3

I have been modelling and simulating a number of simple district heating networks in Dymola and am quite often faced with an error during initialisation.

The system we are simulating consists of

  • A producer: two pressure boundaries - source and sink. Pressure at source is controlled via PI which ensures that the source pressure is such that the minimum differential pressure accross a consumer is greater than or equal to some set value.
  • Consumers: They have a PI controlled valve and a heat exchanger with a fixed return temp. Valve controls mass flow and subsequently the heat flow to match the consumer load at any given time.
  • Pipes: dynamic thermo-hydraulic model with heat loss and and Spatialdistribution to account for delay. Vectorised ports and mixing volumes used to reduce non linear equations.

The figure below is a heavily simplified version of the network (same error occuring here) enter image description here The consumer model looks as follows: enter image description here And the producer: enter image description here

During initialisation, the following error occurs:

        ERROR: Failed to solve non-linear system using Newton solver.
    To get more information: Turn on Simulation/Setup/Debug/Nonlinear solver diagnostics/Details
    Solution to systems of equations not found at time = 0
       Nonlinear system of equations number = 3
       Infinity-norm of residue = 118280
       Iteration is not making good progress.
       Accumulated number of residue       calc.: 389
       Accumulated number of symbolic Jacobian calc.: 5
       Last values of solution vector:
    L.PI.gainPID.y = 0
       Last values of residual vector:
    { -118280 }
Trying to solve non-linear system using global homotopy-method.
... loading "data" from "C:/Users/Sim1/Desktop/Keith Dymola Files/GrazReininghaus_UseCase/PythonScriptsforTranslation/Reininghaus.txt"
ERROR: Failed to solve non-linear system using Newton solver.
To get more information: Turn on Simulation/Setup/Debug/Nonlinear solver diagnostics/Details
Solution to systems of equations not found at time = 0
   Nonlinear system of equations number = 1
   Infinity-norm of residue = 2.22814E+018
   Iteration is not making good progress.
   Accumulated number of residue       calc.: 101
   Accumulated number of symbolic Jacobian calc.: 9
   Last values of solution vector:
M.port_a.m_flow = 0.000485868
N.valveLinear.dp = -55.8243
O.valveLinear.dp = -135.618
P.valveLinear.dp = 550.474
I.port_a.m_flow = 3.20321E-010
C.port_a.m_flow = 2.19343E-011
D.port_a.m_flow = 0.00208272
E.valveLinear.dp = 371.552
L.port_a.m_flow = -7.10982E-012
J.valveLinear.dp = 243.085
K.port_a.m_flow = 1.924E-005
   Last values of residual vector:
{ 6.60393E+013, -1.14781E+018, -1.05438E+018, -2.58754E+016, -111988,
  -1.56817E+010, 16024.9, 3.14411E+007, 3.99781E+008, 3.14412E+007,
  -15012.9 }

Error: could not solve simplified initialization for homotopy method.
Error: could not solve simplified initialization for homotopy method.
FixInitials:Init

The components A,B,C e.t.c are the consumers in the network. I am using the Radau IIa 5th order solver with tol=1e-06. The PI controller in the consumer valves inittype is to integrate only with integrtor state and the PI in the producer is initialised with an output value. I have tried playing around with all sorts of nominal values for mass flows and pressure drops in the network, a well as initial values in the PI controllerrs but the same form ERROR is always returned. The model passes the error check but always fails at initialisation.

I would like to know if anybody has had experience in debugging such nonlinear systems, and if so, a few tips in how to initialise these models would be a great help with the debugging process.

Keith O'Donovan
  • 151
  • 9
  • Keith, I work with the same type of systems. It would be really helpful if you could share your model. Regards Rene Just Nielsen – Rene Just Nielsen Mar 16 '17 at 15:50
  • 1
    I have added some pictures of the main components and a simplified version of the model. Pipe models are adapted from Annex60. – Keith O'Donovan Mar 17 '17 at 08:00
  • Did you test the producer and consumer models by themselves and then gradually extend the model? – Rene Just Nielsen Mar 17 '17 at 09:41
  • Yes I've used all of these components before in various networks with success, however in certain cases initialisation just doesn't work out. Have you had any experiences with such errors? – Keith O'Donovan Mar 17 '17 at 10:30
  • related: http://stackoverflow.com/questions/34661475/how-to-initialize-model-with-previous-simulation-solution Now that you have one successfull simulation run, you should keep the results and try to use them for future initialisation. – matth Mar 17 '17 at 18:38

1 Answers1

2

Ok so for anybody who is interested, I managed to simulate my network in the end. It turns out the initialisation problem was arising in the "first order" block within the consumer which takes the measured heat flow signal in the heat exchanger and passes it to the PI. The default init type for this component was "noinit", however by changing it to take in an initial guess value (nominal consumer load worked in this case), the initialisation sections passed. I guess this problem occured in this example as my consumer nominal loads were quite a bit higher than in previous examples and therefore the initial value was outside of the suitable range without specifying it manually.

Keith O'Donovan
  • 151
  • 9