAOYSA-N dioxosilane;oxo(oxoalumanyloxy)alumane Chemical compound O=[Si]=O.O=[Al]O[Al]=O HNPSIPDUKPIQMN-UHFFFAOYSA-N 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- HYBBIBNJHNGZAN-UHFFFAOYSA-N furfural Chemical group O=CC1=CC=CO1 HYBBIBNJHNGZAN-UHFFFAOYSA-N 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000007062 hydrolysis Effects 0.000 description 1
- 238000006460 hydrolysis reaction Methods 0.000 description 1
- 239000002440 industrial waste Substances 0.000 description 1
- 238000010565 inoculated fermentation Methods 0.000 description 1
- 229910017053 inorganic salt Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004310 lactic acid Substances 0.000 description 1
- 235000014655 lactic acid Nutrition 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 235000019421 lipase Nutrition 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- VUZPPFZMUPKLLV-UHFFFAOYSA-N methane;hydrate Chemical compound C.O VUZPPFZMUPKLLV-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 150000002894 organic compounds Chemical class 0.000 description 1
- 239000011368 organic material Substances 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- USHAGKDGDHPEEY-UHFFFAOYSA-L potassium persulfate Chemical compound [K+].[K+].[O-]S(=O)(=O)OOS([O-])(=O)=O USHAGKDGDHPEEY-UHFFFAOYSA-L 0.000 description 1
- 102000004196 processed proteins & peptides Human genes 0.000 description 1
- 108090000765 processed proteins & peptides Proteins 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 235000019260 propionic acid Nutrition 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 229940024999 proteolytic enzymes for treatment of wounds and ulcers Drugs 0.000 description 1
- IUVKMZGDUIUOCP-BTNSXGMBSA-N quinbolone Chemical compound O([C@H]1CC[C@H]2[C@H]3[C@@H]([C@]4(C=CC(=O)C=C4CC3)C)CC[C@@]21C)C1=CCCC1 IUVKMZGDUIUOCP-BTNSXGMBSA-N 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 229940074386 skatole Drugs 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
- 239000011593 sulfur Substances 0.000 description 1
- QAOWNCQODCNURD-UHFFFAOYSA-N sulfuric acid Substances OS(O)(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-N 0.000 description 1
- 210000001550 testis Anatomy 0.000 description 1
- 150000003568 thioethers Chemical class 0.000 description 1
- 239000002341 toxic gas Substances 0.000 description 1
- 241001446247 uncultured actinomycete Species 0.000 description 1
- 229940005605 valeric acid Drugs 0.000 description 1
- 239000000052 vinegar Substances 0.000 description 1
- 235000021419 vinegar Nutrition 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C05—FERTILISERS; MANUFACTURE THEREOF
- C05F—ORGANIC FERTILISERS NOT COVERED BY SUBCLASSES C05B, C05C, e.g. FERTILISERS FROM WASTE OR REFUSE
- C05F1/00—Fertilisers made from animal corpses, or parts thereof
- C05F1/002—Fertilisers made from animal corpses, or parts thereof from fish or from fish-wastes
-
- C—CHEMISTRY; METALLURGY
- C05—FERTILISERS; MANUFACTURE THEREOF
- C05F—ORGANIC FERTILISERS NOT COVERED BY SUBCLASSES C05B, C05C, e.g. FERTILISERS FROM WASTE OR REFUSE
- C05F11/00—Other organic fertilisers
- C05F11/08—Organic fertilisers containing added bacterial cultures, mycelia or the like
-
- C—CHEMISTRY; METALLURGY
- C05—FERTILISERS; MANUFACTURE THEREOF
- C05F—ORGANIC FERTILISERS NOT COVERED BY SUBCLASSES C05B, C05C, e.g. FERTILISERS FROM WASTE OR REFUSE
- C05F17/00—Preparation of fertilisers characterised by biological or biochemical treatment steps, e.g. composting or fermentation
- C05F17/20—Preparation of fertilisers characterised by biological or biochemical treatment steps, e.g. composting or fermentation using specific microorganisms or substances, e.g. enzymes, for activating or stimulating the treatment
-
- C—CHEMISTRY; METALLURGY
- C05—FERTILISERS; MANUFACTURE THEREOF
- C05F—ORGANIC FERTILISERS NOT COVERED BY SUBCLASSES C05B, C05C, e.g. FERTILISERS FROM WASTE OR REFUSE
- C05F17/00—Preparation of fertilisers characterised by biological or biochemical treatment steps, e.g. composting or fermentation
- C05F17/50—Treatments combining two or more different biological or biochemical treatments, e.g. anaerobic and aerobic treatment or vermicomposting and aerobic treatment
-
- C—CHEMISTRY; METALLURGY
- C05—FERTILISERS; MANUFACTURE THEREOF
- C05F—ORGANIC FERTILISERS NOT COVERED BY SUBCLASSES C05B, C05C, e.g. FERTILISERS FROM WASTE OR REFUSE
- C05F17/00—Preparation of fertilisers characterised by biological or biochemical treatment steps, e.g. composting or fermentation
- C05F17/70—Controlling the treatment in response to process parameters
Landscapes
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Organic Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biochemistry (AREA)
- Molecular Biology (AREA)
- Biotechnology (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Chemical & Material Sciences (AREA)
- Microbiology (AREA)
- Environmental & Geological Engineering (AREA)
- Tropical Medicine & Parasitology (AREA)
- Fertilizers (AREA)
Abstract
The invention discloses a method for producing low-odor fertilizer by fermenting fish fertilizers and wastes based on a neural network multi-strain, and relates to the technical field of organic fertilizer production; crushing fish manure and waste; carrying out composite microbial fermentation treatment on the crushed fish fertilizers and wastes; separating the fermented and enzymolyzed liquid; carrying out adsorption treatment on the liquid; the prepared fertilizer contains rich nitrogen, amino acid, nucleic acid, vitamins and other organic matters and physiologically active substances, can provide various nutrient elements and growth stimulating factors required by crops, and promotes the growth and quality improvement of the crops; the prepared fertilizer has no harmful substance residues such as salt, oil, heavy metal, medicine residues and the like, is low in odor, is easy to apply and store, is a high-quality biological organic fertilizer, and meets the development requirements of green agriculture and organic agriculture. The invention has the advantages of low odor, high efficiency, environmental protection, innocuity and the like.
Description
Technical Field
The invention relates to the technical field of organic fertilizer production, in particular to a method for fermenting fish fertilizers and waste low-odor fertilizers based on a neural network multi-strain.
Background
According to the statistics of the literature, the global aquatic industry generates low-value fish and byproducts accounting for 25-70% of the total fish yield each year. According to data from grain and agricultural organizations, approximately 60% of the fishing gains per year are used for food processing (1.07 million tons), yielding 2785 tens of thousands of tons of available discards worldwide. The harbour fish harbour contains a large amount of various fish harbours without economic value, and a large amount of low-value fish harbour is not processed and is directly discarded or sold as low-value fertilizer or feed, which is called fish fertilizer. The low-odor composting technology is used for producing low-value fertilizers or feeds, so that the resources are wasted greatly and the environment is polluted seriously, development of the low-odor composting technology of the fish fertilizers is needed, the availability of the fish fertilizers is enhanced, the achievement of zero residue and zero carbon footprint targets of low-value fish processing is promoted, and the environmental pollution and the resource waste are avoided.
At present, the utilization mode of the fish fertilizer and the processing waste thereof mainly comprises the steps of drying and then crushing to prepare fertilizer or aquatic feed; the related technology for preparing the bio-organic fertilizer by deodorizing the compost is not seen, and the bio-organic fertilizer fermentation is a mode for comprehensively utilizing the fish fertilizer and the processing waste thereof, so that the environmental pollution can be reduced, the economic benefit can be increased, and the development concept of recycling economy and green agriculture is met.
The biological organic fertilizer is a fertilizer which is formed by compounding microorganism with specific functions and organic materials which mainly take animal and plant residues (such as livestock and poultry manure, crop straws and the like) as sources and are subjected to innocent treatment and decomposition. The biological organic fertilizer has important significance for realizing resource conservation type and environment-friendly society, and is a necessary choice for realizing sustainable development of agriculture. The bio-organic fertilizer has the following advantages: 1) Providing a plurality of nutrient elements and physiologically active substances, promoting the growth of crops and improving the quality; 2) Improving soil structure and water and fertilizer retention capacity, and enhancing soil foundation soil fertility; 3) Regulating the microecological balance of soil and rhizosphere, and inhibiting pathogenic bacteria and pests; 4) Reduces the application amount of chemical fertilizer and the pesticide consumption, and reduces the agricultural input cost and the environmental pollution risk.
At present, various biological organic fertilizers are researched and developed at home and abroad, such as agricultural waste type biological organic fertilizers which take straws, bean pulp, cotton pulp and the like as raw materials; livestock and poultry manure type bio-organic fertilizer taking chicken manure, cow and sheep manure, rabbit manure and the like as raw materials; industrial waste type bio-organic fertilizer taking vinasse, vinegar residue, cassava residue, sugar residue, furfural residue and the like as raw materials; household garbage type bio-organic fertilizer taking kitchen garbage and the like as raw materials; urban sludge type biological organic fertilizer which takes river sludge, sewer sludge and the like as raw materials. However, the current method for preparing the bio-organic fertilizer has the following defects: 1) The selection of fermentation strains and the determination of inoculum size are often empirical, and lack scientific basis and optimization methods; 2) Parameters such as temperature, humidity, oxygen concentration and the like in the fermentation process are difficult to accurately control, so that the fermentation effect is unstable and unpredictable; 3) The determination of the fermentation end time is often subjective and lacks objective evaluation and optimization methods. Therefore, how to utilize advanced mathematical models and computer technology to optimize and control the fermentation process of the bio-organic fertilizer, and improve the effects and quality of low odor, fertility and innocuity of the bio-organic fertilizer is an important subject of research and development of the current bio-organic fertilizer;
therefore, we propose a multi-strain fermented fish fertilizer based on a neural network and a method for processing waste fertilizer by using the same.
Disclosure of Invention
The invention aims to provide a method for fermenting a fish fertilizer and a waste low-odor fertilizer based on a neural network with multiple strains, which has the advantages of high efficiency, environmental protection and innocuity, and solves the problems of low utilization rate of fish fertilizer and waste resources, serious environmental pollution and unstable quality of biological organic fertilizer.
In order to achieve the above purpose, the present invention provides the following technical solutions: the method for fermenting the fish manure and the waste low-odor fertilizer based on the neural network multiple strains comprises the following steps:
step 1, crushing:
pulverizing fish manure and waste (viscera, fish scales, fish gills, fish fins, etc.), and making its granularity smaller than 5mm;
step 2, inoculating strains:
and optimizing and predicting the inoculation quantity of the fermentation strain, a temperature program and other factors by using a neural network prediction modeling technology.
Inoculating aspergillus oryzae, saccharomycetes, actinomycetes and bacillus subtilis in the mixture, wherein the inoculating proportion of the aspergillus oryzae, the saccharomycetes, the actinomycetes and the bacillus subtilis is that the aspergillus oryzae, the saccharomycetes, the actinomycetes, the bacillus subtilis=1.2:0.4:2.7:2.9, the total inoculating amount is 2 percent of the dry weight of the fermentation pile, and uniformly stirring;
step 3, temperature control:
placing the inoculated ferment stack in a ferment box with controllable temperature, setting the temperature program to be 32 ℃ for 4d, then raising the temperature to be 4 ℃ every day until the temperature is 56 ℃ for 9d, and stirring and ventilating periodically;
step 4, fermentation is finished:
and after the fermentation temperature reaches 56 ℃, maintaining the temperature unchanged, and continuing to ferment for 3 days until the fermentation is finished, so as to obtain the low-odor organic fertilizer.
Preferably, the neural network predictive modeling technique includes the steps of:
(a) Adopting a response surface experimental design to perform multi-level multi-factor combined experiments on the inoculum sizes of aspergillus oryzae, saccharomycetes, actinomycetes and bacillus subtilis to obtain experimental data;
(b) A neural network model is adopted, factors in experimental data are taken as input, and low-odor fermentation effect and fertility value are taken as output, so that a neural network prediction model is established;
(c) And predicting and analyzing factors and outputs at various moments in the fermentation process by adopting a neural network prediction model to obtain an optimal combination of the factors and the outputs.
Preferably, the Aspergillus oryzae, saccharomyces, actinomyces and Bacillus subtilis have a respective 1×10 10 CFU/g、2×10 8 CFU/g、1×10 10 CFU/g and 1X10 11 CFU/g viable count.
Preferably, the low odor organic fertilizer obtained comprises the following characteristics: the odor sensory score is greater than or equal to 80 minutes; ammonia nitrogen content less than or equal to 0.5%; the total nitrogen content is more than or equal to 3%; the content of quick-acting potassium is more than or equal to 0.8%; the content of available phosphorus is more than or equal to 0.6 percent.
Preferably, the odor sensory score, ammonia nitrogen content and total nitrogen content calculate a composite score according to the following formula:
；
wherein:
-a comprehensive score value;
-an odor sensory score value;
-total nitrogen content measurement;
-total nitrogen content measurement maximum;
-ammonia nitrogen content measurement;
-maximum ammonia nitrogen content measurement.
Preferably, the temperature of the fermentation tank is an adjustable, humidity and ventilated closed container.
Preferably, the comminution treatment is mechanical comminution or biological comminution or a combination of both.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the low-odor organic fertilizer particles are prepared by using the fish fertilizers and the wastes as raw materials through fermentation, enzyme hydrolysis, drying and other processes, so that the efficient utilization of the fish fertilizers and the wastes is realized, and the environmental pollution and the resource waste are reduced;
the low-odor organic fertilizer particles prepared by the invention contain rich nitrogen, amino acid, vitamins and other organic matters and physiological active substances, can provide various nutrient elements and growth stimulation factors required by crops, and promote the growth and quality improvement of the crops;
the low-odor organic fertilizer particles prepared by the invention have no harmful substance residues such as salt, oil, heavy metal, medicine residues and the like, have good water solubility, low odor and long shelf life, are easy to apply and store, are high-quality biological organic fertilizers, and meet the development requirements of green agriculture and organic agriculture.
Drawings
FIG. 1 is a flow chart of a process for producing low-odor fertilizer by fermenting fish manure and waste processing waste;
FIG. 2 is a graph showing the number of pairs R of different activation functions and nodes according to the present invention 2 An impact analysis graph of values;
FIG. 3 is a schematic diagram of a neural network according to the present invention;
FIG. 4 is a graph showing predicted versus actual values according to the present invention;
FIG. 5 is a diagram of predicted value-residual value according to the present invention;
FIG. 6 is a schematic diagram of a neural network prediction router according to the present invention;
FIG. 7 is a schematic diagram of a curved surface router according to the present invention;
FIG. 8 is a schematic diagram of the setup and temperature procedure of the fermenter of the present invention;
FIG. 9 is a schematic representation of the protocol and results of the response surface experimental design of the present invention;
FIG. 10 is a schematic representation of the protocol and results of a predictive model validation experiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
FIG. 1 is a flow chart of a method for fermenting fish manure and waste low-odor fertilizer based on a neural network.
As shown in figure 1, the method for fermenting the fish manure and the waste low-odor fertilizer based on the neural network multi-strain comprises the following steps:
the fish manure and the wastes (viscera, fish scales, fish gills, fish fins and the like) are crushed to ensure that the granularity is less than 5mm. The pulverization treatment may employ mechanical pulverization or biological pulverization or a combination of both. The mechanical crushing may be performed by using a cutter, a crusher, a mill, or the like. The biological pulverization can be carried out by hydrolytic degradation using proteolytic enzymes, cellulases, amylases, etc., or microorganisms.
The crushed fish fertilizers and wastes are stacked into fermentation piles with the height of 1-1.5 m, the ventilation property and the water retention property of the fermentation piles are increased, and the growth and the metabolism of microorganisms are promoted. Too high or too low a moisture content can affect the fermentation effect, and it is generally preferable to squeeze out a small amount of water droplets after making a fist.
Inoculating Aspergillus oryzae, yeast, actinomycetes and bacillus subtilis in the fermentation pile, wherein the proportion is as follows: 1.2:0.4:2.7:2.9, the total inoculum size was 2% of the dry weight of the fermentation pile, and was stirred uniformly. Aspergillus oryzae, yeast, actinomycetes and Bacillus subtilis Aspergillus oryzae, saccharomyces cerevisiae, streptomyces sp. And Bacillus subtilis, respectively, have a ratio of 1×10 10 CFU/g、2×10 8 CFU/g、1×10 10 CFU/g and 1X10 11 CFU/g viable count. The four strains can cooperatively ferment, secrete various hydrolytic enzymes and metabolites, degrade protein, fat, inorganic salt and other components in fish fertilizers and wastes, convert the components into effective nitrogen, phosphorus, potassium and other plant nutrient elements, generate some beneficial yeast substances and mask bad odors.
The invention selects aspergillus oryzae, saccharomycete, actinomycetes and bacillus subtilis as fermentation strains, and the strains can reduce or eliminate the odor of fish fertilizers and wastes through different mechanisms in the fermentation process. The following will describe in detail how these species reduce or eliminate the odor of fish manure and waste by different mechanisms during fermentation;
aspergillus oryzae can secrete various hydrolytic enzymes such as cellulase, amylase, protease and the like, can effectively degrade organic matters in fish fertilizers and wastes, release nitrogen sources, carbon sources and energy, and provide nutrient matrixes for other strains. Meanwhile, aspergillus oryzae can also produce some yeast-flavor substances such as ethanol, acetic acid, lactic acid and the like, and can mask bad odors in fish fertilizers and wastes.
Yeast can utilize carbon source and nitrogen source released by Aspergillus oryzae to perform aerobic or anaerobic respiration to produce carbon dioxide, water and small amount of ethanol. The saccharomycete can secrete some antibacterial peptides and inhibiting factors, such as acetamide, acetaldehyde and the like, can inhibit the growth of some pathogenic bacteria and putrefying bacteria, and reduce the total number of bacteria and the generation of odor substances in fish fertilizers and wastes.
Actinomycetes can perform aerobic respiration by utilizing a carbon source and a nitrogen source released by aspergillus oryzae to generate carbon dioxide, water, a small amount of organic acid and the like. Actinomycetes can also secrete antibiotics and metabolites such as skatole, 2-MIB and the like, can inhibit the growth of pathogenic bacteria and spoilage bacteria, and can mask odor substances in fish fertilizers and wastes.
Bacillus subtilis can perform aerobic respiration by utilizing a carbon source and a nitrogen source released by aspergillus oryzae to generate carbon dioxide, water, a small amount of organic acid and the like. The bacillus subtilis can also secrete some proteases, lipases and the like, so that organic substances in fish fertilizers and wastes can be further degraded, and more nitrogen sources, carbon sources and energy can be released. Meanwhile, bacillus subtilis can also form spores, and keep activity at high temperature or low temperature, so that the stability of the fermentation process is improved;
through the synergistic effect of the fermentation strains, the invention can realize the low-odor fermentation of the fish manure and the waste. The innovation point of the invention is that: (1) Four different fermentation strains are selected, and respectively have different mechanisms for reducing or eliminating odor, so that the efficiency and effect of low-odor fermentation are improved; (2) The response surface experimental design and the neural network prediction modeling are adopted to optimize and predict the inoculation amount of aspergillus oryzae, saccharomycete, actinomycetes and bacillus subtilis, so that the precision and the controllability of low-odor fermentation are improved; (3) A multi-objective optimization model is adopted, and two response values of the low-odor fermentation effect and the fertility value are considered, so that different requirements and preferences of users are met.
Through the mechanism, the multi-strain synergistic fermentation of the fish fertilizer and the waste can realize the purposes of low odor, fertility and innocuity. In order to verify the low odor characteristics after fermentation, the study plan was evaluated using the following method:
odor score: the three-level scoring method is adopted in the research to score the smell of the fish manure and the waste before and after fermentation. The preset scoring criteria are as follows:
scoring was performed by 30 professionals and the average was taken as the final score. The preset scoring results are shown in table 8:
presetting a conclusion: as shown in the table above, the odor scores of the fermented fish manure and waste are lower than those before fermentation, which means that the odor substances generated by the fermentation of the fish manure and waste can be effectively removed or reduced in the fermentation process. The odor score of the multi-strain fermentation group is the lowest and is only 1.2, which indicates that the multi-strain synergistic fermentation can achieve the effect of low odor or slight odor and is superior to single-strain fermentation.
Volatile Organic Compounds (VOCs) content: the research adopts a gas chromatography-mass spectrometer (GC-MS) to detect the volatile organic compounds in the fish manure and the waste before and after fermentation. Volatile organic compounds are organic compounds which can volatilize at normal temperature and normal pressure, and include odor substances such as sulfides, amines, fatty acids and the like. The preset detection results are shown in the following table:
and (3) presetting analysis: as can be seen from the above table, the content of volatile organic compounds in the fermented fish manure and waste is lower than that before fermentation, which indicates that the fermentation process can effectively degrade or convert organic substances in the fish manure and waste, and reduce the generation of odor substances. The content of volatile organic compounds in the multi-strain fermentation group is lowest and is only 789.5 mg/kg, which indicates that the multi-strain synergistic fermentation can achieve the best low-odor effect and is superior to single-strain fermentation.
Besides comprehensive evaluation, the invention also measures indexes such as volatile fatty acid content, ammonia release amount, hydrogen sulfide release amount and the like of the fermentation product, and the indexes are all related to low odor characteristics. The volatile fatty acid content is an important index reflecting the degradation degree of organic matters and the microecological balance state of the fermentation product, wherein acetic acid, propionic acid, isobutyric acid and the like have lower irritation and higher fertility value, and butyric acid, valeric acid, caproic acid and the like have higher irritation and lower fertility value, so the volatile fatty acid content of the fermentation product is as low as possible and mainly comprises volatile fatty acids with low carbon chains. The release amount of ammonia and the release amount of hydrogen sulfide are important indexes reflecting the odor intensity and the environmental pollution degree of the fermentation product, and the ammonia and the hydrogen sulfide are both pungent and toxic gases and have adverse effects on human bodies and plants, so that the release amount of volatile odor substances such as cadaverine, putrescine, trimethylamine and the like of the fermentation product is low enough to reduce the odor of the composting product.
Taking ammonia nitrogen (NH 3-N) content and hydrogen sulfide (H2S) content as examples, the research adopts a nitrogen analyzer and a hydrogen sulfide analyzer to detect ammonia nitrogen and hydrogen sulfide in fish fertilizers and wastes before and after fermentation. Ammonia nitrogen and hydrogen sulfide are a class of malodorous substances that are irritating and corrosive and are harmful to the human body and the environment. The preset detection results are shown in the following table:
as shown in the table above, the ammonia nitrogen and hydrogen sulfide content in the fermented fish manure and waste are lower than those before fermentation, which means that the fermentation process can effectively consume or convert the nitrogen source and the sulfur source in the fish manure and waste, and reduce the generation of odor substances. Wherein, the ammonia nitrogen and hydrogen sulfide content of the multi-strain fermentation group is lowest and is 67.8 mg/kg and 32.4 mg/kg respectively, which indicates that the multi-strain synergistic fermentation can achieve the best low odor effect and is superior to single-strain fermentation.
Placing the inoculated ferment stack in a ferment box with controllable temperature, setting the temperature program to be 32 ℃ and 4d, then raising the temperature to be 4 ℃ every day until 56 ℃ (9 d), and turning the stack and ventilating periodically. The fermentation box is a closed container with adjustable temperature, humidity and ventilation, can ensure the supply of temperature, humidity and oxygen in the fermentation process, and promotes the growth and metabolism of microorganisms. The temperature program can be regulated according to the optimal temperature of different strains, and the temperature is usually between 32 and 56 ℃, and the activity of microorganisms can be inhibited by too high or too low temperature. The oxygen content in the fermentation pile can be increased by turning and ventilation, odor generated by anaerobic fermentation is prevented, and meanwhile, strains and temperature can be uniformly distributed, so that the fermentation efficiency is improved.
After the fermentation temperature reaches 56 ℃, the fermentation is finished, and the judgment standard is as follows: the internal temperature of the fermentation pile is the same as or similar to the external environment temperature; the fermentation pile is loose, low-odor or light-odor; the fish manure and the waste in the fermentation pile are completely degraded, and no obvious raw material form exists. The obtained low-odor organic fertilizer has the following characteristics: the odor sensory score is greater than or equal to 80 minutes; ammonia nitrogen content less than or equal to 0.5%; the total nitrogen content is more than or equal to 3%; the content of quick-acting potassium is more than or equal to 0.8%; the content of available phosphorus is more than or equal to 0.6 percent. The odor sensory score, ammonia nitrogen content and total nitrogen content were calculated as the following formula:
；
wherein:
-a comprehensive score value;
-an odor sensory score value;
-total nitrogen content measurement;
-total nitrogen content measurement maximum;
-ammonia nitrogen content measurement;
-maximum ammonia nitrogen content measurement.
According to the invention, the low-odor fermentation effect is optimized by adjusting the inoculum size change of aspergillus oryzae, saccharomycetes, actinomycetes and bacillus subtilis, and the optimal strain proportion and temperature program are obtained by performing data analysis and predictive modeling through JMP software through response surface experimental design. In the experimental design of the response surface, the invention adopts a Box-Behnken design method, which is a three-level orthogonal rotation combined design method, can effectively consider the interaction among all factors and reduce the test times, and in the data analysis, the invention adopts a multiple linear regression analysis method, which can establish a mathematical model between all factors and response values and evaluate the rationality and the effectiveness of the model by checking the significance, fitting goodness, residual analysis and other methods of the model. In predictive modeling, the invention adopts a neural network predictive modeling method, which is a nonlinear fitting method based on artificial intelligence, can process complex nonlinear relations, and has higher precision and generalization capability.
The invention adopts a neural network prediction modeling method, which is a nonlinear fitting method based on artificial intelligence, can process complex nonlinear relation and has higher precision and generalization capability, the basic principle of the neural network prediction modeling method is as follows: mapping input data (such as inoculum size and temperature program of each strain) to one or more hidden layers through a series of weighting and activation functions, and then obtaining output data (such as comprehensive evaluation) through an output layer. The invention uses the neural network prediction modeling tool in JMP software, the tool can automatically select proper hidden layer structure and activation function type, and provides various optimization algorithms and evaluation indexes, thereby facilitating the construction and verification of the model by the user. In neural network predictive modeling, the invention adopts a multi-objective optimization model, namely, two response values of comprehensive scores and volatile fatty acid content are considered simultaneously, and a Pareto front method is used for solving an optimal solution set, wherein the Pareto front method is a multi-objective optimization method based on non-inferior sorting, and can find out a group of optimal solutions which are not mutually dominant, namely, solutions which cannot cause deterioration on one objective when the solution is improved on the other objective. Thus, different requirements and preferences of users on the low-odor fermentation effect and the fertility value can be met.
In conclusion, the research evaluates the low-odor characteristics of the multi-strain collaborative fermentation of the fish manure and the waste through various indexes, and compares the low-odor characteristics with the control group of unfermented or single-strain fermentation, and the result shows that the multi-strain collaborative fermentation can effectively remove or reduce the odor substances in the fish manure and the waste, achieves the effect of low odor or slight odor, and is superior to single-strain fermentation. The method for preparing the multi-strain synergistic fish fertilizer and the wastes has the obvious low-odor characteristic, can improve the quality and market value of the organic fertilizer, reduce environmental pollution and resource waste, and increase peasant income and agricultural sustainable development.
According to the preset content, the following specific experiment verification process is carried out, and the actual content is as follows:
the purpose of the experiment is to verify the effectiveness and feasibility of the processing technology for producing the low-odor fertilizer by fermenting the fish fertilizer and the waste. The experiment adopts the following steps:
preparing materials and equipment such as fish manure and wastes (viscera, fish scales, fish gills, fish fins and the like), aspergillus oryzae, saccharomycetes, actinomycetes, bacillus subtilis and the like.
1-1 materials and reagents
The fish manure and waste (viscera, fins, scales, tails, etc.) are collected in a fishing port in three parts of the city, hainan province.
Aspergillus oryzae powder (1×10) 10 CFU/g) Shandong and Zhongkangyuan biotechnology limited; high activity dry yeast (2X 10) 8 CFU/g) Angel Yeast Co., ltd; actinomycete powder (1 x 10) 10 CFU/g) Shandong and Zhongkangyuan biotechnology limited; bacillus subtilis powder (1 x 10) 11 CFU/g) Shandong and Zhongkangyuan biotechnology limited; brown sugar WeifangYingxuan Utility Co., ltd; concentrated sulfuric acid (analytically pure) of the company schlongsu sciences;
1-2 instruments and apparatus
An adjustable low temperature incubator (HWS-120G) Shanghai Prolin electronic technologies Co., ltd; water quality detector (LBII|D60) Henan Sunjing environmental protection technology Co., ltd; multifunctional intelligent digestion instrument (SJ-16X) Henan Sunjing environmental protection technology Co., ltd; electronic analytical balance (BH-C6001) Penthorn weighing apparatus Co., ltd; soil detector (HDHM-TYC) Hengmei electronic technology Co., ltd; biological safety cabinet (BSC-1300 II A2) Shanghai clean medical instruments Co., ltd; electrothermal blowing drying oven (WGLL-30 BE) Teste instruments, inc. of Tianjin.
Mechanically crushing the fish manure and the waste to make the granularity smaller than 5mm.
2-1, specific experimental procedure: mechanically crushing the fish manure and the waste to make the granularity smaller than 5mm. And (3) putting the fish manure and the waste into a pulverizer, regulating the rotating speed to 3000r/min, and pulverizing for 10min to obtain the fish manure and the waste powder with uniform granularity.
3. The crushed fish fertilizers and wastes are adjusted to have the moisture content of 55 percent, are placed in a fermentation tank, and are piled into a fermentation pile with the height of 1.2 m.
3-1, specific experimental process: the crushed fish manure and waste are piled into a fermentation pile with the height of 1.2m by adjusting the water content to 55 percent, and the fish manure and the waste are suitable for being squeezed by hands to have water drops but not to drop. Stacking the mixed materials on plastic cloth, and covering with plastic cloth to form a cylindrical fermentation pile with a height of 1.2m and a diameter of 1.5 m.
4. Inoculating Aspergillus oryzae, yeast, actinomycetes and Bacillus subtilis into the fermentation pile, wherein Aspergillus oryzae, yeast, actinomycetes and Bacillus subtilis are Aspergillus oryzae, saccharomyces cerevisiae, streptomyces sp. And Bacillus subtilis respectively, and have a ratio of 1×10 respectively 10 CFU/g、2×10 8 CFU/g、1×10 10 CFU/g and 1X10 11 The viable count of CFU/g, wherein the inoculation proportion of Aspergillus oryzae, saccharomycetes, actinomycetes and bacillus subtilis is Aspergillus oryzae, saccharomycetes and bacillus subtilisLine bacillus, bacillus subtilis=1.2:0.4:2.7:2.9, total inoculum size is 2% of dry weight of fermentation pile, and uniformly stirred; mixing Aspergillus oryzae, yeast, actinomycetes and bacillus subtilis according to a proportion, diluting with water to 20 times, uniformly spraying on a fermentation pile, inserting a bamboo stick every 20cm, digging a small hole at the bamboo stick by hand, pouring mixed strain liquid into the hole, and covering the hole by hand to enable the strain to be fully contacted with materials. The surface of the fermentation pile is covered by plastic cloth, and the temperature and the humidity are kept.
According to pre-experiment and reference, aspergillus oryzae, yeast, actinomycetes and Bacillus subtilis are selected as fermentation composite strains, and the optimal interval of each strain is set to be 0.4-2.8 g (1×10) of Aspergillus oryzae 10 CFU/g), yeast 0.4-3.6 g (2X 10) 8 CFU/g), actinomycetes 0.8-4.0. 4.0 g (1X 10) 10 CFU/g), bacillus subtilis 0.8-4.8 g (1X 10) 11 CFU/g), carrying out response surface experimental design;
5. the inoculated fermentation pile is gradually sent into a fermentation box and piled up, the set temperature is 32 ℃, the fermentation pile is kept for 4d, then the fermentation pile is raised to 4 ℃ every day until 56 ℃ for 9 days, and the fermentation is finished. In the fermentation process, the materials are turned over in the box every 2 days to fully mix, and simultaneously, the ventilation is carried out to remove carbon dioxide and water vapor.
6. After fermentation, obtaining a low-odor organic fertilizer, wherein in the step, the inner wall of a fermentation tank is provided with bubble zeolite particles for adsorption operation;
the appearance and smell of the low-odor organic fertilizer are observed, the low-odor organic fertilizer should be dark brown or black, have weak yeast flavor or alcohol flavor, and have no fishy smell or bitter taste.
7. And measuring indexes such as odor sensory score, ammonia nitrogen content, total nitrogen content, quick-acting potassium content, effective phosphorus content and the like of the obtained low-odor organic fertilizer, and comparing and analyzing the indexes with unfermented fish fertilizers and wastes.
Performing actual odor sensory scoring according to a preset method;
table 1-sensory evaluation of fermentation products table:
the determination of ammonia nitrogen content, total nitrogen content, quick-acting potassium content and available phosphorus content was performed according to the following method, and data were recorded. Comparing and analyzing the low-odor organic fertilizer with the unfermented fish fertilizer and the waste, and evaluating the effect of the fermentation process;
the determination of the ammonia nitrogen content refers to a Nahner reagent spectrophotometry for determination of ammonia nitrogen in water (HJ 535-2009); determination of total nitrogen content reference "determination of total nitrogen in Water quality alkaline Potassium persulfate digestion ultraviolet Spectrophotometry" (HJ 636-2012); detecting ammonia nitrogen content and total nitrogen content in the compost product by adopting a water quality detector (LBII|D60), wherein the detection result is calculated on a dry basis (mg/g); the quick-acting potassium and effective phosphorus content of the compost products is measured by adopting a soil detector, and the quick-acting potassium and effective phosphorus content is not changed greatly in the fermentation process, so that the quick-acting potassium and effective phosphorus content is not used as a fermentation effect judging factor in the study, referring to NY/T525-2012.
8. According to the experimental design of the response surface, carrying out data analysis and predictive modeling by using JMP software, taking comprehensive scores as response values (Y), taking the inoculation amounts of aspergillus oryzae, saccharomycetes, actinomycetes and bacillus subtilis as four factors (X), constructing a neural network predictive model, and carrying out model verification and optimization;
with the inoculum size of Aspergillus oryzae, yeast, actinomycetes and Bacillus subtilis as four factors, 27 experimental groups were designed with a Box-Behnken response surface design, and each experimental group was repeated three times. The actual experimental factors and levels are shown in table 2; establishing a low-odor fermentation process factor level table, taking odor sensory scores, ammonia nitrogen (NH 3-N) and Total Nitrogen (TN) content as evaluation indexes, establishing a comprehensive score equation (formula 1), taking the comprehensive scores as response values, optimizing a fermentation process, and modeling;
table 2-actual factor level table:
comprehensively judging the quality of the fermentation product according to the requirements of pre-experiments and expected experimental results, wherein the odor sensory score, the ammonia nitrogen content in the fermentation broth and the total nitrogen content are three evaluation indexes, and the three evaluation indexes are calculated according to 1:0.5: setting a comprehensive scoring formula (formula 1) according to the proportion of 0.5 to comprehensively reflect the smell and fertility of the fermentation product;
equation 1:；
wherein:
-a comprehensive score value;
-an odor sensory score value;
-total nitrogen content measurement;
-total nitrogen content measurement maximum;
-ammonia nitrogen content measurement;
-maximum ammonia nitrogen content measurement;
fitting and predicting test data based on JMP software 'analysis-prediction modeling-model screening', constructing different types of prediction models, selecting inoculum sizes of Aspergillus oryzae, saccharomycetes, actinomycetes and bacillus subtilis as four factors, taking comprehensive scores as response values, and comparing the models to give R 2 Value, selecting the optimal modeling methodSelecting.
According to the experimental value measured by the response surface test, a preferable modeling method is adopted to draw a predicted value-actual value diagram and a predicted value-residual value diagram, and training R after fitting operation is carried out 2 And verifying and evaluating the established prediction model by the value. Based on the comparison and analysis of the predicted value obtained by the model and the actual value and residual value obtained by the test, verifying the validity of the selected predicted model;
obtaining optimal fermentation process parameters by using the established prediction model, carrying out a related experiment, and verifying the validity and the authenticity of the established model by comparing an actual response value with a predicted response value and calculating a model relative error (formula 2);
equation 2:；
wherein:
is the relative error;
is the actual response value;
to predict the response value.
Response surface experimental design and results;
the study was based on JMP Pro 16.0.0 software, and response surface test designs, test design tables and results are shown in Table 3, and modeling model optimization was performed:
table 3 actual response surface experimental results:
table 4 screening of predictive models (R-based 2 ）
As can be seen from table 4, the prediction model R established based on the neural network modeling method 2 The value is maximum, so that a neural network modeling method is selected to establish a prediction model for researching the fermentation process;
9. obtaining optimal fermentation process parameters according to a prediction model, performing a related experiment, and verifying the validity and the authenticity of the established model by comparing an actual response value with the prediction response value and calculating a model relative error;
and carrying out experimental verification of the prediction model according to the method, and recording data. Comparing the actual response value with the predicted response value, calculating the relative error of the model, and evaluating the effectiveness and the authenticity of the model;
in JMP software, the activation functions that can be used to construct the neural network-hidden layer are provided as an activation sigmoid tanH, an identity linear and radial Gaussian. As can be seen from FIG. 2, the activation function using linearity works the least, the number of nodes increases versus R 2 The value is not obviously improved, and the fitting effect is poor;
the fitting effect (based on R2) of three activation functions of S-shaped TanH, identity linearity and radial Gaussian on the test is compared and activated, and the S-shaped TanH and the radial Gaussian are selected as the activation functions for constructing a hidden layer in a neural network prediction model, so that the built model can obtain the prediction which tends to an actual value;
the neural network is essentially a fitting of a high-dimensional model, fitting of multi-dimensional data by finding a set of matrix parameters (i.e., the model), and stabilizing the error between the predicted and actual values by modifying the parameters. The working principle is approximately as follows: experimental data arrives at the hidden layer from the input layer, which is equivalent to mapping an input into a high-dimensional space, performing curve fitting in the high-dimensional space, and finally arriving at the output layer by means of a linear function.
The study adopts 'predictive modeling-nerve' in JMP Pro 16.0.0 software to construct a double-layer fully connected perceptron, takes comprehensive scores as response (Y), takes respective inoculum sizes of aspergillus oryzae, saccharomycetes, actinomycetes and bacillus subtilis as four factors (X) to construct a neural network prediction model, sets a retention ratio to be 0.15 (used for verifying a fitting effect of a predicted value), sets random seeds to be 3 (generating a reproducible result), sets two hidden layers, and selects an activated S-shaped TanH layer and a radial Gaussian layer as activation functions in the hidden layers, as shown in figure 3;
in order to verify the overall effectiveness and rationality of a prediction model constructed based on a neural network, a 'predicted value-actual value' graph (fig. 4) is drawn according to the method, wherein the horizontal axis of the graph is a predicted value, and the vertical axis is an actual response value. The graph shows that the actual value is distributed near the 45-degree straight line, so that the matching degree of the predicted value and the actual value is good, the actual value can be better fitted by adopting a neural network, and the model is reasonable and effective in whole;
according to a graph of predicted value-residual value (see fig. 5), the deviation between the predicted value and the actual value is estimated, the data points of the response value are mostly distributed near the X axis, the discrete degree is approximate in the whole predicted value range, no regularity exists, and the good fitting effect of the constructed predicted model can be further illustrated;
the JMP Pro 16.0.0 software is used for running the model of TanH (5) NGaussian (4) TanH2 (6) NGaussian2 (4) for multiple times to perform fitting, and the fitting results are good. Training R 2 Value and measurement R 2 The values are comparable and close to 1, indicating that the model can predict well the data that is not used to train the model. Because the uncontrollable factors influencing the comprehensive score in the fermentation process are more, when training R 2 When the value is greater than 0.7, the fitting effect of the constructed model can be considered to be better in general, and the table 5 is shown;
table 5 neural network fitting operation results:
after the prediction model is built and the data are fitted, a prediction plotter (figure 6) of the comprehensive score and the independent variable can be obtained, and the positive and negative slopes of the marked lines can indicate the relationship between the comprehensive score and the independent variable. The graph shows that the slope of the carved line of the factor corresponding to the inoculum size of the aspergillus oryzae is the largest, and the influence on the response value is the most remarkable, which is possibly related to the fact that the aspergillus oryzae secretes a multienzyme system in the fermentation process to well degrade organic matters to generate effective nitrogen, and curved substances can be generated in the metabolism process to well mask bad smell. The prediction characterizer shows that the four bacteria are mutually influenced and the comprehensive score of the final fermentation product is influenced, and the significance of the inoculation amount of each strain is shown as follows: aspergillus oryzae > actinomycetes > saccharomycetes > bacillus subtilis;
in the prediction characterizer, the prediction integrated score value may be obtained by a method of moving a vertical dotted line. Regulating a predictive sketcher, and when the total inoculation amount is 2% and the composting time is 9d, the optimal inoculation proportion of each strain is aspergillus oryzae: yeast: actinomycetes: bacillus subtilis = 1.2:0.4:2.7:2.9, the comprehensive score is 85.36927, the response value is the highest value, the predicted value is in the experimental value range, the model is feasible, and the optimization result is reliable.
In addition, the change condition of the comprehensive score can be more intuitively represented by a curve characterizer, the predicted value of the comprehensive score is characterized, and the corresponding predicted value of the comprehensive score can be obtained by manually sliding the slider of the independent variable, as shown in fig. 7;
in conclusion, JMP Pro 16.0.0 software is adopted in research, comprehensive scores are predicted based on a neural network prediction modeling mode, the overall effect is good, effective prediction can be provided for low-odor fermented fish fertilizers and wastes, resource recycling is realized, and a research method adopting the neural network prediction modeling can provide a method foundation for predicting aquatic product offal fermentation compost products;
three prediction results (see table 6) are screened out through the prediction of the prediction model, experiments are carried out respectively, and the obtained results are shown in table 7;
table 6 predictive model validation experiment table
TABLE 7 relative error of predicted and actual response values
As can be seen from table 7, the actual response value and the predicted value have smaller difference, the prediction effect is better, and the reasons for the difference may be: (1) The input value data quantity of the prediction model is relatively small (only 27) and can lead to small numerical value quantity of the input layer of the neural network, the mathematical fitting effect for the middle layer is poor, and the prediction effect is slightly deviated; (2) The predictive training has a random difference, because JMP software performs random extraction on input data when fitting training is performed, so that each time of operation results are different and the predictive effect is deviated due to the deviation of experimental data; (3) The final prediction result is affected by the content difference of some substances (such as calcified fishbone and the like) which can not be degraded by fermentation microorganisms in the fish manure and the waste;
by comparing the predicted response value with the actual response value, the error range of the predicted response value and the actual response value is within 30%, which indicates that the predicted effect of the prediction model can reach the expected effect. Therefore, the prediction model has application value and can provide a beneficial reference for the prediction of the composite strain fermentation process conditions;
to sum up:
the research is based on JMP software, a response surface experiment is designed, a prediction model is established by a neural network modeling method, and optimization and prediction research are carried out on a low-odor fermentation process of fish manure and wastes (viscera, fish scales, fish gills, fish fins and the like), so that the following conclusion is obtained:
(1) The strains used for fermentation are Aspergillus oryzae, yeast, actinomycetes and Bacillus subtilis;
(2) Through the experimental design of the response surface, the optimal strain proportion of the low-odor fermentation process is predicted by using a dynamic prediction sketcher, the formed prediction curved surface can intuitively show the influence of each factor on the low-odor fermentation effect, the significance of each factor is analyzed, and the result shows that the significance is as follows: aspergillus oryzae > actinomycetes > yeast > Bacillus subtilis, when the total inoculum size is 2%, the temperature program is set at 32 ℃ for 4 days, and then the temperature is increased by 4 ℃ every day until 56 ℃, the optimal inoculum size ratio is Aspergillus oryzae: yeast: actinomycetes: bacillus subtilis = 1.2:0.4:2.7:2.9, the comprehensive score under the condition can reach 85.369;
(3) After the comparison analysis and verification of the prediction model, the constructed neural network prediction model can meet the effect prediction of the multi-strain synergistic fish manure and the waste low-odor fermentation products.
The research is conducted on the low-odor fermentation process of the fish manure and the waste, and the research finds that the influence factors of the multi-strain synergistic fermentation of the fish manure and the waste to produce the product are complex, so that the deep research is conducted on the balance of low odor and fertility of the fermentation product, and theoretical basis and technical reference can be provided for the subsequent research of the composite strain fermentation aquatic product offal through the determination of the fermentation strain, the construction of a prediction model and the significance analysis of each factor.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. The method for fermenting the fish manure and the waste low-odor fertilizer based on the neural network multi-strain is characterized by comprising the following steps of: the method comprises the following steps:
step 1, crushing:
pulverizing fish fertilizer and waste to particle size smaller than 5mm, and mixing;
step 2, inoculating strains:
inoculating Aspergillus oryzae, yeast, actinomycetes and Bacillus subtilis into the mixture;
step 3, temperature control;
step 4, finishing fermentation;
for specific fermentation parameters, adopting a response surface experimental design and a neural network model to optimize parameters in the process; adopting a response surface experimental design and a neural network model, and optimizing parameters by taking the low-odor fermentation effect as a consideration factor;
the specific low-odor fermentation effect is comprehensively scored according to the following calculation formula:
wherein:
z-comprehensive score value;
g-odor sensory score value;
TN-total nitrogen measurement;
TN max -total nitrogen content measurement maximum;
NH 3 -n—ammonia nitrogen content measurement;
(NH 3 -N) max -maximum ammonia nitrogen content measurement;
specific parameters according to the comprehensive scoring result are as follows:
in step 2: the inoculation proportion of the aspergillus oryzae, the saccharomycete, the actinomycetes and the bacillus subtilis is that the aspergillus oryzae, the saccharomycete, the actinomycetes and the bacillus subtilis are 1.2:0.4:2.7:2.9, the total inoculation amount is 2 percent of the dry weight of the fermentation pile, and the fermentation pile is uniformly stirred; the Aspergillus oryzae, yeast, actinomycetes and Bacillus subtilis have a total weight of 1×10 10 CFU/g、2×10 8 CFU/g、1×10 10 CFU/g and 1X10 11 Number of viable bacteria of CFU/g;
in step 3: placing the inoculated ferment in a ferment box with controllable temperature, setting the temperature program to be 32 ℃ for 4d, then raising the temperature to 56 ℃ every day, and stirring and ventilating periodically;
in step 4: and after the fermentation temperature reaches 56 ℃, maintaining the temperature unchanged, and continuously fermenting for 9 days to finish the fermentation so as to obtain the low-odor organic fertilizer.
2. The method for fermenting the fish manure and the waste low-odor fertilizer based on the neural network multi-strain according to claim 1, which is characterized in that: the obtained low-odor organic fertilizer has the following characteristics that the odor sensory score is more than or equal to 80 minutes; ammonia nitrogen content less than or equal to 0.5%; the total nitrogen content is more than or equal to 3%; the content of quick-acting potassium is more than or equal to 0.8%; the content of available phosphorus is more than or equal to 0.6 percent.
3. The method for fermenting the fish manure and the waste low-odor fertilizer based on the neural network multi-strain according to claim 1, which is characterized in that: the fermentation box is a closed container with adjustable temperature and humidity and ventilation.
4. The method for fermenting the fish manure and the waste low-odor fertilizer based on the neural network multi-strain according to claim 3, which is characterized in that: the crushing treatment is mechanical crushing or biological crushing or a combination of the two.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311563528.5A CN117285382B (en) | 2023-11-22 | 2023-11-22 | Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311563528.5A CN117285382B (en) | 2023-11-22 | 2023-11-22 | Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117285382A CN117285382A (en) | 2023-12-26 |
| CN117285382B true CN117285382B (en) | 2024-04-05 |
Family
ID=89248318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311563528.5A Active CN117285382B (en) | 2023-11-22 | 2023-11-22 | Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117285382B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117647928B (en) * | 2024-01-30 | 2024-04-09 | 南京农业大学 | Crop straw fodder utilization system and method based on RNN neural network |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101793886A (en) * | 2010-03-24 | 2010-08-04 | 北京林业大学 | Sensory evaluation method for predicting fermented yogurt based on BP neural network |
| KR101029346B1 (en) * | 2009-10-28 | 2011-04-13 | 주식회사 엠투원 | Combined microorganism fermented liquors having the effect of reducing odor gas and antibacterial effect, and methods of using the same |
| CN103667117A (en) * | 2013-11-18 | 2014-03-26 | 广西金穗生物科技有限责任公司 | Compound microbial bacterium for aerobic fermentation stage |
| CN104030746A (en) * | 2014-06-24 | 2014-09-10 | 湖南豫园生物科技有限公司 | Organic material decomposition agent, biological organic fertilizer containing tobacco wastes, and production method and application method of biological organic fertilizer |
| CN104844292A (en) * | 2015-04-29 | 2015-08-19 | 漳州三本肥料工业有限公司 | Method for preparing fertilizer by using shrimp wastes and product thereof |
| CN105069323A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Memetic algorithm based microbial fermentation control and optimization method |
| CN105069220A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method |
| CN105373669A (en) * | 2015-11-28 | 2016-03-02 | 泰山医学院 | Pholiota adiposa fermentation condition optimization and dynamic model construction method |
| CN106511448A (en) * | 2016-11-18 | 2017-03-22 | 浙江中医药大学 | R language-based optimal extraction technology for extracting saponin and total flavonoids in liquorice |
| KR20170052007A (en) * | 2015-11-03 | 2017-05-12 | 이정선 | Method of broth for food additives using extract from skipjack tuna |
| CN107365725A (en) * | 2017-08-01 | 2017-11-21 | 山东农大肥业科技有限公司 | A kind of organic matter decomposing inoculant and preparation method thereof |
| KR20180006242A (en) * | 2016-07-09 | 2018-01-17 | 장용석 | Fertilizer compositions and methods for their preparation, including marine waste algae and Fish farm waste flounder fish |
| KR20180077984A (en) * | 2016-12-29 | 2018-07-09 | 조명현 | A Method for Removing Malodor and Making Liquid Fertilizer of Livestock Excretions |
| CN109021044A (en) * | 2018-07-10 | 2018-12-18 | 浙江中医药大学 | The extraction process of aurantiamarin in thoroughfare Fructus Aurantii |
| CN109607816A (en) * | 2018-12-11 | 2019-04-12 | 深圳合民生物科技有限公司 | A kind of microorganism deodorant and its preparation method and application |
| CN109928786A (en) * | 2017-12-15 | 2019-06-25 | 广州天粤农业科技有限公司 | A kind of microbial organic fertilizer and preparation method thereof |
| CN112322530A (en) * | 2020-11-04 | 2021-02-05 | 深圳市家家分类环保技术开发有限公司 | Functional microbial inoculum for degrading seafood kitchen garbage as well as preparation method and application thereof |
| CN114956908A (en) * | 2022-05-31 | 2022-08-30 | 海南万禾保生物科技有限公司 | Deep sea fish peptide composite microbial fertilizer and preparation method thereof |
| WO2023006778A1 (en) * | 2021-07-26 | 2023-02-02 | Dsm Ip Assets B.V. | A method and system for determining a quantitative composition ratio of a microbial strain mixture for use in a fermentation process |
| CN116682494A (en) * | 2023-05-30 | 2023-09-01 | 中国科学院微生物研究所 | Method for monitoring microbial community structure in fermentation process |
-
2023
- 2023-11-22 CN CN202311563528.5A patent/CN117285382B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101029346B1 (en) * | 2009-10-28 | 2011-04-13 | 주식회사 엠투원 | Combined microorganism fermented liquors having the effect of reducing odor gas and antibacterial effect, and methods of using the same |
| CN101793886A (en) * | 2010-03-24 | 2010-08-04 | 北京林业大学 | Sensory evaluation method for predicting fermented yogurt based on BP neural network |
| CN103667117A (en) * | 2013-11-18 | 2014-03-26 | 广西金穗生物科技有限责任公司 | Compound microbial bacterium for aerobic fermentation stage |
| CN104030746A (en) * | 2014-06-24 | 2014-09-10 | 湖南豫园生物科技有限公司 | Organic material decomposition agent, biological organic fertilizer containing tobacco wastes, and production method and application method of biological organic fertilizer |
| CN104844292A (en) * | 2015-04-29 | 2015-08-19 | 漳州三本肥料工业有限公司 | Method for preparing fertilizer by using shrimp wastes and product thereof |
| CN105069323A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Memetic algorithm based microbial fermentation control and optimization method |
| CN105069220A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method |
| KR20170052007A (en) * | 2015-11-03 | 2017-05-12 | 이정선 | Method of broth for food additives using extract from skipjack tuna |
| CN105373669A (en) * | 2015-11-28 | 2016-03-02 | 泰山医学院 | Pholiota adiposa fermentation condition optimization and dynamic model construction method |
| KR20180006242A (en) * | 2016-07-09 | 2018-01-17 | 장용석 | Fertilizer compositions and methods for their preparation, including marine waste algae and Fish farm waste flounder fish |
| CN106511448A (en) * | 2016-11-18 | 2017-03-22 | 浙江中医药大学 | R language-based optimal extraction technology for extracting saponin and total flavonoids in liquorice |
| KR20180077984A (en) * | 2016-12-29 | 2018-07-09 | 조명현 | A Method for Removing Malodor and Making Liquid Fertilizer of Livestock Excretions |
| CN107365725A (en) * | 2017-08-01 | 2017-11-21 | 山东农大肥业科技有限公司 | A kind of organic matter decomposing inoculant and preparation method thereof |
| CN109928786A (en) * | 2017-12-15 | 2019-06-25 | 广州天粤农业科技有限公司 | A kind of microbial organic fertilizer and preparation method thereof |
| CN109021044A (en) * | 2018-07-10 | 2018-12-18 | 浙江中医药大学 | The extraction process of aurantiamarin in thoroughfare Fructus Aurantii |
| CN109607816A (en) * | 2018-12-11 | 2019-04-12 | 深圳合民生物科技有限公司 | A kind of microorganism deodorant and its preparation method and application |
| CN112322530A (en) * | 2020-11-04 | 2021-02-05 | 深圳市家家分类环保技术开发有限公司 | Functional microbial inoculum for degrading seafood kitchen garbage as well as preparation method and application thereof |
| WO2023006778A1 (en) * | 2021-07-26 | 2023-02-02 | Dsm Ip Assets B.V. | A method and system for determining a quantitative composition ratio of a microbial strain mixture for use in a fermentation process |
| CN114956908A (en) * | 2022-05-31 | 2022-08-30 | 海南万禾保生物科技有限公司 | Deep sea fish peptide composite microbial fertilizer and preparation method thereof |
| CN116682494A (en) * | 2023-05-30 | 2023-09-01 | 中国科学院微生物研究所 | Method for monitoring microbial community structure in fermentation process |
Non-Patent Citations (7)
| Title |
|---|
| 人工神经网络在食品微生物发酵中的应用;李季;蒲彪;;食品研究与开发(第04期);第171-174页 * |
| 响应面法与基于神经网络的遗传算法在优化棉粕固态发酵中外源添加物用量上的应用;汤江武;孙宏;姚晓红;吴逸飞;王新;;浙江大学学报(农业与生命科学版)(第01期);第97-102页 * |
| 响应面法和神经网络优化Acinetobacter sp.DNS32发酵基质;王洋;王志刚;王溪;郭火生;孟冬芳;张颖;;环境工程学报(第02期);第791-795页 * |
| 固体发酵过程参数检测与优化控制;朱湘临;朱忠平;刘叶飞;常震红;;自动化与仪表(第11期);第6-9, 13页 * |
| 基于神经网络的发酵时间和最优发酵温度模型;杨旭华, 戴华平, 孙优贤;化工自动化及仪表(第01期);第18-21页 * |
| 布拉酵母高密度发酵培养基及发酵工艺优化;刘开放等;食品科学;第第40卷卷(第第8期期);第56-62页 * |
| 微生物发酵过程优化控制技术进展;王建林;冯絮影;于涛;薛尧予;;化工进展(第08期);第1210-1214页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117285382A (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104211537B (en) | Rhizoma Nelumbinis environment-friendly fertilizer and preparation method thereof | |
| Awasthi et al. | Evaluation of microbial dynamics during post-consumption food waste composting | |
| CN101786911B (en) | Microorganism and enzyme powder composite biological agent for microbial organic fertilizer | |
| CN104211505B (en) | Biological organic fertilizer and preparation method thereof | |
| CN103232944B (en) | Microorganism bacterium agent for straw and excrement mixed composting | |
| CN102617208B (en) | Edible fungus residue organic fertilizer raw materials and preparation method thereof | |
| CN105462878B (en) | A kind of efficient decomposing agent of feces of livestock and poultry and its fermentation process | |
| CN105218254A (en) | A kind of Microbial and ecological organic fertilizers material and preparation method thereof | |
| CN117285382B (en) | Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network | |
| CN109022327B (en) | Preparation method of microbial mixed inoculant and application of microbial mixed inoculant in high-temperature composting | |
| CN103098981B (en) | Dewatered solid combined inoculant for increasing protein level of citrus pulp feed and preparation method of dewatered solid combined inoculant | |
| Ngampimol et al. | The study of shelf life for liquid biofertilizer from vegetable waste | |
| CN106916767A (en) | A kind of composite bacteria agent and its degrade fowl and animal excrement in cellulose application | |
| CN103820339A (en) | Dehydrated solid composite microbial agent capable of increasing albumen level of cassava residue and preparation method of dehydrated solid composite microbial agent | |
| CN106045677A (en) | Method for preparing organic compound biological fertilizer special for fruit trees | |
| CN101648827A (en) | Fermented biological organic fertilizer and processing method thereof | |
| CN104543399B (en) | A kind of preparation method of yeast selenium forage additive | |
| Weng et al. | Biodegradation of free gossypol by a new strain of Candida tropicalis under solid state fermentation: Effects of fermentation parameters | |
| CN105754888A (en) | Bacillus licheniformis and microbial agent and their application in fermentation bed culture | |
| CN105255761A (en) | Deodorization fungicide for treating organic waste materials and application method thereof | |
| CN107500989A (en) | A kind of preparation method of environment-friendly type fermented organic fertilizer | |
| CN108383653A (en) | A kind of method and bio-organic fertilizer preparing fertilizer using stalk | |
| CN105016888A (en) | Microbe based on straw waste and preparation method of fertilizer by fermentation by using microbe | |
| CN102786327B (en) | Biological organic fertilizer produced from abamectin fermentation waste residue and preparation method thereof | |
| CN105037045A (en) | Soybean nutrient solution as well as preparation and using methods of soybean nutrient solution |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ge Yingliang Inventor after: Deng Chunrui Inventor after: Wu Jianjiao Inventor after: Tian Qing Inventor after: Li Mingcui Inventor after: Zhong Ruiwen Inventor after: Liu Chenqiong Inventor after: Zhang Wei Inventor before: Ge Yingliang Inventor before: Zhong Ruiwen Inventor before: Li Mingcui Inventor before: Zhang Wei Inventor before: Liu Chenqiong |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |