Prediction of dissolved oxygen in pond culture water based on K-means clustering and gated recurrent unit neural network

Dissolved oxygen in water is an important ecological factor in ensuring the healthy growth of aquatic products, as hypoxic stress is known to restrict the growth of aquatic products. The accurate monitoring and prediction of dissolved oxygen is the key to precise regulation and control of pond aquaculture water quality. The current dissolved oxygen prediction model has some limitations, such as a short prediction period and inadequate prediction accuracy for actual production demands. Therefore, a prediction model of dissolved oxygen in pond culture was proposed based on K-means clustering and Gated Recurrent Unit (GRU) neural network. Firstly, the key factors affecting the changes in dissolved oxygen were selected by principal component analysis (PCA). The dissolved oxygen time series was then subjected to K-means clustering, and the dissolved oxygen prediction model was constructed using GRU. To improve the clustering effect, we enhanced the similarity calculation for the time series based on the variation of dissolved oxygen. This process combined the Euclidean distance with the dynamic time-warping distance. The proposed method can predict the dissolved oxygen content of aquaculture water over different time intervals according to the demands of real-world scenarios. The average absolute error of the 30-min interval model was 0.264, and the mean absolute percentage error was 3.5 %. Experimental results indicated that the proposed method achieves higher prediction accuracy and flexibility than the conventional approach.     

基于物联网和GIS的水产养殖测控系统平台设计

针对水产养殖水质多参数监测的需求和现有水质环境监测系统存在的问题,设计了一种基于物联网和地理信息系统(GIS)的水产养殖测控系统。通过整体性能的研究分析,设计了测控系统平台的3层体系架构(传感控制层、传输层和应用层),提出了自顶向下、逐步求精以及模块化、结构化的设计方法;根据采集数据传输的可靠性、稳定性等要求,提出WiFi网状组网的配置方法,设计了系统硬件的供电模块;研究了本地服务器、中心服务器和控制模块软件系统;通过网络丢包率测试和水质溶氧量分析,验证了系统数据传输的可靠性,并在溶氧超出范围后自动控制增氧机,有效地调节池塘溶氧量。相比于传统的水产养殖远程监控系统,该系统通过物联网和GIS技术的融合,实现了水质环境的远程无线测控和区域化水产养殖管理,因此能够大大推进水产养殖智能化、自动化系统建设的发展,适应水产养殖的需要。     

微孔曝气增氧技术应用现状

微孔增氧技术与传统增氧方式相比,不仅能增加水产养殖水体中的溶解氧量,尤其是中、下层水体均匀增氧,还能改善养殖池塘的生态环境。本文主要介绍微孔增氧机的工作原理及与其他增氧设备配套使用的优点。     

基于DSP的光伏推流系统设计及效果分析

为解决水产养殖中溶氧浓度低、分布不均衡及常规增氧设备能耗高的问题,设计了一种基于数字信号处理器(DSP)的光伏推流系统。该系统以TMS320F2812为主控芯片,通过电压、电流检测电路对太阳能光伏阵列的输出功率进行实时跟踪,实现对蓄电池充放电切换,并采用最大功率点跟踪(MPPT)方法保证了光伏阵列的最大功率输出。用该系统对长7 m、宽5 m、深1 m的浅水区域进行连续5 d的推流实验,并与相同条件下无推流时的溶氧浓度空间分布情况进行对比。结果显示,无推流情况下,试验区域从岸边到湖中溶氧浓度分布呈现由低到高的梯度分布;推流后的溶氧浓度空间分布趋于均衡,且比无推流时的浓度均值提高1~2 mg/L。研究表明,光伏推流能大大降低能耗,提高水体溶氧浓度,改善水体溶氧分布均衡性,对提高水产养殖的密度和产量具有现实意义。     

河蟹池塘养殖底层微孔曝气增氧技术的研究和应用

在2007年-2008年通过底层微孔曝气技术的开发应用，开展了河蟹池塘养殖增氧研究。结果表明养成河蟹规格和单产显著提高，池底增氧技术是河蟹池塘养殖中的关键控制技术，示范区、推广区河蟹的平均规格、单产、毛利比同期常规技术的一般平均水平分别提高了11．37％～36．26％、7．07％～28．49％；50．29％～71．67％、49．11％；177．51％．187．31％、122．2％；养蟹池塘水体DO、NH3-N、NO2—N、TN、TP、COD等主要水质指标明显优于对照池，总体达到地表水环境质量标准（GB3838—2002）Ⅲ类以上，并实现了养殖期内零排放，是一项节水、环保的新型水产养殖技术。     

上覆水类型及流速对养殖池塘底泥耗氧速率的影响

为了探究上覆水类型及流速对养殖池塘底泥耗氧速率(SOD)的影响,在实验室进行6组水池平行实验,实验期为2 d,采用6个装置相同的玻璃缸进行对照实验,分别选取自来水和池塘原水作为上覆水体,在实验过程中利用水泵对上覆水进行循环流动,调节水泵循环流量以得到不同的上覆水流速,并采用2台溶氧仪测定不同实验条件下的上覆水水温和DO浓度,记录每次测量的对应时间点,测量间隔约为30 min。结果表明,当上覆水体为自来水和池塘原水时,在不同的循环流速下,SOD的范围为0.042~0.426 g/(m~2·d)。实验第2天各水池的SOD值较第1天均有一定下降,说明SOD随着水体中DO降低也相应减小,表明SOD与DO浓度有显著相关性。当上覆水处于静止状态时,其类型对SOD值有较大的影响,池塘原水在第1天和第2天的SOD值分别为0.426 g/(m~2·d)和0.297 g/(m~2·d),而自来水在第1天和第2天的SOD值均为0.258 g/(m~2·d),与上覆水体为自来水相比,有机物质含量高的池塘原水在第1天和第2天的SOD值分别高出65.12%和15.12%;当上覆水处于流动状态时,池塘原水的SOD为0.042~0.237 g/(m~2·d),自来水的SOD为0.045~0.252 g/(m~2·d),增幅仅为5.9%~15.0%,表明在此条件下上覆水体类型对实验水池的SOD值影响不显著。SOD与上覆水流速存在一定的相关性,对应最小的SOD值有一个流速较低值。     

底充式增氧对改善池塘水质效果的初步研究

在凡纳滨对虾（Litopenaeus vannamei）和三疣梭子蟹（Portunus trituberculatus）养殖池塘中进行了底充式增氧对池塘水质改善效果试验。结果表明,增氧2～3h能减小或消除池塘温度和溶解氧（DO）跃层,显著提高池塘底层水体的ρ（DO）（P〈0.05）。在上午8：00～11：00这段时间开增氧机的效果最佳;试验池塘的氨氮（NH4＋-N）和亚硝酸盐（NO2--N）的质量浓度为对照池塘的72.5%～74.1%和2.6%～2.7%,能促进池塘氧化反应,降低有害物质的含量,改善池塘环境条件。     

基于分布式无线网络的水质监控系统设计

为提高对水产养殖水质监控的实时性和测量精度,设计了一种基于无线传感器网络的水产养殖水质参数监控系统。该系统由水质参数采集终端、分布式传感器网络、传输控制中心基站、远程在线监控系统组成。参数采集终端采集水质参数并传输到中心基站,再通过GPRS发送给远程在线监控中心,根据用户向监控中心输入的参数实现水温、pH、溶氧(DO)的调节。参数测量过程中引入数字滤波算法提高测量精度,使用经过改进粒子群优化算法(PSO)整定的PID控制器实现水质参数的调节。结果显示:测量精度达到要求,温度、pH和DO的测量误差分别为2.1%、1.3%和3.6%,系统对温度、pH和溶氧调节的最大误差分别为1.9%、2.6%和3.1%。整个系统工作稳定可靠。     

基于经验模态分解和最小二乘支持向量机的溶氧预测

养殖池塘中溶氧(DO)与鱼、蟹等水产品的生长有着十分密切的关系。为了提高DO的预测精度和有效性,提出了一种基于经验模态分解(EMD)和自适应扰动粒子群优化最小二乘支持向量机(LSSVM)的组合预测模型。首先将DO时间序列通过EMD分解成若干分量,接着对各个分量进行相空间重构,在相空间中用LSSVM对各分量进行建模预测,并使用自适应扰动粒子群算法对LSSVM的超参数进行优化,采用单点迭代法进行多步预测。结果显示:该模型与单一LSSVM预测模型相比,具有良好的预测效果。预测未来4 h DO值时,各项性能指标误差均方根(RMSE)、平均相对误差均值(MAPE)和平均绝对误差(MAE)三项指标分别降低了13.4%、11.3%和1.8%;预测未来24 h DO值时,三项指标分别降低了12.9%、12.1%和2.7%。研究表明:该组合模型可有效提取DO序列特性,具有较高的预测精度和泛化性能。     

循环水养殖半滑舌鳎成鱼摄食活动对主要水质因子的影响

在封闭循环水养殖条件下,半滑舌鳎(Cynoglossus semilaevis Günther)的平均养殖密度(15.07±0.22)kg/m3,观测半滑舌鳎的呼吸频率,检测养殖水体中溶氧、氨氮、亚硝酸氮等24 h内摄食和代谢的变化规律。结果表明:(1)半滑舌鳎摄食前、后的呼吸频率平均值分别为27.3次/min和34.7次/min,摄食后的呼吸频率显著高于摄食前;(2)投喂前、后2.5 h内,水中溶氧一直处于下降趋势,在摄食2.5 h后,水中溶氧处于稳定的上升趋势;(3)投喂后,氨氮、亚硝酸氮浓度显著增高,2.5 h后达到峰值,随后缓慢降低,在下次投喂前0.5 h达到最低值。说明半滑舌鳎摄食活动对循环水养殖水质的影响呈现规律性,也说明循环水养殖模式可以满足半滑舌鳎对水质的基本要求。     

An integrated recirculating aquaculture system (RAS) for land-based fish farming: The effects on water quality and fish production

To mitigate the serious water pollution caused by the rapid expansion of the aquaculture industry in recent years, the development of improved aquaculture systems with more efficient water usage and less environmental impact has become essential. In this study, a land-based recirculating aquaculture system (RAS) was established that consisted of purification units (i.e., a primary biological pond, two parallel horizontal subsurface flow constructed wetlands [CWs], and a long ecological ditch) and 4-5 series-connected recirculating ponds. This system was mainly designed to stock channel catfish (Ictalurus punctatus), fifteen spine stickleback (Spinibarbus sinensis) and yellow catfish (Pelteobagrus fulvidraco), and the culture efficacy was evaluated based on a 2-year field experiment covering two growing seasons. According to the results, the primary biological pond played a role in sedimentation or nutrient retention, although this was not as evident when the CWs were functioning. The water flowing through the wetland system at a hydraulic loading rate (HLR) of 600 mm/day displayed lower values for the temperature, pH, dissolved oxygen (DO), suspended solids, organic matter and nutrients, whereas the electrical conductivity (EC) was higher, suggesting the accumulation of dissolved solids in the system. Due to the recirculation treatment, the trophic status of the recirculating ponds increased gradually along the direction of the flow and was notably lower in comparison to the control. As a result, the fish production responded to the variation of the water quality, which was reflected in the measurements of culture efficacy (final weight, survival rate, SGR and yield). The three main rearing species showed a decreasing trend along the direction of the flow, which was higher compared to the control, whereas an opposite trend was observed for filter-feeding fish. A Pearson correlation analysis revealed that the main culture species were inclined to live in meso- or oligotrophic conditions, and the silver carp adapted to more eutrophic conditions. Because RAS can provide better environmental conditions year-round, the present culture method could be more suitable for species that are sensitive to water quality in typical subtropical areas.     

Reaction of common carp (Cyprinus carpio, L.) to oxygen deficiency in winter as an example for the suitability of radio telemetry for monitoring the reaction of fish to stress factors in pond aquaculture

The reaction of common carp (Cyprinus carpio L.) in an ice‐ and snow‐covered pond to depletion of dissolved oxygen (DO) in winter was recorded using radio telemetry. The carp moved from the deeper parts of the pond to the shallow areas near the tributary in search of better oxygenated water. Evidence was found that feeding occurred until December but ceased with the oxygen crisis. After the carp farmer started aeration to improve the oxygen supply, carp returned towards the deeper parts of the pond. The gross activity was significantly correlated with DO (P<0.001) and was not influenced by water temperature (P>0.05). The clear documentation of the carp's reaction to oxygen depletion suggests, that radio telemetry may be useful for investigating the effects of various stress factors on fish in pond aquaculture.     

基于．NET的池塘养殖数字化管理系统

为了促进水产养殖健康发展,基于．NET Framework技术作为开发环境,Access作为后台数据库开发了一套池塘养殖数字化管理系统,并对系统进行了硬件架构和软件设计。硬件架构由水质监测与管理系统、自动投饵系统和投喂决策系统组成。根据测量的水温、溶氧量和酸碱度等信息,结合鱼类生长需要形成合理的投喂量和最佳的投喂时间,实现池塘养殖数字化管理。应用试验表明,系统能够对养殖水体进行实时监测和控制,达到精准投喂,系统平均降低饲料系数20％,提高摄食量1．5～2．0倍。     

Diversified aeration facilities for effective aquaculture systems—a comprehensive review

The growing intensive aquaculture system around the world maintains a high stocking density, wherein it is essential to increase and sustain the optimum dissolved oxygen concentration (DO) through the provision of artificial aeration systems. The selection of an aerator is a crucial aspect of aquaculture operations. The selected aerator must be economically efficient and should be able to fulfill the requirement of oxygen supply in the pond water. The present study provides an extensive literature review on the importance of artificial aeration in aquaculture, the standard method of test for performance evaluation of an aerator, various aeration systems and their mechanisms, method to determine the numbers of aerator requirement, comparative studies of different type of aerators, and economic consideration in selection of aerators. In addition, a thorough analysis has been done to suggest the type of aerator that is economically viable and efficient for different pond volumes based on the performance data reported in the reviews. Therefore, this study may help the end-users (fish farmers) to select the best aerator based on their requirements.

     

Spatial and temporal succession of bacterial communities in three artificial fishponds

Fishponds are artificial yet dynamic environments. Microbes play a vital role in the conversion and metabolism of organic matter in aquaculture environments such as fishponds. Changes in bacterial community composition in three fishponds over a 5‐month period were investigated by sequencing the 16S rRNA gene through Illumina Miseq. A total of 2,195,879 sequences and 9,975 operational taxonomic units (OTUs) were obtained. Further analysis showed that the dominant phyla in three ponds were similar, including Proteobacteria, and Bacteroidetes. A comprehensive analysis of the diversity, redundancy analysis (RDA) and partial redundancy analysis (pRDA) showed a spatial‐temporal structural pattern in the bacterial communities. The bacterial community composition in the three fishponds was shaped more by spatial variation than by temporal variation. The effect of pond isolation was emphasized by the significant differences observed in the three fishponds. However, the temporal succession of bacterial communities in each pond exhibited a similar trend. Correlation analysis and RDA also indicated that temporal variation was significantly associated with TOC, TN and NO₂^?. This study would improve our understanding of the assembly mechanisms of a microbial structure in artificial pond ecosystems, and provide useful information for fishpond management.     

基于模糊神经网络的池塘溶解氧预测模型

在分析了池塘溶解氧影响因素的基础上，利用模糊神经网络良好的非线性逼近能力建立了池塘溶解氧的模糊神经网络预测模型。神经网络模型如采用常规的BP或其它梯度算法，常导致训练时间较长且易陷入局部极小点，本实验采用快速的粒子群优化算法对模糊神经网络进行训练，收敛速度明显加快。实验结果表明采用该方法预报溶解氧的预测精度较常规BP递推算法的预测精度明显提高，所采用的模型能对溶解氧进行可靠的预测，该方法为研制开发智能水质检测仪以及工厂化养殖工作奠定了基础，对实际生产具有一定的指导意义。     

A combined model of dissolved oxygen prediction in the pond based on multiple-factor analysis and multi-scale feature extraction

As dissolved oxygen (DO) is an important indicator of water quality in aquaculture, an accurate prediction for DO can effectively improve quantity and quality of product. Accordingly, a novel hybrid dissolved oxygen prediction model, which combines the multiple-factor analysis and the multi-scale feature extraction, is proposed. Firstly, considering that dissolved oxygen is affected by complex factors, water temperature and pH are chosen as the most relevant environmental factors for dissolved oxygen, using grey relational degree method. Secondly, the ensemble empirical mode decomposition (EEMD) is adopted to decompose the dissolved oxygen, water temperature and pH data into several sub-sequences, respectively. Then, the sample entropy (SE) algorithm reconstructs the sub-sequences to obtain the trend component, random component and detail component. Lastly, regularized extreme learning machine (RELM), a currently effective and stable artificial intelligent (AI) tool, is applied to predict three components independently. The prediction models of random component, detail component and trend component are RELM1, RELM2 and RELM3 respectively. The dissolved oxygen, water temperature and pH of the random component forms the input layer of RELM1, and predicted value of dissolved oxygen in the random component is the output layer of RELM1. The input and output of RELM2 and RELM3 are similar to that of RELM1. Final prediction results are obtained by superimposing three components predicted values. One of the main features of the proposed approach is that it integrates the multiple-factor analysis and the multi-scale feature extraction using grey correlation analysis and EEMD. Its performance is compared with several outstanding algorithms. Results for experiment show that the proposed model has satisfactory performance and high precision.     

中国水产养殖装备发展现状

水产养殖是我国渔业的最重要组成部分,水产养殖机械装备是现代水产养殖业发展的重要标志,绿色、高效的现代化水产养殖产业结构升级对水产养殖装备提出了更高的要求,基于装备与信息技术协同的智慧水产养殖成为现代渔业发展的新趋势。本文围绕池塘、工厂化、网箱、筏式以及底播养殖等我国主要养殖方式,梳理了当前水产养殖中常用的机械化装备和技术,并从环境监测、养殖对象感知、智能投喂、分级计数和养殖机器人等方向分析了我国水产养殖智能装备技术的研究进展,指出了制约我国水产养殖智能装备发展的关键问题。为实现我国从水产养殖大国向强国转变,融合机械装备和智能技术等两个领域的前沿技术,提出了“机械化、自动化、智能化并举”的水产养殖智能装备发展新思路。     

高效液相色谱法测定水产养殖底泥中呋喃唑酮残留量的研究

运用高效液相色谱建立了一种测定水产养殖底泥中呋喃唑酮残留量的方法。通过比较不同提取方法获得最佳的提取条件。结果表明，底泥样品用乙酸乙酯超声波法提取，无水硫酸钠去除水分，浓缩并用流动相溶解后上机检测，方法线性范围在0．01～1．00μg·mL^-1之间，相关系数为0．999，回收率为88．2％-92．6％，精密度（RSD）为0．88％～2．67％，检出限为1．0μg·kg^-1。该方法操作简便、提取快捷、准确性高、重复性强，可检测出泥样中痕量的呋喃唑酮，适用于水产养殖环境底泥中呋喃唑酮残留量的测定。     

池塘养殖水体净化技术

从池塘养殖水体污染现状入手,分别介绍了池塘养殖水体的净化原理与方法,重点分析了具有投资少、处理成本低、且不产生2次污染的生物净化技术,通过比较,认为生物净化技术在池塘养殖中有着更为广阔地应用和发展前景,是实现无公害养殖和内陆渔业可持续发展的可行之路。