Injector failure mode identification

Abstract

Injector failure mode identification is provided. A process for identifying a failure mode of a fuel supply system includes operating a failure mode model derived from a big data set including field performance data received from a plurality of engine fuel supply systems including one or more injectors, the field performance data includes injection pressures and injection amounts for multiple injections performed by one or more injectors of the engine fuel supply system, and the failure mode model includes a plurality of predetermined rules for evaluating operation of the engine fuel supply system; receiving target field performance data for performance evaluation from a target fuel supply system including one or more target injectors configured to provide fuel to a target engine system; evaluating the target field target performance data using the failure mode model to identify a failure mode of the target fuel supply system; and performing a compensation action in response to the evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to injector failure mode recognition, and more particularly, but not exclusively, to big data based artificial intelligence models for injector failure mode recognition. BACKGROUND

[0002] Fuel injectors for internal combustion engine systems can experience many failures that can involve any of a number of fuel injector components. Numerous efforts have been made to provide diagnostics for fuel injector failures. Such efforts suffer from a number of shortcomings and deficiencies, including, among others, shortcomings and deficiencies with respect to accuracy, precision, reliability, feasibility, and speed of data processing. There remains a significant need for unique apparatuses, processes, and systems disclosed herein.

[0003] DISCLOSURE OF EXAMPLE EMBODIMENTS

[0004] For the purposes of clarity, conciseness, and exactness in describing the example embodiments of the present disclosure, ways and processes of making and using the example embodiments, and for the purposes of enabling enabling, making, and using the example embodiments, reference now will be made to certain example embodiments, including the example embodiments illustrated in the drawings, and specific language will be used to describe the example embodiments. It will, nevertheless, be understood that no limitation of the scope of the application is thereby intended, and that the application includes and protects such alterations, modifications, and further applications of the example embodiments as would occur to one skilled in the art. SUMMARY

[0005] Example embodiments include unique apparatuses, processes, and systems for injector failure mode recognition. Further embodiments, forms, objects, features, advantages, aspects, and benefits shall become apparent from the following description and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0006] Figure 1 is a schematic diagram illustrating certain aspects of an example system for injector failure mode recognition.

[0007] Figure 2 is a flow diagram illustrating certain aspects of an example process for injector failure mode recognition.

[0008] Figure 3 is a schematic diagram illustrating certain aspects of an example process for injector failure mode recognition.

[0009] Figure 4 is a schematic diagram illustrating certain aspects of an example process for injector failure mode recognition. DETAILED DESCRIPTION

[0010] REFERENCE Figure 1FIG. 1 illustrates an example system 100 configured and operable to evaluate and determine one or more failure modes of one or more fuel injectors. The system 100 includes a data set 110. In the illustrated example, the data set 110 includes a big data data set. As understood by those skilled in the art, big data refers to a data set that is so large, so fast, or so complex that it is difficult or impossible to process using traditional data processing techniques. The data set 110 can receive and store field performance data of a plurality of vehicles 102. In the illustrated example, the plurality of vehicles 102 includes any number of a plurality of vehicles 102a, 102b, 102n, which can vary and increase over time. The vehicles 102 can continuously or repeatedly output and provide field performance data (including fuel system field performance data) to the data set 110 via vehicle-to-X (V2X) infrastructure 104 and network infrastructure 108. The data set 110 can also receive repair data related to the plurality of vehicles 102 from one or more repair databases 106 via the network infrastructure 108. The data set 110 can also receive warranty data related to the plurality of vehicles 102 from one or more warranty databases 107 via the network infrastructure 108.

[0011] The system 100 further includes a failure mode model 120 constructed using the data set 110. The failure mode model 120 includes a plurality of rules for evaluating engine fuel supply system operation. The rules can be constructed using field performance data received from a plurality of engine fuel supply systems including one or more injectors. The field performance data can include injection pressure and injection quantity of a plurality of injections performed by one or more injectors of the engine fuel supply system.

[0012] The failure mode model 120 is configured and operable to receive target field performance data 115 from a target fuel supply system or a target engine identified or selected by the failure mode model 120 for evaluation, for example, by identification or selection initiated by a vehicle or other asset associated with the target engine or by identification or selection initiated by the failure mode model 120 or associated components of the system 100. The target fuel supply system includes one or more target injectors configured to provide fuel to the target engine system for performance evaluation. The failure mode model 120 is further configured and operable to determine and provide an injector failure mode output 130, which can include, for example, a diagnostic output, a prognostic output, or a combination thereof.

[0013] The injector fault mode output 130 can be provided to and utilized by one or more compensatory action processes 135, which can include one or more of, for example, modifying operation of the target engine system, providing an operator perceptible notification to an operator of the target engine system, and scheduling maintenance of the target engine system.

[0014] The injector fault mode output 130 can also be provided to and utilized by one or more repair and / or warranty processes 140, in which the target fuel injection system can be repaired, and repair information can be entered into one or more databases, such as repair database(s) 106, and / or warranty claims can be processed, and warranty information can be entered into one or more databases, such as repair database(s) 107. Offline optimization process(es) 150 can also utilize information from repair and / or warranty processes 140 to update fault mode model 120.

[0015] Referring now to Figure 2 FIG. 1 illustrates an example process 200 that can be utilized in conjunction with fault mode identification of one or more injectors of one or more target fuel supply systems. Process 200 begins with start operation 201 and proceeds to operation 202, where target field performance data is received. The received target field performance data can include injection pressures and injection quantities for a plurality of injections performed by one or more injectors of an engine fuel supply system.

[0016] Process 200 proceeds from operation 202 to condition 204, which evaluates whether an injector circuit fault code is true. The injector fault code can be a component of the received target field performance data or can be determined in response to the received target field performance data.

[0017] If condition 204 evaluates to affirmative, process 200 proceeds to operation 214, which identifies an injector circuit or injector harness condition. Process 200 proceeds from operation 214 to operation 290, which is described further below.

[0018] If condition 204 evaluates to negative, process 200 proceeds to condition 206, which evaluates whether a high pressure system leak value is greater than a threshold value. The high pressure system leak value can be a component of the received target field performance data or can be determined in response to the received target field performance data.

[0019] If condition 206 evaluates to positive, process 200 proceeds to condition 216, which evaluates whether the mechanical bleed valve pop-out count has been increased. The mechanical bleed valve pop-out count can be a component of the received target field performance data or can be determined in response to the received target field performance data.

[0020] If condition 216 evaluates to positive, process 200 proceeds to operation 226, which identifies a mechanical bleed valve pop-out condition. Process 200 proceeds from operation 226 to operation 290, which is further described below.

[0021] If condition 216 evaluates to negative, process 200 proceeds to operation 236, which identifies a mechanical bleed valve corrosion condition or an injector check ball rupture condition. Process 200 proceeds from operation 226 to operation 290, which is further described below.

[0022] If condition 206 evaluates to negative, process 200 proceeds to operation 208, which identifies an injector failure mode using the injector failure mode and the received target field performance data. Operation 208 can, for example, utilize techniques such as those described in connection with Figure 3 The operations and techniques of process 300 are illustrated and described. Process 200 proceeds from operation 208 to operation 290.

[0023] Operation 290 performs one or more compensatory actions. The one or more compensatory actions can include, for example, one or more of the following: modifying operation of the target engine system, providing an operator- perceptible notification to an operator of the target engine system, and scheduling a repair of the target engine system. Modifying operation of the target engine system can include reducing a rating of the target engine, such as by imposing a lower engine torque limit, a lower engine speed limit, and / or a lower engine power limit, deactivating one or more injectors of the target engine, or other modifications that will occur to those of skill in the art in light of the benefits and insights provided by the present disclosure. Process 200 proceeds from operation 290 to end operation 299, and can thereafter be repeated or reinvoked or reinitiated.

[0024] Reference is made to Figure 3FIG. 13 illustrates an example process 300 that can be utilized in conjunction with failure mode identification of one or more injectors of one or more target fuel supply systems. Process 300 includes a test point construction operation 310 that is configured and operable to define a plurality of test points applicable to fuel injector field performance data that includes information for a plurality of injection events, the information including respective injection quantities and injection pressures. In the illustrated example, operation 310 is configured to classify or categorize the fuel injector field performance data into injection quantity categories and injection pressure quantities.

[0025] In the illustrated example, the injection quantity categories include three categories, namely high injection quantity, medium injection quantity, and low injection quantity. The injection quantity categories can be defined by injection quantity ranges or by discrete injection quantities. Ranges of injection quantities can be selected and utilized to mitigate or reduce data processing burdens by excluding data outside of the injection quantity ranges, with the use of discrete injection quantities being the most exclusive possibility. Ranges of injection quantities can be selected and utilized based on empirical or statistical techniques to enhance or preserve failure mode signal strength while also reducing data volume. It should be appreciated that different numbers of injection quantities, category definitions, and / or category ranges can be defined and utilized in other embodiments.

[0026] In the illustrated example, the injection pressure categories include three categories, namely high injection pressure, medium injection pressure, and low injection pressure. Ranges of injection pressures can be selected and utilized to mitigate or reduce data processing burdens by excluding data outside of the injection pressure ranges, with the use of discrete injection pressures being the most exclusive possibility. Ranges of injection pressures can be selected and utilized based on empirical or statistical techniques to enhance or preserve failure mode signal strength while also reducing data volume. It should be appreciated that different numbers of injection pressures, category definitions, and / or category ranges can be defined and utilized in other embodiments.

[0027] Process 300 includes a rule construction operation 320 that is configured and operable to receive an output of the test point construction operator 310 and, in response thereto, define a plurality of failure mode identification rules for the fuel injector field performance data that includes information for a plurality of injection events, the information including respective injection quantities and injection pressures. In the illustrated example, operation 310 is configured to classify or categorize the fuel injector field performance data into injection quantity categories and injection pressure quantities.

[0028] In the illustrated example, the rule-building operator has constructed a set of five rules configured and operable to evaluate target field performance data relative to test points established by the test point construction operator 310. Each of the five rules includes a unique set of range assessments for each test point established by the test point construction operator 310. In the illustrated example, the assessment range includes three assessments: below minimum, within range, and above maximum. It should be understood that those skilled in the art will appreciate the benefits and insights of this disclosure and will realize that other range assessments may also be utilized. Furthermore, each set of range assessments corresponds to a specific failure mode. Therefore, once the rules of the rule-building operation 320 are established, the rules can be implemented in a failure mode model such as failure mode model 120 and used to identify injector failure modes in response to target field performance data.

[0029] refer to Figure 4 The illustration shows an example process 400, which can be used to process data from large data datasets (such as dataset 110), for example, as a filter for inputs received from such datasets, or as a data governance tool applied to such datasets after inputs are received therefrom. In process 400, raw field performance data 410 can be provided to a field performance data filter 420. Furthermore, the field performance data filter 420 is configured to determine filtered field performance data 490 and provide it as output.

[0030] The field performance data filter 420 includes a data exclusion operator 422 and a data aggregation operator 424. In the illustrated example, the data exclusion operator 422 is configured to determine each injector and each fuel supply point (Cd) according to equation (1). k The purification data:

[0031] (1)

[0032] In equation (1), i indicates the injector number, j indicates the individual day on which field performance data is available, k indicates the index, and fp k The fuel supply point at index k is indicated; the ~ symbol indicates the exclusion filter. Indicates the fuel supply point at index k (which is not a number), and The fuel supply point at index k is marked (which has a zero value). Therefore, equation (1) effectively filters out the ultimately useless data points, for example, because they have been corrupted, include erroneous indications or flags, are non-existent, or otherwise do not fit according to the rules of equation (1).

[0033] In the illustrated example, the data exclusion operator 422 of the field performance data filter 420 is configured to determine each injector and each fuel supply point (y) according to equation (2).j k ) of the aggregated daily purge data:

[0034] (2) y j k = mean(Cd k ) j

[0035] In equation (2), j denotes individual days for which field performance data is available, k denotes an index, avg denotes an average (such as an arithmetic mean or a weighted average), and Cd k denotes purge data for each injector and each fueling point. Thus, equation (2) effectively compresses the amount of data.

[0036] As shown by the detailed description, the present disclosure contemplates a variety of and numerous embodiments, including but not limited to the following example embodiments.

[0037] Example Embodiment No. 1 is a process for identifying a fueling system failure mode, the process comprising: operating a failure mode model derived from a big data dataset comprising field performance data received from a plurality of engine fueling systems comprising one or more injectors, the field performance data comprising injection pressures and injection quantities for a plurality of injections performed by the one or more injectors of the engine fueling systems, the failure mode model comprising a plurality of predetermined rules for evaluating operation of the engine fueling systems; receiving target field performance data from a target fueling system comprising one or more target injectors configured to provide fuel to a target engine system for performance evaluation; evaluating the target field target performance data using the failure mode model to identify a failure mode of the target fueling system; and performing a compensatory action in response to the evaluation.

[0038] Example Embodiment No. 2 includes the features of Example Embodiment No. 1, wherein the evaluation comprises evaluating the target field target performance data against the plurality of predetermined rules.

[0039] Example Embodiment No. 3 includes the features of Example Embodiment No. 2, wherein each of the plurality of predetermined rules comprises a plurality of test points, each of the plurality of test points comprising a different combination of injection pressure criteria and injection quantity criteria than other test points of the plurality of test points, and each of the plurality of predetermined rules specifies whether each test point must be above an upper limit, below a lower limit, or within the lower limit.

[0040] Example Embodiment No. 4 includes the features of Example Embodiment No. 2, comprising determining the failure mode of the target fueling system in response to the target field target performance being judged to satisfy one of the plurality of predetermined rules.

[0041] Example Embodiment No. 5 includes the features of Example Embodiment No. 1, including performing one or more preliminary fault checks separately from evaluating the target field target performance data using the fault mode model.

[0042] Example Embodiment No. 6 includes the features of Example Embodiment No. 5, wherein the one or more preliminary fault checks include evaluating whether an injector circuit fault code condition is true and identifying an injector circuit condition in response to the evaluation.

[0043] Example Embodiment No. 7 includes the features of Example Embodiment No. 5, wherein the one or more preliminary fault checks include evaluating whether a pressure exceeds a leak threshold and whether a mechanical bleed valve pop count exceeds a threshold; and identifying one of a mechanical bleed valve pop condition, a mechanical bleed valve corrosion condition, and an injector check ball rupture condition in response to the evaluation.

[0044] Example Embodiment No. 8 includes the features of Example Embodiment No. 1, wherein evaluating the field target performance data using the fault mode model includes diagnosing a current state of the target engine system.

[0045] Example Embodiment No. 9 includes the features of Example Embodiment No. 1, wherein evaluating the field target performance data using the fault mode model includes predicting a future state of the target engine system.

[0046] Example Embodiment No. 10 includes the features of Example Embodiment No. 1, wherein the compensatory action includes one or more of modifying operation of the target engine system, providing an operator of the target engine system with an operator perceptible notification, and scheduling a repair of the target engine system.

[0047] Example Embodiment No. 11 is a system for identifying a fault mode of a fuel injector, the system comprising: a computer system including one or more processors and one or more non-transitory memory devices configured with instructions executable by the one or more processors to: operate a fault mode model from a big data dataset, the big data dataset including field performance data received from a plurality of engine fuel supply systems including one or more injectors, the field performance data including injection pressures and injection quantities of a plurality of injections performed by the one or more injectors of the engine fuel supply systems, the fault mode model including a plurality of rules for evaluating operation of the engine fuel supply systems; receive target field performance data from a target fuel supply system including one or more target injectors configured to provide fuel to a target engine system for performance evaluation; evaluate the target field target performance data using the fault mode model to identify a fault mode of the target fuel supply system; and perform a compensatory action in response to the evaluation.

[0048] Example Embodiment No. 12 includes the features of Example Embodiment No. 11, wherein the instructions are executable by the one or more processors to evaluate target field target performance data against the plurality of predetermined rules.

[0049] Example Embodiment No. 13 includes the features of Example Embodiment No. 12, wherein each of the plurality of predetermined rules includes a plurality of test points, each of the plurality of test points including a different combination of injection pressure criteria and injection quantity criteria than other test points in the plurality of test points, and each of the plurality of predetermined rules specifies whether each test point must be above an upper limit, below a lower limit, or within the lower limit.

[0050] Example Embodiment No. 14 includes the features of Example Embodiment No. 12, wherein the instructions are executable by the one or more processors to determine a fault mode of the target fuel supply system in response to the target field target performance being judged to satisfy one of the plurality of predetermined rules.

[0051] Example Embodiment No. 15 includes the features of Example Embodiment No. 11, wherein the instructions are executable by the one or more processors to perform one or more preliminary fault checks separately from evaluating the target field target performance data using the fault mode model.

[0052] Example Embodiment No. 16 includes the features of Example Embodiment No. 15, wherein the one or more preliminary fault checks include evaluating whether an injector circuit fault code condition is true and identifying an injector circuit condition in response to the evaluation.

[0053] Example Embodiment No. 17 includes the features of Example Embodiment No. 15, wherein the one or more preliminary fault checks include evaluating whether a pressure exceeds a leak threshold and whether a mechanical bleed valve pop count exceeds a threshold; and identifying one of a mechanical bleed valve pop condition, a mechanical bleed valve corrosion condition, and an injector check ball rupture condition in response to the evaluation.

[0054] Example Embodiment No. 18 includes the features of Example Embodiment No. 11, wherein the instructions are executable by the one or more processors to evaluate the field target performance data using the fault mode model to diagnose a current state of the target engine system.

[0055] Example Embodiment No. 19 includes the features of Example Embodiment No. 11, wherein the instructions are executable by the one or more processors to evaluate the field target performance data using the fault mode model to predict a future state of the target engine system.

[0056] Example Embodiment No. 20 includes the features of Example Embodiment No. 11, wherein the compensating action includes one or more of modifying operation of the target engine system, providing an operator-perceptible notification to an operator of the target engine system, and scheduling a repair of the target engine system.

[0057] While example embodiments of the disclosure have been illustrated and described in detail in the drawings and foregoing description, the same is to be considered as illustrative and not restrictive in nature, and it will be appreciated that only certain example embodiments have been shown and described and that all changes and modifications that come within the spirit of the claimed application are desired to be protected. It should be understood that although the use of words such as preferable, preferably, preferred or more preferred utilized in the above description are intended to be indicative of a more preferred embodiment or aspect to one disclosed herein, this is not intended to be limiting. It is intended that the features of the above-described embodiments can be used in any combination with one another, and that the disclosure should be construed to encompass all changes and modifications that come within the scope of the claims that are set out below. In reading the claims, it is intended that when words such as "a," "an," "at least one," or "one or more" are utilized as adjectives preceding elements or embodiments within the claims or the specification, that such adjectives should be construed to be limiting only to the immediately following item unless the last use of such an adjective modifies one of the several items for which the adjective has charge. When the language "at least a portion" and / or "a portion" is used, the item can include a portion and / or the entire item, unless specifically stated to the contrary.

Claims

1. A process for identifying failure modes of a fuel supply system, the process comprising: The operation is based on a failure mode model derived from a large data dataset, which includes field performance data received from multiple engine fuel supply systems including one or more injectors. The field performance data includes injection pressure and injection quantity of multiple injections performed by one or more injectors of the engine fuel supply system. The failure mode model includes multiple predetermined rules for evaluating the operation of the engine fuel supply system. Receive target field performance data from a target fuel supply system, which includes one or more target injectors configured to supply fuel to a target engine system, for performance evaluation. The failure mode model is used to evaluate the target performance data at the target site in order to identify the failure modes of the target fuel supply system. as well as In response to the assessment, a compensation action is performed.

2. The process of claim 1, wherein the evaluation includes evaluating the target field performance data relative to the plurality of predetermined rules.

3. The process of claim 2, wherein each of the plurality of predetermined rules comprises a plurality of test points, each of the plurality of test points comprises a combination of injection pressure standards and injection volume standards that are different from those of the other test points in the plurality of test points, and each of the plurality of predetermined rules specifies whether each test point must be above an upper limit, below a lower limit, or within a lower limit.

4. The process of claim 2, comprising determining a failure mode of the target fuel supply system in response to the target site performance being determined to satisfy one of the plurality of predetermined rules.

5. The process of claim 1, comprising performing one or more preliminary fault checks separately from evaluating the target field performance data using the fault mode model.

6. The process of claim 5, wherein the one or more preliminary fault checks include assessing whether an injector circuit fault code condition is true, and identifying the injector circuit condition in response to the assessment.

7. The process of claim 5, wherein the one or more preliminary fault checks include assessing whether the pressure exceeds a leakage threshold and whether the mechanical relief valve pop-out count exceeds a threshold; and in response to the assessment, identifying one of the following: mechanical relief valve pop-out condition, mechanical relief valve corrosion condition, and injector check ball rupture condition.

8. The process of claim 1, wherein evaluating the field target performance data using the failure mode model includes diagnosing the current state of the target engine system.

9. The process of claim 1, wherein evaluating the field target performance data using the failure mode model includes predicting the future state of the target engine system.

10. The process of claim 1, wherein the compensation action includes one or more of the following: modifying the operation of the target engine system, providing the operator of the target engine system with operator-perceptible notification, and arranging maintenance for the target engine system.

11. A system for identifying a failure mode of a fuel injector, the system comprising: A computer system comprising one or more processors and one or more non-transitory memory devices, the one or more non-transitory memory devices being configured with instructions executable by the one or more processors to: The failure mode model operates based on a big data dataset, which includes field performance data received from multiple engine fuel supply systems including one or more injectors. The field performance data includes injection pressure and injection quantity for multiple injections performed by one or more injectors of the engine fuel supply system. The failure mode model includes multiple rules for evaluating the operation of the engine fuel supply system. Receive target field performance data from a target fuel supply system, which includes one or more target injectors configured to supply fuel to a target engine system, for performance evaluation. The failure mode model is used to evaluate the target performance data at the target site in order to identify the failure modes of the target fuel supply system. as well as In response to the assessment, a compensation action is performed.

12. The system of claim 11, wherein the instructions are executable by the one or more processors to evaluate the target field performance data relative to the plurality of predetermined rules.

13. The system of claim 12, wherein each of the plurality of predetermined rules comprises a plurality of test points, each of the plurality of test points comprises a combination of injection pressure standards and injection volume standards that are different from those of the other test points in the plurality of test points, and each of the plurality of predetermined rules specifies whether each test point must be above an upper limit, below a lower limit, or within a lower limit.

14. The system of claim 12, wherein the instructions are executable by the one or more processors to determine the failure mode of the target fuel supply system in response to the target field performance being determined to satisfy one of the plurality of predetermined rules.

15. The system of claim 11, wherein the instructions are executable by the one or more processors to perform one or more preliminary fault checks separately from the evaluation of the target field performance data using the fault mode model.

16. The system of claim 15, wherein the one or more preliminary fault checks include assessing whether an injector circuit fault code condition is true, and identifying the injector circuit condition in response to the assessment.

17. The system of claim 15, wherein the one or more preliminary fault checks include assessing whether the pressure exceeds a leakage threshold and whether the mechanical relief valve pop-out count exceeds a threshold; and in response to the assessment, identifying one of the following: mechanical relief valve pop-out condition, mechanical relief valve corrosion condition, and injector check ball rupture condition.

18. The system of claim 11, wherein the instructions are executable by the one or more processors to evaluate the field target performance data using the fault mode model, thereby diagnosing the current state of the target engine system.

19. The system of claim 11, wherein the instructions are executable by the one or more processors to evaluate the field target performance data using the failure mode model to predict the future state of the target engine system.

20. The system of claim 11, wherein the compensation action includes one or more of the following: modifying the operation of the target engine system, providing an operator-perceptible notification to the operator of the target engine system, and arranging maintenance for the target engine system.

Images