Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network

Rolling bearings are the most fault-prone parts in rotating machinery. In order to find faults in time and reduce losses, this paper presents an intelligent diagnosis method for rolling bearings. At present, the deep residual network (RESNET) is the most widely used convolutional neural network (CNN) and has become one of the hotspots in fault diagnosis. However, the fully connected layer of the deep residual network has the disadvantage of too many training parameters, which makes the model training and testing time longer. So, we proposed a new network structure which the global average pooling (GAP) technology replaces the fully connected layer part of the traditional RESNET. It effectively solves the problem of too many parameters of the traditional RESNET model, and uses data enhancement, dropout, and other deep learning training techniques to prevent the model from overfitting. Experiments show that the accuracy of fault diagnosis of the improved algorithm reaches 99.83%, training time has been shortened. Also, the whole process of rolling bearing fault detection does not need any manually extract features, and this “end-to-end” algorithm has good versatility and operability.

Yield Gap Analysis of Rapeseed (Brassica campestris var. Toria) in Kokrajhar District of Assam, India

The present study was carried out at five different villages of Kokrajhar district of Assam where cluster front line demonstration (CFLD) of High Yielding Variety (HYV) of rape seed (TS 46) was conducted by Krishi Vigyan Kendra, Kokrajhar. A total of 652 nos. of front line demonstration (FLD)s were evaluated to find out the yield gaps between HYV toria variety TS 46 and variety grown by farmers. Yield data of both demonstration and farmers practice were recorded and their yield gap, technology gap, extension gap and technology index were analyzed. The yield of rape seed variety TS 46 was registered 22.38 to 50.00 per cent higher over farmer’s variety. On an average technology gap, extension gap and technology index were recorded as 2.28qha-1, 2.08 qha-1 and 20.73 per cent respectively.

Impact on Cluster Frontline Demonstrations on the Productivity of Mustard (Brassica juncea)

Cluster frontline demonstrations (CFLDs) are the long-term educational activity conducted in a logical method on partner farmer’s field to show the worth of new technology under micro farming. The present investigation was carried out during the Rabi season (October to March) of respective year 2016-17 to 2019-20 under the National Food Security Mission, Government of India. Four hundred thirteen CFLDs were conducted in 165.2 ha area with the farmers and scientists of KVK. The CFLDs were conducted at adopted fifteen villages of Dholpur district. Cultivation technology was applied under CFLDs included scientific intervention. The highest yield was obtained in demonstrated practices (DP) with an average of 2272.00 kg ha-1 as compared to farmer practice (FP) with an average of 1829.00 kg ha-1. Further, an average additional return (` 16,063.6), effective gain (` 14,335.8), net return (` 64,512.1 ha-1) and benefit-cos ratio (3.49) were found in the DP as compared to farmer practice. An average occurrence of Alternaria blight, white rust, stem rot, aphid were recorded 27.44, 5.93 and 14.85 and 25.05, respectively showed in DP as compared to farmer practice. An average extension gap, technology gap and technology index between and was noted 443.0 kg ha-1, 234.75 kg ha-1 and 10.39%, respectively. The results indicate that the use of scientific intervention under CFLDs to increase the production and profitability of Mustard.

Impact of front line demonstration of chickpea (JG 63) in Chhatarpur district of Madhya Pradesh, India

The present investigation was carried out at the adopted villages of Krishi Vigyan Kendra, Chhatarpur during 2017-18 to demonstrate the improved variety JG 63 with the scientific package and practices to improve the production of chickpea. The treatment comprised of scientific package of practices (Improved variety JG 63 + seed treatment with Carbendazim 3g/ kg of seed and seed inoculation with Rhizobium and PSB culture each @ 10 g/ kg of seed + soil test value based fertilizer application + line sowing + adoption of IPM technique). The demonstration plot exhibited higher yield as compared to farmers plot. An average yield of chickpea in the demonstrated plot was 18.74 q/ha as compare to farmers practices 14.16 q/ha in the three years of pooled data. The improved technology gives the higher return with the high benefit cost ratio as farmer’s practices. The observed extension gap, technology gap and technology index were 4.58 q/ha, 1.26 q/ha and 6.30%, respectively. The improved variety with scientific package of practices and technical guidance contributed to increase production of chickpea and profitability of the farmers of the district.

Directional Distance Function Technical Efficiency of Chili Production in Thailand

To overcome the challenging food safety and security problem, in 2003, the Thai government initiated ‘Good Agricultural Practices’ (GAP) technology. This paper used a sample of 107 small chili farms from the Chiyaphoom province for the 2012 crop year, and data envelopment analysis (DEA) meta-frontier directional distance function technique to answer two questions: (1) Are GAP-adopting farms, on average, more efficient than conventional farms? (2) Does access to GAP technology affect farmers’ decisions to adopt GAP technology? We also developed an ‘indirect’ approach to reduce the potential sample selection bias for small samples. For the dry-season subsample, GAP farms were more technically efficient when compared with non-GAP farms. These dry-season non-GAP farms may not adopt the GAP method because they have limited access to GAP technology. For the rainy-season subsample, on average, GAP farms were more efficient than non-GAP farms at the 5% level. Access to the GAP technology is not a possible reason for non-GAP rainy season farms to not adopt the GAP technology. To enable sustainable development, government agencies and nongovernmental organizations (NGOs) must develop and implement appropriate educational and training workshops to promote and assist GAP technology adoption for chili farms in Thailand.

Performance assessment of Bhendi hybrid Co 4 cultivation over local check variety under Front Line Demonstration

A field investigation on productivity augmentation of bhendi [Abelmoschus esculentus L. Moench] was carried out at Melanagai village, Mannargudi block of Thrivarurur district. The study was conducted by ICAR-Krishi Vigyan Kendra, Needamangalam [Tamil Nadu], during 2016-17 to assess the bhendi/okra hybrid Co 4 performance along with local check variety.The per cent yield improvement, technology gap, extension gap, technology index were calculated based on the observation recorded on growth, yield and economical attributes of both demonstration and local adopted check variety. The recorded data showed that the average yield of demonstration plots was 20.35 tha–1whereas the local check recorded an average yield of 12.80 tha–1 and there is an amplified average yield by 37.21 per cent. The gross returns and benefit cost ratios from the demonstration plot were higher [Rs. 121020/ha and 2.80 respectively] as compared to farmer’s practices [Rs. 76800/ha and 1.90]. The demonstrated improved variety i.e. okra hybrid Co 4 recorded superior growth, yield and economical parameters of the local adopted check variety. The enhancement in growth, yield and economic parameters under okra hybrid Co4 than the farmers’ practice [local check] signifying the technical and economic viability of improved variety / hybrid over farmers practices.