In accordance with current problems such as odor pollution,long production period,consumption of a large amount of manpower and so on existing in chicken manure fermentation ,an environment friendly type of chicken ma...In accordance with current problems such as odor pollution,long production period,consumption of a large amount of manpower and so on existing in chicken manure fermentation ,an environment friendly type of chicken manure fermentation device is designed. The key parameters of the equipment are resonance activated tube and fermenting cellar. Resonance activated tube makes the activated water,which could improve obvi- ously the biodegradation rate of chicken manure. The aerator could provide enough oxygen to microbes,and the agitator could make oxygen evenly distributed across the chicken manure in fermenting cellar. The test shows that this equipment is high-efficiency,and only takes 7 days to make the chicken manure achieve the decomposed requirement. The organic matter content of composted chicken manure is 91.2%,C/N ratio is 18.8, MPN is 0.04, mortality of ascarid egg is 99.6% ,concentrations of NH3 and H2 S are 4.20 and 1.58 mg/m3, furthermore ,there is no offensive smell in the fermenting cellar. Therefore,the study can provide a pollution-free, high-efficiency, manpower saving fermentation equipment for organic fertilizer production by chicken manure in agriculture area.展开更多
The problems in equipment fault detection include data dimension explosion,computational complexity,low detection accuracy,etc.To solve these problems,a device anomaly detection algorithm based on enhanced long short-...The problems in equipment fault detection include data dimension explosion,computational complexity,low detection accuracy,etc.To solve these problems,a device anomaly detection algorithm based on enhanced long short-term memory(LSTM)is proposed.The algorithm first reduces the dimensionality of the device sensor data by principal component analysis(PCA),extracts the strongly correlated variable data among the multidimensional sensor data with the lowest possible information loss,and then uses the enhanced stacked LSTM to predict the extracted temporal data,thus improving the accuracy of anomaly detection.To improve the efficiency of the anomaly detection,a genetic algorithm(GA)is used to adjust the magnitude of the enhancements made by the LSTM model.The validation of the actual data from the pumps shows that the algorithm has significantly improved the recall rate and the detection speed of device anomaly detection,with the recall rate of 97.07%,which indicates that the algorithm is effective and efficient for device anomaly detection in the actual production environment.展开更多
基金Supported by National Table Poultry Industry Technology System ItemChina(CARS-42-G21)+1 种基金Technique Innovation Item of Jinan Colleges and AcademiesChina(201302053)
文摘In accordance with current problems such as odor pollution,long production period,consumption of a large amount of manpower and so on existing in chicken manure fermentation ,an environment friendly type of chicken manure fermentation device is designed. The key parameters of the equipment are resonance activated tube and fermenting cellar. Resonance activated tube makes the activated water,which could improve obvi- ously the biodegradation rate of chicken manure. The aerator could provide enough oxygen to microbes,and the agitator could make oxygen evenly distributed across the chicken manure in fermenting cellar. The test shows that this equipment is high-efficiency,and only takes 7 days to make the chicken manure achieve the decomposed requirement. The organic matter content of composted chicken manure is 91.2%,C/N ratio is 18.8, MPN is 0.04, mortality of ascarid egg is 99.6% ,concentrations of NH3 and H2 S are 4.20 and 1.58 mg/m3, furthermore ,there is no offensive smell in the fermenting cellar. Therefore,the study can provide a pollution-free, high-efficiency, manpower saving fermentation equipment for organic fertilizer production by chicken manure in agriculture area.
基金National Key R&D Program of China(No.2020YFB1707700)。
文摘The problems in equipment fault detection include data dimension explosion,computational complexity,low detection accuracy,etc.To solve these problems,a device anomaly detection algorithm based on enhanced long short-term memory(LSTM)is proposed.The algorithm first reduces the dimensionality of the device sensor data by principal component analysis(PCA),extracts the strongly correlated variable data among the multidimensional sensor data with the lowest possible information loss,and then uses the enhanced stacked LSTM to predict the extracted temporal data,thus improving the accuracy of anomaly detection.To improve the efficiency of the anomaly detection,a genetic algorithm(GA)is used to adjust the magnitude of the enhancements made by the LSTM model.The validation of the actual data from the pumps shows that the algorithm has significantly improved the recall rate and the detection speed of device anomaly detection,with the recall rate of 97.07%,which indicates that the algorithm is effective and efficient for device anomaly detection in the actual production environment.
