RO

PLANT
 Table of
Content

• Introduction to RO
• RO System and it's Advantages
• Filtration Technologies
• Advantages of RO plant
• Primary treatment
• Secondary and tertiary treatment
• Suggestion for improvement
• Conclusion
 The Need of RO Plant
• Effluent unfit to release into water body
• Economic Feasability
• Target "Zero Discharge"
• Refinery purchased 1200 m^3 of water but used 450 m^3 while
650m^3 was going to VECL(Vadodara Enviro Channel Pvt Ltd.)
• From CETP Outlet; RO Plant receives a feed of Effluent water at
1350m^3/hr and treat it at the rate of 650m^3/hr and sends it to VECL.
 WHAT IS REVERSE OSMOSIS ?
• TECHNOLOGY USED TO REMOVE A LARGE MAJORITY
OF CONTAMINANTS FROM WATER BY PUSHING THE
WATER UNDER PRESSURE THROUGH A SEMI-
PERMEABLE MEMBRANE.

• A reverse osmosis system is one of the most extensive methods

of filtration. It removes 98% of dissolved solids.
 RO SYSTEM

RO membranes are made of cellulose acetate or

polysulfides coated with aromatic polyamides.
 ADVANTAGES OF RO
• Widely used in residential water purification and industrial water
filtration
• One of the greenest solutions for industrial wastewater
• Less hazardous wastewater
• Easy to maintain and replace
• Can automatically work and need less manpower
 TECHNOLOGIES FOR FILTRATION

Reverse Osmosis (RO) and Ultrafiltration (UF) are two most potential and effective
water filtration technologies :
• In the RO system, Inorganic dissolved materials are removed.
• UF system filters out solid waste and microcontaminants using a hollow
fiber membrane. It removes particles as small as 0.025
microns from water.
• RO is a molecular separation technique, Whereas Ultrafiltration is a Filtering
Device.
 Principle of Reverse Osmosis
• Removes ions, unwanted molecules, and larger particles from discharged water using a
semi-permeable membrane
• Capable of removing 90 - 95% of the total dissolved solids and 99% of all bacteria;
providing safe, pure water
• The feed water entering a RO unit emerges in two sections -
permeate stream and the reject stream.
• Design Capacity of the RO treatment plant - 1250 m3/hr of water at the inlet of RO-I
and 1350 m3/hr of Feed water, including recycled water at the inlet of UF on
continuous basis
 Advantages of RO Plant
REVERSE OSMOSIS IS AN EFFECTIVE AND
PROVEN TECHNOLOGY TO REDUCE
WATER CONTAMINANTS. FURTHER POST
TREATMENT AFTER THE RO SYSTEM SUCH AS
MIXED BED
• NO heating required, no phase change.
DEIONIZATION CAN INCREASE THE QUALITY
• Simple equipment and small footprint.
•
OF THE
Easy to Operate, a wide range of application.
• Low energy consumption and high efficiency. RO PERMEATE AND MAKE IT SUITABLE FOR THE
• The high degree of automation, good quality of MOST DEMANDING APPLICATIONS.
effluent.
• No pollution to the environment.
 OPERATION OF RO PLANT
• IOCL adopted the idea of maximal water recycling and reuse as a step
toward self-sustainability for the effluent exiting the refinery to reduce the
consumption of fresh water
• A Reverse Osmosis (RO) based Tertiary treatment plant planned as part of
the philosophy to treat CETP processed water for further recycling and
reuse
• RO plant intended to continuously treat 1250 m3/hr of water entering RO-1
and 1350 m3/hr of feed water, including recycled water, entering UF.
 PRIMARY TREATMENT
• Removal of settleable suspended particulate matter and removal of impurities like residual oil, BOD,
COD, and inorganic impurities, which may be harmful to UF/RO membranes
• The primary aim of the process is to decrease TSS (Total Suspended Solids).
• The feed to the primary unit should have the following max. limit of the parameters :
-
HRSCC
PARAMETERS
REJUVENATION IN RO SYSTEMS

AI/ML
IN RO FILTRATION
REJUVENATION IN RO SYSTEMS

AI/ML
IN RO FILTRATION
REJUVENATION IN RO SYSTEMS

AI/ML
IN RO FILTRATION
WHAT IS ARTIFICIAL INTELLIGENCE (AI)?

• ARTIFICIAL INTELLIGENCE (AI) REFERS TO THE SIMULATION OF HUMAN INTELLIGENCE

IN MACHINES THAT ARE PROGRAMMED TO THINK LIKE HUMANS AND MIMIC THEIR
ACTIONS.
• THE TERM MAY ALSO BE APPLIED TO ANY MACHINE THAT EXHIBITS TRAITS ASSOCIATED
WITH A HUMAN MIND SUCH AS LEARNING AND PROBLEM-SOLVING.
• AI IS ALSO DEFINED AS,AN INTELLIGENT ENTITY CREATED BY HUMANS CAPABLE OF
PERFORMING TASKS INTELLIGENTLY WITHOUT BEING EXPLICITLY INSTRUCTED AND
ACTING RATIONALLY AND HUMANELY.
• THE IDEAL CHARACTERISTIC OF ARTIFICIAL INTELLIGENCE IS ITS ABILITY TO
RATIONALIZE AND TAKE ACTIONS THAT HAVE THE BEST CHANCE OF ACHIEVING A
SPECIFIC GOAL.
• BUILDING AN AI SYSTEM IS A CAREFUL PROCESS OF REVERSE-ENGINEERING HUMAN
TRAITS AND CAPABILITIES IN A MACHINE, AND USING ITS COMPUTATIONAL PROWESS
TO SURPASS WHAT WE ARE CAPABLE OF.
HOW DOES ARTIFICIAL INTELLIGENCE (AI) WORK?
TO UNDERSTAND HOW ARTIFICIAL INTELLIGENCE WORKS, ONE NEEDS TO DIVE DEEP INTO THE
VARIOUS SUB-DOMAINS OF ARTIFICIAL INTELLIGENCE AND UNDERSTAND HOW THOSE DOMAINS
COULD BE APPLIED TO THE VARIOUS FIELDS OF THE INDUSTRY. THEY ARE AS FOLLOWS

MACHINE LEARNING:
ML TEACHES A MACHINE HOW TO MAKE INFERENCES AND DECISIONS BASED ON PAST
EXPERIENCE. IT IDENTIFIES PATTERNS AND ANALYSES PAST DATA TO INFER THE MEANING OF
THESE DATA POINTS TO REACH A POSSIBLE CONCLUSION WITHOUT HAVING TO INVOLVE HUMAN
EXPERIENCE. THIS AUTOMATION TO REACH CONCLUSIONS BY EVALUATING DATA SAVES HUMAN
TIME FOR BUSINESSES AND HELPS THEM MAKE A BETTER DECISIONS.

DEEP LEARNING:
DEEP LEARNING IS AN ML TECHNIQUE. IT TEACHES A MACHINE TO PROCESS INPUTS THROUGH
LAYERS IN ORDER TO CLASSIFY, INFER AND PREDICT THE OUTCOME.

NEURAL NETWORKS:
NEURAL NETWORKS WORK ON SIMILAR PRINCIPLES TO HUMAN NEURAL CELLS. THEY ARE A
SERIES OF ALGORITHMS THAT CAPTURES THE RELATIONSHIP BETWEEN VARIOUS UNDERLYING
VARIABLES AND PROCESSES THE DATA AS A HUMAN BRAIN DOES.
NATURAL LANGUAGE PROCESSING:
NLP IS A SCIENCE OF READING, UNDERSTANDING, AND INTERPRETING A
LANGUAGE BY A MACHINE. ONCE A MACHINE UNDERSTANDS WHAT THE USER
INTENDS TO COMMUNICATE, IT RESPONDS ACCORDINGLY.

COMPUTER VISION:
COMPUTER VISION ALGORITHMS TRY TO UNDERSTAND AN IMAGE BY BREAKING
DOWN AN IMAGE AND STUDYING DIFFERENT PARTS OF THE OBJECT. THIS HELPS
THE MACHINE CLASSIFY AND LEARN FROM A SET OF IMAGES TO MAKE A BETTER
OUTPUT DECISION BASED ON PREVIOUS OBSERVATIONS.

COGNITIVE COMPUTING:
COGNITIVE COMPUTING ALGORITHMS TRY TO MIMIC A HUMAN BRAIN BY
ANALYSING TEXT/SPEECH/IMAGES/OBJECTS IN A MANNER THAT A HUMAN DOES
AND TRIES TO GIVE THE DESIRED OUTPUT.
3 STAGES OF ARTIFICIAL INTELLIGENCE
WHY AI IN RO FILTRATION:
• THE WIDESPREAD ADOPTION OF REVERSE OSMOSIS TECHNOLOGIES HAS SHOWN
LITTLE SIGNS OF SLOWING DOWN AT 10% CAGR(COMPOUND ANNUAL GROWTH RATE)
SINCE 2004 IN RESPONSE TO STRICTER WATER QUALITY REQUIREMENTS, RISING COSTS,
AND THE NEED FOR RESILIENT INFRASTRUCTURES (MAGNIFIED BY COVID).

• O&M PROFESSIONALS AND PLANT MANAGERS CONTINUE TO SEEK BETTER WAYS TO

MANAGE THEIR MEMBRANE ASSETS AND SERVICE SCHEDULES

• TO OPTIMIZE CONTROL SET-POINTS TO MAXIMIZE RELIABILITY AND MINIMIZE THEIR

UNIT COST ($/M3) OF PRODUCT WATER.

• TO REDUCE MANPOWER

• IMPROVED ACCURACY IN SPECIFICATION OF FINAL PRODUCTS DUE TO INVOLVEMENT

OF COMPUTERS ALGOITHMS WITH HUMAN BRAIN.
1. MEMBRANE SERVICING

“THE AVERAGE SEAWATER REVERSE OSMOSIS (SWRO) PLANT SPENDS 21% OF ITS ANNUAL
OPERATING BUDGET ON MEMBRANE SERVICING ALONE (CLEANINGS AND REPLACEMENTS),
YET MEMBRANE SERVICING HAS SEEN LITTLE INNOVATION IN 30 YEARS.” -
INTERNATIONAL DESALINATION ASSOCIATION

• RO FACILITIES ACTIVELY DOCUMENT CLEANING ACTIVITIES AND RO PERFORMANCE.

• MACHINE LEARNING (ML) TECHNIQUES, A BRANCH OF ARTIFICIAL INTELLIGENCE (AI),
ALLOW MODELS TO BE DEVELOPED AND TRAINED ON SUCH DATASETS TO PROVIDE
ACCURATE PREDICTIONS FOR WHEN A CLEANING OR MEMBRANE REPLACEMENT IS
REQUIRED ON A PRESSURE VESSEL IN THE PLANT ENVIRONMENT.
• THIS HELPS US IN MINIMIZING THE MEMBRANE SERVICING COST AND OPTIMAL USE OF
THE MEMBRANE
2. SPECIFIC ENERGY CONSUMPTION:

• DETERMINING THE MOST COST-EFFECTIVE SET POINTS TO ENSURE PRODUCT WATER

QUALITY, WHILE MINIMIZING ENERGY CONSUMPTION, REQUIRES DETAILED MANUAL
ANALYSIS DUE TO DEGRADING MEMBRANE CONDITIONS AND CHANGING INFLUENT
CONDITIONS (E.G., TSS, FLOW RATES).

• THESE MANUAL CALCULATIONS ARE NOT ALWAYS PRACTICAL FOR OPERATORS AND
ENGINEERS WHOSE PRIMARY TASK IS ENSURING SAFE AND CONTINUOUS PLANT
OPERATIONS.

• MACHINE LEARNING (ML) TECHNIQUES CAN BE USED TO DETERMINE THE OPTIMAL FLOW
RATES, PRESSURES, AND ONLINE TRAIN CONFIGURATION TO MINIMIZE ENERGY USE WHILE
OPERATING WITHIN THE CONSTRAINTS OF MECHANICAL ASSETS (E.G., PUMPS,
TURBOMACHINERY, SEALS) TO MEET TARGET WATER QUALITY.

• WITH THIS ASPECT WE CAN ACHIEVE OUR AIM OF MINIMIZING ENERGY CONSUMPTION
WHILE MEETING THE APPROPRIATE AND REQUIRED QUALITY OF WATER.
3.PLANT-WIDE RISK MITIGATION:

• HUMAN ERROR ACCOUNTS FOR 24% OF UNPLANNED DOWNTIME AT INDUSTRIAL

PLANTS ANDTRADITIONAL RISK MITIGATION PRACTICES, LIKE REACTIVE AND
SCHEDULED MAINTENANCE ACTIVITIES, ARE SUSCEPTIBLE TO SYSTEM UPSETS.

• SYSTEM UPSETS SUCH AS PUMP DAMAGE, UNDETECTED SENSOR DRIFTS, AND

PRESSURE VESSEL LEAKS OFTEN RESULT IN COSTLY DOWNTIME FOR AN
ORGANIZATION SINCE REVENUE WATER IS ON PAUSE WHILE TROUBLESHOOTING AND
MAINTENANCE ARE PERFORMED.

• TO PREVENT THESE KINDS OF UPSETS, PLANT MANAGERS CAN LEVERAGE MACHINE

LEARNING’S PREDICTIVE CAPABILITIES TO FORECAST IN ADVANCE WHEN SUCH
ISSUES (E.G., WHEN A PRESSURE VESSEL SEAL IS LEAKING) MAY OCCUR AND NOTIFY
O&M STAFF SO THEY CAN PLAN AND ALLOCATE RESOURCES BEFORE IT'S TOO LATE
FOR A ERRORLESS EXECUTION OF REQUIRED TASKS

• THIS PREVENTS THE THREAT OF MASSIVE LOSSES POSED BECAUSE OF PLANT-WIDE

RISK BY ACTING AS A PRECAUTIOUS GUARD IN THE INDUSTRIES.
CONCLUSION