Neural Network Based Multi-level Fuzzy Evaluation Model for Mechanical Kinematic Scheme

To implement a quantificational evaluation for mechanical kinematic scheme more effectively,a multi-level and multi-objective evaluation model is presented using neural network and fuzzy theory. Firstly,the structure of evaluation model is constructed according to evaluation indicator system. Then evaluation samples are generated and provided to train this model. Thus it can reflect the relation between attributive value and evaluation result,as well as the weight of evaluation indicator. Once evaluation indicators of each candidate are fuzzily quantified and fed into the trained network model,the corresponding evaluation result is outputted and the best alternative can be selected. Under this model,expert knowledge can be effectively acquired and expressed,and the quantificational evaluation can be implemented for kinematic scheme with multi-level evaluation indicator system. Several key problems on this model are discussed and an illustration has demonstrated that this model is feasible and can be regarded as a new idea for solving kinematic scheme evaluation.

Fuzzy pattern recognition model of geological sweetspot for coalbed methane development

From the perspective of geological zone selection for coalbed methane(CBM) development, the evaluation parameters(covering geological conditions and production conditions) of geological sweetspot for CBM development are determined, and the evaluation index system of geological sweetspot for CBM development is established. On this basis, the fuzzy pattern recognition(FPR) model of geological sweetspot for CBM development is built. The model is applied to evaluate four units of No.3 Coal Seam in the Fanzhuang Block, southern Qinshui Basin, China. The evaluation results are consistent with the actual development effect and the existing research results, which verifies the rationality and reliability of the FPR model. The research shows that the proposed FPR model of geological sweetspot for CBM development does not involve parameter weighting which leads to uncertainties in the results of the conventional models such as analytic hierarchy process and multi-level fuzzy synthesis judgment, and features a simple computation without the construction of multi-level judgment matrix. The FPR model provides reliable results to support the efficient development of CBM.

Determination of amount of irrigation and nitrogen for comprehensive growth of greenhouse cucumber based on multi-level fuzzy evaluation

In the northwestern part of China,rational and efficient management of irrigation and nitrogen significantly affects the intensive production of greenhouse cucumbers(Cucumis sativus L).To evaluate the effects of different combinations of water use and nitrogen(N)on yield,quality,and profitability of the greenhouse cucumbers that planted in 2018 Spring,nine combined treatments were applied.Results indicated the optimal irrigation and nitrogen demands for yield,quality and other indicators were different.The irrigation amount significantly affected the yield,and the yield gradually increased with increasing in irrigation.Single fruit weight(SFW)was significantly affected by the amount of irrigation,nitrogen and their interactions,and the higher amounts of N and irrigation were beneficial to the increase of SFW.The partial factor productivity of the applied N(PFPN)gradually increased with the nitrogen amount decline.Irrigation water use efficiency(IWUE)was closely related to the amount of irrigation.The higher irrigation amount would lead to the lower IWUE.When the amounts of irrigation and nitrogen were at an intermediate level,the content of vitamin C(VC)reached the maximum.As the amount of nitrogen was increased or irrigation was decreased,the Nitrate content(NC)would increase.Free amino acid(FAA)and NC followed a similar variation.When the amounts of irrigation and nitrogen both were at medium levels,the total soluble sugar concentration(TSSC)reached the highest.The multi-level fuzzy evaluation method was used to evaluate different indicators of cucumber.The weights of indicators in the first and second layer were determined by analytic hierarchy process(AHP)and entropy weight method,respectively.Then the fuzzy algorithm was used to comprehensively evaluate all the treatments.The evaluation results show that T4(irrigation,1957.6 m3/hm2;N,210 kg/hm2)is the best strategy for greenhouse cucumber irrigation and nitrogen management in the northwestern part of China.

To Evaluate of the Self-dependent Innovation Ability of Equipment Manufacturing Enterprises in Shaanxi Province

For an enterprise, what is important is to have the self-dependent innovation ability so that it can en- hance the core competence unceasingly and acquire sustainable competitive advantages. In this paper, the indi- cator system of the self-dependent innovation ability of equipment manufacturing enterprises in Shaanxi province is constructed, in which includes 4 one-level indicators and 13 two-level indicators; and conducts empirical re- search by applying the multi-level fuzzy comprehensive evaluation method.

Data fusion of radar and IFF for aircraft identification

The problem of identification of friend-or-foe aircraft in the actual application condition is addressed.A hybrid algorithm combining fuzzy neutral network with probability factor（FNNP）,multi-level fuzzy comprehensive evaluation and the DempsterShafer（D-S） theory is proposed.This hybrid algorithm constructs a complete process from generating the fuzzy database to the final identification,realizes the identification of friend-or-foe automatically if the training samples or expert’s experience can be obtained,and reduces the effect of uncertainties in the process of identification.At the same time,the whole algorithm can update the identification result with the augment of observations.The performance of the proposed algorithm is assessed by simulations.Results show that the proposed algorithm can successfully deduce the aircraft’s identity even if the observations have measurement errors.

Research into selection evaluation system on co-mining of“the three gas”in coal series stratum

Along with the continuously go deep into of the research on coal series stratum,unconventional coalderived gas gets more attention,including coalbed methane,shale gas and tight sandstone gas.However,selection evaluation as the basis and prerequisite for the exploration and development of unconventional coal-derived gas has great significance.The purpose of this paper is to set up a selection evaluation system,and this system is called selection evaluation on co-mining of“the three gas”in coal series stratum.If a basin exists these three gases at the same time,then we can use this evaluation system to evaluate this type of basin and choose dessert area,finally,for co-mining of“the three gas”in coal series stratum provide guidance.By choosing the main control factors of coalbed methane,shale gas and tight sandstone gas,and based on fuzzy mathematics,analytic hierarchy process theory and multilevel fuzzy comprehensive evaluation theory to research selection evaluation system on co-mining of“the three gas”in coal series stratum.Finally,26 main control factors are selected,and then the index system is set up;in addition,by calculating the weight and establishing the membership function and evaluation set,and then selection evaluation system on co-mining of“the three gas”in coal series stratum with a four layer index is established.This paper can provide a theoretical basis and engineering guidance for unconventional gas exploration and development.