System for monitoring expansion valve

• US 5,791,155 A
• Filed: 06/06/1997
• Issued: 08/11/1998
• Est. Priority Date: 06/06/1997
• Status: Expired due to Term

• Current Assignee: Carrier Corporation (Carrier Global Corporation)
• Original Assignee: Carrier Corporation (Carrier Global Corporation)
• Inventors: Tulpule, Sharayu
• Primary Examiner(s): Wayner, William E.
• Application Number:
  US08/869,535
• Time in Patent Office: 431 Days
• Field of Search: 395/22, 62/211, 62/225, 236/78 D
• US Class Current: 62/211
• CPC Class Codes: F25B 2400/06 Several compression cycles arranged in parallel
• CPC Class Codes: F25B 2400/075 with parallel compressors
• CPC Class Codes: F25B 2600/2513 Expansion valves
• CPC Class Codes: F25B 2700/21172 at the inlet
• CPC Class Codes: F25B 2700/21173 at the outlet
• CPC Class Codes: F25B 49/005 of safety devices F25B49/02 and F25B49/04 take precedence
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks

Abstract

A monitoring system for a heating or cooling system includes a neural network for computing the status of one or more expansion valves within the system. The neural network is trained to learn certain characteristics of the heating or cooling system during a development mode of operation. The thus trained neural network timely computes the status of the one or more expansion valves during a run time mode of operation. Information as to the status of the one or more expansion valves is made available for real time assessment during the run time mode of operation.

Claims

1. A process for monitoring the operation of an expansion valve within at least one refrigeration circuit of a heating or cooling system comprising the steps of:

reading values of information produced by a plurality of sensors located within the heating or cooling system;

processing a set of data consisting of at least some of the read values of information produced by the plurality of sensors through a neural network so as to produce a computed valve position for the expansion valve within the refrigeration circuit of the heating or cooling system;

comparing the computed valve position with a commanded valve position for the expansion valve within the refrigeration circuit of the heating or cooling system; and

selectively transmitting a message as to the operation of the expansion valve based upon the comparison of the computed valve position with the commanded valve position.

2. The process of claim 1 wherein the neural network comprises a plurality of input nodes and wherein said step of processing a set of data consisting of at least some of the read values produced by the plurality of sensors through a neural network comprises the step of:

applying each piece of data from the set of data to a corresponding input node in the neural network whereby each piece of data resides within its respective input node.

3. The process of claim 2 wherein the neural network comprises a plurality of interlinking nodes connected to the input nodes and furthermore connected to at least one output node of the neural network and wherein said step of processing a set of data consisting of at least some of the read values produced by the plurality of sensors through a neural network comprises the step:

computing values of the interlinking nodes based upon the values of the set of data applied to the input nodes; and

computing a value of the position of the expansion valve at the output node based upon the computed values of the interlinking nodes.

4. The process of claim 3 wherein the neural network further comprises weighted values for connections between the plurality of interlinking nodes connected to the output node and wherein the neural network further comprises weighted values for connections between the input nodes and the output node and wherein said step of computing a value at the output node based upon the computed values of the interlinking nodes comprises the step of:

computing at least one value of the position of the expansion valve at the output node based upon the computed values at the plurality of interlinking nodes, the weighted values for the connections between the plurality of interlinking nodes and the output node and the weighted values for the connections between the input nodes and the output node.

5. The process of claim 1 further comprising the step of:

reading the commanded valve position that is to be compared with the computed valve position at the time the values of information produced by the plurality of sensors within the heating or cooling system are read.

6. The process of claim 1 further comprising the step of:

deriving at least one value of information to be applied to the neural network from the values of information produced by the plurality of sensors located within the heating or cooling system whereby the derived value becomes part of the set of data processed through the neural network so as to produce the computed valve position for the expansion valve.

7. The process of claim 6 wherein the at least one value of information produced by the plurality of sensors located within the heating or cooling system comprises a superheat value for the refrigerant entering a compressor in the refrigeration circuit containing the expansion valve.

8. The process of claim 1 wherein said step of reading values of information produced by a plurality of sensors located within the heating or cooling system comprises:

reading the value of at least one sensor for sensing the suction temperature of a compressor within the refrigeration circuit containing the expansion valve.

9. The process of claim 8 wherein said step of reading values of information produced by a plurality of sensors within the heating or cooling system further comprises:

reading the value of a sensor for sensing the suction pressure of the compressor within the refrigeration circuit containing the expansion valve.

10. The process of claim 9 further comprising the step of:

computing a superheat value of the refrigerant entering the compressor within the refrigeration circuit containing the expansion value as a function of the read value of suction temperature and the read value of suction pressure of the compressor.

11. The process of claim 10 wherein said step of reading values of information produced by a plurality of sensors located within the heating or cooling system further comprises:

reading the value of a sensor for sensing the temperature of a refrigerant entering the expansion valve in the refrigeration circuit.

12. The process of claim 11 wherein said step of reading values of information produced by a plurality of sensors located within the heating or cooling system further comprises:

reading the temperature of a medium entering a heat exchanger associated with the refrigeration circuit containing the expansion valve in the heating or cooling system; and

reading the temperature of the medium leaving the heat exchanger whereby the read temperature of the medium entering and leaving the heat exchanger define the heating or cooling load on the heating or cooling system.

13. The process of claim 12 wherein said step of reading values of information produced by a plurality of sensors located within the heating or cooling system further comprises:

reading the temperature of a medium flowing through a second heat exchanger associated with the refrigeration circuit containing the expansion valve.

14. A process for learning the characteristics of a heating or cooling system so as to predict the status of an expansion valve in at least one refrigeration circuit of the heating or cooling system, said process comprising the steps of:

storing a plurality of sets of data obtained from information read from sensors within the heating or cooling system when the system is subjected to various load and ambient conditions for known statuses of the expansion valve; and

repetitively processing a number of the stored sets of data through a neural network so as to teach the neural network to accurately predict the known statuses of the expansion valve for the particular sets of data whereby the neural network may be thereafter used to compute the status of the expansion valve from a set of data obtained from information read from sensors within the heating system.

15. The process of claim 14 wherein the neural network comprises a plurality of input nodes for receiving each stored set of data and wherein the neural network further comprises at least one output node for computing the status of the expansion valve and wherein the neural network still further comprises a plurality of interlinking nodes between the plurality of input nodes and the at least one output node, wherein said step of repetitively processing a number of stored sets of data comprises the steps of:

computing the status of the expansion valve at the output node for each set of data; and

comparing the computed statuses of the expansion valve for each set of data with the known statuses of the expansion valve for each set of data.

16. The process of claim 15 wherein the statuses of the expansion valve computed at the output node are computed as a function of weighted connections between the output node and the plurality of interlinking nodes and said step of repetitively processing a number of stored sets of data further comprises the steps of:

adjusting weighted connections between the interlinking nodes and the output node when the computed statuses of the expansion valve do not compare favorably with the known statuses of the expansion valve; and

repeating said steps of computing the statuses of the expansion valve at the output node and comparing the newly computed statuses of the expansion valve with the known statuses of the expansion valve whereby the newly computed statuses are a function of the adjusted weighted connections between the output node and the plurality of interlinking nodes.

17. The process of claim 16 wherein said step of repetitively processing a number of stored sets of data further comprises the step of:

storing the adjusted weighted connections between the output node and the plurality of interlinking nodes for use thereafter by the neural network to process a set of data when the newly computed statuses of the expansion valve compare favorably with the known statuses of the expansion valve.

18. The process of claim 15 wherein the statuses of the expansion valve computed at the output node are computed as a function of both weighted connections between the output node and the plurality of input nodes and weighted connections between the output node and the input node wherein said step of repetitively processing a number of stored sets of data further comprises the steps of:

adjusting the weighted connections between the output node and the plurality of input nodes and the weighted connections between the output node and the plurality of interlinking nodes when the computed statuses of the expansion valve do not compare favorably with the known statuses of the expansion valve; and

repeating said steps of computing the statuses of the expansion valve at the output node and comparing the newly computed statuses of the expansion valve with the known statuses of the expansion valve whereby the newly computed statuses are a function of the adjusted weighted connections between the output node and the plurality of input nodes and the weighted connections between the output node and the plurality of interlinking nodes.

19. The process of claim 18 wherein said step of repetitively processing a number of stored sets of data further comprises the step of:

storing both the adjusted weighted connections between the output node and the input nodes and the adjusted weighted connections between the output node and the plurality of interlinking nodes for use thereafter by the neural network in accurately computing statuses of the expansion valve based upon having processed sets of data.

20. The process of claim 14 wherein said step of storing a plurality of sets of data obtained from information read from sensors within the heating or cooling system comprises:

reading a sensed suction temperature of a compressor within at least one refrigeration circuit of the heating or cooling system each time a particular set of data is to be obtained from information read from sensors within the heating or cooling system; and

storing the sensed suction temperature as part of the particular set of data obtained from information read from sensors within the heating or cooling system.

21. The process of claim 20 wherein said step of storing a plurality of sets of data obtained from information read from sensors within the heating or cooling system further comprises:

reading a sensed suction pressure of the compressor within at least one refrigeration circuit of the heating or cooling system each time a particular set of data is to be obtained;

computing a superheat value for the refrigerant entering the compressor as a function of the read and stored sensed suction temperature for the particular set of data and the read suction pressure; and

storing the computed superheat value as part of the particular set of data obtained from information read from sensors within the heating or cooling system.

22. The process of claim 21 wherein said step of storing a plurality of sets of data obtained from information read from sensors within the heating or cooling system further comprises:

reading a sensed temperature of a refrigerant before the refrigerant enters the expansion valve in the refrigeration circuit each time a particular set of data is to be obtained from information read from sensors within the heating or cooling system; and

storing the sensed temperature as part of the particular set of data obtained from information read from sensors within the heating or cooling system.

23. The process of claim 22 wherein said step of storing a plurality of sets of data obtained from information from sensors within the heating or cooling system comprises the steps of:

reading a sensed temperature of a medium entering a heat exchanger associated with the refrigeration circuit containing the expansion valve;

reading a sensed temperature of the medium leaving the heat exchanger; and

storing the sensed temperature of the medium entering and leaving the heat exchanger as part of the particular set of data obtained from information read from sensors within the heating or cooling system.

24. The process of claim 23 wherein said step of storing a plurality of sets of data obtained from information from sensors within the heating or cooling system comprises:

reading a sensed temperature of a medium flowing through a second heat exchanger associated with the refrigeration circuit containing the expansion valve; and

storing the sensed temperature of the medium flowing through the second heat exchanger as part of the particular set of data obtained from information read from sensors within the heating or cooling system.

25. A process for monitoring the operation of at least one expansion valve within a refrigeration circuit of a heating or cooling system comprising the steps of:

reading a commanded status for the expansion valve within the refrigeration circuit;

reading information from a plurality of sensors located within the heating or cooling system when reading the commanded status of the expansion valve;

deriving a set of data to be applied to a neural network from the information read from the plurality of sensors located within the heating or cooling system;

processing the set of data through a neural network so as to produce a computed value as to the operative status of the expansion valve; and

comparing the computed value as to the operative status of the expansion valve with the read commanded status of the expansion valve; and

selectively transmitting messages as to the operation of the expansion valve when the computed value as to the operative status of each expansion valve is not equal to the commanded status of the expansion valve.

26. The process of claim 25 wherein said step of reading information from a plurality of sensors located within the heating or cooling system comprises:

reading a sensed suction temperature of a compressor in the refrigeration circuit of the heating or cooling system.

27. The process of claim 26 wherein said step of reading information from a plurality of sensors located within the heating or cooling system comprises the step of:

reading a sensed suction pressure of the compressor within the refrigeration circuit of the heating or cooling system; and

wherein said step of deriving a set of data to be applied to a neural network from the information read from the plurality of sensors located within the heating or cooling system comprises;

computing a superheat value for the refrigerant entering the compressor as a function of the read sensed suction temperature of the compressor and the read sensed suction pressure of the compressor.

28. The process of claim 27 wherein said step of reading information from a plurality of sensors located within the heating or cooling system comprises:

reading a sensed temperature of the refrigerant in the refrigeration circuit before the refrigerant enters the expansion valve in the refrigeration circuit.

29. The process of claim 28 wherein said step of reading information from a plurality of sensors located within the heating or cooling system comprises:

reading a sensed temperature of a medium entering a heat exchanger associated with the refrigeration circuit;

reading a sensed temperature of a medium leaving the heat exchanger associated with the refrigeration circuit.

30. The process of claim 29 wherein said step of reading information from a plurality of sensors located within the heating or cooling system comprises:

reading a sensed temperature of a medium entering a second heat exchanger associated with the refrigeration circuit.

31. The process of claim 30 wherein said step of deriving a set of data to be applied to a neural network further comprises:

including the computed superheat value for the refrigerant entering the compressor, the read suction temperature of the compressor, the read temperature of the refrigerant before entering the expansion value, the read temperatures of the medium entering and leaving the heating exchanger and the read temperature of the medium entering the second heat exchanger within the set of data to be applied to the neural network.

32. The process of claim 25 wherein the neural network comprises a plurality of input nodes for receiving a set of data, at least one output node for computing the operative status of the expansion valve and a plurality of interlinking nodes between the input nodes and the output nodes and wherein said step of processing a set of data comprises the step of:

computing the status of the expansion valve at the output node as a function of the values of the input nodes and the values of the interlinking nodes.

33. The process of claim 25 wherein the neural network comprises a plurality of input nodes for receiving a set of data, at least one output node for computing the operative status of the expansion valve and a plurality of interlinking nodes between the input nodes and the output nodes and wherein the neural network furthermore includes weighted connections between the input nodes and the output node and weighted connections between the interlinking nodes and the output nodes wherein said step of computing the status of the expansion valve comprises the step of:

computing the status of the expansion valve at the output node as a function of the values of the input nodes, values of the weighted connections between the input nodes and the output nodes, the values of the interlinking nodes and the values of the weighted connections between the interlinking nodes and the output nodes.