MXPA01001693A - Method and system of intelligent analysis for electrical - Google Patents

Abstract

EQUIPMENT CONTAINING FLUID The present discloses an intelligent analysis apparatus and method for electrical equipment containing fluid which includes sensors for measuring various parameters of the electrical equipment;the analytic model calculates parameters based upon measures of other parameters;the measured and calculated parameters are compared and the result of said comparison is employed as an indicator in a causal network;probabilities on a causal network are recalculated by means of a belief network;the analytic model adjusts with the time to take into account acceptable behavior changes of the equipment with time;the causal network emission can be used for diagnostic and prognostic indication.

Description

SYSTEM AND METHOD OF INTELLIGENT ANALYSIS OF ELECTRICAL EQUIPMENT THAT CONTAINS FLUID FIELD OF THE INVENTION The invention relates generally to electrical equipment containing fluid. More particularly, the invention relates to an apparatus and method for determining the operating status, diagnostic status, and forecasts of electrical equipment in real time and to electrical equipment that incorporates the apparatus. Electrical equipment, particularly medium voltage or high voltage electrical equipment, requires a high degree of thermal and electrical insulation between its components. Accordingly, it is well known to encapsulate the components of electrical equipment, such as coils of a transformer, in a containment container and fill the containment container with a fluid. The fluid facilitates the dissipation of heat generated by the components and can be circulated through a heat exchanger to efficiently lower the operating temperature of the components. The fluid also serves as electrical insulation between components or to supplement other forms of insulation disposed around components, such as cellulose paper or other insulating materials. You can use any fluid that has the desired electrical and thermal properties. Typically, the electrical equipment is filled with an oil, such as castor oil, mineral oil, or vegetable oil, or a synthetic "oil," such as chlorinated diphenyl, silicone, or sulfur hexafluoride. Often electrical equipment is used in a mission critical environment in which failure can be very costly, or even catastrophic, due to a loss of electrical power to critical systems. In addition, the failure of electrical equipment normally results in great damage to the equipment itself and the surrounding equipment thus requiring the replacement of expensive equipment. Additionally, such failure can cause injury to personnel due to electric shock, fire, or explosion. Therefore, it is desirable to monitor the condition of the electrical equipment to predict potential equipment failure through the detection of incipient failures and take corrective action through repair, replacement, or adjustment of the operating conditions of the equipment. However, the performance and behavior of electrical equipment containing fluid is inherently degraded over time. Failures and incipient faults must be distinguished from normal and acceptable degradation. A known method for monitoring the state of electrical equipment containing fluid is to monitor the various parameters of the fluid. For example, the temperature of the fluid and the total fuel gas (TGG) in the fluid is known to be indicative of the operating state of electrical equipment containing fluid. Therefore, the monitoring of those fluid parameters it can provide an indication of any incipient failure in the equipment. For example, it has been found that carbon monoxide and carbon dioxide increase in concentration with thermal aging and degradation of cellulosic insulation in electrical equipment. Hydrogen and various hydrocarbons (and derivatives thereof such as acetylene and ethylene) increase in concentration due to heat points caused by circulating currents and dielectric decomposition such as corona and arcing. Oxygen and nitrogen concentrations indicate the quality of the gas pressurization system used in large equipment, such as transformers. Accordingly, dissolved gas analysis @ (DGA) (Addisolved gas analysis @) has become a well-accepted method for discerning incipient failures in electrical equipment containing fluid. In conventional DGA methods, a quantity of fluid is removed from the containment container of the equipment through a drain valve. The fluid removed is then tested for dissolved gas in a laboratory or by equipment in the field. This test method is referred to herein as Aoff-line @ DGA. Because the gases are generated by several known faults, such as degradation of insulation material or other portions of electrical components in the equipment, recurrent shorts in coils, overload, loose connections, or the like, several diagnostic theories have been developed to correlate the quantities of various gases in fluid with particular faults in electrical equipment in which the fluid is contained.

However, because conventional off-line DGA methods require the removal of fluid from electrical equipment, these methods do not 1) yield localized position information in relation to any equipment failure, 2) take into account spatial variations of gases in the equipment, and 3) provide real-time data regarding the faults. If the analyzes are conducted out of place, the results can not be obtained for several hours. The incipient failures can develop in equipment failure during said period of time. MICROMONITORS, INCJ and SYPROTECJ have each developed a gas sensor that resides in the drain valve, or other unique locations, of a transformer and overcomes some of the limitations of DGA off-line. However, the location data in relation to a fault are not distinguishable with said device because it is located in a predefined position and does not provide any indication of the position of the gas source, i.e., the fault. The patent of E.U.A. 4,654,806 describes an apparatus for monitoring transformers that includes sensors for detecting oil temperature, gas in oil, and cabin temperature. The raw data from the sensors is collected by a microcomputer and periodically downloaded to a remote host computer. The microcomputer can compare several measured parameters with predetermined thresholds and can trigger alarms or other warnings if the thresholds are exceeded. The remote host computer can control a transformer cooling system based on the parameters that are periodically download to the remote host computer. Similarly, the US patent. 3,855,503 describes a remotely supervised transformer in which sensor data is downloaded to a remote computer and compared to predetermined thresholds. If the thresholds are exceeded, the transformer can be left without power. The patent of E.U.A. 4,654,806 describes that the individual thresholds can be varied based on other thresholds. However, the devices described in the patent of E.U.A. 4,654,806 and in the patent of E.U.A. 3,855,503 fall short in providing complete and coherent diagnoses in real time because they do not take into account the complex relationships between the various operating parameters of electrical equipment containing fluid or the normal degradation with time of electrical equipment containing fluid. The article entitled "Monitoring the Health of Power Transformers" discusses research at the Massachusetts Institute of Technology in relation to model-based diagnostic systems. The known methods and apparatus do not provide accurate, real-time diagnosis of incipient failures, and prognosis of electrical equipment containing fluid because the complex relationship between various operating parameters of electrical equipment containing fluid is not completely confronted by the prior art. For example, a rise in temperature outside a normal scale may be due to a temporary increase in load and not to an incipient failure. Other parameters are related in more complex ways that are not addressed by the technique previous. In addition, the devices discussed above do not take into account the dynamic change over time in transformer behavior. The patent of E.U.A. 5,845,272 discloses a system for isolating faults in a machine or in a method having a plurality of equipment. The system uses emissions from several sensors as power inputs in a knowledge base that includes causal networks. However, the patent of E.U.A. 5,845,272 is not aimed at diagnosing electrical equipment that contains fluid and therefore does not take into account the complex relationships between parameters of electrical equipment containing fluid and the dynamic change in behavior over time of electrical equipment containing fluid. In summary, the known methods and apparatus do not take into account the analytical models of operation of electrical equipment containing fluid including thermal, fluid flow, electric field, pressure-volume, chemical, failure mode, cause of failure models Root and gas models in oil, all of which are related in a complex way and change over time. Therefore, known methods and apparatus do not accurately identify and predict failure modes and evaluate the life cycle of electrical equipment containing fluid.

BRIEF DESCRIPTION OF THE INVENTION The invention relates to a diagnostic apparatus and method for electrical equipment. A first aspect of the invention is an intelligent analysis apparatus for electrical equipment containing fluid of the type having components surrounded by fluid. The apparatus comprises electrical equipment having a containment container configured to contain a fluid and at least one electrical component disposed in the containment vessel, plural sensors configured to emit signals indicating plural operating parameters of the electrical equipment, and a coupled diagnostic device. to the sensors and having a processor for determining operating characteristics of the electrical equipment based on at least one analytical model of the electrical equipment and the signals emitted by the sensors by applying parameter values calculated by means of the at least one analytical model and parameter values as indicated by the signals from the sensors in a causal network. A second aspect of the invention is a method for intelligent analysis of electrical equipment containing fluid of the type having components surrounded by fluid. The method comprises the steps of detecting plural operational parameters of electrical equipment having a containment container configured to contain a fluid and at least one electrical component disposed in the containment vessel, generating signals indicating the plural operating parameters of the electrical equipment detected in the detection step, and determine operational characteristics of the electrical equipment based on the at least one analytical model of the electrical equipment, and the signals generated in the generation step by applying parameter values calculated by the at least one analytical model and values of parameters as indicated by the signals generated in the generation step in a causal network.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention can be more fully understood by reading the following detailed description of a preferred embodiment in conjunction with the appended drawings in which: Figure 1 is a schematic illustration of a preferred embodiment of the invention. Figure 2 is a flow chart of a diagnostic determination routine of the preferred embodiment. Figure 3 is a graphical representation of possible failure modes of the preferred embodiment; and Figure 4 is a graphic representation of a causal network for the failure modes of Figure 3.

DETAILED DESCRIPTION OF THE PREFERRED MODALITY One modality of the invention uses analytical models of electrical equipment operation that contains fluid in combination with causal networks for the purpose of determining operating status, diagnostics, and prognosis of electrical equipment containing fluid. Analytical models can include models of thermal characteristics, electric and magnetic fields, temperature-pressure-volume, failure modes, cause of root failure, gas in oil, and chemical composition. The analytical models are adjusted over time to take into account behavioral changes in the electrical equipment that contains fluid. A belief network is used to dynamically adjust the parameters of the causal network. Figure 1 illustrates a preferred embodiment of the invention. The diagnostic system 10 comprises electrical equipment 20, an electrical transformer in the preferred embodiment, and diagnostic device 30. The electrical equipment 20 comprises electrical components 22, which include a transformer core and coils / windings, and a containment container. 24 surrounding the components 22. The containment vessel 24 is adapted to contain fluid F, such as oil, to cool and insulate the components 22. The fluid F can be pumped through the containment vessel 24 and a radiator (not is illustrated) by the pump 26 disposed in or near the containment vessel 24. The radiator serves as a heat exchanger to cool the fluid F and therefore conduct the heat away from the components 22 and may include any known form of tubes, ducts, heat exchange surfaces, cooling elements, pumps, fans, or the like. Cooling can be achieved through thermal convection, thermal conduction, molecular convection of fluid F, or in any other form. A plurality of sensors 28a-28f are operatively coupled to electrical equipment 20 in a suitable manner. The sensors 28a-28f may be of any type suitable for detecting a desired parameter and generating, ie emitting, a signal indicating the value of the detected parameter. In the preferred embodiment, the sensor 28a is a voltmeter, ammeter, or the like for measuring the electrical load on the electrical equipment 20 and is coupled to charging terminals 29 of the electrical equipment 20, the sensor 28b is a temperature sensor disposed in the fluid F inside the containment vessel 24, the sensor 28c is a pressure sensor disposed in the fluid F within the containment vessel 24, the sensor 28d is a molecular hydrogen sensor disposed in the fluid F within the containment vessel 24, sensor 28e is a fluid circulation sensor, and sensor 28f is a fluid level sensor. In the preferred embodiment, the sensors 28b-28f are in contact with the fluid F. However, the invention requires that only the sensors 28b-28f be able to measure the parameters of the fluid F. Accordingly, the sensors can be in contact or non-contact relationship with fluid F depending on the type of sensors used, as discuss in more detail right away. For example, the sensors 28b-28f can be remotely positioned from the fluid F and can have sensor elements disposed in the fluid F. Alternatively, the sensors 28a-28f can be completely away from the fluid F and can monitor parameters in the fluid F from a distance, such as through optical means or the like. The sensors 28a-28f can be arranged at any location and can detect parameters of the electrical equipment 20 at any location as dictated by the type, size, and shape of the electrical equipment 20, the diagnoses and forecasts that will be evaluated, and any other details of the practical application. For example, it may be desirable to detect values of winding temperature, hot spot temperature, core temperature, bypass exchanger charge temperature (OLTC), ambient temperature, gas gap pressure, fluid level, fluid moisture, fluid dielectric strength, partial acoustic discharge, sound pressure in the equipment, ambient sound pressure, various gases in the fluid, fluid flow, fan / pump speeds and currents, load currents, line voltage, and vibration. All these parameters can be detected with known sensors. Additionally, plural sensors can be used to measure the same parameter simultaneously in more than one location. Of course, there can be any number of sensors depending on the parameters that will be measured and the desired measurement locations.

The sensors 28a-28f can be fixedly disposed in the desired position on or in the electrical equipment 20 or they can be disposed removably in desired locations when selectively inserted through sensor ports or other openings formed through of walls of containment container 24 or other portions of electrical equipment 20. Sensors 28a-28f may be of any suitable type. For example, each sensor 28b-28f can be one or more of semiconductor insulating metal diode sensors, fiber optic probes, acoustic or optical waveguides, bimetal sensors, thin film sensors, or any other suitable sensor or transducer to measure the parameters noted in the present. The sensor 28a can be any known type of electrical charge sensing device such as a resistance or inductive device. If the sensors are of an electrical or electronic nature and are arranged within a high EM field region of the electrical equipment 20, a suitable electrical cover can be provided. The types of optical sensors or others do not need to be electrically covered regardless of their location. The sensors 28a-28f generate data or signals that indicate the operating parameters of the electrical equipment 20 detected by them. The diagnostic device 30 is coupled to the electrical equipment 20 to determine various operating characteristics of the electrical equipment 20 and comprises the processor 40, the input / output interface (I / O) 50, the user interface 60, the bus data 70 and power supply 72. Sensors 28a-28f and pump 26 are communicatively coupled to / O 50 to through an adequate conductive mechanism. For example, if the sensors 28a-28f are electronic or produce electronic signals, the electrical conductors can be extended from the sensors 28a-28f to / 50. The conductors can include any strip, connector, or similar terminal suitable for connection to / Or 50. The coupling, ie the driving signals, between sensors 28a-28f and l / O 50 can be achieved by cables, fiber optic strands, radio frequency devices, infrared devices, or any other known mode. The pump 26 can be coupled to IO 50 in a similar manner. The diagnostic device 30 can communicate with the sensors 28a-28f and the pump 26 over a remote or local communication link, such as a telephone line, a serial link RS232, a universal serial bus (USB) link, link of radio frequency, infrared link or similar. The power supply 72 is illustrated as a separate element. However, the power supply can be integral with one or more of the other components. I / O 50 includes the plural signal conditioning circuits 52a-52g which may be of any type suitable for conditioning the signals or data emitted from the sensors 28a-28f and the pump 26. For example, the conditioning circuits of signal 52a-52g may include circuitry for functions of uniformity, sampling, current limitation, obstruction, amplification, attenuation, or others, in a known manner. It should be noted that the pump 26 may include a feedback capability to provide a signal or data that represent the operating state thereof, such as one or more of a tachometer recharge, vibration feedback, or charge feedback. Similarly, each signal conditioning circuit 52a-52g is capable of conditioning emission signals that will be sent to sensors 28a-28g and pump 26. These signals can be related to adjustment of thresholds, linearization parameters, sensitivity, speed settings (in the case of pump 26), and the like as will be described further below. The signal conditioning circuits 52a-52g are illustrated as separate elements. However, one or more of the signal conditioning circuits may be integral with the sensor, the processor, or other components. I / O 50 also includes a digital-to-analog and analog to digital multi-channel converter (D / A) 54 that provides an interface between the signals of the sensors 28a-28f and the pump 26, which are analogous to each other. the preferred embodiment, and the processor 40, which is digital in the preferred embodiment. Of course, if the sensors 28a-28f, the pump 26 and the processor 40 are all analogue or all digital, the D / A 54 can be omitted. The D / A54 is coupled to the processor 40 via the data bus 70 for Two way communication. The processor 40 includes the central processing unit (CPU) 42, and the memory device 44. The CPU 42 executes a control program stored in the memory device 44. The memory device 44 may include a memory device. standard magnetic, such as a hard disk, to store the control program and other data and also includes an Awork space @, such as a random access memory (RAM) for the CPU 42 to store data temporarily. The diagnostic device 30 may also include user interface 60 comprising the display device 62 and the input device 64. The input device 64 may be any type of keyboard, mouse, switch or switches, or any other device to allow the user provides placements, parameters, instructions or the like to the processor 30. The display device 62 may be any type of display to indicate the operating state, such as an LCD or CRT screen, a pilot lamp or series of pilot lamps, an audible alarm or similar. The power supply 72 supplies power to other elements of the diagnostic device 30 and can be any type of known power supply, such as a battery, a fuel cell, or a rectifier to provide DC power from an AC input. The diagnostic device 30 can be a microprocessor-based device, such as a personal computer or programmable logic controller, a hard wire logic device, or any other device to achieve the necessary processing described below. The processor 40 contains a preprogrammed control program stored in the memory device 44 to determine characteristics, such as diagnostics, forecasts, characteristics of performance, and life evaluation of the electrical equipment 20 in the manner described below. Specifically, the control program includes various analytical models of electrical equipment 20 behavior, a causal network, and a belief network. The data bus 70 may use any suitable type of hardware and / or software protocols to transmit and receive data or signals. For example, the data bus 70 may be an ISA bus, DCI bus, GPIB bus, or the like. The data can be transmitted to and received from a remote or local host computer to provide diagnostics, additional forecasts and to control and coordinate diagnostics and operation of a plurality of electrical equipment containing fluid. In operation, the containment vessel 24 is completely or partially filled with fluid F, such as oil. In this state, the sensors, 28b, 28c, 28d, 28e and 28f are in contact with, or otherwise can track parameters in, the fluid F. In the preferred embodiment the sensor 28b detects the fluid temperature F, the sensor 28c detects the pressure in the fluid F, the sensor 28d detects the content of molecular hydrogen in fluid F, the sensor 28e detects the circulation of the fluid F, and the sensor 28f detects the level of the fluid F. Other parameters detected may include, but are not limited to the content of various gases (such as acetylene, carbon, monoxide, and ethylene), winding temperature, hot spot temperature, core temperature, bypass exchanger charge temperature (OLTC), ambient temperature, pressure gas space, fluid level, humidity in fluid, dielectric fluid resistance, partial acoustic discharge, sound pressure, ambient sound pressure, gas content, fluid flow, pump speed, and vibration. Of course, any parameter which is useful for determining the operating state and / or which is considered in an analytical model of electrical equipment 20 can be detected. Figure 2 is a flow chart of a diagnostic determination routine according to the preferred modality. The routine can be in the form of software stored in the memory device 44 and written in any suitable language or code that can be read by the CPU 42. For example, the software routine can be written in Basic, C ++, or the like. The emission signals, ie the sensor data, from D / A 54 are representative of the parameters of the equipment 20 and are fed to the processor 40 on the bus 70. The sensor data is first subjected to the validation step 100 to determine whether the corresponding sensors are working properly. For example, the validation step 100 may include a step of comparing the sensor data with minimum and maximum predetermined thresholds corresponding to possible (though not necessarily desirable) values of the parameters detected by the sensors 28a-28f. For example, if the sensor data corresponding to the sensor 28b (a temperature sensor) indicate a higher or lower temperature of a possible oil temperature, for example lower than an ambient temperature or much higher than the evaluation of At the temperature of the components 22, it can be assumed that the sensor 28a is not working properly. In addition, the passage of validation 100 may include a step of checking for impossible fluctuations in the value indicated by the sensor data that are indicative of an intermittent problem on the sensor 28a. The validation step 100 is conducted in a similar manner for each of the sensors 28a-28f. If one of the sensors 28a-28f is indicated as not functioning properly in the validation step 100, an appropriate error message is displayed on the display device 62 or on a remote display device or otherwise loaded or communicated. to an operator or a remote computer or similar. Data from a faulty sensor can be ignored until the sensor is repaired or replaced. Alternatively, the parameter measured by the defective sensor can be calculated by one of the models in the manner described below. The routine then proceeds to the calculation step 110 in which the various parameters are calculated based on other parameters detected according to models developed for the particular parameter in the equipment 20. For example a hydrogen model is an algorithm that calculates the theoretical value of molecular hydrogen (H2) in the fluid F of the equipment 20 based on equipment configuration information, i.e. the size, relative dimensions, components, type of fluid, etc. of the equipment 20. The preferred embodiment includes the hydrogen model 112, the temperature model 114, and the pressure model 116. Any of several known models can be used for each parameter. For example, the AMIT Hidrogen Model @ developed at the Massachusetts Institute of Technology could be used such as the hydrogen model 112. The MIT hydrogen model uses the following equation: H2 [k] = a + ß X Tácete supeporM + Y (Tácete superior [k] f where: = index of time measurement, H2 [/ c] = calculated value of molecular hydrogen in each index range; upper oil [k] = upper oil temperature measured in each index; a = molecular hydrogen constant; β = first order coefficient of molecular hydrogen; Y ? = second order coefficient of molecular hydrogen.

Similarly, the AMIT Temperature Model @ can be use as the temperature model 114 using the following equation: T T toP [k] = - T toP [k - 1] + - - (T amb [k] = Tu [k]) T + At T + At o o where: k - time measurement index; T top [k] = upper oil temperature calculated in each index interval; T amb [k] = ambient temperature measured in each interval index; ? t = sampling frequency; T u [k] = last higher oil lift for current load L of each index interval; and T0 = oil time constant calculated from several physical transformer properties. Any of the various known pressure models can be used. The models are configured (that is, the constants, and coefficients are calculated) according to the particular physical characteristics of the electrical equipment 20. For example, the evaluated load, the average conductor temperature rise over the top oil, the Upper oil lift, load loss ratio, cooling characteristics, loss, thermal capacity, weight of components 22, weight of containment vessel 24, and fluid capacity of electrical equipment 20 they can be considered in a known way to develop the appropriate models. Once the various values for each parameter have been calculated by the processor 40 according to the models in step 110, the calculated values of each parameter are compared to the measured values, ie the sensor data, of the corresponding parameter in the anomaly detection step 120. If the measured values are within a prescribed tolerance or scale of the calculated value, no anomaly is detected for that parameter and no alarm is sounded. On the other hand, if the measured value of a particular parameter is not within the tolerance or scale prescribed may sound an alarm on the display device 62, a separate alarm device, a remote display device or the like or otherwise charged or communicated, thereby providing a preliminary status indication. In step 130, the differences between the values of measured and calculated parameters are applied as indicators of a causal network. The causal network is part of the routine and therefore can be stored in the memory device 44. The causal network can be developed in advance in the manner described below. Each causal network has a cause and effect relationship between a plurality of nodes, in which some of the nodes represent root causes associated with failures in the electrical equipment 20, ie failure modes, and some of the nodes represent observable manifestations of the failure modes. Each of the failure modes in the causal networks has an earlier probability that indicates the probability of the particular failure. Each of the nodes in the causal network also has conditional probability information that represents the resistance of the relationships of the manifestation node to its failure mode, that is, the cause and effect relationships between faults and observable symptoms for the electrical equipment 20. In this way, in order to develop the causal network there must be an understanding of how each component in the electrical equipment that contains fluid operates and the observable symptoms of each failure mode. Some of the possible failure modes to which the equipment electrical 20 may be subjected to pump failure 26 (including engine failure and damage to the fan blade), containment container leak 24, component 22 failure, insulation failure on component 22, an overload condition , dielectric decomposition of fluid F, and a radiator leak. After all possible failure modes have been identified for electrical equipment 20, the causal network for electrical equipment 20 is developed. Figure 3 illustrates the failure modes identified above for electrical equipment 20. Those failure modes are designed to be illustrative and the list does not include all. Each of the failure modes is designed as a failure mode node, or a cause, and is represented as a box with rounded corners. Each cause has some higher level of effect on electrical equipment 20. It is also possible that several causes may have the same effect. At some point, an effect manifests itself in such a way that it can be measured or observed. When the state of a single observable symptom or the state of several observable symptoms is unique to a single cause, it will then be possible to unequivocally identify the problem. Figure 4 illustrates an example of cause and effect relationships for each of the failure modes identified in Figure 3, that is, a causal network for electrical equipment 20. The phrase Acausal network @ (causal network) as used herein refers to a network, algorithm, or the like that indicates potential failure, and its probable relationship to various manifestations.

The cause and effect relationship between each of the nodes (modes of failure and observable manifestations) is shown with an arrow pointing in the direction of causality. In Figure 4, the modes of failure of pump motor failure and pump blade failure are each shown to have an effect which is characterized by the observable manifestation of low fluid circulation. The low circulation node is coupled with a low circulation indicator node, which indicates whether the fluid circulation is low as measured by the sensor 28e. The indicating node is a node that is always an effect that directly represents the value of a measured parameter, a calculated value of the parameter, or the difference between the measured parameter and the calculated value thereof and is represented by a circle. The pump blade failure node, and the pump motor failure node are each shown to have an effect characterized by low fluid circulation through the containment vessel 24, as indicated by the sensor data. 28e as compared to the values calculated by the pressure model 116 (in step 110 above). The containment container leakage node is shown to have an effect that the fluid level will be low as indicated by the fluid level sensor 28f in the containment vessel 24. In addition, the pump motor failure mode it is coupled with a indicating node corresponding to the feedback, for example, a tachometer, from the pump 26. At a higher level, the effects of low fluid circulation and low fluid level have an effect on the electrical equipment 20 that It is characterized by inadequate cooling capacity because the fluid does not flow properly through a radiator. This effect is coupled with an indicator that checks if the fluid temperature is above normal, as indicated by the difference between the temperature value calculated by the temperature model 114 (in step 110 described above) and the temperature measured by the temperature sensor 28b. For each failure mode in the causal network, an initial conditional probability is assigned that indicates the probability of a failure. Conditional probabilities are factors assigned to each failure mode that indicate the relative likelihood that the cause is present. Figure 4 shows an example of conditional probabilities assigned to each of the failure modes for electrical equipment 20. The conditional probabilities are listed as decimal numbers under the corresponding failure mode node. It should be noted that in cases where a component has multiple failure modes, the conditional probability of failure due to each failure mode is required. Furthermore, it should be noted that the conditional probability magnitudes of fault mode nodes grouped together dictate the relative probability that a particular mode is the problem. For example, according to the causal network of Figure 4, if there is low fluid flow F, then it would be predicted that a pump motor failure (conditional probability of OJ) was ten times more likely to cause low fluid circulation. than a pump blade failure (conditional probability of .001).

After a conditional probability has been assigned to each of the failure modes, a limit probability is assigned that estimates the force of the relationship between the failure mode and a next level of manifestation for each relation. The limit probabilities are listed according to the line connecting the fault mode nodes with the manifestation nodes and represent the probability that the manifestations will exist since the failure mode is already known to exist. If all failure modes are independent and if all failure modes do not exist, then the manifestation does not exist. In the preferred embodiment, a single parameter between 0 and 1 is used as a limit probability to represent the strength of the relationship (1 being indicative of a direct relationship or of a one-to-one relationship) However, any indication representing the relationship between the failure mode node and the manifestation node can be used.As an example, a leak in the containment vessel 24 will result in a detected effect of low fluid level F 90% of the times, as indicated by a limit probability of 0.9. The other 10% of the time, the leak will be too slow to significantly affect the fluid level.It should be noted that the conditional probability information is derived from the limit probability This information can be determined experimentally or mathematically The causal network described above is applied in step 130 of Figure 2 and is used to determine the operational operation of the electrical equipment . The indicators of the causal network, ie the parameters measured by the sensors 28a-28f and the differences between those parameters and the calculated values of the same rendered by the models 112, 114 and 116, are evaluated according to the probability information. conditional and the limiting probability information. The processor 40 continuously recalculates the probabilities of the causal networks according to the status of the mapped indicators, as indicated by the sensors 28a-28f and the appropriate models. In particular, the probabilities are recalculated in the step 140 using a known belief network solution algorithm, such as a Baysian Belief Network and fed back into the causal network of step 130. For example, if low fluid circulation is detected by the sensor 28e and the pump tachometer 26 indicates a normal pump motor condition, the probabilities are adjusted to increase the probability that there is a pump blade failure. The processor 40 then evaluates the probabilities recalculated in the causal network. In addition, the processor 40 can provide a list of the most likely causes for any abnormality, as well as a list of corrective actions that must be taken to correct or prevent the failure. The probabilities recalculate through the belief network based on information learned from the causal network using the previous probabilities. Recalculations can be based on known inference techniques, influence techniques, or Bayes' theorem.

The routine illustrated in Figure 2 is conducted in essentially a continuous manner in the preferred embodiment. However, the procedure can be conducted in a periodic manner automatically, or at the request of an operator. The various constants and coefficients of the models are adjusted over time to compensate for normal behavior changes in electrical equipment 20 over time. The constants and coefficients can be determined mathematically or experimentally in a known manner. The emission of the causal network can be processed in any way for diagnoses, forecasts, or the like. For example, you can generate the status reports that relate to operational characteristics of the electrical equipment, the alarms can be made, or the operation of the equipment can be adjusted. The invention can be applied to any electrical equipment containing fluid. Any desired parameters can be detected. Sensor or signal data can be processed in any form to provide indication of incipient failure forecasts, life evaluation, maintenance programs, fault root cause identification, or other states of electrical equipment based on experimental or mathematical models. Additionally, the invention may provide evaluations of performance characteristics such as utilization factors, load scheduling, efficiency, energy loss, energy factor, harmonics, and on tap changer charge efficiency.

The diagnostic device may be local, that is, located in a close manner with respect to the electrical equipment, or remote, that is, located at a remote location with respect to the electrical equipment. The histories of the values of the various parameters as they are measured and how they are calculated, can be compiled to additionally assist in determining failure. The various sensors can be collected at regular intervals and the intervals can be increased in times of heavy load on the equipment or with the indication of an abnormal state of the equipment. The invention has been described through a preferred embodiment. However, various modifications can be made without departing from the spirit of the invention as defined by the appended claims.

Claims (48)

NOVELTY OF THE INVENTION CLAIMS

1. - An intelligent analysis apparatus (10) for electrical equipment containing fluid (20) of the type having components (22) surrounded by fluid (F), said apparatus comprising: electrical equipment (20) having a containment container (24) ) configured to contain a fluid (F) and at least one electrical component (22) disposed in said containment container (24); plural sensors (28a-e) configured to emit signals indicating plural operating parameters of said electrical equipment (20); and a diagnostic device (30) coupled to said sensors (28a-e), said diagnostic device (30) has a processor (40) operative to determine operating characteristics of said electrical equipment (20) based on at least one analytical model (112, 114, 116) of said electrical equipment (20) and the signals emitted by said sensors (28a-e) by the application of parameter values calculated by at least one analytical model (112, 114, 116) and values of parameters as indicated by the signals of said sensors (28a-e) in a causal network.

2. An apparatus according to claim 1, further characterized in that said diagnostic device (30) compares a parameter calculated by at least one analytical model (112, 114, 116) with a corresponding measured parameter and uses a comparison result as an indicator in the causal network.

3. An apparatus according to claim 2, further characterized in that the probabilities of the causal network are updated based on the probability of the indicators (130) obtained from the analytical model (112, 114, 116) or the parameters detected.

4. An apparatus according to claim 3, further characterized in that the variables of the at least one analytical model (112, 114, 116) are adjusted over time in correspondence with acceptable behavior changes of said electrical equipment (20) with time.

5. An apparatus according to claim 4, further characterized in that said sensors (28a-e) comprise a temperature sensor (29b) configured to emit a signal indicative of fluid temperature (F) within said containment vessel ( 24), a gas sensor (28d) configured to emit a signal indicating the gas content of the fluid (F) within said containment vessel (24), a charge sensor (28a) configured to emit a signal indicating the electric charge on the electrical equipment (20), and a pressure sensor 28 (e) configured to emit a signal indicating the pressure in said containment container (24).

6. An apparatus according to claim 5, further characterized in that said gas sensor (28d) is configured to emit a signal indicating the hydrogen content of the fluid (F) inside said containment vessel (24).

7. - An apparatus according to claim 6, further characterized in that the at least one analytical model (112, 114, 116) comprises a temperature model (114) and a hydrogen model (112).

8. An apparatus according to claim 4, further characterized in that said processor (40) is disposed outside said containment container (24) and said sensors (28a-e) are disposed within the containment vessel (24), said apparatus further comprises means for driving the signals from the sensors (28a-e) to the processor.

9. An apparatus according to claim 4, further characterized in that said diagnostic device (30) further comprises a user interface module (60) having a display device (62) for displaying an indication of the operating characteristics of said electrical equipment (20) and input device (64) to allow a user to supply at least one of data and commands to said diagnostic device (30).

10. An apparatus according to claim 5, further characterized in that said gas sensor (28d) is configured to emit a signal indicating at least one of hydrogen, carbon monoxide, carbon dioxide, oxygen, nitrogen, hydrocarbons, and hydrocarbon derivatives.

11. - An apparatus according to claim 4, further characterized in that said processor (40) comprises a computer having a CPU (42) and a memory device (44).

12. An apparatus according to claim 4, further characterized in that said electrical equipment (20) comprises a transformer.

13. An intelligent analysis apparatus (10) for electrical transformers containing fluid, said apparatus comprises: a transformer (20) having a containment vessel (24) configured to contain a fluid (F) and a core and coil (22) disposed in said containment vessel (24); plural sensors (28a-e) configured to emit signals indicating plural operating parameters of said transformer (20); and a diagnostic device (30) coupled to said sensors (28a-e), said diagnostic device (30) has a processor (40) operative to determine operating characteristics of said transformer (20) based on the at least one analytical model (112, 114, 116) of said transformer (20) and the signals emitted by said sensors (28a-e) applying parameter values calculated by the at least one analytical model (112, 114, 116) and parameter values as indicated by the signals of said sensors (28a-e) in a causal network.

14. An apparatus according to claim 13, further characterized in that said diagnostic device (30) compares a parameter calculated by the at least one analytical model (112, 114, 116) with a corresponding measured parameter and uses a result of the comparison as an indicator in the causal network.

15. An apparatus according to claim 14, further characterized in that the probabilities of the causal network are adjusted based on the probability of the indicators (130) obtained from the analytical model (112, 114, 116) or parameters detected.

16. An apparatus according to claim 15, further characterized in that the at least one analytical model (112, 114, 116) is adjusted over time in correspondence with changes in acceptable behavior of said transformer (20) with time.

17. An apparatus according to claim 16, further characterized in that said sensors (28a-e) comprise a temperature sensor (28b) configured to emit a signal indicative of fluid temperature (F) within said containment vessel ( 24), a gas sensor (28d) configured to emit a signal indicating the content of the gas of the fluid (F) within said containment vessel (24), a charge sensor (28a) configured to emit a signal indicating the electric charge on said transformer (20) and a pressure sensor 28 (e) configured to emit a signal indicating pressure in said containment vessel (24).

18. An apparatus according to claim 17, further characterized in that said gas sensor (28d) is configured to emit a signal indicating a hydrogen content of the fluid (F) inside said containment vessel (24).

19. - An apparatus according to claim 28, further characterized in that the at least one analytical model (112, 114, 116) comprises a temperature model (114) and a hydrogen model (112).

20. An apparatus according to claim 16, further characterized in that said processor (40) is disposed outside the containment vessel (24) and the sensors (28a-e) are disposed within the containment vessel (24), said The system further comprises means for driving signals from the sensors (28a-e) to the processor.

21. An apparatus according to claim 16, further characterized in that said diagnostic device (30) further comprises a user interface module (60) having a display device (62) to display an indication of the operating characteristics of said transformer (20) and an input device (64) to allow a user to supply at least one of data and commands to said diagnostic device (30).

22. An apparatus according to claim 17, further characterized in that said gas sensor (29d) is configured to emit a signal indicating at least one of hydrogen, carbon monoxide, carbon dioxide, oxygen, nitrogen, hydrocarbons, and hydrocarbon derivatives.

23. An apparatus according to claim 16, further characterized in that said processor (40) comprises a computer having a CPU (42) and a memory device (44).

24. - An intelligent analysis apparatus (10) for electrical equipment containing fluid (20) of the type having components (22) surrounded by fluid (F), said apparatus comprising: electrical equipment (20) having a containment container (24) ) configured to contain a fluid (F) and at least one electrical component (22) disposed in said containment container (24); detection means (28a-e) for detecting plural operating parameters of said electrical equipment (20) and for emitting signals indicating the plural operating parameters of said electrical equipment (20); and diagnostic means (30) for determining operating characteristics of said electrical equipment (20) based on at least one analytical model (112, 114, 116) of said electrical equipment (20) and the signals emitted by said detector means (28a- e) applying parameter values calculated by the at least one analytical model (112, 114, 116) and parameter values as indicated by the signals of the detection means (28a-e) in a causal network.

25. An apparatus according to claim 24, further characterized in that said diagnostic means (30) comprise means for comparing a parameter calculated by the at least one analytical model (112, 114, 116) with a corresponding measured parameter and means to use a comparison result as an indicator in the causal network.

26. An apparatus according to claim 25, further characterized in that said diagnostic means (30) comprise means for adjusting probabilities of the causal network based on the probability of the indicators (130) obtained from the analytical models (112, 114, 116) or parameters detected.

27. An apparatus according to claim 26, 5 further characterized in that said diagnostic means (30) comprise means for adjusting variables of the at least one analytical model (112, 114, 116) over time in correspondence to acceptable behavior changes of said electrical equipment (20) over time.

28. An apparatus according to claim 27, »Further characterized in that said sensing means (28a-e) comprise • 9 temperature sensing means (28b) for emitting a signal indicating the fluid temperature (F) within the containment vessel (24), means for detecting gas (28d) for emitting a signal indicating the gas content of the fluid (F) inside said containment vessel (24), load detecting means (28a) for emitting a signal indicative of the electric charge on the equipment electrical (20) and pressure detecting means (28c) for emitting a signal indicating the pressure in said containment vessel (24).

29. An apparatus according to claim 28, further characterized in that said gas detection means (28d) comprise means for emitting a signal indicating a hydrogen content of the fluid (F) inside said containment vessel (24). ).

30. - An apparatus according to claim 29, further characterized in that the at least one analytical model (112, 114, 116) comprises a temperature model (114) and a hydrogen model (112).

31. An apparatus according to claim 27, further characterized in that it additionally comprises means for driving signals from the detector means to said processor.

32. An apparatus according to claim 27, further characterized in that said diagnostic means (30) additionally comprise user interface means (60) to display an indication of the operating characteristics of the electrical equipment (20) and input means to allow a user to supply at least one of data and commands to said diagnostic means (30).

33.- An apparatus according to claim 28, further characterized in that said gas detection means (28d) comprise means for emitting a signal indicating an amount of at least one of hydrogen, carbon monoxide, carbon dioxide, oxygen , nitrogen, hydrocarbons, and hydrocarbon derivatives.

34. An apparatus according to claim 27, further characterized in that said diagnostic means (30) comprise a computer having a CPU (42) and a memory device (44).

35.- An apparatus according to claim 27, further characterized in that said electrical equipment 20 comprises a transformer (20).

36. - A method for intelligent analysis of electrical equipment containing fluid (20) of the type having components (22) surrounded by fluid (F), said method comprises the steps of: detecting plural operational parameters of the electrical equipment (20) having a containment vessel (24) configured to contain a fluid (F) and at least one electrical component (22) disposed in said containment vessel (24); generating signals indicating the plural operating parameters of the electrical equipment (20) detected in the detection step; and determining operating characteristics of the electrical equipment (20) based on at least one analytical model (112, 114, 116) of the electrical equipment (20) and the signals generated in said generation step by applying parameter values calculated by the at least one model analytical (112, 114, 116) and parameter values as indicated by the signals generated in the generation step in a causal network.

37.- A method according to claim 36 further characterized in that said step of determining comprises the steps of comparing a parameter calculated by the at least one analytical model (112, 114, 116) with a corresponding measured parameter as indicated by signals in the generation step and using a result of said comparison step as an indicator in the causal network.

38.- A method according to claim 37, further characterized in that said step of determination comprises the step of adjusting the probabilities of the causal network based on the probability of the indicators (130) obtained from the analytical model (112, 114, 116) or parameters detected.

39. A method according to claim 38, further characterized in that said step of determining comprises the step of adjusting variables of the at least one analytical model (112, 114, 116) with time in correspondence with changes in acceptable behavior of the equipment electrical (20) over time.

40. A method according to claim 39, further characterized in that said detection step comprises the steps of detecting temperature inside the containment vessel (24), detecting gas content of the fluid (F) within the containment vessel (24). ), detecting the electric charge on the electrical equipment (20) and detecting pressure in the containment vessel (24).

41. A method according to claim 48, further characterized in that said step of detecting the gas content comprises detecting a hydrogen content of the fluid (F) within the containment vessel (24).

42. A method according to claim 41, further characterized in that the at least one analytical model (112, 114, 116) used for said determination step comprises a temperature model (114) and a hydrogen model (112).

43.- A method according to claim 39, further characterized in that it additionally comprises the steps of display an indication of the operating characteristics of the electrical equipment (20) and provide at least one of data and orders.

44. A method according to claim 40, further characterized in that said step of detecting the gas content comprises detecting at least one of hydrogen, carbon monoxide, carbon dioxide, oxygen, nitrogen, hydrocarbons, and hydrocarbon derivatives.

45. An apparatus according to claim 7, further characterized in that the at least one analytical model (112, 114, 116) further comprises a pressure model (116).

46.- An apparatus according to claim 19, further characterized in that the at least one analytical model (112, 114, 116) comprises a pressure model (116).

47. An apparatus according to claim 30, further characterized in that the at least one analytical model (112, 114, 116) comprises a pressure model (116).

48. A method according to claim 42, further characterized in that the at least one analytical model (112, 114, 1 16) comprises a pressure model (116).