Intelligent adaptive system and method for monitoring leakage of oil pipeline networks based on big data

An intelligent adaptive system for monitoring leakage of oil pipeline networks based on big data, comprising an upper computer and a lower computer;

• the lower computer comprises a data collector, a filter circuit, an amplifying circuit and a PLC central processing unit,
• wherein the data collector is used for collecting millisecond pressure, millisecond flow rate, temperature and density at an inlet and outlet of a pipeline, conducting multi-source consistent processing to all kinds of collected signals, converting the signals into standard uniform data and sending them to the filter circuit,
• wherein the filter circuit is used for conducting noise filtering to the collected signals and sending the signals after filtering to the amplifying circuit,
• wherein the amplifying circuit is used for amplifying the collected signals and sending the signals after amplification to the PLC central processing unit,
• wherein the PLC central processing unit is used for conducting analogue-to-digital conversion to the collected signals, conducting time correction to the data at the inlet and outlet of each segment of the pipeline, and sending the signals after time correction to the upper computer,
• wherein the upper computer is used for obtaining an initial state of a pipeline network by adopting an intelligent adaptive method in accordance with states of valves and pumps, thereby obtaining the topological structure of the whole pipeline network,
• wherein the upper computer is used for determining the priority detection range of a pipeline network area by judging whether the difference between collected inlet flow rate and outlet flow rate exceeds a threshold;
• wherein the upper computer is used for determining whether a change of collected signals is human-induced by inspecting whether the states of all valves and pumps at this moment are the same as the initial states and judging whether the difference between flow rates is equal to an artificial defueling amount or an artificial refueling amount,
• wherein the upper computer is used for conducting conformance testing to the collected flow rates and determining whether the collected flow rates are effective, and
• wherein the upper computer is used for determining a theoretical time difference between a pressure wave generated by a theoretical preset leakage point arriving at an upstream sensor and a downstream sensor, taking a sequence of the theoretical time difference and a sequence of a length of each segment of the pipeline as the input of a generalized regression neural network, taking a sequence of the distance from each preset leakage point to the inlet of the pipeline where the preset leakage point is located as an expected output, conducting training to obtain a nonlinear model, and putting an actual time difference between a pressure wave generated by a leakage point arriving at the upstream sensor and the downstream sensor into the nonlinear model obtained by training to obtain the location of an actual leakage point.