 Hello friends, I am Mr. Sanjeev B. Naik working in Mechanical Engineering Department of Walchand Institute of Technology, Sulapur. In this video I am explaining about the statistical techniques which are used by an engineer in engineering practice. So, at the end of the session, learners will be able to understand some statistical technique which is used in engineering practice. The probability and statistics are the important working tools which are available with an engineer while he is making decisions in many of the engineering practice as various areas. The statistics quantifies those characteristics of the systems which are our ability. So, an engineer has to take the decisions about the outcomes of certain systems which have got its own variability. So, under such variability conditions, he want to analyze the characteristics of that variability which enables him to take the proper decisions. So, statistical techniques help engineers in decision making where the variability of decision parameters involved. For example, we know that any manufacturing setup, the parts which have been produced cannot produce identical dimensions. So, always the dimensions produced of all the parts on single setup or manufacturing system always vary within certain limit and that is what a variability produced. And in such case, the variability analysis becomes important to either accept that as a quality or to reject it. So, that is the way the statistical technique will help the engineer. Also in project management, many times the time taken up by the activities may vary within certain limit and under such conditions, the decision becomes important. So, is the process capability of the machines or manufacturing processes, forecasting techniques. So, many of the areas where we can apply statistical techniques which help the engineers in decision making. Statistical quality control, we call SQC is one of the very important aspect of manufacturing system. In this the most important word is quality. And we know that the quality of a product is set to satisfactory when it is able to satisfy the stated and implied needs of the customer. So, the customer will dictate the quality norms or quality requirement because product is manufactured for the use of a customer and the requirements of the customer dictates the quality of the product. So, always the manufacturing parts or the product should maintain its quality as per the required norms and that is very important. This particular aspect becomes important so that it is been well handled by techniques called as SQC techniques or statistical quality control. Quality control, that is why becomes a powerful statistical technique for effective diagnosis of lack of quality or lack of conformity to settled standards in any of the materials, processes, machines or introduction. As I said that anything which has been produced must be finally accepted by the customers and it should satisfy particular quality norms. It should satisfactory perform the function, intend or implied function. If it does not do it then it is a lack of quality. So, quality control techniques help to identify the quality products and products which fail in quality so that that will not reach to the customer. So, that way the analysis will help and that is the way it provides a powerful statistical technique. Variation in the quality of manufactured product in repetitive process in the industry is inherent. As I said that the dimensions produced for all the products manufactured in single set up are not same that is what variation, if this dimension goes beyond certain limit it is a matter of quality and that is why quality variation is going to be there. So, whether it is in acceptable region or range or not that one has to verify and that is why variation in the quality of the product is inherent and unavoidable. So, SQC helps in proper analysis of this quality whether it is acceptable in particular range or not and accordingly making changes in the design or processes or economical requirements. So, necessary corrections can be made so that keep the process under control. The various principles which have been used here that no two things are exactly alike. So, variability is inherent in all the manufacturing or production process. Variation in a product or process can be measured so whatever the variation is there inherent still it is measurable and it can be measured that variation can be measured. It is found that these variations according to a definite pattern so variation is going to repeat in terms of pattern if it is observed as a large database we can identify it is repeating with the definite pattern. Whenever things of the same kind are measured as we say that the dimensions of the part if we measure which are been produced in thousands of quantities a large number of observations always cluster around the middle that is called as a central tendency of frequency distribution and that is why that follows a normal curve. So, many times it is assumed that the variations which are been observed in system characteristics they follow normally a normal curve assumption in which it shows a central tendency of the frequency around the middle means around its mean value around its mean value. Now it is also possible to determine the shape of the distribution curve for products manufactured by any process. So, getting a large data in terms of class of interval deciding the interval and plotting it as a histogram and converting that into appropriate distribution curve it is possible. So, any manufacturing process the observations made by samples collected by measuring their dimensions actually one can plot it as certain distribution curve it is possible. Now these variations which is going to be occur is basically because of two causes one is called as chance cause and one is called as assignable cause. The assignable causes are not random basically these are occurring as a because of certain errors which can be eliminated. So, errors can be identified or these causes can be identified and can be eliminated from the system or they can be controlled within certain minimum level otherwise they are going to distort this assumption normal curve assumption a large. So, one has to first control these assignable causes within limit then whatever assumption of normal curve is made remains intact. These statistical methods gives way to picturize these variations so that one can understand the distribution properly and to check whether the assignable causes are in the limit or not or they can be eliminated and process is brought under control what is called as a statistical quality control or statistical process control and then the quality can be controlled by using certain histograms or representation of curves probability curves and various control charts. So, by using these particular techniques we can use proper statistical method to control the quality though there is a variability on particular manufacturing process. So this is a normal distribution curve normally followed which is a standard normal curve which has been specified by plus minus 3 sigma limit about mean and it shows the central tendency in the sense that a maximum area between plus 1 or minus 1 deviation from mean is about 68 percent. So, maximum observations lie in this area as a central tendency of this and that follows the normal distribution curve and total range is divided between minus 3 sigma to plus 3 sigma limit and the area covered under this is no doubt 99.73 but it is assumed to be 100 percent. So, any variation which is been produced as a minimum dimensions that is a lower limit to a upper limit of variability as a dimension if you take example then it is distributed or it is dispersed between this range and that is called as a range. So, some of the characteristics of this curves are mean value and standard deviation. This is a equation for the curve which has been there and it is called as a normal standard curve normally this has been referred in many of the applications. Now, we will list out the thing for a while and list out certain areas of application of statistical techniques which are used in engineering practice. This is my reference. Thank you.