COMBUSTION ENGINE MONITORING SYSTEM
Patent Information
- Application Number
- DE102024117499
- Authority / Receiving Office
- DE · DE
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-06-28
- Filing Date
- 2024-06-20
- Publication Date
- 2025-01-02
Smart Images
Figure 00000000_0000_ABST
Abstract
Description
Technical FieldThe present disclosure relates to internal combustion engines such as those for vehicles or for stationary power generation. The present disclosure relates more particularly to internal combustion engines for work machines such as excavators, track drills, tracks, cold planers, paving machines, dozers, compacting machines, tractors, or the like, as well as to stationary power generation systems or "aggregates.". Internal combustion engines may include fluid filters to prevent contaminants from entering the engine.Prior ArtPower for machines, e.g., agricultural, industrial, construction, or other heavy machinery, and generators may be generated by an internal combustion engine. Internal combustion engines combust a mixture of air and fuel in the cylinders, thereby producing drive torque and power. Generally, an internal combustion engine may include an air intake system that introduces a certain amount of air into the cylinders of the engine. A fuel system may then supply a certain portion of the fuel to the cylinders, resulting in drive torque and power during combustion. A control system may be used to adjust the fuel-air mixture to promote the desired combustion. Internal combustion engines may include fluid filters to prevent contaminants from entering the engine. These fluid filters must typically be replaced to maintain the desired functionality of the engine and to protect other parts of the engine from damage.SummaryThis document describes an internal combustion engine monitoring system. The system may monitor operating conditions of the engine to aid in predicting the useful life or an anticipated plugging event of a fluid filter, e.g., an air or fuel filter. For example, the system may include or use at least one fluid filter disposed between at least one fluid inlet of the internal combustion engine and at least one fluid source or surrounding fluid environment. The system may include a first fluid sensor arranged to receive a first indication of the respective fluid pressure values on the first and second sides of the fluid filter in a first engine operating state. For example, the first and second indications of the respective fluid pressure values each include a plurality of fluid pressure measurements on the first and second sides of the fluid filters over time.In one example, the system may include a second fluid sensor arranged to receive a second indication of the respective fluid pressure values on the first and second sides of the fluid filter in a second engine operating state. The system may include processing circuitry to receive sensor data from the first and second fluid sensors. The processing circuit may determine a time difference between the first and second sides of the fluid filter to estimate the flow of the fluid through the fluid filter. The processing circuit may also adjust at least one parameter of the received first and second indications to the respective fluid pressure values to mitigate a difference due to a difference between the first and second engine operating conditions. The processing circuit may then compare the respectively adjusted first information about the fluid pressure values with the respectively adjusted second information about the fluid pressure values. For example, the processing circuit may estimate a period of time during which the fluid pressure difference exceeds a threshold.The system may include a user interface to display a warning indicative of a condition of the engine fluid filter based on the monitored pressure differential, the warning being triggered by the processing circuit when the determined pressure differential exceeds a certain threshold difference. For example, the user interface may be included to display a warning including an indication of replacement or cleaning of the fluid filter in anticipation of a plugging event of the fluid filter.In one example, the first and second engine operating conditions may include first and second engine boost pressures, respectively. For example, the first engine boost pressure may be in a range of 0 kiloPascals (kPa) and 50 kPa, and the second engine boost pressure may be greater than 100 kPa. In one example, the processing circuit initiates the alert including generating an indication of replacement or cleaning of the fluid filter based on a differential slope that exceeds a certain threshold.Brief Description of the DrawingsIn the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. Like numerals having different letter suffixes may represent different instances of similar components. The drawings illustrate various embodiments discussed herein generally and by way of example, but not limitation. FIG. 1 shows a work machine connected to an engine monitoring system, according to one or more examples. FIG. 2 is a block diagram of an example engine monitoring system executing an algorithm for estimating the state or predicting the replacement date of a fluid filter. FIG. 3 is a block diagram illustrating components of a computing machine for performing operations to estimate a state or predict replacement of a fluid filter. FIG. 4 is an illustration of a method for detecting a fluid filter condition of an internal combustion engine. FIG. 5A is a graph showing a measured air filter restriction versus boost pressure. FIG. 5B is a graph depicting measured air filter restriction versus time. FIG. 6A is a diagram of the operations for predicting a predicted replacement date of fluid filters. FIG. 6B is a diagram of the operations for predicting a predicted replacement date of fluid filters. FIG. 7 includes plots of certain data parameters versus time associated with plugging of a fluid filter.DETAILED DESCRIPTIONFIG. 1 shows a work machine connected to an engine monitoring system, according to one or more examples. The monitoring system 100 may include or be communicatively coupled to one or more internal combustion engines 104, e.g., included in at least one work machine 102 (as shown in FIG. 2 ). The engine 104 may be used to generate power, such as for propulsion of vehicles or other machines, and / or for propulsion of auxiliary machinery of the work machine, such as hydraulic systems and the like. For example, the engine 104 may include one of several piston-cylinder arrangements and configurations, such as V-engines, inline engines, and horizontally opposed engines, as well as top cam and cam in-block configurations. In one example, the engine 104 may be used in both stationary applications and in vehicles and / or machines including those associated with various industries, such as power generation (e.g., a generator), oil exploration, construction, agricultural and forest management, transportation, material turnover, waste management, etc.As shown in FIG. 1, the monitoring system 100 may include or be communicatively coupled to one or more work machines, e.g., an excavator 102. Examples of work machines 102 for use with the monitoring system 100 may include excavators, tractors, dozers, tractors, packers, paving machines, blending vehicles, asphalt distribution vehicles, off-road trucks, wheel loaders, separators, compactors or rollers, ground stabilizers, generators, etc.The monitoring system 100 may also include processing circuitry 106 for receiving data from the one or more internal combustion engines. For example, a single work machine 102 may include a transceiver 108 communicatively coupled to one or more sensors of an internal combustion engine 104 to communicate the data to a remote processing circuit 106. In another example, the processing circuitry 106 may be located onboard the single work machine 102. In one example, work machine 102 may include a frame 110. The frame 110 may be supported on a plurality of wheels 112, and the wheels 112 may allow the work machine 102 to move over the surface of a terrain or operate in an environment. Work machine 102 may also include a control cabin 114 or operator station, which may be located on frame 110 to receive a transport or propulsion system 118. The transport or propulsion system 118 may be configured to move the work machine 102 over the surface of the terrain or in the environment. The propulsion system 118 may include an engine 104, which may include one or more filters, e.g., fuel filters, air filters, or oil filters, coupled to the engine. The internal combustion engine may include a power take-off component for powering other auxiliary systems of the work machine, such as a hydraulic system that may be operably coupled to one or more implements or other systems. In one example, work machine 102 may include at least one power take-off (PTO) for driving a hydraulic system or other auxiliary energy sink, e.g., a motor or generator. The PTO may be mechanically coupled to and operably connected to the engine 104 of the work machine 102. When the PTO is on and powered by the engine 104, the PTO may be used to transfer energy (e.g., in the form of torque) from the engine 104 to, for example, a hydraulic system and / or the ground engagement system 120. For example, the PTO may be used to drive a hydraulic system, and the hydraulic system may be used to operate and implement a work implement connected thereto.The work machine may include a ground engaging drive system 120. The ground engaging drive system 120 may be connected to the frame 110 and the wheels 112 and configured to cooperate with the terrain or environment in which the work machine 102 operates. For example, ground engaging ETC system 120 may include tires, treads, and chains to interact with a surface. The ground engaging system 120 may be arranged to affect the movability of the work machine 102, for example, the ground engaging system 120 may be configured to provide traction, braking and steering functions.In one example, work machine 102 may include a hydraulic system 122. The hydraulic system 122 may be powered by the internal combustion engine 104 of the work machine 102 and used to operate any number of hydraulic work devices, such as hydraulic actuators and hydraulic implements. The hydraulic system 122 may be mechanically coupled to and operably coupled to the engine 104, e.g., via a PTO. The hydraulic system 122 may include a source of hydraulic fluid powered by a hydraulic pump powered by the PTO or otherwise by the engine 104. The hydraulic system 122 may include one or more fluid filters for filtering or removing contaminants from the hydraulic fluid. The hydraulic system 122 may also include a hydraulic reservoir for storing the hydraulic fluid.In one example, work machine 102 may include at least one work implement 124. The implement 124 may be mechanically coupled to and operatively coupled to the frame 110 of the work machine 102, e.g., proximate to the control cabin 114 or operator station. The implement 124 may include, for example, an implement, tool, or task-specific device. For example, the implement 124 may include an implement such as a paver, saw, drill, boom, mower, trencher, or the like, used to perform certain tasks associated with the work machine 102. Implement 124 may also include implements or tools that may be used for construction or construction applications, such as reactive force compaction, vibratory compaction, compaction wheels, or the like. The implement 124 may also include various horticultural and / or agricultural applications, such as rakes, soil tilling tools, planting machines, sod cutters, harvesters, brush cutters, or the like.FIG. 2 is a block diagram of an example engine monitoring system executing an algorithm for estimating the state or predicting the replacement date of a fluid filter. In one example, the engine 104 may be communicatively coupled to an equipment control module (ECM) 120 communicatively coupled to the engine 104 and configured to receive data from at least one of the work machine 102 and the engine 104 to control operation of the engine 104. The ECM 120 may also be communicatively coupled to a user interface located in the control cabin 114, e.g., for outputting onboard diagnostic codes relating to the filters of the engine 104, for example. The ECM 120 may be connected to the systems and components of the work machine 102 and responsible for certain operations of the work machine, e.g., performance management, diagnostics, implement control, travel or other machine movements, etc. The ECM 120 may be configured to store the onboard diagnostic code data, and the data may be transmitted from the ECM 120 and received by the processing circuitry 106 of the monitoring system 100. Additionally, the ECM 120 may be communicatively coupled to one or more sensors (e.g., the fluid sensor 126) to receive sensor data relating to the work machine 102 or the engine 104. The ECM 120 may be communicatively coupled to transceiver circuitry, e.g., the transceiver 108, to receive remote data for generating a remote diagnostic code or to assist in generating the onboard diagnostic code.The transceiver 108 may be configured for communication with the processing circuit 106. The transceiver 108 may include a long-range wireless transceiver, such as a cellular, satellite, or WLAN transceiver, and may receive data from devices communicatively coupled to the transceiver 108, e.g., via a cellular, satellite, or WLAN network. The transceiver 108 may also include a short-range wireless transceiver, such as a Bluetooth transceiver, which may be used for communication with the other systems and components of the work machine 102 and / or with external transmissions outside the machine. In one example, processing circuitry 106 may be remote from work machine 102 and configured to serve as a gateway for data transmission via transceiver 108 communicating over a network. The network may be a local area network such as a mobile network or a global communication network such as the Internet. The network may communicatively couple the processing circuitry 106 to a remote / centralized server, e.g., operated by a manufacturer, dealer, service technician, etc., responsible for the work machine 102. The server may include one or more databases in which updated machine / component information, diagnostic information, replacement part information, analytical information, and machine / component operating data, etc., may be stored.Generally, the engine 104 may be connected to a fluid inlet (e.g., an air inlet, an oil inlet, a fuel inlet, etc.) Fluid is received from a source 132 (e.g., the environment, a reservoir, a fuel tank, etc.). The fluid may be filtered and / or otherwise conditioned by one or more filtering components (e.g., air filters, oil filters, fuel filters, etc.). From the filtering components, the fluid may flow into the engine 104 for combustion, and the exhaust emissions may exit via an exhaust passage. Thus, the engine 104 may be equipped with at least one fluid filter 134 disposed between the fluid inlet of the engine 104 and the source 132 for filtering the fluid from the source 132. The at least one fluid filter 134 may include materials for filtering or removing contaminants, particles, or debris from the fluid. For example, the at least one fluid filter 134 may include a mesh material, porous material, absorbent material, paper, woven material, etc., or a combination thereof. In one example, the at least one fluid filter 134 may include a replaceable filter element that may be replaced by the user, operator of the work machine 102, or service personnel.The monitoring system 100 may include at least one fluid sensor 126 coupled to the internal combustion engine 104. The at least one fluid sensor 126 may be used to detect an indication of a fluid pressure corresponding to the fluid filter 134 in a particular engine operating condition. In one example, the monitoring system 100 may include a plurality of fluid sensors disposed on each side of the fluid filter 134 to collectively detect the indication. The at least one fluid sensor 126 may include, for example, an air filter pressure difference sensor, a fuel filter pressure difference sensor, an engine speed sensor, an engine oil pressure sensor, an engine oil temperature sensor, a fuel pressure sensor, a fuel temperature sensor, an ambient pressure sensor, an ambient temperature sensor, an exhaust temperature sensor, or a combination thereof. The at least one fluid sensor 126 may be configured to provide data corresponding to an operating state of the engine 104, and this data may be received from at least one of the processing circuitry 106 and the device control module (ECM) 120, each of which may be communicatively coupled to the at least one fluid sensor 126.In one example, the processing circuit 106 may determine a pressure difference over time between the first and second sides of the fluid filter 134 to estimate fluid flow through the fluid filter 134. Processing circuit 106 may include, for example, memory 128 coupled to processor 130. The memory 128 may store software that, when executed by the processor 130, may cause the processing circuit 106 to track operating information associated with the internal combustion engine 104, such as boost pressure, fluid flow, engine speed, normal engine combustion, engine temperature, engine vibration, or other metrics of interest. The processing circuit 106 may also determine a status of the engine 104, which may relate to, for example, the performance of the filter or wear of the fluid filter 134, based on the data captured by the one or more first fluid sensor(s) 126. The engine monitoring system 100 may also include a user interface 138 for displaying a warning indicative of a condition of the fluid filter 134, and the warning may be triggered by the processing circuit 106 based on a determined pressure difference, or slope thereof, of the fluid filter 134 exceeding a certain threshold difference. Although the algorithm is shown separately from memory, it should be understood that the algorithm may include computer-implemented instructions stored in memory 128, and / or the algorithm may include software, hardware, or a combination of software and hardware configured to perform certain operations.The data captured by the one or more first fluid sensors 126 may be used by the algorithm 136 to identify or predict flow restrictions of the fluid filter 134. In this case, the algorithm 136 can be used to predict a predicted replacement date of the fluid filter 134. The algorithm 136 may be executed by the processor 130 of the processing circuit 106. The algorithm 136 may include a variety of functions and operations, such as a smoothing operation 202, a normalization operation 204, a slope analysis 206, a prediction operation 208, and a trigger operation 210. In one example, a "steady state" of a filter may be quantified, e.g., based on a ~10 second sliding deviation of normalized engine load (between about 30% load and about 90% load) and engine speed (e.g., above about 1000 U / min), based on the following equations:The smoothing operation 202 may improve results associated with short-term outliers in the raw sensor data, thereby aiding in the derivation of more meaningful data regarding the state of a particular filter. The smoothing operation 202 may also shorten the rendering time for the raw sensor data prior to the slope analysis 206. In one example, the smoothing operation 202 may use a moving average of the calculated slope over time, e.g., a time weighted average, to weight particular recently collected data. The smoothing operation 202 may help limit the noise in the data when processed in downstream steps of the algorithm 136.In one example, comparing a time-based EWMA (where the moving average "look-back" window is a time interval, e.g., 24 hours) to a sample-based EWMA (e.g., a 24 sample "look-back" window) may improve the performance of the algorithm in cases where the data samples are not collected at regular intervals. The main difference between an EWMA and a moving average is that the EWMA may not include a "true" window size as in the case of the moving average. Herein, for example, the algorithm may include data that is outside the 24 hours in calculating the average when the EWMA "look-back" window is a certain amount of time (e.g., 24 hours). In this case, a predetermined window size can be used to decide which weighting factor in the weighted average formula should be used, so that the response resembles a simple moving average considering only the last 24 hours. This may help the algorithm avoid storing any number of samples that may have been taken in a particular 24-time period.The normalization operation 204 may receive the smoothed output of the raw sensor data and thereby normalize a range of values associated with the sensor data. In one example, the normalization operation 204 may determine a maximum peak value for the smoothed output, which may then be normalized to within a predetermined range (e.g., between an upper limit and a lower limit). The normalized values may then be output for use in the slope analysis 206.The slope analysis 206 may determine a rate of change of a series of consecutive or discretized values (e.g., a first normalized value and a second normalized value) associated with the filtered output of the raw sensor data. In an example, the slope analysis 206 may compare a series of consecutive or discretized values (e.g., a first normalized value and a second normalized value), e.g., within a user-defined "look-back" window associated with the normalized sensor data. The slope analysis 206 may compare the first normalized value (e.g., a differential pressure) to the second normalized value and determine whether the difference between the first normalized value and the second normalized value is within a given threshold. If so, the slope analysis 206 may determine a rate of change associated with the normalized sensor data as being substantially constant, flat, or non-increasing. In one example, the slope analysis 206 may include quantifying boundary measurements based on corresponding measured first and second engine charge pressures. In one example, a first engine boost pressure may be in a range between 0 kiloPascals (kPa) and 50 kPa and a second engine boost pressure may be greater than 100 kPa.For example, if P0=limit at <20 kPa boost pressure, P1=limit at >approximately 120 kiloPascals (kPa) boost pressure, X0= boost pressure measurement for P0, and X1= boost pressure measurement for P1, slope analysis 206 may be performed based on the following equation:In one example, a time rate of change (ROC) may be calculated based on the following equation, with a 12 hour EWMA serving as a historical value:In another example, the ROC may be calculated based on the following equation, with a 24-hour EWMA serving as a historical value and a 2-hour EWMA serving as a current value:Subsequently, the slope analysis 206 may output a trend indicator indicating the rate of change of the normalized sensor data as substantially constant. The trend indicator may indicate, for example, that the sensor data is indicative of a filter that is not yet ready for replacement.Alternatively, if the difference between the first normalized value and the second normalized value is determined to be outside the predetermined threshold, the slope analysis 206 may determine a rate of change associated with the normalized sensor data to be substantially non-constant. Next, the slope analysis 206 may output a trend indicator (e.g., a status signal) indicating, for example, that the sensor data is indicative of a filter ready for replacement.In an example, the prediction operation 208 may include a prediction algorithm capable of predicting or estimating a predicted rate of change of the normalized sensor data over a given period of time. The prediction operation 208 may receive the normalized sensor data and predict the rate of change of the normalized sensor data at a future time relative to a current time of the normalized sensor data, and then output a predicted change of the rate of change. The prognosis may include estimating a time to reach a threshold differential pressure based on the following equation:In one example, the threshold differential pressure may be calculated based on the following equation:In another example, the threshold differential pressure may be determined within a range of about 90 kPa to about 110 kPa, e.g., about 100 kPa.The trigger operation 210 may determine when to display a warning or activate other components of the monitoring system 100 based on a determination that the time to reach the threshold differential pressure is less than a predetermined time period, e.g., less than about 48 hours. If so, the triggering operation 210 may output data indicating an executable state for proposing replacement of the fluid filter 134. In one example, the triggering operation 210 may generate a warning to suggest replacement before activating an ECM diagnostic code indicating the proposed replacement of the fluid filter 134. In one example, the algorithm 136 may calculate filter exchange intervals in the range of three to four weeks to six months. In one example, e.g., to verify the accuracy or precision of the algorithm 136, the algorithm 136 may also receive ECM data from the ECM 120 of the work machine 102 and use the ECM data to assist in estimating the state of the filter 134, e.g., by using the ECM data as a secondary indicator of the state of the filter 134 or comparing the ECM data to the estimate from the trigger operation 210.FIG. 3 is a block diagram illustrating components of a machine 300 capable of reading instructions 324 from a machine storage medium 322 (e.g., a non-transitory machine storage medium, a machine storage medium, a computer storage medium, or any suitable combination thereof), and performing in whole or in part one or more of the methodologies discussed herein, in accordance with some embodiments. In particular, FIG. 3 illustrates the machine 300 in the example form of a computer system (e.g., a computer) within which the instructions 324 (e.g., software, a program, an application, an applet, an app, or other executable code) for causing the machine 300 to perform one or more of the methodologies discussed herein may be executed, in whole or in part. For example, the instructions 324 may be processor-executable instructions that, when executed by a processor of the machine 300 (e.g., included in the processing circuitry 106 of FIGS. 1 and 2 ), cause the machine 300 to perform the operations discussed above.In various embodiments, the machine 300 operates as a stand-alone device or may be communicatively coupled (e.g., networked) to other machines. In a networked deployment, the machine 300 may operate in the nature of a server machine or a client machine in a server-client network environment, or as a peer machine in a distributed (e.g., peer-to-peer) network environment. The machine 300 may be a server computer, a client computer, a personal computer (PC), a tablet computer, a laptop computer, a netbook, a mobile phone, a smartphone, a set-top box (STB), a personal digital assistant (PDA), a web appliance, a network router, a network switch, a network bridge, or any other machine capable of sequentially or otherwise executing the instructions 324 specifying the actions to be taken by that machine. Further, while only a single machine is illustrated, the term "machine" is to be understood to include any collection of machines that individually or jointly execute the instructions 324 to perform, in whole or in part, one or more of the methods discussed herein.The machine 300 includes a processor 302 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a radio frequency integrated circuit (RFIC), or any suitable combination thereof), a main memory 304, and a static memory 306 configured for communication with each other via a bus 308. Processor 302 may include microcircuits that are temporarily or permanently configurable by some or all of instructions 324, such that processor 302 is configurable to perform in whole or in part one or more of the methodologies described herein. For example, a set of one or more microcircuits of processor 302 may be configurable to execute one or more modules (e.g., software modules) described herein.The machine 300 may further include a graphics display 310 (e.g., a plasma display panel (PDP), a light emitting diode (LED) display panel, a liquid crystal display (LCD) display panel, a projector, a cathode ray tube (CRT), or any other display that may display graphics or video). The machine 300 may also include an alphanumeric input device 312 (e.g., a keyboard or keypad), a cursor control device 314 (e.g., a mouse, a touchpad, a trackball, a joystick, a motion sensor, an eye tracker, or other pointing instrument), a storage unit 316, an audio generation device 318 (e.g., a sound card, an amplifier, a speaker, a earphone jack, any combination thereof, or other suitable signal generation device), and a network interface device 320.The storage unit 316 includes the machine storage medium 322 (e.g., a tangible and non-transitory machine storage medium) having stored thereon instructions 324 embodying one or more of the methodologies or functions described herein. The instructions 324 may also reside, prior to or during execution thereof by the machine 300, wholly or at least partially within the main memory 304, within the processor 302 (e.g., within the cache of the processor), or both. Accordingly, main memory 304 and processor 302 may be considered machine storage media (e.g., tangible and non-transitory machine storage media). The instructions 324 may be transmitted or received over the network 326 via the network interface device 320. For example, the network interface device 320 may communicate the instructions 324 using one or more transmission protocols (e.g., Hypertext Transfer Protocol (HTTP)).In some example embodiments, machine 300 may be a portable computing device, such as a smartphone or a tablet computer, and may include one or more additional input components (e.g., sensors 328 or gauges). Examples of the additional input components include an image input component (e.g., one or more cameras), an audio input component (e.g., a microphone), a direction input component (e.g., a compass), a location input component (e.g., a global positioning system (GPS) receiver), an orientation component (e.g., a gyroscope), a motion detection component (e.g., one or more accelerometers), an altitude detection component (e.g., an altimeter), and a gas sensing component (e.g., a gas sensor). Inputs obtained from one or more of these input components may be accessible and usable by each of the modules described herein. The various memories (i.e., 304, 306 and / or the memory of the processor / processors 302) and / or the storage unit 316 may store one or more sets of instructions and data structures (e.g., software) 324 embodying or being utilized by one or more of the methodologies or functions described herein. These instructions, when executed by processor(s) 302, cause various operations to implement the disclosed embodiments.As used herein, the terms "machine storage medium", "device storage medium", "computer storage medium" (collectively referred to as "machine storage medium 322") mean the same and may be used interchangeably in this disclosure. The terms refer to single or multiple storage devices and / or media (e.g., a centralized or distributed database and / or associated caches and servers) that store executable instructions and / or data, as well as cloud-based storage systems or storage networks that include multiple storage devices or devices. The terms are accordingly intended to include, but are not limited to, solid state memories, as well as optical and magnetic media, including memory within or outside processors. Specific examples of machine storage media, computer storage media, and / or device storage media 322 include non-volatile memory such as semiconductor memory devices, e.g., erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), FPGA, and flash memory devices, magnetic hard disks such as internal hard disks and removable disks, magneto-optical hard disks, and CD-ROM and DVD-ROM disks. The terms machine storage medium or media, computer storage medium or media, and device storage medium or media 322 expressly exclude carrier waves, modulated data signals, and other such media, at least some of which fall under the term "signal medium" discussed below. In this context, the machine storage medium is non-volatile. The term "signal medium" or "transmission medium" is intended to include any form of modulated data signals, carrier waves, and so forth. The term "modulated data signal" refers to a signal in which one or more of its characteristics have been adjusted or altered to encode information in the signal. The terms "machine-readable medium", "computer-readable medium", and "device-readable medium" mean the same and may be used interchangeably in this disclosure. The terms are defined to include both machine storage media and signal media. The terms therefore include both storage devices / media and carrier wave / modulated data signals.Industrial applicabilityThis document describes a technique for predicting a predicted replacement date of fluid filters, e.g., fuel filters, air filters, or oil filters, included as part of an internal combustion engine of a work machine. In one approach to monitoring a condition of a fluid filter, an engine control module (ECM) of the internal combustion engine may be configured to selectively display an onboard diagnostic code relating to a fluid filter. In this case, the ECM can specify that a filter should be checked or replaced if a predicted future event of the onboard diagnostic code is reached. The predicted future event may include reaching a fixed number or age of usage of the filter, such as a number of engine operating hours, a number of engine starts, or a milestone, such as a number of kilometers traveled. Once the engine control module indicates that a fluid filter should be checked or replaced, the operator of the work machine will typically contact a service provider to agree on a service appointment. This service service can confirm the code displayed by the ECM and judge whether the fluid filter actually needs to be replaced at the time of maintenance. One challenge with this approach is that such diagnostic codes can issue false, inaccurate, or irrelevant warnings, which occur, for example, at such a frequency that an operator begins to ignore or delay the agreement of a maintenance deadline with a maintenance service provider. Such inaccuracies may arise because, in the case of pre-calculated future events, considerable variations in the operating conditions of the machine, for example in connection with the environment or the task of a specific work machine, are not taken into account.The inventors have recognized that an approach for dynamic, continuous assessment of a fluid filter over time, along with the corresponding operating conditions, is required to provide a more meaningful and more distinct indication to an operator or maintenance personnel of the work machine to maintain the machine.The techniques described herein may enable higher accuracy in estimating the state and useful life of the fluid filter, e.g., by using metric measurements of the engine and comparing the rate of change to a configurable threshold. For example, sensor data corresponding to a particular fluid filter may be received from an algorithm to generate a normalized value, which may then be used to predict an exchange date. In one example, the algorithm may include at least one engine metric to "filter out" irrelevant engine transients, e.g., with the metric including a combination of the engine speed and the engine variance over a period of, e.g., about 10 seconds. For operations related in particular to fuel filters, certain raw data may be received by the algorithm, such as for predicted prediction. For operations particularly associated with air filters, the algorithm may alternatively or additionally include one or more additional data processing steps to extract meaningful metrics prior to predicting and providing an alert. For example, the air filter analysis may include normalizing raw sensor data based on its dependence on the operation of the engine and estimating the state and useful life of the air filter based on the normalized raw sensor data. The present approach may allow for more selective and precise filter replacement, thereby avoiding excessive maintenance while avoiding engine issues due to filter plugging.In operation and use, the present described engine monitoring system may be used to monitor a fluid filter and predict a time to replacement of the fluid filter, such as to avoid a plugging event. Herein, a plugging event may refer to a situation where particulates, debris, mud, dirt, and other contaminants have accumulated in the fluid filter in a manner that limits the ability of the fluid filter to operate and / or allow sufficient fluid to pass through. This plugging event may increase the required fluid pressure therethrough or limit the maximum fluid pressure allowed therethrough. In both cases, it is possible that a fluid, although allowed to pass through the fluid filter, is not allowed to pass through the fluid filter in the required amount or at the desired pressure. Therefore, the potentially adverse effects of such a plugging event can be avoided by monitoring and replacing the fluid filter prior to the occurrence of such a plugging event.Generally, the monitoring system described herein may enable detection of a degraded state of the fluid filter prior to an ECM diagnostic code warning. The monitoring system described herein may provide reliable analysis of a condition of a fluid filter over a range of operating conditions (e.g., boost pressure from about 20 kPa to over 100 kPa) and despite a variety of operating conditions of a work machine. Such reliable analysis may provide better scheduling for the proposed fluid filter replacement compared to scheduled replacement based on mileage, operating hours, or filter age, where variations in engine operating state are not fundamentally taken into account. In one example, the monitoring system may be used to receive data from a plurality of work machines, e.g., each corresponding to one or more fluid filters. For example, the monitoring system may be located at a location remote from the plurality of work machines and coupled to the work machines via a communication interface (e.g., a transceiver via a network).FIG. 4 is a flow chart describing a method for detecting a fluid filter state of an internal combustion engine. For example, the method may include monitoring a pressure difference over time between the first and second sides of the fluid filter to estimate fluid flow through the fluid filter.In one example, at 410, such monitoring may include receiving a first indication of the respective fluid pressure values on the first and second sides of the fluid filter at a first engine operating condition. Similarly, at 420, the method may include receiving a second indication of the respective fluid pressure values on the first and second sides of the fluid filter at a second engine operating condition. For example, the first and second engine operating states include first and second engine boost pressures, respectively. The first engine boost pressure may be in a range of 0 kiloPascals (kPa) and 50 kPa, and the second engine boost pressure may be greater than 100 kPa. In one example, the received first and second indications of the respective fluid pressure values may each include receiving a plurality of corresponding fluid pressure measurements on the first and second sides of the fluid filters over time. For example, the plurality of respective fluid pressure measurements may comprise more than 100 measurements per hour.In one example, at 430, the method may include (e.g., when performing the smoothing operation 202 of FIG. 2 ) adjusting at least one parameter of the received first and second indications to the respective fluid pressure values to mitigate a difference attributable to a difference between the first and second engine operating states, such as a difference in engine boost pressure, mass fluid flow rate, mass fluid flow amount, or a combination thereof.In an example, the method may include (e.g., when performing the normalization operation 204 of FIG. 2 ) receiving the adjusted first and second indications of the respective fluid pressure values and normalizing a range of values associated with the first and second indications. For example, the method may determine at least one maximum peak for at least one parameter of the adjusted first and second indications, which may then be normalized to a predetermined range (e.g., between an upper limit and a lower limit).At 440, the method may include (e.g., when performing the slope detection 206 of FIG. 2 ) comparing the adjusted first respective indications of the fluid pressure values to the adjusted second respective indications of the fluid pressure values. For example, the method may include calculating a slope based on the adjusted first respective fluid pressure value indications with the adjusted second respective fluid pressure value indications. In one example, the method may include detecting a differential fluid pressure slope that exceeds a threshold. The method may also include estimating a time period (e.g., when performing the prediction operation 208 of FIG. 2 ) in which the fluid pressure difference will exceed a threshold.At 450, comparing (e.g., when performing the triggering operation 210 of FIG. 2 ) may include triggering a warning indicative of a state of the engine fluid filter based on the monitored pressure difference. Triggering the alert may include, for example, generating an indication to replace or clean the fluid filter based on the differential slope exceeding the threshold. Triggering the alert may also include generating an indication to replace or clean the fluid filter in anticipation of a plugging event of the fluid filter.FIGS. 5A and 5B are plots of measured air filter restriction versus boost pressure and time, respectively. For example, in one example, engine boost pressure of an internal combustion engine may be used as an approximate value for estimating airflow through an air filter. Here, a pressure difference across the air filter may be approximately proportional to a flow through the air filter. In general, the engine monitoring system described herein may track a slope over time and minimize certain effects of measuring air filter restriction at different boost pressures. For example, FIG. 5A shows different slopes corresponding to different time steps a, b, and c, respectively, as indicated in FIG. 5B. Statistically significant slopes may be calculated by acquiring data points over a range of boost values (e.g., a first "low" boost pressure between 0 and about 20 kPa and a second "high" boost pressure above about 120 kPa). As shown, such slopes may increase over time with aging of the filter.FIGS. 6A and 6B are diagrams of operations for predicting a predicted replacement date for fluid filters. At 602, a "steady state" of the fluid filter may be determined, e.g., by determining a sliding variation of an engine load or speed that is below a predetermined threshold. At 604, the boost pressure and constraint data or differential pressure data may be aggregated or filtered, e.g., including more than a threshold of samples to be taken within a certain time (e.g., >150 samples per hour). At 606, constraint measurements may be grouped, e.g., according to measured boost pressure values. At 608, the data may be smoothed, e.g., by taking an EWMA from certain data parameters. At 610, a slope may be calculated, e.g., the change in the limit via the change in boost pressure. At 612, a temporal ROC may be calculated, e.g., using the EWMA as a historical data point. At 614, a forecast for the time to reach a predetermined threshold for the ROC may be calculated. At 616, a warning may be triggered, e.g., when the time to reach a threshold is less than a predetermined time frame (e.g., <48 hours).FIG. 7 includes plots of certain data parameters versus time associated with plugging of a fluid filter. As shown in FIG. 7, the engine monitoring system may monitor at least two similar fluid filters simultaneously, e.g., a left and right air filter or a left and right fuel filter of an engine. In one example, dashed line 700 indicates when an ECM diagnostic code is triggered. Based on performing the operations described herein, the engine monitoring system may predict when the ECM diagnostic code is triggered and predict the code, e.g., more than 24 hours before the ECM code is displayed.The above detailed description is provided by way of illustration and not limitation. The scope of the disclosure should therefore be determined with reference to the appended claims, along with the full scope of equivalents to which the claims are entitled.
Claims
An internal combustion engine monitoring system (100), the system comprising: a fluid filter (134) disposed between at least one fluid inlet of an internal combustion engine (104) and at least one fluid source or surrounding fluid environment; a first fluid sensor (126) disposed to receive a first indication of the respective fluid pressure values on the first and second sides of the fluid filter (134) in a first engine operating condition; a second fluid sensor (126) disposed to receive a second indication of the respective fluid pressure values on the first and second sides of the fluid filter (134) in a second engine operating condition; a processing circuit (106) configured to determine a pressure difference over time between the first and second sides of the fluid filter (134) to estimate fluid flow through the fluid filter, the processing circuit (106) configured to: adjust at least one parameter of the received first and second indications of the respective fluid pressure values to mitigate a difference due to a difference between the first and second engine operating conditions; and compare the adjusted first respective indications of the fluid pressure values with the adjusted second respective indications of the fluid pressure values; and a user interface (138) to generate a warning indicative of a condition of the engine fluid filter (134) based on the monitored pressure difference, the warning being triggered by the processing circuit (106) based on the determined pressure difference exceeding a specified threshold difference.The system of claim 1, wherein the first and second engine operating conditions include first and second engine boost pressures, respectively, and optionally wherein the first engine boost pressure is in a range of 0 kiloPascals (kPa) and 50 kPa and the second engine boost pressure is greater than 100 kPa.The system of any of claims 1 or 2, wherein the processing circuitry (106) is configured to trigger a warning including generating an indication to replace or clean the fluid filter (134) based on a differential slope exceeding a specified threshold.The system of any of claims 1 to 3, wherein: the processing circuit (106) is configured to estimate a time period in which the fluid pressure difference will exceed a threshold; and the user interface (138) is configured to display a warning including an indication to replace or clean the fluid filter (134) in anticipation of a plugging event of the fluid filter (134).The system of any of claims 1 to 4, wherein the received first and second indications of the respective fluid pressure values each include a plurality of respective fluid pressure measurements on the first and second sides of the fluid filters over time, and optionally, wherein the plurality of respective fluid pressure measurements comprises more than (100) measurements per hour, and optionally, wherein the processing circuit (106) is configured to normalize the plurality of respective fluid pressure measurements including calculation of an exponentially weighted moving average (EWMA) of the plurality of respective fluid pressure measurements.A method of detecting a fluid filter condition of an internal combustion engine, the method comprising: monitoring (410) a pressure difference over time between the first and second sides of the fluid filter (134) to estimate fluid flow through the fluid filter (134) comprising: receiving a first indication of the respective fluid pressure values on the first and second sides of the fluid filter (134) at a first engine operating condition; receiving (420) a second indication of the respective fluid pressure values on the first and second sides of the fluid filter (134) at a second engine operating condition; adjusting (430) at least one parameter of the received first and second indications of the respective fluid pressure values to mitigate a difference due to a difference between the first and second engine operating conditions; comparing (440) the adjusted first respective fluid pressure value indications with the adjusted second respective fluid pressure value indications; and triggering (450) a warning indicative of a condition of the engine fluid filter (134) based on the monitored pressure difference.The method of claim 6, wherein the first and second engine operating conditions include first and second engine boost pressures, respectively, and optionally wherein the first engine boost pressure is in a range of 0 kiloPascals (kPa) and 50 kPa and the second engine boost pressure is greater than 100 kPa.The method of claim 6 or 7, further comprising: detecting a differential fluid pressure slope that exceeds a threshold; wherein triggering the alert includes generating an indication for replacing or cleaning the fluid filter (134) based on the differential slope that exceeds the threshold, and optionally further comprising: estimating a period of time that the differential fluid pressure will exceed a threshold; wherein triggering the alert includes generating an indication for replacing or cleaning the fluid filter (134) in anticipation of a plugging event of the fluid filter.The method of any of claims 6 to 8, wherein the received first and second indications of the respective fluid pressure values each include receiving a plurality of corresponding fluid pressure measurements on the first and second sides of the fluid filters (134) over time.The method of claim 9, wherein the plurality of respective fluid pressure measurements includes more than (100) measurements per hour, and optionally wherein adjusting the received first and second indications of the respective fluid pressure values on the first and second sides of the fluid filter (134) includes smoothing the plurality of respective fluid pressure measurements including calculating an exponentially weighted moving average (EWMA) of the plurality of respective fluid pressure measurements.